Seeding... 3
dir: dir isL
Python-Soar Flip environment.
To accept commands from an external sml process, you'll need to
type 'slave <log file> <n decisons>' at the prompt...
sourcing 'flip_predict.soar'
***********
Total: 11 productions sourced.

seeding Soar with 3 ...

soar> Entering slave mode:
  - log file 'rl-slave-2.5K_3.log'....
  - will exit slave mode after 2500 decisions
  waiting for commands from an externally connected sml process...
-/|sleeping...
\sleeping...
-sleeping...
/sleeping...
|sleeping...
\-/|\-/|\-sleeping...
/|\-/|\sleeping...
-1:    O: O2 (predict-no)
I see 0 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction L in state State-A
In  State-A moving L
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isR
rule alias: '*'

rule alias: '*'

/|\-/|\2:    O: O3 (predict-yes)
I see 1 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction R in state State-A
In  State-A moving R
ENV: (next state, see, prediction correct?) = (State-B, 1, True)
predict error 0
dir: dir isR
-/|3:    O: O6 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction R in state State-B
In  State-B moving R
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isR
\-/4:    O: O7 (predict-yes)
I see 1 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction R in state State-B
In  State-B moving R
ENV: (next state, see, prediction correct?) = (State-B, 0, False)
predict error 1
dir: dir isR
|\5:    O: O9 (predict-yes)
I see 0 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction R in state State-B
In  State-B moving R
ENV: (next state, see, prediction correct?) = (State-B, 0, False)
predict error 1
dir: dir isL
-/|6:    O: O12 (predict-no)
I see 0 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction L in state State-B
In  State-B moving L
ENV: (next state, see, prediction correct?) = (State-A, 1, False)
predict error 1
dir: dir isL
\-/|7:    O: O14 (predict-no)
I see 0 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction L in state State-A
In  State-A moving L
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isU
\-8:    O: O15 (predict-yes)
I see 1 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction U in state State-A
In  State-A moving U
ENV: (next state, see, prediction correct?) = (State-A, 0, False)
predict error 1
dir: dir isL
/|9:    O: O18 (predict-no)
I see 0 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction L in state State-A
In  State-A moving L
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isL
\-/10:    O: O19 (predict-yes)
I see 1 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction L in state State-A
In  State-A moving L
ENV: (next state, see, prediction correct?) = (State-A, 0, False)
predict error 1
dir: dir isU
|11:    O: O22 (predict-no)
I see 0 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-A
In  State-A moving U
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isR
rule alias: '*'

rule alias: '*'

rule alias: '*'

rule alias: '*'

\12:    O: O24 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction R in state State-A
In  State-A moving R
ENV: (next state, see, prediction correct?) = (State-B, 1, False)
predict error 1
dir: dir isU
-/|13:    O: O25 (predict-yes)
I see 0 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction U in state State-B
In  State-B moving U
ENV: (next state, see, prediction correct?) = (State-B, 0, False)
predict error 1
dir: dir isR
\14:    O: O28 (predict-no)
I see 0 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction R in state State-B
In  State-B moving R
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isR
-/15:    O: O30 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction R in state State-B
In  State-B moving R
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isL
|\-16:    O: O32 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction L in state State-B
In  State-B moving L
ENV: (next state, see, prediction correct?) = (State-A, 1, False)
predict error 1
dir: dir isR
/|17:    O: O33 (predict-yes)
I see 0 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction R in state State-A
In  State-A moving R
ENV: (next state, see, prediction correct?) = (State-B, 1, True)
predict error 0
dir: dir isU
\-/18:    O: O36 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-B
In  State-B moving U
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isR
|\-19:    O: O38 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction R in state State-B
In  State-B moving R
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isU
/|\20:    O: O40 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-B
In  State-B moving U
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isU
-/21:    O: O42 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-B
In  State-B moving U
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isL
|22:    O: O44 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction L in state State-B
In  State-B moving L
ENV: (next state, see, prediction correct?) = (State-A, 1, False)
predict error 1
dir: dir isU
\-23:    O: O45 (predict-yes)
I see 0 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction U in state State-A
In  State-A moving U
ENV: (next state, see, prediction correct?) = (State-A, 0, False)
predict error 1
dir: dir isR
/|\-24:    O: O48 (predict-no)
I see 0 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction R in state State-A
In  State-A moving R
ENV: (next state, see, prediction correct?) = (State-B, 1, False)
predict error 1
dir: dir isL
/|\25:    O: O50 (predict-no)
I see 0 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction L in state State-B
In  State-B moving L
ENV: (next state, see, prediction correct?) = (State-A, 1, False)
predict error 1
dir: dir isL
-/|26:    O: O52 (predict-no)
I see 0 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction L in state State-A
In  State-A moving L
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isU
\-/27:    O: O54 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-A
In  State-A moving U
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isR
|\28:    O: O56 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction R in state State-A
In  State-A moving R
ENV: (next state, see, prediction correct?) = (State-B, 1, False)
predict error 1
dir: dir isU
-/|29:    O: O58 (predict-no)
I see 0 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-B
In  State-B moving U
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isU
\-30:    O: O60 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-B
In  State-B moving U
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isU
/31:    O: O62 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-B
In  State-B moving U
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isU
|32:    O: O64 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-B
In  State-B moving U
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isR
\-/33:    O: O66 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction R in state State-B
In  State-B moving R
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isU
|\-34:    O: O68 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-B
In  State-B moving U
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isR
/|\35:    O: O70 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction R in state State-B
In  State-B moving R
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isU
-/|36:    O: O72 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-B
In  State-B moving U
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isU
\37:    O: O74 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-B
In  State-B moving U
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isL
-/38:    O: O76 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction L in state State-B
In  State-B moving L
ENV: (next state, see, prediction correct?) = (State-A, 1, False)
predict error 1
dir: dir isL
|\-39:    O: O78 (predict-no)
I see 0 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction L in state State-A
In  State-A moving L
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isL
/|40:    O: O80 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction L in state State-A
In  State-A moving L
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isU
\-41:    O: O82 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-A
In  State-A moving U
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isR
/42:    O: O84 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction R in state State-A
In  State-A moving R
ENV: (next state, see, prediction correct?) = (State-B, 1, False)
predict error 1
dir: dir isR
|\-43:    O: O86 (predict-no)
I see 0 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction R in state State-B
In  State-B moving R
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isL
/|\44:    O: O88 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction L in state State-B
In  State-B moving L
ENV: (next state, see, prediction correct?) = (State-A, 1, False)
predict error 1
dir: dir isR
-/45:    O: O90 (predict-no)
I see 0 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction R in state State-A
In  State-A moving R
ENV: (next state, see, prediction correct?) = (State-B, 1, False)
predict error 1
dir: dir isR
|\-46:    O: O92 (predict-no)
I see 0 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction R in state State-B
In  State-B moving R
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isR
/|\47:    O: O94 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction R in state State-B
In  State-B moving R
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isR
-/48:    O: O96 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction R in state State-B
In  State-B moving R
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isR
|\-49:    O: O98 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction R in state State-B
In  State-B moving R
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isU
/50:    O: O100 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-B
In  State-B moving U
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isU
|\-/|\sleeping...
-51:    O: O102 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-B
In  State-B moving U
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isU
/52:    O: O104 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-B
In  State-B moving U
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isU
|\53:    O: O106 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-B
In  State-B moving U
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isU
-/54:    O: O108 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-B
In  State-B moving U
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isU
|\55:    O: O110 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-B
In  State-B moving U
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isL
-/|56:    O: O112 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction L in state State-B
In  State-B moving L
ENV: (next state, see, prediction correct?) = (State-A, 1, False)
predict error 1
dir: dir isU
\-57:    O: O114 (predict-no)
I see 0 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-A
In  State-A moving U
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isU
/|\58:    O: O116 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-A
In  State-A moving U
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isU
-/59:    O: O118 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-A
In  State-A moving U
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isR
|\60:    O: O119 (predict-yes)
I see 1 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction R in state State-A
In  State-A moving R
ENV: (next state, see, prediction correct?) = (State-B, 1, True)
predict error 0
dir: dir isU
-/61:    O: O122 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-B
In  State-B moving U
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isL
rule alias: '*'

rule alias: '*'

rule alias: '*'

|62:    O: O124 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction L in state State-B
In  State-B moving L
ENV: (next state, see, prediction correct?) = (State-A, 1, False)
predict error 1
dir: dir isU
\-63:    O: O126 (predict-no)
I see 0 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-A
In  State-A moving U
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isR
/|\64:    O: O128 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction R in state State-A
In  State-A moving R
ENV: (next state, see, prediction correct?) = (State-B, 1, False)
predict error 1
dir: dir isL
-/|65:    O: O130 (predict-no)
I see 0 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction L in state State-B
In  State-B moving L
ENV: (next state, see, prediction correct?) = (State-A, 1, False)
predict error 1
dir: dir isL
\-/66:    O: O132 (predict-no)
I see 0 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction L in state State-A
In  State-A moving L
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isU
|\-67:    O: O134 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-A
In  State-A moving U
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isU
/|\68:    O: O136 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-A
In  State-A moving U
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isL
-69:    O: O138 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction L in state State-A
In  State-A moving L
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isU
/|\70:    O: O140 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-A
In  State-A moving U
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isR
-/71:    O: O142 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction R in state State-A
In  State-A moving R
ENV: (next state, see, prediction correct?) = (State-B, 1, False)
predict error 1
dir: dir isL
rule alias: '*'

rule alias: '*'

rule alias: '*'

rule alias: '*'

rule alias: '*'

|72:    O: O144 (predict-no)
I see 0 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction L in state State-B
In  State-B moving L
ENV: (next state, see, prediction correct?) = (State-A, 1, False)
predict error 1
dir: dir isL
\-/|73:    O: O146 (predict-no)
I see 0 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction L in state State-A
In  State-A moving L
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isU
\-/74:    O: O148 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-A
In  State-A moving U
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isU
|\75:    O: O150 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-A
In  State-A moving U
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isL
-/76:    O: O152 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction L in state State-A
In  State-A moving L
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isR
|\-77:    O: O154 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction R in state State-A
In  State-A moving R
ENV: (next state, see, prediction correct?) = (State-B, 1, False)
predict error 1
dir: dir isL
/|\78:    O: O156 (predict-no)
I see 0 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction L in state State-B
In  State-B moving L
ENV: (next state, see, prediction correct?) = (State-A, 1, False)
predict error 1
dir: dir isU
-/|79:    O: O158 (predict-no)
I see 0 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-A
In  State-A moving U
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isL
\-/80:    O: O159 (predict-yes)
I see 1 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction L in state State-A
In  State-A moving L
ENV: (next state, see, prediction correct?) = (State-A, 0, False)
predict error 1
dir: dir isU
|\-81:    O: O162 (predict-no)
I see 0 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-A
In  State-A moving U
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isU
/82:    O: O163 (predict-yes)
I see 1 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction U in state State-A
In  State-A moving U
ENV: (next state, see, prediction correct?) = (State-A, 0, False)
predict error 1
dir: dir isR
|\-83:    O: O165 (predict-yes)
I see 0 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction R in state State-A
In  State-A moving R
ENV: (next state, see, prediction correct?) = (State-B, 1, True)
predict error 0
dir: dir isU
/|\84:    O: O168 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-B
In  State-B moving U
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isL
-/85:    O: O170 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction L in state State-B
In  State-B moving L
ENV: (next state, see, prediction correct?) = (State-A, 1, False)
predict error 1
dir: dir isL
|\-86:    O: O172 (predict-no)
I see 0 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction L in state State-A
In  State-A moving L
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isR
/|\87:    O: O173 (predict-yes)
I see 1 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction R in state State-A
In  State-A moving R
ENV: (next state, see, prediction correct?) = (State-B, 1, True)
predict error 0
dir: dir isL
-/|88:    O: O176 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction L in state State-B
In  State-B moving L
ENV: (next state, see, prediction correct?) = (State-A, 1, False)
predict error 1
dir: dir isL
\-/89:    O: O178 (predict-no)
I see 0 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction L in state State-A
In  State-A moving L
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isR
|\-90:    O: O179 (predict-yes)
I see 1 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction R in state State-A
In  State-A moving R
ENV: (next state, see, prediction correct?) = (State-B, 1, True)
predict error 0
dir: dir isR
/|91:    O: O182 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction R in state State-B
In  State-B moving R
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isL
rule alias: '*'

rule alias: '*'

\92:    O: O184 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction L in state State-B
In  State-B moving L
ENV: (next state, see, prediction correct?) = (State-A, 1, False)
predict error 1
dir: dir isL
-/|93:    O: O186 (predict-no)
I see 0 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction L in state State-A
In  State-A moving L
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isU
\-94:    O: O188 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-A
In  State-A moving U
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isL
/|95:    O: O190 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction L in state State-A
In  State-A moving L
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isU
\-96:    O: O192 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-A
In  State-A moving U
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isU
/|97:    O: O194 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-A
In  State-A moving U
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isR
\-98:    O: O195 (predict-yes)
I see 1 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction R in state State-A
In  State-A moving R
ENV: (next state, see, prediction correct?) = (State-B, 1, True)
predict error 0
dir: dir isR
/|\99:    O: O198 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction R in state State-B
In  State-B moving R
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isR
-/100:    O: O200 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction R in state State-B
In  State-B moving R
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isR
|\101:    O: O202 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction R in state State-B
In  State-B moving R
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isR
rule alias: '*'

rule alias: '*'

-/102:    O: O204 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction R in state State-B
In  State-B moving R
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isR
|\-103:    O: O206 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction R in state State-B
In  State-B moving R
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isR
/|\104:    O: O208 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction R in state State-B
In  State-B moving R
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isU
-/105:    O: O210 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-B
In  State-B moving U
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isR
|\106:    O: O212 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction R in state State-B
In  State-B moving R
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isR
-/107:    O: O214 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction R in state State-B
In  State-B moving R
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isU
|\108:    O: O216 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-B
In  State-B moving U
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isL
-/|109:    O: O217 (predict-yes)
I see 1 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction L in state State-B
In  State-B moving L
ENV: (next state, see, prediction correct?) = (State-A, 1, True)
predict error 0
dir: dir isL
\-/110:    O: O220 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction L in state State-A
In  State-A moving L
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isU
|\-111:    O: O222 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-A
In  State-A moving U
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isR
/112:    O: O223 (predict-yes)
I see 1 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction R in state State-A
In  State-A moving R
ENV: (next state, see, prediction correct?) = (State-B, 1, True)
predict error 0
dir: dir isR
|\-113:    O: O226 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction R in state State-B
In  State-B moving R
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isL
/|\114:    O: O227 (predict-yes)
I see 1 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction L in state State-B
In  State-B moving L
ENV: (next state, see, prediction correct?) = (State-A, 1, True)
predict error 0
dir: dir isR
-/|115:    O: O230 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction R in state State-A
In  State-A moving R
ENV: (next state, see, prediction correct?) = (State-B, 1, False)
predict error 1
dir: dir isR
\-/116:    O: O232 (predict-no)
I see 0 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction R in state State-B
In  State-B moving R
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isL
|\117:    O: O233 (predict-yes)
I see 1 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction L in state State-B
In  State-B moving L
ENV: (next state, see, prediction correct?) = (State-A, 1, True)
predict error 0
dir: dir isR
-/|118:    O: O235 (predict-yes)
I see 1 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction R in state State-A
In  State-A moving R
ENV: (next state, see, prediction correct?) = (State-B, 1, True)
predict error 0
dir: dir isR
\-119:    O: O238 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction R in state State-B
In  State-B moving R
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isL
/|\-120:    O: O239 (predict-yes)
I see 1 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction L in state State-B
In  State-B moving L
ENV: (next state, see, prediction correct?) = (State-A, 1, True)
predict error 0
dir: dir isR
/|121:    O: O241 (predict-yes)
I see 1 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction R in state State-A
In  State-A moving R
ENV: (next state, see, prediction correct?) = (State-B, 1, True)
predict error 0
dir: dir isR
rule alias: '*'

\122:    O: O244 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction R in state State-B
In  State-B moving R
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isU
-/|123:    O: O246 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-B
In  State-B moving U
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isR
\-124:    O: O248 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction R in state State-B
In  State-B moving R
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isU
/|\125:    O: O250 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-B
In  State-B moving U
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isU
-/126:    O: O252 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-B
In  State-B moving U
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isL
|\-127:    O: O253 (predict-yes)
I see 1 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction L in state State-B
In  State-B moving L
ENV: (next state, see, prediction correct?) = (State-A, 1, True)
predict error 0
dir: dir isL
/|128:    O: O256 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction L in state State-A
In  State-A moving L
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isU
\-129:    O: O257 (predict-yes)
I see 1 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction U in state State-A
In  State-A moving U
ENV: (next state, see, prediction correct?) = (State-A, 0, False)
predict error 1
dir: dir isU
/|130:    O: O259 (predict-yes)
I see 0 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction U in state State-A
In  State-A moving U
ENV: (next state, see, prediction correct?) = (State-A, 0, False)
predict error 1
dir: dir isL
\-131:    O: O262 (predict-no)
I see 0 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction L in state State-A
In  State-A moving L
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isR
rule alias: '*'

rule alias: '*'

/132:    O: O263 (predict-yes)
I see 1 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction R in state State-A
In  State-A moving R
ENV: (next state, see, prediction correct?) = (State-B, 1, True)
predict error 0
dir: dir isR
|\-133:    O: O266 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction R in state State-B
In  State-B moving R
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isL
/|\-sleeping...
/134:    O: O267 (predict-yes)
I see 1 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction L in state State-B
In  State-B moving L
ENV: (next state, see, prediction correct?) = (State-A, 1, True)
predict error 0
dir: dir isR
|\-135:    O: O269 (predict-yes)
I see 1 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction R in state State-A
In  State-A moving R
ENV: (next state, see, prediction correct?) = (State-B, 1, True)
predict error 0
dir: dir isL
/|\136:    O: O271 (predict-yes)
I see 1 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction L in state State-B
In  State-B moving L
ENV: (next state, see, prediction correct?) = (State-A, 1, True)
predict error 0
dir: dir isR
-/137:    O: O273 (predict-yes)
I see 1 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction R in state State-A
In  State-A moving R
ENV: (next state, see, prediction correct?) = (State-B, 1, True)
predict error 0
dir: dir isR
|\138:    O: O276 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction R in state State-B
In  State-B moving R
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isL
-/|139:    O: O277 (predict-yes)
I see 1 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction L in state State-B
In  State-B moving L
ENV: (next state, see, prediction correct?) = (State-A, 1, True)
predict error 0
dir: dir isR
\-/140:    O: O279 (predict-yes)
I see 1 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction R in state State-A
In  State-A moving R
ENV: (next state, see, prediction correct?) = (State-B, 1, True)
predict error 0
dir: dir isU
|\141:    O: O282 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-B
In  State-B moving U
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isL
rule alias: '*'

-142:    O: O283 (predict-yes)
I see 1 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction L in state State-B
In  State-B moving L
ENV: (next state, see, prediction correct?) = (State-A, 1, True)
predict error 0
dir: dir isR
/|\143:    O: O285 (predict-yes)
I see 1 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction R in state State-A
In  State-A moving R
ENV: (next state, see, prediction correct?) = (State-B, 1, True)
predict error 0
dir: dir isU
-/144:    O: O288 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-B
In  State-B moving U
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isL
|\-145:    O: O289 (predict-yes)
I see 1 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction L in state State-B
In  State-B moving L
ENV: (next state, see, prediction correct?) = (State-A, 1, True)
predict error 0
dir: dir isL
/146:    O: O292 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction L in state State-A
In  State-A moving L
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isU
|147:    O: O294 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-A
In  State-A moving U
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isL
\-/148:    O: O296 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction L in state State-A
In  State-A moving L
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isL
|\149:    O: O298 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction L in state State-A
In  State-A moving L
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isR
-/150:    O: O299 (predict-yes)
I see 1 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction R in state State-A
In  State-A moving R
ENV: (next state, see, prediction correct?) = (State-B, 1, True)
predict error 0
dir: dir isU
|\-151:    O: O302 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-B
In  State-B moving U
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isL
/152:    O: O303 (predict-yes)
I see 1 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction L in state State-B
In  State-B moving L
ENV: (next state, see, prediction correct?) = (State-A, 1, True)
predict error 0
dir: dir isL
|\153:    O: O306 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction L in state State-A
In  State-A moving L
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isR
-/|154:    O: O307 (predict-yes)
I see 1 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction R in state State-A
In  State-A moving R
ENV: (next state, see, prediction correct?) = (State-B, 1, True)
predict error 0
dir: dir isU
\-/155:    O: O310 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-B
In  State-B moving U
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isR
|\156:    O: O312 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction R in state State-B
In  State-B moving R
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isU
-/|157:    O: O314 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-B
In  State-B moving U
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isL
\-/158:    O: O315 (predict-yes)
I see 1 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction L in state State-B
In  State-B moving L
ENV: (next state, see, prediction correct?) = (State-A, 1, True)
predict error 0
dir: dir isR
|\-159:    O: O317 (predict-yes)
I see 1 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction R in state State-A
In  State-A moving R
ENV: (next state, see, prediction correct?) = (State-B, 1, True)
predict error 0
dir: dir isR
/|\160:    O: O320 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction R in state State-B
In  State-B moving R
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isU
-/161:    O: O322 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-B
In  State-B moving U
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isR
|162:    O: O324 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction R in state State-B
In  State-B moving R
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isL
\-163:    O: O325 (predict-yes)
I see 1 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction L in state State-B
In  State-B moving L
ENV: (next state, see, prediction correct?) = (State-A, 1, True)
predict error 0
dir: dir isL
/|164:    O: O328 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction L in state State-A
In  State-A moving L
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isR
\-/165:    O: O329 (predict-yes)
I see 1 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction R in state State-A
In  State-A moving R
ENV: (next state, see, prediction correct?) = (State-B, 1, True)
predict error 0
dir: dir isL
|\-/166:    O: O331 (predict-yes)
I see 1 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction L in state State-B
In  State-B moving L
ENV: (next state, see, prediction correct?) = (State-A, 1, True)
predict error 0
dir: dir isU
|\-167:    O: O334 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-A
In  State-A moving U
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isU
/|\168:    O: O336 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-A
In  State-A moving U
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isL
-/|169:    O: O338 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction L in state State-A
In  State-A moving L
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isL
\-/170:    O: O340 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction L in state State-A
In  State-A moving L
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isU
|\-171:    O: O342 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-A
In  State-A moving U
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isR
/172:    O: O343 (predict-yes)
I see 1 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction R in state State-A
In  State-A moving R
ENV: (next state, see, prediction correct?) = (State-B, 1, True)
predict error 0
dir: dir isU
|\-173:    O: O346 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-B
In  State-B moving U
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isR
/|\174:    O: O347 (predict-yes)
I see 1 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction R in state State-B
In  State-B moving R
ENV: (next state, see, prediction correct?) = (State-B, 0, False)
predict error 1
dir: dir isL
-/|175:    O: O349 (predict-yes)
I see 0 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction L in state State-B
In  State-B moving L
ENV: (next state, see, prediction correct?) = (State-A, 1, True)
predict error 0
dir: dir isL
\-/176:    O: O352 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction L in state State-A
In  State-A moving L
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isU
|\177:    O: O354 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-A
In  State-A moving U
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isL
-/|\178:    O: O356 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction L in state State-A
In  State-A moving L
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isR
-/179:    O: O357 (predict-yes)
I see 1 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction R in state State-A
In  State-A moving R
ENV: (next state, see, prediction correct?) = (State-B, 1, True)
predict error 0
dir: dir isR
|\-180:    O: O360 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction R in state State-B
In  State-B moving R
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isR
/181:    O: O362 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction R in state State-B
In  State-B moving R
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isR
|182:    O: O364 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction R in state State-B
In  State-B moving R
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isU
\-/183:    O: O366 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-B
In  State-B moving U
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isL
|\-184:    O: O367 (predict-yes)
I see 1 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction L in state State-B
In  State-B moving L
ENV: (next state, see, prediction correct?) = (State-A, 1, True)
predict error 0
dir: dir isL
/|185:    O: O370 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction L in state State-A
In  State-A moving L
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isU
\-/186:    O: O372 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-A
In  State-A moving U
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isU
|\187:    O: O374 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-A
In  State-A moving U
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isU
-/|188:    O: O375 (predict-yes)
I see 1 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction U in state State-A
In  State-A moving U
ENV: (next state, see, prediction correct?) = (State-A, 0, False)
predict error 1
dir: dir isR
\-189:    O: O377 (predict-yes)
I see 0 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction R in state State-A
In  State-A moving R
ENV: (next state, see, prediction correct?) = (State-B, 1, True)
predict error 0
dir: dir isU
/|190:    O: O380 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-B
In  State-B moving U
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isU
\-/191:    O: O382 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-B
In  State-B moving U
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isL
|192:    O: O383 (predict-yes)
I see 1 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction L in state State-B
In  State-B moving L
ENV: (next state, see, prediction correct?) = (State-A, 1, True)
predict error 0
dir: dir isU
\-/193:    O: O386 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-A
In  State-A moving U
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isU
|\194:    O: O388 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-A
In  State-A moving U
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isR
-/195:    O: O389 (predict-yes)
I see 1 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction R in state State-A
In  State-A moving R
ENV: (next state, see, prediction correct?) = (State-B, 1, True)
predict error 0
dir: dir isR
|\-196:    O: O392 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction R in state State-B
In  State-B moving R
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isL
/|\197:    O: O393 (predict-yes)
I see 1 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction L in state State-B
In  State-B moving L
ENV: (next state, see, prediction correct?) = (State-A, 1, True)
predict error 0
dir: dir isR
-/|198:    O: O395 (predict-yes)
I see 1 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction R in state State-A
In  State-A moving R
ENV: (next state, see, prediction correct?) = (State-B, 1, True)
predict error 0
dir: dir isL
\-199:    O: O397 (predict-yes)
I see 1 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction L in state State-B
In  State-B moving L
ENV: (next state, see, prediction correct?) = (State-A, 1, True)
predict error 0
dir: dir isL
/|\200:    O: O400 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction L in state State-A
In  State-A moving L
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isR
-/|201:    O: O401 (predict-yes)
I see 1 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction R in state State-A
In  State-A moving R
ENV: (next state, see, prediction correct?) = (State-B, 1, True)
predict error 0
dir: dir isL
\202:    O: O403 (predict-yes)
I see 1 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction L in state State-B
In  State-B moving L
ENV: (next state, see, prediction correct?) = (State-A, 1, True)
predict error 0
dir: dir isU
-/|203:    O: O406 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-A
In  State-A moving U
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isL
\-/204:    O: O408 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction L in state State-A
In  State-A moving L
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isU
|\-205:    O: O410 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-A
In  State-A moving U
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isU
/|206:    O: O411 (predict-yes)
I see 1 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction U in state State-A
In  State-A moving U
ENV: (next state, see, prediction correct?) = (State-A, 0, False)
predict error 1
dir: dir isU
\-/207:    O: O414 (predict-no)
I see 0 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-A
In  State-A moving U
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isU
|\-208:    O: O416 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-A
In  State-A moving U
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isU
/|209:    O: O418 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-A
In  State-A moving U
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isR
\-/210:    O: O419 (predict-yes)
I see 1 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction R in state State-A
In  State-A moving R
ENV: (next state, see, prediction correct?) = (State-B, 1, True)
predict error 0
dir: dir isL
|\-211:    O: O421 (predict-yes)
I see 1 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction L in state State-B
In  State-B moving L
ENV: (next state, see, prediction correct?) = (State-A, 1, True)
predict error 0
dir: dir isU
/212:    O: O423 (predict-yes)
I see 1 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction U in state State-A
In  State-A moving U
ENV: (next state, see, prediction correct?) = (State-A, 0, False)
predict error 1
dir: dir isL
|\213:    O: O425 (predict-yes)
I see 0 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction L in state State-A
In  State-A moving L
ENV: (next state, see, prediction correct?) = (State-A, 0, False)
predict error 1
dir: dir isL
-/|214:    O: O428 (predict-no)
I see 0 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction L in state State-A
In  State-A moving L
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isR
\-/215:    O: O429 (predict-yes)
I see 1 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction R in state State-A
In  State-A moving R
ENV: (next state, see, prediction correct?) = (State-B, 1, True)
predict error 0
dir: dir isR
|\-/216:    O: O432 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction R in state State-B
In  State-B moving R
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isR
|\217:    O: O434 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction R in state State-B
In  State-B moving R
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isU
-/218:    O: O436 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-B
In  State-B moving U
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isR
|\-219:    O: O438 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction R in state State-B
In  State-B moving R
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isR
/|\220:    O: O440 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction R in state State-B
In  State-B moving R
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isL
-/|\221:    O: O441 (predict-yes)
I see 1 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction L in state State-B
In  State-B moving L
ENV: (next state, see, prediction correct?) = (State-A, 1, True)
predict error 0
dir: dir isU
-222:    O: O444 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-A
In  State-A moving U
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isR
/|\223:    O: O445 (predict-yes)
I see 1 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction R in state State-A
In  State-A moving R
ENV: (next state, see, prediction correct?) = (State-B, 1, True)
predict error 0
dir: dir isU
-/|224:    O: O447 (predict-yes)
I see 1 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction U in state State-B
In  State-B moving U
ENV: (next state, see, prediction correct?) = (State-B, 0, False)
predict error 1
dir: dir isR
\-/225:    O: O450 (predict-no)
I see 0 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction R in state State-B
In  State-B moving R
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isL
|\-/226:    O: O451 (predict-yes)
I see 1 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction L in state State-B
In  State-B moving L
ENV: (next state, see, prediction correct?) = (State-A, 1, True)
predict error 0
dir: dir isR
|\-/sleeping...
|227:    O: O453 (predict-yes)
I see 1 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction R in state State-A
In  State-A moving R
ENV: (next state, see, prediction correct?) = (State-B, 1, True)
predict error 0
dir: dir isU
\-/228:    O: O456 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-B
In  State-B moving U
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isL
|\-229:    O: O457 (predict-yes)
I see 1 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction L in state State-B
In  State-B moving L
ENV: (next state, see, prediction correct?) = (State-A, 1, True)
predict error 0
dir: dir isU
/|230:    O: O459 (predict-yes)
I see 1 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction U in state State-A
In  State-A moving U
ENV: (next state, see, prediction correct?) = (State-A, 0, False)
predict error 1
dir: dir isU
\231:    O: O462 (predict-no)
I see 0 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-A
In  State-A moving U
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isU
-232:    O: O464 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-A
In  State-A moving U
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isU
/|233:    O: O466 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-A
In  State-A moving U
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isL
\-/|234:    O: O468 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction L in state State-A
In  State-A moving L
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isR
\-/235:    O: O469 (predict-yes)
I see 1 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction R in state State-A
In  State-A moving R
ENV: (next state, see, prediction correct?) = (State-B, 1, True)
predict error 0
dir: dir isU
|\-236:    O: O472 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-B
In  State-B moving U
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isL
/|237:    O: O474 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction L in state State-B
In  State-B moving L
ENV: (next state, see, prediction correct?) = (State-A, 1, False)
predict error 1
dir: dir isL
\-/238:    O: O476 (predict-no)
I see 0 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction L in state State-A
In  State-A moving L
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isL
|\-239:    O: O478 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction L in state State-A
In  State-A moving L
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isR
/|\240:    O: O479 (predict-yes)
I see 1 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction R in state State-A
In  State-A moving R
ENV: (next state, see, prediction correct?) = (State-B, 1, True)
predict error 0
dir: dir isR
-/|241:    O: O482 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction R in state State-B
In  State-B moving R
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isR
\242:    O: O484 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction R in state State-B
In  State-B moving R
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isU
-/|243:    O: O486 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-B
In  State-B moving U
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isL
\-244:    O: O487 (predict-yes)
I see 1 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction L in state State-B
In  State-B moving L
ENV: (next state, see, prediction correct?) = (State-A, 1, True)
predict error 0
dir: dir isL
/|245:    O: O490 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction L in state State-A
In  State-A moving L
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isL
\-246:    O: O492 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction L in state State-A
In  State-A moving L
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isL
/|\-247:    O: O494 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction L in state State-A
In  State-A moving L
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isL
/|\248:    O: O496 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction L in state State-A
In  State-A moving L
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isU
-/|249:    O: O498 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-A
In  State-A moving U
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isU
\-/250:    O: O500 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-A
In  State-A moving U
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isL
|\-251:    O: O502 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction L in state State-A
In  State-A moving L
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isR
/252:    O: O503 (predict-yes)
I see 1 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction R in state State-A
In  State-A moving R
ENV: (next state, see, prediction correct?) = (State-B, 1, True)
predict error 0
dir: dir isL
|\-253:    O: O505 (predict-yes)
I see 1 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction L in state State-B
In  State-B moving L
ENV: (next state, see, prediction correct?) = (State-A, 1, True)
predict error 0
dir: dir isL
/|254:    O: O508 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction L in state State-A
In  State-A moving L
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isR
\-/|255:    O: O509 (predict-yes)
I see 1 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction R in state State-A
In  State-A moving R
ENV: (next state, see, prediction correct?) = (State-B, 1, True)
predict error 0
dir: dir isR
\-256:    O: O512 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction R in state State-B
In  State-B moving R
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isR
/|257:    O: O514 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction R in state State-B
In  State-B moving R
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isR
\-/258:    O: O516 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction R in state State-B
In  State-B moving R
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isL
|\-259:    O: O517 (predict-yes)
I see 1 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction L in state State-B
In  State-B moving L
ENV: (next state, see, prediction correct?) = (State-A, 1, True)
predict error 0
dir: dir isL
/|260:    O: O520 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction L in state State-A
In  State-A moving L
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isL
\-/261:    O: O522 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction L in state State-A
In  State-A moving L
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isR
|262:    O: O523 (predict-yes)
I see 1 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction R in state State-A
In  State-A moving R
ENV: (next state, see, prediction correct?) = (State-B, 1, True)
predict error 0
dir: dir isU
\-/263:    O: O526 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-B
In  State-B moving U
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isR
|\-264:    O: O528 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction R in state State-B
In  State-B moving R
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isL
/|\265:    O: O529 (predict-yes)
I see 1 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction L in state State-B
In  State-B moving L
ENV: (next state, see, prediction correct?) = (State-A, 1, True)
predict error 0
dir: dir isL
-/266:    O: O532 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction L in state State-A
In  State-A moving L
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isR
|\267:    O: O533 (predict-yes)
I see 1 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction R in state State-A
In  State-A moving R
ENV: (next state, see, prediction correct?) = (State-B, 1, True)
predict error 0
dir: dir isR
-/268:    O: O536 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction R in state State-B
In  State-B moving R
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isU
|\269:    O: O538 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-B
In  State-B moving U
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isR
-/|270:    O: O540 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction R in state State-B
In  State-B moving R
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isU
\-/271:    O: O542 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-B
In  State-B moving U
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isR
|272:    O: O544 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction R in state State-B
In  State-B moving R
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isR
\-/273:    O: O546 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction R in state State-B
In  State-B moving R
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isR
|\-274:    O: O548 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction R in state State-B
In  State-B moving R
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isR
/|275:    O: O550 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction R in state State-B
In  State-B moving R
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isU
\-/276:    O: O552 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-B
In  State-B moving U
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isR
|\-/277:    O: O554 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction R in state State-B
In  State-B moving R
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isU
|\-278:    O: O556 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-B
In  State-B moving U
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isR
/|\279:    O: O558 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction R in state State-B
In  State-B moving R
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isL
-/280:    O: O560 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction L in state State-B
In  State-B moving L
ENV: (next state, see, prediction correct?) = (State-A, 1, False)
predict error 1
dir: dir isR
|\281:    O: O561 (predict-yes)
I see 0 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction R in state State-A
In  State-A moving R
ENV: (next state, see, prediction correct?) = (State-B, 1, True)
predict error 0
dir: dir isU
-282:    O: O564 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-B
In  State-B moving U
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isL
/|\283:    O: O565 (predict-yes)
I see 1 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction L in state State-B
In  State-B moving L
ENV: (next state, see, prediction correct?) = (State-A, 1, True)
predict error 0
dir: dir isR
-/284:    O: O567 (predict-yes)
I see 1 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction R in state State-A
In  State-A moving R
ENV: (next state, see, prediction correct?) = (State-B, 1, True)
predict error 0
dir: dir isR
|\285:    O: O570 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction R in state State-B
In  State-B moving R
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isU
-/|286:    O: O572 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-B
In  State-B moving U
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isU
\-/287:    O: O574 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-B
In  State-B moving U
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isR
|\288:    O: O576 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction R in state State-B
In  State-B moving R
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isU
-/289:    O: O578 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-B
In  State-B moving U
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isU
|\290:    O: O580 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-B
In  State-B moving U
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isL
-/|291:    O: O581 (predict-yes)
I see 1 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction L in state State-B
In  State-B moving L
ENV: (next state, see, prediction correct?) = (State-A, 1, True)
predict error 0
dir: dir isR
\292:    O: O583 (predict-yes)
I see 1 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction R in state State-A
In  State-A moving R
ENV: (next state, see, prediction correct?) = (State-B, 1, True)
predict error 0
dir: dir isL
-/|293:    O: O585 (predict-yes)
I see 1 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction L in state State-B
In  State-B moving L
ENV: (next state, see, prediction correct?) = (State-A, 1, True)
predict error 0
dir: dir isU
\-/|294:    O: O588 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-A
In  State-A moving U
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isR
\-/295:    O: O589 (predict-yes)
I see 1 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction R in state State-A
In  State-A moving R
ENV: (next state, see, prediction correct?) = (State-B, 1, True)
predict error 0
dir: dir isU
|296:    O: O591 (predict-yes)
I see 1 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction U in state State-B
In  State-B moving U
ENV: (next state, see, prediction correct?) = (State-B, 0, False)
predict error 1
dir: dir isU
\297:    O: O594 (predict-no)
I see 0 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-B
In  State-B moving U
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isU
-/|298:    O: O596 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-B
In  State-B moving U
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isU
\-/299:    O: O598 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-B
In  State-B moving U
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isR
|\-300:    O: O600 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction R in state State-B
In  State-B moving R
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isL
/|\-/301:    O: O601 (predict-yes)
I see 1 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction L in state State-B
In  State-B moving L
ENV: (next state, see, prediction correct?) = (State-A, 1, True)
predict error 0
dir: dir isR
|302:    O: O603 (predict-yes)
I see 1 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction R in state State-A
In  State-A moving R
ENV: (next state, see, prediction correct?) = (State-B, 1, True)
predict error 0
dir: dir isL
\-/303:    O: O605 (predict-yes)
I see 1 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction L in state State-B
In  State-B moving L
ENV: (next state, see, prediction correct?) = (State-A, 1, True)
predict error 0
dir: dir isL
|\304:    O: O608 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction L in state State-A
In  State-A moving L
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isU
-/|305:    O: O610 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-A
In  State-A moving U
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isL
\-/306:    O: O612 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction L in state State-A
In  State-A moving L
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isL
|\307:    O: O614 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction L in state State-A
In  State-A moving L
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isL
-/|308:    O: O616 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction L in state State-A
In  State-A moving L
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isU
\-/309:    O: O618 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-A
In  State-A moving U
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isL
|\310:    O: O620 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction L in state State-A
In  State-A moving L
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isL
-/|311:    O: O622 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction L in state State-A
In  State-A moving L
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isU
\312:    O: O624 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-A
In  State-A moving U
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isL
-/|313:    O: O626 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction L in state State-A
In  State-A moving L
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isU
\-/314:    O: O628 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-A
In  State-A moving U
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isU
|\-315:    O: O630 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-A
In  State-A moving U
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isU
/|\316:    O: O632 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-A
In  State-A moving U
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isU
-/|317:    O: O634 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-A
In  State-A moving U
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isR
\-/318:    O: O635 (predict-yes)
I see 1 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction R in state State-A
In  State-A moving R
ENV: (next state, see, prediction correct?) = (State-B, 1, True)
predict error 0
dir: dir isU
|\-319:    O: O638 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-B
In  State-B moving U
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isL
/|\320:    O: O639 (predict-yes)
I see 1 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction L in state State-B
In  State-B moving L
ENV: (next state, see, prediction correct?) = (State-A, 1, True)
predict error 0
dir: dir isU
-321:    O: O642 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-A
In  State-A moving U
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isR
/322:    O: O643 (predict-yes)
I see 1 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction R in state State-A
In  State-A moving R
ENV: (next state, see, prediction correct?) = (State-B, 1, True)
predict error 0
dir: dir isU
|\-323:    O: O646 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-B
In  State-B moving U
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isL
/|\324:    O: O647 (predict-yes)
I see 1 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction L in state State-B
In  State-B moving L
ENV: (next state, see, prediction correct?) = (State-A, 1, True)
predict error 0
dir: dir isU
-/325:    O: O650 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-A
In  State-A moving U
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isU
|\326:    O: O652 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-A
In  State-A moving U
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isL
-/327:    O: O654 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction L in state State-A
In  State-A moving L
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isL
|\-/sleeping...
|328:    O: O656 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction L in state State-A
In  State-A moving L
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isR
\-329:    O: O657 (predict-yes)
I see 1 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction R in state State-A
In  State-A moving R
ENV: (next state, see, prediction correct?) = (State-B, 1, True)
predict error 0
dir: dir isU
/|\330:    O: O660 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-B
In  State-B moving U
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isL
-/331:    O: O661 (predict-yes)
I see 1 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction L in state State-B
In  State-B moving L
ENV: (next state, see, prediction correct?) = (State-A, 1, True)
predict error 0
dir: dir isL
|332:    O: O664 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction L in state State-A
In  State-A moving L
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isL
\-/333:    O: O666 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction L in state State-A
In  State-A moving L
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isR
|\-334:    O: O667 (predict-yes)
I see 1 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction R in state State-A
In  State-A moving R
ENV: (next state, see, prediction correct?) = (State-B, 1, True)
predict error 0
dir: dir isU
/|335:    O: O669 (predict-yes)
I see 1 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction U in state State-B
In  State-B moving U
ENV: (next state, see, prediction correct?) = (State-B, 0, False)
predict error 1
dir: dir isR
\-/336:    O: O672 (predict-no)
I see 0 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction R in state State-B
In  State-B moving R
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isR
|\-337:    O: O674 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction R in state State-B
In  State-B moving R
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isR
/|\338:    O: O676 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction R in state State-B
In  State-B moving R
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isR
-/339:    O: O678 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction R in state State-B
In  State-B moving R
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isR
|\-340:    O: O679 (predict-yes)
I see 1 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction R in state State-B
In  State-B moving R
ENV: (next state, see, prediction correct?) = (State-B, 0, False)
predict error 1
dir: dir isL
/|341:    O: O681 (predict-yes)
I see 0 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction L in state State-B
In  State-B moving L
ENV: (next state, see, prediction correct?) = (State-A, 1, True)
predict error 0
dir: dir isR
\342:    O: O683 (predict-yes)
I see 1 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction R in state State-A
In  State-A moving R
ENV: (next state, see, prediction correct?) = (State-B, 1, True)
predict error 0
dir: dir isU
-/|343:    O: O686 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-B
In  State-B moving U
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isR
\-/344:    O: O687 (predict-yes)
I see 1 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction R in state State-B
In  State-B moving R
ENV: (next state, see, prediction correct?) = (State-B, 0, False)
predict error 1
dir: dir isU
|\-345:    O: O690 (predict-no)
I see 0 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-B
In  State-B moving U
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isL
/|346:    O: O691 (predict-yes)
I see 1 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction L in state State-B
In  State-B moving L
ENV: (next state, see, prediction correct?) = (State-A, 1, True)
predict error 0
dir: dir isU
\-/347:    O: O694 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-A
In  State-A moving U
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isU
|\-348:    O: O696 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-A
In  State-A moving U
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isU
/|\349:    O: O698 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-A
In  State-A moving U
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isR
-/|350:    O: O699 (predict-yes)
I see 1 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction R in state State-A
In  State-A moving R
ENV: (next state, see, prediction correct?) = (State-B, 1, True)
predict error 0
dir: dir isR
\-/351:    O: O702 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction R in state State-B
In  State-B moving R
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isR
|352:    O: O704 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction R in state State-B
In  State-B moving R
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isU
\-353:    O: O706 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-B
In  State-B moving U
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isL
/|\354:    O: O707 (predict-yes)
I see 1 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction L in state State-B
In  State-B moving L
ENV: (next state, see, prediction correct?) = (State-A, 1, True)
predict error 0
dir: dir isL
-/|355:    O: O710 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction L in state State-A
In  State-A moving L
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isU
\-/356:    O: O712 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-A
In  State-A moving U
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isU
|\-357:    O: O714 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-A
In  State-A moving U
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isR
/|\358:    O: O715 (predict-yes)
I see 1 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction R in state State-A
In  State-A moving R
ENV: (next state, see, prediction correct?) = (State-B, 1, True)
predict error 0
dir: dir isR
-/|359:    O: O718 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction R in state State-B
In  State-B moving R
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isU
\-/360:    O: O720 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-B
In  State-B moving U
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isL
|\361:    O: O721 (predict-yes)
I see 1 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction L in state State-B
In  State-B moving L
ENV: (next state, see, prediction correct?) = (State-A, 1, True)
predict error 0
dir: dir isL
-362:    O: O724 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction L in state State-A
In  State-A moving L
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isL
/|\363:    O: O726 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction L in state State-A
In  State-A moving L
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isR
-/|364:    O: O727 (predict-yes)
I see 1 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction R in state State-A
In  State-A moving R
ENV: (next state, see, prediction correct?) = (State-B, 1, True)
predict error 0
dir: dir isL
\-/365:    O: O729 (predict-yes)
I see 1 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction L in state State-B
In  State-B moving L
ENV: (next state, see, prediction correct?) = (State-A, 1, True)
predict error 0
dir: dir isL
|366:    O: O732 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction L in state State-A
In  State-A moving L
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isU
\-/367:    O: O734 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-A
In  State-A moving U
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isU
|\-368:    O: O735 (predict-yes)
I see 1 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction U in state State-A
In  State-A moving U
ENV: (next state, see, prediction correct?) = (State-A, 0, False)
predict error 1
dir: dir isL
/|\369:    O: O738 (predict-no)
I see 0 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction L in state State-A
In  State-A moving L
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isU
-/|370:    O: O740 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-A
In  State-A moving U
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isR
\-371:    O: O741 (predict-yes)
I see 1 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction R in state State-A
In  State-A moving R
ENV: (next state, see, prediction correct?) = (State-B, 1, True)
predict error 0
dir: dir isU
/372:    O: O744 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-B
In  State-B moving U
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isR
|\-373:    O: O745 (predict-yes)
I see 1 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction R in state State-B
In  State-B moving R
ENV: (next state, see, prediction correct?) = (State-B, 0, False)
predict error 1
dir: dir isL
/|374:    O: O747 (predict-yes)
I see 0 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction L in state State-B
In  State-B moving L
ENV: (next state, see, prediction correct?) = (State-A, 1, True)
predict error 0
dir: dir isL
\-/375:    O: O750 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction L in state State-A
In  State-A moving L
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isL
|\-376:    O: O752 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction L in state State-A
In  State-A moving L
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isR
/|\377:    O: O753 (predict-yes)
I see 1 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction R in state State-A
In  State-A moving R
ENV: (next state, see, prediction correct?) = (State-B, 1, True)
predict error 0
dir: dir isR
-/|378:    O: O756 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction R in state State-B
In  State-B moving R
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isL
\-/379:    O: O757 (predict-yes)
I see 1 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction L in state State-B
In  State-B moving L
ENV: (next state, see, prediction correct?) = (State-A, 1, True)
predict error 0
dir: dir isR
|\380:    O: O759 (predict-yes)
I see 1 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction R in state State-A
In  State-A moving R
ENV: (next state, see, prediction correct?) = (State-B, 1, True)
predict error 0
dir: dir isL
-/381:    O: O761 (predict-yes)
I see 1 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction L in state State-B
In  State-B moving L
ENV: (next state, see, prediction correct?) = (State-A, 1, True)
predict error 0
dir: dir isU
|382:    O: O764 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-A
In  State-A moving U
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isL
\-383:    O: O766 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction L in state State-A
In  State-A moving L
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isU
/|384:    O: O768 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-A
In  State-A moving U
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isR
\-385:    O: O769 (predict-yes)
I see 1 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction R in state State-A
In  State-A moving R
ENV: (next state, see, prediction correct?) = (State-B, 1, True)
predict error 0
dir: dir isR
/|386:    O: O772 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction R in state State-B
In  State-B moving R
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isR
\-387:    O: O774 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction R in state State-B
In  State-B moving R
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isU
/|\-388:    O: O776 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-B
In  State-B moving U
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isU
/|\389:    O: O778 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-B
In  State-B moving U
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isR
-/|390:    O: O780 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction R in state State-B
In  State-B moving R
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isR
\-391:    O: O782 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction R in state State-B
In  State-B moving R
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isU
/392:    O: O784 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-B
In  State-B moving U
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isU
|\393:    O: O786 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-B
In  State-B moving U
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isR
-/394:    O: O788 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction R in state State-B
In  State-B moving R
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isU
|\-395:    O: O790 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-B
In  State-B moving U
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isU
/|396:    O: O792 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-B
In  State-B moving U
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isR
\-/397:    O: O794 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction R in state State-B
In  State-B moving R
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isL
|\-398:    O: O795 (predict-yes)
I see 1 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction L in state State-B
In  State-B moving L
ENV: (next state, see, prediction correct?) = (State-A, 1, True)
predict error 0
dir: dir isL
/|399:    O: O798 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction L in state State-A
In  State-A moving L
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isU
\-/400:    O: O800 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-A
In  State-A moving U
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isU
|\-401:    O: O802 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-A
In  State-A moving U
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isU
/402:    O: O804 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-A
In  State-A moving U
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isU
|\-403:    O: O806 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-A
In  State-A moving U
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isL
/|\404:    O: O808 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction L in state State-A
In  State-A moving L
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isL
-/|405:    O: O810 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction L in state State-A
In  State-A moving L
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isL
\-/406:    O: O812 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction L in state State-A
In  State-A moving L
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isL
|\-407:    O: O814 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction L in state State-A
In  State-A moving L
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isU
/|\408:    O: O816 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-A
In  State-A moving U
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isU
-/|409:    O: O818 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-A
In  State-A moving U
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isU
\-/410:    O: O820 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-A
In  State-A moving U
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isL
|\411:    O: O822 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction L in state State-A
In  State-A moving L
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isU
-412:    O: O824 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-A
In  State-A moving U
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isL
/|413:    O: O826 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction L in state State-A
In  State-A moving L
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isR
\-/414:    O: O827 (predict-yes)
I see 1 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction R in state State-A
In  State-A moving R
ENV: (next state, see, prediction correct?) = (State-B, 1, True)
predict error 0
dir: dir isU
|\-415:    O: O829 (predict-yes)
I see 1 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction U in state State-B
In  State-B moving U
ENV: (next state, see, prediction correct?) = (State-B, 0, False)
predict error 1
dir: dir isL
/|416:    O: O831 (predict-yes)
I see 0 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction L in state State-B
In  State-B moving L
ENV: (next state, see, prediction correct?) = (State-A, 1, True)
predict error 0
dir: dir isL
\-417:    O: O834 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction L in state State-A
In  State-A moving L
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isU
/|\418:    O: O835 (predict-yes)
I see 1 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction U in state State-A
In  State-A moving U
ENV: (next state, see, prediction correct?) = (State-A, 0, False)
predict error 1
dir: dir isL
-/419:    O: O838 (predict-no)
I see 0 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction L in state State-A
In  State-A moving L
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isR
|\-420:    O: O839 (predict-yes)
I see 1 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction R in state State-A
In  State-A moving R
ENV: (next state, see, prediction correct?) = (State-B, 1, True)
predict error 0
dir: dir isR
/421:    O: O842 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction R in state State-B
In  State-B moving R
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isU
|422:    O: O844 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-B
In  State-B moving U
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isL
\-423:    O: O845 (predict-yes)
I see 1 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction L in state State-B
In  State-B moving L
ENV: (next state, see, prediction correct?) = (State-A, 1, True)
predict error 0
dir: dir isR
/424:    O: O847 (predict-yes)
I see 1 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction R in state State-A
In  State-A moving R
ENV: (next state, see, prediction correct?) = (State-B, 1, True)
predict error 0
dir: dir isR
|\-425:    O: O850 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction R in state State-B
In  State-B moving R
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isR
/|426:    O: O852 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction R in state State-B
In  State-B moving R
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isL
\-/427:    O: O853 (predict-yes)
I see 1 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction L in state State-B
In  State-B moving L
ENV: (next state, see, prediction correct?) = (State-A, 1, True)
predict error 0
dir: dir isR
|\-428:    O: O855 (predict-yes)
I see 1 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction R in state State-A
In  State-A moving R
ENV: (next state, see, prediction correct?) = (State-B, 1, True)
predict error 0
dir: dir isU
/|\429:    O: O858 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-B
In  State-B moving U
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isR
-/430:    O: O860 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction R in state State-B
In  State-B moving R
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isR
|\431:    O: O862 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction R in state State-B
In  State-B moving R
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isL
-432:    O: O863 (predict-yes)
I see 1 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction L in state State-B
In  State-B moving L
ENV: (next state, see, prediction correct?) = (State-A, 1, True)
predict error 0
dir: dir isL
/|\433:    O: O866 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction L in state State-A
In  State-A moving L
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isR
-/434:    O: O867 (predict-yes)
I see 1 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction R in state State-A
In  State-A moving R
ENV: (next state, see, prediction correct?) = (State-B, 1, True)
predict error 0
dir: dir isL
|\-435:    O: O869 (predict-yes)
I see 1 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction L in state State-B
In  State-B moving L
ENV: (next state, see, prediction correct?) = (State-A, 1, True)
predict error 0
dir: dir isU
/|\436:    O: O872 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-A
In  State-A moving U
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isU
-/|437:    O: O874 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-A
In  State-A moving U
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isL
\-/438:    O: O876 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction L in state State-A
In  State-A moving L
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isU
|\-439:    O: O878 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-A
In  State-A moving U
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isR
/|\440:    O: O879 (predict-yes)
I see 1 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction R in state State-A
In  State-A moving R
ENV: (next state, see, prediction correct?) = (State-B, 1, True)
predict error 0
dir: dir isU
-/|441:    O: O882 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-B
In  State-B moving U
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isU
\442:    O: O884 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-B
In  State-B moving U
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isL
-/|443:    O: O885 (predict-yes)
I see 1 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction L in state State-B
In  State-B moving L
ENV: (next state, see, prediction correct?) = (State-A, 1, True)
predict error 0
dir: dir isU
\-444:    O: O888 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-A
In  State-A moving U
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isR
/445:    O: O889 (predict-yes)
I see 1 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction R in state State-A
In  State-A moving R
ENV: (next state, see, prediction correct?) = (State-B, 1, True)
predict error 0
dir: dir isU
|\-446:    O: O892 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-B
In  State-B moving U
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isL
/|447:    O: O893 (predict-yes)
I see 1 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction L in state State-B
In  State-B moving L
ENV: (next state, see, prediction correct?) = (State-A, 1, True)
predict error 0
dir: dir isU
\-/448:    O: O896 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-A
In  State-A moving U
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isU
|\-449:    O: O898 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-A
In  State-A moving U
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isU
/|\450:    O: O900 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-A
In  State-A moving U
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isR
-451:    O: O901 (predict-yes)
I see 1 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction R in state State-A
In  State-A moving R
ENV: (next state, see, prediction correct?) = (State-B, 1, True)
predict error 0
dir: dir isL
/452:    O: O903 (predict-yes)
I see 1 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction L in state State-B
In  State-B moving L
ENV: (next state, see, prediction correct?) = (State-A, 1, True)
predict error 0
dir: dir isR
|\-/sleeping...
|453:    O: O905 (predict-yes)
I see 1 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction R in state State-A
In  State-A moving R
ENV: (next state, see, prediction correct?) = (State-B, 1, True)
predict error 0
dir: dir isR
\-/454:    O: O908 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction R in state State-B
In  State-B moving R
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isU
|\-455:    O: O910 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-B
In  State-B moving U
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isU
/|\456:    O: O912 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-B
In  State-B moving U
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isR
-/|457:    O: O914 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction R in state State-B
In  State-B moving R
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isL
\458:    O: O915 (predict-yes)
I see 1 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction L in state State-B
In  State-B moving L
ENV: (next state, see, prediction correct?) = (State-A, 1, True)
predict error 0
dir: dir isR
-/459:    O: O917 (predict-yes)
I see 1 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction R in state State-A
In  State-A moving R
ENV: (next state, see, prediction correct?) = (State-B, 1, True)
predict error 0
dir: dir isR
|\-460:    O: O920 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction R in state State-B
In  State-B moving R
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isL
/|\461:    O: O921 (predict-yes)
I see 1 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction L in state State-B
In  State-B moving L
ENV: (next state, see, prediction correct?) = (State-A, 1, True)
predict error 0
dir: dir isU
-462:    O: O924 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-A
In  State-A moving U
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isR
/|463:    O: O925 (predict-yes)
I see 1 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction R in state State-A
In  State-A moving R
ENV: (next state, see, prediction correct?) = (State-B, 1, True)
predict error 0
dir: dir isL
\464:    O: O927 (predict-yes)
I see 1 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction L in state State-B
In  State-B moving L
ENV: (next state, see, prediction correct?) = (State-A, 1, True)
predict error 0
dir: dir isU
-/465:    O: O930 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-A
In  State-A moving U
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isL
|\-466:    O: O932 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction L in state State-A
In  State-A moving L
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isL
/|\-467:    O: O934 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction L in state State-A
In  State-A moving L
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isU
/|\468:    O: O936 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-A
In  State-A moving U
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isR
-/469:    O: O937 (predict-yes)
I see 1 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction R in state State-A
In  State-A moving R
ENV: (next state, see, prediction correct?) = (State-B, 1, True)
predict error 0
dir: dir isR
|\470:    O: O940 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction R in state State-B
In  State-B moving R
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isR
-/|\471:    O: O942 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction R in state State-B
In  State-B moving R
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isR
-472:    O: O944 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction R in state State-B
In  State-B moving R
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isL
/|473:    O: O945 (predict-yes)
I see 1 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction L in state State-B
In  State-B moving L
ENV: (next state, see, prediction correct?) = (State-A, 1, True)
predict error 0
dir: dir isL
\-/474:    O: O948 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction L in state State-A
In  State-A moving L
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isL
|\-475:    O: O950 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction L in state State-A
In  State-A moving L
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isU
/|\476:    O: O952 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-A
In  State-A moving U
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isU
-/|477:    O: O954 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-A
In  State-A moving U
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isR
\-478:    O: O955 (predict-yes)
I see 1 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction R in state State-A
In  State-A moving R
ENV: (next state, see, prediction correct?) = (State-B, 1, True)
predict error 0
dir: dir isU
/|479:    O: O958 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-B
In  State-B moving U
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isR
\-/480:    O: O960 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction R in state State-B
In  State-B moving R
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isL
|\-481:    O: O961 (predict-yes)
I see 1 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction L in state State-B
In  State-B moving L
ENV: (next state, see, prediction correct?) = (State-A, 1, True)
predict error 0
dir: dir isR
/482:    O: O963 (predict-yes)
I see 1 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction R in state State-A
In  State-A moving R
ENV: (next state, see, prediction correct?) = (State-B, 1, True)
predict error 0
dir: dir isU
|\-483:    O: O966 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-B
In  State-B moving U
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isL
/|\484:    O: O967 (predict-yes)
I see 1 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction L in state State-B
In  State-B moving L
ENV: (next state, see, prediction correct?) = (State-A, 1, True)
predict error 0
dir: dir isR
-/485:    O: O969 (predict-yes)
I see 1 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction R in state State-A
In  State-A moving R
ENV: (next state, see, prediction correct?) = (State-B, 1, True)
predict error 0
dir: dir isL
|\-486:    O: O971 (predict-yes)
I see 1 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction L in state State-B
In  State-B moving L
ENV: (next state, see, prediction correct?) = (State-A, 1, True)
predict error 0
dir: dir isU
/|\487:    O: O974 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-A
In  State-A moving U
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isR
-/488:    O: O975 (predict-yes)
I see 1 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction R in state State-A
In  State-A moving R
ENV: (next state, see, prediction correct?) = (State-B, 1, True)
predict error 0
dir: dir isL
|489:    O: O977 (predict-yes)
I see 1 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction L in state State-B
In  State-B moving L
ENV: (next state, see, prediction correct?) = (State-A, 1, True)
predict error 0
dir: dir isR
\-/490:    O: O979 (predict-yes)
I see 1 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction R in state State-A
In  State-A moving R
ENV: (next state, see, prediction correct?) = (State-B, 1, True)
predict error 0
dir: dir isR
|491:    O: O982 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction R in state State-B
In  State-B moving R
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isU
\492:    O: O984 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-B
In  State-B moving U
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isR
-/|493:    O: O986 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction R in state State-B
In  State-B moving R
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isU
\-/494:    O: O988 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-B
In  State-B moving U
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isL
|\-495:    O: O989 (predict-yes)
I see 1 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction L in state State-B
In  State-B moving L
ENV: (next state, see, prediction correct?) = (State-A, 1, True)
predict error 0
dir: dir isL
/|\496:    O: O992 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction L in state State-A
In  State-A moving L
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isL
-/|497:    O: O994 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction L in state State-A
In  State-A moving L
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isL
\-/498:    O: O996 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction L in state State-A
In  State-A moving L
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isU
|\-/499:    O: O998 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-A
In  State-A moving U
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isU
|\500:    O: O1000 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-A
In  State-A moving U
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isL
-/|\501:    O: O1002 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction L in state State-A
In  State-A moving L
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isL
-502:    O: O1004 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction L in state State-A
In  State-A moving L
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isR
/|\-503:    O: O1005 (predict-yes)
I see 1 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction R in state State-A
In  State-A moving R
ENV: (next state, see, prediction correct?) = (State-B, 1, True)
predict error 0
dir: dir isU
/|504:    O: O1008 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-B
In  State-B moving U
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isU
\-505:    O: O1010 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-B
In  State-B moving U
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isU
/|\506:    O: O1012 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-B
In  State-B moving U
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isR
-/|507:    O: O1014 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction R in state State-B
In  State-B moving R
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isL
\-/508:    O: O1015 (predict-yes)
I see 1 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction L in state State-B
In  State-B moving L
ENV: (next state, see, prediction correct?) = (State-A, 1, True)
predict error 0
dir: dir isR
|\-509:    O: O1017 (predict-yes)
I see 1 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction R in state State-A
In  State-A moving R
ENV: (next state, see, prediction correct?) = (State-B, 1, True)
predict error 0
dir: dir isL
/|\510:    O: O1019 (predict-yes)
I see 1 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction L in state State-B
In  State-B moving L
ENV: (next state, see, prediction correct?) = (State-A, 1, True)
predict error 0
dir: dir isR
-/|511:    O: O1021 (predict-yes)
I see 1 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction R in state State-A
In  State-A moving R
ENV: (next state, see, prediction correct?) = (State-B, 1, True)
predict error 0
dir: dir isR
\512:    O: O1024 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction R in state State-B
In  State-B moving R
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isL
-/513:    O: O1025 (predict-yes)
I see 1 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction L in state State-B
In  State-B moving L
ENV: (next state, see, prediction correct?) = (State-A, 1, True)
predict error 0
dir: dir isL
|\-514:    O: O1028 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction L in state State-A
In  State-A moving L
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isU
/|\515:    O: O1030 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-A
In  State-A moving U
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isL
-/|516:    O: O1032 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction L in state State-A
In  State-A moving L
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isU
\-517:    O: O1034 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-A
In  State-A moving U
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isU
/|\518:    O: O1036 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-A
In  State-A moving U
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isU
-/519:    O: O1038 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-A
In  State-A moving U
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isR
|\520:    O: O1039 (predict-yes)
I see 1 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction R in state State-A
In  State-A moving R
ENV: (next state, see, prediction correct?) = (State-B, 1, True)
predict error 0
dir: dir isR
-/|521:    O: O1042 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction R in state State-B
In  State-B moving R
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isR
\522:    O: O1044 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction R in state State-B
In  State-B moving R
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isR
-/523:    O: O1046 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction R in state State-B
In  State-B moving R
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isU
|\-524:    O: O1048 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-B
In  State-B moving U
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isU
/|\525:    O: O1050 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-B
In  State-B moving U
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isL
-/|526:    O: O1051 (predict-yes)
I see 1 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction L in state State-B
In  State-B moving L
ENV: (next state, see, prediction correct?) = (State-A, 1, True)
predict error 0
dir: dir isU
\-/527:    O: O1054 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-A
In  State-A moving U
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isR
|\528:    O: O1055 (predict-yes)
I see 1 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction R in state State-A
In  State-A moving R
ENV: (next state, see, prediction correct?) = (State-B, 1, True)
predict error 0
dir: dir isR
-529:    O: O1058 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction R in state State-B
In  State-B moving R
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isU
/|530:    O: O1060 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-B
In  State-B moving U
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isL
\-/531:    O: O1061 (predict-yes)
I see 1 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction L in state State-B
In  State-B moving L
ENV: (next state, see, prediction correct?) = (State-A, 1, True)
predict error 0
dir: dir isU
|532:    O: O1064 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-A
In  State-A moving U
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isR
\-/533:    O: O1065 (predict-yes)
I see 1 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction R in state State-A
In  State-A moving R
ENV: (next state, see, prediction correct?) = (State-B, 1, True)
predict error 0
dir: dir isR
|\-534:    O: O1068 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction R in state State-B
In  State-B moving R
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isR
/|\535:    O: O1070 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction R in state State-B
In  State-B moving R
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isR
-/|536:    O: O1072 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction R in state State-B
In  State-B moving R
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isL
\-537:    O: O1073 (predict-yes)
I see 1 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction L in state State-B
In  State-B moving L
ENV: (next state, see, prediction correct?) = (State-A, 1, True)
predict error 0
dir: dir isR
/|\538:    O: O1075 (predict-yes)
I see 1 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction R in state State-A
In  State-A moving R
ENV: (next state, see, prediction correct?) = (State-B, 1, True)
predict error 0
dir: dir isL
-539:    O: O1077 (predict-yes)
I see 1 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction L in state State-B
In  State-B moving L
ENV: (next state, see, prediction correct?) = (State-A, 1, True)
predict error 0
dir: dir isR
/|\540:    O: O1079 (predict-yes)
I see 1 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction R in state State-A
In  State-A moving R
ENV: (next state, see, prediction correct?) = (State-B, 1, True)
predict error 0
dir: dir isR
-/541:    O: O1082 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction R in state State-B
In  State-B moving R
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isR
|542:    O: O1084 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction R in state State-B
In  State-B moving R
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isR
\-543:    O: O1086 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction R in state State-B
In  State-B moving R
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isU
/544:    O: O1088 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-B
In  State-B moving U
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isU
|\545:    O: O1090 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-B
In  State-B moving U
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isL
-/|546:    O: O1091 (predict-yes)
I see 1 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction L in state State-B
In  State-B moving L
ENV: (next state, see, prediction correct?) = (State-A, 1, True)
predict error 0
dir: dir isU
\-/547:    O: O1094 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-A
In  State-A moving U
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isR
|\-548:    O: O1095 (predict-yes)
I see 1 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction R in state State-A
In  State-A moving R
ENV: (next state, see, prediction correct?) = (State-B, 1, True)
predict error 0
dir: dir isL
/|\549:    O: O1097 (predict-yes)
I see 1 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction L in state State-B
In  State-B moving L
ENV: (next state, see, prediction correct?) = (State-A, 1, True)
predict error 0
dir: dir isR
-/|550:    O: O1099 (predict-yes)
I see 1 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction R in state State-A
In  State-A moving R
ENV: (next state, see, prediction correct?) = (State-B, 1, True)
predict error 0
dir: dir isL
\-/551:    O: O1101 (predict-yes)
I see 1 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction L in state State-B
In  State-B moving L
ENV: (next state, see, prediction correct?) = (State-A, 1, True)
predict error 0
dir: dir isL
|552:    O: O1104 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction L in state State-A
In  State-A moving L
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isR
\-553:    O: O1105 (predict-yes)
I see 1 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction R in state State-A
In  State-A moving R
ENV: (next state, see, prediction correct?) = (State-B, 1, True)
predict error 0
dir: dir isU
/|\554:    O: O1108 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-B
In  State-B moving U
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isL
-555:    O: O1109 (predict-yes)
I see 1 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction L in state State-B
In  State-B moving L
ENV: (next state, see, prediction correct?) = (State-A, 1, True)
predict error 0
dir: dir isU
/|\556:    O: O1112 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-A
In  State-A moving U
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isU
-/|557:    O: O1114 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-A
In  State-A moving U
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isL
\-/558:    O: O1116 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction L in state State-A
In  State-A moving L
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isU
|\-559:    O: O1118 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-A
In  State-A moving U
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isR
/|\560:    O: O1119 (predict-yes)
I see 1 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction R in state State-A
In  State-A moving R
ENV: (next state, see, prediction correct?) = (State-B, 1, True)
predict error 0
dir: dir isU
-/|\561:    O: O1122 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-B
In  State-B moving U
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isU
-562:    O: O1124 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-B
In  State-B moving U
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isU
/|563:    O: O1126 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-B
In  State-B moving U
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isR
\-/564:    O: O1128 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction R in state State-B
In  State-B moving R
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isU
|\565:    O: O1130 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-B
In  State-B moving U
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isU
-/|566:    O: O1132 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-B
In  State-B moving U
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isU
\-/567:    O: O1134 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-B
In  State-B moving U
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isR
|\-568:    O: O1136 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction R in state State-B
In  State-B moving R
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isU
/|\569:    O: O1138 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-B
In  State-B moving U
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isR
-/|570:    O: O1140 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction R in state State-B
In  State-B moving R
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isL
\571:    O: O1141 (predict-yes)
I see 1 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction L in state State-B
In  State-B moving L
ENV: (next state, see, prediction correct?) = (State-A, 1, True)
predict error 0
dir: dir isL
-572:    O: O1144 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction L in state State-A
In  State-A moving L
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isL
/|\573:    O: O1146 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction L in state State-A
In  State-A moving L
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isL
-/|574:    O: O1148 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction L in state State-A
In  State-A moving L
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isL
\-/575:    O: O1150 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction L in state State-A
In  State-A moving L
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isR
|\-576:    O: O1151 (predict-yes)
I see 1 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction R in state State-A
In  State-A moving R
ENV: (next state, see, prediction correct?) = (State-B, 1, True)
predict error 0
dir: dir isU
/|\577:    O: O1154 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-B
In  State-B moving U
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isR
-/578:    O: O1156 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction R in state State-B
In  State-B moving R
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isR
|\-579:    O: O1158 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction R in state State-B
In  State-B moving R
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isR
/|\580:    O: O1160 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction R in state State-B
In  State-B moving R
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isL
-/581:    O: O1161 (predict-yes)
I see 1 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction L in state State-B
In  State-B moving L
ENV: (next state, see, prediction correct?) = (State-A, 1, True)
predict error 0
dir: dir isR
|582:    O: O1163 (predict-yes)
I see 1 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction R in state State-A
In  State-A moving R
ENV: (next state, see, prediction correct?) = (State-B, 1, True)
predict error 0
dir: dir isU
\-583:    O: O1166 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-B
In  State-B moving U
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isR
/|\584:    O: O1168 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction R in state State-B
In  State-B moving R
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isL
-/|\585:    O: O1169 (predict-yes)
I see 1 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction L in state State-B
In  State-B moving L
ENV: (next state, see, prediction correct?) = (State-A, 1, True)
predict error 0
dir: dir isU
-/|586:    O: O1172 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-A
In  State-A moving U
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isU
\-/587:    O: O1174 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-A
In  State-A moving U
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isR
|\-588:    O: O1175 (predict-yes)
I see 1 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction R in state State-A
In  State-A moving R
ENV: (next state, see, prediction correct?) = (State-B, 1, True)
predict error 0
dir: dir isR
/|\589:    O: O1178 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction R in state State-B
In  State-B moving R
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isR
-/|590:    O: O1180 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction R in state State-B
In  State-B moving R
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isR
\-591:    O: O1182 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction R in state State-B
In  State-B moving R
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isL
/592:    O: O1183 (predict-yes)
I see 1 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction L in state State-B
In  State-B moving L
ENV: (next state, see, prediction correct?) = (State-A, 1, True)
predict error 0
dir: dir isL
|\-593:    O: O1186 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction L in state State-A
In  State-A moving L
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isL
/|\-594:    O: O1188 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction L in state State-A
In  State-A moving L
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isU
/|595:    O: O1190 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-A
In  State-A moving U
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isL
\-/596:    O: O1192 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction L in state State-A
In  State-A moving L
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isR
|\-597:    O: O1193 (predict-yes)
I see 1 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction R in state State-A
In  State-A moving R
ENV: (next state, see, prediction correct?) = (State-B, 1, True)
predict error 0
dir: dir isL
/|\598:    O: O1195 (predict-yes)
I see 1 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction L in state State-B
In  State-B moving L
ENV: (next state, see, prediction correct?) = (State-A, 1, True)
predict error 0
dir: dir isL
-/|599:    O: O1198 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction L in state State-A
In  State-A moving L
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isL
\-600:    O: O1200 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction L in state State-A
In  State-A moving L
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isR
/|\601:    O: O1201 (predict-yes)
I see 1 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction R in state State-A
In  State-A moving R
ENV: (next state, see, prediction correct?) = (State-B, 1, True)
predict error 0
dir: dir isL
-602:    O: O1203 (predict-yes)
I see 1 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction L in state State-B
In  State-B moving L
ENV: (next state, see, prediction correct?) = (State-A, 1, True)
predict error 0
dir: dir isL
/|\-603:    O: O1206 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction L in state State-A
In  State-A moving L
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isL
/|604:    O: O1208 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction L in state State-A
In  State-A moving L
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isL
\-/605:    O: O1210 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction L in state State-A
In  State-A moving L
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isR
|\-/606:    O: O1211 (predict-yes)
I see 1 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction R in state State-A
In  State-A moving R
ENV: (next state, see, prediction correct?) = (State-B, 1, True)
predict error 0
dir: dir isL
|\607:    O: O1213 (predict-yes)
I see 1 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction L in state State-B
In  State-B moving L
ENV: (next state, see, prediction correct?) = (State-A, 1, True)
predict error 0
dir: dir isL
-/|608:    O: O1216 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction L in state State-A
In  State-A moving L
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isR
\-/609:    O: O1217 (predict-yes)
I see 1 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction R in state State-A
In  State-A moving R
ENV: (next state, see, prediction correct?) = (State-B, 1, True)
predict error 0
dir: dir isR
|\610:    O: O1220 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction R in state State-B
In  State-B moving R
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isU
-/|611:    O: O1222 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-B
In  State-B moving U
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isL
\612:    O: O1223 (predict-yes)
I see 1 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction L in state State-B
In  State-B moving L
ENV: (next state, see, prediction correct?) = (State-A, 1, True)
predict error 0
dir: dir isR
-/|613:    O: O1225 (predict-yes)
I see 1 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction R in state State-A
In  State-A moving R
ENV: (next state, see, prediction correct?) = (State-B, 1, True)
predict error 0
dir: dir isR
\-/614:    O: O1228 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction R in state State-B
In  State-B moving R
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isL
|\-615:    O: O1229 (predict-yes)
I see 1 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction L in state State-B
In  State-B moving L
ENV: (next state, see, prediction correct?) = (State-A, 1, True)
predict error 0
dir: dir isU
/|\616:    O: O1232 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-A
In  State-A moving U
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isL
-/|617:    O: O1234 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction L in state State-A
In  State-A moving L
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isL
\-618:    O: O1236 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction L in state State-A
In  State-A moving L
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isR
/|619:    O: O1237 (predict-yes)
I see 1 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction R in state State-A
In  State-A moving R
ENV: (next state, see, prediction correct?) = (State-B, 1, True)
predict error 0
dir: dir isL
\-/620:    O: O1239 (predict-yes)
I see 1 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction L in state State-B
In  State-B moving L
ENV: (next state, see, prediction correct?) = (State-A, 1, True)
predict error 0
dir: dir isR
|\-621:    O: O1241 (predict-yes)
I see 1 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction R in state State-A
In  State-A moving R
ENV: (next state, see, prediction correct?) = (State-B, 1, True)
predict error 0
dir: dir isR
/622:    O: O1244 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction R in state State-B
In  State-B moving R
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isL
|\623:    O: O1245 (predict-yes)
I see 1 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction L in state State-B
In  State-B moving L
ENV: (next state, see, prediction correct?) = (State-A, 1, True)
predict error 0
dir: dir isL
-/624:    O: O1248 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction L in state State-A
In  State-A moving L
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isU
|\625:    O: O1250 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-A
In  State-A moving U
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isL
-/|626:    O: O1252 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction L in state State-A
In  State-A moving L
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isU
\-627:    O: O1254 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-A
In  State-A moving U
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isR
/|\628:    O: O1255 (predict-yes)
I see 1 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction R in state State-A
In  State-A moving R
ENV: (next state, see, prediction correct?) = (State-B, 1, True)
predict error 0
dir: dir isU
-/|\629:    O: O1258 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-B
In  State-B moving U
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isL
-/630:    O: O1259 (predict-yes)
I see 1 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction L in state State-B
In  State-B moving L
ENV: (next state, see, prediction correct?) = (State-A, 1, True)
predict error 0
dir: dir isL
|\631:    O: O1262 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction L in state State-A
In  State-A moving L
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isL
-632:    O: O1264 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction L in state State-A
In  State-A moving L
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isU
/|\633:    O: O1266 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-A
In  State-A moving U
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isR
-/|\634:    O: O1267 (predict-yes)
I see 1 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction R in state State-A
In  State-A moving R
ENV: (next state, see, prediction correct?) = (State-B, 1, True)
predict error 0
dir: dir isR
-/|\635:    O: O1270 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction R in state State-B
In  State-B moving R
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isL
-/636:    O: O1271 (predict-yes)
I see 1 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction L in state State-B
In  State-B moving L
ENV: (next state, see, prediction correct?) = (State-A, 1, True)
predict error 0
dir: dir isU
|\-637:    O: O1274 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-A
In  State-A moving U
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isU
/|638:    O: O1276 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-A
In  State-A moving U
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isR
\-/639:    O: O1277 (predict-yes)
I see 1 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction R in state State-A
In  State-A moving R
ENV: (next state, see, prediction correct?) = (State-B, 1, True)
predict error 0
dir: dir isL
|\-640:    O: O1279 (predict-yes)
I see 1 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction L in state State-B
In  State-B moving L
ENV: (next state, see, prediction correct?) = (State-A, 1, True)
predict error 0
dir: dir isL
/|\641:    O: O1282 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction L in state State-A
In  State-A moving L
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isL
-642:    O: O1284 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction L in state State-A
In  State-A moving L
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isL
/|\643:    O: O1286 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction L in state State-A
In  State-A moving L
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isL
-/644:    O: O1288 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction L in state State-A
In  State-A moving L
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isL
|\-645:    O: O1290 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction L in state State-A
In  State-A moving L
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isR
/|\646:    O: O1291 (predict-yes)
I see 1 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction R in state State-A
In  State-A moving R
ENV: (next state, see, prediction correct?) = (State-B, 1, True)
predict error 0
dir: dir isU
-/|647:    O: O1294 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-B
In  State-B moving U
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isL
\-/648:    O: O1295 (predict-yes)
I see 1 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction L in state State-B
In  State-B moving L
ENV: (next state, see, prediction correct?) = (State-A, 1, True)
predict error 0
dir: dir isU
|\-649:    O: O1298 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-A
In  State-A moving U
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isR
/|\650:    O: O1299 (predict-yes)
I see 1 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction R in state State-A
In  State-A moving R
ENV: (next state, see, prediction correct?) = (State-B, 1, True)
predict error 0
dir: dir isU
-/|651:    O: O1302 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-B
In  State-B moving U
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isU
\652:    O: O1304 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-B
In  State-B moving U
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isU
-/653:    O: O1306 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-B
In  State-B moving U
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isL
|\654:    O: O1307 (predict-yes)
I see 1 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction L in state State-B
In  State-B moving L
ENV: (next state, see, prediction correct?) = (State-A, 1, True)
predict error 0
dir: dir isL
-/655:    O: O1310 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction L in state State-A
In  State-A moving L
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isR
|656:    O: O1311 (predict-yes)
I see 1 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction R in state State-A
In  State-A moving R
ENV: (next state, see, prediction correct?) = (State-B, 1, True)
predict error 0
dir: dir isU
\-/657:    O: O1314 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-B
In  State-B moving U
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isL
|\-658:    O: O1315 (predict-yes)
I see 1 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction L in state State-B
In  State-B moving L
ENV: (next state, see, prediction correct?) = (State-A, 1, True)
predict error 0
dir: dir isL
/|\659:    O: O1318 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction L in state State-A
In  State-A moving L
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isU
-/|660:    O: O1320 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-A
In  State-A moving U
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isL
\-/661:    O: O1322 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction L in state State-A
In  State-A moving L
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isR
|662:    O: O1323 (predict-yes)
I see 1 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction R in state State-A
In  State-A moving R
ENV: (next state, see, prediction correct?) = (State-B, 1, True)
predict error 0
dir: dir isR
\-/663:    O: O1326 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction R in state State-B
In  State-B moving R
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isU
|664:    O: O1328 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-B
In  State-B moving U
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isU
\-/665:    O: O1330 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-B
In  State-B moving U
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isL
|666:    O: O1331 (predict-yes)
I see 1 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction L in state State-B
In  State-B moving L
ENV: (next state, see, prediction correct?) = (State-A, 1, True)
predict error 0
dir: dir isU
\-/667:    O: O1334 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-A
In  State-A moving U
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isU
|\668:    O: O1336 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-A
In  State-A moving U
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isU
-669:    O: O1338 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-A
In  State-A moving U
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isR
/|\670:    O: O1339 (predict-yes)
I see 1 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction R in state State-A
In  State-A moving R
ENV: (next state, see, prediction correct?) = (State-B, 1, True)
predict error 0
dir: dir isU
-/|671:    O: O1342 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-B
In  State-B moving U
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isR
\672:    O: O1344 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction R in state State-B
In  State-B moving R
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isR
-/|673:    O: O1346 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction R in state State-B
In  State-B moving R
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isL
\-/674:    O: O1347 (predict-yes)
I see 1 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction L in state State-B
In  State-B moving L
ENV: (next state, see, prediction correct?) = (State-A, 1, True)
predict error 0
dir: dir isU
|\-675:    O: O1350 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-A
In  State-A moving U
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isR
/|\676:    O: O1351 (predict-yes)
I see 1 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction R in state State-A
In  State-A moving R
ENV: (next state, see, prediction correct?) = (State-B, 1, True)
predict error 0
dir: dir isL
-/|\677:    O: O1353 (predict-yes)
I see 1 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction L in state State-B
In  State-B moving L
ENV: (next state, see, prediction correct?) = (State-A, 1, True)
predict error 0
dir: dir isL
-/678:    O: O1356 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction L in state State-A
In  State-A moving L
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isU
|\-679:    O: O1358 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-A
In  State-A moving U
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isR
/|\680:    O: O1359 (predict-yes)
I see 1 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction R in state State-A
In  State-A moving R
ENV: (next state, see, prediction correct?) = (State-B, 1, True)
predict error 0
dir: dir isU
-/|681:    O: O1362 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-B
In  State-B moving U
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isR
\682:    O: O1364 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction R in state State-B
In  State-B moving R
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isR
-/|683:    O: O1366 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction R in state State-B
In  State-B moving R
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isL
\-/684:    O: O1367 (predict-yes)
I see 1 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction L in state State-B
In  State-B moving L
ENV: (next state, see, prediction correct?) = (State-A, 1, True)
predict error 0
dir: dir isU
|\-685:    O: O1370 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-A
In  State-A moving U
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isL
/|\686:    O: O1372 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction L in state State-A
In  State-A moving L
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isR
-/|687:    O: O1373 (predict-yes)
I see 1 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction R in state State-A
In  State-A moving R
ENV: (next state, see, prediction correct?) = (State-B, 1, True)
predict error 0
dir: dir isU
\-688:    O: O1376 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-B
In  State-B moving U
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isU
/|689:    O: O1378 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-B
In  State-B moving U
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isL
\-/690:    O: O1379 (predict-yes)
I see 1 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction L in state State-B
In  State-B moving L
ENV: (next state, see, prediction correct?) = (State-A, 1, True)
predict error 0
dir: dir isL
|\-/691:    O: O1382 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction L in state State-A
In  State-A moving L
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isU
|692:    O: O1384 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-A
In  State-A moving U
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isR
\-693:    O: O1385 (predict-yes)
I see 1 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction R in state State-A
In  State-A moving R
ENV: (next state, see, prediction correct?) = (State-B, 1, True)
predict error 0
dir: dir isU
/|694:    O: O1388 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-B
In  State-B moving U
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isU
\-695:    O: O1390 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-B
In  State-B moving U
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isR
/|\696:    O: O1392 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction R in state State-B
In  State-B moving R
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isU
-/|697:    O: O1394 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-B
In  State-B moving U
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isU
\-/698:    O: O1396 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-B
In  State-B moving U
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isR
|\-/699:    O: O1398 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction R in state State-B
In  State-B moving R
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isR
|\-700:    O: O1400 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction R in state State-B
In  State-B moving R
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isL
/|701:    O: O1401 (predict-yes)
I see 1 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction L in state State-B
In  State-B moving L
ENV: (next state, see, prediction correct?) = (State-A, 1, True)
predict error 0
dir: dir isR
\702:    O: O1403 (predict-yes)
I see 1 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction R in state State-A
In  State-A moving R
ENV: (next state, see, prediction correct?) = (State-B, 1, True)
predict error 0
dir: dir isU
-/|703:    O: O1406 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-B
In  State-B moving U
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isL
\-/704:    O: O1407 (predict-yes)
I see 1 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction L in state State-B
In  State-B moving L
ENV: (next state, see, prediction correct?) = (State-A, 1, True)
predict error 0
dir: dir isR
|\705:    O: O1409 (predict-yes)
I see 1 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction R in state State-A
In  State-A moving R
ENV: (next state, see, prediction correct?) = (State-B, 1, True)
predict error 0
dir: dir isL
-/706:    O: O1411 (predict-yes)
I see 1 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction L in state State-B
In  State-B moving L
ENV: (next state, see, prediction correct?) = (State-A, 1, True)
predict error 0
dir: dir isL
|\-707:    O: O1414 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction L in state State-A
In  State-A moving L
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isR
/|708:    O: O1415 (predict-yes)
I see 1 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction R in state State-A
In  State-A moving R
ENV: (next state, see, prediction correct?) = (State-B, 1, True)
predict error 0
dir: dir isL
\-/709:    O: O1417 (predict-yes)
I see 1 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction L in state State-B
In  State-B moving L
ENV: (next state, see, prediction correct?) = (State-A, 1, True)
predict error 0
dir: dir isL
|\-710:    O: O1420 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction L in state State-A
In  State-A moving L
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isL
/|\711:    O: O1422 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction L in state State-A
In  State-A moving L
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isR
-712:    O: O1423 (predict-yes)
I see 1 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction R in state State-A
In  State-A moving R
ENV: (next state, see, prediction correct?) = (State-B, 1, True)
predict error 0
dir: dir isR
/|713:    O: O1426 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction R in state State-B
In  State-B moving R
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isL
\-/714:    O: O1427 (predict-yes)
I see 1 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction L in state State-B
In  State-B moving L
ENV: (next state, see, prediction correct?) = (State-A, 1, True)
predict error 0
dir: dir isL
|\-715:    O: O1430 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction L in state State-A
In  State-A moving L
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isU
/|716:    O: O1432 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-A
In  State-A moving U
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isL
\-717:    O: O1434 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction L in state State-A
In  State-A moving L
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isR
/|\-718:    O: O1435 (predict-yes)
I see 1 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction R in state State-A
In  State-A moving R
ENV: (next state, see, prediction correct?) = (State-B, 1, True)
predict error 0
dir: dir isR
/|\719:    O: O1438 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction R in state State-B
In  State-B moving R
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isU
-/720:    O: O1440 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-B
In  State-B moving U
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isR
|\-721:    O: O1442 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction R in state State-B
In  State-B moving R
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isU
/722:    O: O1444 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-B
In  State-B moving U
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isR
|\723:    O: O1446 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction R in state State-B
In  State-B moving R
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isL
-/724:    O: O1447 (predict-yes)
I see 1 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction L in state State-B
In  State-B moving L
ENV: (next state, see, prediction correct?) = (State-A, 1, True)
predict error 0
dir: dir isL
|\-725:    O: O1450 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction L in state State-A
In  State-A moving L
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isL
/|726:    O: O1452 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction L in state State-A
In  State-A moving L
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isU
\-/727:    O: O1454 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-A
In  State-A moving U
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isL
|\-/728:    O: O1456 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction L in state State-A
In  State-A moving L
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isL
|\729:    O: O1458 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction L in state State-A
In  State-A moving L
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isU
-/|730:    O: O1460 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-A
In  State-A moving U
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isL
\-731:    O: O1462 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction L in state State-A
In  State-A moving L
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isU
/732:    O: O1464 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-A
In  State-A moving U
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isL
|\733:    O: O1466 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction L in state State-A
In  State-A moving L
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isR
-/734:    O: O1467 (predict-yes)
I see 1 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction R in state State-A
In  State-A moving R
ENV: (next state, see, prediction correct?) = (State-B, 1, True)
predict error 0
dir: dir isL
|\-735:    O: O1469 (predict-yes)
I see 1 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction L in state State-B
In  State-B moving L
ENV: (next state, see, prediction correct?) = (State-A, 1, True)
predict error 0
dir: dir isU
/|\736:    O: O1472 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-A
In  State-A moving U
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isR
-737:    O: O1473 (predict-yes)
I see 1 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction R in state State-A
In  State-A moving R
ENV: (next state, see, prediction correct?) = (State-B, 1, True)
predict error 0
dir: dir isR
/|\738:    O: O1476 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction R in state State-B
In  State-B moving R
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isU
-/|739:    O: O1478 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-B
In  State-B moving U
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isU
\-740:    O: O1480 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-B
In  State-B moving U
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isR
/|741:    O: O1482 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction R in state State-B
In  State-B moving R
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isR
\742:    O: O1484 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction R in state State-B
In  State-B moving R
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isR
-/743:    O: O1486 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction R in state State-B
In  State-B moving R
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isL
|\744:    O: O1487 (predict-yes)
I see 1 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction L in state State-B
In  State-B moving L
ENV: (next state, see, prediction correct?) = (State-A, 1, True)
predict error 0
dir: dir isU
-/|745:    O: O1490 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-A
In  State-A moving U
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isR
\-746:    O: O1491 (predict-yes)
I see 1 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction R in state State-A
In  State-A moving R
ENV: (next state, see, prediction correct?) = (State-B, 1, True)
predict error 0
dir: dir isU
/|\747:    O: O1494 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-B
In  State-B moving U
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isL
-/|748:    O: O1495 (predict-yes)
I see 1 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction L in state State-B
In  State-B moving L
ENV: (next state, see, prediction correct?) = (State-A, 1, True)
predict error 0
dir: dir isR
\-/749:    O: O1497 (predict-yes)
I see 1 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction R in state State-A
In  State-A moving R
ENV: (next state, see, prediction correct?) = (State-B, 1, True)
predict error 0
dir: dir isR
|\-750:    O: O1500 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction R in state State-B
In  State-B moving R
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isU
/|\751:    O: O1502 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-B
In  State-B moving U
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isL
-752:    O: O1503 (predict-yes)
I see 1 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction L in state State-B
In  State-B moving L
ENV: (next state, see, prediction correct?) = (State-A, 1, True)
predict error 0
dir: dir isR
/|\753:    O: O1505 (predict-yes)
I see 1 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction R in state State-A
In  State-A moving R
ENV: (next state, see, prediction correct?) = (State-B, 1, True)
predict error 0
dir: dir isR
-/|754:    O: O1508 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction R in state State-B
In  State-B moving R
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isL
\-755:    O: O1509 (predict-yes)
I see 1 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction L in state State-B
In  State-B moving L
ENV: (next state, see, prediction correct?) = (State-A, 1, True)
predict error 0
dir: dir isR
/|\756:    O: O1511 (predict-yes)
I see 1 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction R in state State-A
In  State-A moving R
ENV: (next state, see, prediction correct?) = (State-B, 1, True)
predict error 0
dir: dir isU
-/|757:    O: O1514 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-B
In  State-B moving U
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isR
\-/|758:    O: O1516 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction R in state State-B
In  State-B moving R
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isR
\-/759:    O: O1518 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction R in state State-B
In  State-B moving R
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isR
|\760:    O: O1520 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction R in state State-B
In  State-B moving R
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isL
-/|761:    O: O1521 (predict-yes)
I see 1 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction L in state State-B
In  State-B moving L
ENV: (next state, see, prediction correct?) = (State-A, 1, True)
predict error 0
dir: dir isR
\762:    O: O1523 (predict-yes)
I see 1 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction R in state State-A
In  State-A moving R
ENV: (next state, see, prediction correct?) = (State-B, 1, True)
predict error 0
dir: dir isU
-/|\763:    O: O1526 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-B
In  State-B moving U
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isR
-/|764:    O: O1528 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction R in state State-B
In  State-B moving R
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isR
\-/765:    O: O1530 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction R in state State-B
In  State-B moving R
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isL
|\-766:    O: O1531 (predict-yes)
I see 1 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction L in state State-B
In  State-B moving L
ENV: (next state, see, prediction correct?) = (State-A, 1, True)
predict error 0
dir: dir isL
/|767:    O: O1534 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction L in state State-A
In  State-A moving L
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isL
\-/768:    O: O1536 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction L in state State-A
In  State-A moving L
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isU
|\769:    O: O1538 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-A
In  State-A moving U
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isU
-/770:    O: O1540 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-A
In  State-A moving U
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isU
|\-771:    O: O1542 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-A
In  State-A moving U
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isU
/772:    O: O1544 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-A
In  State-A moving U
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isR
|\-773:    O: O1545 (predict-yes)
I see 1 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction R in state State-A
In  State-A moving R
ENV: (next state, see, prediction correct?) = (State-B, 1, True)
predict error 0
dir: dir isU
/|\774:    O: O1548 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-B
In  State-B moving U
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isR
-/|775:    O: O1550 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction R in state State-B
In  State-B moving R
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isR
\-/776:    O: O1552 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction R in state State-B
In  State-B moving R
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isU
|\-777:    O: O1554 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-B
In  State-B moving U
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isU
/|\778:    O: O1556 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-B
In  State-B moving U
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isU
-/779:    O: O1558 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-B
In  State-B moving U
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isR
|\780:    O: O1560 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction R in state State-B
In  State-B moving R
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isU
-/|\781:    O: O1562 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-B
In  State-B moving U
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isR
-782:    O: O1564 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction R in state State-B
In  State-B moving R
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isU
/783:    O: O1566 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-B
In  State-B moving U
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isU
|\-784:    O: O1568 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-B
In  State-B moving U
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isL
/|\785:    O: O1569 (predict-yes)
I see 1 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction L in state State-B
In  State-B moving L
ENV: (next state, see, prediction correct?) = (State-A, 1, True)
predict error 0
dir: dir isU
-/|\786:    O: O1572 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-A
In  State-A moving U
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isL
-/|787:    O: O1574 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction L in state State-A
In  State-A moving L
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isL
\-788:    O: O1576 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction L in state State-A
In  State-A moving L
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isU
/|\789:    O: O1578 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-A
In  State-A moving U
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isL
-/|790:    O: O1580 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction L in state State-A
In  State-A moving L
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isR
\-791:    O: O1581 (predict-yes)
I see 1 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction R in state State-A
In  State-A moving R
ENV: (next state, see, prediction correct?) = (State-B, 1, True)
predict error 0
dir: dir isR
/792:    O: O1584 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction R in state State-B
In  State-B moving R
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isL
|\793:    O: O1585 (predict-yes)
I see 1 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction L in state State-B
In  State-B moving L
ENV: (next state, see, prediction correct?) = (State-A, 1, True)
predict error 0
dir: dir isU
-/|794:    O: O1588 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-A
In  State-A moving U
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isL
\-/795:    O: O1590 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction L in state State-A
In  State-A moving L
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isR
|\796:    O: O1591 (predict-yes)
I see 1 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction R in state State-A
In  State-A moving R
ENV: (next state, see, prediction correct?) = (State-B, 1, True)
predict error 0
dir: dir isR
-/|797:    O: O1594 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction R in state State-B
In  State-B moving R
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isU
\-/798:    O: O1596 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-B
In  State-B moving U
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isU
|\799:    O: O1598 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-B
In  State-B moving U
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isL
-/|800:    O: O1599 (predict-yes)
I see 1 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction L in state State-B
In  State-B moving L
ENV: (next state, see, prediction correct?) = (State-A, 1, True)
predict error 0
dir: dir isL
\-/801:    O: O1602 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction L in state State-A
In  State-A moving L
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isL
|802:    O: O1604 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction L in state State-A
In  State-A moving L
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isR
\-/803:    O: O1605 (predict-yes)
I see 1 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction R in state State-A
In  State-A moving R
ENV: (next state, see, prediction correct?) = (State-B, 1, True)
predict error 0
dir: dir isL
|\-804:    O: O1607 (predict-yes)
I see 1 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction L in state State-B
In  State-B moving L
ENV: (next state, see, prediction correct?) = (State-A, 1, True)
predict error 0
dir: dir isL
/|\805:    O: O1610 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction L in state State-A
In  State-A moving L
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isU
-/806:    O: O1612 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-A
In  State-A moving U
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isU
|\-807:    O: O1614 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-A
In  State-A moving U
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isU
/|\808:    O: O1616 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-A
In  State-A moving U
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isU
-/|809:    O: O1618 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-A
In  State-A moving U
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isU
\-/810:    O: O1620 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-A
In  State-A moving U
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isR
|\811:    O: O1621 (predict-yes)
I see 1 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction R in state State-A
In  State-A moving R
ENV: (next state, see, prediction correct?) = (State-B, 1, True)
predict error 0
dir: dir isL
-812:    O: O1623 (predict-yes)
I see 1 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction L in state State-B
In  State-B moving L
ENV: (next state, see, prediction correct?) = (State-A, 1, True)
predict error 0
dir: dir isL
/|\813:    O: O1626 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction L in state State-A
In  State-A moving L
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isR
-/|814:    O: O1627 (predict-yes)
I see 1 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction R in state State-A
In  State-A moving R
ENV: (next state, see, prediction correct?) = (State-B, 1, True)
predict error 0
dir: dir isR
\-815:    O: O1630 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction R in state State-B
In  State-B moving R
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isR
/|\816:    O: O1632 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction R in state State-B
In  State-B moving R
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isR
-/817:    O: O1634 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction R in state State-B
In  State-B moving R
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isU
|\-818:    O: O1636 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-B
In  State-B moving U
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isL
/|819:    O: O1637 (predict-yes)
I see 1 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction L in state State-B
In  State-B moving L
ENV: (next state, see, prediction correct?) = (State-A, 1, True)
predict error 0
dir: dir isR
\820:    O: O1639 (predict-yes)
I see 1 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction R in state State-A
In  State-A moving R
ENV: (next state, see, prediction correct?) = (State-B, 1, True)
predict error 0
dir: dir isU
-/|821:    O: O1642 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-B
In  State-B moving U
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isU
\822:    O: O1644 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-B
In  State-B moving U
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isL
-/|823:    O: O1645 (predict-yes)
I see 1 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction L in state State-B
In  State-B moving L
ENV: (next state, see, prediction correct?) = (State-A, 1, True)
predict error 0
dir: dir isL
\-824:    O: O1648 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction L in state State-A
In  State-A moving L
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isU
/|\-825:    O: O1650 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-A
In  State-A moving U
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isL
/|826:    O: O1652 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction L in state State-A
In  State-A moving L
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isL
\-/827:    O: O1654 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction L in state State-A
In  State-A moving L
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isR
|\-828:    O: O1655 (predict-yes)
I see 1 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction R in state State-A
In  State-A moving R
ENV: (next state, see, prediction correct?) = (State-B, 1, True)
predict error 0
dir: dir isR
/|829:    O: O1658 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction R in state State-B
In  State-B moving R
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isL
\-/830:    O: O1659 (predict-yes)
I see 1 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction L in state State-B
In  State-B moving L
ENV: (next state, see, prediction correct?) = (State-A, 1, True)
predict error 0
dir: dir isL
|\-831:    O: O1662 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction L in state State-A
In  State-A moving L
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isL
/832:    O: O1664 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction L in state State-A
In  State-A moving L
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isU
|833:    O: O1666 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-A
In  State-A moving U
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isR
\-/834:    O: O1667 (predict-yes)
I see 1 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction R in state State-A
In  State-A moving R
ENV: (next state, see, prediction correct?) = (State-B, 1, True)
predict error 0
dir: dir isU
|\-835:    O: O1670 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-B
In  State-B moving U
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isU
/|\836:    O: O1672 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-B
In  State-B moving U
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isU
-/|837:    O: O1674 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-B
In  State-B moving U
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isL
\-838:    O: O1675 (predict-yes)
I see 1 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction L in state State-B
In  State-B moving L
ENV: (next state, see, prediction correct?) = (State-A, 1, True)
predict error 0
dir: dir isL
/|\839:    O: O1678 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction L in state State-A
In  State-A moving L
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isL
-/|\840:    O: O1680 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction L in state State-A
In  State-A moving L
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isR
-/|841:    O: O1681 (predict-yes)
I see 1 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction R in state State-A
In  State-A moving R
ENV: (next state, see, prediction correct?) = (State-B, 1, True)
predict error 0
dir: dir isR
\842:    O: O1684 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction R in state State-B
In  State-B moving R
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isL
-/843:    O: O1685 (predict-yes)
I see 1 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction L in state State-B
In  State-B moving L
ENV: (next state, see, prediction correct?) = (State-A, 1, True)
predict error 0
dir: dir isR
|\-844:    O: O1687 (predict-yes)
I see 1 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction R in state State-A
In  State-A moving R
ENV: (next state, see, prediction correct?) = (State-B, 1, True)
predict error 0
dir: dir isL
/|\845:    O: O1689 (predict-yes)
I see 1 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction L in state State-B
In  State-B moving L
ENV: (next state, see, prediction correct?) = (State-A, 1, True)
predict error 0
dir: dir isL
-/|846:    O: O1692 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction L in state State-A
In  State-A moving L
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isL
\-847:    O: O1694 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction L in state State-A
In  State-A moving L
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isU
/|\848:    O: O1696 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-A
In  State-A moving U
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isR
-/849:    O: O1697 (predict-yes)
I see 1 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction R in state State-A
In  State-A moving R
ENV: (next state, see, prediction correct?) = (State-B, 1, True)
predict error 0
dir: dir isL
|\-/850:    O: O1699 (predict-yes)
I see 1 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction L in state State-B
In  State-B moving L
ENV: (next state, see, prediction correct?) = (State-A, 1, True)
predict error 0
dir: dir isL
|\-851:    O: O1702 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction L in state State-A
In  State-A moving L
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isR
/852:    O: O1703 (predict-yes)
I see 1 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction R in state State-A
In  State-A moving R
ENV: (next state, see, prediction correct?) = (State-B, 1, True)
predict error 0
dir: dir isR
|\853:    O: O1706 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction R in state State-B
In  State-B moving R
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isU
-/|854:    O: O1708 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-B
In  State-B moving U
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isU
\-/855:    O: O1710 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-B
In  State-B moving U
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isU
|\-856:    O: O1712 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-B
In  State-B moving U
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isL
/|\857:    O: O1713 (predict-yes)
I see 1 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction L in state State-B
In  State-B moving L
ENV: (next state, see, prediction correct?) = (State-A, 1, True)
predict error 0
dir: dir isL
-/858:    O: O1716 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction L in state State-A
In  State-A moving L
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isU
|\-859:    O: O1718 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-A
In  State-A moving U
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isU
/|\860:    O: O1720 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-A
In  State-A moving U
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isR
-/|861:    O: O1721 (predict-yes)
I see 1 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction R in state State-A
In  State-A moving R
ENV: (next state, see, prediction correct?) = (State-B, 1, True)
predict error 0
dir: dir isU
\862:    O: O1724 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-B
In  State-B moving U
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isR
-/|863:    O: O1726 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction R in state State-B
In  State-B moving R
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isL
\-/864:    O: O1727 (predict-yes)
I see 1 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction L in state State-B
In  State-B moving L
ENV: (next state, see, prediction correct?) = (State-A, 1, True)
predict error 0
dir: dir isL
|\-865:    O: O1730 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction L in state State-A
In  State-A moving L
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isL
/|866:    O: O1732 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction L in state State-A
In  State-A moving L
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isR
\-867:    O: O1733 (predict-yes)
I see 1 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction R in state State-A
In  State-A moving R
ENV: (next state, see, prediction correct?) = (State-B, 1, True)
predict error 0
dir: dir isU
/|\868:    O: O1736 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-B
In  State-B moving U
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isU
-/|869:    O: O1738 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-B
In  State-B moving U
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isR
\-870:    O: O1740 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction R in state State-B
In  State-B moving R
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isR
/|\871:    O: O1742 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction R in state State-B
In  State-B moving R
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isU
-872:    O: O1744 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-B
In  State-B moving U
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isU
/|873:    O: O1746 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-B
In  State-B moving U
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isR
\-/874:    O: O1748 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction R in state State-B
In  State-B moving R
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isR
|\-875:    O: O1750 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction R in state State-B
In  State-B moving R
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isR
/|\876:    O: O1752 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction R in state State-B
In  State-B moving R
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isL
-/|877:    O: O1753 (predict-yes)
I see 1 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction L in state State-B
In  State-B moving L
ENV: (next state, see, prediction correct?) = (State-A, 1, True)
predict error 0
dir: dir isL
\-/878:    O: O1756 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction L in state State-A
In  State-A moving L
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isU
|\-879:    O: O1758 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-A
In  State-A moving U
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isU
/|880:    O: O1760 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-A
In  State-A moving U
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isR
\-881:    O: O1761 (predict-yes)
I see 1 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction R in state State-A
In  State-A moving R
ENV: (next state, see, prediction correct?) = (State-B, 1, True)
predict error 0
dir: dir isR
/882:    O: O1764 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction R in state State-B
In  State-B moving R
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isR
|\-883:    O: O1766 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction R in state State-B
In  State-B moving R
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isR
/|\884:    O: O1768 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction R in state State-B
In  State-B moving R
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isU
-/|885:    O: O1770 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-B
In  State-B moving U
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isR
\-886:    O: O1772 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction R in state State-B
In  State-B moving R
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isU
/|887:    O: O1774 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-B
In  State-B moving U
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isL
\-/888:    O: O1775 (predict-yes)
I see 1 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction L in state State-B
In  State-B moving L
ENV: (next state, see, prediction correct?) = (State-A, 1, True)
predict error 0
dir: dir isL
|\-889:    O: O1778 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction L in state State-A
In  State-A moving L
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isR
/|\890:    O: O1779 (predict-yes)
I see 1 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction R in state State-A
In  State-A moving R
ENV: (next state, see, prediction correct?) = (State-B, 1, True)
predict error 0
dir: dir isR
-/|891:    O: O1782 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction R in state State-B
In  State-B moving R
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isU
\892:    O: O1784 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-B
In  State-B moving U
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isU
-/|893:    O: O1786 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-B
In  State-B moving U
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isU
\-/894:    O: O1788 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-B
In  State-B moving U
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isR
|\895:    O: O1790 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction R in state State-B
In  State-B moving R
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isL
-/|896:    O: O1791 (predict-yes)
I see 1 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction L in state State-B
In  State-B moving L
ENV: (next state, see, prediction correct?) = (State-A, 1, True)
predict error 0
dir: dir isR
\-897:    O: O1793 (predict-yes)
I see 1 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction R in state State-A
In  State-A moving R
ENV: (next state, see, prediction correct?) = (State-B, 1, True)
predict error 0
dir: dir isR
/|\898:    O: O1796 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction R in state State-B
In  State-B moving R
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isR
-/|899:    O: O1798 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction R in state State-B
In  State-B moving R
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isL
\-/900:    O: O1799 (predict-yes)
I see 1 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction L in state State-B
In  State-B moving L
ENV: (next state, see, prediction correct?) = (State-A, 1, True)
predict error 0
dir: dir isU
|\-901:    O: O1802 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-A
In  State-A moving U
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isU
/902:    O: O1804 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-A
In  State-A moving U
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isL
|\-903:    O: O1806 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction L in state State-A
In  State-A moving L
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isU
/|904:    O: O1808 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-A
In  State-A moving U
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isR
\-/905:    O: O1809 (predict-yes)
I see 1 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction R in state State-A
In  State-A moving R
ENV: (next state, see, prediction correct?) = (State-B, 1, True)
predict error 0
dir: dir isR
|\906:    O: O1812 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction R in state State-B
In  State-B moving R
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isU
-/|907:    O: O1814 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-B
In  State-B moving U
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isU
\-/908:    O: O1816 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-B
In  State-B moving U
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isR
|\909:    O: O1818 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction R in state State-B
In  State-B moving R
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isL
-/|910:    O: O1819 (predict-yes)
I see 1 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction L in state State-B
In  State-B moving L
ENV: (next state, see, prediction correct?) = (State-A, 1, True)
predict error 0
dir: dir isU
\-/911:    O: O1822 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-A
In  State-A moving U
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isL
|912:    O: O1824 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction L in state State-A
In  State-A moving L
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isR
\-913:    O: O1825 (predict-yes)
I see 1 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction R in state State-A
In  State-A moving R
ENV: (next state, see, prediction correct?) = (State-B, 1, True)
predict error 0
dir: dir isU
/|914:    O: O1828 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-B
In  State-B moving U
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isL
\-/915:    O: O1829 (predict-yes)
I see 1 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction L in state State-B
In  State-B moving L
ENV: (next state, see, prediction correct?) = (State-A, 1, True)
predict error 0
dir: dir isL
|\916:    O: O1832 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction L in state State-A
In  State-A moving L
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isU
-/|\917:    O: O1834 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-A
In  State-A moving U
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isU
-/918:    O: O1836 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-A
In  State-A moving U
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isL
|919:    O: O1838 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction L in state State-A
In  State-A moving L
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isR
\-/920:    O: O1839 (predict-yes)
I see 1 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction R in state State-A
In  State-A moving R
ENV: (next state, see, prediction correct?) = (State-B, 1, True)
predict error 0
dir: dir isL
|\-921:    O: O1841 (predict-yes)
I see 1 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction L in state State-B
In  State-B moving L
ENV: (next state, see, prediction correct?) = (State-A, 1, True)
predict error 0
dir: dir isL
/922:    O: O1844 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction L in state State-A
In  State-A moving L
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isL
|\923:    O: O1846 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction L in state State-A
In  State-A moving L
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isU
-/|924:    O: O1848 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-A
In  State-A moving U
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isL
\-/925:    O: O1850 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction L in state State-A
In  State-A moving L
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isL
|\926:    O: O1852 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction L in state State-A
In  State-A moving L
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isL
-/|927:    O: O1854 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction L in state State-A
In  State-A moving L
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isL
\-/928:    O: O1856 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction L in state State-A
In  State-A moving L
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isR
|\-929:    O: O1857 (predict-yes)
I see 1 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction R in state State-A
In  State-A moving R
ENV: (next state, see, prediction correct?) = (State-B, 1, True)
predict error 0
dir: dir isU
/|\930:    O: O1860 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-B
In  State-B moving U
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isU
-/|931:    O: O1862 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-B
In  State-B moving U
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isR
\932:    O: O1864 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction R in state State-B
In  State-B moving R
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isU
-/933:    O: O1866 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-B
In  State-B moving U
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isL
|\934:    O: O1867 (predict-yes)
I see 1 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction L in state State-B
In  State-B moving L
ENV: (next state, see, prediction correct?) = (State-A, 1, True)
predict error 0
dir: dir isL
-/|935:    O: O1870 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction L in state State-A
In  State-A moving L
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isU
\-/936:    O: O1872 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-A
In  State-A moving U
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isL
|\937:    O: O1874 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction L in state State-A
In  State-A moving L
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isL
-/938:    O: O1876 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction L in state State-A
In  State-A moving L
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isR
|\939:    O: O1877 (predict-yes)
I see 1 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction R in state State-A
In  State-A moving R
ENV: (next state, see, prediction correct?) = (State-B, 1, True)
predict error 0
dir: dir isL
-/940:    O: O1879 (predict-yes)
I see 1 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction L in state State-B
In  State-B moving L
ENV: (next state, see, prediction correct?) = (State-A, 1, True)
predict error 0
dir: dir isR
|\-941:    O: O1881 (predict-yes)
I see 1 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction R in state State-A
In  State-A moving R
ENV: (next state, see, prediction correct?) = (State-B, 1, True)
predict error 0
dir: dir isL
/942:    O: O1883 (predict-yes)
I see 1 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction L in state State-B
In  State-B moving L
ENV: (next state, see, prediction correct?) = (State-A, 1, True)
predict error 0
dir: dir isL
|\-943:    O: O1886 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction L in state State-A
In  State-A moving L
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isU
/|\944:    O: O1888 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-A
In  State-A moving U
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isL
-/945:    O: O1890 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction L in state State-A
In  State-A moving L
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isU
|\-946:    O: O1892 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-A
In  State-A moving U
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isL
/|947:    O: O1894 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction L in state State-A
In  State-A moving L
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isU
\948:    O: O1896 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-A
In  State-A moving U
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isU
-/|949:    O: O1898 (predict-no)
I see 1 and I'm going to do: predict-no
ENV: Agent did: predict-no for direction U in state State-A
In  State-A moving U
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isR
\-/950:    O: O1899 (predict-yes)
I see 1 and I'm going to do: predict-yes
ENV: Agent did: predict-yes for direction R in state State-A
In  State-A moving R
ENV: (next state, see, prediction correct?) = (State-B, 1, True)
predict error 0
dir: dir isL
|\-/|\-/|--- Input Phase --- 
=>WM: (13351: I2 ^dir L)
=>WM: (13350: I2 ^reward 1)
=>WM: (13349: I2 ^see 1)
=>WM: (13348: N950 ^status complete)
<=WM: (13337: I2 ^dir R)
<=WM: (13336: I2 ^reward 1)
<=WM: (13335: I2 ^see 0)
=>WM: (13352: I2 ^level-1 R1-root)
<=WM: (13338: I2 ^level-1 L0-root)

--- END Input Phase --- 

--- Proposal Phase ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing rl*prefer*rvt*predict-yes*H0*1*H1*22
 -->
 (S1 ^operator O1899 = 0.4768760547163575)
Firing rl*prefer*rvt*predict-no*H0*2*H1*10
 -->
 (S1 ^operator O1900 = -0.01194930198035649)
Firing prefer*rvt*predict-no*H0*2*H1
 -->
Firing prefer*rvt*predict-yes*H0*1*H1
 -->
Firing elaborate*copy-see-to-output-link
 -->
 (I3 ^see 1 +)
Firing elaborate*reward*based*on*reward
 -->
 (R954 ^value 1 +)
 (R1 ^reward R954 +)
Firing propose*predict-yes
 -->
 (O1901 ^name predict-yes +)
 (S1 ^operator O1901 +)
Firing propose*predict-no
 -->
 (O1902 ^name predict-no +)
 (S1 ^operator O1902 +)
Firing rl*prefer*rvt*predict-no*H0*2
 -->
 (S1 ^operator O1900 = 0.2550132695707557)
Firing rl*prefer*rvt*predict-yes*H0*1
 -->
 (S1 ^operator O1899 = 0.5231202597544767)
Firing prefer*rvt*predict-yes*H0
 -->
Firing prefer*rvt*predict-no*H0
 -->
Firing elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir L +)
 inner elaboration loop at bottom goal.
Retracting elaborate*copy-see-to-output-link
 -->
 (I3 ^see 0 +)
Retracting propose*predict-no
 -->
 (O1900 ^name predict-no +)
 (S1 ^operator O1900 +)
Retracting propose*predict-yes
 -->
 (O1899 ^name predict-yes +)
 (S1 ^operator O1899 +)
Retracting elaborate*reward*based*on*reward
 -->
 (R953 ^value 1 +)
 (R1 ^reward R953 +)
Retracting elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir R +)
Retracting rl*prefer*rvt*predict-no*H0*4
 -->
 (S1 ^operator O1900 = 0.1269768259493387)
Retracting rl*prefer*rvt*predict-no*H0*4*H1*13
 -->
 (S1 ^operator O1900 = 0.4910065094545203)
Retracting rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O1899 = 0.3829293116822346)
Retracting rl*prefer*rvt*predict-yes*H0*3*H1*14
 -->
 (S1 ^operator O1899 = 0.6170848495907595)
=>WM: (13360: S1 ^operator O1902 +)
=>WM: (13359: S1 ^operator O1901 +)
=>WM: (13358: I3 ^dir L)
=>WM: (13357: O1902 ^name predict-no)
=>WM: (13356: O1901 ^name predict-yes)
=>WM: (13355: R954 ^value 1)
=>WM: (13354: R1 ^reward R954)
=>WM: (13353: I3 ^see 1)
<=WM: (13344: S1 ^operator O1899 +)
<=WM: (13346: S1 ^operator O1899)
<=WM: (13345: S1 ^operator O1900 +)
<=WM: (13343: I3 ^dir R)
<=WM: (13339: R1 ^reward R953)
<=WM: (13255: I3 ^see 0)
<=WM: (13342: O1900 ^name predict-no)
<=WM: (13341: O1899 ^name predict-yes)
<=WM: (13340: R953 ^value 1)

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing prefer*rvt*predict-yes*H0
 -->
Firing rl*prefer*rvt*predict-yes*H0*1
 -->
 (S1 ^operator O1901 = 0.5231202597544767)
Firing prefer*rvt*predict-yes*H0*1*H1
 -->
Firing rl*prefer*rvt*predict-yes*H0*1*H1*22
 -->
 (S1 ^operator O1901 = 0.4768760547163575)
Firing prefer*rvt*predict-no*H0
 -->
Firing rl*prefer*rvt*predict-no*H0*2
 -->
 (S1 ^operator O1902 = 0.2550132695707557)
Firing prefer*rvt*predict-no*H0*2*H1
 -->
Firing rl*prefer*rvt*predict-no*H0*2*H1*10
 -->
 (S1 ^operator O1902 = -0.01194930198035649)
 inner elaboration loop at bottom goal.
Retracting rl*prefer*rvt*predict-no*H0*2
 -->
 (S1 ^operator O1900 = 0.2550132695707557)
Retracting rl*prefer*rvt*predict-no*H0*2*H1*10
 -->
 (S1 ^operator O1900 = -0.01194930198035649)
Retracting rl*prefer*rvt*predict-yes*H0*1
 -->
 (S1 ^operator O1899 = 0.5231202597544767)
Retracting rl*prefer*rvt*predict-yes*H0*1*H1*22
 -->
 (S1 ^operator O1899 = 0.4768760547163575)

--- END Proposal Phase ---

--- Decision Phase ---
RL update rl*prefer*rvt*predict-yes*H0*3 0.673123 -0.290194 0.382929 -> 0.673122 -0.290194 0.382927(R,m,v=1,0.958904,0.0396788)
RL update rl*prefer*rvt*predict-yes*H0*3*H1*14 0.326889 0.290195 0.617085 -> 0.326888 0.290195 0.617083(R,m,v=1,1,0)
=>WM: (13361: S1 ^operator O1901)

   951:    O: O1901 (predict-yes)
--- END Decision Phase ---

--- Application Phase ---
	--- Firing Productions (PE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing apply*operator
 -->
 (I3 ^predict-yes N951 +  :O )
Firing apply*operator*complete
 -->
 (I3 ^predict-yes N950 -  :O )
 inner elaboration loop at bottom goal.
	--- Change Working Memory (PE) ---
=>WM: (13362: I3 ^predict-yes N951)
<=WM: (13348: N950 ^status complete)
<=WM: (13347: I3 ^predict-yes N950)
	--- Firing Productions (IE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing monitor*world
 -->

I see 1 and I'm going to do: predict-yes inner elaboration loop at bottom goal.
	--- Change Working Memory (IE) ---

--- END Application Phase ---
--- Output Phase ---
ENV: Agent did: predict-yes for direction L in state State-B
In  State-B moving L
ENV: (next state, see, prediction correct?) = (State-A, 1, True)
predict error 0
dir: dir isL
--- END Output Phase ---
\--- Input Phase --- 
=>WM: (13366: I2 ^dir L)
=>WM: (13365: I2 ^reward 1)
=>WM: (13364: I2 ^see 1)
=>WM: (13363: N951 ^status complete)
<=WM: (13351: I2 ^dir L)
<=WM: (13350: I2 ^reward 1)
<=WM: (13349: I2 ^see 1)
=>WM: (13367: I2 ^level-1 L1-root)
<=WM: (13352: I2 ^level-1 R1-root)

--- END Input Phase --- 

--- Proposal Phase ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing rl*prefer*rvt*predict-yes*H0*1*H1*20
 -->
 (S1 ^operator O1901 = 0.1693592933936033)
Firing rl*prefer*rvt*predict-no*H0*2*H1*11
 -->
 (S1 ^operator O1902 = 0.7449862034212327)
Firing prefer*rvt*predict-no*H0*2*H1
 -->
Firing prefer*rvt*predict-yes*H0*1*H1
 -->
Firing elaborate*copy-see-to-output-link
 -->
 (I3 ^see 1 +)
Firing elaborate*reward*based*on*reward
 -->
 (R955 ^value 1 +)
 (R1 ^reward R955 +)
Firing propose*predict-yes
 -->
 (O1903 ^name predict-yes +)
 (S1 ^operator O1903 +)
Firing propose*predict-no
 -->
 (O1904 ^name predict-no +)
 (S1 ^operator O1904 +)
Firing rl*prefer*rvt*predict-no*H0*2
 -->
 (S1 ^operator O1902 = 0.2550132695707557)
Firing rl*prefer*rvt*predict-yes*H0*1
 -->
 (S1 ^operator O1901 = 0.5231202597544767)
Firing prefer*rvt*predict-yes*H0
 -->
Firing prefer*rvt*predict-no*H0
 -->
Firing elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir L +)
 inner elaboration loop at bottom goal.
Retracting elaborate*copy-see-to-output-link
 -->
 (I3 ^see 1 +)
Retracting propose*predict-no
 -->
 (O1902 ^name predict-no +)
 (S1 ^operator O1902 +)
Retracting propose*predict-yes
 -->
 (O1901 ^name predict-yes +)
 (S1 ^operator O1901 +)
Retracting elaborate*reward*based*on*reward
 -->
 (R954 ^value 1 +)
 (R1 ^reward R954 +)
Retracting elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir L +)
Retracting rl*prefer*rvt*predict-no*H0*2*H1*10
 -->
 (S1 ^operator O1902 = -0.01194930198035649)
Retracting rl*prefer*rvt*predict-no*H0*2
 -->
 (S1 ^operator O1902 = 0.2550132695707557)
Retracting rl*prefer*rvt*predict-yes*H0*1*H1*22
 -->
 (S1 ^operator O1901 = 0.4768760547163575)
Retracting rl*prefer*rvt*predict-yes*H0*1
 -->
 (S1 ^operator O1901 = 0.5231202597544767)
=>WM: (13373: S1 ^operator O1904 +)
=>WM: (13372: S1 ^operator O1903 +)
=>WM: (13371: O1904 ^name predict-no)
=>WM: (13370: O1903 ^name predict-yes)
=>WM: (13369: R955 ^value 1)
=>WM: (13368: R1 ^reward R955)
<=WM: (13359: S1 ^operator O1901 +)
<=WM: (13361: S1 ^operator O1901)
<=WM: (13360: S1 ^operator O1902 +)
<=WM: (13354: R1 ^reward R954)
<=WM: (13357: O1902 ^name predict-no)
<=WM: (13356: O1901 ^name predict-yes)
<=WM: (13355: R954 ^value 1)

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing prefer*rvt*predict-yes*H0
 -->
Firing rl*prefer*rvt*predict-yes*H0*1
 -->
 (S1 ^operator O1903 = 0.5231202597544767)
Firing prefer*rvt*predict-yes*H0*1*H1
 -->
Firing rl*prefer*rvt*predict-yes*H0*1*H1*20
 -->
 (S1 ^operator O1903 = 0.1693592933936033)
Firing prefer*rvt*predict-no*H0
 -->
Firing rl*prefer*rvt*predict-no*H0*2
 -->
 (S1 ^operator O1904 = 0.2550132695707557)
Firing prefer*rvt*predict-no*H0*2*H1
 -->
Firing rl*prefer*rvt*predict-no*H0*2*H1*11
 -->
 (S1 ^operator O1904 = 0.7449862034212327)
 inner elaboration loop at bottom goal.
Retracting rl*prefer*rvt*predict-no*H0*2
 -->
 (S1 ^operator O1902 = 0.2550132695707557)
Retracting rl*prefer*rvt*predict-no*H0*2*H1*11
 -->
 (S1 ^operator O1902 = 0.7449862034212327)
Retracting rl*prefer*rvt*predict-yes*H0*1
 -->
 (S1 ^operator O1901 = 0.5231202597544767)
Retracting rl*prefer*rvt*predict-yes*H0*1*H1*20
 -->
 (S1 ^operator O1901 = 0.1693592933936033)

--- END Proposal Phase ---

--- Decision Phase ---
RL update rl*prefer*rvt*predict-yes*H0*1 0.72796 -0.20484 0.52312 -> 0.727961 -0.20484 0.523121(R,m,v=1,0.977941,0.021732)
RL update rl*prefer*rvt*predict-yes*H0*1*H1*22 0.272035 0.204841 0.476876 -> 0.272036 0.204841 0.476877(R,m,v=1,1,0)
=>WM: (13374: S1 ^operator O1904)

   952:    O: O1904 (predict-no)
--- END Decision Phase ---

--- Application Phase ---
	--- Firing Productions (PE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing apply*operator
 -->
 (I3 ^predict-no N952 +  :O )
Firing apply*operator*complete
 -->
 (I3 ^predict-yes N951 -  :O )
 inner elaboration loop at bottom goal.
	--- Change Working Memory (PE) ---
=>WM: (13375: I3 ^predict-no N952)
<=WM: (13363: N951 ^status complete)
<=WM: (13362: I3 ^predict-yes N951)
	--- Firing Productions (IE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing monitor*world
 -->

I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
	--- Change Working Memory (IE) ---

--- END Application Phase ---
--- Output Phase ---
ENV: Agent did: predict-no for direction L in state State-A
In  State-A moving L
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isU
--- END Output Phase ---
-/|\--- Input Phase --- 
=>WM: (13379: I2 ^dir U)
=>WM: (13378: I2 ^reward 1)
=>WM: (13377: I2 ^see 0)
=>WM: (13376: N952 ^status complete)
<=WM: (13366: I2 ^dir L)
<=WM: (13365: I2 ^reward 1)
<=WM: (13364: I2 ^see 1)
=>WM: (13380: I2 ^level-1 L0-root)
<=WM: (13367: I2 ^level-1 L1-root)

--- END Input Phase --- 

--- Proposal Phase ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing elaborate*copy-see-to-output-link
 -->
 (I3 ^see 0 +)
Firing elaborate*reward*based*on*reward
 -->
 (R956 ^value 1 +)
 (R1 ^reward R956 +)
Firing propose*predict-yes
 -->
 (O1905 ^name predict-yes +)
 (S1 ^operator O1905 +)
Firing propose*predict-no
 -->
 (O1906 ^name predict-no +)
 (S1 ^operator O1906 +)
Firing rl*prefer*rvt*predict-no*H0*6
 -->
 (S1 ^operator O1904 = 0.9999999999999999)
Firing rl*prefer*rvt*predict-yes*H0*5
 -->
 (S1 ^operator O1903 = 0.)
Firing prefer*rvt*predict-yes*H0
 -->
Firing prefer*rvt*predict-no*H0
 -->
Firing elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir U +)
 inner elaboration loop at bottom goal.
Retracting elaborate*copy-see-to-output-link
 -->
 (I3 ^see 1 +)
Retracting propose*predict-no
 -->
 (O1904 ^name predict-no +)
 (S1 ^operator O1904 +)
Retracting propose*predict-yes
 -->
 (O1903 ^name predict-yes +)
 (S1 ^operator O1903 +)
Retracting elaborate*reward*based*on*reward
 -->
 (R955 ^value 1 +)
 (R1 ^reward R955 +)
Retracting elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir L +)
Retracting rl*prefer*rvt*predict-no*H0*2*H1*11
 -->
 (S1 ^operator O1904 = 0.7449862034212327)
Retracting rl*prefer*rvt*predict-no*H0*2
 -->
 (S1 ^operator O1904 = 0.2550132695707557)
Retracting rl*prefer*rvt*predict-yes*H0*1*H1*20
 -->
 (S1 ^operator O1903 = 0.1693592933936033)
Retracting rl*prefer*rvt*predict-yes*H0*1
 -->
 (S1 ^operator O1903 = 0.5231208125838516)
=>WM: (13388: S1 ^operator O1906 +)
=>WM: (13387: S1 ^operator O1905 +)
=>WM: (13386: I3 ^dir U)
=>WM: (13385: O1906 ^name predict-no)
=>WM: (13384: O1905 ^name predict-yes)
=>WM: (13383: R956 ^value 1)
=>WM: (13382: R1 ^reward R956)
=>WM: (13381: I3 ^see 0)
<=WM: (13372: S1 ^operator O1903 +)
<=WM: (13373: S1 ^operator O1904 +)
<=WM: (13374: S1 ^operator O1904)
<=WM: (13358: I3 ^dir L)
<=WM: (13368: R1 ^reward R955)
<=WM: (13353: I3 ^see 1)
<=WM: (13371: O1904 ^name predict-no)
<=WM: (13370: O1903 ^name predict-yes)
<=WM: (13369: R955 ^value 1)

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing prefer*rvt*predict-yes*H0
 -->
Firing rl*prefer*rvt*predict-yes*H0*5
 -->
 (S1 ^operator O1905 = 0.)
Firing prefer*rvt*predict-no*H0
 -->
Firing rl*prefer*rvt*predict-no*H0*6
 -->
 (S1 ^operator O1906 = 0.9999999999999999)
 inner elaboration loop at bottom goal.
Retracting rl*prefer*rvt*predict-no*H0*6
 -->
 (S1 ^operator O1904 = 0.9999999999999999)
Retracting rl*prefer*rvt*predict-yes*H0*5
 -->
 (S1 ^operator O1903 = 0.)

--- END Proposal Phase ---

--- Decision Phase ---
RL update rl*prefer*rvt*predict-no*H0*2 0.631495 -0.376482 0.255013 -> 0.631495 -0.376482 0.255013(R,m,v=1,0.913043,0.0798289)
RL update rl*prefer*rvt*predict-no*H0*2*H1*11 0.368505 0.376481 0.744986 -> 0.368505 0.376482 0.744986(R,m,v=1,1,0)
=>WM: (13389: S1 ^operator O1906)

   953:    O: O1906 (predict-no)
--- END Decision Phase ---

--- Application Phase ---
	--- Firing Productions (PE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing apply*operator
 -->
 (I3 ^predict-no N953 +  :O )
Firing apply*operator*complete
 -->
 (I3 ^predict-no N952 -  :O )
 inner elaboration loop at bottom goal.
	--- Change Working Memory (PE) ---
=>WM: (13390: I3 ^predict-no N953)
<=WM: (13376: N952 ^status complete)
<=WM: (13375: I3 ^predict-no N952)
	--- Firing Productions (IE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing monitor*world
 -->

I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
	--- Change Working Memory (IE) ---

--- END Application Phase ---
--- Output Phase ---
ENV: Agent did: predict-no for direction U in state State-A
In  State-A moving U
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isL
--- END Output Phase ---
-/|--- Input Phase --- 
=>WM: (13394: I2 ^dir L)
=>WM: (13393: I2 ^reward 1)
=>WM: (13392: I2 ^see 0)
=>WM: (13391: N953 ^status complete)
<=WM: (13379: I2 ^dir U)
<=WM: (13378: I2 ^reward 1)
<=WM: (13377: I2 ^see 0)
=>WM: (13395: I2 ^level-1 L0-root)
<=WM: (13380: I2 ^level-1 L0-root)

--- END Input Phase --- 

--- Proposal Phase ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing rl*prefer*rvt*predict-yes*H0*1*H1*21
 -->
 (S1 ^operator O1905 = 0.3)
Firing rl*prefer*rvt*predict-no*H0*2*H1*12
 -->
 (S1 ^operator O1906 = 0.7449868594607382)
Firing prefer*rvt*predict-no*H0*2*H1
 -->
Firing prefer*rvt*predict-yes*H0*1*H1
 -->
Firing elaborate*copy-see-to-output-link
 -->
 (I3 ^see 0 +)
Firing elaborate*reward*based*on*reward
 -->
 (R957 ^value 1 +)
 (R1 ^reward R957 +)
Firing propose*predict-yes
 -->
 (O1907 ^name predict-yes +)
 (S1 ^operator O1907 +)
Firing propose*predict-no
 -->
 (O1908 ^name predict-no +)
 (S1 ^operator O1908 +)
Firing rl*prefer*rvt*predict-no*H0*2
 -->
 (S1 ^operator O1906 = 0.2550133486219575)
Firing rl*prefer*rvt*predict-yes*H0*1
 -->
 (S1 ^operator O1905 = 0.5231208125838516)
Firing prefer*rvt*predict-yes*H0
 -->
Firing prefer*rvt*predict-no*H0
 -->
Firing elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir L +)
 inner elaboration loop at bottom goal.
Retracting elaborate*copy-see-to-output-link
 -->
 (I3 ^see 0 +)
Retracting propose*predict-no
 -->
 (O1906 ^name predict-no +)
 (S1 ^operator O1906 +)
Retracting propose*predict-yes
 -->
 (O1905 ^name predict-yes +)
 (S1 ^operator O1905 +)
Retracting elaborate*reward*based*on*reward
 -->
 (R956 ^value 1 +)
 (R1 ^reward R956 +)
Retracting elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir U +)
Retracting rl*prefer*rvt*predict-no*H0*6
 -->
 (S1 ^operator O1906 = 0.9999999999999999)
Retracting rl*prefer*rvt*predict-yes*H0*5
 -->
 (S1 ^operator O1905 = 0.)
=>WM: (13402: S1 ^operator O1908 +)
=>WM: (13401: S1 ^operator O1907 +)
=>WM: (13400: I3 ^dir L)
=>WM: (13399: O1908 ^name predict-no)
=>WM: (13398: O1907 ^name predict-yes)
=>WM: (13397: R957 ^value 1)
=>WM: (13396: R1 ^reward R957)
<=WM: (13387: S1 ^operator O1905 +)
<=WM: (13388: S1 ^operator O1906 +)
<=WM: (13389: S1 ^operator O1906)
<=WM: (13386: I3 ^dir U)
<=WM: (13382: R1 ^reward R956)
<=WM: (13385: O1906 ^name predict-no)
<=WM: (13384: O1905 ^name predict-yes)
<=WM: (13383: R956 ^value 1)

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing prefer*rvt*predict-yes*H0
 -->
Firing rl*prefer*rvt*predict-yes*H0*1*H1*21
 -->
 (S1 ^operator O1907 = 0.3)
Firing rl*prefer*rvt*predict-yes*H0*1
 -->
 (S1 ^operator O1907 = 0.5231208125838516)
Firing prefer*rvt*predict-yes*H0*1*H1
 -->
Firing prefer*rvt*predict-no*H0
 -->
Firing rl*prefer*rvt*predict-no*H0*2*H1*12
 -->
 (S1 ^operator O1908 = 0.7449868594607382)
Firing rl*prefer*rvt*predict-no*H0*2
 -->
 (S1 ^operator O1908 = 0.2550133486219575)
Firing prefer*rvt*predict-no*H0*2*H1
 -->
 inner elaboration loop at bottom goal.
Retracting rl*prefer*rvt*predict-no*H0*2
 -->
 (S1 ^operator O1906 = 0.2550133486219575)
Retracting rl*prefer*rvt*predict-no*H0*2*H1*12
 -->
 (S1 ^operator O1906 = 0.7449868594607382)
Retracting rl*prefer*rvt*predict-yes*H0*1
 -->
 (S1 ^operator O1905 = 0.5231208125838516)
Retracting rl*prefer*rvt*predict-yes*H0*1*H1*21
 -->
 (S1 ^operator O1905 = 0.3)

--- END Proposal Phase ---

--- Decision Phase ---
RL update rl*prefer*rvt*predict-no*H0*6 1 0 1 -> 1 0 1(R,m,v=1,1,0)
=>WM: (13403: S1 ^operator O1908)

   954:    O: O1908 (predict-no)
--- END Decision Phase ---

--- Application Phase ---
	--- Firing Productions (PE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing apply*operator
 -->
 (I3 ^predict-no N954 +  :O )
Firing apply*operator*complete
 -->
 (I3 ^predict-no N953 -  :O )
 inner elaboration loop at bottom goal.
	--- Change Working Memory (PE) ---
=>WM: (13404: I3 ^predict-no N954)
<=WM: (13391: N953 ^status complete)
<=WM: (13390: I3 ^predict-no N953)
	--- Firing Productions (IE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing monitor*world
 -->

I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
	--- Change Working Memory (IE) ---

--- END Application Phase ---
--- Output Phase ---
ENV: Agent did: predict-no for direction L in state State-A
In  State-A moving L
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isL
--- END Output Phase ---
\-/--- Input Phase --- 
=>WM: (13408: I2 ^dir L)
=>WM: (13407: I2 ^reward 1)
=>WM: (13406: I2 ^see 0)
=>WM: (13405: N954 ^status complete)
<=WM: (13394: I2 ^dir L)
<=WM: (13393: I2 ^reward 1)
<=WM: (13392: I2 ^see 0)
=>WM: (13409: I2 ^level-1 L0-root)
<=WM: (13395: I2 ^level-1 L0-root)

--- END Input Phase --- 

--- Proposal Phase ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing rl*prefer*rvt*predict-yes*H0*1*H1*21
 -->
 (S1 ^operator O1907 = 0.3)
Firing rl*prefer*rvt*predict-no*H0*2*H1*12
 -->
 (S1 ^operator O1908 = 0.7449868594607382)
Firing prefer*rvt*predict-no*H0*2*H1
 -->
Firing prefer*rvt*predict-yes*H0*1*H1
 -->
Firing elaborate*copy-see-to-output-link
 -->
 (I3 ^see 0 +)
Firing elaborate*reward*based*on*reward
 -->
 (R958 ^value 1 +)
 (R1 ^reward R958 +)
Firing propose*predict-yes
 -->
 (O1909 ^name predict-yes +)
 (S1 ^operator O1909 +)
Firing propose*predict-no
 -->
 (O1910 ^name predict-no +)
 (S1 ^operator O1910 +)
Firing rl*prefer*rvt*predict-no*H0*2
 -->
 (S1 ^operator O1908 = 0.2550133486219575)
Firing rl*prefer*rvt*predict-yes*H0*1
 -->
 (S1 ^operator O1907 = 0.5231208125838516)
Firing prefer*rvt*predict-yes*H0
 -->
Firing prefer*rvt*predict-no*H0
 -->
Firing elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir L +)
 inner elaboration loop at bottom goal.
Retracting elaborate*copy-see-to-output-link
 -->
 (I3 ^see 0 +)
Retracting propose*predict-no
 -->
 (O1908 ^name predict-no +)
 (S1 ^operator O1908 +)
Retracting propose*predict-yes
 -->
 (O1907 ^name predict-yes +)
 (S1 ^operator O1907 +)
Retracting elaborate*reward*based*on*reward
 -->
 (R957 ^value 1 +)
 (R1 ^reward R957 +)
Retracting elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir L +)
Retracting rl*prefer*rvt*predict-no*H0*2
 -->
 (S1 ^operator O1908 = 0.2550133486219575)
Retracting rl*prefer*rvt*predict-no*H0*2*H1*12
 -->
 (S1 ^operator O1908 = 0.7449868594607382)
Retracting rl*prefer*rvt*predict-yes*H0*1
 -->
 (S1 ^operator O1907 = 0.5231208125838516)
Retracting rl*prefer*rvt*predict-yes*H0*1*H1*21
 -->
 (S1 ^operator O1907 = 0.3)
=>WM: (13415: S1 ^operator O1910 +)
=>WM: (13414: S1 ^operator O1909 +)
=>WM: (13413: O1910 ^name predict-no)
=>WM: (13412: O1909 ^name predict-yes)
=>WM: (13411: R958 ^value 1)
=>WM: (13410: R1 ^reward R958)
<=WM: (13401: S1 ^operator O1907 +)
<=WM: (13402: S1 ^operator O1908 +)
<=WM: (13403: S1 ^operator O1908)
<=WM: (13396: R1 ^reward R957)
<=WM: (13399: O1908 ^name predict-no)
<=WM: (13398: O1907 ^name predict-yes)
<=WM: (13397: R957 ^value 1)

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing prefer*rvt*predict-yes*H0
 -->
Firing rl*prefer*rvt*predict-yes*H0*1*H1*21
 -->
 (S1 ^operator O1909 = 0.3)
Firing rl*prefer*rvt*predict-yes*H0*1
 -->
 (S1 ^operator O1909 = 0.5231208125838516)
Firing prefer*rvt*predict-yes*H0*1*H1
 -->
Firing prefer*rvt*predict-no*H0
 -->
Firing rl*prefer*rvt*predict-no*H0*2*H1*12
 -->
 (S1 ^operator O1910 = 0.7449868594607382)
Firing rl*prefer*rvt*predict-no*H0*2
 -->
 (S1 ^operator O1910 = 0.2550133486219575)
Firing prefer*rvt*predict-no*H0*2*H1
 -->
 inner elaboration loop at bottom goal.
Retracting rl*prefer*rvt*predict-no*H0*2
 -->
 (S1 ^operator O1908 = 0.2550133486219575)
Retracting rl*prefer*rvt*predict-no*H0*2*H1*12
 -->
 (S1 ^operator O1908 = 0.7449868594607382)
Retracting rl*prefer*rvt*predict-yes*H0*1
 -->
 (S1 ^operator O1907 = 0.5231208125838516)
Retracting rl*prefer*rvt*predict-yes*H0*1*H1*21
 -->
 (S1 ^operator O1907 = 0.3)

--- END Proposal Phase ---

--- Decision Phase ---
RL update rl*prefer*rvt*predict-no*H0*2 0.631495 -0.376482 0.255013 -> 0.631495 -0.376482 0.255013(R,m,v=1,0.913514,0.079436)
RL update rl*prefer*rvt*predict-no*H0*2*H1*12 0.368505 0.376482 0.744987 -> 0.368505 0.376482 0.744987(R,m,v=1,1,0)
=>WM: (13416: S1 ^operator O1910)

   955:    O: O1910 (predict-no)
--- END Decision Phase ---

--- Application Phase ---
	--- Firing Productions (PE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing apply*operator
 -->
 (I3 ^predict-no N955 +  :O )
Firing apply*operator*complete
 -->
 (I3 ^predict-no N954 -  :O )
 inner elaboration loop at bottom goal.
	--- Change Working Memory (PE) ---
=>WM: (13417: I3 ^predict-no N955)
<=WM: (13405: N954 ^status complete)
<=WM: (13404: I3 ^predict-no N954)
	--- Firing Productions (IE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing monitor*world
 -->

I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
	--- Change Working Memory (IE) ---

--- END Application Phase ---
--- Output Phase ---
ENV: Agent did: predict-no for direction L in state State-A
In  State-A moving L
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isU
--- END Output Phase ---
|\---- Input Phase --- 
=>WM: (13421: I2 ^dir U)
=>WM: (13420: I2 ^reward 1)
=>WM: (13419: I2 ^see 0)
=>WM: (13418: N955 ^status complete)
<=WM: (13408: I2 ^dir L)
<=WM: (13407: I2 ^reward 1)
<=WM: (13406: I2 ^see 0)
=>WM: (13422: I2 ^level-1 L0-root)
<=WM: (13409: I2 ^level-1 L0-root)

--- END Input Phase --- 

--- Proposal Phase ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing elaborate*copy-see-to-output-link
 -->
 (I3 ^see 0 +)
Firing elaborate*reward*based*on*reward
 -->
 (R959 ^value 1 +)
 (R1 ^reward R959 +)
Firing propose*predict-yes
 -->
 (O1911 ^name predict-yes +)
 (S1 ^operator O1911 +)
Firing propose*predict-no
 -->
 (O1912 ^name predict-no +)
 (S1 ^operator O1912 +)
Firing rl*prefer*rvt*predict-no*H0*6
 -->
 (S1 ^operator O1910 = 0.9999999999999999)
Firing rl*prefer*rvt*predict-yes*H0*5
 -->
 (S1 ^operator O1909 = 0.)
Firing prefer*rvt*predict-yes*H0
 -->
Firing prefer*rvt*predict-no*H0
 -->
Firing elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir U +)
 inner elaboration loop at bottom goal.
Retracting elaborate*copy-see-to-output-link
 -->
 (I3 ^see 0 +)
Retracting propose*predict-no
 -->
 (O1910 ^name predict-no +)
 (S1 ^operator O1910 +)
Retracting propose*predict-yes
 -->
 (O1909 ^name predict-yes +)
 (S1 ^operator O1909 +)
Retracting elaborate*reward*based*on*reward
 -->
 (R958 ^value 1 +)
 (R1 ^reward R958 +)
Retracting elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir L +)
Retracting rl*prefer*rvt*predict-no*H0*2
 -->
 (S1 ^operator O1910 = 0.2550133174095531)
Retracting rl*prefer*rvt*predict-no*H0*2*H1*12
 -->
 (S1 ^operator O1910 = 0.7449868282483338)
Retracting rl*prefer*rvt*predict-yes*H0*1
 -->
 (S1 ^operator O1909 = 0.5231208125838516)
Retracting rl*prefer*rvt*predict-yes*H0*1*H1*21
 -->
 (S1 ^operator O1909 = 0.3)
=>WM: (13429: S1 ^operator O1912 +)
=>WM: (13428: S1 ^operator O1911 +)
=>WM: (13427: I3 ^dir U)
=>WM: (13426: O1912 ^name predict-no)
=>WM: (13425: O1911 ^name predict-yes)
=>WM: (13424: R959 ^value 1)
=>WM: (13423: R1 ^reward R959)
<=WM: (13414: S1 ^operator O1909 +)
<=WM: (13415: S1 ^operator O1910 +)
<=WM: (13416: S1 ^operator O1910)
<=WM: (13400: I3 ^dir L)
<=WM: (13410: R1 ^reward R958)
<=WM: (13413: O1910 ^name predict-no)
<=WM: (13412: O1909 ^name predict-yes)
<=WM: (13411: R958 ^value 1)

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing prefer*rvt*predict-yes*H0
 -->
Firing rl*prefer*rvt*predict-yes*H0*5
 -->
 (S1 ^operator O1911 = 0.)
Firing prefer*rvt*predict-no*H0
 -->
Firing rl*prefer*rvt*predict-no*H0*6
 -->
 (S1 ^operator O1912 = 0.9999999999999999)
 inner elaboration loop at bottom goal.
Retracting rl*prefer*rvt*predict-no*H0*6
 -->
 (S1 ^operator O1910 = 0.9999999999999999)
Retracting rl*prefer*rvt*predict-yes*H0*5
 -->
 (S1 ^operator O1909 = 0.)

--- END Proposal Phase ---

--- Decision Phase ---
RL update rl*prefer*rvt*predict-no*H0*2 0.631495 -0.376482 0.255013 -> 0.631495 -0.376482 0.255013(R,m,v=1,0.913978,0.0790468)
RL update rl*prefer*rvt*predict-no*H0*2*H1*12 0.368505 0.376482 0.744987 -> 0.368505 0.376482 0.744987(R,m,v=1,1,0)
=>WM: (13430: S1 ^operator O1912)

   956:    O: O1912 (predict-no)
--- END Decision Phase ---

--- Application Phase ---
	--- Firing Productions (PE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing apply*operator
 -->
 (I3 ^predict-no N956 +  :O )
Firing apply*operator*complete
 -->
 (I3 ^predict-no N955 -  :O )
 inner elaboration loop at bottom goal.
	--- Change Working Memory (PE) ---
=>WM: (13431: I3 ^predict-no N956)
<=WM: (13418: N955 ^status complete)
<=WM: (13417: I3 ^predict-no N955)
	--- Firing Productions (IE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing monitor*world
 -->

I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
	--- Change Working Memory (IE) ---

--- END Application Phase ---
--- Output Phase ---
ENV: Agent did: predict-no for direction U in state State-A
In  State-A moving U
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isU
--- END Output Phase ---
/|\--- Input Phase --- 
=>WM: (13435: I2 ^dir U)
=>WM: (13434: I2 ^reward 1)
=>WM: (13433: I2 ^see 0)
=>WM: (13432: N956 ^status complete)
<=WM: (13421: I2 ^dir U)
<=WM: (13420: I2 ^reward 1)
<=WM: (13419: I2 ^see 0)
=>WM: (13436: I2 ^level-1 L0-root)
<=WM: (13422: I2 ^level-1 L0-root)

--- END Input Phase --- 

--- Proposal Phase ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing elaborate*copy-see-to-output-link
 -->
 (I3 ^see 0 +)
Firing elaborate*reward*based*on*reward
 -->
 (R960 ^value 1 +)
 (R1 ^reward R960 +)
Firing propose*predict-yes
 -->
 (O1913 ^name predict-yes +)
 (S1 ^operator O1913 +)
Firing propose*predict-no
 -->
 (O1914 ^name predict-no +)
 (S1 ^operator O1914 +)
Firing rl*prefer*rvt*predict-no*H0*6
 -->
 (S1 ^operator O1912 = 0.9999999999999999)
Firing rl*prefer*rvt*predict-yes*H0*5
 -->
 (S1 ^operator O1911 = 0.)
Firing prefer*rvt*predict-yes*H0
 -->
Firing prefer*rvt*predict-no*H0
 -->
Firing elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir U +)
 inner elaboration loop at bottom goal.
Retracting elaborate*copy-see-to-output-link
 -->
 (I3 ^see 0 +)
Retracting propose*predict-no
 -->
 (O1912 ^name predict-no +)
 (S1 ^operator O1912 +)
Retracting propose*predict-yes
 -->
 (O1911 ^name predict-yes +)
 (S1 ^operator O1911 +)
Retracting elaborate*reward*based*on*reward
 -->
 (R959 ^value 1 +)
 (R1 ^reward R959 +)
Retracting elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir U +)
Retracting rl*prefer*rvt*predict-no*H0*6
 -->
 (S1 ^operator O1912 = 0.9999999999999999)
Retracting rl*prefer*rvt*predict-yes*H0*5
 -->
 (S1 ^operator O1911 = 0.)
=>WM: (13442: S1 ^operator O1914 +)
=>WM: (13441: S1 ^operator O1913 +)
=>WM: (13440: O1914 ^name predict-no)
=>WM: (13439: O1913 ^name predict-yes)
=>WM: (13438: R960 ^value 1)
=>WM: (13437: R1 ^reward R960)
<=WM: (13428: S1 ^operator O1911 +)
<=WM: (13429: S1 ^operator O1912 +)
<=WM: (13430: S1 ^operator O1912)
<=WM: (13423: R1 ^reward R959)
<=WM: (13426: O1912 ^name predict-no)
<=WM: (13425: O1911 ^name predict-yes)
<=WM: (13424: R959 ^value 1)

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing prefer*rvt*predict-yes*H0
 -->
Firing rl*prefer*rvt*predict-yes*H0*5
 -->
 (S1 ^operator O1913 = 0.)
Firing prefer*rvt*predict-no*H0
 -->
Firing rl*prefer*rvt*predict-no*H0*6
 -->
 (S1 ^operator O1914 = 0.9999999999999999)
 inner elaboration loop at bottom goal.
Retracting rl*prefer*rvt*predict-no*H0*6
 -->
 (S1 ^operator O1912 = 0.9999999999999999)
Retracting rl*prefer*rvt*predict-yes*H0*5
 -->
 (S1 ^operator O1911 = 0.)

--- END Proposal Phase ---

--- Decision Phase ---
RL update rl*prefer*rvt*predict-no*H0*6 1 0 1 -> 1 0 1(R,m,v=1,1,0)
=>WM: (13443: S1 ^operator O1914)

   957:    O: O1914 (predict-no)
--- END Decision Phase ---

--- Application Phase ---
	--- Firing Productions (PE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing apply*operator
 -->
 (I3 ^predict-no N957 +  :O )
Firing apply*operator*complete
 -->
 (I3 ^predict-no N956 -  :O )
 inner elaboration loop at bottom goal.
	--- Change Working Memory (PE) ---
=>WM: (13444: I3 ^predict-no N957)
<=WM: (13432: N956 ^status complete)
<=WM: (13431: I3 ^predict-no N956)
	--- Firing Productions (IE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing monitor*world
 -->

I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
	--- Change Working Memory (IE) ---

--- END Application Phase ---
--- Output Phase ---
ENV: Agent did: predict-no for direction U in state State-A
In  State-A moving U
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isL
--- END Output Phase ---
-/|--- Input Phase --- 
=>WM: (13448: I2 ^dir L)
=>WM: (13447: I2 ^reward 1)
=>WM: (13446: I2 ^see 0)
=>WM: (13445: N957 ^status complete)
<=WM: (13435: I2 ^dir U)
<=WM: (13434: I2 ^reward 1)
<=WM: (13433: I2 ^see 0)
=>WM: (13449: I2 ^level-1 L0-root)
<=WM: (13436: I2 ^level-1 L0-root)

--- END Input Phase --- 

--- Proposal Phase ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing rl*prefer*rvt*predict-yes*H0*1*H1*21
 -->
 (S1 ^operator O1913 = 0.3)
Firing rl*prefer*rvt*predict-no*H0*2*H1*12
 -->
 (S1 ^operator O1914 = 0.7449868063996508)
Firing prefer*rvt*predict-no*H0*2*H1
 -->
Firing prefer*rvt*predict-yes*H0*1*H1
 -->
Firing elaborate*copy-see-to-output-link
 -->
 (I3 ^see 0 +)
Firing elaborate*reward*based*on*reward
 -->
 (R961 ^value 1 +)
 (R1 ^reward R961 +)
Firing propose*predict-yes
 -->
 (O1915 ^name predict-yes +)
 (S1 ^operator O1915 +)
Firing propose*predict-no
 -->
 (O1916 ^name predict-no +)
 (S1 ^operator O1916 +)
Firing rl*prefer*rvt*predict-no*H0*2
 -->
 (S1 ^operator O1914 = 0.2550132955608701)
Firing rl*prefer*rvt*predict-yes*H0*1
 -->
 (S1 ^operator O1913 = 0.5231208125838516)
Firing prefer*rvt*predict-yes*H0
 -->
Firing prefer*rvt*predict-no*H0
 -->
Firing elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir L +)
 inner elaboration loop at bottom goal.
Retracting elaborate*copy-see-to-output-link
 -->
 (I3 ^see 0 +)
Retracting propose*predict-no
 -->
 (O1914 ^name predict-no +)
 (S1 ^operator O1914 +)
Retracting propose*predict-yes
 -->
 (O1913 ^name predict-yes +)
 (S1 ^operator O1913 +)
Retracting elaborate*reward*based*on*reward
 -->
 (R960 ^value 1 +)
 (R1 ^reward R960 +)
Retracting elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir U +)
Retracting rl*prefer*rvt*predict-no*H0*6
 -->
 (S1 ^operator O1914 = 0.9999999999999999)
Retracting rl*prefer*rvt*predict-yes*H0*5
 -->
 (S1 ^operator O1913 = 0.)
=>WM: (13456: S1 ^operator O1916 +)
=>WM: (13455: S1 ^operator O1915 +)
=>WM: (13454: I3 ^dir L)
=>WM: (13453: O1916 ^name predict-no)
=>WM: (13452: O1915 ^name predict-yes)
=>WM: (13451: R961 ^value 1)
=>WM: (13450: R1 ^reward R961)
<=WM: (13441: S1 ^operator O1913 +)
<=WM: (13442: S1 ^operator O1914 +)
<=WM: (13443: S1 ^operator O1914)
<=WM: (13427: I3 ^dir U)
<=WM: (13437: R1 ^reward R960)
<=WM: (13440: O1914 ^name predict-no)
<=WM: (13439: O1913 ^name predict-yes)
<=WM: (13438: R960 ^value 1)

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing prefer*rvt*predict-yes*H0
 -->
Firing rl*prefer*rvt*predict-yes*H0*1*H1*21
 -->
 (S1 ^operator O1915 = 0.3)
Firing rl*prefer*rvt*predict-yes*H0*1
 -->
 (S1 ^operator O1915 = 0.5231208125838516)
Firing prefer*rvt*predict-yes*H0*1*H1
 -->
Firing prefer*rvt*predict-no*H0
 -->
Firing rl*prefer*rvt*predict-no*H0*2*H1*12
 -->
 (S1 ^operator O1916 = 0.7449868063996508)
Firing rl*prefer*rvt*predict-no*H0*2
 -->
 (S1 ^operator O1916 = 0.2550132955608701)
Firing prefer*rvt*predict-no*H0*2*H1
 -->
 inner elaboration loop at bottom goal.
Retracting rl*prefer*rvt*predict-no*H0*2
 -->
 (S1 ^operator O1914 = 0.2550132955608701)
Retracting rl*prefer*rvt*predict-no*H0*2*H1*12
 -->
 (S1 ^operator O1914 = 0.7449868063996508)
Retracting rl*prefer*rvt*predict-yes*H0*1
 -->
 (S1 ^operator O1913 = 0.5231208125838516)
Retracting rl*prefer*rvt*predict-yes*H0*1*H1*21
 -->
 (S1 ^operator O1913 = 0.3)

--- END Proposal Phase ---

--- Decision Phase ---
RL update rl*prefer*rvt*predict-no*H0*6 1 0 1 -> 1 0 1(R,m,v=1,1,0)
=>WM: (13457: S1 ^operator O1916)

   958:    O: O1916 (predict-no)
--- END Decision Phase ---

--- Application Phase ---
	--- Firing Productions (PE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing apply*operator
 -->
 (I3 ^predict-no N958 +  :O )
Firing apply*operator*complete
 -->
 (I3 ^predict-no N957 -  :O )
 inner elaboration loop at bottom goal.
	--- Change Working Memory (PE) ---
=>WM: (13458: I3 ^predict-no N958)
<=WM: (13445: N957 ^status complete)
<=WM: (13444: I3 ^predict-no N957)
	--- Firing Productions (IE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing monitor*world
 -->

I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
	--- Change Working Memory (IE) ---

--- END Application Phase ---
--- Output Phase ---
ENV: Agent did: predict-no for direction L in state State-A
In  State-A moving L
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isU
--- END Output Phase ---
\-/--- Input Phase --- 
=>WM: (13462: I2 ^dir U)
=>WM: (13461: I2 ^reward 1)
=>WM: (13460: I2 ^see 0)
=>WM: (13459: N958 ^status complete)
<=WM: (13448: I2 ^dir L)
<=WM: (13447: I2 ^reward 1)
<=WM: (13446: I2 ^see 0)
=>WM: (13463: I2 ^level-1 L0-root)
<=WM: (13449: I2 ^level-1 L0-root)

--- END Input Phase --- 

--- Proposal Phase ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing elaborate*copy-see-to-output-link
 -->
 (I3 ^see 0 +)
Firing elaborate*reward*based*on*reward
 -->
 (R962 ^value 1 +)
 (R1 ^reward R962 +)
Firing propose*predict-yes
 -->
 (O1917 ^name predict-yes +)
 (S1 ^operator O1917 +)
Firing propose*predict-no
 -->
 (O1918 ^name predict-no +)
 (S1 ^operator O1918 +)
Firing rl*prefer*rvt*predict-no*H0*6
 -->
 (S1 ^operator O1916 = 0.9999999999999999)
Firing rl*prefer*rvt*predict-yes*H0*5
 -->
 (S1 ^operator O1915 = 0.)
Firing prefer*rvt*predict-yes*H0
 -->
Firing prefer*rvt*predict-no*H0
 -->
Firing elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir U +)
 inner elaboration loop at bottom goal.
Retracting elaborate*copy-see-to-output-link
 -->
 (I3 ^see 0 +)
Retracting propose*predict-no
 -->
 (O1916 ^name predict-no +)
 (S1 ^operator O1916 +)
Retracting propose*predict-yes
 -->
 (O1915 ^name predict-yes +)
 (S1 ^operator O1915 +)
Retracting elaborate*reward*based*on*reward
 -->
 (R961 ^value 1 +)
 (R1 ^reward R961 +)
Retracting elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir L +)
Retracting rl*prefer*rvt*predict-no*H0*2
 -->
 (S1 ^operator O1916 = 0.2550132955608701)
Retracting rl*prefer*rvt*predict-no*H0*2*H1*12
 -->
 (S1 ^operator O1916 = 0.7449868063996508)
Retracting rl*prefer*rvt*predict-yes*H0*1
 -->
 (S1 ^operator O1915 = 0.5231208125838516)
Retracting rl*prefer*rvt*predict-yes*H0*1*H1*21
 -->
 (S1 ^operator O1915 = 0.3)
=>WM: (13470: S1 ^operator O1918 +)
=>WM: (13469: S1 ^operator O1917 +)
=>WM: (13468: I3 ^dir U)
=>WM: (13467: O1918 ^name predict-no)
=>WM: (13466: O1917 ^name predict-yes)
=>WM: (13465: R962 ^value 1)
=>WM: (13464: R1 ^reward R962)
<=WM: (13455: S1 ^operator O1915 +)
<=WM: (13456: S1 ^operator O1916 +)
<=WM: (13457: S1 ^operator O1916)
<=WM: (13454: I3 ^dir L)
<=WM: (13450: R1 ^reward R961)
<=WM: (13453: O1916 ^name predict-no)
<=WM: (13452: O1915 ^name predict-yes)
<=WM: (13451: R961 ^value 1)

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing prefer*rvt*predict-yes*H0
 -->
Firing rl*prefer*rvt*predict-yes*H0*5
 -->
 (S1 ^operator O1917 = 0.)
Firing prefer*rvt*predict-no*H0
 -->
Firing rl*prefer*rvt*predict-no*H0*6
 -->
 (S1 ^operator O1918 = 0.9999999999999999)
 inner elaboration loop at bottom goal.
Retracting rl*prefer*rvt*predict-no*H0*6
 -->
 (S1 ^operator O1916 = 0.9999999999999999)
Retracting rl*prefer*rvt*predict-yes*H0*5
 -->
 (S1 ^operator O1915 = 0.)

--- END Proposal Phase ---

--- Decision Phase ---
RL update rl*prefer*rvt*predict-no*H0*2 0.631495 -0.376482 0.255013 -> 0.631495 -0.376482 0.255013(R,m,v=1,0.914439,0.0786614)
RL update rl*prefer*rvt*predict-no*H0*2*H1*12 0.368505 0.376482 0.744987 -> 0.368505 0.376482 0.744987(R,m,v=1,1,0)
=>WM: (13471: S1 ^operator O1918)

   959:    O: O1918 (predict-no)
--- END Decision Phase ---

--- Application Phase ---
	--- Firing Productions (PE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing apply*operator
 -->
 (I3 ^predict-no N959 +  :O )
Firing apply*operator*complete
 -->
 (I3 ^predict-no N958 -  :O )
 inner elaboration loop at bottom goal.
	--- Change Working Memory (PE) ---
=>WM: (13472: I3 ^predict-no N959)
<=WM: (13459: N958 ^status complete)
<=WM: (13458: I3 ^predict-no N958)
	--- Firing Productions (IE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing monitor*world
 -->

I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
	--- Change Working Memory (IE) ---

--- END Application Phase ---
--- Output Phase ---
ENV: Agent did: predict-no for direction U in state State-A
In  State-A moving U
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isR
--- END Output Phase ---
|\---- Input Phase --- 
=>WM: (13476: I2 ^dir R)
=>WM: (13475: I2 ^reward 1)
=>WM: (13474: I2 ^see 0)
=>WM: (13473: N959 ^status complete)
<=WM: (13462: I2 ^dir U)
<=WM: (13461: I2 ^reward 1)
<=WM: (13460: I2 ^see 0)
=>WM: (13477: I2 ^level-1 L0-root)
<=WM: (13463: I2 ^level-1 L0-root)

--- END Input Phase --- 

--- Proposal Phase ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing rl*prefer*rvt*predict-yes*H0*3*H1*14
 -->
 (S1 ^operator O1917 = 0.6170827253998104)
Firing rl*prefer*rvt*predict-no*H0*4*H1*13
 -->
 (S1 ^operator O1918 = 0.4910065094545203)
Firing prefer*rvt*predict-no*H0*4*H1
 -->
Firing prefer*rvt*predict-yes*H0*3*H1
 -->
Firing elaborate*copy-see-to-output-link
 -->
 (I3 ^see 0 +)
Firing elaborate*reward*based*on*reward
 -->
 (R963 ^value 1 +)
 (R1 ^reward R963 +)
Firing propose*predict-yes
 -->
 (O1919 ^name predict-yes +)
 (S1 ^operator O1919 +)
Firing propose*predict-no
 -->
 (O1920 ^name predict-no +)
 (S1 ^operator O1920 +)
Firing rl*prefer*rvt*predict-no*H0*4
 -->
 (S1 ^operator O1918 = 0.1269768259493387)
Firing rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O1917 = 0.3829271874912855)
Firing prefer*rvt*predict-yes*H0
 -->
Firing prefer*rvt*predict-no*H0
 -->
Firing elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir R +)
 inner elaboration loop at bottom goal.
Retracting elaborate*copy-see-to-output-link
 -->
 (I3 ^see 0 +)
Retracting propose*predict-no
 -->
 (O1918 ^name predict-no +)
 (S1 ^operator O1918 +)
Retracting propose*predict-yes
 -->
 (O1917 ^name predict-yes +)
 (S1 ^operator O1917 +)
Retracting elaborate*reward*based*on*reward
 -->
 (R962 ^value 1 +)
 (R1 ^reward R962 +)
Retracting elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir U +)
Retracting rl*prefer*rvt*predict-no*H0*6
 -->
 (S1 ^operator O1918 = 0.9999999999999999)
Retracting rl*prefer*rvt*predict-yes*H0*5
 -->
 (S1 ^operator O1917 = 0.)
=>WM: (13484: S1 ^operator O1920 +)
=>WM: (13483: S1 ^operator O1919 +)
=>WM: (13482: I3 ^dir R)
=>WM: (13481: O1920 ^name predict-no)
=>WM: (13480: O1919 ^name predict-yes)
=>WM: (13479: R963 ^value 1)
=>WM: (13478: R1 ^reward R963)
<=WM: (13469: S1 ^operator O1917 +)
<=WM: (13470: S1 ^operator O1918 +)
<=WM: (13471: S1 ^operator O1918)
<=WM: (13468: I3 ^dir U)
<=WM: (13464: R1 ^reward R962)
<=WM: (13467: O1918 ^name predict-no)
<=WM: (13466: O1917 ^name predict-yes)
<=WM: (13465: R962 ^value 1)

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing prefer*rvt*predict-yes*H0
 -->
Firing rl*prefer*rvt*predict-yes*H0*3*H1*14
 -->
 (S1 ^operator O1919 = 0.6170827253998104)
Firing rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O1919 = 0.3829271874912855)
Firing prefer*rvt*predict-yes*H0*3*H1
 -->
Firing prefer*rvt*predict-no*H0
 -->
Firing rl*prefer*rvt*predict-no*H0*4*H1*13
 -->
 (S1 ^operator O1920 = 0.4910065094545203)
Firing rl*prefer*rvt*predict-no*H0*4
 -->
 (S1 ^operator O1920 = 0.1269768259493387)
Firing prefer*rvt*predict-no*H0*4*H1
 -->
 inner elaboration loop at bottom goal.
Retracting rl*prefer*rvt*predict-no*H0*4
 -->
 (S1 ^operator O1918 = 0.1269768259493387)
Retracting rl*prefer*rvt*predict-no*H0*4*H1*13
 -->
 (S1 ^operator O1918 = 0.4910065094545203)
Retracting rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O1917 = 0.3829271874912855)
Retracting rl*prefer*rvt*predict-yes*H0*3*H1*14
 -->
 (S1 ^operator O1917 = 0.6170827253998104)

--- END Proposal Phase ---

--- Decision Phase ---
RL update rl*prefer*rvt*predict-no*H0*6 1 0 1 -> 1 0 1(R,m,v=1,1,0)
=>WM: (13485: S1 ^operator O1919)

   960:    O: O1919 (predict-yes)
--- END Decision Phase ---

--- Application Phase ---
	--- Firing Productions (PE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing apply*operator
 -->
 (I3 ^predict-yes N960 +  :O )
Firing apply*operator*complete
 -->
 (I3 ^predict-no N959 -  :O )
 inner elaboration loop at bottom goal.
	--- Change Working Memory (PE) ---
=>WM: (13486: I3 ^predict-yes N960)
<=WM: (13473: N959 ^status complete)
<=WM: (13472: I3 ^predict-no N959)
	--- Firing Productions (IE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing monitor*world
 -->

I see 1 and I'm going to do: predict-yes inner elaboration loop at bottom goal.
	--- Change Working Memory (IE) ---

--- END Application Phase ---
--- Output Phase ---
ENV: Agent did: predict-yes for direction R in state State-A
In  State-A moving R
ENV: (next state, see, prediction correct?) = (State-B, 1, True)
predict error 0
dir: dir isR
--- END Output Phase ---
/|\--- Input Phase --- 
=>WM: (13490: I2 ^dir R)
=>WM: (13489: I2 ^reward 1)
=>WM: (13488: I2 ^see 1)
=>WM: (13487: N960 ^status complete)
<=WM: (13476: I2 ^dir R)
<=WM: (13475: I2 ^reward 1)
<=WM: (13474: I2 ^see 0)
=>WM: (13491: I2 ^level-1 R1-root)
<=WM: (13477: I2 ^level-1 L0-root)

--- END Input Phase --- 

--- Proposal Phase ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing rl*prefer*rvt*predict-yes*H0*3*H1*16
 -->
 (S1 ^operator O1919 = 0.08783148430849691)
Firing rl*prefer*rvt*predict-no*H0*4*H1*15
 -->
 (S1 ^operator O1920 = 0.873023493232603)
Firing prefer*rvt*predict-no*H0*4*H1
 -->
Firing prefer*rvt*predict-yes*H0*3*H1
 -->
Firing elaborate*copy-see-to-output-link
 -->
 (I3 ^see 1 +)
Firing elaborate*reward*based*on*reward
 -->
 (R964 ^value 1 +)
 (R1 ^reward R964 +)
Firing propose*predict-yes
 -->
 (O1921 ^name predict-yes +)
 (S1 ^operator O1921 +)
Firing propose*predict-no
 -->
 (O1922 ^name predict-no +)
 (S1 ^operator O1922 +)
Firing rl*prefer*rvt*predict-no*H0*4
 -->
 (S1 ^operator O1920 = 0.1269768259493387)
Firing rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O1919 = 0.3829271874912855)
Firing prefer*rvt*predict-yes*H0
 -->
Firing prefer*rvt*predict-no*H0
 -->
Firing elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir R +)
 inner elaboration loop at bottom goal.
Retracting elaborate*copy-see-to-output-link
 -->
 (I3 ^see 0 +)
Retracting propose*predict-no
 -->
 (O1920 ^name predict-no +)
 (S1 ^operator O1920 +)
Retracting propose*predict-yes
 -->
 (O1919 ^name predict-yes +)
 (S1 ^operator O1919 +)
Retracting elaborate*reward*based*on*reward
 -->
 (R963 ^value 1 +)
 (R1 ^reward R963 +)
Retracting elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir R +)
Retracting rl*prefer*rvt*predict-no*H0*4
 -->
 (S1 ^operator O1920 = 0.1269768259493387)
Retracting rl*prefer*rvt*predict-no*H0*4*H1*13
 -->
 (S1 ^operator O1920 = 0.4910065094545203)
Retracting rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O1919 = 0.3829271874912855)
Retracting rl*prefer*rvt*predict-yes*H0*3*H1*14
 -->
 (S1 ^operator O1919 = 0.6170827253998104)
=>WM: (13498: S1 ^operator O1922 +)
=>WM: (13497: S1 ^operator O1921 +)
=>WM: (13496: O1922 ^name predict-no)
=>WM: (13495: O1921 ^name predict-yes)
=>WM: (13494: R964 ^value 1)
=>WM: (13493: R1 ^reward R964)
=>WM: (13492: I3 ^see 1)
<=WM: (13483: S1 ^operator O1919 +)
<=WM: (13485: S1 ^operator O1919)
<=WM: (13484: S1 ^operator O1920 +)
<=WM: (13478: R1 ^reward R963)
<=WM: (13381: I3 ^see 0)
<=WM: (13481: O1920 ^name predict-no)
<=WM: (13480: O1919 ^name predict-yes)
<=WM: (13479: R963 ^value 1)

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing prefer*rvt*predict-yes*H0
 -->
Firing rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O1921 = 0.3829271874912855)
Firing prefer*rvt*predict-yes*H0*3*H1
 -->
Firing rl*prefer*rvt*predict-yes*H0*3*H1*16
 -->
 (S1 ^operator O1921 = 0.08783148430849691)
Firing prefer*rvt*predict-no*H0
 -->
Firing rl*prefer*rvt*predict-no*H0*4
 -->
 (S1 ^operator O1922 = 0.1269768259493387)
Firing prefer*rvt*predict-no*H0*4*H1
 -->
Firing rl*prefer*rvt*predict-no*H0*4*H1*15
 -->
 (S1 ^operator O1922 = 0.873023493232603)
 inner elaboration loop at bottom goal.
Retracting rl*prefer*rvt*predict-no*H0*4
 -->
 (S1 ^operator O1920 = 0.1269768259493387)
Retracting rl*prefer*rvt*predict-no*H0*4*H1*15
 -->
 (S1 ^operator O1920 = 0.873023493232603)
Retracting rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O1919 = 0.3829271874912855)
Retracting rl*prefer*rvt*predict-yes*H0*3*H1*16
 -->
 (S1 ^operator O1919 = 0.08783148430849691)

--- END Proposal Phase ---

--- Decision Phase ---
RL update rl*prefer*rvt*predict-yes*H0*3 0.673122 -0.290194 0.382927 -> 0.67312 -0.290194 0.382926(R,m,v=1,0.959184,0.0394185)
RL update rl*prefer*rvt*predict-yes*H0*3*H1*14 0.326888 0.290195 0.617083 -> 0.326886 0.290195 0.617081(R,m,v=1,1,0)
=>WM: (13499: S1 ^operator O1922)

   961:    O: O1922 (predict-no)
--- END Decision Phase ---

--- Application Phase ---
	--- Firing Productions (PE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing apply*operator
 -->
 (I3 ^predict-no N961 +  :O )
Firing apply*operator*complete
 -->
 (I3 ^predict-yes N960 -  :O )
 inner elaboration loop at bottom goal.
	--- Change Working Memory (PE) ---
=>WM: (13500: I3 ^predict-no N961)
<=WM: (13487: N960 ^status complete)
<=WM: (13486: I3 ^predict-yes N960)
	--- Firing Productions (IE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing monitor*world
 -->

I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
	--- Change Working Memory (IE) ---

--- END Application Phase ---
--- Output Phase ---
ENV: Agent did: predict-no for direction R in state State-B
In  State-B moving R
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isL
--- END Output Phase ---
---- Input Phase --- 
=>WM: (13504: I2 ^dir L)
=>WM: (13503: I2 ^reward 1)
=>WM: (13502: I2 ^see 0)
=>WM: (13501: N961 ^status complete)
<=WM: (13490: I2 ^dir R)
<=WM: (13489: I2 ^reward 1)
<=WM: (13488: I2 ^see 1)
=>WM: (13505: I2 ^level-1 R0-root)
<=WM: (13491: I2 ^level-1 R1-root)

--- END Input Phase --- 

--- Proposal Phase ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing rl*prefer*rvt*predict-yes*H0*1*H1*19
 -->
 (S1 ^operator O1921 = 0.4768849116445159)
Firing rl*prefer*rvt*predict-no*H0*2*H1*7
 -->
 (S1 ^operator O1922 = 0.1700769046561409)
Firing prefer*rvt*predict-no*H0*2*H1
 -->
Firing prefer*rvt*predict-yes*H0*1*H1
 -->
Firing elaborate*copy-see-to-output-link
 -->
 (I3 ^see 0 +)
Firing elaborate*reward*based*on*reward
 -->
 (R965 ^value 1 +)
 (R1 ^reward R965 +)
Firing propose*predict-yes
 -->
 (O1923 ^name predict-yes +)
 (S1 ^operator O1923 +)
Firing propose*predict-no
 -->
 (O1924 ^name predict-no +)
 (S1 ^operator O1924 +)
Firing rl*prefer*rvt*predict-no*H0*2
 -->
 (S1 ^operator O1922 = 0.255013280266792)
Firing rl*prefer*rvt*predict-yes*H0*1
 -->
 (S1 ^operator O1921 = 0.5231208125838516)
Firing prefer*rvt*predict-yes*H0
 -->
Firing prefer*rvt*predict-no*H0
 -->
Firing elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir L +)
 inner elaboration loop at bottom goal.
Retracting elaborate*copy-see-to-output-link
 -->
 (I3 ^see 1 +)
Retracting propose*predict-no
 -->
 (O1922 ^name predict-no +)
 (S1 ^operator O1922 +)
Retracting propose*predict-yes
 -->
 (O1921 ^name predict-yes +)
 (S1 ^operator O1921 +)
Retracting elaborate*reward*based*on*reward
 -->
 (R964 ^value 1 +)
 (R1 ^reward R964 +)
Retracting elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir R +)
Retracting rl*prefer*rvt*predict-no*H0*4*H1*15
 -->
 (S1 ^operator O1922 = 0.873023493232603)
Retracting rl*prefer*rvt*predict-no*H0*4
 -->
 (S1 ^operator O1922 = 0.1269768259493387)
Retracting rl*prefer*rvt*predict-yes*H0*3*H1*16
 -->
 (S1 ^operator O1921 = 0.08783148430849691)
Retracting rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O1921 = 0.3829257005576211)
=>WM: (13513: S1 ^operator O1924 +)
=>WM: (13512: S1 ^operator O1923 +)
=>WM: (13511: I3 ^dir L)
=>WM: (13510: O1924 ^name predict-no)
=>WM: (13509: O1923 ^name predict-yes)
=>WM: (13508: R965 ^value 1)
=>WM: (13507: R1 ^reward R965)
=>WM: (13506: I3 ^see 0)
<=WM: (13497: S1 ^operator O1921 +)
<=WM: (13498: S1 ^operator O1922 +)
<=WM: (13499: S1 ^operator O1922)
<=WM: (13482: I3 ^dir R)
<=WM: (13493: R1 ^reward R964)
<=WM: (13492: I3 ^see 1)
<=WM: (13496: O1922 ^name predict-no)
<=WM: (13495: O1921 ^name predict-yes)
<=WM: (13494: R964 ^value 1)

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing prefer*rvt*predict-yes*H0
 -->
Firing rl*prefer*rvt*predict-yes*H0*1
 -->
 (S1 ^operator O1923 = 0.5231208125838516)
Firing prefer*rvt*predict-yes*H0*1*H1
 -->
Firing rl*prefer*rvt*predict-yes*H0*1*H1*19
 -->
 (S1 ^operator O1923 = 0.4768849116445159)
Firing prefer*rvt*predict-no*H0
 -->
Firing rl*prefer*rvt*predict-no*H0*2
 -->
 (S1 ^operator O1924 = 0.255013280266792)
Firing prefer*rvt*predict-no*H0*2*H1
 -->
Firing rl*prefer*rvt*predict-no*H0*2*H1*7
 -->
 (S1 ^operator O1924 = 0.1700769046561409)
 inner elaboration loop at bottom goal.
Retracting rl*prefer*rvt*predict-no*H0*2
 -->
 (S1 ^operator O1922 = 0.255013280266792)
Retracting rl*prefer*rvt*predict-no*H0*2*H1*7
 -->
 (S1 ^operator O1922 = 0.1700769046561409)
Retracting rl*prefer*rvt*predict-yes*H0*1
 -->
 (S1 ^operator O1921 = 0.5231208125838516)
Retracting rl*prefer*rvt*predict-yes*H0*1*H1*19
 -->
 (S1 ^operator O1921 = 0.4768849116445159)

--- END Proposal Phase ---

--- Decision Phase ---
RL update rl*prefer*rvt*predict-no*H0*4 0.814714 -0.687737 0.126977 -> 0.814714 -0.687737 0.126977(R,m,v=1,0.947674,0.0498776)
RL update rl*prefer*rvt*predict-no*H0*4*H1*15 0.185286 0.687737 0.873023 -> 0.185286 0.687737 0.873023(R,m,v=1,1,0)
=>WM: (13514: S1 ^operator O1923)

   962:    O: O1923 (predict-yes)
--- END Decision Phase ---

--- Application Phase ---
	--- Firing Productions (PE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing apply*operator
 -->
 (I3 ^predict-yes N962 +  :O )
Firing apply*operator*complete
 -->
 (I3 ^predict-no N961 -  :O )
 inner elaboration loop at bottom goal.
	--- Change Working Memory (PE) ---
=>WM: (13515: I3 ^predict-yes N962)
<=WM: (13501: N961 ^status complete)
<=WM: (13500: I3 ^predict-no N961)
	--- Firing Productions (IE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing monitor*world
 -->

I see 1 and I'm going to do: predict-yes inner elaboration loop at bottom goal.
	--- Change Working Memory (IE) ---

--- END Application Phase ---
--- Output Phase ---
ENV: Agent did: predict-yes for direction L in state State-B
In  State-B moving L
ENV: (next state, see, prediction correct?) = (State-A, 1, True)
predict error 0
dir: dir isR
--- END Output Phase ---
/|\--- Input Phase --- 
=>WM: (13519: I2 ^dir R)
=>WM: (13518: I2 ^reward 1)
=>WM: (13517: I2 ^see 1)
=>WM: (13516: N962 ^status complete)
<=WM: (13504: I2 ^dir L)
<=WM: (13503: I2 ^reward 1)
<=WM: (13502: I2 ^see 0)
=>WM: (13520: I2 ^level-1 L1-root)
<=WM: (13505: I2 ^level-1 R0-root)

--- END Input Phase --- 

--- Proposal Phase ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing rl*prefer*rvt*predict-yes*H0*3*H1*9
 -->
 (S1 ^operator O1923 = 0.6170188666021243)
Firing rl*prefer*rvt*predict-no*H0*4*H1*8
 -->
 (S1 ^operator O1924 = 0.4901349546100854)
Firing prefer*rvt*predict-no*H0*4*H1
 -->
Firing prefer*rvt*predict-yes*H0*3*H1
 -->
Firing elaborate*copy-see-to-output-link
 -->
 (I3 ^see 1 +)
Firing elaborate*reward*based*on*reward
 -->
 (R966 ^value 1 +)
 (R1 ^reward R966 +)
Firing propose*predict-yes
 -->
 (O1925 ^name predict-yes +)
 (S1 ^operator O1925 +)
Firing propose*predict-no
 -->
 (O1926 ^name predict-no +)
 (S1 ^operator O1926 +)
Firing rl*prefer*rvt*predict-no*H0*4
 -->
 (S1 ^operator O1924 = 0.1269767780720474)
Firing rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O1923 = 0.3829257005576211)
Firing prefer*rvt*predict-yes*H0
 -->
Firing prefer*rvt*predict-no*H0
 -->
Firing elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir R +)
 inner elaboration loop at bottom goal.
Retracting elaborate*copy-see-to-output-link
 -->
 (I3 ^see 0 +)
Retracting propose*predict-no
 -->
 (O1924 ^name predict-no +)
 (S1 ^operator O1924 +)
Retracting propose*predict-yes
 -->
 (O1923 ^name predict-yes +)
 (S1 ^operator O1923 +)
Retracting elaborate*reward*based*on*reward
 -->
 (R965 ^value 1 +)
 (R1 ^reward R965 +)
Retracting elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir L +)
Retracting rl*prefer*rvt*predict-no*H0*2*H1*7
 -->
 (S1 ^operator O1924 = 0.1700769046561409)
Retracting rl*prefer*rvt*predict-no*H0*2
 -->
 (S1 ^operator O1924 = 0.255013280266792)
Retracting rl*prefer*rvt*predict-yes*H0*1*H1*19
 -->
 (S1 ^operator O1923 = 0.4768849116445159)
Retracting rl*prefer*rvt*predict-yes*H0*1
 -->
 (S1 ^operator O1923 = 0.5231208125838516)
=>WM: (13528: S1 ^operator O1926 +)
=>WM: (13527: S1 ^operator O1925 +)
=>WM: (13526: I3 ^dir R)
=>WM: (13525: O1926 ^name predict-no)
=>WM: (13524: O1925 ^name predict-yes)
=>WM: (13523: R966 ^value 1)
=>WM: (13522: R1 ^reward R966)
=>WM: (13521: I3 ^see 1)
<=WM: (13512: S1 ^operator O1923 +)
<=WM: (13514: S1 ^operator O1923)
<=WM: (13513: S1 ^operator O1924 +)
<=WM: (13511: I3 ^dir L)
<=WM: (13507: R1 ^reward R965)
<=WM: (13506: I3 ^see 0)
<=WM: (13510: O1924 ^name predict-no)
<=WM: (13509: O1923 ^name predict-yes)
<=WM: (13508: R965 ^value 1)

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing prefer*rvt*predict-yes*H0
 -->
Firing rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O1925 = 0.3829257005576211)
Firing prefer*rvt*predict-yes*H0*3*H1
 -->
Firing rl*prefer*rvt*predict-yes*H0*3*H1*9
 -->
 (S1 ^operator O1925 = 0.6170188666021243)
Firing prefer*rvt*predict-no*H0
 -->
Firing rl*prefer*rvt*predict-no*H0*4
 -->
 (S1 ^operator O1926 = 0.1269767780720474)
Firing prefer*rvt*predict-no*H0*4*H1
 -->
Firing rl*prefer*rvt*predict-no*H0*4*H1*8
 -->
 (S1 ^operator O1926 = 0.4901349546100854)
 inner elaboration loop at bottom goal.
Retracting rl*prefer*rvt*predict-no*H0*4
 -->
 (S1 ^operator O1924 = 0.1269767780720474)
Retracting rl*prefer*rvt*predict-no*H0*4*H1*8
 -->
 (S1 ^operator O1924 = 0.4901349546100854)
Retracting rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O1923 = 0.3829257005576211)
Retracting rl*prefer*rvt*predict-yes*H0*3*H1*9
 -->
 (S1 ^operator O1923 = 0.6170188666021243)

--- END Proposal Phase ---

--- Decision Phase ---
RL update rl*prefer*rvt*predict-yes*H0*1 0.727961 -0.20484 0.523121 -> 0.72796 -0.20484 0.52312(R,m,v=1,0.978102,0.0215758)
RL update rl*prefer*rvt*predict-yes*H0*1*H1*19 0.272047 0.204838 0.476885 -> 0.272045 0.204839 0.476884(R,m,v=1,1,0)
=>WM: (13529: S1 ^operator O1925)

   963:    O: O1925 (predict-yes)
--- END Decision Phase ---

--- Application Phase ---
	--- Firing Productions (PE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing apply*operator
 -->
 (I3 ^predict-yes N963 +  :O )
Firing apply*operator*complete
 -->
 (I3 ^predict-yes N962 -  :O )
 inner elaboration loop at bottom goal.
	--- Change Working Memory (PE) ---
=>WM: (13530: I3 ^predict-yes N963)
<=WM: (13516: N962 ^status complete)
<=WM: (13515: I3 ^predict-yes N962)
	--- Firing Productions (IE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing monitor*world
 -->

I see 1 and I'm going to do: predict-yes inner elaboration loop at bottom goal.
	--- Change Working Memory (IE) ---

--- END Application Phase ---
--- Output Phase ---
ENV: Agent did: predict-yes for direction R in state State-A
In  State-A moving R
ENV: (next state, see, prediction correct?) = (State-B, 1, True)
predict error 0
dir: dir isU
--- END Output Phase ---
-/--- Input Phase --- 
=>WM: (13534: I2 ^dir U)
=>WM: (13533: I2 ^reward 1)
=>WM: (13532: I2 ^see 1)
=>WM: (13531: N963 ^status complete)
<=WM: (13519: I2 ^dir R)
<=WM: (13518: I2 ^reward 1)
<=WM: (13517: I2 ^see 1)
=>WM: (13535: I2 ^level-1 R1-root)
<=WM: (13520: I2 ^level-1 L1-root)

--- END Input Phase --- 

--- Proposal Phase ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing elaborate*copy-see-to-output-link
 -->
 (I3 ^see 1 +)
Firing elaborate*reward*based*on*reward
 -->
 (R967 ^value 1 +)
 (R1 ^reward R967 +)
Firing propose*predict-yes
 -->
 (O1927 ^name predict-yes +)
 (S1 ^operator O1927 +)
Firing propose*predict-no
 -->
 (O1928 ^name predict-no +)
 (S1 ^operator O1928 +)
Firing rl*prefer*rvt*predict-no*H0*6
 -->
 (S1 ^operator O1926 = 0.9999999999999999)
Firing rl*prefer*rvt*predict-yes*H0*5
 -->
 (S1 ^operator O1925 = 0.)
Firing prefer*rvt*predict-yes*H0
 -->
Firing prefer*rvt*predict-no*H0
 -->
Firing elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir U +)
 inner elaboration loop at bottom goal.
Retracting elaborate*copy-see-to-output-link
 -->
 (I3 ^see 1 +)
Retracting propose*predict-no
 -->
 (O1926 ^name predict-no +)
 (S1 ^operator O1926 +)
Retracting propose*predict-yes
 -->
 (O1925 ^name predict-yes +)
 (S1 ^operator O1925 +)
Retracting elaborate*reward*based*on*reward
 -->
 (R966 ^value 1 +)
 (R1 ^reward R966 +)
Retracting elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir R +)
Retracting rl*prefer*rvt*predict-no*H0*4*H1*8
 -->
 (S1 ^operator O1926 = 0.4901349546100854)
Retracting rl*prefer*rvt*predict-no*H0*4
 -->
 (S1 ^operator O1926 = 0.1269767780720474)
Retracting rl*prefer*rvt*predict-yes*H0*3*H1*9
 -->
 (S1 ^operator O1925 = 0.6170188666021243)
Retracting rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O1925 = 0.3829257005576211)
=>WM: (13542: S1 ^operator O1928 +)
=>WM: (13541: S1 ^operator O1927 +)
=>WM: (13540: I3 ^dir U)
=>WM: (13539: O1928 ^name predict-no)
=>WM: (13538: O1927 ^name predict-yes)
=>WM: (13537: R967 ^value 1)
=>WM: (13536: R1 ^reward R967)
<=WM: (13527: S1 ^operator O1925 +)
<=WM: (13529: S1 ^operator O1925)
<=WM: (13528: S1 ^operator O1926 +)
<=WM: (13526: I3 ^dir R)
<=WM: (13522: R1 ^reward R966)
<=WM: (13525: O1926 ^name predict-no)
<=WM: (13524: O1925 ^name predict-yes)
<=WM: (13523: R966 ^value 1)

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing prefer*rvt*predict-yes*H0
 -->
Firing rl*prefer*rvt*predict-yes*H0*5
 -->
 (S1 ^operator O1927 = 0.)
Firing prefer*rvt*predict-no*H0
 -->
Firing rl*prefer*rvt*predict-no*H0*6
 -->
 (S1 ^operator O1928 = 0.9999999999999999)
 inner elaboration loop at bottom goal.
Retracting rl*prefer*rvt*predict-no*H0*6
 -->
 (S1 ^operator O1926 = 0.9999999999999999)
Retracting rl*prefer*rvt*predict-yes*H0*5
 -->
 (S1 ^operator O1925 = 0.)

--- END Proposal Phase ---

--- Decision Phase ---
RL update rl*prefer*rvt*predict-yes*H0*3 0.67312 -0.290194 0.382926 -> 0.673128 -0.290194 0.382934(R,m,v=1,0.959459,0.0391616)
RL update rl*prefer*rvt*predict-yes*H0*3*H1*9 0.326829 0.29019 0.617019 -> 0.326837 0.29019 0.617027(R,m,v=1,1,0)
=>WM: (13543: S1 ^operator O1928)

   964:    O: O1928 (predict-no)
--- END Decision Phase ---

--- Application Phase ---
	--- Firing Productions (PE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing apply*operator
 -->
 (I3 ^predict-no N964 +  :O )
Firing apply*operator*complete
 -->
 (I3 ^predict-yes N963 -  :O )
 inner elaboration loop at bottom goal.
	--- Change Working Memory (PE) ---
=>WM: (13544: I3 ^predict-no N964)
<=WM: (13531: N963 ^status complete)
<=WM: (13530: I3 ^predict-yes N963)
	--- Firing Productions (IE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing monitor*world
 -->

I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
	--- Change Working Memory (IE) ---

--- END Application Phase ---
--- Output Phase ---
ENV: Agent did: predict-no for direction U in state State-B
In  State-B moving U
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isL
--- END Output Phase ---
|\---- Input Phase --- 
=>WM: (13548: I2 ^dir L)
=>WM: (13547: I2 ^reward 1)
=>WM: (13546: I2 ^see 0)
=>WM: (13545: N964 ^status complete)
<=WM: (13534: I2 ^dir U)
<=WM: (13533: I2 ^reward 1)
<=WM: (13532: I2 ^see 1)
=>WM: (13549: I2 ^level-1 R1-root)
<=WM: (13535: I2 ^level-1 R1-root)

--- END Input Phase --- 

--- Proposal Phase ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing rl*prefer*rvt*predict-yes*H0*1*H1*22
 -->
 (S1 ^operator O1927 = 0.4768766075457324)
Firing rl*prefer*rvt*predict-no*H0*2*H1*10
 -->
 (S1 ^operator O1928 = -0.01194930198035649)
Firing prefer*rvt*predict-no*H0*2*H1
 -->
Firing prefer*rvt*predict-yes*H0*1*H1
 -->
Firing elaborate*copy-see-to-output-link
 -->
 (I3 ^see 0 +)
Firing elaborate*reward*based*on*reward
 -->
 (R968 ^value 1 +)
 (R1 ^reward R968 +)
Firing propose*predict-yes
 -->
 (O1929 ^name predict-yes +)
 (S1 ^operator O1929 +)
Firing propose*predict-no
 -->
 (O1930 ^name predict-no +)
 (S1 ^operator O1930 +)
Firing rl*prefer*rvt*predict-no*H0*2
 -->
 (S1 ^operator O1928 = 0.255013280266792)
Firing rl*prefer*rvt*predict-yes*H0*1
 -->
 (S1 ^operator O1927 = 0.5231199539495964)
Firing prefer*rvt*predict-yes*H0
 -->
Firing prefer*rvt*predict-no*H0
 -->
Firing elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir L +)
 inner elaboration loop at bottom goal.
Retracting elaborate*copy-see-to-output-link
 -->
 (I3 ^see 1 +)
Retracting propose*predict-no
 -->
 (O1928 ^name predict-no +)
 (S1 ^operator O1928 +)
Retracting propose*predict-yes
 -->
 (O1927 ^name predict-yes +)
 (S1 ^operator O1927 +)
Retracting elaborate*reward*based*on*reward
 -->
 (R967 ^value 1 +)
 (R1 ^reward R967 +)
Retracting elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir U +)
Retracting rl*prefer*rvt*predict-no*H0*6
 -->
 (S1 ^operator O1928 = 0.9999999999999999)
Retracting rl*prefer*rvt*predict-yes*H0*5
 -->
 (S1 ^operator O1927 = 0.)
=>WM: (13557: S1 ^operator O1930 +)
=>WM: (13556: S1 ^operator O1929 +)
=>WM: (13555: I3 ^dir L)
=>WM: (13554: O1930 ^name predict-no)
=>WM: (13553: O1929 ^name predict-yes)
=>WM: (13552: R968 ^value 1)
=>WM: (13551: R1 ^reward R968)
=>WM: (13550: I3 ^see 0)
<=WM: (13541: S1 ^operator O1927 +)
<=WM: (13542: S1 ^operator O1928 +)
<=WM: (13543: S1 ^operator O1928)
<=WM: (13540: I3 ^dir U)
<=WM: (13536: R1 ^reward R967)
<=WM: (13521: I3 ^see 1)
<=WM: (13539: O1928 ^name predict-no)
<=WM: (13538: O1927 ^name predict-yes)
<=WM: (13537: R967 ^value 1)

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing prefer*rvt*predict-yes*H0
 -->
Firing rl*prefer*rvt*predict-yes*H0*1*H1*22
 -->
 (S1 ^operator O1929 = 0.4768766075457324)
Firing rl*prefer*rvt*predict-yes*H0*1
 -->
 (S1 ^operator O1929 = 0.5231199539495964)
Firing prefer*rvt*predict-yes*H0*1*H1
 -->
Firing prefer*rvt*predict-no*H0
 -->
Firing rl*prefer*rvt*predict-no*H0*2*H1*10
 -->
 (S1 ^operator O1930 = -0.01194930198035649)
Firing rl*prefer*rvt*predict-no*H0*2
 -->
 (S1 ^operator O1930 = 0.255013280266792)
Firing prefer*rvt*predict-no*H0*2*H1
 -->
 inner elaboration loop at bottom goal.
Retracting rl*prefer*rvt*predict-no*H0*2
 -->
 (S1 ^operator O1928 = 0.255013280266792)
Retracting rl*prefer*rvt*predict-no*H0*2*H1*10
 -->
 (S1 ^operator O1928 = -0.01194930198035649)
Retracting rl*prefer*rvt*predict-yes*H0*1
 -->
 (S1 ^operator O1927 = 0.5231199539495964)
Retracting rl*prefer*rvt*predict-yes*H0*1*H1*22
 -->
 (S1 ^operator O1927 = 0.4768766075457324)

--- END Proposal Phase ---

--- Decision Phase ---
RL update rl*prefer*rvt*predict-no*H0*6 1 0 1 -> 1 0 1(R,m,v=1,1,0)
=>WM: (13558: S1 ^operator O1929)

   965:    O: O1929 (predict-yes)
--- END Decision Phase ---

--- Application Phase ---
	--- Firing Productions (PE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing apply*operator
 -->
 (I3 ^predict-yes N965 +  :O )
Firing apply*operator*complete
 -->
 (I3 ^predict-no N964 -  :O )
 inner elaboration loop at bottom goal.
	--- Change Working Memory (PE) ---
=>WM: (13559: I3 ^predict-yes N965)
<=WM: (13545: N964 ^status complete)
<=WM: (13544: I3 ^predict-no N964)
	--- Firing Productions (IE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing monitor*world
 -->

I see 1 and I'm going to do: predict-yes inner elaboration loop at bottom goal.
	--- Change Working Memory (IE) ---

--- END Application Phase ---
--- Output Phase ---
ENV: Agent did: predict-yes for direction L in state State-B
In  State-B moving L
ENV: (next state, see, prediction correct?) = (State-A, 1, True)
predict error 0
dir: dir isL
--- END Output Phase ---
/|\--- Input Phase --- 
=>WM: (13563: I2 ^dir L)
=>WM: (13562: I2 ^reward 1)
=>WM: (13561: I2 ^see 1)
=>WM: (13560: N965 ^status complete)
<=WM: (13548: I2 ^dir L)
<=WM: (13547: I2 ^reward 1)
<=WM: (13546: I2 ^see 0)
=>WM: (13564: I2 ^level-1 L1-root)
<=WM: (13549: I2 ^level-1 R1-root)

--- END Input Phase --- 

--- Proposal Phase ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing rl*prefer*rvt*predict-yes*H0*1*H1*20
 -->
 (S1 ^operator O1929 = 0.1693592933936033)
Firing rl*prefer*rvt*predict-no*H0*2*H1*11
 -->
 (S1 ^operator O1930 = 0.7449862824724345)
Firing prefer*rvt*predict-no*H0*2*H1
 -->
Firing prefer*rvt*predict-yes*H0*1*H1
 -->
Firing elaborate*copy-see-to-output-link
 -->
 (I3 ^see 1 +)
Firing elaborate*reward*based*on*reward
 -->
 (R969 ^value 1 +)
 (R1 ^reward R969 +)
Firing propose*predict-yes
 -->
 (O1931 ^name predict-yes +)
 (S1 ^operator O1931 +)
Firing propose*predict-no
 -->
 (O1932 ^name predict-no +)
 (S1 ^operator O1932 +)
Firing rl*prefer*rvt*predict-no*H0*2
 -->
 (S1 ^operator O1930 = 0.255013280266792)
Firing rl*prefer*rvt*predict-yes*H0*1
 -->
 (S1 ^operator O1929 = 0.5231199539495964)
Firing prefer*rvt*predict-yes*H0
 -->
Firing prefer*rvt*predict-no*H0
 -->
Firing elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir L +)
 inner elaboration loop at bottom goal.
Retracting elaborate*copy-see-to-output-link
 -->
 (I3 ^see 0 +)
Retracting propose*predict-no
 -->
 (O1930 ^name predict-no +)
 (S1 ^operator O1930 +)
Retracting propose*predict-yes
 -->
 (O1929 ^name predict-yes +)
 (S1 ^operator O1929 +)
Retracting elaborate*reward*based*on*reward
 -->
 (R968 ^value 1 +)
 (R1 ^reward R968 +)
Retracting elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir L +)
Retracting rl*prefer*rvt*predict-no*H0*2
 -->
 (S1 ^operator O1930 = 0.255013280266792)
Retracting rl*prefer*rvt*predict-no*H0*2*H1*10
 -->
 (S1 ^operator O1930 = -0.01194930198035649)
Retracting rl*prefer*rvt*predict-yes*H0*1
 -->
 (S1 ^operator O1929 = 0.5231199539495964)
Retracting rl*prefer*rvt*predict-yes*H0*1*H1*22
 -->
 (S1 ^operator O1929 = 0.4768766075457324)
=>WM: (13571: S1 ^operator O1932 +)
=>WM: (13570: S1 ^operator O1931 +)
=>WM: (13569: O1932 ^name predict-no)
=>WM: (13568: O1931 ^name predict-yes)
=>WM: (13567: R969 ^value 1)
=>WM: (13566: R1 ^reward R969)
=>WM: (13565: I3 ^see 1)
<=WM: (13556: S1 ^operator O1929 +)
<=WM: (13558: S1 ^operator O1929)
<=WM: (13557: S1 ^operator O1930 +)
<=WM: (13551: R1 ^reward R968)
<=WM: (13550: I3 ^see 0)
<=WM: (13554: O1930 ^name predict-no)
<=WM: (13553: O1929 ^name predict-yes)
<=WM: (13552: R968 ^value 1)

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing prefer*rvt*predict-yes*H0
 -->
Firing rl*prefer*rvt*predict-yes*H0*1
 -->
 (S1 ^operator O1931 = 0.5231199539495964)
Firing prefer*rvt*predict-yes*H0*1*H1
 -->
Firing rl*prefer*rvt*predict-yes*H0*1*H1*20
 -->
 (S1 ^operator O1931 = 0.1693592933936033)
Firing prefer*rvt*predict-no*H0
 -->
Firing rl*prefer*rvt*predict-no*H0*2
 -->
 (S1 ^operator O1932 = 0.255013280266792)
Firing prefer*rvt*predict-no*H0*2*H1
 -->
Firing rl*prefer*rvt*predict-no*H0*2*H1*11
 -->
 (S1 ^operator O1932 = 0.7449862824724345)
 inner elaboration loop at bottom goal.
Retracting rl*prefer*rvt*predict-no*H0*2
 -->
 (S1 ^operator O1930 = 0.255013280266792)
Retracting rl*prefer*rvt*predict-no*H0*2*H1*11
 -->
 (S1 ^operator O1930 = 0.7449862824724345)
Retracting rl*prefer*rvt*predict-yes*H0*1
 -->
 (S1 ^operator O1929 = 0.5231199539495964)
Retracting rl*prefer*rvt*predict-yes*H0*1*H1*20
 -->
 (S1 ^operator O1929 = 0.1693592933936033)

--- END Proposal Phase ---

--- Decision Phase ---
RL update rl*prefer*rvt*predict-yes*H0*1 0.72796 -0.20484 0.52312 -> 0.727961 -0.20484 0.52312(R,m,v=1,0.978261,0.0214218)
RL update rl*prefer*rvt*predict-yes*H0*1*H1*22 0.272036 0.204841 0.476877 -> 0.272036 0.204841 0.476877(R,m,v=1,1,0)
=>WM: (13572: S1 ^operator O1932)

   966:    O: O1932 (predict-no)
--- END Decision Phase ---

--- Application Phase ---
	--- Firing Productions (PE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing apply*operator
 -->
 (I3 ^predict-no N966 +  :O )
Firing apply*operator*complete
 -->
 (I3 ^predict-yes N965 -  :O )
 inner elaboration loop at bottom goal.
	--- Change Working Memory (PE) ---
=>WM: (13573: I3 ^predict-no N966)
<=WM: (13560: N965 ^status complete)
<=WM: (13559: I3 ^predict-yes N965)
	--- Firing Productions (IE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing monitor*world
 -->

I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
	--- Change Working Memory (IE) ---

--- END Application Phase ---
--- Output Phase ---
ENV: Agent did: predict-no for direction L in state State-A
In  State-A moving L
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isL
--- END Output Phase ---
---- Input Phase --- 
=>WM: (13577: I2 ^dir L)
=>WM: (13576: I2 ^reward 1)
=>WM: (13575: I2 ^see 0)
=>WM: (13574: N966 ^status complete)
<=WM: (13563: I2 ^dir L)
<=WM: (13562: I2 ^reward 1)
<=WM: (13561: I2 ^see 1)
=>WM: (13578: I2 ^level-1 L0-root)
<=WM: (13564: I2 ^level-1 L1-root)

--- END Input Phase --- 

--- Proposal Phase ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing rl*prefer*rvt*predict-yes*H0*1*H1*21
 -->
 (S1 ^operator O1931 = 0.3)
Firing rl*prefer*rvt*predict-no*H0*2*H1*12
 -->
 (S1 ^operator O1932 = 0.7449867911055725)
Firing prefer*rvt*predict-no*H0*2*H1
 -->
Firing prefer*rvt*predict-yes*H0*1*H1
 -->
Firing elaborate*copy-see-to-output-link
 -->
 (I3 ^see 0 +)
Firing elaborate*reward*based*on*reward
 -->
 (R970 ^value 1 +)
 (R1 ^reward R970 +)
Firing propose*predict-yes
 -->
 (O1933 ^name predict-yes +)
 (S1 ^operator O1933 +)
Firing propose*predict-no
 -->
 (O1934 ^name predict-no +)
 (S1 ^operator O1934 +)
Firing rl*prefer*rvt*predict-no*H0*2
 -->
 (S1 ^operator O1932 = 0.255013280266792)
Firing rl*prefer*rvt*predict-yes*H0*1
 -->
 (S1 ^operator O1931 = 0.5231204697252971)
Firing prefer*rvt*predict-yes*H0
 -->
Firing prefer*rvt*predict-no*H0
 -->
Firing elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir L +)
 inner elaboration loop at bottom goal.
Retracting elaborate*copy-see-to-output-link
 -->
 (I3 ^see 1 +)
Retracting propose*predict-no
 -->
 (O1932 ^name predict-no +)
 (S1 ^operator O1932 +)
Retracting propose*predict-yes
 -->
 (O1931 ^name predict-yes +)
 (S1 ^operator O1931 +)
Retracting elaborate*reward*based*on*reward
 -->
 (R969 ^value 1 +)
 (R1 ^reward R969 +)
Retracting elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir L +)
Retracting rl*prefer*rvt*predict-no*H0*2*H1*11
 -->
 (S1 ^operator O1932 = 0.7449862824724345)
Retracting rl*prefer*rvt*predict-no*H0*2
 -->
 (S1 ^operator O1932 = 0.255013280266792)
Retracting rl*prefer*rvt*predict-yes*H0*1*H1*20
 -->
 (S1 ^operator O1931 = 0.1693592933936033)
Retracting rl*prefer*rvt*predict-yes*H0*1
 -->
 (S1 ^operator O1931 = 0.5231204697252971)
=>WM: (13585: S1 ^operator O1934 +)
=>WM: (13584: S1 ^operator O1933 +)
=>WM: (13583: O1934 ^name predict-no)
=>WM: (13582: O1933 ^name predict-yes)
=>WM: (13581: R970 ^value 1)
=>WM: (13580: R1 ^reward R970)
=>WM: (13579: I3 ^see 0)
<=WM: (13570: S1 ^operator O1931 +)
<=WM: (13571: S1 ^operator O1932 +)
<=WM: (13572: S1 ^operator O1932)
<=WM: (13566: R1 ^reward R969)
<=WM: (13565: I3 ^see 1)
<=WM: (13569: O1932 ^name predict-no)
<=WM: (13568: O1931 ^name predict-yes)
<=WM: (13567: R969 ^value 1)

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing prefer*rvt*predict-yes*H0
 -->
Firing rl*prefer*rvt*predict-yes*H0*1
 -->
 (S1 ^operator O1933 = 0.5231204697252971)
Firing prefer*rvt*predict-yes*H0*1*H1
 -->
Firing rl*prefer*rvt*predict-yes*H0*1*H1*21
 -->
 (S1 ^operator O1933 = 0.3)
Firing prefer*rvt*predict-no*H0
 -->
Firing rl*prefer*rvt*predict-no*H0*2
 -->
 (S1 ^operator O1934 = 0.255013280266792)
Firing prefer*rvt*predict-no*H0*2*H1
 -->
Firing rl*prefer*rvt*predict-no*H0*2*H1*12
 -->
 (S1 ^operator O1934 = 0.7449867911055725)
 inner elaboration loop at bottom goal.
Retracting rl*prefer*rvt*predict-no*H0*2
 -->
 (S1 ^operator O1932 = 0.255013280266792)
Retracting rl*prefer*rvt*predict-no*H0*2*H1*12
 -->
 (S1 ^operator O1932 = 0.7449867911055725)
Retracting rl*prefer*rvt*predict-yes*H0*1
 -->
 (S1 ^operator O1931 = 0.5231204697252971)
Retracting rl*prefer*rvt*predict-yes*H0*1*H1*21
 -->
 (S1 ^operator O1931 = 0.3)

--- END Proposal Phase ---

--- Decision Phase ---
RL update rl*prefer*rvt*predict-no*H0*2 0.631495 -0.376482 0.255013 -> 0.631495 -0.376482 0.255013(R,m,v=1,0.914894,0.0782797)
RL update rl*prefer*rvt*predict-no*H0*2*H1*11 0.368505 0.376482 0.744986 -> 0.368505 0.376482 0.744986(R,m,v=1,1,0)
=>WM: (13586: S1 ^operator O1934)

   967:    O: O1934 (predict-no)
--- END Decision Phase ---

--- Application Phase ---
	--- Firing Productions (PE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing apply*operator
 -->
 (I3 ^predict-no N967 +  :O )
Firing apply*operator*complete
 -->
 (I3 ^predict-no N966 -  :O )
 inner elaboration loop at bottom goal.
	--- Change Working Memory (PE) ---
=>WM: (13587: I3 ^predict-no N967)
<=WM: (13574: N966 ^status complete)
<=WM: (13573: I3 ^predict-no N966)
	--- Firing Productions (IE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing monitor*world
 -->

I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
	--- Change Working Memory (IE) ---

--- END Application Phase ---
--- Output Phase ---
ENV: Agent did: predict-no for direction L in state State-A
In  State-A moving L
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isL
--- END Output Phase ---
/|\--- Input Phase --- 
=>WM: (13591: I2 ^dir L)
=>WM: (13590: I2 ^reward 1)
=>WM: (13589: I2 ^see 0)
=>WM: (13588: N967 ^status complete)
<=WM: (13577: I2 ^dir L)
<=WM: (13576: I2 ^reward 1)
<=WM: (13575: I2 ^see 0)
=>WM: (13592: I2 ^level-1 L0-root)
<=WM: (13578: I2 ^level-1 L0-root)

--- END Input Phase --- 

--- Proposal Phase ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing rl*prefer*rvt*predict-yes*H0*1*H1*21
 -->
 (S1 ^operator O1933 = 0.3)
Firing rl*prefer*rvt*predict-no*H0*2*H1*12
 -->
 (S1 ^operator O1934 = 0.7449867911055725)
Firing prefer*rvt*predict-no*H0*2*H1
 -->
Firing prefer*rvt*predict-yes*H0*1*H1
 -->
Firing elaborate*copy-see-to-output-link
 -->
 (I3 ^see 0 +)
Firing elaborate*reward*based*on*reward
 -->
 (R971 ^value 1 +)
 (R1 ^reward R971 +)
Firing propose*predict-yes
 -->
 (O1935 ^name predict-yes +)
 (S1 ^operator O1935 +)
Firing propose*predict-no
 -->
 (O1936 ^name predict-no +)
 (S1 ^operator O1936 +)
Firing rl*prefer*rvt*predict-no*H0*2
 -->
 (S1 ^operator O1934 = 0.255013345855908)
Firing rl*prefer*rvt*predict-yes*H0*1
 -->
 (S1 ^operator O1933 = 0.5231204697252971)
Firing prefer*rvt*predict-yes*H0
 -->
Firing prefer*rvt*predict-no*H0
 -->
Firing elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir L +)
 inner elaboration loop at bottom goal.
Retracting elaborate*copy-see-to-output-link
 -->
 (I3 ^see 0 +)
Retracting propose*predict-no
 -->
 (O1934 ^name predict-no +)
 (S1 ^operator O1934 +)
Retracting propose*predict-yes
 -->
 (O1933 ^name predict-yes +)
 (S1 ^operator O1933 +)
Retracting elaborate*reward*based*on*reward
 -->
 (R970 ^value 1 +)
 (R1 ^reward R970 +)
Retracting elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir L +)
Retracting rl*prefer*rvt*predict-no*H0*2*H1*12
 -->
 (S1 ^operator O1934 = 0.7449867911055725)
Retracting rl*prefer*rvt*predict-no*H0*2
 -->
 (S1 ^operator O1934 = 0.255013345855908)
Retracting rl*prefer*rvt*predict-yes*H0*1*H1*21
 -->
 (S1 ^operator O1933 = 0.3)
Retracting rl*prefer*rvt*predict-yes*H0*1
 -->
 (S1 ^operator O1933 = 0.5231204697252971)
=>WM: (13598: S1 ^operator O1936 +)
=>WM: (13597: S1 ^operator O1935 +)
=>WM: (13596: O1936 ^name predict-no)
=>WM: (13595: O1935 ^name predict-yes)
=>WM: (13594: R971 ^value 1)
=>WM: (13593: R1 ^reward R971)
<=WM: (13584: S1 ^operator O1933 +)
<=WM: (13585: S1 ^operator O1934 +)
<=WM: (13586: S1 ^operator O1934)
<=WM: (13580: R1 ^reward R970)
<=WM: (13583: O1934 ^name predict-no)
<=WM: (13582: O1933 ^name predict-yes)
<=WM: (13581: R970 ^value 1)

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing prefer*rvt*predict-yes*H0
 -->
Firing rl*prefer*rvt*predict-yes*H0*1
 -->
 (S1 ^operator O1935 = 0.5231204697252971)
Firing prefer*rvt*predict-yes*H0*1*H1
 -->
Firing rl*prefer*rvt*predict-yes*H0*1*H1*21
 -->
 (S1 ^operator O1935 = 0.3)
Firing prefer*rvt*predict-no*H0
 -->
Firing rl*prefer*rvt*predict-no*H0*2
 -->
 (S1 ^operator O1936 = 0.255013345855908)
Firing prefer*rvt*predict-no*H0*2*H1
 -->
Firing rl*prefer*rvt*predict-no*H0*2*H1*12
 -->
 (S1 ^operator O1936 = 0.7449867911055725)
 inner elaboration loop at bottom goal.
Retracting rl*prefer*rvt*predict-no*H0*2
 -->
 (S1 ^operator O1934 = 0.255013345855908)
Retracting rl*prefer*rvt*predict-no*H0*2*H1*12
 -->
 (S1 ^operator O1934 = 0.7449867911055725)
Retracting rl*prefer*rvt*predict-yes*H0*1
 -->
 (S1 ^operator O1933 = 0.5231204697252971)
Retracting rl*prefer*rvt*predict-yes*H0*1*H1*21
 -->
 (S1 ^operator O1933 = 0.3)

--- END Proposal Phase ---

--- Decision Phase ---
RL update rl*prefer*rvt*predict-no*H0*2 0.631495 -0.376482 0.255013 -> 0.631495 -0.376482 0.255013(R,m,v=1,0.915344,0.0779016)
RL update rl*prefer*rvt*predict-no*H0*2*H1*12 0.368505 0.376482 0.744987 -> 0.368505 0.376482 0.744987(R,m,v=1,1,0)
=>WM: (13599: S1 ^operator O1936)

   968:    O: O1936 (predict-no)
--- END Decision Phase ---

--- Application Phase ---
	--- Firing Productions (PE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing apply*operator
 -->
 (I3 ^predict-no N968 +  :O )
Firing apply*operator*complete
 -->
 (I3 ^predict-no N967 -  :O )
 inner elaboration loop at bottom goal.
	--- Change Working Memory (PE) ---
=>WM: (13600: I3 ^predict-no N968)
<=WM: (13588: N967 ^status complete)
<=WM: (13587: I3 ^predict-no N967)
	--- Firing Productions (IE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing monitor*world
 -->

I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
	--- Change Working Memory (IE) ---

--- END Application Phase ---
--- Output Phase ---
ENV: Agent did: predict-no for direction L in state State-A
In  State-A moving L
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isR
--- END Output Phase ---
-/--- Input Phase --- 
=>WM: (13604: I2 ^dir R)
=>WM: (13603: I2 ^reward 1)
=>WM: (13602: I2 ^see 0)
=>WM: (13601: N968 ^status complete)
<=WM: (13591: I2 ^dir L)
<=WM: (13590: I2 ^reward 1)
<=WM: (13589: I2 ^see 0)
=>WM: (13605: I2 ^level-1 L0-root)
<=WM: (13592: I2 ^level-1 L0-root)

--- END Input Phase --- 

--- Proposal Phase ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing rl*prefer*rvt*predict-yes*H0*3*H1*14
 -->
 (S1 ^operator O1935 = 0.6170812384661459)
Firing rl*prefer*rvt*predict-no*H0*4*H1*13
 -->
 (S1 ^operator O1936 = 0.4910065094545203)
Firing prefer*rvt*predict-no*H0*4*H1
 -->
Firing prefer*rvt*predict-yes*H0*3*H1
 -->
Firing elaborate*copy-see-to-output-link
 -->
 (I3 ^see 0 +)
Firing elaborate*reward*based*on*reward
 -->
 (R972 ^value 1 +)
 (R1 ^reward R972 +)
Firing propose*predict-yes
 -->
 (O1937 ^name predict-yes +)
 (S1 ^operator O1937 +)
Firing propose*predict-no
 -->
 (O1938 ^name predict-no +)
 (S1 ^operator O1938 +)
Firing rl*prefer*rvt*predict-no*H0*4
 -->
 (S1 ^operator O1936 = 0.1269767780720474)
Firing rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O1935 = 0.3829340154836592)
Firing prefer*rvt*predict-yes*H0
 -->
Firing prefer*rvt*predict-no*H0
 -->
Firing elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir R +)
 inner elaboration loop at bottom goal.
Retracting elaborate*copy-see-to-output-link
 -->
 (I3 ^see 0 +)
Retracting propose*predict-no
 -->
 (O1936 ^name predict-no +)
 (S1 ^operator O1936 +)
Retracting propose*predict-yes
 -->
 (O1935 ^name predict-yes +)
 (S1 ^operator O1935 +)
Retracting elaborate*reward*based*on*reward
 -->
 (R971 ^value 1 +)
 (R1 ^reward R971 +)
Retracting elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir L +)
Retracting rl*prefer*rvt*predict-no*H0*2*H1*12
 -->
 (S1 ^operator O1936 = 0.7449867705613504)
Retracting rl*prefer*rvt*predict-no*H0*2
 -->
 (S1 ^operator O1936 = 0.255013325311686)
Retracting rl*prefer*rvt*predict-yes*H0*1*H1*21
 -->
 (S1 ^operator O1935 = 0.3)
Retracting rl*prefer*rvt*predict-yes*H0*1
 -->
 (S1 ^operator O1935 = 0.5231204697252971)
=>WM: (13612: S1 ^operator O1938 +)
=>WM: (13611: S1 ^operator O1937 +)
=>WM: (13610: I3 ^dir R)
=>WM: (13609: O1938 ^name predict-no)
=>WM: (13608: O1937 ^name predict-yes)
=>WM: (13607: R972 ^value 1)
=>WM: (13606: R1 ^reward R972)
<=WM: (13597: S1 ^operator O1935 +)
<=WM: (13598: S1 ^operator O1936 +)
<=WM: (13599: S1 ^operator O1936)
<=WM: (13555: I3 ^dir L)
<=WM: (13593: R1 ^reward R971)
<=WM: (13596: O1936 ^name predict-no)
<=WM: (13595: O1935 ^name predict-yes)
<=WM: (13594: R971 ^value 1)

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing prefer*rvt*predict-yes*H0
 -->
Firing rl*prefer*rvt*predict-yes*H0*3*H1*14
 -->
 (S1 ^operator O1937 = 0.6170812384661459)
Firing rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O1937 = 0.3829340154836592)
Firing prefer*rvt*predict-yes*H0*3*H1
 -->
Firing prefer*rvt*predict-no*H0
 -->
Firing rl*prefer*rvt*predict-no*H0*4*H1*13
 -->
 (S1 ^operator O1938 = 0.4910065094545203)
Firing rl*prefer*rvt*predict-no*H0*4
 -->
 (S1 ^operator O1938 = 0.1269767780720474)
Firing prefer*rvt*predict-no*H0*4*H1
 -->
 inner elaboration loop at bottom goal.
Retracting rl*prefer*rvt*predict-no*H0*4
 -->
 (S1 ^operator O1936 = 0.1269767780720474)
Retracting rl*prefer*rvt*predict-no*H0*4*H1*13
 -->
 (S1 ^operator O1936 = 0.4910065094545203)
Retracting rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O1935 = 0.3829340154836592)
Retracting rl*prefer*rvt*predict-yes*H0*3*H1*14
 -->
 (S1 ^operator O1935 = 0.6170812384661459)

--- END Proposal Phase ---

--- Decision Phase ---
RL update rl*prefer*rvt*predict-no*H0*2 0.631495 -0.376482 0.255013 -> 0.631495 -0.376482 0.255013(R,m,v=1,0.915789,0.0775272)
RL update rl*prefer*rvt*predict-no*H0*2*H1*12 0.368505 0.376482 0.744987 -> 0.368505 0.376482 0.744987(R,m,v=1,1,0)
=>WM: (13613: S1 ^operator O1937)

   969:    O: O1937 (predict-yes)
--- END Decision Phase ---

--- Application Phase ---
	--- Firing Productions (PE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing apply*operator
 -->
 (I3 ^predict-yes N969 +  :O )
Firing apply*operator*complete
 -->
 (I3 ^predict-no N968 -  :O )
 inner elaboration loop at bottom goal.
	--- Change Working Memory (PE) ---
=>WM: (13614: I3 ^predict-yes N969)
<=WM: (13601: N968 ^status complete)
<=WM: (13600: I3 ^predict-no N968)
	--- Firing Productions (IE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing monitor*world
 -->

I see 1 and I'm going to do: predict-yes inner elaboration loop at bottom goal.
	--- Change Working Memory (IE) ---

--- END Application Phase ---
--- Output Phase ---
ENV: Agent did: predict-yes for direction R in state State-A
In  State-A moving R
ENV: (next state, see, prediction correct?) = (State-B, 1, True)
predict error 0
dir: dir isU
--- END Output Phase ---
|\---- Input Phase --- 
=>WM: (13618: I2 ^dir U)
=>WM: (13617: I2 ^reward 1)
=>WM: (13616: I2 ^see 1)
=>WM: (13615: N969 ^status complete)
<=WM: (13604: I2 ^dir R)
<=WM: (13603: I2 ^reward 1)
<=WM: (13602: I2 ^see 0)
=>WM: (13619: I2 ^level-1 R1-root)
<=WM: (13605: I2 ^level-1 L0-root)

--- END Input Phase --- 

--- Proposal Phase ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing elaborate*copy-see-to-output-link
 -->
 (I3 ^see 1 +)
Firing elaborate*reward*based*on*reward
 -->
 (R973 ^value 1 +)
 (R1 ^reward R973 +)
Firing propose*predict-yes
 -->
 (O1939 ^name predict-yes +)
 (S1 ^operator O1939 +)
Firing propose*predict-no
 -->
 (O1940 ^name predict-no +)
 (S1 ^operator O1940 +)
Firing rl*prefer*rvt*predict-no*H0*6
 -->
 (S1 ^operator O1938 = 0.9999999999999999)
Firing rl*prefer*rvt*predict-yes*H0*5
 -->
 (S1 ^operator O1937 = 0.)
Firing prefer*rvt*predict-yes*H0
 -->
Firing prefer*rvt*predict-no*H0
 -->
Firing elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir U +)
 inner elaboration loop at bottom goal.
Retracting elaborate*copy-see-to-output-link
 -->
 (I3 ^see 0 +)
Retracting propose*predict-no
 -->
 (O1938 ^name predict-no +)
 (S1 ^operator O1938 +)
Retracting propose*predict-yes
 -->
 (O1937 ^name predict-yes +)
 (S1 ^operator O1937 +)
Retracting elaborate*reward*based*on*reward
 -->
 (R972 ^value 1 +)
 (R1 ^reward R972 +)
Retracting elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir R +)
Retracting rl*prefer*rvt*predict-no*H0*4
 -->
 (S1 ^operator O1938 = 0.1269767780720474)
Retracting rl*prefer*rvt*predict-no*H0*4*H1*13
 -->
 (S1 ^operator O1938 = 0.4910065094545203)
Retracting rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O1937 = 0.3829340154836592)
Retracting rl*prefer*rvt*predict-yes*H0*3*H1*14
 -->
 (S1 ^operator O1937 = 0.6170812384661459)
=>WM: (13627: S1 ^operator O1940 +)
=>WM: (13626: S1 ^operator O1939 +)
=>WM: (13625: I3 ^dir U)
=>WM: (13624: O1940 ^name predict-no)
=>WM: (13623: O1939 ^name predict-yes)
=>WM: (13622: R973 ^value 1)
=>WM: (13621: R1 ^reward R973)
=>WM: (13620: I3 ^see 1)
<=WM: (13611: S1 ^operator O1937 +)
<=WM: (13613: S1 ^operator O1937)
<=WM: (13612: S1 ^operator O1938 +)
<=WM: (13610: I3 ^dir R)
<=WM: (13606: R1 ^reward R972)
<=WM: (13579: I3 ^see 0)
<=WM: (13609: O1938 ^name predict-no)
<=WM: (13608: O1937 ^name predict-yes)
<=WM: (13607: R972 ^value 1)

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing prefer*rvt*predict-yes*H0
 -->
Firing rl*prefer*rvt*predict-yes*H0*5
 -->
 (S1 ^operator O1939 = 0.)
Firing prefer*rvt*predict-no*H0
 -->
Firing rl*prefer*rvt*predict-no*H0*6
 -->
 (S1 ^operator O1940 = 0.9999999999999999)
 inner elaboration loop at bottom goal.
Retracting rl*prefer*rvt*predict-no*H0*6
 -->
 (S1 ^operator O1938 = 0.9999999999999999)
Retracting rl*prefer*rvt*predict-yes*H0*5
 -->
 (S1 ^operator O1937 = 0.)

--- END Proposal Phase ---

--- Decision Phase ---
RL update rl*prefer*rvt*predict-yes*H0*3 0.673128 -0.290194 0.382934 -> 0.673126 -0.290194 0.382932(R,m,v=1,0.959732,0.038908)
RL update rl*prefer*rvt*predict-yes*H0*3*H1*14 0.326886 0.290195 0.617081 -> 0.326884 0.290195 0.617079(R,m,v=1,1,0)
=>WM: (13628: S1 ^operator O1940)

   970:    O: O1940 (predict-no)
--- END Decision Phase ---

--- Application Phase ---
	--- Firing Productions (PE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing apply*operator
 -->
 (I3 ^predict-no N970 +  :O )
Firing apply*operator*complete
 -->
 (I3 ^predict-yes N969 -  :O )
 inner elaboration loop at bottom goal.
	--- Change Working Memory (PE) ---
=>WM: (13629: I3 ^predict-no N970)
<=WM: (13615: N969 ^status complete)
<=WM: (13614: I3 ^predict-yes N969)
	--- Firing Productions (IE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing monitor*world
 -->

I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
	--- Change Working Memory (IE) ---

--- END Application Phase ---
--- Output Phase ---
ENV: Agent did: predict-no for direction U in state State-B
In  State-B moving U
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isL
--- END Output Phase ---
/|--- Input Phase --- 
=>WM: (13633: I2 ^dir L)
=>WM: (13632: I2 ^reward 1)
=>WM: (13631: I2 ^see 0)
=>WM: (13630: N970 ^status complete)
<=WM: (13618: I2 ^dir U)
<=WM: (13617: I2 ^reward 1)
<=WM: (13616: I2 ^see 1)
=>WM: (13634: I2 ^level-1 R1-root)
<=WM: (13619: I2 ^level-1 R1-root)

--- END Input Phase --- 

--- Proposal Phase ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing rl*prefer*rvt*predict-yes*H0*1*H1*22
 -->
 (S1 ^operator O1939 = 0.4768771233214331)
Firing rl*prefer*rvt*predict-no*H0*2*H1*10
 -->
 (S1 ^operator O1940 = -0.01194930198035649)
Firing prefer*rvt*predict-no*H0*2*H1
 -->
Firing prefer*rvt*predict-yes*H0*1*H1
 -->
Firing elaborate*copy-see-to-output-link
 -->
 (I3 ^see 0 +)
Firing elaborate*reward*based*on*reward
 -->
 (R974 ^value 1 +)
 (R1 ^reward R974 +)
Firing propose*predict-yes
 -->
 (O1941 ^name predict-yes +)
 (S1 ^operator O1941 +)
Firing propose*predict-no
 -->
 (O1942 ^name predict-no +)
 (S1 ^operator O1942 +)
Firing rl*prefer*rvt*predict-no*H0*2
 -->
 (S1 ^operator O1940 = 0.2550133109307305)
Firing rl*prefer*rvt*predict-yes*H0*1
 -->
 (S1 ^operator O1939 = 0.5231204697252971)
Firing prefer*rvt*predict-yes*H0
 -->
Firing prefer*rvt*predict-no*H0
 -->
Firing elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir L +)
 inner elaboration loop at bottom goal.
Retracting elaborate*copy-see-to-output-link
 -->
 (I3 ^see 1 +)
Retracting propose*predict-no
 -->
 (O1940 ^name predict-no +)
 (S1 ^operator O1940 +)
Retracting propose*predict-yes
 -->
 (O1939 ^name predict-yes +)
 (S1 ^operator O1939 +)
Retracting elaborate*reward*based*on*reward
 -->
 (R973 ^value 1 +)
 (R1 ^reward R973 +)
Retracting elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir U +)
Retracting rl*prefer*rvt*predict-no*H0*6
 -->
 (S1 ^operator O1940 = 0.9999999999999999)
Retracting rl*prefer*rvt*predict-yes*H0*5
 -->
 (S1 ^operator O1939 = 0.)
=>WM: (13642: S1 ^operator O1942 +)
=>WM: (13641: S1 ^operator O1941 +)
=>WM: (13640: I3 ^dir L)
=>WM: (13639: O1942 ^name predict-no)
=>WM: (13638: O1941 ^name predict-yes)
=>WM: (13637: R974 ^value 1)
=>WM: (13636: R1 ^reward R974)
=>WM: (13635: I3 ^see 0)
<=WM: (13626: S1 ^operator O1939 +)
<=WM: (13627: S1 ^operator O1940 +)
<=WM: (13628: S1 ^operator O1940)
<=WM: (13625: I3 ^dir U)
<=WM: (13621: R1 ^reward R973)
<=WM: (13620: I3 ^see 1)
<=WM: (13624: O1940 ^name predict-no)
<=WM: (13623: O1939 ^name predict-yes)
<=WM: (13622: R973 ^value 1)

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing prefer*rvt*predict-yes*H0
 -->
Firing rl*prefer*rvt*predict-yes*H0*1*H1*22
 -->
 (S1 ^operator O1941 = 0.4768771233214331)
Firing rl*prefer*rvt*predict-yes*H0*1
 -->
 (S1 ^operator O1941 = 0.5231204697252971)
Firing prefer*rvt*predict-yes*H0*1*H1
 -->
Firing prefer*rvt*predict-no*H0
 -->
Firing rl*prefer*rvt*predict-no*H0*2*H1*10
 -->
 (S1 ^operator O1942 = -0.01194930198035649)
Firing rl*prefer*rvt*predict-no*H0*2
 -->
 (S1 ^operator O1942 = 0.2550133109307305)
Firing prefer*rvt*predict-no*H0*2*H1
 -->
 inner elaboration loop at bottom goal.
Retracting rl*prefer*rvt*predict-no*H0*2
 -->
 (S1 ^operator O1940 = 0.2550133109307305)
Retracting rl*prefer*rvt*predict-no*H0*2*H1*10
 -->
 (S1 ^operator O1940 = -0.01194930198035649)
Retracting rl*prefer*rvt*predict-yes*H0*1
 -->
 (S1 ^operator O1939 = 0.5231204697252971)
Retracting rl*prefer*rvt*predict-yes*H0*1*H1*22
 -->
 (S1 ^operator O1939 = 0.4768771233214331)

--- END Proposal Phase ---

--- Decision Phase ---
RL update rl*prefer*rvt*predict-no*H0*6 1 0 1 -> 1 0 1(R,m,v=1,1,0)
=>WM: (13643: S1 ^operator O1941)

   971:    O: O1941 (predict-yes)
--- END Decision Phase ---

--- Application Phase ---
	--- Firing Productions (PE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing apply*operator
 -->
 (I3 ^predict-yes N971 +  :O )
Firing apply*operator*complete
 -->
 (I3 ^predict-no N970 -  :O )
 inner elaboration loop at bottom goal.
	--- Change Working Memory (PE) ---
=>WM: (13644: I3 ^predict-yes N971)
<=WM: (13630: N970 ^status complete)
<=WM: (13629: I3 ^predict-no N970)
	--- Firing Productions (IE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing monitor*world
 -->

I see 1 and I'm going to do: predict-yes inner elaboration loop at bottom goal.
	--- Change Working Memory (IE) ---

--- END Application Phase ---
--- Output Phase ---
ENV: Agent did: predict-yes for direction L in state State-B
In  State-B moving L
ENV: (next state, see, prediction correct?) = (State-A, 1, True)
predict error 0
dir: dir isL
--- END Output Phase ---
\--- Input Phase --- 
=>WM: (13648: I2 ^dir L)
=>WM: (13647: I2 ^reward 1)
=>WM: (13646: I2 ^see 1)
=>WM: (13645: N971 ^status complete)
<=WM: (13633: I2 ^dir L)
<=WM: (13632: I2 ^reward 1)
<=WM: (13631: I2 ^see 0)
=>WM: (13649: I2 ^level-1 L1-root)
<=WM: (13634: I2 ^level-1 R1-root)

--- END Input Phase --- 

--- Proposal Phase ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing rl*prefer*rvt*predict-yes*H0*1*H1*20
 -->
 (S1 ^operator O1941 = 0.1693592933936033)
Firing rl*prefer*rvt*predict-no*H0*2*H1*11
 -->
 (S1 ^operator O1942 = 0.7449863480615504)
Firing prefer*rvt*predict-no*H0*2*H1
 -->
Firing prefer*rvt*predict-yes*H0*1*H1
 -->
Firing elaborate*copy-see-to-output-link
 -->
 (I3 ^see 1 +)
Firing elaborate*reward*based*on*reward
 -->
 (R975 ^value 1 +)
 (R1 ^reward R975 +)
Firing propose*predict-yes
 -->
 (O1943 ^name predict-yes +)
 (S1 ^operator O1943 +)
Firing propose*predict-no
 -->
 (O1944 ^name predict-no +)
 (S1 ^operator O1944 +)
Firing rl*prefer*rvt*predict-no*H0*2
 -->
 (S1 ^operator O1942 = 0.2550133109307305)
Firing rl*prefer*rvt*predict-yes*H0*1
 -->
 (S1 ^operator O1941 = 0.5231204697252971)
Firing prefer*rvt*predict-yes*H0
 -->
Firing prefer*rvt*predict-no*H0
 -->
Firing elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir L +)
 inner elaboration loop at bottom goal.
Retracting elaborate*copy-see-to-output-link
 -->
 (I3 ^see 0 +)
Retracting propose*predict-no
 -->
 (O1942 ^name predict-no +)
 (S1 ^operator O1942 +)
Retracting propose*predict-yes
 -->
 (O1941 ^name predict-yes +)
 (S1 ^operator O1941 +)
Retracting elaborate*reward*based*on*reward
 -->
 (R974 ^value 1 +)
 (R1 ^reward R974 +)
Retracting elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir L +)
Retracting rl*prefer*rvt*predict-no*H0*2
 -->
 (S1 ^operator O1942 = 0.2550133109307305)
Retracting rl*prefer*rvt*predict-no*H0*2*H1*10
 -->
 (S1 ^operator O1942 = -0.01194930198035649)
Retracting rl*prefer*rvt*predict-yes*H0*1
 -->
 (S1 ^operator O1941 = 0.5231204697252971)
Retracting rl*prefer*rvt*predict-yes*H0*1*H1*22
 -->
 (S1 ^operator O1941 = 0.4768771233214331)
=>WM: (13656: S1 ^operator O1944 +)
=>WM: (13655: S1 ^operator O1943 +)
=>WM: (13654: O1944 ^name predict-no)
=>WM: (13653: O1943 ^name predict-yes)
=>WM: (13652: R975 ^value 1)
=>WM: (13651: R1 ^reward R975)
=>WM: (13650: I3 ^see 1)
<=WM: (13641: S1 ^operator O1941 +)
<=WM: (13643: S1 ^operator O1941)
<=WM: (13642: S1 ^operator O1942 +)
<=WM: (13636: R1 ^reward R974)
<=WM: (13635: I3 ^see 0)
<=WM: (13639: O1942 ^name predict-no)
<=WM: (13638: O1941 ^name predict-yes)
<=WM: (13637: R974 ^value 1)

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing prefer*rvt*predict-yes*H0
 -->
Firing rl*prefer*rvt*predict-yes*H0*1
 -->
 (S1 ^operator O1943 = 0.5231204697252971)
Firing prefer*rvt*predict-yes*H0*1*H1
 -->
Firing rl*prefer*rvt*predict-yes*H0*1*H1*20
 -->
 (S1 ^operator O1943 = 0.1693592933936033)
Firing prefer*rvt*predict-no*H0
 -->
Firing rl*prefer*rvt*predict-no*H0*2
 -->
 (S1 ^operator O1944 = 0.2550133109307305)
Firing prefer*rvt*predict-no*H0*2*H1
 -->
Firing rl*prefer*rvt*predict-no*H0*2*H1*11
 -->
 (S1 ^operator O1944 = 0.7449863480615504)
 inner elaboration loop at bottom goal.
Retracting rl*prefer*rvt*predict-no*H0*2
 -->
 (S1 ^operator O1942 = 0.2550133109307305)
Retracting rl*prefer*rvt*predict-no*H0*2*H1*11
 -->
 (S1 ^operator O1942 = 0.7449863480615504)
Retracting rl*prefer*rvt*predict-yes*H0*1
 -->
 (S1 ^operator O1941 = 0.5231204697252971)
Retracting rl*prefer*rvt*predict-yes*H0*1*H1*20
 -->
 (S1 ^operator O1941 = 0.1693592933936033)

--- END Proposal Phase ---

--- Decision Phase ---
RL update rl*prefer*rvt*predict-yes*H0*1 0.727961 -0.20484 0.52312 -> 0.727961 -0.20484 0.523121(R,m,v=1,0.978417,0.0212699)
RL update rl*prefer*rvt*predict-yes*H0*1*H1*22 0.272036 0.204841 0.476877 -> 0.272037 0.204841 0.476877(R,m,v=1,1,0)
=>WM: (13657: S1 ^operator O1944)

   972:    O: O1944 (predict-no)
--- END Decision Phase ---

--- Application Phase ---
	--- Firing Productions (PE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing apply*operator
 -->
 (I3 ^predict-no N972 +  :O )
Firing apply*operator*complete
 -->
 (I3 ^predict-yes N971 -  :O )
 inner elaboration loop at bottom goal.
	--- Change Working Memory (PE) ---
=>WM: (13658: I3 ^predict-no N972)
<=WM: (13645: N971 ^status complete)
<=WM: (13644: I3 ^predict-yes N971)
	--- Firing Productions (IE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing monitor*world
 -->

I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
	--- Change Working Memory (IE) ---

--- END Application Phase ---
--- Output Phase ---
ENV: Agent did: predict-no for direction L in state State-A
In  State-A moving L
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isU
--- END Output Phase ---
-/--- Input Phase --- 
=>WM: (13662: I2 ^dir U)
=>WM: (13661: I2 ^reward 1)
=>WM: (13660: I2 ^see 0)
=>WM: (13659: N972 ^status complete)
<=WM: (13648: I2 ^dir L)
<=WM: (13647: I2 ^reward 1)
<=WM: (13646: I2 ^see 1)
=>WM: (13663: I2 ^level-1 L0-root)
<=WM: (13649: I2 ^level-1 L1-root)

--- END Input Phase --- 

--- Proposal Phase ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing elaborate*copy-see-to-output-link
 -->
 (I3 ^see 0 +)
Firing elaborate*reward*based*on*reward
 -->
 (R976 ^value 1 +)
 (R1 ^reward R976 +)
Firing propose*predict-yes
 -->
 (O1945 ^name predict-yes +)
 (S1 ^operator O1945 +)
Firing propose*predict-no
 -->
 (O1946 ^name predict-no +)
 (S1 ^operator O1946 +)
Firing rl*prefer*rvt*predict-no*H0*6
 -->
 (S1 ^operator O1944 = 0.9999999999999999)
Firing rl*prefer*rvt*predict-yes*H0*5
 -->
 (S1 ^operator O1943 = 0.)
Firing prefer*rvt*predict-yes*H0
 -->
Firing prefer*rvt*predict-no*H0
 -->
Firing elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir U +)
 inner elaboration loop at bottom goal.
Retracting elaborate*copy-see-to-output-link
 -->
 (I3 ^see 1 +)
Retracting propose*predict-no
 -->
 (O1944 ^name predict-no +)
 (S1 ^operator O1944 +)
Retracting propose*predict-yes
 -->
 (O1943 ^name predict-yes +)
 (S1 ^operator O1943 +)
Retracting elaborate*reward*based*on*reward
 -->
 (R975 ^value 1 +)
 (R1 ^reward R975 +)
Retracting elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir L +)
Retracting rl*prefer*rvt*predict-no*H0*2*H1*11
 -->
 (S1 ^operator O1944 = 0.7449863480615504)
Retracting rl*prefer*rvt*predict-no*H0*2
 -->
 (S1 ^operator O1944 = 0.2550133109307305)
Retracting rl*prefer*rvt*predict-yes*H0*1*H1*20
 -->
 (S1 ^operator O1943 = 0.1693592933936033)
Retracting rl*prefer*rvt*predict-yes*H0*1
 -->
 (S1 ^operator O1943 = 0.5231208307682875)
=>WM: (13671: S1 ^operator O1946 +)
=>WM: (13670: S1 ^operator O1945 +)
=>WM: (13669: I3 ^dir U)
=>WM: (13668: O1946 ^name predict-no)
=>WM: (13667: O1945 ^name predict-yes)
=>WM: (13666: R976 ^value 1)
=>WM: (13665: R1 ^reward R976)
=>WM: (13664: I3 ^see 0)
<=WM: (13655: S1 ^operator O1943 +)
<=WM: (13656: S1 ^operator O1944 +)
<=WM: (13657: S1 ^operator O1944)
<=WM: (13640: I3 ^dir L)
<=WM: (13651: R1 ^reward R975)
<=WM: (13650: I3 ^see 1)
<=WM: (13654: O1944 ^name predict-no)
<=WM: (13653: O1943 ^name predict-yes)
<=WM: (13652: R975 ^value 1)

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing prefer*rvt*predict-yes*H0
 -->
Firing rl*prefer*rvt*predict-yes*H0*5
 -->
 (S1 ^operator O1945 = 0.)
Firing prefer*rvt*predict-no*H0
 -->
Firing rl*prefer*rvt*predict-no*H0*6
 -->
 (S1 ^operator O1946 = 0.9999999999999999)
 inner elaboration loop at bottom goal.
Retracting rl*prefer*rvt*predict-no*H0*6
 -->
 (S1 ^operator O1944 = 0.9999999999999999)
Retracting rl*prefer*rvt*predict-yes*H0*5
 -->
 (S1 ^operator O1943 = 0.)

--- END Proposal Phase ---

--- Decision Phase ---
RL update rl*prefer*rvt*predict-no*H0*2 0.631495 -0.376482 0.255013 -> 0.631495 -0.376482 0.255013(R,m,v=1,0.91623,0.0771562)
RL update rl*prefer*rvt*predict-no*H0*2*H1*11 0.368505 0.376482 0.744986 -> 0.368505 0.376482 0.744986(R,m,v=1,1,0)
=>WM: (13672: S1 ^operator O1946)

   973:    O: O1946 (predict-no)
--- END Decision Phase ---

--- Application Phase ---
	--- Firing Productions (PE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing apply*operator
 -->
 (I3 ^predict-no N973 +  :O )
Firing apply*operator*complete
 -->
 (I3 ^predict-no N972 -  :O )
 inner elaboration loop at bottom goal.
	--- Change Working Memory (PE) ---
=>WM: (13673: I3 ^predict-no N973)
<=WM: (13659: N972 ^status complete)
<=WM: (13658: I3 ^predict-no N972)
	--- Firing Productions (IE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing monitor*world
 -->

I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
	--- Change Working Memory (IE) ---

--- END Application Phase ---
--- Output Phase ---
ENV: Agent did: predict-no for direction U in state State-A
In  State-A moving U
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isU
--- END Output Phase ---
|\-/--- Input Phase --- 
=>WM: (13677: I2 ^dir U)
=>WM: (13676: I2 ^reward 1)
=>WM: (13675: I2 ^see 0)
=>WM: (13674: N973 ^status complete)
<=WM: (13662: I2 ^dir U)
<=WM: (13661: I2 ^reward 1)
<=WM: (13660: I2 ^see 0)
=>WM: (13678: I2 ^level-1 L0-root)
<=WM: (13663: I2 ^level-1 L0-root)

--- END Input Phase --- 

--- Proposal Phase ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing elaborate*copy-see-to-output-link
 -->
 (I3 ^see 0 +)
Firing elaborate*reward*based*on*reward
 -->
 (R977 ^value 1 +)
 (R1 ^reward R977 +)
Firing propose*predict-yes
 -->
 (O1947 ^name predict-yes +)
 (S1 ^operator O1947 +)
Firing propose*predict-no
 -->
 (O1948 ^name predict-no +)
 (S1 ^operator O1948 +)
Firing rl*prefer*rvt*predict-no*H0*6
 -->
 (S1 ^operator O1946 = 0.9999999999999999)
Firing rl*prefer*rvt*predict-yes*H0*5
 -->
 (S1 ^operator O1945 = 0.)
Firing prefer*rvt*predict-yes*H0
 -->
Firing prefer*rvt*predict-no*H0
 -->
Firing elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir U +)
 inner elaboration loop at bottom goal.
Retracting elaborate*copy-see-to-output-link
 -->
 (I3 ^see 0 +)
Retracting propose*predict-no
 -->
 (O1946 ^name predict-no +)
 (S1 ^operator O1946 +)
Retracting propose*predict-yes
 -->
 (O1945 ^name predict-yes +)
 (S1 ^operator O1945 +)
Retracting elaborate*reward*based*on*reward
 -->
 (R976 ^value 1 +)
 (R1 ^reward R976 +)
Retracting elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir U +)
Retracting rl*prefer*rvt*predict-no*H0*6
 -->
 (S1 ^operator O1946 = 0.9999999999999999)
Retracting rl*prefer*rvt*predict-yes*H0*5
 -->
 (S1 ^operator O1945 = 0.)
=>WM: (13684: S1 ^operator O1948 +)
=>WM: (13683: S1 ^operator O1947 +)
=>WM: (13682: O1948 ^name predict-no)
=>WM: (13681: O1947 ^name predict-yes)
=>WM: (13680: R977 ^value 1)
=>WM: (13679: R1 ^reward R977)
<=WM: (13670: S1 ^operator O1945 +)
<=WM: (13671: S1 ^operator O1946 +)
<=WM: (13672: S1 ^operator O1946)
<=WM: (13665: R1 ^reward R976)
<=WM: (13668: O1946 ^name predict-no)
<=WM: (13667: O1945 ^name predict-yes)
<=WM: (13666: R976 ^value 1)

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing prefer*rvt*predict-yes*H0
 -->
Firing rl*prefer*rvt*predict-yes*H0*5
 -->
 (S1 ^operator O1947 = 0.)
Firing prefer*rvt*predict-no*H0
 -->
Firing rl*prefer*rvt*predict-no*H0*6
 -->
 (S1 ^operator O1948 = 0.9999999999999999)
 inner elaboration loop at bottom goal.
Retracting rl*prefer*rvt*predict-no*H0*6
 -->
 (S1 ^operator O1946 = 0.9999999999999999)
Retracting rl*prefer*rvt*predict-yes*H0*5
 -->
 (S1 ^operator O1945 = 0.)

--- END Proposal Phase ---

--- Decision Phase ---
RL update rl*prefer*rvt*predict-no*H0*6 1 0 1 -> 1 0 1(R,m,v=1,1,0)
=>WM: (13685: S1 ^operator O1948)

   974:    O: O1948 (predict-no)
--- END Decision Phase ---

--- Application Phase ---
	--- Firing Productions (PE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing apply*operator
 -->
 (I3 ^predict-no N974 +  :O )
Firing apply*operator*complete
 -->
 (I3 ^predict-no N973 -  :O )
 inner elaboration loop at bottom goal.
	--- Change Working Memory (PE) ---
=>WM: (13686: I3 ^predict-no N974)
<=WM: (13674: N973 ^status complete)
<=WM: (13673: I3 ^predict-no N973)
	--- Firing Productions (IE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing monitor*world
 -->

I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
	--- Change Working Memory (IE) ---

--- END Application Phase ---
--- Output Phase ---
ENV: Agent did: predict-no for direction U in state State-A
In  State-A moving U
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isU
--- END Output Phase ---
|\--- Input Phase --- 
=>WM: (13690: I2 ^dir U)
=>WM: (13689: I2 ^reward 1)
=>WM: (13688: I2 ^see 0)
=>WM: (13687: N974 ^status complete)
<=WM: (13677: I2 ^dir U)
<=WM: (13676: I2 ^reward 1)
<=WM: (13675: I2 ^see 0)
=>WM: (13691: I2 ^level-1 L0-root)
<=WM: (13678: I2 ^level-1 L0-root)

--- END Input Phase --- 

--- Proposal Phase ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing elaborate*copy-see-to-output-link
 -->
 (I3 ^see 0 +)
Firing elaborate*reward*based*on*reward
 -->
 (R978 ^value 1 +)
 (R1 ^reward R978 +)
Firing propose*predict-yes
 -->
 (O1949 ^name predict-yes +)
 (S1 ^operator O1949 +)
Firing propose*predict-no
 -->
 (O1950 ^name predict-no +)
 (S1 ^operator O1950 +)
Firing rl*prefer*rvt*predict-no*H0*6
 -->
 (S1 ^operator O1948 = 0.9999999999999999)
Firing rl*prefer*rvt*predict-yes*H0*5
 -->
 (S1 ^operator O1947 = 0.)
Firing prefer*rvt*predict-yes*H0
 -->
Firing prefer*rvt*predict-no*H0
 -->
Firing elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir U +)
 inner elaboration loop at bottom goal.
Retracting elaborate*copy-see-to-output-link
 -->
 (I3 ^see 0 +)
Retracting propose*predict-no
 -->
 (O1948 ^name predict-no +)
 (S1 ^operator O1948 +)
Retracting propose*predict-yes
 -->
 (O1947 ^name predict-yes +)
 (S1 ^operator O1947 +)
Retracting elaborate*reward*based*on*reward
 -->
 (R977 ^value 1 +)
 (R1 ^reward R977 +)
Retracting elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir U +)
Retracting rl*prefer*rvt*predict-no*H0*6
 -->
 (S1 ^operator O1948 = 0.9999999999999999)
Retracting rl*prefer*rvt*predict-yes*H0*5
 -->
 (S1 ^operator O1947 = 0.)
=>WM: (13697: S1 ^operator O1950 +)
=>WM: (13696: S1 ^operator O1949 +)
=>WM: (13695: O1950 ^name predict-no)
=>WM: (13694: O1949 ^name predict-yes)
=>WM: (13693: R978 ^value 1)
=>WM: (13692: R1 ^reward R978)
<=WM: (13683: S1 ^operator O1947 +)
<=WM: (13684: S1 ^operator O1948 +)
<=WM: (13685: S1 ^operator O1948)
<=WM: (13679: R1 ^reward R977)
<=WM: (13682: O1948 ^name predict-no)
<=WM: (13681: O1947 ^name predict-yes)
<=WM: (13680: R977 ^value 1)

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing prefer*rvt*predict-yes*H0
 -->
Firing rl*prefer*rvt*predict-yes*H0*5
 -->
 (S1 ^operator O1949 = 0.)
Firing prefer*rvt*predict-no*H0
 -->
Firing rl*prefer*rvt*predict-no*H0*6
 -->
 (S1 ^operator O1950 = 0.9999999999999999)
 inner elaboration loop at bottom goal.
Retracting rl*prefer*rvt*predict-no*H0*6
 -->
 (S1 ^operator O1948 = 0.9999999999999999)
Retracting rl*prefer*rvt*predict-yes*H0*5
 -->
 (S1 ^operator O1947 = 0.)

--- END Proposal Phase ---

--- Decision Phase ---
RL update rl*prefer*rvt*predict-no*H0*6 1 0 1 -> 1 0 1(R,m,v=1,1,0)
=>WM: (13698: S1 ^operator O1950)

   975:    O: O1950 (predict-no)
--- END Decision Phase ---

--- Application Phase ---
	--- Firing Productions (PE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing apply*operator
 -->
 (I3 ^predict-no N975 +  :O )
Firing apply*operator*complete
 -->
 (I3 ^predict-no N974 -  :O )
 inner elaboration loop at bottom goal.
	--- Change Working Memory (PE) ---
=>WM: (13699: I3 ^predict-no N975)
<=WM: (13687: N974 ^status complete)
<=WM: (13686: I3 ^predict-no N974)
	--- Firing Productions (IE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing monitor*world
 -->

I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
	--- Change Working Memory (IE) ---

--- END Application Phase ---
--- Output Phase ---
ENV: Agent did: predict-no for direction U in state State-A
In  State-A moving U
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isL
--- END Output Phase ---
-/--- Input Phase --- 
=>WM: (13703: I2 ^dir L)
=>WM: (13702: I2 ^reward 1)
=>WM: (13701: I2 ^see 0)
=>WM: (13700: N975 ^status complete)
<=WM: (13690: I2 ^dir U)
<=WM: (13689: I2 ^reward 1)
<=WM: (13688: I2 ^see 0)
=>WM: (13704: I2 ^level-1 L0-root)
<=WM: (13691: I2 ^level-1 L0-root)

--- END Input Phase --- 

--- Proposal Phase ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing rl*prefer*rvt*predict-yes*H0*1*H1*21
 -->
 (S1 ^operator O1949 = 0.3)
Firing rl*prefer*rvt*predict-no*H0*2*H1*12
 -->
 (S1 ^operator O1950 = 0.744986756180395)
Firing prefer*rvt*predict-no*H0*2*H1
 -->
Firing prefer*rvt*predict-yes*H0*1*H1
 -->
Firing elaborate*copy-see-to-output-link
 -->
 (I3 ^see 0 +)
Firing elaborate*reward*based*on*reward
 -->
 (R979 ^value 1 +)
 (R1 ^reward R979 +)
Firing propose*predict-yes
 -->
 (O1951 ^name predict-yes +)
 (S1 ^operator O1951 +)
Firing propose*predict-no
 -->
 (O1952 ^name predict-no +)
 (S1 ^operator O1952 +)
Firing rl*prefer*rvt*predict-no*H0*2
 -->
 (S1 ^operator O1950 = 0.2550133620818883)
Firing rl*prefer*rvt*predict-yes*H0*1
 -->
 (S1 ^operator O1949 = 0.5231208307682875)
Firing prefer*rvt*predict-yes*H0
 -->
Firing prefer*rvt*predict-no*H0
 -->
Firing elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir L +)
 inner elaboration loop at bottom goal.
Retracting elaborate*copy-see-to-output-link
 -->
 (I3 ^see 0 +)
Retracting propose*predict-no
 -->
 (O1950 ^name predict-no +)
 (S1 ^operator O1950 +)
Retracting propose*predict-yes
 -->
 (O1949 ^name predict-yes +)
 (S1 ^operator O1949 +)
Retracting elaborate*reward*based*on*reward
 -->
 (R978 ^value 1 +)
 (R1 ^reward R978 +)
Retracting elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir U +)
Retracting rl*prefer*rvt*predict-no*H0*6
 -->
 (S1 ^operator O1950 = 0.9999999999999999)
Retracting rl*prefer*rvt*predict-yes*H0*5
 -->
 (S1 ^operator O1949 = 0.)
=>WM: (13711: S1 ^operator O1952 +)
=>WM: (13710: S1 ^operator O1951 +)
=>WM: (13709: I3 ^dir L)
=>WM: (13708: O1952 ^name predict-no)
=>WM: (13707: O1951 ^name predict-yes)
=>WM: (13706: R979 ^value 1)
=>WM: (13705: R1 ^reward R979)
<=WM: (13696: S1 ^operator O1949 +)
<=WM: (13697: S1 ^operator O1950 +)
<=WM: (13698: S1 ^operator O1950)
<=WM: (13669: I3 ^dir U)
<=WM: (13692: R1 ^reward R978)
<=WM: (13695: O1950 ^name predict-no)
<=WM: (13694: O1949 ^name predict-yes)
<=WM: (13693: R978 ^value 1)

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing prefer*rvt*predict-yes*H0
 -->
Firing rl*prefer*rvt*predict-yes*H0*1*H1*21
 -->
 (S1 ^operator O1951 = 0.3)
Firing rl*prefer*rvt*predict-yes*H0*1
 -->
 (S1 ^operator O1951 = 0.5231208307682875)
Firing prefer*rvt*predict-yes*H0*1*H1
 -->
Firing prefer*rvt*predict-no*H0
 -->
Firing rl*prefer*rvt*predict-no*H0*2*H1*12
 -->
 (S1 ^operator O1952 = 0.744986756180395)
Firing rl*prefer*rvt*predict-no*H0*2
 -->
 (S1 ^operator O1952 = 0.2550133620818883)
Firing prefer*rvt*predict-no*H0*2*H1
 -->
 inner elaboration loop at bottom goal.
Retracting rl*prefer*rvt*predict-no*H0*2
 -->
 (S1 ^operator O1950 = 0.2550133620818883)
Retracting rl*prefer*rvt*predict-no*H0*2*H1*12
 -->
 (S1 ^operator O1950 = 0.744986756180395)
Retracting rl*prefer*rvt*predict-yes*H0*1
 -->
 (S1 ^operator O1949 = 0.5231208307682875)
Retracting rl*prefer*rvt*predict-yes*H0*1*H1*21
 -->
 (S1 ^operator O1949 = 0.3)

--- END Proposal Phase ---

--- Decision Phase ---
RL update rl*prefer*rvt*predict-no*H0*6 1 0 1 -> 1 0 1(R,m,v=1,1,0)
=>WM: (13712: S1 ^operator O1952)

   976:    O: O1952 (predict-no)
--- END Decision Phase ---

--- Application Phase ---
	--- Firing Productions (PE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing apply*operator
 -->
 (I3 ^predict-no N976 +  :O )
Firing apply*operator*complete
 -->
 (I3 ^predict-no N975 -  :O )
 inner elaboration loop at bottom goal.
	--- Change Working Memory (PE) ---
=>WM: (13713: I3 ^predict-no N976)
<=WM: (13700: N975 ^status complete)
<=WM: (13699: I3 ^predict-no N975)
	--- Firing Productions (IE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing monitor*world
 -->

I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
	--- Change Working Memory (IE) ---

--- END Application Phase ---
--- Output Phase ---
ENV: Agent did: predict-no for direction L in state State-A
In  State-A moving L
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isR
--- END Output Phase ---
|\---- Input Phase --- 
=>WM: (13717: I2 ^dir R)
=>WM: (13716: I2 ^reward 1)
=>WM: (13715: I2 ^see 0)
=>WM: (13714: N976 ^status complete)
<=WM: (13703: I2 ^dir L)
<=WM: (13702: I2 ^reward 1)
<=WM: (13701: I2 ^see 0)
=>WM: (13718: I2 ^level-1 L0-root)
<=WM: (13704: I2 ^level-1 L0-root)

--- END Input Phase --- 

--- Proposal Phase ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing rl*prefer*rvt*predict-yes*H0*3*H1*14
 -->
 (S1 ^operator O1951 = 0.6170789503736752)
Firing rl*prefer*rvt*predict-no*H0*4*H1*13
 -->
 (S1 ^operator O1952 = 0.4910065094545203)
Firing prefer*rvt*predict-no*H0*4*H1
 -->
Firing prefer*rvt*predict-yes*H0*3*H1
 -->
Firing elaborate*copy-see-to-output-link
 -->
 (I3 ^see 0 +)
Firing elaborate*reward*based*on*reward
 -->
 (R980 ^value 1 +)
 (R1 ^reward R980 +)
Firing propose*predict-yes
 -->
 (O1953 ^name predict-yes +)
 (S1 ^operator O1953 +)
Firing propose*predict-no
 -->
 (O1954 ^name predict-no +)
 (S1 ^operator O1954 +)
Firing rl*prefer*rvt*predict-no*H0*4
 -->
 (S1 ^operator O1952 = 0.1269767780720474)
Firing rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O1951 = 0.3829317273911885)
Firing prefer*rvt*predict-yes*H0
 -->
Firing prefer*rvt*predict-no*H0
 -->
Firing elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir R +)
 inner elaboration loop at bottom goal.
Retracting elaborate*copy-see-to-output-link
 -->
 (I3 ^see 0 +)
Retracting propose*predict-no
 -->
 (O1952 ^name predict-no +)
 (S1 ^operator O1952 +)
Retracting propose*predict-yes
 -->
 (O1951 ^name predict-yes +)
 (S1 ^operator O1951 +)
Retracting elaborate*reward*based*on*reward
 -->
 (R979 ^value 1 +)
 (R1 ^reward R979 +)
Retracting elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir L +)
Retracting rl*prefer*rvt*predict-no*H0*2
 -->
 (S1 ^operator O1952 = 0.2550133620818883)
Retracting rl*prefer*rvt*predict-no*H0*2*H1*12
 -->
 (S1 ^operator O1952 = 0.744986756180395)
Retracting rl*prefer*rvt*predict-yes*H0*1
 -->
 (S1 ^operator O1951 = 0.5231208307682875)
Retracting rl*prefer*rvt*predict-yes*H0*1*H1*21
 -->
 (S1 ^operator O1951 = 0.3)
=>WM: (13725: S1 ^operator O1954 +)
=>WM: (13724: S1 ^operator O1953 +)
=>WM: (13723: I3 ^dir R)
=>WM: (13722: O1954 ^name predict-no)
=>WM: (13721: O1953 ^name predict-yes)
=>WM: (13720: R980 ^value 1)
=>WM: (13719: R1 ^reward R980)
<=WM: (13710: S1 ^operator O1951 +)
<=WM: (13711: S1 ^operator O1952 +)
<=WM: (13712: S1 ^operator O1952)
<=WM: (13709: I3 ^dir L)
<=WM: (13705: R1 ^reward R979)
<=WM: (13708: O1952 ^name predict-no)
<=WM: (13707: O1951 ^name predict-yes)
<=WM: (13706: R979 ^value 1)

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing prefer*rvt*predict-yes*H0
 -->
Firing rl*prefer*rvt*predict-yes*H0*3*H1*14
 -->
 (S1 ^operator O1953 = 0.6170789503736752)
Firing rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O1953 = 0.3829317273911885)
Firing prefer*rvt*predict-yes*H0*3*H1
 -->
Firing prefer*rvt*predict-no*H0
 -->
Firing rl*prefer*rvt*predict-no*H0*4*H1*13
 -->
 (S1 ^operator O1954 = 0.4910065094545203)
Firing rl*prefer*rvt*predict-no*H0*4
 -->
 (S1 ^operator O1954 = 0.1269767780720474)
Firing prefer*rvt*predict-no*H0*4*H1
 -->
 inner elaboration loop at bottom goal.
Retracting rl*prefer*rvt*predict-no*H0*4
 -->
 (S1 ^operator O1952 = 0.1269767780720474)
Retracting rl*prefer*rvt*predict-no*H0*4*H1*13
 -->
 (S1 ^operator O1952 = 0.4910065094545203)
Retracting rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O1951 = 0.3829317273911885)
Retracting rl*prefer*rvt*predict-yes*H0*3*H1*14
 -->
 (S1 ^operator O1951 = 0.6170789503736752)

--- END Proposal Phase ---

--- Decision Phase ---
RL update rl*prefer*rvt*predict-no*H0*2 0.631495 -0.376482 0.255013 -> 0.631495 -0.376482 0.255013(R,m,v=1,0.916667,0.0767888)
RL update rl*prefer*rvt*predict-no*H0*2*H1*12 0.368505 0.376482 0.744987 -> 0.368505 0.376482 0.744987(R,m,v=1,1,0)
=>WM: (13726: S1 ^operator O1953)

   977:    O: O1953 (predict-yes)
--- END Decision Phase ---

--- Application Phase ---
	--- Firing Productions (PE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing apply*operator
 -->
 (I3 ^predict-yes N977 +  :O )
Firing apply*operator*complete
 -->
 (I3 ^predict-no N976 -  :O )
 inner elaboration loop at bottom goal.
	--- Change Working Memory (PE) ---
=>WM: (13727: I3 ^predict-yes N977)
<=WM: (13714: N976 ^status complete)
<=WM: (13713: I3 ^predict-no N976)
	--- Firing Productions (IE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing monitor*world
 -->

I see 1 and I'm going to do: predict-yes inner elaboration loop at bottom goal.
	--- Change Working Memory (IE) ---

--- END Application Phase ---
--- Output Phase ---
ENV: Agent did: predict-yes for direction R in state State-A
In  State-A moving R
ENV: (next state, see, prediction correct?) = (State-B, 1, True)
predict error 0
dir: dir isU
--- END Output Phase ---
/|\--- Input Phase --- 
=>WM: (13731: I2 ^dir U)
=>WM: (13730: I2 ^reward 1)
=>WM: (13729: I2 ^see 1)
=>WM: (13728: N977 ^status complete)
<=WM: (13717: I2 ^dir R)
<=WM: (13716: I2 ^reward 1)
<=WM: (13715: I2 ^see 0)
=>WM: (13732: I2 ^level-1 R1-root)
<=WM: (13718: I2 ^level-1 L0-root)

--- END Input Phase --- 

--- Proposal Phase ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing elaborate*copy-see-to-output-link
 -->
 (I3 ^see 1 +)
Firing elaborate*reward*based*on*reward
 -->
 (R981 ^value 1 +)
 (R1 ^reward R981 +)
Firing propose*predict-yes
 -->
 (O1955 ^name predict-yes +)
 (S1 ^operator O1955 +)
Firing propose*predict-no
 -->
 (O1956 ^name predict-no +)
 (S1 ^operator O1956 +)
Firing rl*prefer*rvt*predict-no*H0*6
 -->
 (S1 ^operator O1954 = 0.9999999999999999)
Firing rl*prefer*rvt*predict-yes*H0*5
 -->
 (S1 ^operator O1953 = 0.)
Firing prefer*rvt*predict-yes*H0
 -->
Firing prefer*rvt*predict-no*H0
 -->
Firing elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir U +)
 inner elaboration loop at bottom goal.
Retracting elaborate*copy-see-to-output-link
 -->
 (I3 ^see 0 +)
Retracting propose*predict-no
 -->
 (O1954 ^name predict-no +)
 (S1 ^operator O1954 +)
Retracting propose*predict-yes
 -->
 (O1953 ^name predict-yes +)
 (S1 ^operator O1953 +)
Retracting elaborate*reward*based*on*reward
 -->
 (R980 ^value 1 +)
 (R1 ^reward R980 +)
Retracting elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir R +)
Retracting rl*prefer*rvt*predict-no*H0*4
 -->
 (S1 ^operator O1954 = 0.1269767780720474)
Retracting rl*prefer*rvt*predict-no*H0*4*H1*13
 -->
 (S1 ^operator O1954 = 0.4910065094545203)
Retracting rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O1953 = 0.3829317273911885)
Retracting rl*prefer*rvt*predict-yes*H0*3*H1*14
 -->
 (S1 ^operator O1953 = 0.6170789503736752)
=>WM: (13740: S1 ^operator O1956 +)
=>WM: (13739: S1 ^operator O1955 +)
=>WM: (13738: I3 ^dir U)
=>WM: (13737: O1956 ^name predict-no)
=>WM: (13736: O1955 ^name predict-yes)
=>WM: (13735: R981 ^value 1)
=>WM: (13734: R1 ^reward R981)
=>WM: (13733: I3 ^see 1)
<=WM: (13724: S1 ^operator O1953 +)
<=WM: (13726: S1 ^operator O1953)
<=WM: (13725: S1 ^operator O1954 +)
<=WM: (13723: I3 ^dir R)
<=WM: (13719: R1 ^reward R980)
<=WM: (13664: I3 ^see 0)
<=WM: (13722: O1954 ^name predict-no)
<=WM: (13721: O1953 ^name predict-yes)
<=WM: (13720: R980 ^value 1)

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing prefer*rvt*predict-yes*H0
 -->
Firing rl*prefer*rvt*predict-yes*H0*5
 -->
 (S1 ^operator O1955 = 0.)
Firing prefer*rvt*predict-no*H0
 -->
Firing rl*prefer*rvt*predict-no*H0*6
 -->
 (S1 ^operator O1956 = 0.9999999999999999)
 inner elaboration loop at bottom goal.
Retracting rl*prefer*rvt*predict-no*H0*6
 -->
 (S1 ^operator O1954 = 0.9999999999999999)
Retracting rl*prefer*rvt*predict-yes*H0*5
 -->
 (S1 ^operator O1953 = 0.)

--- END Proposal Phase ---

--- Decision Phase ---
RL update rl*prefer*rvt*predict-yes*H0*3 0.673126 -0.290194 0.382932 -> 0.673124 -0.290194 0.38293(R,m,v=1,0.96,0.0386577)
RL update rl*prefer*rvt*predict-yes*H0*3*H1*14 0.326884 0.290195 0.617079 -> 0.326883 0.290195 0.617077(R,m,v=1,1,0)
=>WM: (13741: S1 ^operator O1956)

   978:    O: O1956 (predict-no)
--- END Decision Phase ---

--- Application Phase ---
	--- Firing Productions (PE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing apply*operator
 -->
 (I3 ^predict-no N978 +  :O )
Firing apply*operator*complete
 -->
 (I3 ^predict-yes N977 -  :O )
 inner elaboration loop at bottom goal.
	--- Change Working Memory (PE) ---
=>WM: (13742: I3 ^predict-no N978)
<=WM: (13728: N977 ^status complete)
<=WM: (13727: I3 ^predict-yes N977)
	--- Firing Productions (IE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing monitor*world
 -->

I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
	--- Change Working Memory (IE) ---

--- END Application Phase ---
--- Output Phase ---
ENV: Agent did: predict-no for direction U in state State-B
In  State-B moving U
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isR
--- END Output Phase ---
-/|--- Input Phase --- 
=>WM: (13746: I2 ^dir R)
=>WM: (13745: I2 ^reward 1)
=>WM: (13744: I2 ^see 0)
=>WM: (13743: N978 ^status complete)
<=WM: (13731: I2 ^dir U)
<=WM: (13730: I2 ^reward 1)
<=WM: (13729: I2 ^see 1)
=>WM: (13747: I2 ^level-1 R1-root)
<=WM: (13732: I2 ^level-1 R1-root)

--- END Input Phase --- 

--- Proposal Phase ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing rl*prefer*rvt*predict-yes*H0*3*H1*16
 -->
 (S1 ^operator O1955 = 0.08783148430849691)
Firing rl*prefer*rvt*predict-no*H0*4*H1*15
 -->
 (S1 ^operator O1956 = 0.8730234453553117)
Firing prefer*rvt*predict-no*H0*4*H1
 -->
Firing prefer*rvt*predict-yes*H0*3*H1
 -->
Firing elaborate*copy-see-to-output-link
 -->
 (I3 ^see 0 +)
Firing elaborate*reward*based*on*reward
 -->
 (R982 ^value 1 +)
 (R1 ^reward R982 +)
Firing propose*predict-yes
 -->
 (O1957 ^name predict-yes +)
 (S1 ^operator O1957 +)
Firing propose*predict-no
 -->
 (O1958 ^name predict-no +)
 (S1 ^operator O1958 +)
Firing rl*prefer*rvt*predict-no*H0*4
 -->
 (S1 ^operator O1956 = 0.1269767780720474)
Firing rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O1955 = 0.3829301257264589)
Firing prefer*rvt*predict-yes*H0
 -->
Firing prefer*rvt*predict-no*H0
 -->
Firing elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir R +)
 inner elaboration loop at bottom goal.
Retracting elaborate*copy-see-to-output-link
 -->
 (I3 ^see 1 +)
Retracting propose*predict-no
 -->
 (O1956 ^name predict-no +)
 (S1 ^operator O1956 +)
Retracting propose*predict-yes
 -->
 (O1955 ^name predict-yes +)
 (S1 ^operator O1955 +)
Retracting elaborate*reward*based*on*reward
 -->
 (R981 ^value 1 +)
 (R1 ^reward R981 +)
Retracting elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir U +)
Retracting rl*prefer*rvt*predict-no*H0*6
 -->
 (S1 ^operator O1956 = 0.9999999999999999)
Retracting rl*prefer*rvt*predict-yes*H0*5
 -->
 (S1 ^operator O1955 = 0.)
=>WM: (13755: S1 ^operator O1958 +)
=>WM: (13754: S1 ^operator O1957 +)
=>WM: (13753: I3 ^dir R)
=>WM: (13752: O1958 ^name predict-no)
=>WM: (13751: O1957 ^name predict-yes)
=>WM: (13750: R982 ^value 1)
=>WM: (13749: R1 ^reward R982)
=>WM: (13748: I3 ^see 0)
<=WM: (13739: S1 ^operator O1955 +)
<=WM: (13740: S1 ^operator O1956 +)
<=WM: (13741: S1 ^operator O1956)
<=WM: (13738: I3 ^dir U)
<=WM: (13734: R1 ^reward R981)
<=WM: (13733: I3 ^see 1)
<=WM: (13737: O1956 ^name predict-no)
<=WM: (13736: O1955 ^name predict-yes)
<=WM: (13735: R981 ^value 1)

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing prefer*rvt*predict-yes*H0
 -->
Firing rl*prefer*rvt*predict-yes*H0*3*H1*16
 -->
 (S1 ^operator O1957 = 0.08783148430849691)
Firing rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O1957 = 0.3829301257264589)
Firing prefer*rvt*predict-yes*H0*3*H1
 -->
Firing prefer*rvt*predict-no*H0
 -->
Firing rl*prefer*rvt*predict-no*H0*4*H1*15
 -->
 (S1 ^operator O1958 = 0.8730234453553117)
Firing rl*prefer*rvt*predict-no*H0*4
 -->
 (S1 ^operator O1958 = 0.1269767780720474)
Firing prefer*rvt*predict-no*H0*4*H1
 -->
 inner elaboration loop at bottom goal.
Retracting rl*prefer*rvt*predict-no*H0*4
 -->
 (S1 ^operator O1956 = 0.1269767780720474)
Retracting rl*prefer*rvt*predict-no*H0*4*H1*15
 -->
 (S1 ^operator O1956 = 0.8730234453553117)
Retracting rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O1955 = 0.3829301257264589)
Retracting rl*prefer*rvt*predict-yes*H0*3*H1*16
 -->
 (S1 ^operator O1955 = 0.08783148430849691)

--- END Proposal Phase ---

--- Decision Phase ---
RL update rl*prefer*rvt*predict-no*H0*6 1 0 1 -> 1 0 1(R,m,v=1,1,0)
=>WM: (13756: S1 ^operator O1958)

   979:    O: O1958 (predict-no)
--- END Decision Phase ---

--- Application Phase ---
	--- Firing Productions (PE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing apply*operator
 -->
 (I3 ^predict-no N979 +  :O )
Firing apply*operator*complete
 -->
 (I3 ^predict-no N978 -  :O )
 inner elaboration loop at bottom goal.
	--- Change Working Memory (PE) ---
=>WM: (13757: I3 ^predict-no N979)
<=WM: (13743: N978 ^status complete)
<=WM: (13742: I3 ^predict-no N978)
	--- Firing Productions (IE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing monitor*world
 -->

I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
	--- Change Working Memory (IE) ---

--- END Application Phase ---
--- Output Phase ---
ENV: Agent did: predict-no for direction R in state State-B
In  State-B moving R
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isU
--- END Output Phase ---
\-/--- Input Phase --- 
=>WM: (13761: I2 ^dir U)
=>WM: (13760: I2 ^reward 1)
=>WM: (13759: I2 ^see 0)
=>WM: (13758: N979 ^status complete)
<=WM: (13746: I2 ^dir R)
<=WM: (13745: I2 ^reward 1)
<=WM: (13744: I2 ^see 0)
=>WM: (13762: I2 ^level-1 R0-root)
<=WM: (13747: I2 ^level-1 R1-root)

--- END Input Phase --- 

--- Proposal Phase ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing elaborate*copy-see-to-output-link
 -->
 (I3 ^see 0 +)
Firing elaborate*reward*based*on*reward
 -->
 (R983 ^value 1 +)
 (R1 ^reward R983 +)
Firing propose*predict-yes
 -->
 (O1959 ^name predict-yes +)
 (S1 ^operator O1959 +)
Firing propose*predict-no
 -->
 (O1960 ^name predict-no +)
 (S1 ^operator O1960 +)
Firing rl*prefer*rvt*predict-no*H0*6
 -->
 (S1 ^operator O1958 = 0.9999999999999999)
Firing rl*prefer*rvt*predict-yes*H0*5
 -->
 (S1 ^operator O1957 = 0.)
Firing prefer*rvt*predict-yes*H0
 -->
Firing prefer*rvt*predict-no*H0
 -->
Firing elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir U +)
 inner elaboration loop at bottom goal.
Retracting elaborate*copy-see-to-output-link
 -->
 (I3 ^see 0 +)
Retracting propose*predict-no
 -->
 (O1958 ^name predict-no +)
 (S1 ^operator O1958 +)
Retracting propose*predict-yes
 -->
 (O1957 ^name predict-yes +)
 (S1 ^operator O1957 +)
Retracting elaborate*reward*based*on*reward
 -->
 (R982 ^value 1 +)
 (R1 ^reward R982 +)
Retracting elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir R +)
Retracting rl*prefer*rvt*predict-no*H0*4
 -->
 (S1 ^operator O1958 = 0.1269767780720474)
Retracting rl*prefer*rvt*predict-no*H0*4*H1*15
 -->
 (S1 ^operator O1958 = 0.8730234453553117)
Retracting rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O1957 = 0.3829301257264589)
Retracting rl*prefer*rvt*predict-yes*H0*3*H1*16
 -->
 (S1 ^operator O1957 = 0.08783148430849691)
=>WM: (13769: S1 ^operator O1960 +)
=>WM: (13768: S1 ^operator O1959 +)
=>WM: (13767: I3 ^dir U)
=>WM: (13766: O1960 ^name predict-no)
=>WM: (13765: O1959 ^name predict-yes)
=>WM: (13764: R983 ^value 1)
=>WM: (13763: R1 ^reward R983)
<=WM: (13754: S1 ^operator O1957 +)
<=WM: (13755: S1 ^operator O1958 +)
<=WM: (13756: S1 ^operator O1958)
<=WM: (13753: I3 ^dir R)
<=WM: (13749: R1 ^reward R982)
<=WM: (13752: O1958 ^name predict-no)
<=WM: (13751: O1957 ^name predict-yes)
<=WM: (13750: R982 ^value 1)

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing prefer*rvt*predict-yes*H0
 -->
Firing rl*prefer*rvt*predict-yes*H0*5
 -->
 (S1 ^operator O1959 = 0.)
Firing prefer*rvt*predict-no*H0
 -->
Firing rl*prefer*rvt*predict-no*H0*6
 -->
 (S1 ^operator O1960 = 0.9999999999999999)
 inner elaboration loop at bottom goal.
Retracting rl*prefer*rvt*predict-no*H0*6
 -->
 (S1 ^operator O1958 = 0.9999999999999999)
Retracting rl*prefer*rvt*predict-yes*H0*5
 -->
 (S1 ^operator O1957 = 0.)

--- END Proposal Phase ---

--- Decision Phase ---
RL update rl*prefer*rvt*predict-no*H0*4 0.814714 -0.687737 0.126977 -> 0.814714 -0.687737 0.126977(R,m,v=1,0.947977,0.0496034)
RL update rl*prefer*rvt*predict-no*H0*4*H1*15 0.185286 0.687737 0.873023 -> 0.185286 0.687737 0.873023(R,m,v=1,1,0)
=>WM: (13770: S1 ^operator O1960)

   980:    O: O1960 (predict-no)
--- END Decision Phase ---

--- Application Phase ---
	--- Firing Productions (PE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing apply*operator
 -->
 (I3 ^predict-no N980 +  :O )
Firing apply*operator*complete
 -->
 (I3 ^predict-no N979 -  :O )
 inner elaboration loop at bottom goal.
	--- Change Working Memory (PE) ---
=>WM: (13771: I3 ^predict-no N980)
<=WM: (13758: N979 ^status complete)
<=WM: (13757: I3 ^predict-no N979)
	--- Firing Productions (IE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing monitor*world
 -->

I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
	--- Change Working Memory (IE) ---

--- END Application Phase ---
--- Output Phase ---
ENV: Agent did: predict-no for direction U in state State-B
In  State-B moving U
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isL
--- END Output Phase ---
|\--- Input Phase --- 
=>WM: (13775: I2 ^dir L)
=>WM: (13774: I2 ^reward 1)
=>WM: (13773: I2 ^see 0)
=>WM: (13772: N980 ^status complete)
<=WM: (13761: I2 ^dir U)
<=WM: (13760: I2 ^reward 1)
<=WM: (13759: I2 ^see 0)
=>WM: (13776: I2 ^level-1 R0-root)
<=WM: (13762: I2 ^level-1 R0-root)

--- END Input Phase --- 

--- Proposal Phase ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing rl*prefer*rvt*predict-yes*H0*1*H1*19
 -->
 (S1 ^operator O1959 = 0.4768840530102607)
Firing rl*prefer*rvt*predict-no*H0*2*H1*7
 -->
 (S1 ^operator O1960 = 0.1700769046561409)
Firing prefer*rvt*predict-no*H0*2*H1
 -->
Firing prefer*rvt*predict-yes*H0*1*H1
 -->
Firing elaborate*copy-see-to-output-link
 -->
 (I3 ^see 0 +)
Firing elaborate*reward*based*on*reward
 -->
 (R984 ^value 1 +)
 (R1 ^reward R984 +)
Firing propose*predict-yes
 -->
 (O1961 ^name predict-yes +)
 (S1 ^operator O1961 +)
Firing propose*predict-no
 -->
 (O1962 ^name predict-no +)
 (S1 ^operator O1962 +)
Firing rl*prefer*rvt*predict-no*H0*2
 -->
 (S1 ^operator O1960 = 0.2550133443425458)
Firing rl*prefer*rvt*predict-yes*H0*1
 -->
 (S1 ^operator O1959 = 0.5231208307682875)
Firing prefer*rvt*predict-yes*H0
 -->
Firing prefer*rvt*predict-no*H0
 -->
Firing elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir L +)
 inner elaboration loop at bottom goal.
Retracting elaborate*copy-see-to-output-link
 -->
 (I3 ^see 0 +)
Retracting propose*predict-no
 -->
 (O1960 ^name predict-no +)
 (S1 ^operator O1960 +)
Retracting propose*predict-yes
 -->
 (O1959 ^name predict-yes +)
 (S1 ^operator O1959 +)
Retracting elaborate*reward*based*on*reward
 -->
 (R983 ^value 1 +)
 (R1 ^reward R983 +)
Retracting elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir U +)
Retracting rl*prefer*rvt*predict-no*H0*6
 -->
 (S1 ^operator O1960 = 0.9999999999999999)
Retracting rl*prefer*rvt*predict-yes*H0*5
 -->
 (S1 ^operator O1959 = 0.)
=>WM: (13783: S1 ^operator O1962 +)
=>WM: (13782: S1 ^operator O1961 +)
=>WM: (13781: I3 ^dir L)
=>WM: (13780: O1962 ^name predict-no)
=>WM: (13779: O1961 ^name predict-yes)
=>WM: (13778: R984 ^value 1)
=>WM: (13777: R1 ^reward R984)
<=WM: (13768: S1 ^operator O1959 +)
<=WM: (13769: S1 ^operator O1960 +)
<=WM: (13770: S1 ^operator O1960)
<=WM: (13767: I3 ^dir U)
<=WM: (13763: R1 ^reward R983)
<=WM: (13766: O1960 ^name predict-no)
<=WM: (13765: O1959 ^name predict-yes)
<=WM: (13764: R983 ^value 1)

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing prefer*rvt*predict-yes*H0
 -->
Firing rl*prefer*rvt*predict-yes*H0*1*H1*19
 -->
 (S1 ^operator O1961 = 0.4768840530102607)
Firing rl*prefer*rvt*predict-yes*H0*1
 -->
 (S1 ^operator O1961 = 0.5231208307682875)
Firing prefer*rvt*predict-yes*H0*1*H1
 -->
Firing prefer*rvt*predict-no*H0
 -->
Firing rl*prefer*rvt*predict-no*H0*2*H1*7
 -->
 (S1 ^operator O1962 = 0.1700769046561409)
Firing rl*prefer*rvt*predict-no*H0*2
 -->
 (S1 ^operator O1962 = 0.2550133443425458)
Firing prefer*rvt*predict-no*H0*2*H1
 -->
 inner elaboration loop at bottom goal.
Retracting rl*prefer*rvt*predict-no*H0*2
 -->
 (S1 ^operator O1960 = 0.2550133443425458)
Retracting rl*prefer*rvt*predict-no*H0*2*H1*7
 -->
 (S1 ^operator O1960 = 0.1700769046561409)
Retracting rl*prefer*rvt*predict-yes*H0*1
 -->
 (S1 ^operator O1959 = 0.5231208307682875)
Retracting rl*prefer*rvt*predict-yes*H0*1*H1*19
 -->
 (S1 ^operator O1959 = 0.4768840530102607)

--- END Proposal Phase ---

--- Decision Phase ---
RL update rl*prefer*rvt*predict-no*H0*6 1 0 1 -> 1 0 1(R,m,v=1,1,0)
=>WM: (13784: S1 ^operator O1961)

   981:    O: O1961 (predict-yes)
--- END Decision Phase ---

--- Application Phase ---
	--- Firing Productions (PE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing apply*operator
 -->
 (I3 ^predict-yes N981 +  :O )
Firing apply*operator*complete
 -->
 (I3 ^predict-no N980 -  :O )
 inner elaboration loop at bottom goal.
	--- Change Working Memory (PE) ---
=>WM: (13785: I3 ^predict-yes N981)
<=WM: (13772: N980 ^status complete)
<=WM: (13771: I3 ^predict-no N980)
	--- Firing Productions (IE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing monitor*world
 -->

I see 1 and I'm going to do: predict-yes inner elaboration loop at bottom goal.
	--- Change Working Memory (IE) ---

--- END Application Phase ---
--- Output Phase ---
ENV: Agent did: predict-yes for direction L in state State-B
In  State-B moving L
ENV: (next state, see, prediction correct?) = (State-A, 1, True)
predict error 0
dir: dir isL
--- END Output Phase ---
---- Input Phase --- 
=>WM: (13789: I2 ^dir L)
=>WM: (13788: I2 ^reward 1)
=>WM: (13787: I2 ^see 1)
=>WM: (13786: N981 ^status complete)
<=WM: (13775: I2 ^dir L)
<=WM: (13774: I2 ^reward 1)
<=WM: (13773: I2 ^see 0)
=>WM: (13790: I2 ^level-1 L1-root)
<=WM: (13776: I2 ^level-1 R0-root)

--- END Input Phase --- 

--- Proposal Phase ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing rl*prefer*rvt*predict-yes*H0*1*H1*20
 -->
 (S1 ^operator O1961 = 0.1693592933936033)
Firing rl*prefer*rvt*predict-no*H0*2*H1*11
 -->
 (S1 ^operator O1962 = 0.7449863992127084)
Firing prefer*rvt*predict-no*H0*2*H1
 -->
Firing prefer*rvt*predict-yes*H0*1*H1
 -->
Firing elaborate*copy-see-to-output-link
 -->
 (I3 ^see 1 +)
Firing elaborate*reward*based*on*reward
 -->
 (R985 ^value 1 +)
 (R1 ^reward R985 +)
Firing propose*predict-yes
 -->
 (O1963 ^name predict-yes +)
 (S1 ^operator O1963 +)
Firing propose*predict-no
 -->
 (O1964 ^name predict-no +)
 (S1 ^operator O1964 +)
Firing rl*prefer*rvt*predict-no*H0*2
 -->
 (S1 ^operator O1962 = 0.2550133443425458)
Firing rl*prefer*rvt*predict-yes*H0*1
 -->
 (S1 ^operator O1961 = 0.5231208307682875)
Firing prefer*rvt*predict-yes*H0
 -->
Firing prefer*rvt*predict-no*H0
 -->
Firing elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir L +)
 inner elaboration loop at bottom goal.
Retracting elaborate*copy-see-to-output-link
 -->
 (I3 ^see 0 +)
Retracting propose*predict-no
 -->
 (O1962 ^name predict-no +)
 (S1 ^operator O1962 +)
Retracting propose*predict-yes
 -->
 (O1961 ^name predict-yes +)
 (S1 ^operator O1961 +)
Retracting elaborate*reward*based*on*reward
 -->
 (R984 ^value 1 +)
 (R1 ^reward R984 +)
Retracting elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir L +)
Retracting rl*prefer*rvt*predict-no*H0*2
 -->
 (S1 ^operator O1962 = 0.2550133443425458)
Retracting rl*prefer*rvt*predict-no*H0*2*H1*7
 -->
 (S1 ^operator O1962 = 0.1700769046561409)
Retracting rl*prefer*rvt*predict-yes*H0*1
 -->
 (S1 ^operator O1961 = 0.5231208307682875)
Retracting rl*prefer*rvt*predict-yes*H0*1*H1*19
 -->
 (S1 ^operator O1961 = 0.4768840530102607)
=>WM: (13797: S1 ^operator O1964 +)
=>WM: (13796: S1 ^operator O1963 +)
=>WM: (13795: O1964 ^name predict-no)
=>WM: (13794: O1963 ^name predict-yes)
=>WM: (13793: R985 ^value 1)
=>WM: (13792: R1 ^reward R985)
=>WM: (13791: I3 ^see 1)
<=WM: (13782: S1 ^operator O1961 +)
<=WM: (13784: S1 ^operator O1961)
<=WM: (13783: S1 ^operator O1962 +)
<=WM: (13777: R1 ^reward R984)
<=WM: (13748: I3 ^see 0)
<=WM: (13780: O1962 ^name predict-no)
<=WM: (13779: O1961 ^name predict-yes)
<=WM: (13778: R984 ^value 1)

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing prefer*rvt*predict-yes*H0
 -->
Firing rl*prefer*rvt*predict-yes*H0*1
 -->
 (S1 ^operator O1963 = 0.5231208307682875)
Firing prefer*rvt*predict-yes*H0*1*H1
 -->
Firing rl*prefer*rvt*predict-yes*H0*1*H1*20
 -->
 (S1 ^operator O1963 = 0.1693592933936033)
Firing prefer*rvt*predict-no*H0
 -->
Firing rl*prefer*rvt*predict-no*H0*2
 -->
 (S1 ^operator O1964 = 0.2550133443425458)
Firing prefer*rvt*predict-no*H0*2*H1
 -->
Firing rl*prefer*rvt*predict-no*H0*2*H1*11
 -->
 (S1 ^operator O1964 = 0.7449863992127084)
 inner elaboration loop at bottom goal.
Retracting rl*prefer*rvt*predict-no*H0*2
 -->
 (S1 ^operator O1962 = 0.2550133443425458)
Retracting rl*prefer*rvt*predict-no*H0*2*H1*11
 -->
 (S1 ^operator O1962 = 0.7449863992127084)
Retracting rl*prefer*rvt*predict-yes*H0*1
 -->
 (S1 ^operator O1961 = 0.5231208307682875)
Retracting rl*prefer*rvt*predict-yes*H0*1*H1*20
 -->
 (S1 ^operator O1961 = 0.1693592933936033)

--- END Proposal Phase ---

--- Decision Phase ---
RL update rl*prefer*rvt*predict-yes*H0*1 0.727961 -0.20484 0.523121 -> 0.72796 -0.20484 0.52312(R,m,v=1,0.978571,0.0211202)
RL update rl*prefer*rvt*predict-yes*H0*1*H1*19 0.272045 0.204839 0.476884 -> 0.272045 0.204839 0.476883(R,m,v=1,1,0)
=>WM: (13798: S1 ^operator O1964)

   982:    O: O1964 (predict-no)
--- END Decision Phase ---

--- Application Phase ---
	--- Firing Productions (PE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing apply*operator
 -->
 (I3 ^predict-no N982 +  :O )
Firing apply*operator*complete
 -->
 (I3 ^predict-yes N981 -  :O )
 inner elaboration loop at bottom goal.
	--- Change Working Memory (PE) ---
=>WM: (13799: I3 ^predict-no N982)
<=WM: (13786: N981 ^status complete)
<=WM: (13785: I3 ^predict-yes N981)
	--- Firing Productions (IE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing monitor*world
 -->

I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
	--- Change Working Memory (IE) ---

--- END Application Phase ---
--- Output Phase ---
ENV: Agent did: predict-no for direction L in state State-A
In  State-A moving L
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isR
--- END Output Phase ---
/|\--- Input Phase --- 
=>WM: (13803: I2 ^dir R)
=>WM: (13802: I2 ^reward 1)
=>WM: (13801: I2 ^see 0)
=>WM: (13800: N982 ^status complete)
<=WM: (13789: I2 ^dir L)
<=WM: (13788: I2 ^reward 1)
<=WM: (13787: I2 ^see 1)
=>WM: (13804: I2 ^level-1 L0-root)
<=WM: (13790: I2 ^level-1 L1-root)

--- END Input Phase --- 

--- Proposal Phase ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing rl*prefer*rvt*predict-yes*H0*3*H1*14
 -->
 (S1 ^operator O1963 = 0.6170773487089456)
Firing rl*prefer*rvt*predict-no*H0*4*H1*13
 -->
 (S1 ^operator O1964 = 0.4910065094545203)
Firing prefer*rvt*predict-no*H0*4*H1
 -->
Firing prefer*rvt*predict-yes*H0*3*H1
 -->
Firing elaborate*copy-see-to-output-link
 -->
 (I3 ^see 0 +)
Firing elaborate*reward*based*on*reward
 -->
 (R986 ^value 1 +)
 (R1 ^reward R986 +)
Firing propose*predict-yes
 -->
 (O1965 ^name predict-yes +)
 (S1 ^operator O1965 +)
Firing propose*predict-no
 -->
 (O1966 ^name predict-no +)
 (S1 ^operator O1966 +)
Firing rl*prefer*rvt*predict-no*H0*4
 -->
 (S1 ^operator O1964 = 0.1269767445579436)
Firing rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O1963 = 0.3829301257264589)
Firing prefer*rvt*predict-yes*H0
 -->
Firing prefer*rvt*predict-no*H0
 -->
Firing elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir R +)
 inner elaboration loop at bottom goal.
Retracting elaborate*copy-see-to-output-link
 -->
 (I3 ^see 1 +)
Retracting propose*predict-no
 -->
 (O1964 ^name predict-no +)
 (S1 ^operator O1964 +)
Retracting propose*predict-yes
 -->
 (O1963 ^name predict-yes +)
 (S1 ^operator O1963 +)
Retracting elaborate*reward*based*on*reward
 -->
 (R985 ^value 1 +)
 (R1 ^reward R985 +)
Retracting elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir L +)
Retracting rl*prefer*rvt*predict-no*H0*2*H1*11
 -->
 (S1 ^operator O1964 = 0.7449863992127084)
Retracting rl*prefer*rvt*predict-no*H0*2
 -->
 (S1 ^operator O1964 = 0.2550133443425458)
Retracting rl*prefer*rvt*predict-yes*H0*1*H1*20
 -->
 (S1 ^operator O1963 = 0.1693592933936033)
Retracting rl*prefer*rvt*predict-yes*H0*1
 -->
 (S1 ^operator O1963 = 0.5231200982015054)
=>WM: (13812: S1 ^operator O1966 +)
=>WM: (13811: S1 ^operator O1965 +)
=>WM: (13810: I3 ^dir R)
=>WM: (13809: O1966 ^name predict-no)
=>WM: (13808: O1965 ^name predict-yes)
=>WM: (13807: R986 ^value 1)
=>WM: (13806: R1 ^reward R986)
=>WM: (13805: I3 ^see 0)
<=WM: (13796: S1 ^operator O1963 +)
<=WM: (13797: S1 ^operator O1964 +)
<=WM: (13798: S1 ^operator O1964)
<=WM: (13781: I3 ^dir L)
<=WM: (13792: R1 ^reward R985)
<=WM: (13791: I3 ^see 1)
<=WM: (13795: O1964 ^name predict-no)
<=WM: (13794: O1963 ^name predict-yes)
<=WM: (13793: R985 ^value 1)

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing prefer*rvt*predict-yes*H0
 -->
Firing rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O1965 = 0.3829301257264589)
Firing prefer*rvt*predict-yes*H0*3*H1
 -->
Firing rl*prefer*rvt*predict-yes*H0*3*H1*14
 -->
 (S1 ^operator O1965 = 0.6170773487089456)
Firing prefer*rvt*predict-no*H0
 -->
Firing rl*prefer*rvt*predict-no*H0*4
 -->
 (S1 ^operator O1966 = 0.1269767445579436)
Firing prefer*rvt*predict-no*H0*4*H1
 -->
Firing rl*prefer*rvt*predict-no*H0*4*H1*13
 -->
 (S1 ^operator O1966 = 0.4910065094545203)
 inner elaboration loop at bottom goal.
Retracting rl*prefer*rvt*predict-no*H0*4
 -->
 (S1 ^operator O1964 = 0.1269767445579436)
Retracting rl*prefer*rvt*predict-no*H0*4*H1*13
 -->
 (S1 ^operator O1964 = 0.4910065094545203)
Retracting rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O1963 = 0.3829301257264589)
Retracting rl*prefer*rvt*predict-yes*H0*3*H1*14
 -->
 (S1 ^operator O1963 = 0.6170773487089456)

--- END Proposal Phase ---

--- Decision Phase ---
RL update rl*prefer*rvt*predict-no*H0*2 0.631495 -0.376482 0.255013 -> 0.631495 -0.376482 0.255013(R,m,v=1,0.917098,0.0764249)
RL update rl*prefer*rvt*predict-no*H0*2*H1*11 0.368505 0.376482 0.744986 -> 0.368505 0.376482 0.744986(R,m,v=1,1,0)
=>WM: (13813: S1 ^operator O1965)

   983:    O: O1965 (predict-yes)
--- END Decision Phase ---

--- Application Phase ---
	--- Firing Productions (PE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing apply*operator
 -->
 (I3 ^predict-yes N983 +  :O )
Firing apply*operator*complete
 -->
 (I3 ^predict-no N982 -  :O )
 inner elaboration loop at bottom goal.
	--- Change Working Memory (PE) ---
=>WM: (13814: I3 ^predict-yes N983)
<=WM: (13800: N982 ^status complete)
<=WM: (13799: I3 ^predict-no N982)
	--- Firing Productions (IE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing monitor*world
 -->

I see 1 and I'm going to do: predict-yes inner elaboration loop at bottom goal.
	--- Change Working Memory (IE) ---

--- END Application Phase ---
--- Output Phase ---
ENV: Agent did: predict-yes for direction R in state State-A
In  State-A moving R
ENV: (next state, see, prediction correct?) = (State-B, 1, True)
predict error 0
dir: dir isU
--- END Output Phase ---
-/|--- Input Phase --- 
=>WM: (13818: I2 ^dir U)
=>WM: (13817: I2 ^reward 1)
=>WM: (13816: I2 ^see 1)
=>WM: (13815: N983 ^status complete)
<=WM: (13803: I2 ^dir R)
<=WM: (13802: I2 ^reward 1)
<=WM: (13801: I2 ^see 0)
=>WM: (13819: I2 ^level-1 R1-root)
<=WM: (13804: I2 ^level-1 L0-root)

--- END Input Phase --- 

--- Proposal Phase ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing elaborate*copy-see-to-output-link
 -->
 (I3 ^see 1 +)
Firing elaborate*reward*based*on*reward
 -->
 (R987 ^value 1 +)
 (R1 ^reward R987 +)
Firing propose*predict-yes
 -->
 (O1967 ^name predict-yes +)
 (S1 ^operator O1967 +)
Firing propose*predict-no
 -->
 (O1968 ^name predict-no +)
 (S1 ^operator O1968 +)
Firing rl*prefer*rvt*predict-no*H0*6
 -->
 (S1 ^operator O1966 = 0.9999999999999999)
Firing rl*prefer*rvt*predict-yes*H0*5
 -->
 (S1 ^operator O1965 = 0.)
Firing prefer*rvt*predict-yes*H0
 -->
Firing prefer*rvt*predict-no*H0
 -->
Firing elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir U +)
 inner elaboration loop at bottom goal.
Retracting elaborate*copy-see-to-output-link
 -->
 (I3 ^see 0 +)
Retracting propose*predict-no
 -->
 (O1966 ^name predict-no +)
 (S1 ^operator O1966 +)
Retracting propose*predict-yes
 -->
 (O1965 ^name predict-yes +)
 (S1 ^operator O1965 +)
Retracting elaborate*reward*based*on*reward
 -->
 (R986 ^value 1 +)
 (R1 ^reward R986 +)
Retracting elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir R +)
Retracting rl*prefer*rvt*predict-no*H0*4*H1*13
 -->
 (S1 ^operator O1966 = 0.4910065094545203)
Retracting rl*prefer*rvt*predict-no*H0*4
 -->
 (S1 ^operator O1966 = 0.1269767445579436)
Retracting rl*prefer*rvt*predict-yes*H0*3*H1*14
 -->
 (S1 ^operator O1965 = 0.6170773487089456)
Retracting rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O1965 = 0.3829301257264589)
=>WM: (13827: S1 ^operator O1968 +)
=>WM: (13826: S1 ^operator O1967 +)
=>WM: (13825: I3 ^dir U)
=>WM: (13824: O1968 ^name predict-no)
=>WM: (13823: O1967 ^name predict-yes)
=>WM: (13822: R987 ^value 1)
=>WM: (13821: R1 ^reward R987)
=>WM: (13820: I3 ^see 1)
<=WM: (13811: S1 ^operator O1965 +)
<=WM: (13813: S1 ^operator O1965)
<=WM: (13812: S1 ^operator O1966 +)
<=WM: (13810: I3 ^dir R)
<=WM: (13806: R1 ^reward R986)
<=WM: (13805: I3 ^see 0)
<=WM: (13809: O1966 ^name predict-no)
<=WM: (13808: O1965 ^name predict-yes)
<=WM: (13807: R986 ^value 1)

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing prefer*rvt*predict-yes*H0
 -->
Firing rl*prefer*rvt*predict-yes*H0*5
 -->
 (S1 ^operator O1967 = 0.)
Firing prefer*rvt*predict-no*H0
 -->
Firing rl*prefer*rvt*predict-no*H0*6
 -->
 (S1 ^operator O1968 = 0.9999999999999999)
 inner elaboration loop at bottom goal.
Retracting rl*prefer*rvt*predict-no*H0*6
 -->
 (S1 ^operator O1966 = 0.9999999999999999)
Retracting rl*prefer*rvt*predict-yes*H0*5
 -->
 (S1 ^operator O1965 = 0.)

--- END Proposal Phase ---

--- Decision Phase ---
RL update rl*prefer*rvt*predict-yes*H0*3 0.673124 -0.290194 0.38293 -> 0.673123 -0.290194 0.382929(R,m,v=1,0.960265,0.0384106)
RL update rl*prefer*rvt*predict-yes*H0*3*H1*14 0.326883 0.290195 0.617077 -> 0.326882 0.290195 0.617076(R,m,v=1,1,0)
=>WM: (13828: S1 ^operator O1968)

   984:    O: O1968 (predict-no)
--- END Decision Phase ---

--- Application Phase ---
	--- Firing Productions (PE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing apply*operator
 -->
 (I3 ^predict-no N984 +  :O )
Firing apply*operator*complete
 -->
 (I3 ^predict-yes N983 -  :O )
 inner elaboration loop at bottom goal.
	--- Change Working Memory (PE) ---
=>WM: (13829: I3 ^predict-no N984)
<=WM: (13815: N983 ^status complete)
<=WM: (13814: I3 ^predict-yes N983)
	--- Firing Productions (IE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing monitor*world
 -->

I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
	--- Change Working Memory (IE) ---

--- END Application Phase ---
--- Output Phase ---
ENV: Agent did: predict-no for direction U in state State-B
In  State-B moving U
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isU
--- END Output Phase ---
\-/--- Input Phase --- 
=>WM: (13833: I2 ^dir U)
=>WM: (13832: I2 ^reward 1)
=>WM: (13831: I2 ^see 0)
=>WM: (13830: N984 ^status complete)
<=WM: (13818: I2 ^dir U)
<=WM: (13817: I2 ^reward 1)
<=WM: (13816: I2 ^see 1)
=>WM: (13834: I2 ^level-1 R1-root)
<=WM: (13819: I2 ^level-1 R1-root)

--- END Input Phase --- 

--- Proposal Phase ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing elaborate*copy-see-to-output-link
 -->
 (I3 ^see 0 +)
Firing elaborate*reward*based*on*reward
 -->
 (R988 ^value 1 +)
 (R1 ^reward R988 +)
Firing propose*predict-yes
 -->
 (O1969 ^name predict-yes +)
 (S1 ^operator O1969 +)
Firing propose*predict-no
 -->
 (O1970 ^name predict-no +)
 (S1 ^operator O1970 +)
Firing rl*prefer*rvt*predict-no*H0*6
 -->
 (S1 ^operator O1968 = 0.9999999999999999)
Firing rl*prefer*rvt*predict-yes*H0*5
 -->
 (S1 ^operator O1967 = 0.)
Firing prefer*rvt*predict-yes*H0
 -->
Firing prefer*rvt*predict-no*H0
 -->
Firing elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir U +)
 inner elaboration loop at bottom goal.
Retracting elaborate*copy-see-to-output-link
 -->
 (I3 ^see 1 +)
Retracting propose*predict-no
 -->
 (O1968 ^name predict-no +)
 (S1 ^operator O1968 +)
Retracting propose*predict-yes
 -->
 (O1967 ^name predict-yes +)
 (S1 ^operator O1967 +)
Retracting elaborate*reward*based*on*reward
 -->
 (R987 ^value 1 +)
 (R1 ^reward R987 +)
Retracting elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir U +)
Retracting rl*prefer*rvt*predict-no*H0*6
 -->
 (S1 ^operator O1968 = 0.9999999999999999)
Retracting rl*prefer*rvt*predict-yes*H0*5
 -->
 (S1 ^operator O1967 = 0.)
=>WM: (13841: S1 ^operator O1970 +)
=>WM: (13840: S1 ^operator O1969 +)
=>WM: (13839: O1970 ^name predict-no)
=>WM: (13838: O1969 ^name predict-yes)
=>WM: (13837: R988 ^value 1)
=>WM: (13836: R1 ^reward R988)
=>WM: (13835: I3 ^see 0)
<=WM: (13826: S1 ^operator O1967 +)
<=WM: (13827: S1 ^operator O1968 +)
<=WM: (13828: S1 ^operator O1968)
<=WM: (13821: R1 ^reward R987)
<=WM: (13820: I3 ^see 1)
<=WM: (13824: O1968 ^name predict-no)
<=WM: (13823: O1967 ^name predict-yes)
<=WM: (13822: R987 ^value 1)

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing prefer*rvt*predict-yes*H0
 -->
Firing rl*prefer*rvt*predict-yes*H0*5
 -->
 (S1 ^operator O1969 = 0.)
Firing prefer*rvt*predict-no*H0
 -->
Firing rl*prefer*rvt*predict-no*H0*6
 -->
 (S1 ^operator O1970 = 0.9999999999999999)
 inner elaboration loop at bottom goal.
Retracting rl*prefer*rvt*predict-no*H0*6
 -->
 (S1 ^operator O1968 = 0.9999999999999999)
Retracting rl*prefer*rvt*predict-yes*H0*5
 -->
 (S1 ^operator O1967 = 0.)

--- END Proposal Phase ---

--- Decision Phase ---
RL update rl*prefer*rvt*predict-no*H0*6 1 0 1 -> 1 0 1(R,m,v=1,1,0)
=>WM: (13842: S1 ^operator O1970)

   985:    O: O1970 (predict-no)
--- END Decision Phase ---

--- Application Phase ---
	--- Firing Productions (PE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing apply*operator
 -->
 (I3 ^predict-no N985 +  :O )
Firing apply*operator*complete
 -->
 (I3 ^predict-no N984 -  :O )
 inner elaboration loop at bottom goal.
	--- Change Working Memory (PE) ---
=>WM: (13843: I3 ^predict-no N985)
<=WM: (13830: N984 ^status complete)
<=WM: (13829: I3 ^predict-no N984)
	--- Firing Productions (IE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing monitor*world
 -->

I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
	--- Change Working Memory (IE) ---

--- END Application Phase ---
--- Output Phase ---
ENV: Agent did: predict-no for direction U in state State-B
In  State-B moving U
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isR
--- END Output Phase ---
|\--- Input Phase --- 
=>WM: (13847: I2 ^dir R)
=>WM: (13846: I2 ^reward 1)
=>WM: (13845: I2 ^see 0)
=>WM: (13844: N985 ^status complete)
<=WM: (13833: I2 ^dir U)
<=WM: (13832: I2 ^reward 1)
<=WM: (13831: I2 ^see 0)
=>WM: (13848: I2 ^level-1 R1-root)
<=WM: (13834: I2 ^level-1 R1-root)

--- END Input Phase --- 

--- Proposal Phase ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing rl*prefer*rvt*predict-yes*H0*3*H1*16
 -->
 (S1 ^operator O1969 = 0.08783148430849691)
Firing rl*prefer*rvt*predict-no*H0*4*H1*15
 -->
 (S1 ^operator O1970 = 0.8730234118412079)
Firing prefer*rvt*predict-no*H0*4*H1
 -->
Firing prefer*rvt*predict-yes*H0*3*H1
 -->
Firing elaborate*copy-see-to-output-link
 -->
 (I3 ^see 0 +)
Firing elaborate*reward*based*on*reward
 -->
 (R989 ^value 1 +)
 (R1 ^reward R989 +)
Firing propose*predict-yes
 -->
 (O1971 ^name predict-yes +)
 (S1 ^operator O1971 +)
Firing propose*predict-no
 -->
 (O1972 ^name predict-no +)
 (S1 ^operator O1972 +)
Firing rl*prefer*rvt*predict-no*H0*4
 -->
 (S1 ^operator O1970 = 0.1269767445579436)
Firing rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O1969 = 0.3829290045611482)
Firing prefer*rvt*predict-yes*H0
 -->
Firing prefer*rvt*predict-no*H0
 -->
Firing elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir R +)
 inner elaboration loop at bottom goal.
Retracting elaborate*copy-see-to-output-link
 -->
 (I3 ^see 0 +)
Retracting propose*predict-no
 -->
 (O1970 ^name predict-no +)
 (S1 ^operator O1970 +)
Retracting propose*predict-yes
 -->
 (O1969 ^name predict-yes +)
 (S1 ^operator O1969 +)
Retracting elaborate*reward*based*on*reward
 -->
 (R988 ^value 1 +)
 (R1 ^reward R988 +)
Retracting elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir U +)
Retracting rl*prefer*rvt*predict-no*H0*6
 -->
 (S1 ^operator O1970 = 0.9999999999999999)
Retracting rl*prefer*rvt*predict-yes*H0*5
 -->
 (S1 ^operator O1969 = 0.)
=>WM: (13855: S1 ^operator O1972 +)
=>WM: (13854: S1 ^operator O1971 +)
=>WM: (13853: I3 ^dir R)
=>WM: (13852: O1972 ^name predict-no)
=>WM: (13851: O1971 ^name predict-yes)
=>WM: (13850: R989 ^value 1)
=>WM: (13849: R1 ^reward R989)
<=WM: (13840: S1 ^operator O1969 +)
<=WM: (13841: S1 ^operator O1970 +)
<=WM: (13842: S1 ^operator O1970)
<=WM: (13825: I3 ^dir U)
<=WM: (13836: R1 ^reward R988)
<=WM: (13839: O1970 ^name predict-no)
<=WM: (13838: O1969 ^name predict-yes)
<=WM: (13837: R988 ^value 1)

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing prefer*rvt*predict-yes*H0
 -->
Firing rl*prefer*rvt*predict-yes*H0*3*H1*16
 -->
 (S1 ^operator O1971 = 0.08783148430849691)
Firing rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O1971 = 0.3829290045611482)
Firing prefer*rvt*predict-yes*H0*3*H1
 -->
Firing prefer*rvt*predict-no*H0
 -->
Firing rl*prefer*rvt*predict-no*H0*4*H1*15
 -->
 (S1 ^operator O1972 = 0.8730234118412079)
Firing rl*prefer*rvt*predict-no*H0*4
 -->
 (S1 ^operator O1972 = 0.1269767445579436)
Firing prefer*rvt*predict-no*H0*4*H1
 -->
 inner elaboration loop at bottom goal.
Retracting rl*prefer*rvt*predict-no*H0*4
 -->
 (S1 ^operator O1970 = 0.1269767445579436)
Retracting rl*prefer*rvt*predict-no*H0*4*H1*15
 -->
 (S1 ^operator O1970 = 0.8730234118412079)
Retracting rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O1969 = 0.3829290045611482)
Retracting rl*prefer*rvt*predict-yes*H0*3*H1*16
 -->
 (S1 ^operator O1969 = 0.08783148430849691)

--- END Proposal Phase ---

--- Decision Phase ---
RL update rl*prefer*rvt*predict-no*H0*6 1 0 1 -> 1 0 1(R,m,v=1,1,0)
=>WM: (13856: S1 ^operator O1972)

   986:    O: O1972 (predict-no)
--- END Decision Phase ---

--- Application Phase ---
	--- Firing Productions (PE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing apply*operator
 -->
 (I3 ^predict-no N986 +  :O )
Firing apply*operator*complete
 -->
 (I3 ^predict-no N985 -  :O )
 inner elaboration loop at bottom goal.
	--- Change Working Memory (PE) ---
=>WM: (13857: I3 ^predict-no N986)
<=WM: (13844: N985 ^status complete)
<=WM: (13843: I3 ^predict-no N985)
	--- Firing Productions (IE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing monitor*world
 -->

I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
	--- Change Working Memory (IE) ---

--- END Application Phase ---
--- Output Phase ---
ENV: Agent did: predict-no for direction R in state State-B
In  State-B moving R
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isR
--- END Output Phase ---
-/|--- Input Phase --- 
=>WM: (13861: I2 ^dir R)
=>WM: (13860: I2 ^reward 1)
=>WM: (13859: I2 ^see 0)
=>WM: (13858: N986 ^status complete)
<=WM: (13847: I2 ^dir R)
<=WM: (13846: I2 ^reward 1)
<=WM: (13845: I2 ^see 0)
=>WM: (13862: I2 ^level-1 R0-root)
<=WM: (13848: I2 ^level-1 R1-root)

--- END Input Phase --- 

--- Proposal Phase ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing rl*prefer*rvt*predict-yes*H0*3*H1*18
 -->
 (S1 ^operator O1971 = 0.2696941111808541)
Firing rl*prefer*rvt*predict-no*H0*4*H1*17
 -->
 (S1 ^operator O1972 = 0.8730228631156078)
Firing prefer*rvt*predict-no*H0*4*H1
 -->
Firing prefer*rvt*predict-yes*H0*3*H1
 -->
Firing elaborate*copy-see-to-output-link
 -->
 (I3 ^see 0 +)
Firing elaborate*reward*based*on*reward
 -->
 (R990 ^value 1 +)
 (R1 ^reward R990 +)
Firing propose*predict-yes
 -->
 (O1973 ^name predict-yes +)
 (S1 ^operator O1973 +)
Firing propose*predict-no
 -->
 (O1974 ^name predict-no +)
 (S1 ^operator O1974 +)
Firing rl*prefer*rvt*predict-no*H0*4
 -->
 (S1 ^operator O1972 = 0.1269767445579436)
Firing rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O1971 = 0.3829290045611482)
Firing prefer*rvt*predict-yes*H0
 -->
Firing prefer*rvt*predict-no*H0
 -->
Firing elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir R +)
 inner elaboration loop at bottom goal.
Retracting elaborate*copy-see-to-output-link
 -->
 (I3 ^see 0 +)
Retracting propose*predict-no
 -->
 (O1972 ^name predict-no +)
 (S1 ^operator O1972 +)
Retracting propose*predict-yes
 -->
 (O1971 ^name predict-yes +)
 (S1 ^operator O1971 +)
Retracting elaborate*reward*based*on*reward
 -->
 (R989 ^value 1 +)
 (R1 ^reward R989 +)
Retracting elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir R +)
Retracting rl*prefer*rvt*predict-no*H0*4
 -->
 (S1 ^operator O1972 = 0.1269767445579436)
Retracting rl*prefer*rvt*predict-no*H0*4*H1*15
 -->
 (S1 ^operator O1972 = 0.8730234118412079)
Retracting rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O1971 = 0.3829290045611482)
Retracting rl*prefer*rvt*predict-yes*H0*3*H1*16
 -->
 (S1 ^operator O1971 = 0.08783148430849691)
=>WM: (13868: S1 ^operator O1974 +)
=>WM: (13867: S1 ^operator O1973 +)
=>WM: (13866: O1974 ^name predict-no)
=>WM: (13865: O1973 ^name predict-yes)
=>WM: (13864: R990 ^value 1)
=>WM: (13863: R1 ^reward R990)
<=WM: (13854: S1 ^operator O1971 +)
<=WM: (13855: S1 ^operator O1972 +)
<=WM: (13856: S1 ^operator O1972)
<=WM: (13849: R1 ^reward R989)
<=WM: (13852: O1972 ^name predict-no)
<=WM: (13851: O1971 ^name predict-yes)
<=WM: (13850: R989 ^value 1)

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing prefer*rvt*predict-yes*H0
 -->
Firing rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O1973 = 0.3829290045611482)
Firing prefer*rvt*predict-yes*H0*3*H1
 -->
Firing rl*prefer*rvt*predict-yes*H0*3*H1*18
 -->
 (S1 ^operator O1973 = 0.2696941111808541)
Firing prefer*rvt*predict-no*H0
 -->
Firing rl*prefer*rvt*predict-no*H0*4
 -->
 (S1 ^operator O1974 = 0.1269767445579436)
Firing prefer*rvt*predict-no*H0*4*H1
 -->
Firing rl*prefer*rvt*predict-no*H0*4*H1*17
 -->
 (S1 ^operator O1974 = 0.8730228631156078)
 inner elaboration loop at bottom goal.
Retracting rl*prefer*rvt*predict-no*H0*4
 -->
 (S1 ^operator O1972 = 0.1269767445579436)
Retracting rl*prefer*rvt*predict-no*H0*4*H1*17
 -->
 (S1 ^operator O1972 = 0.8730228631156078)
Retracting rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O1971 = 0.3829290045611482)
Retracting rl*prefer*rvt*predict-yes*H0*3*H1*18
 -->
 (S1 ^operator O1971 = 0.2696941111808541)

--- END Proposal Phase ---

--- Decision Phase ---
RL update rl*prefer*rvt*predict-no*H0*4 0.814714 -0.687737 0.126977 -> 0.814714 -0.687737 0.126977(R,m,v=1,0.948276,0.0493323)
RL update rl*prefer*rvt*predict-no*H0*4*H1*15 0.185286 0.687737 0.873023 -> 0.185286 0.687737 0.873023(R,m,v=1,1,0)
=>WM: (13869: S1 ^operator O1974)

   987:    O: O1974 (predict-no)
--- END Decision Phase ---

--- Application Phase ---
	--- Firing Productions (PE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing apply*operator
 -->
 (I3 ^predict-no N987 +  :O )
Firing apply*operator*complete
 -->
 (I3 ^predict-no N986 -  :O )
 inner elaboration loop at bottom goal.
	--- Change Working Memory (PE) ---
=>WM: (13870: I3 ^predict-no N987)
<=WM: (13858: N986 ^status complete)
<=WM: (13857: I3 ^predict-no N986)
	--- Firing Productions (IE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing monitor*world
 -->

I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
	--- Change Working Memory (IE) ---

--- END Application Phase ---
--- Output Phase ---
ENV: Agent did: predict-no for direction R in state State-B
In  State-B moving R
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isR
--- END Output Phase ---
\-/|--- Input Phase --- 
=>WM: (13874: I2 ^dir R)
=>WM: (13873: I2 ^reward 1)
=>WM: (13872: I2 ^see 0)
=>WM: (13871: N987 ^status complete)
<=WM: (13861: I2 ^dir R)
<=WM: (13860: I2 ^reward 1)
<=WM: (13859: I2 ^see 0)
=>WM: (13875: I2 ^level-1 R0-root)
<=WM: (13862: I2 ^level-1 R0-root)

--- END Input Phase --- 

--- Proposal Phase ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing rl*prefer*rvt*predict-yes*H0*3*H1*18
 -->
 (S1 ^operator O1973 = 0.2696941111808541)
Firing rl*prefer*rvt*predict-no*H0*4*H1*17
 -->
 (S1 ^operator O1974 = 0.8730228631156078)
Firing prefer*rvt*predict-no*H0*4*H1
 -->
Firing prefer*rvt*predict-yes*H0*3*H1
 -->
Firing elaborate*copy-see-to-output-link
 -->
 (I3 ^see 0 +)
Firing elaborate*reward*based*on*reward
 -->
 (R991 ^value 1 +)
 (R1 ^reward R991 +)
Firing propose*predict-yes
 -->
 (O1975 ^name predict-yes +)
 (S1 ^operator O1975 +)
Firing propose*predict-no
 -->
 (O1976 ^name predict-no +)
 (S1 ^operator O1976 +)
Firing rl*prefer*rvt*predict-no*H0*4
 -->
 (S1 ^operator O1974 = 0.1269767210980709)
Firing rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O1973 = 0.3829290045611482)
Firing prefer*rvt*predict-yes*H0
 -->
Firing prefer*rvt*predict-no*H0
 -->
Firing elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir R +)
 inner elaboration loop at bottom goal.
Retracting elaborate*copy-see-to-output-link
 -->
 (I3 ^see 0 +)
Retracting propose*predict-no
 -->
 (O1974 ^name predict-no +)
 (S1 ^operator O1974 +)
Retracting propose*predict-yes
 -->
 (O1973 ^name predict-yes +)
 (S1 ^operator O1973 +)
Retracting elaborate*reward*based*on*reward
 -->
 (R990 ^value 1 +)
 (R1 ^reward R990 +)
Retracting elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir R +)
Retracting rl*prefer*rvt*predict-no*H0*4*H1*17
 -->
 (S1 ^operator O1974 = 0.8730228631156078)
Retracting rl*prefer*rvt*predict-no*H0*4
 -->
 (S1 ^operator O1974 = 0.1269767210980709)
Retracting rl*prefer*rvt*predict-yes*H0*3*H1*18
 -->
 (S1 ^operator O1973 = 0.2696941111808541)
Retracting rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O1973 = 0.3829290045611482)
=>WM: (13881: S1 ^operator O1976 +)
=>WM: (13880: S1 ^operator O1975 +)
=>WM: (13879: O1976 ^name predict-no)
=>WM: (13878: O1975 ^name predict-yes)
=>WM: (13877: R991 ^value 1)
=>WM: (13876: R1 ^reward R991)
<=WM: (13867: S1 ^operator O1973 +)
<=WM: (13868: S1 ^operator O1974 +)
<=WM: (13869: S1 ^operator O1974)
<=WM: (13863: R1 ^reward R990)
<=WM: (13866: O1974 ^name predict-no)
<=WM: (13865: O1973 ^name predict-yes)
<=WM: (13864: R990 ^value 1)

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing prefer*rvt*predict-yes*H0
 -->
Firing rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O1975 = 0.3829290045611482)
Firing prefer*rvt*predict-yes*H0*3*H1
 -->
Firing rl*prefer*rvt*predict-yes*H0*3*H1*18
 -->
 (S1 ^operator O1975 = 0.2696941111808541)
Firing prefer*rvt*predict-no*H0
 -->
Firing rl*prefer*rvt*predict-no*H0*4
 -->
 (S1 ^operator O1976 = 0.1269767210980709)
Firing prefer*rvt*predict-no*H0*4*H1
 -->
Firing rl*prefer*rvt*predict-no*H0*4*H1*17
 -->
 (S1 ^operator O1976 = 0.8730228631156078)
 inner elaboration loop at bottom goal.
Retracting rl*prefer*rvt*predict-no*H0*4
 -->
 (S1 ^operator O1974 = 0.1269767210980709)
Retracting rl*prefer*rvt*predict-no*H0*4*H1*17
 -->
 (S1 ^operator O1974 = 0.8730228631156078)
Retracting rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O1973 = 0.3829290045611482)
Retracting rl*prefer*rvt*predict-yes*H0*3*H1*18
 -->
 (S1 ^operator O1973 = 0.2696941111808541)

--- END Proposal Phase ---

--- Decision Phase ---
RL update rl*prefer*rvt*predict-no*H0*4 0.814714 -0.687737 0.126977 -> 0.814714 -0.687737 0.126977(R,m,v=1,0.948571,0.049064)
RL update rl*prefer*rvt*predict-no*H0*4*H1*17 0.185286 0.687737 0.873023 -> 0.185286 0.687737 0.873023(R,m,v=1,1,0)
=>WM: (13882: S1 ^operator O1976)

   988:    O: O1976 (predict-no)
--- END Decision Phase ---

--- Application Phase ---
	--- Firing Productions (PE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing apply*operator
 -->
 (I3 ^predict-no N988 +  :O )
Firing apply*operator*complete
 -->
 (I3 ^predict-no N987 -  :O )
 inner elaboration loop at bottom goal.
	--- Change Working Memory (PE) ---
=>WM: (13883: I3 ^predict-no N988)
<=WM: (13871: N987 ^status complete)
<=WM: (13870: I3 ^predict-no N987)
	--- Firing Productions (IE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing monitor*world
 -->

I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
	--- Change Working Memory (IE) ---

--- END Application Phase ---
--- Output Phase ---
ENV: Agent did: predict-no for direction R in state State-B
In  State-B moving R
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isR
--- END Output Phase ---
\---- Input Phase --- 
=>WM: (13887: I2 ^dir R)
=>WM: (13886: I2 ^reward 1)
=>WM: (13885: I2 ^see 0)
=>WM: (13884: N988 ^status complete)
<=WM: (13874: I2 ^dir R)
<=WM: (13873: I2 ^reward 1)
<=WM: (13872: I2 ^see 0)
=>WM: (13888: I2 ^level-1 R0-root)
<=WM: (13875: I2 ^level-1 R0-root)

--- END Input Phase --- 

--- Proposal Phase ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing rl*prefer*rvt*predict-yes*H0*3*H1*18
 -->
 (S1 ^operator O1975 = 0.2696941111808541)
Firing rl*prefer*rvt*predict-no*H0*4*H1*17
 -->
 (S1 ^operator O1976 = 0.8730229254835561)
Firing prefer*rvt*predict-no*H0*4*H1
 -->
Firing prefer*rvt*predict-yes*H0*3*H1
 -->
Firing elaborate*copy-see-to-output-link
 -->
 (I3 ^see 0 +)
Firing elaborate*reward*based*on*reward
 -->
 (R992 ^value 1 +)
 (R1 ^reward R992 +)
Firing propose*predict-yes
 -->
 (O1977 ^name predict-yes +)
 (S1 ^operator O1977 +)
Firing propose*predict-no
 -->
 (O1978 ^name predict-no +)
 (S1 ^operator O1978 +)
Firing rl*prefer*rvt*predict-no*H0*4
 -->
 (S1 ^operator O1976 = 0.126976783466019)
Firing rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O1975 = 0.3829290045611482)
Firing prefer*rvt*predict-yes*H0
 -->
Firing prefer*rvt*predict-no*H0
 -->
Firing elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir R +)
 inner elaboration loop at bottom goal.
Retracting elaborate*copy-see-to-output-link
 -->
 (I3 ^see 0 +)
Retracting propose*predict-no
 -->
 (O1976 ^name predict-no +)
 (S1 ^operator O1976 +)
Retracting propose*predict-yes
 -->
 (O1975 ^name predict-yes +)
 (S1 ^operator O1975 +)
Retracting elaborate*reward*based*on*reward
 -->
 (R991 ^value 1 +)
 (R1 ^reward R991 +)
Retracting elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir R +)
Retracting rl*prefer*rvt*predict-no*H0*4*H1*17
 -->
 (S1 ^operator O1976 = 0.8730229254835561)
Retracting rl*prefer*rvt*predict-no*H0*4
 -->
 (S1 ^operator O1976 = 0.126976783466019)
Retracting rl*prefer*rvt*predict-yes*H0*3*H1*18
 -->
 (S1 ^operator O1975 = 0.2696941111808541)
Retracting rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O1975 = 0.3829290045611482)
=>WM: (13894: S1 ^operator O1978 +)
=>WM: (13893: S1 ^operator O1977 +)
=>WM: (13892: O1978 ^name predict-no)
=>WM: (13891: O1977 ^name predict-yes)
=>WM: (13890: R992 ^value 1)
=>WM: (13889: R1 ^reward R992)
<=WM: (13880: S1 ^operator O1975 +)
<=WM: (13881: S1 ^operator O1976 +)
<=WM: (13882: S1 ^operator O1976)
<=WM: (13876: R1 ^reward R991)
<=WM: (13879: O1976 ^name predict-no)
<=WM: (13878: O1975 ^name predict-yes)
<=WM: (13877: R991 ^value 1)

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing prefer*rvt*predict-yes*H0
 -->
Firing rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O1977 = 0.3829290045611482)
Firing prefer*rvt*predict-yes*H0*3*H1
 -->
Firing rl*prefer*rvt*predict-yes*H0*3*H1*18
 -->
 (S1 ^operator O1977 = 0.2696941111808541)
Firing prefer*rvt*predict-no*H0
 -->
Firing rl*prefer*rvt*predict-no*H0*4
 -->
 (S1 ^operator O1978 = 0.126976783466019)
Firing prefer*rvt*predict-no*H0*4*H1
 -->
Firing rl*prefer*rvt*predict-no*H0*4*H1*17
 -->
 (S1 ^operator O1978 = 0.8730229254835561)
 inner elaboration loop at bottom goal.
Retracting rl*prefer*rvt*predict-no*H0*4
 -->
 (S1 ^operator O1976 = 0.126976783466019)
Retracting rl*prefer*rvt*predict-no*H0*4*H1*17
 -->
 (S1 ^operator O1976 = 0.8730229254835561)
Retracting rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O1975 = 0.3829290045611482)
Retracting rl*prefer*rvt*predict-yes*H0*3*H1*18
 -->
 (S1 ^operator O1975 = 0.2696941111808541)

--- END Proposal Phase ---

--- Decision Phase ---
RL update rl*prefer*rvt*predict-no*H0*4 0.814714 -0.687737 0.126977 -> 0.814714 -0.687737 0.126977(R,m,v=1,0.948864,0.0487987)
RL update rl*prefer*rvt*predict-no*H0*4*H1*17 0.185286 0.687737 0.873023 -> 0.185286 0.687737 0.873023(R,m,v=1,1,0)
=>WM: (13895: S1 ^operator O1978)

   989:    O: O1978 (predict-no)
--- END Decision Phase ---

--- Application Phase ---
	--- Firing Productions (PE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing apply*operator
 -->
 (I3 ^predict-no N989 +  :O )
Firing apply*operator*complete
 -->
 (I3 ^predict-no N988 -  :O )
 inner elaboration loop at bottom goal.
	--- Change Working Memory (PE) ---
=>WM: (13896: I3 ^predict-no N989)
<=WM: (13884: N988 ^status complete)
<=WM: (13883: I3 ^predict-no N988)
	--- Firing Productions (IE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing monitor*world
 -->

I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
	--- Change Working Memory (IE) ---

--- END Application Phase ---
--- Output Phase ---
ENV: Agent did: predict-no for direction R in state State-B
In  State-B moving R
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isR
--- END Output Phase ---
/|\--- Input Phase --- 
=>WM: (13900: I2 ^dir R)
=>WM: (13899: I2 ^reward 1)
=>WM: (13898: I2 ^see 0)
=>WM: (13897: N989 ^status complete)
<=WM: (13887: I2 ^dir R)
<=WM: (13886: I2 ^reward 1)
<=WM: (13885: I2 ^see 0)
=>WM: (13901: I2 ^level-1 R0-root)
<=WM: (13888: I2 ^level-1 R0-root)

--- END Input Phase --- 

--- Proposal Phase ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing rl*prefer*rvt*predict-yes*H0*3*H1*18
 -->
 (S1 ^operator O1977 = 0.2696941111808541)
Firing rl*prefer*rvt*predict-no*H0*4*H1*17
 -->
 (S1 ^operator O1978 = 0.8730229691411198)
Firing prefer*rvt*predict-no*H0*4*H1
 -->
Firing prefer*rvt*predict-yes*H0*3*H1
 -->
Firing elaborate*copy-see-to-output-link
 -->
 (I3 ^see 0 +)
Firing elaborate*reward*based*on*reward
 -->
 (R993 ^value 1 +)
 (R1 ^reward R993 +)
Firing propose*predict-yes
 -->
 (O1979 ^name predict-yes +)
 (S1 ^operator O1979 +)
Firing propose*predict-no
 -->
 (O1980 ^name predict-no +)
 (S1 ^operator O1980 +)
Firing rl*prefer*rvt*predict-no*H0*4
 -->
 (S1 ^operator O1978 = 0.1269768271235827)
Firing rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O1977 = 0.3829290045611482)
Firing prefer*rvt*predict-yes*H0
 -->
Firing prefer*rvt*predict-no*H0
 -->
Firing elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir R +)
 inner elaboration loop at bottom goal.
Retracting elaborate*copy-see-to-output-link
 -->
 (I3 ^see 0 +)
Retracting propose*predict-no
 -->
 (O1978 ^name predict-no +)
 (S1 ^operator O1978 +)
Retracting propose*predict-yes
 -->
 (O1977 ^name predict-yes +)
 (S1 ^operator O1977 +)
Retracting elaborate*reward*based*on*reward
 -->
 (R992 ^value 1 +)
 (R1 ^reward R992 +)
Retracting elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir R +)
Retracting rl*prefer*rvt*predict-no*H0*4*H1*17
 -->
 (S1 ^operator O1978 = 0.8730229691411198)
Retracting rl*prefer*rvt*predict-no*H0*4
 -->
 (S1 ^operator O1978 = 0.1269768271235827)
Retracting rl*prefer*rvt*predict-yes*H0*3*H1*18
 -->
 (S1 ^operator O1977 = 0.2696941111808541)
Retracting rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O1977 = 0.3829290045611482)
=>WM: (13907: S1 ^operator O1980 +)
=>WM: (13906: S1 ^operator O1979 +)
=>WM: (13905: O1980 ^name predict-no)
=>WM: (13904: O1979 ^name predict-yes)
=>WM: (13903: R993 ^value 1)
=>WM: (13902: R1 ^reward R993)
<=WM: (13893: S1 ^operator O1977 +)
<=WM: (13894: S1 ^operator O1978 +)
<=WM: (13895: S1 ^operator O1978)
<=WM: (13889: R1 ^reward R992)
<=WM: (13892: O1978 ^name predict-no)
<=WM: (13891: O1977 ^name predict-yes)
<=WM: (13890: R992 ^value 1)

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing prefer*rvt*predict-yes*H0
 -->
Firing rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O1979 = 0.3829290045611482)
Firing prefer*rvt*predict-yes*H0*3*H1
 -->
Firing rl*prefer*rvt*predict-yes*H0*3*H1*18
 -->
 (S1 ^operator O1979 = 0.2696941111808541)
Firing prefer*rvt*predict-no*H0
 -->
Firing rl*prefer*rvt*predict-no*H0*4
 -->
 (S1 ^operator O1980 = 0.1269768271235827)
Firing prefer*rvt*predict-no*H0*4*H1
 -->
Firing rl*prefer*rvt*predict-no*H0*4*H1*17
 -->
 (S1 ^operator O1980 = 0.8730229691411198)
 inner elaboration loop at bottom goal.
Retracting rl*prefer*rvt*predict-no*H0*4
 -->
 (S1 ^operator O1978 = 0.1269768271235827)
Retracting rl*prefer*rvt*predict-no*H0*4*H1*17
 -->
 (S1 ^operator O1978 = 0.8730229691411198)
Retracting rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O1977 = 0.3829290045611482)
Retracting rl*prefer*rvt*predict-yes*H0*3*H1*18
 -->
 (S1 ^operator O1977 = 0.2696941111808541)

--- END Proposal Phase ---

--- Decision Phase ---
RL update rl*prefer*rvt*predict-no*H0*4 0.814714 -0.687737 0.126977 -> 0.814714 -0.687737 0.126977(R,m,v=1,0.949153,0.0485362)
RL update rl*prefer*rvt*predict-no*H0*4*H1*17 0.185286 0.687737 0.873023 -> 0.185286 0.687737 0.873023(R,m,v=1,1,0)
=>WM: (13908: S1 ^operator O1980)

   990:    O: O1980 (predict-no)
--- END Decision Phase ---

--- Application Phase ---
	--- Firing Productions (PE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing apply*operator
 -->
 (I3 ^predict-no N990 +  :O )
Firing apply*operator*complete
 -->
 (I3 ^predict-no N989 -  :O )
 inner elaboration loop at bottom goal.
	--- Change Working Memory (PE) ---
=>WM: (13909: I3 ^predict-no N990)
<=WM: (13897: N989 ^status complete)
<=WM: (13896: I3 ^predict-no N989)
	--- Firing Productions (IE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing monitor*world
 -->

I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
	--- Change Working Memory (IE) ---

--- END Application Phase ---
--- Output Phase ---
ENV: Agent did: predict-no for direction R in state State-B
In  State-B moving R
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isU
--- END Output Phase ---
-/--- Input Phase --- 
=>WM: (13913: I2 ^dir U)
=>WM: (13912: I2 ^reward 1)
=>WM: (13911: I2 ^see 0)
=>WM: (13910: N990 ^status complete)
<=WM: (13900: I2 ^dir R)
<=WM: (13899: I2 ^reward 1)
<=WM: (13898: I2 ^see 0)
=>WM: (13914: I2 ^level-1 R0-root)
<=WM: (13901: I2 ^level-1 R0-root)

--- END Input Phase --- 

--- Proposal Phase ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing elaborate*copy-see-to-output-link
 -->
 (I3 ^see 0 +)
Firing elaborate*reward*based*on*reward
 -->
 (R994 ^value 1 +)
 (R1 ^reward R994 +)
Firing propose*predict-yes
 -->
 (O1981 ^name predict-yes +)
 (S1 ^operator O1981 +)
Firing propose*predict-no
 -->
 (O1982 ^name predict-no +)
 (S1 ^operator O1982 +)
Firing rl*prefer*rvt*predict-no*H0*6
 -->
 (S1 ^operator O1980 = 0.9999999999999999)
Firing rl*prefer*rvt*predict-yes*H0*5
 -->
 (S1 ^operator O1979 = 0.)
Firing prefer*rvt*predict-yes*H0
 -->
Firing prefer*rvt*predict-no*H0
 -->
Firing elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir U +)
 inner elaboration loop at bottom goal.
Retracting elaborate*copy-see-to-output-link
 -->
 (I3 ^see 0 +)
Retracting propose*predict-no
 -->
 (O1980 ^name predict-no +)
 (S1 ^operator O1980 +)
Retracting propose*predict-yes
 -->
 (O1979 ^name predict-yes +)
 (S1 ^operator O1979 +)
Retracting elaborate*reward*based*on*reward
 -->
 (R993 ^value 1 +)
 (R1 ^reward R993 +)
Retracting elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir R +)
Retracting rl*prefer*rvt*predict-no*H0*4*H1*17
 -->
 (S1 ^operator O1980 = 0.8730229997014144)
Retracting rl*prefer*rvt*predict-no*H0*4
 -->
 (S1 ^operator O1980 = 0.1269768576838773)
Retracting rl*prefer*rvt*predict-yes*H0*3*H1*18
 -->
 (S1 ^operator O1979 = 0.2696941111808541)
Retracting rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O1979 = 0.3829290045611482)
=>WM: (13921: S1 ^operator O1982 +)
=>WM: (13920: S1 ^operator O1981 +)
=>WM: (13919: I3 ^dir U)
=>WM: (13918: O1982 ^name predict-no)
=>WM: (13917: O1981 ^name predict-yes)
=>WM: (13916: R994 ^value 1)
=>WM: (13915: R1 ^reward R994)
<=WM: (13906: S1 ^operator O1979 +)
<=WM: (13907: S1 ^operator O1980 +)
<=WM: (13908: S1 ^operator O1980)
<=WM: (13853: I3 ^dir R)
<=WM: (13902: R1 ^reward R993)
<=WM: (13905: O1980 ^name predict-no)
<=WM: (13904: O1979 ^name predict-yes)
<=WM: (13903: R993 ^value 1)

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing prefer*rvt*predict-yes*H0
 -->
Firing rl*prefer*rvt*predict-yes*H0*5
 -->
 (S1 ^operator O1981 = 0.)
Firing prefer*rvt*predict-no*H0
 -->
Firing rl*prefer*rvt*predict-no*H0*6
 -->
 (S1 ^operator O1982 = 0.9999999999999999)
 inner elaboration loop at bottom goal.
Retracting rl*prefer*rvt*predict-no*H0*6
 -->
 (S1 ^operator O1980 = 0.9999999999999999)
Retracting rl*prefer*rvt*predict-yes*H0*5
 -->
 (S1 ^operator O1979 = 0.)

--- END Proposal Phase ---

--- Decision Phase ---
RL update rl*prefer*rvt*predict-no*H0*4 0.814714 -0.687737 0.126977 -> 0.814714 -0.687737 0.126977(R,m,v=1,0.949438,0.0482765)
RL update rl*prefer*rvt*predict-no*H0*4*H1*17 0.185286 0.687737 0.873023 -> 0.185286 0.687737 0.873023(R,m,v=1,1,0)
=>WM: (13922: S1 ^operator O1982)

   991:    O: O1982 (predict-no)
--- END Decision Phase ---

--- Application Phase ---
	--- Firing Productions (PE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing apply*operator
 -->
 (I3 ^predict-no N991 +  :O )
Firing apply*operator*complete
 -->
 (I3 ^predict-no N990 -  :O )
 inner elaboration loop at bottom goal.
	--- Change Working Memory (PE) ---
=>WM: (13923: I3 ^predict-no N991)
<=WM: (13910: N990 ^status complete)
<=WM: (13909: I3 ^predict-no N990)
	--- Firing Productions (IE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing monitor*world
 -->

I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
	--- Change Working Memory (IE) ---

--- END Application Phase ---
--- Output Phase ---
ENV: Agent did: predict-no for direction U in state State-B
In  State-B moving U
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isL
--- END Output Phase ---
|--- Input Phase --- 
=>WM: (13927: I2 ^dir L)
=>WM: (13926: I2 ^reward 1)
=>WM: (13925: I2 ^see 0)
=>WM: (13924: N991 ^status complete)
<=WM: (13913: I2 ^dir U)
<=WM: (13912: I2 ^reward 1)
<=WM: (13911: I2 ^see 0)
=>WM: (13928: I2 ^level-1 R0-root)
<=WM: (13914: I2 ^level-1 R0-root)

--- END Input Phase --- 

--- Proposal Phase ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing rl*prefer*rvt*predict-yes*H0*1*H1*19
 -->
 (S1 ^operator O1981 = 0.4768833204434785)
Firing rl*prefer*rvt*predict-no*H0*2*H1*7
 -->
 (S1 ^operator O1982 = 0.1700769046561409)
Firing prefer*rvt*predict-no*H0*2*H1
 -->
Firing prefer*rvt*predict-yes*H0*1*H1
 -->
Firing elaborate*copy-see-to-output-link
 -->
 (I3 ^see 0 +)
Firing elaborate*reward*based*on*reward
 -->
 (R995 ^value 1 +)
 (R1 ^reward R995 +)
Firing propose*predict-yes
 -->
 (O1983 ^name predict-yes +)
 (S1 ^operator O1983 +)
Firing propose*predict-no
 -->
 (O1984 ^name predict-no +)
 (S1 ^operator O1984 +)
Firing rl*prefer*rvt*predict-no*H0*2
 -->
 (S1 ^operator O1982 = 0.2550133828092577)
Firing rl*prefer*rvt*predict-yes*H0*1
 -->
 (S1 ^operator O1981 = 0.5231200982015054)
Firing prefer*rvt*predict-yes*H0
 -->
Firing prefer*rvt*predict-no*H0
 -->
Firing elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir L +)
 inner elaboration loop at bottom goal.
Retracting elaborate*copy-see-to-output-link
 -->
 (I3 ^see 0 +)
Retracting propose*predict-no
 -->
 (O1982 ^name predict-no +)
 (S1 ^operator O1982 +)
Retracting propose*predict-yes
 -->
 (O1981 ^name predict-yes +)
 (S1 ^operator O1981 +)
Retracting elaborate*reward*based*on*reward
 -->
 (R994 ^value 1 +)
 (R1 ^reward R994 +)
Retracting elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir U +)
Retracting rl*prefer*rvt*predict-no*H0*6
 -->
 (S1 ^operator O1982 = 0.9999999999999999)
Retracting rl*prefer*rvt*predict-yes*H0*5
 -->
 (S1 ^operator O1981 = 0.)
=>WM: (13935: S1 ^operator O1984 +)
=>WM: (13934: S1 ^operator O1983 +)
=>WM: (13933: I3 ^dir L)
=>WM: (13932: O1984 ^name predict-no)
=>WM: (13931: O1983 ^name predict-yes)
=>WM: (13930: R995 ^value 1)
=>WM: (13929: R1 ^reward R995)
<=WM: (13920: S1 ^operator O1981 +)
<=WM: (13921: S1 ^operator O1982 +)
<=WM: (13922: S1 ^operator O1982)
<=WM: (13919: I3 ^dir U)
<=WM: (13915: R1 ^reward R994)
<=WM: (13918: O1982 ^name predict-no)
<=WM: (13917: O1981 ^name predict-yes)
<=WM: (13916: R994 ^value 1)

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing prefer*rvt*predict-yes*H0
 -->
Firing rl*prefer*rvt*predict-yes*H0*1*H1*19
 -->
 (S1 ^operator O1983 = 0.4768833204434785)
Firing rl*prefer*rvt*predict-yes*H0*1
 -->
 (S1 ^operator O1983 = 0.5231200982015054)
Firing prefer*rvt*predict-yes*H0*1*H1
 -->
Firing prefer*rvt*predict-no*H0
 -->
Firing rl*prefer*rvt*predict-no*H0*2*H1*7
 -->
 (S1 ^operator O1984 = 0.1700769046561409)
Firing rl*prefer*rvt*predict-no*H0*2
 -->
 (S1 ^operator O1984 = 0.2550133828092577)
Firing prefer*rvt*predict-no*H0*2*H1
 -->
 inner elaboration loop at bottom goal.
Retracting rl*prefer*rvt*predict-no*H0*2
 -->
 (S1 ^operator O1982 = 0.2550133828092577)
Retracting rl*prefer*rvt*predict-no*H0*2*H1*7
 -->
 (S1 ^operator O1982 = 0.1700769046561409)
Retracting rl*prefer*rvt*predict-yes*H0*1
 -->
 (S1 ^operator O1981 = 0.5231200982015054)
Retracting rl*prefer*rvt*predict-yes*H0*1*H1*19
 -->
 (S1 ^operator O1981 = 0.4768833204434785)

--- END Proposal Phase ---

--- Decision Phase ---
RL update rl*prefer*rvt*predict-no*H0*6 1 0 1 -> 1 0 1(R,m,v=1,1,0)
=>WM: (13936: S1 ^operator O1983)

   992:    O: O1983 (predict-yes)
--- END Decision Phase ---

--- Application Phase ---
	--- Firing Productions (PE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing apply*operator
 -->
 (I3 ^predict-yes N992 +  :O )
Firing apply*operator*complete
 -->
 (I3 ^predict-no N991 -  :O )
 inner elaboration loop at bottom goal.
	--- Change Working Memory (PE) ---
=>WM: (13937: I3 ^predict-yes N992)
<=WM: (13924: N991 ^status complete)
<=WM: (13923: I3 ^predict-no N991)
	--- Firing Productions (IE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing monitor*world
 -->

I see 1 and I'm going to do: predict-yes inner elaboration loop at bottom goal.
	--- Change Working Memory (IE) ---

--- END Application Phase ---
--- Output Phase ---
ENV: Agent did: predict-yes for direction L in state State-B
In  State-B moving L
ENV: (next state, see, prediction correct?) = (State-A, 1, True)
predict error 0
dir: dir isR
--- END Output Phase ---
\-/--- Input Phase --- 
=>WM: (13941: I2 ^dir R)
=>WM: (13940: I2 ^reward 1)
=>WM: (13939: I2 ^see 1)
=>WM: (13938: N992 ^status complete)
<=WM: (13927: I2 ^dir L)
<=WM: (13926: I2 ^reward 1)
<=WM: (13925: I2 ^see 0)
=>WM: (13942: I2 ^level-1 L1-root)
<=WM: (13928: I2 ^level-1 R0-root)

--- END Input Phase --- 

--- Proposal Phase ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing rl*prefer*rvt*predict-yes*H0*3*H1*9
 -->
 (S1 ^operator O1983 = 0.6170271815281626)
Firing rl*prefer*rvt*predict-no*H0*4*H1*8
 -->
 (S1 ^operator O1984 = 0.4901349546100854)
Firing prefer*rvt*predict-no*H0*4*H1
 -->
Firing prefer*rvt*predict-yes*H0*3*H1
 -->
Firing elaborate*copy-see-to-output-link
 -->
 (I3 ^see 1 +)
Firing elaborate*reward*based*on*reward
 -->
 (R996 ^value 1 +)
 (R1 ^reward R996 +)
Firing propose*predict-yes
 -->
 (O1985 ^name predict-yes +)
 (S1 ^operator O1985 +)
Firing propose*predict-no
 -->
 (O1986 ^name predict-no +)
 (S1 ^operator O1986 +)
Firing rl*prefer*rvt*predict-no*H0*4
 -->
 (S1 ^operator O1984 = 0.1269768790760836)
Firing rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O1983 = 0.3829290045611482)
Firing prefer*rvt*predict-yes*H0
 -->
Firing prefer*rvt*predict-no*H0
 -->
Firing elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir R +)
 inner elaboration loop at bottom goal.
Retracting elaborate*copy-see-to-output-link
 -->
 (I3 ^see 0 +)
Retracting propose*predict-no
 -->
 (O1984 ^name predict-no +)
 (S1 ^operator O1984 +)
Retracting propose*predict-yes
 -->
 (O1983 ^name predict-yes +)
 (S1 ^operator O1983 +)
Retracting elaborate*reward*based*on*reward
 -->
 (R995 ^value 1 +)
 (R1 ^reward R995 +)
Retracting elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir L +)
Retracting rl*prefer*rvt*predict-no*H0*2
 -->
 (S1 ^operator O1984 = 0.2550133828092577)
Retracting rl*prefer*rvt*predict-no*H0*2*H1*7
 -->
 (S1 ^operator O1984 = 0.1700769046561409)
Retracting rl*prefer*rvt*predict-yes*H0*1
 -->
 (S1 ^operator O1983 = 0.5231200982015054)
Retracting rl*prefer*rvt*predict-yes*H0*1*H1*19
 -->
 (S1 ^operator O1983 = 0.4768833204434785)
=>WM: (13950: S1 ^operator O1986 +)
=>WM: (13949: S1 ^operator O1985 +)
=>WM: (13948: I3 ^dir R)
=>WM: (13947: O1986 ^name predict-no)
=>WM: (13946: O1985 ^name predict-yes)
=>WM: (13945: R996 ^value 1)
=>WM: (13944: R1 ^reward R996)
=>WM: (13943: I3 ^see 1)
<=WM: (13934: S1 ^operator O1983 +)
<=WM: (13936: S1 ^operator O1983)
<=WM: (13935: S1 ^operator O1984 +)
<=WM: (13933: I3 ^dir L)
<=WM: (13929: R1 ^reward R995)
<=WM: (13835: I3 ^see 0)
<=WM: (13932: O1984 ^name predict-no)
<=WM: (13931: O1983 ^name predict-yes)
<=WM: (13930: R995 ^value 1)

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing prefer*rvt*predict-yes*H0
 -->
Firing rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O1985 = 0.3829290045611482)
Firing prefer*rvt*predict-yes*H0*3*H1
 -->
Firing rl*prefer*rvt*predict-yes*H0*3*H1*9
 -->
 (S1 ^operator O1985 = 0.6170271815281626)
Firing prefer*rvt*predict-no*H0
 -->
Firing rl*prefer*rvt*predict-no*H0*4
 -->
 (S1 ^operator O1986 = 0.1269768790760836)
Firing prefer*rvt*predict-no*H0*4*H1
 -->
Firing rl*prefer*rvt*predict-no*H0*4*H1*8
 -->
 (S1 ^operator O1986 = 0.4901349546100854)
 inner elaboration loop at bottom goal.
Retracting rl*prefer*rvt*predict-no*H0*4
 -->
 (S1 ^operator O1984 = 0.1269768790760836)
Retracting rl*prefer*rvt*predict-no*H0*4*H1*8
 -->
 (S1 ^operator O1984 = 0.4901349546100854)
Retracting rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O1983 = 0.3829290045611482)
Retracting rl*prefer*rvt*predict-yes*H0*3*H1*9
 -->
 (S1 ^operator O1983 = 0.6170271815281626)

--- END Proposal Phase ---

--- Decision Phase ---
RL update rl*prefer*rvt*predict-yes*H0*1 0.72796 -0.20484 0.52312 -> 0.727959 -0.20484 0.52312(R,m,v=1,0.978723,0.0209726)
RL update rl*prefer*rvt*predict-yes*H0*1*H1*19 0.272045 0.204839 0.476883 -> 0.272044 0.204839 0.476883(R,m,v=1,1,0)
=>WM: (13951: S1 ^operator O1985)

   993:    O: O1985 (predict-yes)
--- END Decision Phase ---

--- Application Phase ---
	--- Firing Productions (PE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing apply*operator
 -->
 (I3 ^predict-yes N993 +  :O )
Firing apply*operator*complete
 -->
 (I3 ^predict-yes N992 -  :O )
 inner elaboration loop at bottom goal.
	--- Change Working Memory (PE) ---
=>WM: (13952: I3 ^predict-yes N993)
<=WM: (13938: N992 ^status complete)
<=WM: (13937: I3 ^predict-yes N992)
	--- Firing Productions (IE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing monitor*world
 -->

I see 1 and I'm going to do: predict-yes inner elaboration loop at bottom goal.
	--- Change Working Memory (IE) ---

--- END Application Phase ---
--- Output Phase ---
ENV: Agent did: predict-yes for direction R in state State-A
In  State-A moving R
ENV: (next state, see, prediction correct?) = (State-B, 1, True)
predict error 0
dir: dir isU
--- END Output Phase ---
|\---- Input Phase --- 
=>WM: (13956: I2 ^dir U)
=>WM: (13955: I2 ^reward 1)
=>WM: (13954: I2 ^see 1)
=>WM: (13953: N993 ^status complete)
<=WM: (13941: I2 ^dir R)
<=WM: (13940: I2 ^reward 1)
<=WM: (13939: I2 ^see 1)
=>WM: (13957: I2 ^level-1 R1-root)
<=WM: (13942: I2 ^level-1 L1-root)

--- END Input Phase --- 

--- Proposal Phase ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing elaborate*copy-see-to-output-link
 -->
 (I3 ^see 1 +)
Firing elaborate*reward*based*on*reward
 -->
 (R997 ^value 1 +)
 (R1 ^reward R997 +)
Firing propose*predict-yes
 -->
 (O1987 ^name predict-yes +)
 (S1 ^operator O1987 +)
Firing propose*predict-no
 -->
 (O1988 ^name predict-no +)
 (S1 ^operator O1988 +)
Firing rl*prefer*rvt*predict-no*H0*6
 -->
 (S1 ^operator O1986 = 0.9999999999999999)
Firing rl*prefer*rvt*predict-yes*H0*5
 -->
 (S1 ^operator O1985 = 0.)
Firing prefer*rvt*predict-yes*H0
 -->
Firing prefer*rvt*predict-no*H0
 -->
Firing elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir U +)
 inner elaboration loop at bottom goal.
Retracting elaborate*copy-see-to-output-link
 -->
 (I3 ^see 1 +)
Retracting propose*predict-no
 -->
 (O1986 ^name predict-no +)
 (S1 ^operator O1986 +)
Retracting propose*predict-yes
 -->
 (O1985 ^name predict-yes +)
 (S1 ^operator O1985 +)
Retracting elaborate*reward*based*on*reward
 -->
 (R996 ^value 1 +)
 (R1 ^reward R996 +)
Retracting elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir R +)
Retracting rl*prefer*rvt*predict-no*H0*4*H1*8
 -->
 (S1 ^operator O1986 = 0.4901349546100854)
Retracting rl*prefer*rvt*predict-no*H0*4
 -->
 (S1 ^operator O1986 = 0.1269768790760836)
Retracting rl*prefer*rvt*predict-yes*H0*3*H1*9
 -->
 (S1 ^operator O1985 = 0.6170271815281626)
Retracting rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O1985 = 0.3829290045611482)
=>WM: (13964: S1 ^operator O1988 +)
=>WM: (13963: S1 ^operator O1987 +)
=>WM: (13962: I3 ^dir U)
=>WM: (13961: O1988 ^name predict-no)
=>WM: (13960: O1987 ^name predict-yes)
=>WM: (13959: R997 ^value 1)
=>WM: (13958: R1 ^reward R997)
<=WM: (13949: S1 ^operator O1985 +)
<=WM: (13951: S1 ^operator O1985)
<=WM: (13950: S1 ^operator O1986 +)
<=WM: (13948: I3 ^dir R)
<=WM: (13944: R1 ^reward R996)
<=WM: (13947: O1986 ^name predict-no)
<=WM: (13946: O1985 ^name predict-yes)
<=WM: (13945: R996 ^value 1)

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing prefer*rvt*predict-yes*H0
 -->
Firing rl*prefer*rvt*predict-yes*H0*5
 -->
 (S1 ^operator O1987 = 0.)
Firing prefer*rvt*predict-no*H0
 -->
Firing rl*prefer*rvt*predict-no*H0*6
 -->
 (S1 ^operator O1988 = 0.9999999999999999)
 inner elaboration loop at bottom goal.
Retracting rl*prefer*rvt*predict-no*H0*6
 -->
 (S1 ^operator O1986 = 0.9999999999999999)
Retracting rl*prefer*rvt*predict-yes*H0*5
 -->
 (S1 ^operator O1985 = 0.)

--- END Proposal Phase ---

--- Decision Phase ---
RL update rl*prefer*rvt*predict-yes*H0*3 0.673123 -0.290194 0.382929 -> 0.673129 -0.290194 0.382936(R,m,v=1,0.960526,0.0381666)
RL update rl*prefer*rvt*predict-yes*H0*3*H1*9 0.326837 0.29019 0.617027 -> 0.326843 0.290191 0.617034(R,m,v=1,1,0)
=>WM: (13965: S1 ^operator O1988)

   994:    O: O1988 (predict-no)
--- END Decision Phase ---

--- Application Phase ---
	--- Firing Productions (PE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing apply*operator
 -->
 (I3 ^predict-no N994 +  :O )
Firing apply*operator*complete
 -->
 (I3 ^predict-yes N993 -  :O )
 inner elaboration loop at bottom goal.
	--- Change Working Memory (PE) ---
=>WM: (13966: I3 ^predict-no N994)
<=WM: (13953: N993 ^status complete)
<=WM: (13952: I3 ^predict-yes N993)
	--- Firing Productions (IE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing monitor*world
 -->

I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
	--- Change Working Memory (IE) ---

--- END Application Phase ---
--- Output Phase ---
ENV: Agent did: predict-no for direction U in state State-B
In  State-B moving U
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isU
--- END Output Phase ---
/|\--- Input Phase --- 
=>WM: (13970: I2 ^dir U)
=>WM: (13969: I2 ^reward 1)
=>WM: (13968: I2 ^see 0)
=>WM: (13967: N994 ^status complete)
<=WM: (13956: I2 ^dir U)
<=WM: (13955: I2 ^reward 1)
<=WM: (13954: I2 ^see 1)
=>WM: (13971: I2 ^level-1 R1-root)
<=WM: (13957: I2 ^level-1 R1-root)

--- END Input Phase --- 

--- Proposal Phase ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing elaborate*copy-see-to-output-link
 -->
 (I3 ^see 0 +)
Firing elaborate*reward*based*on*reward
 -->
 (R998 ^value 1 +)
 (R1 ^reward R998 +)
Firing propose*predict-yes
 -->
 (O1989 ^name predict-yes +)
 (S1 ^operator O1989 +)
Firing propose*predict-no
 -->
 (O1990 ^name predict-no +)
 (S1 ^operator O1990 +)
Firing rl*prefer*rvt*predict-no*H0*6
 -->
 (S1 ^operator O1988 = 0.9999999999999999)
Firing rl*prefer*rvt*predict-yes*H0*5
 -->
 (S1 ^operator O1987 = 0.)
Firing prefer*rvt*predict-yes*H0
 -->
Firing prefer*rvt*predict-no*H0
 -->
Firing elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir U +)
 inner elaboration loop at bottom goal.
Retracting elaborate*copy-see-to-output-link
 -->
 (I3 ^see 1 +)
Retracting propose*predict-no
 -->
 (O1988 ^name predict-no +)
 (S1 ^operator O1988 +)
Retracting propose*predict-yes
 -->
 (O1987 ^name predict-yes +)
 (S1 ^operator O1987 +)
Retracting elaborate*reward*based*on*reward
 -->
 (R997 ^value 1 +)
 (R1 ^reward R997 +)
Retracting elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir U +)
Retracting rl*prefer*rvt*predict-no*H0*6
 -->
 (S1 ^operator O1988 = 0.9999999999999999)
Retracting rl*prefer*rvt*predict-yes*H0*5
 -->
 (S1 ^operator O1987 = 0.)
=>WM: (13978: S1 ^operator O1990 +)
=>WM: (13977: S1 ^operator O1989 +)
=>WM: (13976: O1990 ^name predict-no)
=>WM: (13975: O1989 ^name predict-yes)
=>WM: (13974: R998 ^value 1)
=>WM: (13973: R1 ^reward R998)
=>WM: (13972: I3 ^see 0)
<=WM: (13963: S1 ^operator O1987 +)
<=WM: (13964: S1 ^operator O1988 +)
<=WM: (13965: S1 ^operator O1988)
<=WM: (13958: R1 ^reward R997)
<=WM: (13943: I3 ^see 1)
<=WM: (13961: O1988 ^name predict-no)
<=WM: (13960: O1987 ^name predict-yes)
<=WM: (13959: R997 ^value 1)

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing prefer*rvt*predict-yes*H0
 -->
Firing rl*prefer*rvt*predict-yes*H0*5
 -->
 (S1 ^operator O1989 = 0.)
Firing prefer*rvt*predict-no*H0
 -->
Firing rl*prefer*rvt*predict-no*H0*6
 -->
 (S1 ^operator O1990 = 0.9999999999999999)
 inner elaboration loop at bottom goal.
Retracting rl*prefer*rvt*predict-no*H0*6
 -->
 (S1 ^operator O1988 = 0.9999999999999999)
Retracting rl*prefer*rvt*predict-yes*H0*5
 -->
 (S1 ^operator O1987 = 0.)

--- END Proposal Phase ---

--- Decision Phase ---
RL update rl*prefer*rvt*predict-no*H0*6 1 0 1 -> 1 0 1(R,m,v=1,1,0)
=>WM: (13979: S1 ^operator O1990)

   995:    O: O1990 (predict-no)
--- END Decision Phase ---

--- Application Phase ---
	--- Firing Productions (PE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing apply*operator
 -->
 (I3 ^predict-no N995 +  :O )
Firing apply*operator*complete
 -->
 (I3 ^predict-no N994 -  :O )
 inner elaboration loop at bottom goal.
	--- Change Working Memory (PE) ---
=>WM: (13980: I3 ^predict-no N995)
<=WM: (13967: N994 ^status complete)
<=WM: (13966: I3 ^predict-no N994)
	--- Firing Productions (IE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing monitor*world
 -->

I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
	--- Change Working Memory (IE) ---

--- END Application Phase ---
--- Output Phase ---
ENV: Agent did: predict-no for direction U in state State-B
In  State-B moving U
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isL
--- END Output Phase ---
-/--- Input Phase --- 
=>WM: (13984: I2 ^dir L)
=>WM: (13983: I2 ^reward 1)
=>WM: (13982: I2 ^see 0)
=>WM: (13981: N995 ^status complete)
<=WM: (13970: I2 ^dir U)
<=WM: (13969: I2 ^reward 1)
<=WM: (13968: I2 ^see 0)
=>WM: (13985: I2 ^level-1 R1-root)
<=WM: (13971: I2 ^level-1 R1-root)

--- END Input Phase --- 

--- Proposal Phase ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing rl*prefer*rvt*predict-yes*H0*1*H1*22
 -->
 (S1 ^operator O1989 = 0.4768774843644236)
Firing rl*prefer*rvt*predict-no*H0*2*H1*10
 -->
 (S1 ^operator O1990 = -0.01194930198035649)
Firing prefer*rvt*predict-no*H0*2*H1
 -->
Firing prefer*rvt*predict-yes*H0*1*H1
 -->
Firing elaborate*copy-see-to-output-link
 -->
 (I3 ^see 0 +)
Firing elaborate*reward*based*on*reward
 -->
 (R999 ^value 1 +)
 (R1 ^reward R999 +)
Firing propose*predict-yes
 -->
 (O1991 ^name predict-yes +)
 (S1 ^operator O1991 +)
Firing propose*predict-no
 -->
 (O1992 ^name predict-no +)
 (S1 ^operator O1992 +)
Firing rl*prefer*rvt*predict-no*H0*2
 -->
 (S1 ^operator O1990 = 0.2550133828092577)
Firing rl*prefer*rvt*predict-yes*H0*1
 -->
 (S1 ^operator O1989 = 0.5231195854047579)
Firing prefer*rvt*predict-yes*H0
 -->
Firing prefer*rvt*predict-no*H0
 -->
Firing elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir L +)
 inner elaboration loop at bottom goal.
Retracting elaborate*copy-see-to-output-link
 -->
 (I3 ^see 0 +)
Retracting propose*predict-no
 -->
 (O1990 ^name predict-no +)
 (S1 ^operator O1990 +)
Retracting propose*predict-yes
 -->
 (O1989 ^name predict-yes +)
 (S1 ^operator O1989 +)
Retracting elaborate*reward*based*on*reward
 -->
 (R998 ^value 1 +)
 (R1 ^reward R998 +)
Retracting elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir U +)
Retracting rl*prefer*rvt*predict-no*H0*6
 -->
 (S1 ^operator O1990 = 0.9999999999999999)
Retracting rl*prefer*rvt*predict-yes*H0*5
 -->
 (S1 ^operator O1989 = 0.)
=>WM: (13992: S1 ^operator O1992 +)
=>WM: (13991: S1 ^operator O1991 +)
=>WM: (13990: I3 ^dir L)
=>WM: (13989: O1992 ^name predict-no)
=>WM: (13988: O1991 ^name predict-yes)
=>WM: (13987: R999 ^value 1)
=>WM: (13986: R1 ^reward R999)
<=WM: (13977: S1 ^operator O1989 +)
<=WM: (13978: S1 ^operator O1990 +)
<=WM: (13979: S1 ^operator O1990)
<=WM: (13962: I3 ^dir U)
<=WM: (13973: R1 ^reward R998)
<=WM: (13976: O1990 ^name predict-no)
<=WM: (13975: O1989 ^name predict-yes)
<=WM: (13974: R998 ^value 1)

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing prefer*rvt*predict-yes*H0
 -->
Firing rl*prefer*rvt*predict-yes*H0*1*H1*22
 -->
 (S1 ^operator O1991 = 0.4768774843644236)
Firing rl*prefer*rvt*predict-yes*H0*1
 -->
 (S1 ^operator O1991 = 0.5231195854047579)
Firing prefer*rvt*predict-yes*H0*1*H1
 -->
Firing prefer*rvt*predict-no*H0
 -->
Firing rl*prefer*rvt*predict-no*H0*2*H1*10
 -->
 (S1 ^operator O1992 = -0.01194930198035649)
Firing rl*prefer*rvt*predict-no*H0*2
 -->
 (S1 ^operator O1992 = 0.2550133828092577)
Firing prefer*rvt*predict-no*H0*2*H1
 -->
 inner elaboration loop at bottom goal.
Retracting rl*prefer*rvt*predict-no*H0*2
 -->
 (S1 ^operator O1990 = 0.2550133828092577)
Retracting rl*prefer*rvt*predict-no*H0*2*H1*10
 -->
 (S1 ^operator O1990 = -0.01194930198035649)
Retracting rl*prefer*rvt*predict-yes*H0*1
 -->
 (S1 ^operator O1989 = 0.5231195854047579)
Retracting rl*prefer*rvt*predict-yes*H0*1*H1*22
 -->
 (S1 ^operator O1989 = 0.4768774843644236)

--- END Proposal Phase ---

--- Decision Phase ---
RL update rl*prefer*rvt*predict-no*H0*6 1 0 1 -> 1 0 1(R,m,v=1,1,0)
=>WM: (13993: S1 ^operator O1991)

   996:    O: O1991 (predict-yes)
--- END Decision Phase ---

--- Application Phase ---
	--- Firing Productions (PE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing apply*operator
 -->
 (I3 ^predict-yes N996 +  :O )
Firing apply*operator*complete
 -->
 (I3 ^predict-no N995 -  :O )
 inner elaboration loop at bottom goal.
	--- Change Working Memory (PE) ---
=>WM: (13994: I3 ^predict-yes N996)
<=WM: (13981: N995 ^status complete)
<=WM: (13980: I3 ^predict-no N995)
	--- Firing Productions (IE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing monitor*world
 -->

I see 1 and I'm going to do: predict-yes inner elaboration loop at bottom goal.
	--- Change Working Memory (IE) ---

--- END Application Phase ---
--- Output Phase ---
ENV: Agent did: predict-yes for direction L in state State-B
In  State-B moving L
ENV: (next state, see, prediction correct?) = (State-A, 1, True)
predict error 0
dir: dir isU
--- END Output Phase ---
|\--- Input Phase --- 
=>WM: (13998: I2 ^dir U)
=>WM: (13997: I2 ^reward 1)
=>WM: (13996: I2 ^see 1)
=>WM: (13995: N996 ^status complete)
<=WM: (13984: I2 ^dir L)
<=WM: (13983: I2 ^reward 1)
<=WM: (13982: I2 ^see 0)
=>WM: (13999: I2 ^level-1 L1-root)
<=WM: (13985: I2 ^level-1 R1-root)

--- END Input Phase --- 

--- Proposal Phase ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing elaborate*copy-see-to-output-link
 -->
 (I3 ^see 1 +)
Firing elaborate*reward*based*on*reward
 -->
 (R1000 ^value 1 +)
 (R1 ^reward R1000 +)
Firing propose*predict-yes
 -->
 (O1993 ^name predict-yes +)
 (S1 ^operator O1993 +)
Firing propose*predict-no
 -->
 (O1994 ^name predict-no +)
 (S1 ^operator O1994 +)
Firing rl*prefer*rvt*predict-no*H0*6
 -->
 (S1 ^operator O1992 = 0.9999999999999999)
Firing rl*prefer*rvt*predict-yes*H0*5
 -->
 (S1 ^operator O1991 = 0.)
Firing prefer*rvt*predict-yes*H0
 -->
Firing prefer*rvt*predict-no*H0
 -->
Firing elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir U +)
 inner elaboration loop at bottom goal.
Retracting elaborate*copy-see-to-output-link
 -->
 (I3 ^see 0 +)
Retracting propose*predict-no
 -->
 (O1992 ^name predict-no +)
 (S1 ^operator O1992 +)
Retracting propose*predict-yes
 -->
 (O1991 ^name predict-yes +)
 (S1 ^operator O1991 +)
Retracting elaborate*reward*based*on*reward
 -->
 (R999 ^value 1 +)
 (R1 ^reward R999 +)
Retracting elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir L +)
Retracting rl*prefer*rvt*predict-no*H0*2
 -->
 (S1 ^operator O1992 = 0.2550133828092577)
Retracting rl*prefer*rvt*predict-no*H0*2*H1*10
 -->
 (S1 ^operator O1992 = -0.01194930198035649)
Retracting rl*prefer*rvt*predict-yes*H0*1
 -->
 (S1 ^operator O1991 = 0.5231195854047579)
Retracting rl*prefer*rvt*predict-yes*H0*1*H1*22
 -->
 (S1 ^operator O1991 = 0.4768774843644236)
=>WM: (14007: S1 ^operator O1994 +)
=>WM: (14006: S1 ^operator O1993 +)
=>WM: (14005: I3 ^dir U)
=>WM: (14004: O1994 ^name predict-no)
=>WM: (14003: O1993 ^name predict-yes)
=>WM: (14002: R1000 ^value 1)
=>WM: (14001: R1 ^reward R1000)
=>WM: (14000: I3 ^see 1)
<=WM: (13991: S1 ^operator O1991 +)
<=WM: (13993: S1 ^operator O1991)
<=WM: (13992: S1 ^operator O1992 +)
<=WM: (13990: I3 ^dir L)
<=WM: (13986: R1 ^reward R999)
<=WM: (13972: I3 ^see 0)
<=WM: (13989: O1992 ^name predict-no)
<=WM: (13988: O1991 ^name predict-yes)
<=WM: (13987: R999 ^value 1)

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing prefer*rvt*predict-yes*H0
 -->
Firing rl*prefer*rvt*predict-yes*H0*5
 -->
 (S1 ^operator O1993 = 0.)
Firing prefer*rvt*predict-no*H0
 -->
Firing rl*prefer*rvt*predict-no*H0*6
 -->
 (S1 ^operator O1994 = 0.9999999999999999)
 inner elaboration loop at bottom goal.
Retracting rl*prefer*rvt*predict-no*H0*6
 -->
 (S1 ^operator O1992 = 0.9999999999999999)
Retracting rl*prefer*rvt*predict-yes*H0*5
 -->
 (S1 ^operator O1991 = 0.)

--- END Proposal Phase ---

--- Decision Phase ---
RL update rl*prefer*rvt*predict-yes*H0*1 0.727959 -0.20484 0.52312 -> 0.72796 -0.20484 0.52312(R,m,v=1,0.978873,0.0208271)
RL update rl*prefer*rvt*predict-yes*H0*1*H1*22 0.272037 0.204841 0.476877 -> 0.272037 0.204841 0.476878(R,m,v=1,1,0)
=>WM: (14008: S1 ^operator O1994)

   997:    O: O1994 (predict-no)
--- END Decision Phase ---

--- Application Phase ---
	--- Firing Productions (PE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing apply*operator
 -->
 (I3 ^predict-no N997 +  :O )
Firing apply*operator*complete
 -->
 (I3 ^predict-yes N996 -  :O )
 inner elaboration loop at bottom goal.
	--- Change Working Memory (PE) ---
=>WM: (14009: I3 ^predict-no N997)
<=WM: (13995: N996 ^status complete)
<=WM: (13994: I3 ^predict-yes N996)
	--- Firing Productions (IE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing monitor*world
 -->

I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
	--- Change Working Memory (IE) ---

--- END Application Phase ---
--- Output Phase ---
ENV: Agent did: predict-no for direction U in state State-A
In  State-A moving U
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isU
--- END Output Phase ---
-/|--- Input Phase --- 
=>WM: (14013: I2 ^dir U)
=>WM: (14012: I2 ^reward 1)
=>WM: (14011: I2 ^see 0)
=>WM: (14010: N997 ^status complete)
<=WM: (13998: I2 ^dir U)
<=WM: (13997: I2 ^reward 1)
<=WM: (13996: I2 ^see 1)
=>WM: (14014: I2 ^level-1 L1-root)
<=WM: (13999: I2 ^level-1 L1-root)

--- END Input Phase --- 

--- Proposal Phase ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing elaborate*copy-see-to-output-link
 -->
 (I3 ^see 0 +)
Firing elaborate*reward*based*on*reward
 -->
 (R1001 ^value 1 +)
 (R1 ^reward R1001 +)
Firing propose*predict-yes
 -->
 (O1995 ^name predict-yes +)
 (S1 ^operator O1995 +)
Firing propose*predict-no
 -->
 (O1996 ^name predict-no +)
 (S1 ^operator O1996 +)
Firing rl*prefer*rvt*predict-no*H0*6
 -->
 (S1 ^operator O1994 = 0.9999999999999999)
Firing rl*prefer*rvt*predict-yes*H0*5
 -->
 (S1 ^operator O1993 = 0.)
Firing prefer*rvt*predict-yes*H0
 -->
Firing prefer*rvt*predict-no*H0
 -->
Firing elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir U +)
 inner elaboration loop at bottom goal.
Retracting elaborate*copy-see-to-output-link
 -->
 (I3 ^see 1 +)
Retracting propose*predict-no
 -->
 (O1994 ^name predict-no +)
 (S1 ^operator O1994 +)
Retracting propose*predict-yes
 -->
 (O1993 ^name predict-yes +)
 (S1 ^operator O1993 +)
Retracting elaborate*reward*based*on*reward
 -->
 (R1000 ^value 1 +)
 (R1 ^reward R1000 +)
Retracting elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir U +)
Retracting rl*prefer*rvt*predict-no*H0*6
 -->
 (S1 ^operator O1994 = 0.9999999999999999)
Retracting rl*prefer*rvt*predict-yes*H0*5
 -->
 (S1 ^operator O1993 = 0.)
=>WM: (14021: S1 ^operator O1996 +)
=>WM: (14020: S1 ^operator O1995 +)
=>WM: (14019: O1996 ^name predict-no)
=>WM: (14018: O1995 ^name predict-yes)
=>WM: (14017: R1001 ^value 1)
=>WM: (14016: R1 ^reward R1001)
=>WM: (14015: I3 ^see 0)
<=WM: (14006: S1 ^operator O1993 +)
<=WM: (14007: S1 ^operator O1994 +)
<=WM: (14008: S1 ^operator O1994)
<=WM: (14001: R1 ^reward R1000)
<=WM: (14000: I3 ^see 1)
<=WM: (14004: O1994 ^name predict-no)
<=WM: (14003: O1993 ^name predict-yes)
<=WM: (14002: R1000 ^value 1)

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing prefer*rvt*predict-yes*H0
 -->
Firing rl*prefer*rvt*predict-yes*H0*5
 -->
 (S1 ^operator O1995 = 0.)
Firing prefer*rvt*predict-no*H0
 -->
Firing rl*prefer*rvt*predict-no*H0*6
 -->
 (S1 ^operator O1996 = 0.9999999999999999)
 inner elaboration loop at bottom goal.
Retracting rl*prefer*rvt*predict-no*H0*6
 -->
 (S1 ^operator O1994 = 0.9999999999999999)
Retracting rl*prefer*rvt*predict-yes*H0*5
 -->
 (S1 ^operator O1993 = 0.)

--- END Proposal Phase ---

--- Decision Phase ---
RL update rl*prefer*rvt*predict-no*H0*6 1 0 1 -> 1 0 1(R,m,v=1,1,0)
=>WM: (14022: S1 ^operator O1996)

   998:    O: O1996 (predict-no)
--- END Decision Phase ---

--- Application Phase ---
	--- Firing Productions (PE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing apply*operator
 -->
 (I3 ^predict-no N998 +  :O )
Firing apply*operator*complete
 -->
 (I3 ^predict-no N997 -  :O )
 inner elaboration loop at bottom goal.
	--- Change Working Memory (PE) ---
=>WM: (14023: I3 ^predict-no N998)
<=WM: (14010: N997 ^status complete)
<=WM: (14009: I3 ^predict-no N997)
	--- Firing Productions (IE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing monitor*world
 -->

I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
	--- Change Working Memory (IE) ---

--- END Application Phase ---
--- Output Phase ---
ENV: Agent did: predict-no for direction U in state State-A
In  State-A moving U
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isL
--- END Output Phase ---
\-/--- Input Phase --- 
=>WM: (14027: I2 ^dir L)
=>WM: (14026: I2 ^reward 1)
=>WM: (14025: I2 ^see 0)
=>WM: (14024: N998 ^status complete)
<=WM: (14013: I2 ^dir U)
<=WM: (14012: I2 ^reward 1)
<=WM: (14011: I2 ^see 0)
=>WM: (14028: I2 ^level-1 L1-root)
<=WM: (14014: I2 ^level-1 L1-root)

--- END Input Phase --- 

--- Proposal Phase ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing rl*prefer*rvt*predict-yes*H0*1*H1*20
 -->
 (S1 ^operator O1995 = 0.1693592933936033)
Firing rl*prefer*rvt*predict-no*H0*2*H1*11
 -->
 (S1 ^operator O1996 = 0.7449864376794202)
Firing prefer*rvt*predict-no*H0*2*H1
 -->
Firing prefer*rvt*predict-yes*H0*1*H1
 -->
Firing elaborate*copy-see-to-output-link
 -->
 (I3 ^see 0 +)
Firing elaborate*reward*based*on*reward
 -->
 (R1002 ^value 1 +)
 (R1 ^reward R1002 +)
Firing propose*predict-yes
 -->
 (O1997 ^name predict-yes +)
 (S1 ^operator O1997 +)
Firing propose*predict-no
 -->
 (O1998 ^name predict-no +)
 (S1 ^operator O1998 +)
Firing rl*prefer*rvt*predict-no*H0*2
 -->
 (S1 ^operator O1996 = 0.2550133828092577)
Firing rl*prefer*rvt*predict-yes*H0*1
 -->
 (S1 ^operator O1995 = 0.5231200249393807)
Firing prefer*rvt*predict-yes*H0
 -->
Firing prefer*rvt*predict-no*H0
 -->
Firing elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir L +)
 inner elaboration loop at bottom goal.
Retracting elaborate*copy-see-to-output-link
 -->
 (I3 ^see 0 +)
Retracting propose*predict-no
 -->
 (O1996 ^name predict-no +)
 (S1 ^operator O1996 +)
Retracting propose*predict-yes
 -->
 (O1995 ^name predict-yes +)
 (S1 ^operator O1995 +)
Retracting elaborate*reward*based*on*reward
 -->
 (R1001 ^value 1 +)
 (R1 ^reward R1001 +)
Retracting elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir U +)
Retracting rl*prefer*rvt*predict-no*H0*6
 -->
 (S1 ^operator O1996 = 0.9999999999999999)
Retracting rl*prefer*rvt*predict-yes*H0*5
 -->
 (S1 ^operator O1995 = 0.)
=>WM: (14035: S1 ^operator O1998 +)
=>WM: (14034: S1 ^operator O1997 +)
=>WM: (14033: I3 ^dir L)
=>WM: (14032: O1998 ^name predict-no)
=>WM: (14031: O1997 ^name predict-yes)
=>WM: (14030: R1002 ^value 1)
=>WM: (14029: R1 ^reward R1002)
<=WM: (14020: S1 ^operator O1995 +)
<=WM: (14021: S1 ^operator O1996 +)
<=WM: (14022: S1 ^operator O1996)
<=WM: (14005: I3 ^dir U)
<=WM: (14016: R1 ^reward R1001)
<=WM: (14019: O1996 ^name predict-no)
<=WM: (14018: O1995 ^name predict-yes)
<=WM: (14017: R1001 ^value 1)

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing prefer*rvt*predict-yes*H0
 -->
Firing rl*prefer*rvt*predict-yes*H0*1*H1*20
 -->
 (S1 ^operator O1997 = 0.1693592933936033)
Firing rl*prefer*rvt*predict-yes*H0*1
 -->
 (S1 ^operator O1997 = 0.5231200249393807)
Firing prefer*rvt*predict-yes*H0*1*H1
 -->
Firing prefer*rvt*predict-no*H0
 -->
Firing rl*prefer*rvt*predict-no*H0*2*H1*11
 -->
 (S1 ^operator O1998 = 0.7449864376794202)
Firing rl*prefer*rvt*predict-no*H0*2
 -->
 (S1 ^operator O1998 = 0.2550133828092577)
Firing prefer*rvt*predict-no*H0*2*H1
 -->
 inner elaboration loop at bottom goal.
Retracting rl*prefer*rvt*predict-no*H0*2
 -->
 (S1 ^operator O1996 = 0.2550133828092577)
Retracting rl*prefer*rvt*predict-no*H0*2*H1*11
 -->
 (S1 ^operator O1996 = 0.7449864376794202)
Retracting rl*prefer*rvt*predict-yes*H0*1
 -->
 (S1 ^operator O1995 = 0.5231200249393807)
Retracting rl*prefer*rvt*predict-yes*H0*1*H1*20
 -->
 (S1 ^operator O1995 = 0.1693592933936033)

--- END Proposal Phase ---

--- Decision Phase ---
RL update rl*prefer*rvt*predict-no*H0*6 1 0 1 -> 1 0 1(R,m,v=1,1,0)
=>WM: (14036: S1 ^operator O1998)

   999:    O: O1998 (predict-no)
--- END Decision Phase ---

--- Application Phase ---
	--- Firing Productions (PE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing apply*operator
 -->
 (I3 ^predict-no N999 +  :O )
Firing apply*operator*complete
 -->
 (I3 ^predict-no N998 -  :O )
 inner elaboration loop at bottom goal.
	--- Change Working Memory (PE) ---
=>WM: (14037: I3 ^predict-no N999)
<=WM: (14024: N998 ^status complete)
<=WM: (14023: I3 ^predict-no N998)
	--- Firing Productions (IE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing monitor*world
 -->

I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
	--- Change Working Memory (IE) ---

--- END Application Phase ---
--- Output Phase ---
ENV: Agent did: predict-no for direction L in state State-A
In  State-A moving L
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isL
--- END Output Phase ---
|\---- Input Phase --- 
=>WM: (14041: I2 ^dir L)
=>WM: (14040: I2 ^reward 1)
=>WM: (14039: I2 ^see 0)
=>WM: (14038: N999 ^status complete)
<=WM: (14027: I2 ^dir L)
<=WM: (14026: I2 ^reward 1)
<=WM: (14025: I2 ^see 0)
=>WM: (14042: I2 ^level-1 L0-root)
<=WM: (14028: I2 ^level-1 L1-root)

--- END Input Phase --- 

--- Proposal Phase ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing rl*prefer*rvt*predict-yes*H0*1*H1*21
 -->
 (S1 ^operator O1997 = 0.3)
Firing rl*prefer*rvt*predict-no*H0*2*H1*12
 -->
 (S1 ^operator O1998 = 0.7449867384410525)
Firing prefer*rvt*predict-no*H0*2*H1
 -->
Firing prefer*rvt*predict-yes*H0*1*H1
 -->
Firing elaborate*copy-see-to-output-link
 -->
 (I3 ^see 0 +)
Firing elaborate*reward*based*on*reward
 -->
 (R1003 ^value 1 +)
 (R1 ^reward R1003 +)
Firing propose*predict-yes
 -->
 (O1999 ^name predict-yes +)
 (S1 ^operator O1999 +)
Firing propose*predict-no
 -->
 (O2000 ^name predict-no +)
 (S1 ^operator O2000 +)
Firing rl*prefer*rvt*predict-no*H0*2
 -->
 (S1 ^operator O1998 = 0.2550133828092577)
Firing rl*prefer*rvt*predict-yes*H0*1
 -->
 (S1 ^operator O1997 = 0.5231200249393807)
Firing prefer*rvt*predict-yes*H0
 -->
Firing prefer*rvt*predict-no*H0
 -->
Firing elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir L +)
 inner elaboration loop at bottom goal.
Retracting elaborate*copy-see-to-output-link
 -->
 (I3 ^see 0 +)
Retracting propose*predict-no
 -->
 (O1998 ^name predict-no +)
 (S1 ^operator O1998 +)
Retracting propose*predict-yes
 -->
 (O1997 ^name predict-yes +)
 (S1 ^operator O1997 +)
Retracting elaborate*reward*based*on*reward
 -->
 (R1002 ^value 1 +)
 (R1 ^reward R1002 +)
Retracting elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir L +)
Retracting rl*prefer*rvt*predict-no*H0*2
 -->
 (S1 ^operator O1998 = 0.2550133828092577)
Retracting rl*prefer*rvt*predict-no*H0*2*H1*11
 -->
 (S1 ^operator O1998 = 0.7449864376794202)
Retracting rl*prefer*rvt*predict-yes*H0*1
 -->
 (S1 ^operator O1997 = 0.5231200249393807)
Retracting rl*prefer*rvt*predict-yes*H0*1*H1*20
 -->
 (S1 ^operator O1997 = 0.1693592933936033)
=>WM: (14048: S1 ^operator O2000 +)
=>WM: (14047: S1 ^operator O1999 +)
=>WM: (14046: O2000 ^name predict-no)
=>WM: (14045: O1999 ^name predict-yes)
=>WM: (14044: R1003 ^value 1)
=>WM: (14043: R1 ^reward R1003)
<=WM: (14034: S1 ^operator O1997 +)
<=WM: (14035: S1 ^operator O1998 +)
<=WM: (14036: S1 ^operator O1998)
<=WM: (14029: R1 ^reward R1002)
<=WM: (14032: O1998 ^name predict-no)
<=WM: (14031: O1997 ^name predict-yes)
<=WM: (14030: R1002 ^value 1)

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing prefer*rvt*predict-yes*H0
 -->
Firing rl*prefer*rvt*predict-yes*H0*1
 -->
 (S1 ^operator O1999 = 0.5231200249393807)
Firing prefer*rvt*predict-yes*H0*1*H1
 -->
Firing rl*prefer*rvt*predict-yes*H0*1*H1*21
 -->
 (S1 ^operator O1999 = 0.3)
Firing prefer*rvt*predict-no*H0
 -->
Firing rl*prefer*rvt*predict-no*H0*2
 -->
 (S1 ^operator O2000 = 0.2550133828092577)
Firing prefer*rvt*predict-no*H0*2*H1
 -->
Firing rl*prefer*rvt*predict-no*H0*2*H1*12
 -->
 (S1 ^operator O2000 = 0.7449867384410525)
 inner elaboration loop at bottom goal.
Retracting rl*prefer*rvt*predict-no*H0*2
 -->
 (S1 ^operator O1998 = 0.2550133828092577)
Retracting rl*prefer*rvt*predict-no*H0*2*H1*12
 -->
 (S1 ^operator O1998 = 0.7449867384410525)
Retracting rl*prefer*rvt*predict-yes*H0*1
 -->
 (S1 ^operator O1997 = 0.5231200249393807)
Retracting rl*prefer*rvt*predict-yes*H0*1*H1*21
 -->
 (S1 ^operator O1997 = 0.3)

--- END Proposal Phase ---

--- Decision Phase ---
RL update rl*prefer*rvt*predict-no*H0*2 0.631495 -0.376482 0.255013 -> 0.631495 -0.376482 0.255013(R,m,v=1,0.917526,0.0760643)
RL update rl*prefer*rvt*predict-no*H0*2*H1*11 0.368505 0.376482 0.744986 -> 0.368505 0.376482 0.744986(R,m,v=1,1,0)
=>WM: (14049: S1 ^operator O2000)

  1000:    O: O2000 (predict-no)
--- END Decision Phase ---

--- Application Phase ---
	--- Firing Productions (PE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing apply*operator
 -->
 (I3 ^predict-no N1000 +  :O )
Firing apply*operator*complete
 -->
 (I3 ^predict-no N999 -  :O )
 inner elaboration loop at bottom goal.
	--- Change Working Memory (PE) ---
=>WM: (14050: I3 ^predict-no N1000)
<=WM: (14038: N999 ^status complete)
<=WM: (14037: I3 ^predict-no N999)
	--- Firing Productions (IE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing monitor*world
 -->

I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
	--- Change Working Memory (IE) ---

--- END Application Phase ---
--- Output Phase ---
ENV: Agent did: predict-no for direction L in state State-A
In  State-A moving L
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isL
--- END Output Phase ---
/|\-/--- Input Phase --- 
=>WM: (14054: I2 ^dir L)
=>WM: (14053: I2 ^reward 1)
=>WM: (14052: I2 ^see 0)
=>WM: (14051: N1000 ^status complete)
<=WM: (14041: I2 ^dir L)
<=WM: (14040: I2 ^reward 1)
<=WM: (14039: I2 ^see 0)
=>WM: (14055: I2 ^level-1 L0-root)
<=WM: (14042: I2 ^level-1 L0-root)

--- END Input Phase --- 

--- Proposal Phase ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing rl*prefer*rvt*predict-yes*H0*1*H1*21
 -->
 (S1 ^operator O1999 = 0.3)
Firing rl*prefer*rvt*predict-no*H0*2*H1*12
 -->
 (S1 ^operator O2000 = 0.7449867384410525)
Firing prefer*rvt*predict-no*H0*2*H1
 -->
Firing prefer*rvt*predict-yes*H0*1*H1
 -->
Firing elaborate*copy-see-to-output-link
 -->
 (I3 ^see 0 +)
Firing elaborate*reward*based*on*reward
 -->
 (R1004 ^value 1 +)
 (R1 ^reward R1004 +)
Firing propose*predict-yes
 -->
 (O2001 ^name predict-yes +)
 (S1 ^operator O2001 +)
Firing propose*predict-no
 -->
 (O2002 ^name predict-no +)
 (S1 ^operator O2002 +)
Firing rl*prefer*rvt*predict-no*H0*2
 -->
 (S1 ^operator O2000 = 0.255013409735956)
Firing rl*prefer*rvt*predict-yes*H0*1
 -->
 (S1 ^operator O1999 = 0.5231200249393807)
Firing prefer*rvt*predict-yes*H0
 -->
Firing prefer*rvt*predict-no*H0
 -->
Firing elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir L +)
 inner elaboration loop at bottom goal.
Retracting elaborate*copy-see-to-output-link
 -->
 (I3 ^see 0 +)
Retracting propose*predict-no
 -->
 (O2000 ^name predict-no +)
 (S1 ^operator O2000 +)
Retracting propose*predict-yes
 -->
 (O1999 ^name predict-yes +)
 (S1 ^operator O1999 +)
Retracting elaborate*reward*based*on*reward
 -->
 (R1003 ^value 1 +)
 (R1 ^reward R1003 +)
Retracting elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir L +)
Retracting rl*prefer*rvt*predict-no*H0*2*H1*12
 -->
 (S1 ^operator O2000 = 0.7449867384410525)
Retracting rl*prefer*rvt*predict-no*H0*2
 -->
 (S1 ^operator O2000 = 0.255013409735956)
Retracting rl*prefer*rvt*predict-yes*H0*1*H1*21
 -->
 (S1 ^operator O1999 = 0.3)
Retracting rl*prefer*rvt*predict-yes*H0*1
 -->
 (S1 ^operator O1999 = 0.5231200249393807)
=>WM: (14061: S1 ^operator O2002 +)
=>WM: (14060: S1 ^operator O2001 +)
=>WM: (14059: O2002 ^name predict-no)
=>WM: (14058: O2001 ^name predict-yes)
=>WM: (14057: R1004 ^value 1)
=>WM: (14056: R1 ^reward R1004)
<=WM: (14047: S1 ^operator O1999 +)
<=WM: (14048: S1 ^operator O2000 +)
<=WM: (14049: S1 ^operator O2000)
<=WM: (14043: R1 ^reward R1003)
<=WM: (14046: O2000 ^name predict-no)
<=WM: (14045: O1999 ^name predict-yes)
<=WM: (14044: R1003 ^value 1)

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing prefer*rvt*predict-yes*H0
 -->
Firing rl*prefer*rvt*predict-yes*H0*1
 -->
 (S1 ^operator O2001 = 0.5231200249393807)
Firing prefer*rvt*predict-yes*H0*1*H1
 -->
Firing rl*prefer*rvt*predict-yes*H0*1*H1*21
 -->
 (S1 ^operator O2001 = 0.3)
Firing prefer*rvt*predict-no*H0
 -->
Firing rl*prefer*rvt*predict-no*H0*2
 -->
 (S1 ^operator O2002 = 0.255013409735956)
Firing prefer*rvt*predict-no*H0*2*H1
 -->
Firing rl*prefer*rvt*predict-no*H0*2*H1*12
 -->
 (S1 ^operator O2002 = 0.7449867384410525)
 inner elaboration loop at bottom goal.
Retracting rl*prefer*rvt*predict-no*H0*2
 -->
 (S1 ^operator O2000 = 0.255013409735956)
Retracting rl*prefer*rvt*predict-no*H0*2*H1*12
 -->
 (S1 ^operator O2000 = 0.7449867384410525)
Retracting rl*prefer*rvt*predict-yes*H0*1
 -->
 (S1 ^operator O1999 = 0.5231200249393807)
Retracting rl*prefer*rvt*predict-yes*H0*1*H1*21
 -->
 (S1 ^operator O1999 = 0.3)

--- END Proposal Phase ---

--- Decision Phase ---
RL update rl*prefer*rvt*predict-no*H0*2 0.631495 -0.376482 0.255013 -> 0.631495 -0.376482 0.255013(R,m,v=1,0.917949,0.0757071)
RL update rl*prefer*rvt*predict-no*H0*2*H1*12 0.368505 0.376482 0.744987 -> 0.368505 0.376482 0.744987(R,m,v=1,1,0)
=>WM: (14062: S1 ^operator O2002)

  1001:    O: O2002 (predict-no)
--- END Decision Phase ---

--- Application Phase ---
	--- Firing Productions (PE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing apply*operator
 -->
 (I3 ^predict-no N1001 +  :O )
Firing apply*operator*complete
 -->
 (I3 ^predict-no N1000 -  :O )
 inner elaboration loop at bottom goal.
	--- Change Working Memory (PE) ---
=>WM: (14063: I3 ^predict-no N1001)
<=WM: (14051: N1000 ^status complete)
<=WM: (14050: I3 ^predict-no N1000)
	--- Firing Productions (IE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing monitor*world
 -->

I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
	--- Change Working Memory (IE) ---

--- END Application Phase ---
--- Output Phase ---
ENV: Agent did: predict-no for direction L in state State-A
In  State-A moving L
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isL
--- END Output Phase ---
|--- Input Phase --- 
=>WM: (14067: I2 ^dir L)
=>WM: (14066: I2 ^reward 1)
=>WM: (14065: I2 ^see 0)
=>WM: (14064: N1001 ^status complete)
<=WM: (14054: I2 ^dir L)
<=WM: (14053: I2 ^reward 1)
<=WM: (14052: I2 ^see 0)
=>WM: (14068: I2 ^level-1 L0-root)
<=WM: (14055: I2 ^level-1 L0-root)

--- END Input Phase --- 

--- Proposal Phase ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing rl*prefer*rvt*predict-yes*H0*1*H1*21
 -->
 (S1 ^operator O2001 = 0.3)
Firing rl*prefer*rvt*predict-no*H0*2*H1*12
 -->
 (S1 ^operator O2002 = 0.7449867162145012)
Firing prefer*rvt*predict-no*H0*2*H1
 -->
Firing prefer*rvt*predict-yes*H0*1*H1
 -->
Firing elaborate*copy-see-to-output-link
 -->
 (I3 ^see 0 +)
Firing elaborate*reward*based*on*reward
 -->
 (R1005 ^value 1 +)
 (R1 ^reward R1005 +)
Firing propose*predict-yes
 -->
 (O2003 ^name predict-yes +)
 (S1 ^operator O2003 +)
Firing propose*predict-no
 -->
 (O2004 ^name predict-no +)
 (S1 ^operator O2004 +)
Firing rl*prefer*rvt*predict-no*H0*2
 -->
 (S1 ^operator O2002 = 0.2550133875094047)
Firing rl*prefer*rvt*predict-yes*H0*1
 -->
 (S1 ^operator O2001 = 0.5231200249393807)
Firing prefer*rvt*predict-yes*H0
 -->
Firing prefer*rvt*predict-no*H0
 -->
Firing elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir L +)
 inner elaboration loop at bottom goal.
Retracting elaborate*copy-see-to-output-link
 -->
 (I3 ^see 0 +)
Retracting propose*predict-no
 -->
 (O2002 ^name predict-no +)
 (S1 ^operator O2002 +)
Retracting propose*predict-yes
 -->
 (O2001 ^name predict-yes +)
 (S1 ^operator O2001 +)
Retracting elaborate*reward*based*on*reward
 -->
 (R1004 ^value 1 +)
 (R1 ^reward R1004 +)
Retracting elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir L +)
Retracting rl*prefer*rvt*predict-no*H0*2*H1*12
 -->
 (S1 ^operator O2002 = 0.7449867162145012)
Retracting rl*prefer*rvt*predict-no*H0*2
 -->
 (S1 ^operator O2002 = 0.2550133875094047)
Retracting rl*prefer*rvt*predict-yes*H0*1*H1*21
 -->
 (S1 ^operator O2001 = 0.3)
Retracting rl*prefer*rvt*predict-yes*H0*1
 -->
 (S1 ^operator O2001 = 0.5231200249393807)
=>WM: (14074: S1 ^operator O2004 +)
=>WM: (14073: S1 ^operator O2003 +)
=>WM: (14072: O2004 ^name predict-no)
=>WM: (14071: O2003 ^name predict-yes)
=>WM: (14070: R1005 ^value 1)
=>WM: (14069: R1 ^reward R1005)
<=WM: (14060: S1 ^operator O2001 +)
<=WM: (14061: S1 ^operator O2002 +)
<=WM: (14062: S1 ^operator O2002)
<=WM: (14056: R1 ^reward R1004)
<=WM: (14059: O2002 ^name predict-no)
<=WM: (14058: O2001 ^name predict-yes)
<=WM: (14057: R1004 ^value 1)

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing prefer*rvt*predict-yes*H0
 -->
Firing rl*prefer*rvt*predict-yes*H0*1
 -->
 (S1 ^operator O2003 = 0.5231200249393807)
Firing prefer*rvt*predict-yes*H0*1*H1
 -->
Firing rl*prefer*rvt*predict-yes*H0*1*H1*21
 -->
 (S1 ^operator O2003 = 0.3)
Firing prefer*rvt*predict-no*H0
 -->
Firing rl*prefer*rvt*predict-no*H0*2
 -->
 (S1 ^operator O2004 = 0.2550133875094047)
Firing prefer*rvt*predict-no*H0*2*H1
 -->
Firing rl*prefer*rvt*predict-no*H0*2*H1*12
 -->
 (S1 ^operator O2004 = 0.7449867162145012)
 inner elaboration loop at bottom goal.
Retracting rl*prefer*rvt*predict-no*H0*2
 -->
 (S1 ^operator O2002 = 0.2550133875094047)
Retracting rl*prefer*rvt*predict-no*H0*2*H1*12
 -->
 (S1 ^operator O2002 = 0.7449867162145012)
Retracting rl*prefer*rvt*predict-yes*H0*1
 -->
 (S1 ^operator O2001 = 0.5231200249393807)
Retracting rl*prefer*rvt*predict-yes*H0*1*H1*21
 -->
 (S1 ^operator O2001 = 0.3)

--- END Proposal Phase ---

--- Decision Phase ---
RL update rl*prefer*rvt*predict-no*H0*2 0.631495 -0.376482 0.255013 -> 0.631495 -0.376482 0.255013(R,m,v=1,0.918367,0.0753532)
RL update rl*prefer*rvt*predict-no*H0*2*H1*12 0.368505 0.376482 0.744987 -> 0.368505 0.376482 0.744987(R,m,v=1,1,0)
=>WM: (14075: S1 ^operator O2004)

  1002:    O: O2004 (predict-no)
--- END Decision Phase ---

--- Application Phase ---
	--- Firing Productions (PE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing apply*operator
 -->
 (I3 ^predict-no N1002 +  :O )
Firing apply*operator*complete
 -->
 (I3 ^predict-no N1001 -  :O )
 inner elaboration loop at bottom goal.
	--- Change Working Memory (PE) ---
=>WM: (14076: I3 ^predict-no N1002)
<=WM: (14064: N1001 ^status complete)
<=WM: (14063: I3 ^predict-no N1001)
	--- Firing Productions (IE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing monitor*world
 -->

I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
	--- Change Working Memory (IE) ---

--- END Application Phase ---
--- Output Phase ---
ENV: Agent did: predict-no for direction L in state State-A
In  State-A moving L
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isU
--- END Output Phase ---
\---- Input Phase --- 
=>WM: (14080: I2 ^dir U)
=>WM: (14079: I2 ^reward 1)
=>WM: (14078: I2 ^see 0)
=>WM: (14077: N1002 ^status complete)
<=WM: (14067: I2 ^dir L)
<=WM: (14066: I2 ^reward 1)
<=WM: (14065: I2 ^see 0)
=>WM: (14081: I2 ^level-1 L0-root)
<=WM: (14068: I2 ^level-1 L0-root)

--- END Input Phase --- 

--- Proposal Phase ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing elaborate*copy-see-to-output-link
 -->
 (I3 ^see 0 +)
Firing elaborate*reward*based*on*reward
 -->
 (R1006 ^value 1 +)
 (R1 ^reward R1006 +)
Firing propose*predict-yes
 -->
 (O2005 ^name predict-yes +)
 (S1 ^operator O2005 +)
Firing propose*predict-no
 -->
 (O2006 ^name predict-no +)
 (S1 ^operator O2006 +)
Firing rl*prefer*rvt*predict-no*H0*6
 -->
 (S1 ^operator O2004 = 0.9999999999999999)
Firing rl*prefer*rvt*predict-yes*H0*5
 -->
 (S1 ^operator O2003 = 0.)
Firing prefer*rvt*predict-yes*H0
 -->
Firing prefer*rvt*predict-no*H0
 -->
Firing elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir U +)
 inner elaboration loop at bottom goal.
Retracting elaborate*copy-see-to-output-link
 -->
 (I3 ^see 0 +)
Retracting propose*predict-no
 -->
 (O2004 ^name predict-no +)
 (S1 ^operator O2004 +)
Retracting propose*predict-yes
 -->
 (O2003 ^name predict-yes +)
 (S1 ^operator O2003 +)
Retracting elaborate*reward*based*on*reward
 -->
 (R1005 ^value 1 +)
 (R1 ^reward R1005 +)
Retracting elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir L +)
Retracting rl*prefer*rvt*predict-no*H0*2*H1*12
 -->
 (S1 ^operator O2004 = 0.7449867006559153)
Retracting rl*prefer*rvt*predict-no*H0*2
 -->
 (S1 ^operator O2004 = 0.2550133719508188)
Retracting rl*prefer*rvt*predict-yes*H0*1*H1*21
 -->
 (S1 ^operator O2003 = 0.3)
Retracting rl*prefer*rvt*predict-yes*H0*1
 -->
 (S1 ^operator O2003 = 0.5231200249393807)
=>WM: (14088: S1 ^operator O2006 +)
=>WM: (14087: S1 ^operator O2005 +)
=>WM: (14086: I3 ^dir U)
=>WM: (14085: O2006 ^name predict-no)
=>WM: (14084: O2005 ^name predict-yes)
=>WM: (14083: R1006 ^value 1)
=>WM: (14082: R1 ^reward R1006)
<=WM: (14073: S1 ^operator O2003 +)
<=WM: (14074: S1 ^operator O2004 +)
<=WM: (14075: S1 ^operator O2004)
<=WM: (14033: I3 ^dir L)
<=WM: (14069: R1 ^reward R1005)
<=WM: (14072: O2004 ^name predict-no)
<=WM: (14071: O2003 ^name predict-yes)
<=WM: (14070: R1005 ^value 1)

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing prefer*rvt*predict-yes*H0
 -->
Firing rl*prefer*rvt*predict-yes*H0*5
 -->
 (S1 ^operator O2005 = 0.)
Firing prefer*rvt*predict-no*H0
 -->
Firing rl*prefer*rvt*predict-no*H0*6
 -->
 (S1 ^operator O2006 = 0.9999999999999999)
 inner elaboration loop at bottom goal.
Retracting rl*prefer*rvt*predict-no*H0*6
 -->
 (S1 ^operator O2004 = 0.9999999999999999)
Retracting rl*prefer*rvt*predict-yes*H0*5
 -->
 (S1 ^operator O2003 = 0.)

--- END Proposal Phase ---

--- Decision Phase ---
RL update rl*prefer*rvt*predict-no*H0*2 0.631495 -0.376482 0.255013 -> 0.631495 -0.376482 0.255013(R,m,v=1,0.918782,0.0750026)
RL update rl*prefer*rvt*predict-no*H0*2*H1*12 0.368505 0.376482 0.744987 -> 0.368505 0.376482 0.744987(R,m,v=1,1,0)
=>WM: (14089: S1 ^operator O2006)

  1003:    O: O2006 (predict-no)
--- END Decision Phase ---

--- Application Phase ---
	--- Firing Productions (PE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing apply*operator
 -->
 (I3 ^predict-no N1003 +  :O )
Firing apply*operator*complete
 -->
 (I3 ^predict-no N1002 -  :O )
 inner elaboration loop at bottom goal.
	--- Change Working Memory (PE) ---
=>WM: (14090: I3 ^predict-no N1003)
<=WM: (14077: N1002 ^status complete)
<=WM: (14076: I3 ^predict-no N1002)
	--- Firing Productions (IE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing monitor*world
 -->

I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
	--- Change Working Memory (IE) ---

--- END Application Phase ---
--- Output Phase ---
ENV: Agent did: predict-no for direction U in state State-A
In  State-A moving U
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isR
--- END Output Phase ---
/|\--- Input Phase --- 
=>WM: (14094: I2 ^dir R)
=>WM: (14093: I2 ^reward 1)
=>WM: (14092: I2 ^see 0)
=>WM: (14091: N1003 ^status complete)
<=WM: (14080: I2 ^dir U)
<=WM: (14079: I2 ^reward 1)
<=WM: (14078: I2 ^see 0)
=>WM: (14095: I2 ^level-1 L0-root)
<=WM: (14081: I2 ^level-1 L0-root)

--- END Input Phase --- 

--- Proposal Phase ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing rl*prefer*rvt*predict-yes*H0*3*H1*14
 -->
 (S1 ^operator O2005 = 0.617076227543635)
Firing rl*prefer*rvt*predict-no*H0*4*H1*13
 -->
 (S1 ^operator O2006 = 0.4910065094545203)
Firing prefer*rvt*predict-no*H0*4*H1
 -->
Firing prefer*rvt*predict-yes*H0*3*H1
 -->
Firing elaborate*copy-see-to-output-link
 -->
 (I3 ^see 0 +)
Firing elaborate*reward*based*on*reward
 -->
 (R1007 ^value 1 +)
 (R1 ^reward R1007 +)
Firing propose*predict-yes
 -->
 (O2007 ^name predict-yes +)
 (S1 ^operator O2007 +)
Firing propose*predict-no
 -->
 (O2008 ^name predict-no +)
 (S1 ^operator O2008 +)
Firing rl*prefer*rvt*predict-no*H0*4
 -->
 (S1 ^operator O2006 = 0.1269768790760836)
Firing rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O2005 = 0.3829355766477516)
Firing prefer*rvt*predict-yes*H0
 -->
Firing prefer*rvt*predict-no*H0
 -->
Firing elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir R +)
 inner elaboration loop at bottom goal.
Retracting elaborate*copy-see-to-output-link
 -->
 (I3 ^see 0 +)
Retracting propose*predict-no
 -->
 (O2006 ^name predict-no +)
 (S1 ^operator O2006 +)
Retracting propose*predict-yes
 -->
 (O2005 ^name predict-yes +)
 (S1 ^operator O2005 +)
Retracting elaborate*reward*based*on*reward
 -->
 (R1006 ^value 1 +)
 (R1 ^reward R1006 +)
Retracting elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir U +)
Retracting rl*prefer*rvt*predict-no*H0*6
 -->
 (S1 ^operator O2006 = 0.9999999999999999)
Retracting rl*prefer*rvt*predict-yes*H0*5
 -->
 (S1 ^operator O2005 = 0.)
=>WM: (14102: S1 ^operator O2008 +)
=>WM: (14101: S1 ^operator O2007 +)
=>WM: (14100: I3 ^dir R)
=>WM: (14099: O2008 ^name predict-no)
=>WM: (14098: O2007 ^name predict-yes)
=>WM: (14097: R1007 ^value 1)
=>WM: (14096: R1 ^reward R1007)
<=WM: (14087: S1 ^operator O2005 +)
<=WM: (14088: S1 ^operator O2006 +)
<=WM: (14089: S1 ^operator O2006)
<=WM: (14086: I3 ^dir U)
<=WM: (14082: R1 ^reward R1006)
<=WM: (14085: O2006 ^name predict-no)
<=WM: (14084: O2005 ^name predict-yes)
<=WM: (14083: R1006 ^value 1)

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing prefer*rvt*predict-yes*H0
 -->
Firing rl*prefer*rvt*predict-yes*H0*3*H1*14
 -->
 (S1 ^operator O2007 = 0.617076227543635)
Firing rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O2007 = 0.3829355766477516)
Firing prefer*rvt*predict-yes*H0*3*H1
 -->
Firing prefer*rvt*predict-no*H0
 -->
Firing rl*prefer*rvt*predict-no*H0*4*H1*13
 -->
 (S1 ^operator O2008 = 0.4910065094545203)
Firing rl*prefer*rvt*predict-no*H0*4
 -->
 (S1 ^operator O2008 = 0.1269768790760836)
Firing prefer*rvt*predict-no*H0*4*H1
 -->
 inner elaboration loop at bottom goal.
Retracting rl*prefer*rvt*predict-no*H0*4
 -->
 (S1 ^operator O2006 = 0.1269768790760836)
Retracting rl*prefer*rvt*predict-no*H0*4*H1*13
 -->
 (S1 ^operator O2006 = 0.4910065094545203)
Retracting rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O2005 = 0.3829355766477516)
Retracting rl*prefer*rvt*predict-yes*H0*3*H1*14
 -->
 (S1 ^operator O2005 = 0.617076227543635)

--- END Proposal Phase ---

--- Decision Phase ---
RL update rl*prefer*rvt*predict-no*H0*6 1 0 1 -> 1 0 1(R,m,v=1,1,0)
=>WM: (14103: S1 ^operator O2007)

  1004:    O: O2007 (predict-yes)
--- END Decision Phase ---

--- Application Phase ---
	--- Firing Productions (PE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing apply*operator
 -->
 (I3 ^predict-yes N1004 +  :O )
Firing apply*operator*complete
 -->
 (I3 ^predict-no N1003 -  :O )
 inner elaboration loop at bottom goal.
	--- Change Working Memory (PE) ---
=>WM: (14104: I3 ^predict-yes N1004)
<=WM: (14091: N1003 ^status complete)
<=WM: (14090: I3 ^predict-no N1003)
	--- Firing Productions (IE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing monitor*world
 -->

I see 1 and I'm going to do: predict-yes inner elaboration loop at bottom goal.
	--- Change Working Memory (IE) ---

--- END Application Phase ---
--- Output Phase ---
ENV: Agent did: predict-yes for direction R in state State-A
In  State-A moving R
ENV: (next state, see, prediction correct?) = (State-B, 1, True)
predict error 0
dir: dir isU
--- END Output Phase ---
-/|--- Input Phase --- 
=>WM: (14108: I2 ^dir U)
=>WM: (14107: I2 ^reward 1)
=>WM: (14106: I2 ^see 1)
=>WM: (14105: N1004 ^status complete)
<=WM: (14094: I2 ^dir R)
<=WM: (14093: I2 ^reward 1)
<=WM: (14092: I2 ^see 0)
=>WM: (14109: I2 ^level-1 R1-root)
<=WM: (14095: I2 ^level-1 L0-root)

--- END Input Phase --- 

--- Proposal Phase ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing elaborate*copy-see-to-output-link
 -->
 (I3 ^see 1 +)
Firing elaborate*reward*based*on*reward
 -->
 (R1008 ^value 1 +)
 (R1 ^reward R1008 +)
Firing propose*predict-yes
 -->
 (O2009 ^name predict-yes +)
 (S1 ^operator O2009 +)
Firing propose*predict-no
 -->
 (O2010 ^name predict-no +)
 (S1 ^operator O2010 +)
Firing rl*prefer*rvt*predict-no*H0*6
 -->
 (S1 ^operator O2008 = 0.9999999999999999)
Firing rl*prefer*rvt*predict-yes*H0*5
 -->
 (S1 ^operator O2007 = 0.)
Firing prefer*rvt*predict-yes*H0
 -->
Firing prefer*rvt*predict-no*H0
 -->
Firing elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir U +)
 inner elaboration loop at bottom goal.
Retracting elaborate*copy-see-to-output-link
 -->
 (I3 ^see 0 +)
Retracting propose*predict-no
 -->
 (O2008 ^name predict-no +)
 (S1 ^operator O2008 +)
Retracting propose*predict-yes
 -->
 (O2007 ^name predict-yes +)
 (S1 ^operator O2007 +)
Retracting elaborate*reward*based*on*reward
 -->
 (R1007 ^value 1 +)
 (R1 ^reward R1007 +)
Retracting elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir R +)
Retracting rl*prefer*rvt*predict-no*H0*4
 -->
 (S1 ^operator O2008 = 0.1269768790760836)
Retracting rl*prefer*rvt*predict-no*H0*4*H1*13
 -->
 (S1 ^operator O2008 = 0.4910065094545203)
Retracting rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O2007 = 0.3829355766477516)
Retracting rl*prefer*rvt*predict-yes*H0*3*H1*14
 -->
 (S1 ^operator O2007 = 0.617076227543635)
=>WM: (14117: S1 ^operator O2010 +)
=>WM: (14116: S1 ^operator O2009 +)
=>WM: (14115: I3 ^dir U)
=>WM: (14114: O2010 ^name predict-no)
=>WM: (14113: O2009 ^name predict-yes)
=>WM: (14112: R1008 ^value 1)
=>WM: (14111: R1 ^reward R1008)
=>WM: (14110: I3 ^see 1)
<=WM: (14101: S1 ^operator O2007 +)
<=WM: (14103: S1 ^operator O2007)
<=WM: (14102: S1 ^operator O2008 +)
<=WM: (14100: I3 ^dir R)
<=WM: (14096: R1 ^reward R1007)
<=WM: (14015: I3 ^see 0)
<=WM: (14099: O2008 ^name predict-no)
<=WM: (14098: O2007 ^name predict-yes)
<=WM: (14097: R1007 ^value 1)

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing prefer*rvt*predict-yes*H0
 -->
Firing rl*prefer*rvt*predict-yes*H0*5
 -->
 (S1 ^operator O2009 = 0.)
Firing prefer*rvt*predict-no*H0
 -->
Firing rl*prefer*rvt*predict-no*H0*6
 -->
 (S1 ^operator O2010 = 0.9999999999999999)
 inner elaboration loop at bottom goal.
Retracting rl*prefer*rvt*predict-no*H0*6
 -->
 (S1 ^operator O2008 = 0.9999999999999999)
Retracting rl*prefer*rvt*predict-yes*H0*5
 -->
 (S1 ^operator O2007 = 0.)

--- END Proposal Phase ---

--- Decision Phase ---
RL update rl*prefer*rvt*predict-yes*H0*3 0.673129 -0.290194 0.382936 -> 0.673128 -0.290194 0.382934(R,m,v=1,0.960784,0.0379257)
RL update rl*prefer*rvt*predict-yes*H0*3*H1*14 0.326882 0.290195 0.617076 -> 0.32688 0.290194 0.617074(R,m,v=1,1,0)
=>WM: (14118: S1 ^operator O2010)

  1005:    O: O2010 (predict-no)
--- END Decision Phase ---

--- Application Phase ---
	--- Firing Productions (PE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing apply*operator
 -->
 (I3 ^predict-no N1005 +  :O )
Firing apply*operator*complete
 -->
 (I3 ^predict-yes N1004 -  :O )
 inner elaboration loop at bottom goal.
	--- Change Working Memory (PE) ---
=>WM: (14119: I3 ^predict-no N1005)
<=WM: (14105: N1004 ^status complete)
<=WM: (14104: I3 ^predict-yes N1004)
	--- Firing Productions (IE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing monitor*world
 -->

I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
	--- Change Working Memory (IE) ---

--- END Application Phase ---
--- Output Phase ---
ENV: Agent did: predict-no for direction U in state State-B
In  State-B moving U
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isL
--- END Output Phase ---
\-/--- Input Phase --- 
=>WM: (14123: I2 ^dir L)
=>WM: (14122: I2 ^reward 1)
=>WM: (14121: I2 ^see 0)
=>WM: (14120: N1005 ^status complete)
<=WM: (14108: I2 ^dir U)
<=WM: (14107: I2 ^reward 1)
<=WM: (14106: I2 ^see 1)
=>WM: (14124: I2 ^level-1 R1-root)
<=WM: (14109: I2 ^level-1 R1-root)

--- END Input Phase --- 

--- Proposal Phase ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing rl*prefer*rvt*predict-yes*H0*1*H1*22
 -->
 (S1 ^operator O2009 = 0.4768779238990463)
Firing rl*prefer*rvt*predict-no*H0*2*H1*10
 -->
 (S1 ^operator O2010 = -0.01194930198035649)
Firing prefer*rvt*predict-no*H0*2*H1
 -->
Firing prefer*rvt*predict-yes*H0*1*H1
 -->
Firing elaborate*copy-see-to-output-link
 -->
 (I3 ^see 0 +)
Firing elaborate*reward*based*on*reward
 -->
 (R1009 ^value 1 +)
 (R1 ^reward R1009 +)
Firing propose*predict-yes
 -->
 (O2011 ^name predict-yes +)
 (S1 ^operator O2011 +)
Firing propose*predict-no
 -->
 (O2012 ^name predict-no +)
 (S1 ^operator O2012 +)
Firing rl*prefer*rvt*predict-no*H0*2
 -->
 (S1 ^operator O2010 = 0.2550133610598087)
Firing rl*prefer*rvt*predict-yes*H0*1
 -->
 (S1 ^operator O2009 = 0.5231200249393807)
Firing prefer*rvt*predict-yes*H0
 -->
Firing prefer*rvt*predict-no*H0
 -->
Firing elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir L +)
 inner elaboration loop at bottom goal.
Retracting elaborate*copy-see-to-output-link
 -->
 (I3 ^see 1 +)
Retracting propose*predict-no
 -->
 (O2010 ^name predict-no +)
 (S1 ^operator O2010 +)
Retracting propose*predict-yes
 -->
 (O2009 ^name predict-yes +)
 (S1 ^operator O2009 +)
Retracting elaborate*reward*based*on*reward
 -->
 (R1008 ^value 1 +)
 (R1 ^reward R1008 +)
Retracting elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir U +)
Retracting rl*prefer*rvt*predict-no*H0*6
 -->
 (S1 ^operator O2010 = 0.9999999999999999)
Retracting rl*prefer*rvt*predict-yes*H0*5
 -->
 (S1 ^operator O2009 = 0.)
=>WM: (14132: S1 ^operator O2012 +)
=>WM: (14131: S1 ^operator O2011 +)
=>WM: (14130: I3 ^dir L)
=>WM: (14129: O2012 ^name predict-no)
=>WM: (14128: O2011 ^name predict-yes)
=>WM: (14127: R1009 ^value 1)
=>WM: (14126: R1 ^reward R1009)
=>WM: (14125: I3 ^see 0)
<=WM: (14116: S1 ^operator O2009 +)
<=WM: (14117: S1 ^operator O2010 +)
<=WM: (14118: S1 ^operator O2010)
<=WM: (14115: I3 ^dir U)
<=WM: (14111: R1 ^reward R1008)
<=WM: (14110: I3 ^see 1)
<=WM: (14114: O2010 ^name predict-no)
<=WM: (14113: O2009 ^name predict-yes)
<=WM: (14112: R1008 ^value 1)

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing prefer*rvt*predict-yes*H0
 -->
Firing rl*prefer*rvt*predict-yes*H0*1*H1*22
 -->
 (S1 ^operator O2011 = 0.4768779238990463)
Firing rl*prefer*rvt*predict-yes*H0*1
 -->
 (S1 ^operator O2011 = 0.5231200249393807)
Firing prefer*rvt*predict-yes*H0*1*H1
 -->
Firing prefer*rvt*predict-no*H0
 -->
Firing rl*prefer*rvt*predict-no*H0*2*H1*10
 -->
 (S1 ^operator O2012 = -0.01194930198035649)
Firing rl*prefer*rvt*predict-no*H0*2
 -->
 (S1 ^operator O2012 = 0.2550133610598087)
Firing prefer*rvt*predict-no*H0*2*H1
 -->
 inner elaboration loop at bottom goal.
Retracting rl*prefer*rvt*predict-no*H0*2
 -->
 (S1 ^operator O2010 = 0.2550133610598087)
Retracting rl*prefer*rvt*predict-no*H0*2*H1*10
 -->
 (S1 ^operator O2010 = -0.01194930198035649)
Retracting rl*prefer*rvt*predict-yes*H0*1
 -->
 (S1 ^operator O2009 = 0.5231200249393807)
Retracting rl*prefer*rvt*predict-yes*H0*1*H1*22
 -->
 (S1 ^operator O2009 = 0.4768779238990463)

--- END Proposal Phase ---

--- Decision Phase ---
RL update rl*prefer*rvt*predict-no*H0*6 1 0 1 -> 1 0 1(R,m,v=1,1,0)
=>WM: (14133: S1 ^operator O2011)

  1006:    O: O2011 (predict-yes)
--- END Decision Phase ---

--- Application Phase ---
	--- Firing Productions (PE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing apply*operator
 -->
 (I3 ^predict-yes N1006 +  :O )
Firing apply*operator*complete
 -->
 (I3 ^predict-no N1005 -  :O )
 inner elaboration loop at bottom goal.
	--- Change Working Memory (PE) ---
=>WM: (14134: I3 ^predict-yes N1006)
<=WM: (14120: N1005 ^status complete)
<=WM: (14119: I3 ^predict-no N1005)
	--- Firing Productions (IE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing monitor*world
 -->

I see 1 and I'm going to do: predict-yes inner elaboration loop at bottom goal.
	--- Change Working Memory (IE) ---

--- END Application Phase ---
--- Output Phase ---
ENV: Agent did: predict-yes for direction L in state State-B
In  State-B moving L
ENV: (next state, see, prediction correct?) = (State-A, 1, True)
predict error 0
dir: dir isL
--- END Output Phase ---
|\---- Input Phase --- 
=>WM: (14138: I2 ^dir L)
=>WM: (14137: I2 ^reward 1)
=>WM: (14136: I2 ^see 1)
=>WM: (14135: N1006 ^status complete)
<=WM: (14123: I2 ^dir L)
<=WM: (14122: I2 ^reward 1)
<=WM: (14121: I2 ^see 0)
=>WM: (14139: I2 ^level-1 L1-root)
<=WM: (14124: I2 ^level-1 R1-root)

--- END Input Phase --- 

--- Proposal Phase ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing rl*prefer*rvt*predict-yes*H0*1*H1*20
 -->
 (S1 ^operator O2011 = 0.1693592933936033)
Firing rl*prefer*rvt*predict-no*H0*2*H1*11
 -->
 (S1 ^operator O2012 = 0.7449864646061185)
Firing prefer*rvt*predict-no*H0*2*H1
 -->
Firing prefer*rvt*predict-yes*H0*1*H1
 -->
Firing elaborate*copy-see-to-output-link
 -->
 (I3 ^see 1 +)
Firing elaborate*reward*based*on*reward
 -->
 (R1010 ^value 1 +)
 (R1 ^reward R1010 +)
Firing propose*predict-yes
 -->
 (O2013 ^name predict-yes +)
 (S1 ^operator O2013 +)
Firing propose*predict-no
 -->
 (O2014 ^name predict-no +)
 (S1 ^operator O2014 +)
Firing rl*prefer*rvt*predict-no*H0*2
 -->
 (S1 ^operator O2012 = 0.2550133610598087)
Firing rl*prefer*rvt*predict-yes*H0*1
 -->
 (S1 ^operator O2011 = 0.5231200249393807)
Firing prefer*rvt*predict-yes*H0
 -->
Firing prefer*rvt*predict-no*H0
 -->
Firing elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir L +)
 inner elaboration loop at bottom goal.
Retracting elaborate*copy-see-to-output-link
 -->
 (I3 ^see 0 +)
Retracting propose*predict-no
 -->
 (O2012 ^name predict-no +)
 (S1 ^operator O2012 +)
Retracting propose*predict-yes
 -->
 (O2011 ^name predict-yes +)
 (S1 ^operator O2011 +)
Retracting elaborate*reward*based*on*reward
 -->
 (R1009 ^value 1 +)
 (R1 ^reward R1009 +)
Retracting elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir L +)
Retracting rl*prefer*rvt*predict-no*H0*2
 -->
 (S1 ^operator O2012 = 0.2550133610598087)
Retracting rl*prefer*rvt*predict-no*H0*2*H1*10
 -->
 (S1 ^operator O2012 = -0.01194930198035649)
Retracting rl*prefer*rvt*predict-yes*H0*1
 -->
 (S1 ^operator O2011 = 0.5231200249393807)
Retracting rl*prefer*rvt*predict-yes*H0*1*H1*22
 -->
 (S1 ^operator O2011 = 0.4768779238990463)
=>WM: (14146: S1 ^operator O2014 +)
=>WM: (14145: S1 ^operator O2013 +)
=>WM: (14144: O2014 ^name predict-no)
=>WM: (14143: O2013 ^name predict-yes)
=>WM: (14142: R1010 ^value 1)
=>WM: (14141: R1 ^reward R1010)
=>WM: (14140: I3 ^see 1)
<=WM: (14131: S1 ^operator O2011 +)
<=WM: (14133: S1 ^operator O2011)
<=WM: (14132: S1 ^operator O2012 +)
<=WM: (14126: R1 ^reward R1009)
<=WM: (14125: I3 ^see 0)
<=WM: (14129: O2012 ^name predict-no)
<=WM: (14128: O2011 ^name predict-yes)
<=WM: (14127: R1009 ^value 1)

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing prefer*rvt*predict-yes*H0
 -->
Firing rl*prefer*rvt*predict-yes*H0*1
 -->
 (S1 ^operator O2013 = 0.5231200249393807)
Firing prefer*rvt*predict-yes*H0*1*H1
 -->
Firing rl*prefer*rvt*predict-yes*H0*1*H1*20
 -->
 (S1 ^operator O2013 = 0.1693592933936033)
Firing prefer*rvt*predict-no*H0
 -->
Firing rl*prefer*rvt*predict-no*H0*2
 -->
 (S1 ^operator O2014 = 0.2550133610598087)
Firing prefer*rvt*predict-no*H0*2*H1
 -->
Firing rl*prefer*rvt*predict-no*H0*2*H1*11
 -->
 (S1 ^operator O2014 = 0.7449864646061185)
 inner elaboration loop at bottom goal.
Retracting rl*prefer*rvt*predict-no*H0*2
 -->
 (S1 ^operator O2012 = 0.2550133610598087)
Retracting rl*prefer*rvt*predict-no*H0*2*H1*11
 -->
 (S1 ^operator O2012 = 0.7449864646061185)
Retracting rl*prefer*rvt*predict-yes*H0*1
 -->
 (S1 ^operator O2011 = 0.5231200249393807)
Retracting rl*prefer*rvt*predict-yes*H0*1*H1*20
 -->
 (S1 ^operator O2011 = 0.1693592933936033)

--- END Proposal Phase ---

--- Decision Phase ---
RL update rl*prefer*rvt*predict-yes*H0*1 0.72796 -0.20484 0.52312 -> 0.72796 -0.20484 0.52312(R,m,v=1,0.979021,0.0206835)
RL update rl*prefer*rvt*predict-yes*H0*1*H1*22 0.272037 0.204841 0.476878 -> 0.272038 0.20484 0.476878(R,m,v=1,1,0)
=>WM: (14147: S1 ^operator O2014)

  1007:    O: O2014 (predict-no)
--- END Decision Phase ---

--- Application Phase ---
	--- Firing Productions (PE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing apply*operator
 -->
 (I3 ^predict-no N1007 +  :O )
Firing apply*operator*complete
 -->
 (I3 ^predict-yes N1006 -  :O )
 inner elaboration loop at bottom goal.
	--- Change Working Memory (PE) ---
=>WM: (14148: I3 ^predict-no N1007)
<=WM: (14135: N1006 ^status complete)
<=WM: (14134: I3 ^predict-yes N1006)
	--- Firing Productions (IE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing monitor*world
 -->

I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
	--- Change Working Memory (IE) ---

--- END Application Phase ---
--- Output Phase ---
ENV: Agent did: predict-no for direction L in state State-A
In  State-A moving L
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isU
--- END Output Phase ---
/|\--- Input Phase --- 
=>WM: (14152: I2 ^dir U)
=>WM: (14151: I2 ^reward 1)
=>WM: (14150: I2 ^see 0)
=>WM: (14149: N1007 ^status complete)
<=WM: (14138: I2 ^dir L)
<=WM: (14137: I2 ^reward 1)
<=WM: (14136: I2 ^see 1)
=>WM: (14153: I2 ^level-1 L0-root)
<=WM: (14139: I2 ^level-1 L1-root)

--- END Input Phase --- 

--- Proposal Phase ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing elaborate*copy-see-to-output-link
 -->
 (I3 ^see 0 +)
Firing elaborate*reward*based*on*reward
 -->
 (R1011 ^value 1 +)
 (R1 ^reward R1011 +)
Firing propose*predict-yes
 -->
 (O2015 ^name predict-yes +)
 (S1 ^operator O2015 +)
Firing propose*predict-no
 -->
 (O2016 ^name predict-no +)
 (S1 ^operator O2016 +)
Firing rl*prefer*rvt*predict-no*H0*6
 -->
 (S1 ^operator O2014 = 0.9999999999999999)
Firing rl*prefer*rvt*predict-yes*H0*5
 -->
 (S1 ^operator O2013 = 0.)
Firing prefer*rvt*predict-yes*H0
 -->
Firing prefer*rvt*predict-no*H0
 -->
Firing elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir U +)
 inner elaboration loop at bottom goal.
Retracting elaborate*copy-see-to-output-link
 -->
 (I3 ^see 1 +)
Retracting propose*predict-no
 -->
 (O2014 ^name predict-no +)
 (S1 ^operator O2014 +)
Retracting propose*predict-yes
 -->
 (O2013 ^name predict-yes +)
 (S1 ^operator O2013 +)
Retracting elaborate*reward*based*on*reward
 -->
 (R1010 ^value 1 +)
 (R1 ^reward R1010 +)
Retracting elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir L +)
Retracting rl*prefer*rvt*predict-no*H0*2*H1*11
 -->
 (S1 ^operator O2014 = 0.7449864646061185)
Retracting rl*prefer*rvt*predict-no*H0*2
 -->
 (S1 ^operator O2014 = 0.2550133610598087)
Retracting rl*prefer*rvt*predict-yes*H0*1*H1*20
 -->
 (S1 ^operator O2013 = 0.1693592933936033)
Retracting rl*prefer*rvt*predict-yes*H0*1
 -->
 (S1 ^operator O2013 = 0.5231203326136166)
=>WM: (14161: S1 ^operator O2016 +)
=>WM: (14160: S1 ^operator O2015 +)
=>WM: (14159: I3 ^dir U)
=>WM: (14158: O2016 ^name predict-no)
=>WM: (14157: O2015 ^name predict-yes)
=>WM: (14156: R1011 ^value 1)
=>WM: (14155: R1 ^reward R1011)
=>WM: (14154: I3 ^see 0)
<=WM: (14145: S1 ^operator O2013 +)
<=WM: (14146: S1 ^operator O2014 +)
<=WM: (14147: S1 ^operator O2014)
<=WM: (14130: I3 ^dir L)
<=WM: (14141: R1 ^reward R1010)
<=WM: (14140: I3 ^see 1)
<=WM: (14144: O2014 ^name predict-no)
<=WM: (14143: O2013 ^name predict-yes)
<=WM: (14142: R1010 ^value 1)

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing prefer*rvt*predict-yes*H0
 -->
Firing rl*prefer*rvt*predict-yes*H0*5
 -->
 (S1 ^operator O2015 = 0.)
Firing prefer*rvt*predict-no*H0
 -->
Firing rl*prefer*rvt*predict-no*H0*6
 -->
 (S1 ^operator O2016 = 0.9999999999999999)
 inner elaboration loop at bottom goal.
Retracting rl*prefer*rvt*predict-no*H0*6
 -->
 (S1 ^operator O2014 = 0.9999999999999999)
Retracting rl*prefer*rvt*predict-yes*H0*5
 -->
 (S1 ^operator O2013 = 0.)

--- END Proposal Phase ---

--- Decision Phase ---
RL update rl*prefer*rvt*predict-no*H0*2 0.631495 -0.376482 0.255013 -> 0.631495 -0.376482 0.255013(R,m,v=1,0.919192,0.0746552)
RL update rl*prefer*rvt*predict-no*H0*2*H1*11 0.368505 0.376482 0.744986 -> 0.368505 0.376482 0.744986(R,m,v=1,1,0)
=>WM: (14162: S1 ^operator O2016)

  1008:    O: O2016 (predict-no)
--- END Decision Phase ---

--- Application Phase ---
	--- Firing Productions (PE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing apply*operator
 -->
 (I3 ^predict-no N1008 +  :O )
Firing apply*operator*complete
 -->
 (I3 ^predict-no N1007 -  :O )
 inner elaboration loop at bottom goal.
	--- Change Working Memory (PE) ---
=>WM: (14163: I3 ^predict-no N1008)
<=WM: (14149: N1007 ^status complete)
<=WM: (14148: I3 ^predict-no N1007)
	--- Firing Productions (IE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing monitor*world
 -->

I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
	--- Change Working Memory (IE) ---

--- END Application Phase ---
--- Output Phase ---
ENV: Agent did: predict-no for direction U in state State-A
In  State-A moving U
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isU
--- END Output Phase ---
-/|--- Input Phase --- 
=>WM: (14167: I2 ^dir U)
=>WM: (14166: I2 ^reward 1)
=>WM: (14165: I2 ^see 0)
=>WM: (14164: N1008 ^status complete)
<=WM: (14152: I2 ^dir U)
<=WM: (14151: I2 ^reward 1)
<=WM: (14150: I2 ^see 0)
=>WM: (14168: I2 ^level-1 L0-root)
<=WM: (14153: I2 ^level-1 L0-root)

--- END Input Phase --- 

--- Proposal Phase ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing elaborate*copy-see-to-output-link
 -->
 (I3 ^see 0 +)
Firing elaborate*reward*based*on*reward
 -->
 (R1012 ^value 1 +)
 (R1 ^reward R1012 +)
Firing propose*predict-yes
 -->
 (O2017 ^name predict-yes +)
 (S1 ^operator O2017 +)
Firing propose*predict-no
 -->
 (O2018 ^name predict-no +)
 (S1 ^operator O2018 +)
Firing rl*prefer*rvt*predict-no*H0*6
 -->
 (S1 ^operator O2016 = 0.9999999999999999)
Firing rl*prefer*rvt*predict-yes*H0*5
 -->
 (S1 ^operator O2015 = 0.)
Firing prefer*rvt*predict-yes*H0
 -->
Firing prefer*rvt*predict-no*H0
 -->
Firing elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir U +)
 inner elaboration loop at bottom goal.
Retracting elaborate*copy-see-to-output-link
 -->
 (I3 ^see 0 +)
Retracting propose*predict-no
 -->
 (O2016 ^name predict-no +)
 (S1 ^operator O2016 +)
Retracting propose*predict-yes
 -->
 (O2015 ^name predict-yes +)
 (S1 ^operator O2015 +)
Retracting elaborate*reward*based*on*reward
 -->
 (R1011 ^value 1 +)
 (R1 ^reward R1011 +)
Retracting elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir U +)
Retracting rl*prefer*rvt*predict-no*H0*6
 -->
 (S1 ^operator O2016 = 0.9999999999999999)
Retracting rl*prefer*rvt*predict-yes*H0*5
 -->
 (S1 ^operator O2015 = 0.)
=>WM: (14174: S1 ^operator O2018 +)
=>WM: (14173: S1 ^operator O2017 +)
=>WM: (14172: O2018 ^name predict-no)
=>WM: (14171: O2017 ^name predict-yes)
=>WM: (14170: R1012 ^value 1)
=>WM: (14169: R1 ^reward R1012)
<=WM: (14160: S1 ^operator O2015 +)
<=WM: (14161: S1 ^operator O2016 +)
<=WM: (14162: S1 ^operator O2016)
<=WM: (14155: R1 ^reward R1011)
<=WM: (14158: O2016 ^name predict-no)
<=WM: (14157: O2015 ^name predict-yes)
<=WM: (14156: R1011 ^value 1)

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing prefer*rvt*predict-yes*H0
 -->
Firing rl*prefer*rvt*predict-yes*H0*5
 -->
 (S1 ^operator O2017 = 0.)
Firing prefer*rvt*predict-no*H0
 -->
Firing rl*prefer*rvt*predict-no*H0*6
 -->
 (S1 ^operator O2018 = 0.9999999999999999)
 inner elaboration loop at bottom goal.
Retracting rl*prefer*rvt*predict-no*H0*6
 -->
 (S1 ^operator O2016 = 0.9999999999999999)
Retracting rl*prefer*rvt*predict-yes*H0*5
 -->
 (S1 ^operator O2015 = 0.)

--- END Proposal Phase ---

--- Decision Phase ---
RL update rl*prefer*rvt*predict-no*H0*6 1 0 1 -> 1 0 1(R,m,v=1,1,0)
=>WM: (14175: S1 ^operator O2018)

  1009:    O: O2018 (predict-no)
--- END Decision Phase ---

--- Application Phase ---
	--- Firing Productions (PE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing apply*operator
 -->
 (I3 ^predict-no N1009 +  :O )
Firing apply*operator*complete
 -->
 (I3 ^predict-no N1008 -  :O )
 inner elaboration loop at bottom goal.
	--- Change Working Memory (PE) ---
=>WM: (14176: I3 ^predict-no N1009)
<=WM: (14164: N1008 ^status complete)
<=WM: (14163: I3 ^predict-no N1008)
	--- Firing Productions (IE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing monitor*world
 -->

I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
	--- Change Working Memory (IE) ---

--- END Application Phase ---
--- Output Phase ---
ENV: Agent did: predict-no for direction U in state State-A
In  State-A moving U
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isU
--- END Output Phase ---
\-/--- Input Phase --- 
=>WM: (14180: I2 ^dir U)
=>WM: (14179: I2 ^reward 1)
=>WM: (14178: I2 ^see 0)
=>WM: (14177: N1009 ^status complete)
<=WM: (14167: I2 ^dir U)
<=WM: (14166: I2 ^reward 1)
<=WM: (14165: I2 ^see 0)
=>WM: (14181: I2 ^level-1 L0-root)
<=WM: (14168: I2 ^level-1 L0-root)

--- END Input Phase --- 

--- Proposal Phase ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing elaborate*copy-see-to-output-link
 -->
 (I3 ^see 0 +)
Firing elaborate*reward*based*on*reward
 -->
 (R1013 ^value 1 +)
 (R1 ^reward R1013 +)
Firing propose*predict-yes
 -->
 (O2019 ^name predict-yes +)
 (S1 ^operator O2019 +)
Firing propose*predict-no
 -->
 (O2020 ^name predict-no +)
 (S1 ^operator O2020 +)
Firing rl*prefer*rvt*predict-no*H0*6
 -->
 (S1 ^operator O2018 = 0.9999999999999999)
Firing rl*prefer*rvt*predict-yes*H0*5
 -->
 (S1 ^operator O2017 = 0.)
Firing prefer*rvt*predict-yes*H0
 -->
Firing prefer*rvt*predict-no*H0
 -->
Firing elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir U +)
 inner elaboration loop at bottom goal.
Retracting elaborate*copy-see-to-output-link
 -->
 (I3 ^see 0 +)
Retracting propose*predict-no
 -->
 (O2018 ^name predict-no +)
 (S1 ^operator O2018 +)
Retracting propose*predict-yes
 -->
 (O2017 ^name predict-yes +)
 (S1 ^operator O2017 +)
Retracting elaborate*reward*based*on*reward
 -->
 (R1012 ^value 1 +)
 (R1 ^reward R1012 +)
Retracting elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir U +)
Retracting rl*prefer*rvt*predict-no*H0*6
 -->
 (S1 ^operator O2018 = 0.9999999999999999)
Retracting rl*prefer*rvt*predict-yes*H0*5
 -->
 (S1 ^operator O2017 = 0.)
=>WM: (14187: S1 ^operator O2020 +)
=>WM: (14186: S1 ^operator O2019 +)
=>WM: (14185: O2020 ^name predict-no)
=>WM: (14184: O2019 ^name predict-yes)
=>WM: (14183: R1013 ^value 1)
=>WM: (14182: R1 ^reward R1013)
<=WM: (14173: S1 ^operator O2017 +)
<=WM: (14174: S1 ^operator O2018 +)
<=WM: (14175: S1 ^operator O2018)
<=WM: (14169: R1 ^reward R1012)
<=WM: (14172: O2018 ^name predict-no)
<=WM: (14171: O2017 ^name predict-yes)
<=WM: (14170: R1012 ^value 1)

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing prefer*rvt*predict-yes*H0
 -->
Firing rl*prefer*rvt*predict-yes*H0*5
 -->
 (S1 ^operator O2019 = 0.)
Firing prefer*rvt*predict-no*H0
 -->
Firing rl*prefer*rvt*predict-no*H0*6
 -->
 (S1 ^operator O2020 = 0.9999999999999999)
 inner elaboration loop at bottom goal.
Retracting rl*prefer*rvt*predict-no*H0*6
 -->
 (S1 ^operator O2018 = 0.9999999999999999)
Retracting rl*prefer*rvt*predict-yes*H0*5
 -->
 (S1 ^operator O2017 = 0.)

--- END Proposal Phase ---

--- Decision Phase ---
RL update rl*prefer*rvt*predict-no*H0*6 1 0 1 -> 1 0 1(R,m,v=1,1,0)
=>WM: (14188: S1 ^operator O2020)

  1010:    O: O2020 (predict-no)
--- END Decision Phase ---

--- Application Phase ---
	--- Firing Productions (PE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing apply*operator
 -->
 (I3 ^predict-no N1010 +  :O )
Firing apply*operator*complete
 -->
 (I3 ^predict-no N1009 -  :O )
 inner elaboration loop at bottom goal.
	--- Change Working Memory (PE) ---
=>WM: (14189: I3 ^predict-no N1010)
<=WM: (14177: N1009 ^status complete)
<=WM: (14176: I3 ^predict-no N1009)
	--- Firing Productions (IE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing monitor*world
 -->

I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
	--- Change Working Memory (IE) ---

--- END Application Phase ---
--- Output Phase ---
ENV: Agent did: predict-no for direction U in state State-A
In  State-A moving U
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isU
--- END Output Phase ---
|\---- Input Phase --- 
=>WM: (14193: I2 ^dir U)
=>WM: (14192: I2 ^reward 1)
=>WM: (14191: I2 ^see 0)
=>WM: (14190: N1010 ^status complete)
<=WM: (14180: I2 ^dir U)
<=WM: (14179: I2 ^reward 1)
<=WM: (14178: I2 ^see 0)
=>WM: (14194: I2 ^level-1 L0-root)
<=WM: (14181: I2 ^level-1 L0-root)

--- END Input Phase --- 

--- Proposal Phase ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing elaborate*copy-see-to-output-link
 -->
 (I3 ^see 0 +)
Firing elaborate*reward*based*on*reward
 -->
 (R1014 ^value 1 +)
 (R1 ^reward R1014 +)
Firing propose*predict-yes
 -->
 (O2021 ^name predict-yes +)
 (S1 ^operator O2021 +)
Firing propose*predict-no
 -->
 (O2022 ^name predict-no +)
 (S1 ^operator O2022 +)
Firing rl*prefer*rvt*predict-no*H0*6
 -->
 (S1 ^operator O2020 = 0.9999999999999999)
Firing rl*prefer*rvt*predict-yes*H0*5
 -->
 (S1 ^operator O2019 = 0.)
Firing prefer*rvt*predict-yes*H0
 -->
Firing prefer*rvt*predict-no*H0
 -->
Firing elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir U +)
 inner elaboration loop at bottom goal.
Retracting elaborate*copy-see-to-output-link
 -->
 (I3 ^see 0 +)
Retracting propose*predict-no
 -->
 (O2020 ^name predict-no +)
 (S1 ^operator O2020 +)
Retracting propose*predict-yes
 -->
 (O2019 ^name predict-yes +)
 (S1 ^operator O2019 +)
Retracting elaborate*reward*based*on*reward
 -->
 (R1013 ^value 1 +)
 (R1 ^reward R1013 +)
Retracting elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir U +)
Retracting rl*prefer*rvt*predict-no*H0*6
 -->
 (S1 ^operator O2020 = 0.9999999999999999)
Retracting rl*prefer*rvt*predict-yes*H0*5
 -->
 (S1 ^operator O2019 = 0.)
=>WM: (14200: S1 ^operator O2022 +)
=>WM: (14199: S1 ^operator O2021 +)
=>WM: (14198: O2022 ^name predict-no)
=>WM: (14197: O2021 ^name predict-yes)
=>WM: (14196: R1014 ^value 1)
=>WM: (14195: R1 ^reward R1014)
<=WM: (14186: S1 ^operator O2019 +)
<=WM: (14187: S1 ^operator O2020 +)
<=WM: (14188: S1 ^operator O2020)
<=WM: (14182: R1 ^reward R1013)
<=WM: (14185: O2020 ^name predict-no)
<=WM: (14184: O2019 ^name predict-yes)
<=WM: (14183: R1013 ^value 1)

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing prefer*rvt*predict-yes*H0
 -->
Firing rl*prefer*rvt*predict-yes*H0*5
 -->
 (S1 ^operator O2021 = 0.)
Firing prefer*rvt*predict-no*H0
 -->
Firing rl*prefer*rvt*predict-no*H0*6
 -->
 (S1 ^operator O2022 = 0.9999999999999999)
 inner elaboration loop at bottom goal.
Retracting rl*prefer*rvt*predict-no*H0*6
 -->
 (S1 ^operator O2020 = 0.9999999999999999)
Retracting rl*prefer*rvt*predict-yes*H0*5
 -->
 (S1 ^operator O2019 = 0.)

--- END Proposal Phase ---

--- Decision Phase ---
RL update rl*prefer*rvt*predict-no*H0*6 1 0 1 -> 1 0 1(R,m,v=1,1,0)
=>WM: (14201: S1 ^operator O2022)

  1011:    O: O2022 (predict-no)
--- END Decision Phase ---

--- Application Phase ---
	--- Firing Productions (PE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing apply*operator
 -->
 (I3 ^predict-no N1011 +  :O )
Firing apply*operator*complete
 -->
 (I3 ^predict-no N1010 -  :O )
 inner elaboration loop at bottom goal.
	--- Change Working Memory (PE) ---
=>WM: (14202: I3 ^predict-no N1011)
<=WM: (14190: N1010 ^status complete)
<=WM: (14189: I3 ^predict-no N1010)
	--- Firing Productions (IE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing monitor*world
 -->

I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
	--- Change Working Memory (IE) ---

--- END Application Phase ---
--- Output Phase ---
ENV: Agent did: predict-no for direction U in state State-A
In  State-A moving U
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isR
--- END Output Phase ---
/--- Input Phase --- 
=>WM: (14206: I2 ^dir R)
=>WM: (14205: I2 ^reward 1)
=>WM: (14204: I2 ^see 0)
=>WM: (14203: N1011 ^status complete)
<=WM: (14193: I2 ^dir U)
<=WM: (14192: I2 ^reward 1)
<=WM: (14191: I2 ^see 0)
=>WM: (14207: I2 ^level-1 L0-root)
<=WM: (14194: I2 ^level-1 L0-root)

--- END Input Phase --- 

--- Proposal Phase ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing rl*prefer*rvt*predict-yes*H0*3*H1*14
 -->
 (S1 ^operator O2021 = 0.6170744569149269)
Firing rl*prefer*rvt*predict-no*H0*4*H1*13
 -->
 (S1 ^operator O2022 = 0.4910065094545203)
Firing prefer*rvt*predict-no*H0*4*H1
 -->
Firing prefer*rvt*predict-yes*H0*3*H1
 -->
Firing elaborate*copy-see-to-output-link
 -->
 (I3 ^see 0 +)
Firing elaborate*reward*based*on*reward
 -->
 (R1015 ^value 1 +)
 (R1 ^reward R1015 +)
Firing propose*predict-yes
 -->
 (O2023 ^name predict-yes +)
 (S1 ^operator O2023 +)
Firing propose*predict-no
 -->
 (O2024 ^name predict-no +)
 (S1 ^operator O2024 +)
Firing rl*prefer*rvt*predict-no*H0*4
 -->
 (S1 ^operator O2022 = 0.1269768790760836)
Firing rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O2021 = 0.3829338060190436)
Firing prefer*rvt*predict-yes*H0
 -->
Firing prefer*rvt*predict-no*H0
 -->
Firing elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir R +)
 inner elaboration loop at bottom goal.
Retracting elaborate*copy-see-to-output-link
 -->
 (I3 ^see 0 +)
Retracting propose*predict-no
 -->
 (O2022 ^name predict-no +)
 (S1 ^operator O2022 +)
Retracting propose*predict-yes
 -->
 (O2021 ^name predict-yes +)
 (S1 ^operator O2021 +)
Retracting elaborate*reward*based*on*reward
 -->
 (R1014 ^value 1 +)
 (R1 ^reward R1014 +)
Retracting elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir U +)
Retracting rl*prefer*rvt*predict-no*H0*6
 -->
 (S1 ^operator O2022 = 0.9999999999999999)
Retracting rl*prefer*rvt*predict-yes*H0*5
 -->
 (S1 ^operator O2021 = 0.)
=>WM: (14214: S1 ^operator O2024 +)
=>WM: (14213: S1 ^operator O2023 +)
=>WM: (14212: I3 ^dir R)
=>WM: (14211: O2024 ^name predict-no)
=>WM: (14210: O2023 ^name predict-yes)
=>WM: (14209: R1015 ^value 1)
=>WM: (14208: R1 ^reward R1015)
<=WM: (14199: S1 ^operator O2021 +)
<=WM: (14200: S1 ^operator O2022 +)
<=WM: (14201: S1 ^operator O2022)
<=WM: (14159: I3 ^dir U)
<=WM: (14195: R1 ^reward R1014)
<=WM: (14198: O2022 ^name predict-no)
<=WM: (14197: O2021 ^name predict-yes)
<=WM: (14196: R1014 ^value 1)

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing prefer*rvt*predict-yes*H0
 -->
Firing rl*prefer*rvt*predict-yes*H0*3*H1*14
 -->
 (S1 ^operator O2023 = 0.6170744569149269)
Firing rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O2023 = 0.3829338060190436)
Firing prefer*rvt*predict-yes*H0*3*H1
 -->
Firing prefer*rvt*predict-no*H0
 -->
Firing rl*prefer*rvt*predict-no*H0*4*H1*13
 -->
 (S1 ^operator O2024 = 0.4910065094545203)
Firing rl*prefer*rvt*predict-no*H0*4
 -->
 (S1 ^operator O2024 = 0.1269768790760836)
Firing prefer*rvt*predict-no*H0*4*H1
 -->
 inner elaboration loop at bottom goal.
Retracting rl*prefer*rvt*predict-no*H0*4
 -->
 (S1 ^operator O2022 = 0.1269768790760836)
Retracting rl*prefer*rvt*predict-no*H0*4*H1*13
 -->
 (S1 ^operator O2022 = 0.4910065094545203)
Retracting rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O2021 = 0.3829338060190436)
Retracting rl*prefer*rvt*predict-yes*H0*3*H1*14
 -->
 (S1 ^operator O2021 = 0.6170744569149269)

--- END Proposal Phase ---

--- Decision Phase ---
RL update rl*prefer*rvt*predict-no*H0*6 1 0 1 -> 1 0 1(R,m,v=1,1,0)
=>WM: (14215: S1 ^operator O2023)

  1012:    O: O2023 (predict-yes)
--- END Decision Phase ---

--- Application Phase ---
	--- Firing Productions (PE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing apply*operator
 -->
 (I3 ^predict-yes N1012 +  :O )
Firing apply*operator*complete
 -->
 (I3 ^predict-no N1011 -  :O )
 inner elaboration loop at bottom goal.
	--- Change Working Memory (PE) ---
=>WM: (14216: I3 ^predict-yes N1012)
<=WM: (14203: N1011 ^status complete)
<=WM: (14202: I3 ^predict-no N1011)
	--- Firing Productions (IE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing monitor*world
 -->

I see 1 and I'm going to do: predict-yes inner elaboration loop at bottom goal.
	--- Change Working Memory (IE) ---

--- END Application Phase ---
--- Output Phase ---
ENV: Agent did: predict-yes for direction R in state State-A
In  State-A moving R
ENV: (next state, see, prediction correct?) = (State-B, 1, True)
predict error 0
dir: dir isU
--- END Output Phase ---
|\---- Input Phase --- 
=>WM: (14220: I2 ^dir U)
=>WM: (14219: I2 ^reward 1)
=>WM: (14218: I2 ^see 1)
=>WM: (14217: N1012 ^status complete)
<=WM: (14206: I2 ^dir R)
<=WM: (14205: I2 ^reward 1)
<=WM: (14204: I2 ^see 0)
=>WM: (14221: I2 ^level-1 R1-root)
<=WM: (14207: I2 ^level-1 L0-root)

--- END Input Phase --- 

--- Proposal Phase ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing elaborate*copy-see-to-output-link
 -->
 (I3 ^see 1 +)
Firing elaborate*reward*based*on*reward
 -->
 (R1016 ^value 1 +)
 (R1 ^reward R1016 +)
Firing propose*predict-yes
 -->
 (O2025 ^name predict-yes +)
 (S1 ^operator O2025 +)
Firing propose*predict-no
 -->
 (O2026 ^name predict-no +)
 (S1 ^operator O2026 +)
Firing rl*prefer*rvt*predict-no*H0*6
 -->
 (S1 ^operator O2024 = 0.9999999999999999)
Firing rl*prefer*rvt*predict-yes*H0*5
 -->
 (S1 ^operator O2023 = 0.)
Firing prefer*rvt*predict-yes*H0
 -->
Firing prefer*rvt*predict-no*H0
 -->
Firing elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir U +)
 inner elaboration loop at bottom goal.
Retracting elaborate*copy-see-to-output-link
 -->
 (I3 ^see 0 +)
Retracting propose*predict-no
 -->
 (O2024 ^name predict-no +)
 (S1 ^operator O2024 +)
Retracting propose*predict-yes
 -->
 (O2023 ^name predict-yes +)
 (S1 ^operator O2023 +)
Retracting elaborate*reward*based*on*reward
 -->
 (R1015 ^value 1 +)
 (R1 ^reward R1015 +)
Retracting elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir R +)
Retracting rl*prefer*rvt*predict-no*H0*4
 -->
 (S1 ^operator O2024 = 0.1269768790760836)
Retracting rl*prefer*rvt*predict-no*H0*4*H1*13
 -->
 (S1 ^operator O2024 = 0.4910065094545203)
Retracting rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O2023 = 0.3829338060190436)
Retracting rl*prefer*rvt*predict-yes*H0*3*H1*14
 -->
 (S1 ^operator O2023 = 0.6170744569149269)
=>WM: (14229: S1 ^operator O2026 +)
=>WM: (14228: S1 ^operator O2025 +)
=>WM: (14227: I3 ^dir U)
=>WM: (14226: O2026 ^name predict-no)
=>WM: (14225: O2025 ^name predict-yes)
=>WM: (14224: R1016 ^value 1)
=>WM: (14223: R1 ^reward R1016)
=>WM: (14222: I3 ^see 1)
<=WM: (14213: S1 ^operator O2023 +)
<=WM: (14215: S1 ^operator O2023)
<=WM: (14214: S1 ^operator O2024 +)
<=WM: (14212: I3 ^dir R)
<=WM: (14208: R1 ^reward R1015)
<=WM: (14154: I3 ^see 0)
<=WM: (14211: O2024 ^name predict-no)
<=WM: (14210: O2023 ^name predict-yes)
<=WM: (14209: R1015 ^value 1)

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing prefer*rvt*predict-yes*H0
 -->
Firing rl*prefer*rvt*predict-yes*H0*5
 -->
 (S1 ^operator O2025 = 0.)
Firing prefer*rvt*predict-no*H0
 -->
Firing rl*prefer*rvt*predict-no*H0*6
 -->
 (S1 ^operator O2026 = 0.9999999999999999)
 inner elaboration loop at bottom goal.
Retracting rl*prefer*rvt*predict-no*H0*6
 -->
 (S1 ^operator O2024 = 0.9999999999999999)
Retracting rl*prefer*rvt*predict-yes*H0*5
 -->
 (S1 ^operator O2023 = 0.)

--- END Proposal Phase ---

--- Decision Phase ---
RL update rl*prefer*rvt*predict-yes*H0*3 0.673128 -0.290194 0.382934 -> 0.673126 -0.290194 0.382933(R,m,v=1,0.961039,0.0376878)
RL update rl*prefer*rvt*predict-yes*H0*3*H1*14 0.32688 0.290194 0.617074 -> 0.326879 0.290194 0.617073(R,m,v=1,1,0)
=>WM: (14230: S1 ^operator O2026)

  1013:    O: O2026 (predict-no)
--- END Decision Phase ---

--- Application Phase ---
	--- Firing Productions (PE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing apply*operator
 -->
 (I3 ^predict-no N1013 +  :O )
Firing apply*operator*complete
 -->
 (I3 ^predict-yes N1012 -  :O )
 inner elaboration loop at bottom goal.
	--- Change Working Memory (PE) ---
=>WM: (14231: I3 ^predict-no N1013)
<=WM: (14217: N1012 ^status complete)
<=WM: (14216: I3 ^predict-yes N1012)
	--- Firing Productions (IE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing monitor*world
 -->

I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
	--- Change Working Memory (IE) ---

--- END Application Phase ---
--- Output Phase ---
ENV: Agent did: predict-no for direction U in state State-B
In  State-B moving U
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isL
--- END Output Phase ---
/|\--- Input Phase --- 
=>WM: (14235: I2 ^dir L)
=>WM: (14234: I2 ^reward 1)
=>WM: (14233: I2 ^see 0)
=>WM: (14232: N1013 ^status complete)
<=WM: (14220: I2 ^dir U)
<=WM: (14219: I2 ^reward 1)
<=WM: (14218: I2 ^see 1)
=>WM: (14236: I2 ^level-1 R1-root)
<=WM: (14221: I2 ^level-1 R1-root)

--- END Input Phase --- 

--- Proposal Phase ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing rl*prefer*rvt*predict-yes*H0*1*H1*22
 -->
 (S1 ^operator O2025 = 0.4768782315732822)
Firing rl*prefer*rvt*predict-no*H0*2*H1*10
 -->
 (S1 ^operator O2026 = -0.01194930198035649)
Firing prefer*rvt*predict-no*H0*2*H1
 -->
Firing prefer*rvt*predict-yes*H0*1*H1
 -->
Firing elaborate*copy-see-to-output-link
 -->
 (I3 ^see 0 +)
Firing elaborate*reward*based*on*reward
 -->
 (R1017 ^value 1 +)
 (R1 ^reward R1017 +)
Firing propose*predict-yes
 -->
 (O2027 ^name predict-yes +)
 (S1 ^operator O2027 +)
Firing propose*predict-no
 -->
 (O2028 ^name predict-no +)
 (S1 ^operator O2028 +)
Firing rl*prefer*rvt*predict-no*H0*2
 -->
 (S1 ^operator O2026 = 0.2550133872099196)
Firing rl*prefer*rvt*predict-yes*H0*1
 -->
 (S1 ^operator O2025 = 0.5231203326136166)
Firing prefer*rvt*predict-yes*H0
 -->
Firing prefer*rvt*predict-no*H0
 -->
Firing elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir L +)
 inner elaboration loop at bottom goal.
Retracting elaborate*copy-see-to-output-link
 -->
 (I3 ^see 1 +)
Retracting propose*predict-no
 -->
 (O2026 ^name predict-no +)
 (S1 ^operator O2026 +)
Retracting propose*predict-yes
 -->
 (O2025 ^name predict-yes +)
 (S1 ^operator O2025 +)
Retracting elaborate*reward*based*on*reward
 -->
 (R1016 ^value 1 +)
 (R1 ^reward R1016 +)
Retracting elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir U +)
Retracting rl*prefer*rvt*predict-no*H0*6
 -->
 (S1 ^operator O2026 = 0.9999999999999999)
Retracting rl*prefer*rvt*predict-yes*H0*5
 -->
 (S1 ^operator O2025 = 0.)
=>WM: (14244: S1 ^operator O2028 +)
=>WM: (14243: S1 ^operator O2027 +)
=>WM: (14242: I3 ^dir L)
=>WM: (14241: O2028 ^name predict-no)
=>WM: (14240: O2027 ^name predict-yes)
=>WM: (14239: R1017 ^value 1)
=>WM: (14238: R1 ^reward R1017)
=>WM: (14237: I3 ^see 0)
<=WM: (14228: S1 ^operator O2025 +)
<=WM: (14229: S1 ^operator O2026 +)
<=WM: (14230: S1 ^operator O2026)
<=WM: (14227: I3 ^dir U)
<=WM: (14223: R1 ^reward R1016)
<=WM: (14222: I3 ^see 1)
<=WM: (14226: O2026 ^name predict-no)
<=WM: (14225: O2025 ^name predict-yes)
<=WM: (14224: R1016 ^value 1)

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing prefer*rvt*predict-yes*H0
 -->
Firing rl*prefer*rvt*predict-yes*H0*1*H1*22
 -->
 (S1 ^operator O2027 = 0.4768782315732822)
Firing rl*prefer*rvt*predict-yes*H0*1
 -->
 (S1 ^operator O2027 = 0.5231203326136166)
Firing prefer*rvt*predict-yes*H0*1*H1
 -->
Firing prefer*rvt*predict-no*H0
 -->
Firing rl*prefer*rvt*predict-no*H0*2*H1*10
 -->
 (S1 ^operator O2028 = -0.01194930198035649)
Firing rl*prefer*rvt*predict-no*H0*2
 -->
 (S1 ^operator O2028 = 0.2550133872099196)
Firing prefer*rvt*predict-no*H0*2*H1
 -->
 inner elaboration loop at bottom goal.
Retracting rl*prefer*rvt*predict-no*H0*2
 -->
 (S1 ^operator O2026 = 0.2550133872099196)
Retracting rl*prefer*rvt*predict-no*H0*2*H1*10
 -->
 (S1 ^operator O2026 = -0.01194930198035649)
Retracting rl*prefer*rvt*predict-yes*H0*1
 -->
 (S1 ^operator O2025 = 0.5231203326136166)
Retracting rl*prefer*rvt*predict-yes*H0*1*H1*22
 -->
 (S1 ^operator O2025 = 0.4768782315732822)

--- END Proposal Phase ---

--- Decision Phase ---
RL update rl*prefer*rvt*predict-no*H0*6 1 0 1 -> 1 0 1(R,m,v=1,1,0)
=>WM: (14245: S1 ^operator O2027)

  1014:    O: O2027 (predict-yes)
--- END Decision Phase ---

--- Application Phase ---
	--- Firing Productions (PE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing apply*operator
 -->
 (I3 ^predict-yes N1014 +  :O )
Firing apply*operator*complete
 -->
 (I3 ^predict-no N1013 -  :O )
 inner elaboration loop at bottom goal.
	--- Change Working Memory (PE) ---
=>WM: (14246: I3 ^predict-yes N1014)
<=WM: (14232: N1013 ^status complete)
<=WM: (14231: I3 ^predict-no N1013)
	--- Firing Productions (IE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing monitor*world
 -->

I see 1 and I'm going to do: predict-yes inner elaboration loop at bottom goal.
	--- Change Working Memory (IE) ---

--- END Application Phase ---
--- Output Phase ---
ENV: Agent did: predict-yes for direction L in state State-B
In  State-B moving L
ENV: (next state, see, prediction correct?) = (State-A, 1, True)
predict error 0
dir: dir isR
--- END Output Phase ---
-/|--- Input Phase --- 
=>WM: (14250: I2 ^dir R)
=>WM: (14249: I2 ^reward 1)
=>WM: (14248: I2 ^see 1)
=>WM: (14247: N1014 ^status complete)
<=WM: (14235: I2 ^dir L)
<=WM: (14234: I2 ^reward 1)
<=WM: (14233: I2 ^see 0)
=>WM: (14251: I2 ^level-1 L1-root)
<=WM: (14236: I2 ^level-1 R1-root)

--- END Input Phase --- 

--- Proposal Phase ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing rl*prefer*rvt*predict-yes*H0*3*H1*9
 -->
 (S1 ^operator O2027 = 0.617033753614766)
Firing rl*prefer*rvt*predict-no*H0*4*H1*8
 -->
 (S1 ^operator O2028 = 0.4901349546100854)
Firing prefer*rvt*predict-no*H0*4*H1
 -->
Firing prefer*rvt*predict-yes*H0*3*H1
 -->
Firing elaborate*copy-see-to-output-link
 -->
 (I3 ^see 1 +)
Firing elaborate*reward*based*on*reward
 -->
 (R1018 ^value 1 +)
 (R1 ^reward R1018 +)
Firing propose*predict-yes
 -->
 (O2029 ^name predict-yes +)
 (S1 ^operator O2029 +)
Firing propose*predict-no
 -->
 (O2030 ^name predict-no +)
 (S1 ^operator O2030 +)
Firing rl*prefer*rvt*predict-no*H0*4
 -->
 (S1 ^operator O2028 = 0.1269768790760836)
Firing rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O2027 = 0.382932566578948)
Firing prefer*rvt*predict-yes*H0
 -->
Firing prefer*rvt*predict-no*H0
 -->
Firing elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir R +)
 inner elaboration loop at bottom goal.
Retracting elaborate*copy-see-to-output-link
 -->
 (I3 ^see 0 +)
Retracting propose*predict-no
 -->
 (O2028 ^name predict-no +)
 (S1 ^operator O2028 +)
Retracting propose*predict-yes
 -->
 (O2027 ^name predict-yes +)
 (S1 ^operator O2027 +)
Retracting elaborate*reward*based*on*reward
 -->
 (R1017 ^value 1 +)
 (R1 ^reward R1017 +)
Retracting elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir L +)
Retracting rl*prefer*rvt*predict-no*H0*2
 -->
 (S1 ^operator O2028 = 0.2550133872099196)
Retracting rl*prefer*rvt*predict-no*H0*2*H1*10
 -->
 (S1 ^operator O2028 = -0.01194930198035649)
Retracting rl*prefer*rvt*predict-yes*H0*1
 -->
 (S1 ^operator O2027 = 0.5231203326136166)
Retracting rl*prefer*rvt*predict-yes*H0*1*H1*22
 -->
 (S1 ^operator O2027 = 0.4768782315732822)
=>WM: (14259: S1 ^operator O2030 +)
=>WM: (14258: S1 ^operator O2029 +)
=>WM: (14257: I3 ^dir R)
=>WM: (14256: O2030 ^name predict-no)
=>WM: (14255: O2029 ^name predict-yes)
=>WM: (14254: R1018 ^value 1)
=>WM: (14253: R1 ^reward R1018)
=>WM: (14252: I3 ^see 1)
<=WM: (14243: S1 ^operator O2027 +)
<=WM: (14245: S1 ^operator O2027)
<=WM: (14244: S1 ^operator O2028 +)
<=WM: (14242: I3 ^dir L)
<=WM: (14238: R1 ^reward R1017)
<=WM: (14237: I3 ^see 0)
<=WM: (14241: O2028 ^name predict-no)
<=WM: (14240: O2027 ^name predict-yes)
<=WM: (14239: R1017 ^value 1)

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing prefer*rvt*predict-yes*H0
 -->
Firing rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O2029 = 0.382932566578948)
Firing prefer*rvt*predict-yes*H0*3*H1
 -->
Firing rl*prefer*rvt*predict-yes*H0*3*H1*9
 -->
 (S1 ^operator O2029 = 0.617033753614766)
Firing prefer*rvt*predict-no*H0
 -->
Firing rl*prefer*rvt*predict-no*H0*4
 -->
 (S1 ^operator O2030 = 0.1269768790760836)
Firing prefer*rvt*predict-no*H0*4*H1
 -->
Firing rl*prefer*rvt*predict-no*H0*4*H1*8
 -->
 (S1 ^operator O2030 = 0.4901349546100854)
 inner elaboration loop at bottom goal.
Retracting rl*prefer*rvt*predict-no*H0*4
 -->
 (S1 ^operator O2028 = 0.1269768790760836)
Retracting rl*prefer*rvt*predict-no*H0*4*H1*8
 -->
 (S1 ^operator O2028 = 0.4901349546100854)
Retracting rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O2027 = 0.382932566578948)
Retracting rl*prefer*rvt*predict-yes*H0*3*H1*9
 -->
 (S1 ^operator O2027 = 0.617033753614766)

--- END Proposal Phase ---

--- Decision Phase ---
RL update rl*prefer*rvt*predict-yes*H0*1 0.72796 -0.20484 0.52312 -> 0.727961 -0.20484 0.523121(R,m,v=1,0.979167,0.020542)
RL update rl*prefer*rvt*predict-yes*H0*1*H1*22 0.272038 0.20484 0.476878 -> 0.272038 0.20484 0.476878(R,m,v=1,1,0)
=>WM: (14260: S1 ^operator O2029)

  1015:    O: O2029 (predict-yes)
--- END Decision Phase ---

--- Application Phase ---
	--- Firing Productions (PE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing apply*operator
 -->
 (I3 ^predict-yes N1015 +  :O )
Firing apply*operator*complete
 -->
 (I3 ^predict-yes N1014 -  :O )
 inner elaboration loop at bottom goal.
	--- Change Working Memory (PE) ---
=>WM: (14261: I3 ^predict-yes N1015)
<=WM: (14247: N1014 ^status complete)
<=WM: (14246: I3 ^predict-yes N1014)
	--- Firing Productions (IE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing monitor*world
 -->

I see 1 and I'm going to do: predict-yes inner elaboration loop at bottom goal.
	--- Change Working Memory (IE) ---

--- END Application Phase ---
--- Output Phase ---
ENV: Agent did: predict-yes for direction R in state State-A
In  State-A moving R
ENV: (next state, see, prediction correct?) = (State-B, 1, True)
predict error 0
dir: dir isR
--- END Output Phase ---
\--- Input Phase --- 
=>WM: (14265: I2 ^dir R)
=>WM: (14264: I2 ^reward 1)
=>WM: (14263: I2 ^see 1)
=>WM: (14262: N1015 ^status complete)
<=WM: (14250: I2 ^dir R)
<=WM: (14249: I2 ^reward 1)
<=WM: (14248: I2 ^see 1)
=>WM: (14266: I2 ^level-1 R1-root)
<=WM: (14251: I2 ^level-1 L1-root)

--- END Input Phase --- 

--- Proposal Phase ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing rl*prefer*rvt*predict-yes*H0*3*H1*16
 -->
 (S1 ^operator O2029 = 0.08783148430849691)
Firing rl*prefer*rvt*predict-no*H0*4*H1*15
 -->
 (S1 ^operator O2030 = 0.8730233883813352)
Firing prefer*rvt*predict-no*H0*4*H1
 -->
Firing prefer*rvt*predict-yes*H0*3*H1
 -->
Firing elaborate*copy-see-to-output-link
 -->
 (I3 ^see 1 +)
Firing elaborate*reward*based*on*reward
 -->
 (R1019 ^value 1 +)
 (R1 ^reward R1019 +)
Firing propose*predict-yes
 -->
 (O2031 ^name predict-yes +)
 (S1 ^operator O2031 +)
Firing propose*predict-no
 -->
 (O2032 ^name predict-no +)
 (S1 ^operator O2032 +)
Firing rl*prefer*rvt*predict-no*H0*4
 -->
 (S1 ^operator O2030 = 0.1269768790760836)
Firing rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O2029 = 0.382932566578948)
Firing prefer*rvt*predict-yes*H0
 -->
Firing prefer*rvt*predict-no*H0
 -->
Firing elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir R +)
 inner elaboration loop at bottom goal.
Retracting elaborate*copy-see-to-output-link
 -->
 (I3 ^see 1 +)
Retracting propose*predict-no
 -->
 (O2030 ^name predict-no +)
 (S1 ^operator O2030 +)
Retracting propose*predict-yes
 -->
 (O2029 ^name predict-yes +)
 (S1 ^operator O2029 +)
Retracting elaborate*reward*based*on*reward
 -->
 (R1018 ^value 1 +)
 (R1 ^reward R1018 +)
Retracting elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir R +)
Retracting rl*prefer*rvt*predict-no*H0*4*H1*8
 -->
 (S1 ^operator O2030 = 0.4901349546100854)
Retracting rl*prefer*rvt*predict-no*H0*4
 -->
 (S1 ^operator O2030 = 0.1269768790760836)
Retracting rl*prefer*rvt*predict-yes*H0*3*H1*9
 -->
 (S1 ^operator O2029 = 0.617033753614766)
Retracting rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O2029 = 0.382932566578948)
=>WM: (14272: S1 ^operator O2032 +)
=>WM: (14271: S1 ^operator O2031 +)
=>WM: (14270: O2032 ^name predict-no)
=>WM: (14269: O2031 ^name predict-yes)
=>WM: (14268: R1019 ^value 1)
=>WM: (14267: R1 ^reward R1019)
<=WM: (14258: S1 ^operator O2029 +)
<=WM: (14260: S1 ^operator O2029)
<=WM: (14259: S1 ^operator O2030 +)
<=WM: (14253: R1 ^reward R1018)
<=WM: (14256: O2030 ^name predict-no)
<=WM: (14255: O2029 ^name predict-yes)
<=WM: (14254: R1018 ^value 1)

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing prefer*rvt*predict-yes*H0
 -->
Firing rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O2031 = 0.382932566578948)
Firing prefer*rvt*predict-yes*H0*3*H1
 -->
Firing rl*prefer*rvt*predict-yes*H0*3*H1*16
 -->
 (S1 ^operator O2031 = 0.08783148430849691)
Firing prefer*rvt*predict-no*H0
 -->
Firing rl*prefer*rvt*predict-no*H0*4
 -->
 (S1 ^operator O2032 = 0.1269768790760836)
Firing prefer*rvt*predict-no*H0*4*H1
 -->
Firing rl*prefer*rvt*predict-no*H0*4*H1*15
 -->
 (S1 ^operator O2032 = 0.8730233883813352)
 inner elaboration loop at bottom goal.
Retracting rl*prefer*rvt*predict-no*H0*4
 -->
 (S1 ^operator O2030 = 0.1269768790760836)
Retracting rl*prefer*rvt*predict-no*H0*4*H1*15
 -->
 (S1 ^operator O2030 = 0.8730233883813352)
Retracting rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O2029 = 0.382932566578948)
Retracting rl*prefer*rvt*predict-yes*H0*3*H1*16
 -->
 (S1 ^operator O2029 = 0.08783148430849691)

--- END Proposal Phase ---

--- Decision Phase ---
RL update rl*prefer*rvt*predict-yes*H0*3 0.673126 -0.290194 0.382933 -> 0.673131 -0.290193 0.382938(R,m,v=1,0.96129,0.0374529)
RL update rl*prefer*rvt*predict-yes*H0*3*H1*9 0.326843 0.290191 0.617034 -> 0.326848 0.290191 0.617039(R,m,v=1,1,0)
=>WM: (14273: S1 ^operator O2032)

  1016:    O: O2032 (predict-no)
--- END Decision Phase ---

--- Application Phase ---
	--- Firing Productions (PE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing apply*operator
 -->
 (I3 ^predict-no N1016 +  :O )
Firing apply*operator*complete
 -->
 (I3 ^predict-yes N1015 -  :O )
 inner elaboration loop at bottom goal.
	--- Change Working Memory (PE) ---
=>WM: (14274: I3 ^predict-no N1016)
<=WM: (14262: N1015 ^status complete)
<=WM: (14261: I3 ^predict-yes N1015)
	--- Firing Productions (IE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing monitor*world
 -->

I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
	--- Change Working Memory (IE) ---

--- END Application Phase ---
--- Output Phase ---
ENV: Agent did: predict-no for direction R in state State-B
In  State-B moving R
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isL
--- END Output Phase ---
-/|--- Input Phase --- 
=>WM: (14278: I2 ^dir L)
=>WM: (14277: I2 ^reward 1)
=>WM: (14276: I2 ^see 0)
=>WM: (14275: N1016 ^status complete)
<=WM: (14265: I2 ^dir R)
<=WM: (14264: I2 ^reward 1)
<=WM: (14263: I2 ^see 1)
=>WM: (14279: I2 ^level-1 R0-root)
<=WM: (14266: I2 ^level-1 R1-root)

--- END Input Phase --- 

--- Proposal Phase ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing rl*prefer*rvt*predict-yes*H0*1*H1*19
 -->
 (S1 ^operator O2031 = 0.476882807646731)
Firing rl*prefer*rvt*predict-no*H0*2*H1*7
 -->
 (S1 ^operator O2032 = 0.1700769046561409)
Firing prefer*rvt*predict-no*H0*2*H1
 -->
Firing prefer*rvt*predict-yes*H0*1*H1
 -->
Firing elaborate*copy-see-to-output-link
 -->
 (I3 ^see 0 +)
Firing elaborate*reward*based*on*reward
 -->
 (R1020 ^value 1 +)
 (R1 ^reward R1020 +)
Firing propose*predict-yes
 -->
 (O2033 ^name predict-yes +)
 (S1 ^operator O2033 +)
Firing propose*predict-no
 -->
 (O2034 ^name predict-no +)
 (S1 ^operator O2034 +)
Firing rl*prefer*rvt*predict-no*H0*2
 -->
 (S1 ^operator O2032 = 0.2550133872099196)
Firing rl*prefer*rvt*predict-yes*H0*1
 -->
 (S1 ^operator O2031 = 0.5231205479855817)
Firing prefer*rvt*predict-yes*H0
 -->
Firing prefer*rvt*predict-no*H0
 -->
Firing elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir L +)
 inner elaboration loop at bottom goal.
Retracting elaborate*copy-see-to-output-link
 -->
 (I3 ^see 1 +)
Retracting propose*predict-no
 -->
 (O2032 ^name predict-no +)
 (S1 ^operator O2032 +)
Retracting propose*predict-yes
 -->
 (O2031 ^name predict-yes +)
 (S1 ^operator O2031 +)
Retracting elaborate*reward*based*on*reward
 -->
 (R1019 ^value 1 +)
 (R1 ^reward R1019 +)
Retracting elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir R +)
Retracting rl*prefer*rvt*predict-no*H0*4*H1*15
 -->
 (S1 ^operator O2032 = 0.8730233883813352)
Retracting rl*prefer*rvt*predict-no*H0*4
 -->
 (S1 ^operator O2032 = 0.1269768790760836)
Retracting rl*prefer*rvt*predict-yes*H0*3*H1*16
 -->
 (S1 ^operator O2031 = 0.08783148430849691)
Retracting rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O2031 = 0.3829376185498909)
=>WM: (14287: S1 ^operator O2034 +)
=>WM: (14286: S1 ^operator O2033 +)
=>WM: (14285: I3 ^dir L)
=>WM: (14284: O2034 ^name predict-no)
=>WM: (14283: O2033 ^name predict-yes)
=>WM: (14282: R1020 ^value 1)
=>WM: (14281: R1 ^reward R1020)
=>WM: (14280: I3 ^see 0)
<=WM: (14271: S1 ^operator O2031 +)
<=WM: (14272: S1 ^operator O2032 +)
<=WM: (14273: S1 ^operator O2032)
<=WM: (14257: I3 ^dir R)
<=WM: (14267: R1 ^reward R1019)
<=WM: (14252: I3 ^see 1)
<=WM: (14270: O2032 ^name predict-no)
<=WM: (14269: O2031 ^name predict-yes)
<=WM: (14268: R1019 ^value 1)

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing prefer*rvt*predict-yes*H0
 -->
Firing rl*prefer*rvt*predict-yes*H0*1
 -->
 (S1 ^operator O2033 = 0.5231205479855817)
Firing prefer*rvt*predict-yes*H0*1*H1
 -->
Firing rl*prefer*rvt*predict-yes*H0*1*H1*19
 -->
 (S1 ^operator O2033 = 0.476882807646731)
Firing prefer*rvt*predict-no*H0
 -->
Firing rl*prefer*rvt*predict-no*H0*2
 -->
 (S1 ^operator O2034 = 0.2550133872099196)
Firing prefer*rvt*predict-no*H0*2*H1
 -->
Firing rl*prefer*rvt*predict-no*H0*2*H1*7
 -->
 (S1 ^operator O2034 = 0.1700769046561409)
 inner elaboration loop at bottom goal.
Retracting rl*prefer*rvt*predict-no*H0*2
 -->
 (S1 ^operator O2032 = 0.2550133872099196)
Retracting rl*prefer*rvt*predict-no*H0*2*H1*7
 -->
 (S1 ^operator O2032 = 0.1700769046561409)
Retracting rl*prefer*rvt*predict-yes*H0*1
 -->
 (S1 ^operator O2031 = 0.5231205479855817)
Retracting rl*prefer*rvt*predict-yes*H0*1*H1*19
 -->
 (S1 ^operator O2031 = 0.476882807646731)

--- END Proposal Phase ---

--- Decision Phase ---
RL update rl*prefer*rvt*predict-no*H0*4 0.814714 -0.687737 0.126977 -> 0.814714 -0.687737 0.126977(R,m,v=1,0.949721,0.0480196)
RL update rl*prefer*rvt*predict-no*H0*4*H1*15 0.185286 0.687737 0.873023 -> 0.185286 0.687737 0.873023(R,m,v=1,1,0)
=>WM: (14288: S1 ^operator O2033)

  1017:    O: O2033 (predict-yes)
--- END Decision Phase ---

--- Application Phase ---
	--- Firing Productions (PE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing apply*operator
 -->
 (I3 ^predict-yes N1017 +  :O )
Firing apply*operator*complete
 -->
 (I3 ^predict-no N1016 -  :O )
 inner elaboration loop at bottom goal.
	--- Change Working Memory (PE) ---
=>WM: (14289: I3 ^predict-yes N1017)
<=WM: (14275: N1016 ^status complete)
<=WM: (14274: I3 ^predict-no N1016)
	--- Firing Productions (IE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing monitor*world
 -->

I see 1 and I'm going to do: predict-yes inner elaboration loop at bottom goal.
	--- Change Working Memory (IE) ---

--- END Application Phase ---
--- Output Phase ---
ENV: Agent did: predict-yes for direction L in state State-B
In  State-B moving L
ENV: (next state, see, prediction correct?) = (State-A, 1, True)
predict error 0
dir: dir isR
--- END Output Phase ---
\-/--- Input Phase --- 
=>WM: (14293: I2 ^dir R)
=>WM: (14292: I2 ^reward 1)
=>WM: (14291: I2 ^see 1)
=>WM: (14290: N1017 ^status complete)
<=WM: (14278: I2 ^dir L)
<=WM: (14277: I2 ^reward 1)
<=WM: (14276: I2 ^see 0)
=>WM: (14294: I2 ^level-1 L1-root)
<=WM: (14279: I2 ^level-1 R0-root)

--- END Input Phase --- 

--- Proposal Phase ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing rl*prefer*rvt*predict-yes*H0*3*H1*9
 -->
 (S1 ^operator O2033 = 0.6170388055857089)
Firing rl*prefer*rvt*predict-no*H0*4*H1*8
 -->
 (S1 ^operator O2034 = 0.4901349546100854)
Firing prefer*rvt*predict-no*H0*4*H1
 -->
Firing prefer*rvt*predict-yes*H0*3*H1
 -->
Firing elaborate*copy-see-to-output-link
 -->
 (I3 ^see 1 +)
Firing elaborate*reward*based*on*reward
 -->
 (R1021 ^value 1 +)
 (R1 ^reward R1021 +)
Firing propose*predict-yes
 -->
 (O2035 ^name predict-yes +)
 (S1 ^operator O2035 +)
Firing propose*predict-no
 -->
 (O2036 ^name predict-no +)
 (S1 ^operator O2036 +)
Firing rl*prefer*rvt*predict-no*H0*4
 -->
 (S1 ^operator O2034 = 0.1269768389574707)
Firing rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O2033 = 0.3829376185498909)
Firing prefer*rvt*predict-yes*H0
 -->
Firing prefer*rvt*predict-no*H0
 -->
Firing elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir R +)
 inner elaboration loop at bottom goal.
Retracting elaborate*copy-see-to-output-link
 -->
 (I3 ^see 0 +)
Retracting propose*predict-no
 -->
 (O2034 ^name predict-no +)
 (S1 ^operator O2034 +)
Retracting propose*predict-yes
 -->
 (O2033 ^name predict-yes +)
 (S1 ^operator O2033 +)
Retracting elaborate*reward*based*on*reward
 -->
 (R1020 ^value 1 +)
 (R1 ^reward R1020 +)
Retracting elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir L +)
Retracting rl*prefer*rvt*predict-no*H0*2*H1*7
 -->
 (S1 ^operator O2034 = 0.1700769046561409)
Retracting rl*prefer*rvt*predict-no*H0*2
 -->
 (S1 ^operator O2034 = 0.2550133872099196)
Retracting rl*prefer*rvt*predict-yes*H0*1*H1*19
 -->
 (S1 ^operator O2033 = 0.476882807646731)
Retracting rl*prefer*rvt*predict-yes*H0*1
 -->
 (S1 ^operator O2033 = 0.5231205479855817)
=>WM: (14302: S1 ^operator O2036 +)
=>WM: (14301: S1 ^operator O2035 +)
=>WM: (14300: I3 ^dir R)
=>WM: (14299: O2036 ^name predict-no)
=>WM: (14298: O2035 ^name predict-yes)
=>WM: (14297: R1021 ^value 1)
=>WM: (14296: R1 ^reward R1021)
=>WM: (14295: I3 ^see 1)
<=WM: (14286: S1 ^operator O2033 +)
<=WM: (14288: S1 ^operator O2033)
<=WM: (14287: S1 ^operator O2034 +)
<=WM: (14285: I3 ^dir L)
<=WM: (14281: R1 ^reward R1020)
<=WM: (14280: I3 ^see 0)
<=WM: (14284: O2034 ^name predict-no)
<=WM: (14283: O2033 ^name predict-yes)
<=WM: (14282: R1020 ^value 1)

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing prefer*rvt*predict-yes*H0
 -->
Firing rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O2035 = 0.3829376185498909)
Firing prefer*rvt*predict-yes*H0*3*H1
 -->
Firing rl*prefer*rvt*predict-yes*H0*3*H1*9
 -->
 (S1 ^operator O2035 = 0.6170388055857089)
Firing prefer*rvt*predict-no*H0
 -->
Firing rl*prefer*rvt*predict-no*H0*4
 -->
 (S1 ^operator O2036 = 0.1269768389574707)
Firing prefer*rvt*predict-no*H0*4*H1
 -->
Firing rl*prefer*rvt*predict-no*H0*4*H1*8
 -->
 (S1 ^operator O2036 = 0.4901349546100854)
 inner elaboration loop at bottom goal.
Retracting rl*prefer*rvt*predict-no*H0*4
 -->
 (S1 ^operator O2034 = 0.1269768389574707)
Retracting rl*prefer*rvt*predict-no*H0*4*H1*8
 -->
 (S1 ^operator O2034 = 0.4901349546100854)
Retracting rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O2033 = 0.3829376185498909)
Retracting rl*prefer*rvt*predict-yes*H0*3*H1*9
 -->
 (S1 ^operator O2033 = 0.6170388055857089)

--- END Proposal Phase ---

--- Decision Phase ---
RL update rl*prefer*rvt*predict-yes*H0*1 0.727961 -0.20484 0.523121 -> 0.72796 -0.20484 0.52312(R,m,v=1,0.97931,0.0204023)
RL update rl*prefer*rvt*predict-yes*H0*1*H1*19 0.272044 0.204839 0.476883 -> 0.272043 0.204839 0.476882(R,m,v=1,1,0)
=>WM: (14303: S1 ^operator O2035)

  1018:    O: O2035 (predict-yes)
--- END Decision Phase ---

--- Application Phase ---
	--- Firing Productions (PE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing apply*operator
 -->
 (I3 ^predict-yes N1018 +  :O )
Firing apply*operator*complete
 -->
 (I3 ^predict-yes N1017 -  :O )
 inner elaboration loop at bottom goal.
	--- Change Working Memory (PE) ---
=>WM: (14304: I3 ^predict-yes N1018)
<=WM: (14290: N1017 ^status complete)
<=WM: (14289: I3 ^predict-yes N1017)
	--- Firing Productions (IE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing monitor*world
 -->

I see 1 and I'm going to do: predict-yes inner elaboration loop at bottom goal.
	--- Change Working Memory (IE) ---

--- END Application Phase ---
--- Output Phase ---
ENV: Agent did: predict-yes for direction R in state State-A
In  State-A moving R
ENV: (next state, see, prediction correct?) = (State-B, 1, True)
predict error 0
dir: dir isL
--- END Output Phase ---
|\---- Input Phase --- 
=>WM: (14308: I2 ^dir L)
=>WM: (14307: I2 ^reward 1)
=>WM: (14306: I2 ^see 1)
=>WM: (14305: N1018 ^status complete)
<=WM: (14293: I2 ^dir R)
<=WM: (14292: I2 ^reward 1)
<=WM: (14291: I2 ^see 1)
=>WM: (14309: I2 ^level-1 R1-root)
<=WM: (14294: I2 ^level-1 L1-root)

--- END Input Phase --- 

--- Proposal Phase ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing rl*prefer*rvt*predict-yes*H0*1*H1*22
 -->
 (S1 ^operator O2035 = 0.4768784469452474)
Firing rl*prefer*rvt*predict-no*H0*2*H1*10
 -->
 (S1 ^operator O2036 = -0.01194930198035649)
Firing prefer*rvt*predict-no*H0*2*H1
 -->
Firing prefer*rvt*predict-yes*H0*1*H1
 -->
Firing elaborate*copy-see-to-output-link
 -->
 (I3 ^see 1 +)
Firing elaborate*reward*based*on*reward
 -->
 (R1022 ^value 1 +)
 (R1 ^reward R1022 +)
Firing propose*predict-yes
 -->
 (O2037 ^name predict-yes +)
 (S1 ^operator O2037 +)
Firing propose*predict-no
 -->
 (O2038 ^name predict-no +)
 (S1 ^operator O2038 +)
Firing rl*prefer*rvt*predict-no*H0*2
 -->
 (S1 ^operator O2036 = 0.2550133872099196)
Firing rl*prefer*rvt*predict-yes*H0*1
 -->
 (S1 ^operator O2035 = 0.5231200446407348)
Firing prefer*rvt*predict-yes*H0
 -->
Firing prefer*rvt*predict-no*H0
 -->
Firing elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir L +)
 inner elaboration loop at bottom goal.
Retracting elaborate*copy-see-to-output-link
 -->
 (I3 ^see 1 +)
Retracting propose*predict-no
 -->
 (O2036 ^name predict-no +)
 (S1 ^operator O2036 +)
Retracting propose*predict-yes
 -->
 (O2035 ^name predict-yes +)
 (S1 ^operator O2035 +)
Retracting elaborate*reward*based*on*reward
 -->
 (R1021 ^value 1 +)
 (R1 ^reward R1021 +)
Retracting elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir R +)
Retracting rl*prefer*rvt*predict-no*H0*4*H1*8
 -->
 (S1 ^operator O2036 = 0.4901349546100854)
Retracting rl*prefer*rvt*predict-no*H0*4
 -->
 (S1 ^operator O2036 = 0.1269768389574707)
Retracting rl*prefer*rvt*predict-yes*H0*3*H1*9
 -->
 (S1 ^operator O2035 = 0.6170388055857089)
Retracting rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O2035 = 0.3829376185498909)
=>WM: (14316: S1 ^operator O2038 +)
=>WM: (14315: S1 ^operator O2037 +)
=>WM: (14314: I3 ^dir L)
=>WM: (14313: O2038 ^name predict-no)
=>WM: (14312: O2037 ^name predict-yes)
=>WM: (14311: R1022 ^value 1)
=>WM: (14310: R1 ^reward R1022)
<=WM: (14301: S1 ^operator O2035 +)
<=WM: (14303: S1 ^operator O2035)
<=WM: (14302: S1 ^operator O2036 +)
<=WM: (14300: I3 ^dir R)
<=WM: (14296: R1 ^reward R1021)
<=WM: (14299: O2036 ^name predict-no)
<=WM: (14298: O2035 ^name predict-yes)
<=WM: (14297: R1021 ^value 1)

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing prefer*rvt*predict-yes*H0
 -->
Firing rl*prefer*rvt*predict-yes*H0*1
 -->
 (S1 ^operator O2037 = 0.5231200446407348)
Firing prefer*rvt*predict-yes*H0*1*H1
 -->
Firing rl*prefer*rvt*predict-yes*H0*1*H1*22
 -->
 (S1 ^operator O2037 = 0.4768784469452474)
Firing prefer*rvt*predict-no*H0
 -->
Firing rl*prefer*rvt*predict-no*H0*2
 -->
 (S1 ^operator O2038 = 0.2550133872099196)
Firing prefer*rvt*predict-no*H0*2*H1
 -->
Firing rl*prefer*rvt*predict-no*H0*2*H1*10
 -->
 (S1 ^operator O2038 = -0.01194930198035649)
 inner elaboration loop at bottom goal.
Retracting rl*prefer*rvt*predict-no*H0*2
 -->
 (S1 ^operator O2036 = 0.2550133872099196)
Retracting rl*prefer*rvt*predict-no*H0*2*H1*10
 -->
 (S1 ^operator O2036 = -0.01194930198035649)
Retracting rl*prefer*rvt*predict-yes*H0*1
 -->
 (S1 ^operator O2035 = 0.5231200446407348)
Retracting rl*prefer*rvt*predict-yes*H0*1*H1*22
 -->
 (S1 ^operator O2035 = 0.4768784469452474)

--- END Proposal Phase ---

--- Decision Phase ---
RL update rl*prefer*rvt*predict-yes*H0*3 0.673131 -0.290193 0.382938 -> 0.673134 -0.290193 0.382941(R,m,v=1,0.961538,0.0372208)
RL update rl*prefer*rvt*predict-yes*H0*3*H1*9 0.326848 0.290191 0.617039 -> 0.326851 0.290192 0.617042(R,m,v=1,1,0)
=>WM: (14317: S1 ^operator O2037)

  1019:    O: O2037 (predict-yes)
--- END Decision Phase ---

--- Application Phase ---
	--- Firing Productions (PE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing apply*operator
 -->
 (I3 ^predict-yes N1019 +  :O )
Firing apply*operator*complete
 -->
 (I3 ^predict-yes N1018 -  :O )
 inner elaboration loop at bottom goal.
	--- Change Working Memory (PE) ---
=>WM: (14318: I3 ^predict-yes N1019)
<=WM: (14305: N1018 ^status complete)
<=WM: (14304: I3 ^predict-yes N1018)
	--- Firing Productions (IE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing monitor*world
 -->

I see 1 and I'm going to do: predict-yes inner elaboration loop at bottom goal.
	--- Change Working Memory (IE) ---

--- END Application Phase ---
--- Output Phase ---
ENV: Agent did: predict-yes for direction L in state State-B
In  State-B moving L
ENV: (next state, see, prediction correct?) = (State-A, 1, True)
predict error 0
dir: dir isR
--- END Output Phase ---
/|--- Input Phase --- 
=>WM: (14322: I2 ^dir R)
=>WM: (14321: I2 ^reward 1)
=>WM: (14320: I2 ^see 1)
=>WM: (14319: N1019 ^status complete)
<=WM: (14308: I2 ^dir L)
<=WM: (14307: I2 ^reward 1)
<=WM: (14306: I2 ^see 1)
=>WM: (14323: I2 ^level-1 L1-root)
<=WM: (14309: I2 ^level-1 R1-root)

--- END Input Phase --- 

--- Proposal Phase ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing rl*prefer*rvt*predict-yes*H0*3*H1*9
 -->
 (S1 ^operator O2037 = 0.617042341965369)
Firing rl*prefer*rvt*predict-no*H0*4*H1*8
 -->
 (S1 ^operator O2038 = 0.4901349546100854)
Firing prefer*rvt*predict-no*H0*4*H1
 -->
Firing prefer*rvt*predict-yes*H0*3*H1
 -->
Firing elaborate*copy-see-to-output-link
 -->
 (I3 ^see 1 +)
Firing elaborate*reward*based*on*reward
 -->
 (R1023 ^value 1 +)
 (R1 ^reward R1023 +)
Firing propose*predict-yes
 -->
 (O2039 ^name predict-yes +)
 (S1 ^operator O2039 +)
Firing propose*predict-no
 -->
 (O2040 ^name predict-no +)
 (S1 ^operator O2040 +)
Firing rl*prefer*rvt*predict-no*H0*4
 -->
 (S1 ^operator O2038 = 0.1269768389574707)
Firing rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O2037 = 0.3829411549295509)
Firing prefer*rvt*predict-yes*H0
 -->
Firing prefer*rvt*predict-no*H0
 -->
Firing elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir R +)
 inner elaboration loop at bottom goal.
Retracting elaborate*copy-see-to-output-link
 -->
 (I3 ^see 1 +)
Retracting propose*predict-no
 -->
 (O2038 ^name predict-no +)
 (S1 ^operator O2038 +)
Retracting propose*predict-yes
 -->
 (O2037 ^name predict-yes +)
 (S1 ^operator O2037 +)
Retracting elaborate*reward*based*on*reward
 -->
 (R1022 ^value 1 +)
 (R1 ^reward R1022 +)
Retracting elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir L +)
Retracting rl*prefer*rvt*predict-no*H0*2*H1*10
 -->
 (S1 ^operator O2038 = -0.01194930198035649)
Retracting rl*prefer*rvt*predict-no*H0*2
 -->
 (S1 ^operator O2038 = 0.2550133872099196)
Retracting rl*prefer*rvt*predict-yes*H0*1*H1*22
 -->
 (S1 ^operator O2037 = 0.4768784469452474)
Retracting rl*prefer*rvt*predict-yes*H0*1
 -->
 (S1 ^operator O2037 = 0.5231200446407348)
=>WM: (14330: S1 ^operator O2040 +)
=>WM: (14329: S1 ^operator O2039 +)
=>WM: (14328: I3 ^dir R)
=>WM: (14327: O2040 ^name predict-no)
=>WM: (14326: O2039 ^name predict-yes)
=>WM: (14325: R1023 ^value 1)
=>WM: (14324: R1 ^reward R1023)
<=WM: (14315: S1 ^operator O2037 +)
<=WM: (14317: S1 ^operator O2037)
<=WM: (14316: S1 ^operator O2038 +)
<=WM: (14314: I3 ^dir L)
<=WM: (14310: R1 ^reward R1022)
<=WM: (14313: O2038 ^name predict-no)
<=WM: (14312: O2037 ^name predict-yes)
<=WM: (14311: R1022 ^value 1)

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing prefer*rvt*predict-yes*H0
 -->
Firing rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O2039 = 0.3829411549295509)
Firing prefer*rvt*predict-yes*H0*3*H1
 -->
Firing rl*prefer*rvt*predict-yes*H0*3*H1*9
 -->
 (S1 ^operator O2039 = 0.617042341965369)
Firing prefer*rvt*predict-no*H0
 -->
Firing rl*prefer*rvt*predict-no*H0*4
 -->
 (S1 ^operator O2040 = 0.1269768389574707)
Firing prefer*rvt*predict-no*H0*4*H1
 -->
Firing rl*prefer*rvt*predict-no*H0*4*H1*8
 -->
 (S1 ^operator O2040 = 0.4901349546100854)
 inner elaboration loop at bottom goal.
Retracting rl*prefer*rvt*predict-no*H0*4
 -->
 (S1 ^operator O2038 = 0.1269768389574707)
Retracting rl*prefer*rvt*predict-no*H0*4*H1*8
 -->
 (S1 ^operator O2038 = 0.4901349546100854)
Retracting rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O2037 = 0.3829411549295509)
Retracting rl*prefer*rvt*predict-yes*H0*3*H1*9
 -->
 (S1 ^operator O2037 = 0.617042341965369)

--- END Proposal Phase ---

--- Decision Phase ---
RL update rl*prefer*rvt*predict-yes*H0*1 0.72796 -0.20484 0.52312 -> 0.72796 -0.20484 0.52312(R,m,v=1,0.979452,0.0202645)
RL update rl*prefer*rvt*predict-yes*H0*1*H1*22 0.272038 0.20484 0.476878 -> 0.272038 0.20484 0.476879(R,m,v=1,1,0)
=>WM: (14331: S1 ^operator O2039)

  1020:    O: O2039 (predict-yes)
--- END Decision Phase ---

--- Application Phase ---
	--- Firing Productions (PE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing apply*operator
 -->
 (I3 ^predict-yes N1020 +  :O )
Firing apply*operator*complete
 -->
 (I3 ^predict-yes N1019 -  :O )
 inner elaboration loop at bottom goal.
	--- Change Working Memory (PE) ---
=>WM: (14332: I3 ^predict-yes N1020)
<=WM: (14319: N1019 ^status complete)
<=WM: (14318: I3 ^predict-yes N1019)
	--- Firing Productions (IE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing monitor*world
 -->

I see 1 and I'm going to do: predict-yes inner elaboration loop at bottom goal.
	--- Change Working Memory (IE) ---

--- END Application Phase ---
--- Output Phase ---
ENV: Agent did: predict-yes for direction R in state State-A
In  State-A moving R
ENV: (next state, see, prediction correct?) = (State-B, 1, True)
predict error 0
dir: dir isR
--- END Output Phase ---
\--- Input Phase --- 
=>WM: (14336: I2 ^dir R)
=>WM: (14335: I2 ^reward 1)
=>WM: (14334: I2 ^see 1)
=>WM: (14333: N1020 ^status complete)
<=WM: (14322: I2 ^dir R)
<=WM: (14321: I2 ^reward 1)
<=WM: (14320: I2 ^see 1)
=>WM: (14337: I2 ^level-1 R1-root)
<=WM: (14323: I2 ^level-1 L1-root)

--- END Input Phase --- 

--- Proposal Phase ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing rl*prefer*rvt*predict-yes*H0*3*H1*16
 -->
 (S1 ^operator O2039 = 0.08783148430849691)
Firing rl*prefer*rvt*predict-no*H0*4*H1*15
 -->
 (S1 ^operator O2040 = 0.8730233482627223)
Firing prefer*rvt*predict-no*H0*4*H1
 -->
Firing prefer*rvt*predict-yes*H0*3*H1
 -->
Firing elaborate*copy-see-to-output-link
 -->
 (I3 ^see 1 +)
Firing elaborate*reward*based*on*reward
 -->
 (R1024 ^value 1 +)
 (R1 ^reward R1024 +)
Firing propose*predict-yes
 -->
 (O2041 ^name predict-yes +)
 (S1 ^operator O2041 +)
Firing propose*predict-no
 -->
 (O2042 ^name predict-no +)
 (S1 ^operator O2042 +)
Firing rl*prefer*rvt*predict-no*H0*4
 -->
 (S1 ^operator O2040 = 0.1269768389574707)
Firing rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O2039 = 0.3829411549295509)
Firing prefer*rvt*predict-yes*H0
 -->
Firing prefer*rvt*predict-no*H0
 -->
Firing elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir R +)
 inner elaboration loop at bottom goal.
Retracting elaborate*copy-see-to-output-link
 -->
 (I3 ^see 1 +)
Retracting propose*predict-no
 -->
 (O2040 ^name predict-no +)
 (S1 ^operator O2040 +)
Retracting propose*predict-yes
 -->
 (O2039 ^name predict-yes +)
 (S1 ^operator O2039 +)
Retracting elaborate*reward*based*on*reward
 -->
 (R1023 ^value 1 +)
 (R1 ^reward R1023 +)
Retracting elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir R +)
Retracting rl*prefer*rvt*predict-no*H0*4*H1*8
 -->
 (S1 ^operator O2040 = 0.4901349546100854)
Retracting rl*prefer*rvt*predict-no*H0*4
 -->
 (S1 ^operator O2040 = 0.1269768389574707)
Retracting rl*prefer*rvt*predict-yes*H0*3*H1*9
 -->
 (S1 ^operator O2039 = 0.617042341965369)
Retracting rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O2039 = 0.3829411549295509)
=>WM: (14343: S1 ^operator O2042 +)
=>WM: (14342: S1 ^operator O2041 +)
=>WM: (14341: O2042 ^name predict-no)
=>WM: (14340: O2041 ^name predict-yes)
=>WM: (14339: R1024 ^value 1)
=>WM: (14338: R1 ^reward R1024)
<=WM: (14329: S1 ^operator O2039 +)
<=WM: (14331: S1 ^operator O2039)
<=WM: (14330: S1 ^operator O2040 +)
<=WM: (14324: R1 ^reward R1023)
<=WM: (14327: O2040 ^name predict-no)
<=WM: (14326: O2039 ^name predict-yes)
<=WM: (14325: R1023 ^value 1)

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing prefer*rvt*predict-yes*H0
 -->
Firing rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O2041 = 0.3829411549295509)
Firing prefer*rvt*predict-yes*H0*3*H1
 -->
Firing rl*prefer*rvt*predict-yes*H0*3*H1*16
 -->
 (S1 ^operator O2041 = 0.08783148430849691)
Firing prefer*rvt*predict-no*H0
 -->
Firing rl*prefer*rvt*predict-no*H0*4
 -->
 (S1 ^operator O2042 = 0.1269768389574707)
Firing prefer*rvt*predict-no*H0*4*H1
 -->
Firing rl*prefer*rvt*predict-no*H0*4*H1*15
 -->
 (S1 ^operator O2042 = 0.8730233482627223)
 inner elaboration loop at bottom goal.
Retracting rl*prefer*rvt*predict-no*H0*4
 -->
 (S1 ^operator O2040 = 0.1269768389574707)
Retracting rl*prefer*rvt*predict-no*H0*4*H1*15
 -->
 (S1 ^operator O2040 = 0.8730233482627223)
Retracting rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O2039 = 0.3829411549295509)
Retracting rl*prefer*rvt*predict-yes*H0*3*H1*16
 -->
 (S1 ^operator O2039 = 0.08783148430849691)

--- END Proposal Phase ---

--- Decision Phase ---
RL update rl*prefer*rvt*predict-yes*H0*3 0.673134 -0.290193 0.382941 -> 0.673136 -0.290193 0.382944(R,m,v=1,0.961783,0.0369917)
RL update rl*prefer*rvt*predict-yes*H0*3*H1*9 0.326851 0.290192 0.617042 -> 0.326853 0.290192 0.617045(R,m,v=1,1,0)
=>WM: (14344: S1 ^operator O2042)

  1021:    O: O2042 (predict-no)
--- END Decision Phase ---

--- Application Phase ---
	--- Firing Productions (PE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing apply*operator
 -->
 (I3 ^predict-no N1021 +  :O )
Firing apply*operator*complete
 -->
 (I3 ^predict-yes N1020 -  :O )
 inner elaboration loop at bottom goal.
	--- Change Working Memory (PE) ---
=>WM: (14345: I3 ^predict-no N1021)
<=WM: (14333: N1020 ^status complete)
<=WM: (14332: I3 ^predict-yes N1020)
	--- Firing Productions (IE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing monitor*world
 -->

I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
	--- Change Working Memory (IE) ---

--- END Application Phase ---
--- Output Phase ---
ENV: Agent did: predict-no for direction R in state State-B
In  State-B moving R
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isL
--- END Output Phase ---
---- Input Phase --- 
=>WM: (14349: I2 ^dir L)
=>WM: (14348: I2 ^reward 1)
=>WM: (14347: I2 ^see 0)
=>WM: (14346: N1021 ^status complete)
<=WM: (14336: I2 ^dir R)
<=WM: (14335: I2 ^reward 1)
<=WM: (14334: I2 ^see 1)
=>WM: (14350: I2 ^level-1 R0-root)
<=WM: (14337: I2 ^level-1 R1-root)

--- END Input Phase --- 

--- Proposal Phase ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing rl*prefer*rvt*predict-yes*H0*1*H1*19
 -->
 (S1 ^operator O2041 = 0.4768823043018841)
Firing rl*prefer*rvt*predict-no*H0*2*H1*7
 -->
 (S1 ^operator O2042 = 0.1700769046561409)
Firing prefer*rvt*predict-no*H0*2*H1
 -->
Firing prefer*rvt*predict-yes*H0*1*H1
 -->
Firing elaborate*copy-see-to-output-link
 -->
 (I3 ^see 0 +)
Firing elaborate*reward*based*on*reward
 -->
 (R1025 ^value 1 +)
 (R1 ^reward R1025 +)
Firing propose*predict-yes
 -->
 (O2043 ^name predict-yes +)
 (S1 ^operator O2043 +)
Firing propose*predict-no
 -->
 (O2044 ^name predict-no +)
 (S1 ^operator O2044 +)
Firing rl*prefer*rvt*predict-no*H0*2
 -->
 (S1 ^operator O2042 = 0.2550133872099196)
Firing rl*prefer*rvt*predict-yes*H0*1
 -->
 (S1 ^operator O2041 = 0.5231202709028374)
Firing prefer*rvt*predict-yes*H0
 -->
Firing prefer*rvt*predict-no*H0
 -->
Firing elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir L +)
 inner elaboration loop at bottom goal.
Retracting elaborate*copy-see-to-output-link
 -->
 (I3 ^see 1 +)
Retracting propose*predict-no
 -->
 (O2042 ^name predict-no +)
 (S1 ^operator O2042 +)
Retracting propose*predict-yes
 -->
 (O2041 ^name predict-yes +)
 (S1 ^operator O2041 +)
Retracting elaborate*reward*based*on*reward
 -->
 (R1024 ^value 1 +)
 (R1 ^reward R1024 +)
Retracting elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir R +)
Retracting rl*prefer*rvt*predict-no*H0*4*H1*15
 -->
 (S1 ^operator O2042 = 0.8730233482627223)
Retracting rl*prefer*rvt*predict-no*H0*4
 -->
 (S1 ^operator O2042 = 0.1269768389574707)
Retracting rl*prefer*rvt*predict-yes*H0*3*H1*16
 -->
 (S1 ^operator O2041 = 0.08783148430849691)
Retracting rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O2041 = 0.3829436303953129)
=>WM: (14358: S1 ^operator O2044 +)
=>WM: (14357: S1 ^operator O2043 +)
=>WM: (14356: I3 ^dir L)
=>WM: (14355: O2044 ^name predict-no)
=>WM: (14354: O2043 ^name predict-yes)
=>WM: (14353: R1025 ^value 1)
=>WM: (14352: R1 ^reward R1025)
=>WM: (14351: I3 ^see 0)
<=WM: (14342: S1 ^operator O2041 +)
<=WM: (14343: S1 ^operator O2042 +)
<=WM: (14344: S1 ^operator O2042)
<=WM: (14328: I3 ^dir R)
<=WM: (14338: R1 ^reward R1024)
<=WM: (14295: I3 ^see 1)
<=WM: (14341: O2042 ^name predict-no)
<=WM: (14340: O2041 ^name predict-yes)
<=WM: (14339: R1024 ^value 1)

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing prefer*rvt*predict-yes*H0
 -->
Firing rl*prefer*rvt*predict-yes*H0*1
 -->
 (S1 ^operator O2043 = 0.5231202709028374)
Firing prefer*rvt*predict-yes*H0*1*H1
 -->
Firing rl*prefer*rvt*predict-yes*H0*1*H1*19
 -->
 (S1 ^operator O2043 = 0.4768823043018841)
Firing prefer*rvt*predict-no*H0
 -->
Firing rl*prefer*rvt*predict-no*H0*2
 -->
 (S1 ^operator O2044 = 0.2550133872099196)
Firing prefer*rvt*predict-no*H0*2*H1
 -->
Firing rl*prefer*rvt*predict-no*H0*2*H1*7
 -->
 (S1 ^operator O2044 = 0.1700769046561409)
 inner elaboration loop at bottom goal.
Retracting rl*prefer*rvt*predict-no*H0*2
 -->
 (S1 ^operator O2042 = 0.2550133872099196)
Retracting rl*prefer*rvt*predict-no*H0*2*H1*7
 -->
 (S1 ^operator O2042 = 0.1700769046561409)
Retracting rl*prefer*rvt*predict-yes*H0*1
 -->
 (S1 ^operator O2041 = 0.5231202709028374)
Retracting rl*prefer*rvt*predict-yes*H0*1*H1*19
 -->
 (S1 ^operator O2041 = 0.4768823043018841)

--- END Proposal Phase ---

--- Decision Phase ---
RL update rl*prefer*rvt*predict-no*H0*4 0.814714 -0.687737 0.126977 -> 0.814714 -0.687737 0.126977(R,m,v=1,0.95,0.0477654)
RL update rl*prefer*rvt*predict-no*H0*4*H1*15 0.185286 0.687737 0.873023 -> 0.185286 0.687737 0.873023(R,m,v=1,1,0)
=>WM: (14359: S1 ^operator O2043)

  1022:    O: O2043 (predict-yes)
--- END Decision Phase ---

--- Application Phase ---
	--- Firing Productions (PE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing apply*operator
 -->
 (I3 ^predict-yes N1022 +  :O )
Firing apply*operator*complete
 -->
 (I3 ^predict-no N1021 -  :O )
 inner elaboration loop at bottom goal.
	--- Change Working Memory (PE) ---
=>WM: (14360: I3 ^predict-yes N1022)
<=WM: (14346: N1021 ^status complete)
<=WM: (14345: I3 ^predict-no N1021)
	--- Firing Productions (IE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing monitor*world
 -->

I see 1 and I'm going to do: predict-yes inner elaboration loop at bottom goal.
	--- Change Working Memory (IE) ---

--- END Application Phase ---
--- Output Phase ---
ENV: Agent did: predict-yes for direction L in state State-B
In  State-B moving L
ENV: (next state, see, prediction correct?) = (State-A, 1, True)
predict error 0
dir: dir isR
--- END Output Phase ---
/|\--- Input Phase --- 
=>WM: (14364: I2 ^dir R)
=>WM: (14363: I2 ^reward 1)
=>WM: (14362: I2 ^see 1)
=>WM: (14361: N1022 ^status complete)
<=WM: (14349: I2 ^dir L)
<=WM: (14348: I2 ^reward 1)
<=WM: (14347: I2 ^see 0)
=>WM: (14365: I2 ^level-1 L1-root)
<=WM: (14350: I2 ^level-1 R0-root)

--- END Input Phase --- 

--- Proposal Phase ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing rl*prefer*rvt*predict-yes*H0*3*H1*9
 -->
 (S1 ^operator O2043 = 0.6170448174311309)
Firing rl*prefer*rvt*predict-no*H0*4*H1*8
 -->
 (S1 ^operator O2044 = 0.4901349546100854)
Firing prefer*rvt*predict-no*H0*4*H1
 -->
Firing prefer*rvt*predict-yes*H0*3*H1
 -->
Firing elaborate*copy-see-to-output-link
 -->
 (I3 ^see 1 +)
Firing elaborate*reward*based*on*reward
 -->
 (R1026 ^value 1 +)
 (R1 ^reward R1026 +)
Firing propose*predict-yes
 -->
 (O2045 ^name predict-yes +)
 (S1 ^operator O2045 +)
Firing propose*predict-no
 -->
 (O2046 ^name predict-no +)
 (S1 ^operator O2046 +)
Firing rl*prefer*rvt*predict-no*H0*4
 -->
 (S1 ^operator O2044 = 0.1269768108744418)
Firing rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O2043 = 0.3829436303953129)
Firing prefer*rvt*predict-yes*H0
 -->
Firing prefer*rvt*predict-no*H0
 -->
Firing elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir R +)
 inner elaboration loop at bottom goal.
Retracting elaborate*copy-see-to-output-link
 -->
 (I3 ^see 0 +)
Retracting propose*predict-no
 -->
 (O2044 ^name predict-no +)
 (S1 ^operator O2044 +)
Retracting propose*predict-yes
 -->
 (O2043 ^name predict-yes +)
 (S1 ^operator O2043 +)
Retracting elaborate*reward*based*on*reward
 -->
 (R1025 ^value 1 +)
 (R1 ^reward R1025 +)
Retracting elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir L +)
Retracting rl*prefer*rvt*predict-no*H0*2*H1*7
 -->
 (S1 ^operator O2044 = 0.1700769046561409)
Retracting rl*prefer*rvt*predict-no*H0*2
 -->
 (S1 ^operator O2044 = 0.2550133872099196)
Retracting rl*prefer*rvt*predict-yes*H0*1*H1*19
 -->
 (S1 ^operator O2043 = 0.4768823043018841)
Retracting rl*prefer*rvt*predict-yes*H0*1
 -->
 (S1 ^operator O2043 = 0.5231202709028374)
=>WM: (14373: S1 ^operator O2046 +)
=>WM: (14372: S1 ^operator O2045 +)
=>WM: (14371: I3 ^dir R)
=>WM: (14370: O2046 ^name predict-no)
=>WM: (14369: O2045 ^name predict-yes)
=>WM: (14368: R1026 ^value 1)
=>WM: (14367: R1 ^reward R1026)
=>WM: (14366: I3 ^see 1)
<=WM: (14357: S1 ^operator O2043 +)
<=WM: (14359: S1 ^operator O2043)
<=WM: (14358: S1 ^operator O2044 +)
<=WM: (14356: I3 ^dir L)
<=WM: (14352: R1 ^reward R1025)
<=WM: (14351: I3 ^see 0)
<=WM: (14355: O2044 ^name predict-no)
<=WM: (14354: O2043 ^name predict-yes)
<=WM: (14353: R1025 ^value 1)

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing prefer*rvt*predict-yes*H0
 -->
Firing rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O2045 = 0.3829436303953129)
Firing prefer*rvt*predict-yes*H0*3*H1
 -->
Firing rl*prefer*rvt*predict-yes*H0*3*H1*9
 -->
 (S1 ^operator O2045 = 0.6170448174311309)
Firing prefer*rvt*predict-no*H0
 -->
Firing rl*prefer*rvt*predict-no*H0*4
 -->
 (S1 ^operator O2046 = 0.1269768108744418)
Firing prefer*rvt*predict-no*H0*4*H1
 -->
Firing rl*prefer*rvt*predict-no*H0*4*H1*8
 -->
 (S1 ^operator O2046 = 0.4901349546100854)
 inner elaboration loop at bottom goal.
Retracting rl*prefer*rvt*predict-no*H0*4
 -->
 (S1 ^operator O2044 = 0.1269768108744418)
Retracting rl*prefer*rvt*predict-no*H0*4*H1*8
 -->
 (S1 ^operator O2044 = 0.4901349546100854)
Retracting rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O2043 = 0.3829436303953129)
Retracting rl*prefer*rvt*predict-yes*H0*3*H1*9
 -->
 (S1 ^operator O2043 = 0.6170448174311309)

--- END Proposal Phase ---

--- Decision Phase ---
RL update rl*prefer*rvt*predict-yes*H0*1 0.72796 -0.20484 0.52312 -> 0.72796 -0.20484 0.52312(R,m,v=1,0.979592,0.0201286)
RL update rl*prefer*rvt*predict-yes*H0*1*H1*19 0.272043 0.204839 0.476882 -> 0.272043 0.204839 0.476882(R,m,v=1,1,0)
=>WM: (14374: S1 ^operator O2045)

  1023:    O: O2045 (predict-yes)
--- END Decision Phase ---

--- Application Phase ---
	--- Firing Productions (PE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing apply*operator
 -->
 (I3 ^predict-yes N1023 +  :O )
Firing apply*operator*complete
 -->
 (I3 ^predict-yes N1022 -  :O )
 inner elaboration loop at bottom goal.
	--- Change Working Memory (PE) ---
=>WM: (14375: I3 ^predict-yes N1023)
<=WM: (14361: N1022 ^status complete)
<=WM: (14360: I3 ^predict-yes N1022)
	--- Firing Productions (IE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing monitor*world
 -->

I see 1 and I'm going to do: predict-yes inner elaboration loop at bottom goal.
	--- Change Working Memory (IE) ---

--- END Application Phase ---
--- Output Phase ---
ENV: Agent did: predict-yes for direction R in state State-A
In  State-A moving R
ENV: (next state, see, prediction correct?) = (State-B, 1, True)
predict error 0
dir: dir isR
--- END Output Phase ---
-/|--- Input Phase --- 
=>WM: (14379: I2 ^dir R)
=>WM: (14378: I2 ^reward 1)
=>WM: (14377: I2 ^see 1)
=>WM: (14376: N1023 ^status complete)
<=WM: (14364: I2 ^dir R)
<=WM: (14363: I2 ^reward 1)
<=WM: (14362: I2 ^see 1)
=>WM: (14380: I2 ^level-1 R1-root)
<=WM: (14365: I2 ^level-1 L1-root)

--- END Input Phase --- 

--- Proposal Phase ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing rl*prefer*rvt*predict-yes*H0*3*H1*16
 -->
 (S1 ^operator O2045 = 0.08783148430849691)
Firing rl*prefer*rvt*predict-no*H0*4*H1*15
 -->
 (S1 ^operator O2046 = 0.8730233201796934)
Firing prefer*rvt*predict-no*H0*4*H1
 -->
Firing prefer*rvt*predict-yes*H0*3*H1
 -->
Firing elaborate*copy-see-to-output-link
 -->
 (I3 ^see 1 +)
Firing elaborate*reward*based*on*reward
 -->
 (R1027 ^value 1 +)
 (R1 ^reward R1027 +)
Firing propose*predict-yes
 -->
 (O2047 ^name predict-yes +)
 (S1 ^operator O2047 +)
Firing propose*predict-no
 -->
 (O2048 ^name predict-no +)
 (S1 ^operator O2048 +)
Firing rl*prefer*rvt*predict-no*H0*4
 -->
 (S1 ^operator O2046 = 0.1269768108744418)
Firing rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O2045 = 0.3829436303953129)
Firing prefer*rvt*predict-yes*H0
 -->
Firing prefer*rvt*predict-no*H0
 -->
Firing elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir R +)
 inner elaboration loop at bottom goal.
Retracting elaborate*copy-see-to-output-link
 -->
 (I3 ^see 1 +)
Retracting propose*predict-no
 -->
 (O2046 ^name predict-no +)
 (S1 ^operator O2046 +)
Retracting propose*predict-yes
 -->
 (O2045 ^name predict-yes +)
 (S1 ^operator O2045 +)
Retracting elaborate*reward*based*on*reward
 -->
 (R1026 ^value 1 +)
 (R1 ^reward R1026 +)
Retracting elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir R +)
Retracting rl*prefer*rvt*predict-no*H0*4*H1*8
 -->
 (S1 ^operator O2046 = 0.4901349546100854)
Retracting rl*prefer*rvt*predict-no*H0*4
 -->
 (S1 ^operator O2046 = 0.1269768108744418)
Retracting rl*prefer*rvt*predict-yes*H0*3*H1*9
 -->
 (S1 ^operator O2045 = 0.6170448174311309)
Retracting rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O2045 = 0.3829436303953129)
=>WM: (14386: S1 ^operator O2048 +)
=>WM: (14385: S1 ^operator O2047 +)
=>WM: (14384: O2048 ^name predict-no)
=>WM: (14383: O2047 ^name predict-yes)
=>WM: (14382: R1027 ^value 1)
=>WM: (14381: R1 ^reward R1027)
<=WM: (14372: S1 ^operator O2045 +)
<=WM: (14374: S1 ^operator O2045)
<=WM: (14373: S1 ^operator O2046 +)
<=WM: (14367: R1 ^reward R1026)
<=WM: (14370: O2046 ^name predict-no)
<=WM: (14369: O2045 ^name predict-yes)
<=WM: (14368: R1026 ^value 1)

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing prefer*rvt*predict-yes*H0
 -->
Firing rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O2047 = 0.3829436303953129)
Firing prefer*rvt*predict-yes*H0*3*H1
 -->
Firing rl*prefer*rvt*predict-yes*H0*3*H1*16
 -->
 (S1 ^operator O2047 = 0.08783148430849691)
Firing prefer*rvt*predict-no*H0
 -->
Firing rl*prefer*rvt*predict-no*H0*4
 -->
 (S1 ^operator O2048 = 0.1269768108744418)
Firing prefer*rvt*predict-no*H0*4*H1
 -->
Firing rl*prefer*rvt*predict-no*H0*4*H1*15
 -->
 (S1 ^operator O2048 = 0.8730233201796934)
 inner elaboration loop at bottom goal.
Retracting rl*prefer*rvt*predict-no*H0*4
 -->
 (S1 ^operator O2046 = 0.1269768108744418)
Retracting rl*prefer*rvt*predict-no*H0*4*H1*15
 -->
 (S1 ^operator O2046 = 0.8730233201796934)
Retracting rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O2045 = 0.3829436303953129)
Retracting rl*prefer*rvt*predict-yes*H0*3*H1*16
 -->
 (S1 ^operator O2045 = 0.08783148430849691)

--- END Proposal Phase ---

--- Decision Phase ---
RL update rl*prefer*rvt*predict-yes*H0*3 0.673136 -0.290193 0.382944 -> 0.673138 -0.290193 0.382945(R,m,v=1,0.962025,0.0367653)
RL update rl*prefer*rvt*predict-yes*H0*3*H1*9 0.326853 0.290192 0.617045 -> 0.326855 0.290192 0.617047(R,m,v=1,1,0)
=>WM: (14387: S1 ^operator O2048)

  1024:    O: O2048 (predict-no)
--- END Decision Phase ---

--- Application Phase ---
	--- Firing Productions (PE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing apply*operator
 -->
 (I3 ^predict-no N1024 +  :O )
Firing apply*operator*complete
 -->
 (I3 ^predict-yes N1023 -  :O )
 inner elaboration loop at bottom goal.
	--- Change Working Memory (PE) ---
=>WM: (14388: I3 ^predict-no N1024)
<=WM: (14376: N1023 ^status complete)
<=WM: (14375: I3 ^predict-yes N1023)
	--- Firing Productions (IE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing monitor*world
 -->

I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
	--- Change Working Memory (IE) ---

--- END Application Phase ---
--- Output Phase ---
ENV: Agent did: predict-no for direction R in state State-B
In  State-B moving R
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isU
--- END Output Phase ---
\-/--- Input Phase --- 
=>WM: (14392: I2 ^dir U)
=>WM: (14391: I2 ^reward 1)
=>WM: (14390: I2 ^see 0)
=>WM: (14389: N1024 ^status complete)
<=WM: (14379: I2 ^dir R)
<=WM: (14378: I2 ^reward 1)
<=WM: (14377: I2 ^see 1)
=>WM: (14393: I2 ^level-1 R0-root)
<=WM: (14380: I2 ^level-1 R1-root)

--- END Input Phase --- 

--- Proposal Phase ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing elaborate*copy-see-to-output-link
 -->
 (I3 ^see 0 +)
Firing elaborate*reward*based*on*reward
 -->
 (R1028 ^value 1 +)
 (R1 ^reward R1028 +)
Firing propose*predict-yes
 -->
 (O2049 ^name predict-yes +)
 (S1 ^operator O2049 +)
Firing propose*predict-no
 -->
 (O2050 ^name predict-no +)
 (S1 ^operator O2050 +)
Firing rl*prefer*rvt*predict-no*H0*6
 -->
 (S1 ^operator O2048 = 0.9999999999999999)
Firing rl*prefer*rvt*predict-yes*H0*5
 -->
 (S1 ^operator O2047 = 0.)
Firing prefer*rvt*predict-yes*H0
 -->
Firing prefer*rvt*predict-no*H0
 -->
Firing elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir U +)
 inner elaboration loop at bottom goal.
Retracting elaborate*copy-see-to-output-link
 -->
 (I3 ^see 1 +)
Retracting propose*predict-no
 -->
 (O2048 ^name predict-no +)
 (S1 ^operator O2048 +)
Retracting propose*predict-yes
 -->
 (O2047 ^name predict-yes +)
 (S1 ^operator O2047 +)
Retracting elaborate*reward*based*on*reward
 -->
 (R1027 ^value 1 +)
 (R1 ^reward R1027 +)
Retracting elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir R +)
Retracting rl*prefer*rvt*predict-no*H0*4*H1*15
 -->
 (S1 ^operator O2048 = 0.8730233201796934)
Retracting rl*prefer*rvt*predict-no*H0*4
 -->
 (S1 ^operator O2048 = 0.1269768108744418)
Retracting rl*prefer*rvt*predict-yes*H0*3*H1*16
 -->
 (S1 ^operator O2047 = 0.08783148430849691)
Retracting rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O2047 = 0.3829453632213463)
=>WM: (14401: S1 ^operator O2050 +)
=>WM: (14400: S1 ^operator O2049 +)
=>WM: (14399: I3 ^dir U)
=>WM: (14398: O2050 ^name predict-no)
=>WM: (14397: O2049 ^name predict-yes)
=>WM: (14396: R1028 ^value 1)
=>WM: (14395: R1 ^reward R1028)
=>WM: (14394: I3 ^see 0)
<=WM: (14385: S1 ^operator O2047 +)
<=WM: (14386: S1 ^operator O2048 +)
<=WM: (14387: S1 ^operator O2048)
<=WM: (14371: I3 ^dir R)
<=WM: (14381: R1 ^reward R1027)
<=WM: (14366: I3 ^see 1)
<=WM: (14384: O2048 ^name predict-no)
<=WM: (14383: O2047 ^name predict-yes)
<=WM: (14382: R1027 ^value 1)

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing prefer*rvt*predict-yes*H0
 -->
Firing rl*prefer*rvt*predict-yes*H0*5
 -->
 (S1 ^operator O2049 = 0.)
Firing prefer*rvt*predict-no*H0
 -->
Firing rl*prefer*rvt*predict-no*H0*6
 -->
 (S1 ^operator O2050 = 0.9999999999999999)
 inner elaboration loop at bottom goal.
Retracting rl*prefer*rvt*predict-no*H0*6
 -->
 (S1 ^operator O2048 = 0.9999999999999999)
Retracting rl*prefer*rvt*predict-yes*H0*5
 -->
 (S1 ^operator O2047 = 0.)

--- END Proposal Phase ---

--- Decision Phase ---
RL update rl*prefer*rvt*predict-no*H0*4 0.814714 -0.687737 0.126977 -> 0.814714 -0.687737 0.126977(R,m,v=1,0.950276,0.0475138)
RL update rl*prefer*rvt*predict-no*H0*4*H1*15 0.185286 0.687737 0.873023 -> 0.185286 0.687737 0.873023(R,m,v=1,1,0)
=>WM: (14402: S1 ^operator O2050)

  1025:    O: O2050 (predict-no)
--- END Decision Phase ---

--- Application Phase ---
	--- Firing Productions (PE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing apply*operator
 -->
 (I3 ^predict-no N1025 +  :O )
Firing apply*operator*complete
 -->
 (I3 ^predict-no N1024 -  :O )
 inner elaboration loop at bottom goal.
	--- Change Working Memory (PE) ---
=>WM: (14403: I3 ^predict-no N1025)
<=WM: (14389: N1024 ^status complete)
<=WM: (14388: I3 ^predict-no N1024)
	--- Firing Productions (IE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing monitor*world
 -->

I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
	--- Change Working Memory (IE) ---

--- END Application Phase ---
--- Output Phase ---
ENV: Agent did: predict-no for direction U in state State-B
In  State-B moving U
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isU
--- END Output Phase ---
|\--- Input Phase --- 
=>WM: (14407: I2 ^dir U)
=>WM: (14406: I2 ^reward 1)
=>WM: (14405: I2 ^see 0)
=>WM: (14404: N1025 ^status complete)
<=WM: (14392: I2 ^dir U)
<=WM: (14391: I2 ^reward 1)
<=WM: (14390: I2 ^see 0)
=>WM: (14408: I2 ^level-1 R0-root)
<=WM: (14393: I2 ^level-1 R0-root)

--- END Input Phase --- 

--- Proposal Phase ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing elaborate*copy-see-to-output-link
 -->
 (I3 ^see 0 +)
Firing elaborate*reward*based*on*reward
 -->
 (R1029 ^value 1 +)
 (R1 ^reward R1029 +)
Firing propose*predict-yes
 -->
 (O2051 ^name predict-yes +)
 (S1 ^operator O2051 +)
Firing propose*predict-no
 -->
 (O2052 ^name predict-no +)
 (S1 ^operator O2052 +)
Firing rl*prefer*rvt*predict-no*H0*6
 -->
 (S1 ^operator O2050 = 0.9999999999999999)
Firing rl*prefer*rvt*predict-yes*H0*5
 -->
 (S1 ^operator O2049 = 0.)
Firing prefer*rvt*predict-yes*H0
 -->
Firing prefer*rvt*predict-no*H0
 -->
Firing elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir U +)
 inner elaboration loop at bottom goal.
Retracting elaborate*copy-see-to-output-link
 -->
 (I3 ^see 0 +)
Retracting propose*predict-no
 -->
 (O2050 ^name predict-no +)
 (S1 ^operator O2050 +)
Retracting propose*predict-yes
 -->
 (O2049 ^name predict-yes +)
 (S1 ^operator O2049 +)
Retracting elaborate*reward*based*on*reward
 -->
 (R1028 ^value 1 +)
 (R1 ^reward R1028 +)
Retracting elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir U +)
Retracting rl*prefer*rvt*predict-no*H0*6
 -->
 (S1 ^operator O2050 = 0.9999999999999999)
Retracting rl*prefer*rvt*predict-yes*H0*5
 -->
 (S1 ^operator O2049 = 0.)
=>WM: (14414: S1 ^operator O2052 +)
=>WM: (14413: S1 ^operator O2051 +)
=>WM: (14412: O2052 ^name predict-no)
=>WM: (14411: O2051 ^name predict-yes)
=>WM: (14410: R1029 ^value 1)
=>WM: (14409: R1 ^reward R1029)
<=WM: (14400: S1 ^operator O2049 +)
<=WM: (14401: S1 ^operator O2050 +)
<=WM: (14402: S1 ^operator O2050)
<=WM: (14395: R1 ^reward R1028)
<=WM: (14398: O2050 ^name predict-no)
<=WM: (14397: O2049 ^name predict-yes)
<=WM: (14396: R1028 ^value 1)

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing prefer*rvt*predict-yes*H0
 -->
Firing rl*prefer*rvt*predict-yes*H0*5
 -->
 (S1 ^operator O2051 = 0.)
Firing prefer*rvt*predict-no*H0
 -->
Firing rl*prefer*rvt*predict-no*H0*6
 -->
 (S1 ^operator O2052 = 0.9999999999999999)
 inner elaboration loop at bottom goal.
Retracting rl*prefer*rvt*predict-no*H0*6
 -->
 (S1 ^operator O2050 = 0.9999999999999999)
Retracting rl*prefer*rvt*predict-yes*H0*5
 -->
 (S1 ^operator O2049 = 0.)

--- END Proposal Phase ---

--- Decision Phase ---
RL update rl*prefer*rvt*predict-no*H0*6 1 0 1 -> 1 0 1(R,m,v=1,1,0)
=>WM: (14415: S1 ^operator O2052)

  1026:    O: O2052 (predict-no)
--- END Decision Phase ---

--- Application Phase ---
	--- Firing Productions (PE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing apply*operator
 -->
 (I3 ^predict-no N1026 +  :O )
Firing apply*operator*complete
 -->
 (I3 ^predict-no N1025 -  :O )
 inner elaboration loop at bottom goal.
	--- Change Working Memory (PE) ---
=>WM: (14416: I3 ^predict-no N1026)
<=WM: (14404: N1025 ^status complete)
<=WM: (14403: I3 ^predict-no N1025)
	--- Firing Productions (IE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing monitor*world
 -->

I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
	--- Change Working Memory (IE) ---

--- END Application Phase ---
--- Output Phase ---
ENV: Agent did: predict-no for direction U in state State-B
In  State-B moving U
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isU
--- END Output Phase ---
---- Input Phase --- 
=>WM: (14420: I2 ^dir U)
=>WM: (14419: I2 ^reward 1)
=>WM: (14418: I2 ^see 0)
=>WM: (14417: N1026 ^status complete)
<=WM: (14407: I2 ^dir U)
<=WM: (14406: I2 ^reward 1)
<=WM: (14405: I2 ^see 0)
=>WM: (14421: I2 ^level-1 R0-root)
<=WM: (14408: I2 ^level-1 R0-root)

--- END Input Phase --- 

--- Proposal Phase ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing elaborate*copy-see-to-output-link
 -->
 (I3 ^see 0 +)
Firing elaborate*reward*based*on*reward
 -->
 (R1030 ^value 1 +)
 (R1 ^reward R1030 +)
Firing propose*predict-yes
 -->
 (O2053 ^name predict-yes +)
 (S1 ^operator O2053 +)
Firing propose*predict-no
 -->
 (O2054 ^name predict-no +)
 (S1 ^operator O2054 +)
Firing rl*prefer*rvt*predict-no*H0*6
 -->
 (S1 ^operator O2052 = 0.9999999999999999)
Firing rl*prefer*rvt*predict-yes*H0*5
 -->
 (S1 ^operator O2051 = 0.)
Firing prefer*rvt*predict-yes*H0
 -->
Firing prefer*rvt*predict-no*H0
 -->
Firing elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir U +)
 inner elaboration loop at bottom goal.
Retracting elaborate*copy-see-to-output-link
 -->
 (I3 ^see 0 +)
Retracting propose*predict-no
 -->
 (O2052 ^name predict-no +)
 (S1 ^operator O2052 +)
Retracting propose*predict-yes
 -->
 (O2051 ^name predict-yes +)
 (S1 ^operator O2051 +)
Retracting elaborate*reward*based*on*reward
 -->
 (R1029 ^value 1 +)
 (R1 ^reward R1029 +)
Retracting elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir U +)
Retracting rl*prefer*rvt*predict-no*H0*6
 -->
 (S1 ^operator O2052 = 0.9999999999999999)
Retracting rl*prefer*rvt*predict-yes*H0*5
 -->
 (S1 ^operator O2051 = 0.)
=>WM: (14427: S1 ^operator O2054 +)
=>WM: (14426: S1 ^operator O2053 +)
=>WM: (14425: O2054 ^name predict-no)
=>WM: (14424: O2053 ^name predict-yes)
=>WM: (14423: R1030 ^value 1)
=>WM: (14422: R1 ^reward R1030)
<=WM: (14413: S1 ^operator O2051 +)
<=WM: (14414: S1 ^operator O2052 +)
<=WM: (14415: S1 ^operator O2052)
<=WM: (14409: R1 ^reward R1029)
<=WM: (14412: O2052 ^name predict-no)
<=WM: (14411: O2051 ^name predict-yes)
<=WM: (14410: R1029 ^value 1)

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing prefer*rvt*predict-yes*H0
 -->
Firing rl*prefer*rvt*predict-yes*H0*5
 -->
 (S1 ^operator O2053 = 0.)
Firing prefer*rvt*predict-no*H0
 -->
Firing rl*prefer*rvt*predict-no*H0*6
 -->
 (S1 ^operator O2054 = 0.9999999999999999)
 inner elaboration loop at bottom goal.
Retracting rl*prefer*rvt*predict-no*H0*6
 -->
 (S1 ^operator O2052 = 0.9999999999999999)
Retracting rl*prefer*rvt*predict-yes*H0*5
 -->
 (S1 ^operator O2051 = 0.)

--- END Proposal Phase ---

--- Decision Phase ---
RL update rl*prefer*rvt*predict-no*H0*6 1 0 1 -> 1 0 1(R,m,v=1,1,0)
=>WM: (14428: S1 ^operator O2054)

  1027:    O: O2054 (predict-no)
--- END Decision Phase ---

--- Application Phase ---
	--- Firing Productions (PE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing apply*operator
 -->
 (I3 ^predict-no N1027 +  :O )
Firing apply*operator*complete
 -->
 (I3 ^predict-no N1026 -  :O )
 inner elaboration loop at bottom goal.
	--- Change Working Memory (PE) ---
=>WM: (14429: I3 ^predict-no N1027)
<=WM: (14417: N1026 ^status complete)
<=WM: (14416: I3 ^predict-no N1026)
	--- Firing Productions (IE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing monitor*world
 -->

I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
	--- Change Working Memory (IE) ---

--- END Application Phase ---
--- Output Phase ---
ENV: Agent did: predict-no for direction U in state State-B
In  State-B moving U
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isU
--- END Output Phase ---
/|--- Input Phase --- 
=>WM: (14433: I2 ^dir U)
=>WM: (14432: I2 ^reward 1)
=>WM: (14431: I2 ^see 0)
=>WM: (14430: N1027 ^status complete)
<=WM: (14420: I2 ^dir U)
<=WM: (14419: I2 ^reward 1)
<=WM: (14418: I2 ^see 0)
=>WM: (14434: I2 ^level-1 R0-root)
<=WM: (14421: I2 ^level-1 R0-root)

--- END Input Phase --- 

--- Proposal Phase ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing elaborate*copy-see-to-output-link
 -->
 (I3 ^see 0 +)
Firing elaborate*reward*based*on*reward
 -->
 (R1031 ^value 1 +)
 (R1 ^reward R1031 +)
Firing propose*predict-yes
 -->
 (O2055 ^name predict-yes +)
 (S1 ^operator O2055 +)
Firing propose*predict-no
 -->
 (O2056 ^name predict-no +)
 (S1 ^operator O2056 +)
Firing rl*prefer*rvt*predict-no*H0*6
 -->
 (S1 ^operator O2054 = 0.9999999999999999)
Firing rl*prefer*rvt*predict-yes*H0*5
 -->
 (S1 ^operator O2053 = 0.)
Firing prefer*rvt*predict-yes*H0
 -->
Firing prefer*rvt*predict-no*H0
 -->
Firing elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir U +)
 inner elaboration loop at bottom goal.
Retracting elaborate*copy-see-to-output-link
 -->
 (I3 ^see 0 +)
Retracting propose*predict-no
 -->
 (O2054 ^name predict-no +)
 (S1 ^operator O2054 +)
Retracting propose*predict-yes
 -->
 (O2053 ^name predict-yes +)
 (S1 ^operator O2053 +)
Retracting elaborate*reward*based*on*reward
 -->
 (R1030 ^value 1 +)
 (R1 ^reward R1030 +)
Retracting elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir U +)
Retracting rl*prefer*rvt*predict-no*H0*6
 -->
 (S1 ^operator O2054 = 0.9999999999999999)
Retracting rl*prefer*rvt*predict-yes*H0*5
 -->
 (S1 ^operator O2053 = 0.)
=>WM: (14440: S1 ^operator O2056 +)
=>WM: (14439: S1 ^operator O2055 +)
=>WM: (14438: O2056 ^name predict-no)
=>WM: (14437: O2055 ^name predict-yes)
=>WM: (14436: R1031 ^value 1)
=>WM: (14435: R1 ^reward R1031)
<=WM: (14426: S1 ^operator O2053 +)
<=WM: (14427: S1 ^operator O2054 +)
<=WM: (14428: S1 ^operator O2054)
<=WM: (14422: R1 ^reward R1030)
<=WM: (14425: O2054 ^name predict-no)
<=WM: (14424: O2053 ^name predict-yes)
<=WM: (14423: R1030 ^value 1)

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing prefer*rvt*predict-yes*H0
 -->
Firing rl*prefer*rvt*predict-yes*H0*5
 -->
 (S1 ^operator O2055 = 0.)
Firing prefer*rvt*predict-no*H0
 -->
Firing rl*prefer*rvt*predict-no*H0*6
 -->
 (S1 ^operator O2056 = 0.9999999999999999)
 inner elaboration loop at bottom goal.
Retracting rl*prefer*rvt*predict-no*H0*6
 -->
 (S1 ^operator O2054 = 0.9999999999999999)
Retracting rl*prefer*rvt*predict-yes*H0*5
 -->
 (S1 ^operator O2053 = 0.)

--- END Proposal Phase ---

--- Decision Phase ---
RL update rl*prefer*rvt*predict-no*H0*6 1 0 1 -> 1 0 1(R,m,v=1,1,0)
=>WM: (14441: S1 ^operator O2056)

  1028:    O: O2056 (predict-no)
--- END Decision Phase ---

--- Application Phase ---
	--- Firing Productions (PE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing apply*operator
 -->
 (I3 ^predict-no N1028 +  :O )
Firing apply*operator*complete
 -->
 (I3 ^predict-no N1027 -  :O )
 inner elaboration loop at bottom goal.
	--- Change Working Memory (PE) ---
=>WM: (14442: I3 ^predict-no N1028)
<=WM: (14430: N1027 ^status complete)
<=WM: (14429: I3 ^predict-no N1027)
	--- Firing Productions (IE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing monitor*world
 -->

I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
	--- Change Working Memory (IE) ---

--- END Application Phase ---
--- Output Phase ---
ENV: Agent did: predict-no for direction U in state State-B
In  State-B moving U
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isL
--- END Output Phase ---
\--- Input Phase --- 
=>WM: (14446: I2 ^dir L)
=>WM: (14445: I2 ^reward 1)
=>WM: (14444: I2 ^see 0)
=>WM: (14443: N1028 ^status complete)
<=WM: (14433: I2 ^dir U)
<=WM: (14432: I2 ^reward 1)
<=WM: (14431: I2 ^see 0)
=>WM: (14447: I2 ^level-1 R0-root)
<=WM: (14434: I2 ^level-1 R0-root)

--- END Input Phase --- 

--- Proposal Phase ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing rl*prefer*rvt*predict-yes*H0*1*H1*19
 -->
 (S1 ^operator O2055 = 0.4768819180211759)
Firing rl*prefer*rvt*predict-no*H0*2*H1*7
 -->
 (S1 ^operator O2056 = 0.1700769046561409)
Firing prefer*rvt*predict-no*H0*2*H1
 -->
Firing prefer*rvt*predict-yes*H0*1*H1
 -->
Firing elaborate*copy-see-to-output-link
 -->
 (I3 ^see 0 +)
Firing elaborate*reward*based*on*reward
 -->
 (R1032 ^value 1 +)
 (R1 ^reward R1032 +)
Firing propose*predict-yes
 -->
 (O2057 ^name predict-yes +)
 (S1 ^operator O2057 +)
Firing propose*predict-no
 -->
 (O2058 ^name predict-no +)
 (S1 ^operator O2058 +)
Firing rl*prefer*rvt*predict-no*H0*2
 -->
 (S1 ^operator O2056 = 0.2550133872099196)
Firing rl*prefer*rvt*predict-yes*H0*1
 -->
 (S1 ^operator O2055 = 0.5231198846221292)
Firing prefer*rvt*predict-yes*H0
 -->
Firing prefer*rvt*predict-no*H0
 -->
Firing elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir L +)
 inner elaboration loop at bottom goal.
Retracting elaborate*copy-see-to-output-link
 -->
 (I3 ^see 0 +)
Retracting propose*predict-no
 -->
 (O2056 ^name predict-no +)
 (S1 ^operator O2056 +)
Retracting propose*predict-yes
 -->
 (O2055 ^name predict-yes +)
 (S1 ^operator O2055 +)
Retracting elaborate*reward*based*on*reward
 -->
 (R1031 ^value 1 +)
 (R1 ^reward R1031 +)
Retracting elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir U +)
Retracting rl*prefer*rvt*predict-no*H0*6
 -->
 (S1 ^operator O2056 = 0.9999999999999999)
Retracting rl*prefer*rvt*predict-yes*H0*5
 -->
 (S1 ^operator O2055 = 0.)
=>WM: (14454: S1 ^operator O2058 +)
=>WM: (14453: S1 ^operator O2057 +)
=>WM: (14452: I3 ^dir L)
=>WM: (14451: O2058 ^name predict-no)
=>WM: (14450: O2057 ^name predict-yes)
=>WM: (14449: R1032 ^value 1)
=>WM: (14448: R1 ^reward R1032)
<=WM: (14439: S1 ^operator O2055 +)
<=WM: (14440: S1 ^operator O2056 +)
<=WM: (14441: S1 ^operator O2056)
<=WM: (14399: I3 ^dir U)
<=WM: (14435: R1 ^reward R1031)
<=WM: (14438: O2056 ^name predict-no)
<=WM: (14437: O2055 ^name predict-yes)
<=WM: (14436: R1031 ^value 1)

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing prefer*rvt*predict-yes*H0
 -->
Firing rl*prefer*rvt*predict-yes*H0*1*H1*19
 -->
 (S1 ^operator O2057 = 0.4768819180211759)
Firing rl*prefer*rvt*predict-yes*H0*1
 -->
 (S1 ^operator O2057 = 0.5231198846221292)
Firing prefer*rvt*predict-yes*H0*1*H1
 -->
Firing prefer*rvt*predict-no*H0
 -->
Firing rl*prefer*rvt*predict-no*H0*2*H1*7
 -->
 (S1 ^operator O2058 = 0.1700769046561409)
Firing rl*prefer*rvt*predict-no*H0*2
 -->
 (S1 ^operator O2058 = 0.2550133872099196)
Firing prefer*rvt*predict-no*H0*2*H1
 -->
 inner elaboration loop at bottom goal.
Retracting rl*prefer*rvt*predict-no*H0*2
 -->
 (S1 ^operator O2056 = 0.2550133872099196)
Retracting rl*prefer*rvt*predict-no*H0*2*H1*7
 -->
 (S1 ^operator O2056 = 0.1700769046561409)
Retracting rl*prefer*rvt*predict-yes*H0*1
 -->
 (S1 ^operator O2055 = 0.5231198846221292)
Retracting rl*prefer*rvt*predict-yes*H0*1*H1*19
 -->
 (S1 ^operator O2055 = 0.4768819180211759)

--- END Proposal Phase ---

--- Decision Phase ---
RL update rl*prefer*rvt*predict-no*H0*6 1 0 1 -> 1 0 1(R,m,v=1,1,0)
=>WM: (14455: S1 ^operator O2057)

  1029:    O: O2057 (predict-yes)
--- END Decision Phase ---

--- Application Phase ---
	--- Firing Productions (PE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing apply*operator
 -->
 (I3 ^predict-yes N1029 +  :O )
Firing apply*operator*complete
 -->
 (I3 ^predict-no N1028 -  :O )
 inner elaboration loop at bottom goal.
	--- Change Working Memory (PE) ---
=>WM: (14456: I3 ^predict-yes N1029)
<=WM: (14443: N1028 ^status complete)
<=WM: (14442: I3 ^predict-no N1028)
	--- Firing Productions (IE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing monitor*world
 -->

I see 1 and I'm going to do: predict-yes inner elaboration loop at bottom goal.
	--- Change Working Memory (IE) ---

--- END Application Phase ---
--- Output Phase ---
ENV: Agent did: predict-yes for direction L in state State-B
In  State-B moving L
ENV: (next state, see, prediction correct?) = (State-A, 1, True)
predict error 0
dir: dir isU
--- END Output Phase ---
-/|--- Input Phase --- 
=>WM: (14460: I2 ^dir U)
=>WM: (14459: I2 ^reward 1)
=>WM: (14458: I2 ^see 1)
=>WM: (14457: N1029 ^status complete)
<=WM: (14446: I2 ^dir L)
<=WM: (14445: I2 ^reward 1)
<=WM: (14444: I2 ^see 0)
=>WM: (14461: I2 ^level-1 L1-root)
<=WM: (14447: I2 ^level-1 R0-root)

--- END Input Phase --- 

--- Proposal Phase ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing elaborate*copy-see-to-output-link
 -->
 (I3 ^see 1 +)
Firing elaborate*reward*based*on*reward
 -->
 (R1033 ^value 1 +)
 (R1 ^reward R1033 +)
Firing propose*predict-yes
 -->
 (O2059 ^name predict-yes +)
 (S1 ^operator O2059 +)
Firing propose*predict-no
 -->
 (O2060 ^name predict-no +)
 (S1 ^operator O2060 +)
Firing rl*prefer*rvt*predict-no*H0*6
 -->
 (S1 ^operator O2058 = 0.9999999999999999)
Firing rl*prefer*rvt*predict-yes*H0*5
 -->
 (S1 ^operator O2057 = 0.)
Firing prefer*rvt*predict-yes*H0
 -->
Firing prefer*rvt*predict-no*H0
 -->
Firing elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir U +)
 inner elaboration loop at bottom goal.
Retracting elaborate*copy-see-to-output-link
 -->
 (I3 ^see 0 +)
Retracting propose*predict-no
 -->
 (O2058 ^name predict-no +)
 (S1 ^operator O2058 +)
Retracting propose*predict-yes
 -->
 (O2057 ^name predict-yes +)
 (S1 ^operator O2057 +)
Retracting elaborate*reward*based*on*reward
 -->
 (R1032 ^value 1 +)
 (R1 ^reward R1032 +)
Retracting elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir L +)
Retracting rl*prefer*rvt*predict-no*H0*2
 -->
 (S1 ^operator O2058 = 0.2550133872099196)
Retracting rl*prefer*rvt*predict-no*H0*2*H1*7
 -->
 (S1 ^operator O2058 = 0.1700769046561409)
Retracting rl*prefer*rvt*predict-yes*H0*1
 -->
 (S1 ^operator O2057 = 0.5231198846221292)
Retracting rl*prefer*rvt*predict-yes*H0*1*H1*19
 -->
 (S1 ^operator O2057 = 0.4768819180211759)
=>WM: (14469: S1 ^operator O2060 +)
=>WM: (14468: S1 ^operator O2059 +)
=>WM: (14467: I3 ^dir U)
=>WM: (14466: O2060 ^name predict-no)
=>WM: (14465: O2059 ^name predict-yes)
=>WM: (14464: R1033 ^value 1)
=>WM: (14463: R1 ^reward R1033)
=>WM: (14462: I3 ^see 1)
<=WM: (14453: S1 ^operator O2057 +)
<=WM: (14455: S1 ^operator O2057)
<=WM: (14454: S1 ^operator O2058 +)
<=WM: (14452: I3 ^dir L)
<=WM: (14448: R1 ^reward R1032)
<=WM: (14394: I3 ^see 0)
<=WM: (14451: O2058 ^name predict-no)
<=WM: (14450: O2057 ^name predict-yes)
<=WM: (14449: R1032 ^value 1)

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing prefer*rvt*predict-yes*H0
 -->
Firing rl*prefer*rvt*predict-yes*H0*5
 -->
 (S1 ^operator O2059 = 0.)
Firing prefer*rvt*predict-no*H0
 -->
Firing rl*prefer*rvt*predict-no*H0*6
 -->
 (S1 ^operator O2060 = 0.9999999999999999)
 inner elaboration loop at bottom goal.
Retracting rl*prefer*rvt*predict-no*H0*6
 -->
 (S1 ^operator O2058 = 0.9999999999999999)
Retracting rl*prefer*rvt*predict-yes*H0*5
 -->
 (S1 ^operator O2057 = 0.)

--- END Proposal Phase ---

--- Decision Phase ---
RL update rl*prefer*rvt*predict-yes*H0*1 0.72796 -0.20484 0.52312 -> 0.727959 -0.20484 0.52312(R,m,v=1,0.97973,0.0199945)
RL update rl*prefer*rvt*predict-yes*H0*1*H1*19 0.272043 0.204839 0.476882 -> 0.272042 0.204839 0.476882(R,m,v=1,1,0)
=>WM: (14470: S1 ^operator O2060)

  1030:    O: O2060 (predict-no)
--- END Decision Phase ---

--- Application Phase ---
	--- Firing Productions (PE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing apply*operator
 -->
 (I3 ^predict-no N1030 +  :O )
Firing apply*operator*complete
 -->
 (I3 ^predict-yes N1029 -  :O )
 inner elaboration loop at bottom goal.
	--- Change Working Memory (PE) ---
=>WM: (14471: I3 ^predict-no N1030)
<=WM: (14457: N1029 ^status complete)
<=WM: (14456: I3 ^predict-yes N1029)
	--- Firing Productions (IE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing monitor*world
 -->

I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
	--- Change Working Memory (IE) ---

--- END Application Phase ---
--- Output Phase ---
ENV: Agent did: predict-no for direction U in state State-A
In  State-A moving U
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isL
--- END Output Phase ---
\-/--- Input Phase --- 
=>WM: (14475: I2 ^dir L)
=>WM: (14474: I2 ^reward 1)
=>WM: (14473: I2 ^see 0)
=>WM: (14472: N1030 ^status complete)
<=WM: (14460: I2 ^dir U)
<=WM: (14459: I2 ^reward 1)
<=WM: (14458: I2 ^see 1)
=>WM: (14476: I2 ^level-1 L1-root)
<=WM: (14461: I2 ^level-1 L1-root)

--- END Input Phase --- 

--- Proposal Phase ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing rl*prefer*rvt*predict-yes*H0*1*H1*20
 -->
 (S1 ^operator O2059 = 0.1693592933936033)
Firing rl*prefer*rvt*predict-no*H0*2*H1*11
 -->
 (S1 ^operator O2060 = 0.7449864907562294)
Firing prefer*rvt*predict-no*H0*2*H1
 -->
Firing prefer*rvt*predict-yes*H0*1*H1
 -->
Firing elaborate*copy-see-to-output-link
 -->
 (I3 ^see 0 +)
Firing elaborate*reward*based*on*reward
 -->
 (R1034 ^value 1 +)
 (R1 ^reward R1034 +)
Firing propose*predict-yes
 -->
 (O2061 ^name predict-yes +)
 (S1 ^operator O2061 +)
Firing propose*predict-no
 -->
 (O2062 ^name predict-no +)
 (S1 ^operator O2062 +)
Firing rl*prefer*rvt*predict-no*H0*2
 -->
 (S1 ^operator O2060 = 0.2550133872099196)
Firing rl*prefer*rvt*predict-yes*H0*1
 -->
 (S1 ^operator O2059 = 0.5231196142256334)
Firing prefer*rvt*predict-yes*H0
 -->
Firing prefer*rvt*predict-no*H0
 -->
Firing elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir L +)
 inner elaboration loop at bottom goal.
Retracting elaborate*copy-see-to-output-link
 -->
 (I3 ^see 1 +)
Retracting propose*predict-no
 -->
 (O2060 ^name predict-no +)
 (S1 ^operator O2060 +)
Retracting propose*predict-yes
 -->
 (O2059 ^name predict-yes +)
 (S1 ^operator O2059 +)
Retracting elaborate*reward*based*on*reward
 -->
 (R1033 ^value 1 +)
 (R1 ^reward R1033 +)
Retracting elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir U +)
Retracting rl*prefer*rvt*predict-no*H0*6
 -->
 (S1 ^operator O2060 = 0.9999999999999999)
Retracting rl*prefer*rvt*predict-yes*H0*5
 -->
 (S1 ^operator O2059 = 0.)
=>WM: (14484: S1 ^operator O2062 +)
=>WM: (14483: S1 ^operator O2061 +)
=>WM: (14482: I3 ^dir L)
=>WM: (14481: O2062 ^name predict-no)
=>WM: (14480: O2061 ^name predict-yes)
=>WM: (14479: R1034 ^value 1)
=>WM: (14478: R1 ^reward R1034)
=>WM: (14477: I3 ^see 0)
<=WM: (14468: S1 ^operator O2059 +)
<=WM: (14469: S1 ^operator O2060 +)
<=WM: (14470: S1 ^operator O2060)
<=WM: (14467: I3 ^dir U)
<=WM: (14463: R1 ^reward R1033)
<=WM: (14462: I3 ^see 1)
<=WM: (14466: O2060 ^name predict-no)
<=WM: (14465: O2059 ^name predict-yes)
<=WM: (14464: R1033 ^value 1)

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing prefer*rvt*predict-yes*H0
 -->
Firing rl*prefer*rvt*predict-yes*H0*1*H1*20
 -->
 (S1 ^operator O2061 = 0.1693592933936033)
Firing rl*prefer*rvt*predict-yes*H0*1
 -->
 (S1 ^operator O2061 = 0.5231196142256334)
Firing prefer*rvt*predict-yes*H0*1*H1
 -->
Firing prefer*rvt*predict-no*H0
 -->
Firing rl*prefer*rvt*predict-no*H0*2*H1*11
 -->
 (S1 ^operator O2062 = 0.7449864907562294)
Firing rl*prefer*rvt*predict-no*H0*2
 -->
 (S1 ^operator O2062 = 0.2550133872099196)
Firing prefer*rvt*predict-no*H0*2*H1
 -->
 inner elaboration loop at bottom goal.
Retracting rl*prefer*rvt*predict-no*H0*2
 -->
 (S1 ^operator O2060 = 0.2550133872099196)
Retracting rl*prefer*rvt*predict-no*H0*2*H1*11
 -->
 (S1 ^operator O2060 = 0.7449864907562294)
Retracting rl*prefer*rvt*predict-yes*H0*1
 -->
 (S1 ^operator O2059 = 0.5231196142256334)
Retracting rl*prefer*rvt*predict-yes*H0*1*H1*20
 -->
 (S1 ^operator O2059 = 0.1693592933936033)

--- END Proposal Phase ---

--- Decision Phase ---
RL update rl*prefer*rvt*predict-no*H0*6 1 0 1 -> 1 0 1(R,m,v=1,1,0)
=>WM: (14485: S1 ^operator O2062)

  1031:    O: O2062 (predict-no)
--- END Decision Phase ---

--- Application Phase ---
	--- Firing Productions (PE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing apply*operator
 -->
 (I3 ^predict-no N1031 +  :O )
Firing apply*operator*complete
 -->
 (I3 ^predict-no N1030 -  :O )
 inner elaboration loop at bottom goal.
	--- Change Working Memory (PE) ---
=>WM: (14486: I3 ^predict-no N1031)
<=WM: (14472: N1030 ^status complete)
<=WM: (14471: I3 ^predict-no N1030)
	--- Firing Productions (IE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing monitor*world
 -->

I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
	--- Change Working Memory (IE) ---

--- END Application Phase ---
--- Output Phase ---
ENV: Agent did: predict-no for direction L in state State-A
In  State-A moving L
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isL
--- END Output Phase ---
|--- Input Phase --- 
=>WM: (14490: I2 ^dir L)
=>WM: (14489: I2 ^reward 1)
=>WM: (14488: I2 ^see 0)
=>WM: (14487: N1031 ^status complete)
<=WM: (14475: I2 ^dir L)
<=WM: (14474: I2 ^reward 1)
<=WM: (14473: I2 ^see 0)
=>WM: (14491: I2 ^level-1 L0-root)
<=WM: (14476: I2 ^level-1 L1-root)

--- END Input Phase --- 

--- Proposal Phase ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing rl*prefer*rvt*predict-yes*H0*1*H1*21
 -->
 (S1 ^operator O2061 = 0.3)
Firing rl*prefer*rvt*predict-no*H0*2*H1*12
 -->
 (S1 ^operator O2062 = 0.7449866897649052)
Firing prefer*rvt*predict-no*H0*2*H1
 -->
Firing prefer*rvt*predict-yes*H0*1*H1
 -->
Firing elaborate*copy-see-to-output-link
 -->
 (I3 ^see 0 +)
Firing elaborate*reward*based*on*reward
 -->
 (R1035 ^value 1 +)
 (R1 ^reward R1035 +)
Firing propose*predict-yes
 -->
 (O2063 ^name predict-yes +)
 (S1 ^operator O2063 +)
Firing propose*predict-no
 -->
 (O2064 ^name predict-no +)
 (S1 ^operator O2064 +)
Firing rl*prefer*rvt*predict-no*H0*2
 -->
 (S1 ^operator O2062 = 0.2550133872099196)
Firing rl*prefer*rvt*predict-yes*H0*1
 -->
 (S1 ^operator O2061 = 0.5231196142256334)
Firing prefer*rvt*predict-yes*H0
 -->
Firing prefer*rvt*predict-no*H0
 -->
Firing elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir L +)
 inner elaboration loop at bottom goal.
Retracting elaborate*copy-see-to-output-link
 -->
 (I3 ^see 0 +)
Retracting propose*predict-no
 -->
 (O2062 ^name predict-no +)
 (S1 ^operator O2062 +)
Retracting propose*predict-yes
 -->
 (O2061 ^name predict-yes +)
 (S1 ^operator O2061 +)
Retracting elaborate*reward*based*on*reward
 -->
 (R1034 ^value 1 +)
 (R1 ^reward R1034 +)
Retracting elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir L +)
Retracting rl*prefer*rvt*predict-no*H0*2
 -->
 (S1 ^operator O2062 = 0.2550133872099196)
Retracting rl*prefer*rvt*predict-no*H0*2*H1*11
 -->
 (S1 ^operator O2062 = 0.7449864907562294)
Retracting rl*prefer*rvt*predict-yes*H0*1
 -->
 (S1 ^operator O2061 = 0.5231196142256334)
Retracting rl*prefer*rvt*predict-yes*H0*1*H1*20
 -->
 (S1 ^operator O2061 = 0.1693592933936033)
=>WM: (14497: S1 ^operator O2064 +)
=>WM: (14496: S1 ^operator O2063 +)
=>WM: (14495: O2064 ^name predict-no)
=>WM: (14494: O2063 ^name predict-yes)
=>WM: (14493: R1035 ^value 1)
=>WM: (14492: R1 ^reward R1035)
<=WM: (14483: S1 ^operator O2061 +)
<=WM: (14484: S1 ^operator O2062 +)
<=WM: (14485: S1 ^operator O2062)
<=WM: (14478: R1 ^reward R1034)
<=WM: (14481: O2062 ^name predict-no)
<=WM: (14480: O2061 ^name predict-yes)
<=WM: (14479: R1034 ^value 1)

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing prefer*rvt*predict-yes*H0
 -->
Firing rl*prefer*rvt*predict-yes*H0*1
 -->
 (S1 ^operator O2063 = 0.5231196142256334)
Firing prefer*rvt*predict-yes*H0*1*H1
 -->
Firing rl*prefer*rvt*predict-yes*H0*1*H1*21
 -->
 (S1 ^operator O2063 = 0.3)
Firing prefer*rvt*predict-no*H0
 -->
Firing rl*prefer*rvt*predict-no*H0*2
 -->
 (S1 ^operator O2064 = 0.2550133872099196)
Firing prefer*rvt*predict-no*H0*2*H1
 -->
Firing rl*prefer*rvt*predict-no*H0*2*H1*12
 -->
 (S1 ^operator O2064 = 0.7449866897649052)
 inner elaboration loop at bottom goal.
Retracting rl*prefer*rvt*predict-no*H0*2
 -->
 (S1 ^operator O2062 = 0.2550133872099196)
Retracting rl*prefer*rvt*predict-no*H0*2*H1*12
 -->
 (S1 ^operator O2062 = 0.7449866897649052)
Retracting rl*prefer*rvt*predict-yes*H0*1
 -->
 (S1 ^operator O2061 = 0.5231196142256334)
Retracting rl*prefer*rvt*predict-yes*H0*1*H1*21
 -->
 (S1 ^operator O2061 = 0.3)

--- END Proposal Phase ---

--- Decision Phase ---
RL update rl*prefer*rvt*predict-no*H0*2 0.631495 -0.376482 0.255013 -> 0.631495 -0.376482 0.255013(R,m,v=1,0.919598,0.0743109)
RL update rl*prefer*rvt*predict-no*H0*2*H1*11 0.368505 0.376482 0.744986 -> 0.368505 0.376482 0.744987(R,m,v=1,1,0)
=>WM: (14498: S1 ^operator O2064)

  1032:    O: O2064 (predict-no)
--- END Decision Phase ---

--- Application Phase ---
	--- Firing Productions (PE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing apply*operator
 -->
 (I3 ^predict-no N1032 +  :O )
Firing apply*operator*complete
 -->
 (I3 ^predict-no N1031 -  :O )
 inner elaboration loop at bottom goal.
	--- Change Working Memory (PE) ---
=>WM: (14499: I3 ^predict-no N1032)
<=WM: (14487: N1031 ^status complete)
<=WM: (14486: I3 ^predict-no N1031)
	--- Firing Productions (IE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing monitor*world
 -->

I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
	--- Change Working Memory (IE) ---

--- END Application Phase ---
--- Output Phase ---
ENV: Agent did: predict-no for direction L in state State-A
In  State-A moving L
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isR
--- END Output Phase ---
\---- Input Phase --- 
=>WM: (14503: I2 ^dir R)
=>WM: (14502: I2 ^reward 1)
=>WM: (14501: I2 ^see 0)
=>WM: (14500: N1032 ^status complete)
<=WM: (14490: I2 ^dir L)
<=WM: (14489: I2 ^reward 1)
<=WM: (14488: I2 ^see 0)
=>WM: (14504: I2 ^level-1 L0-root)
<=WM: (14491: I2 ^level-1 L0-root)

--- END Input Phase --- 

--- Proposal Phase ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing rl*prefer*rvt*predict-yes*H0*3*H1*14
 -->
 (S1 ^operator O2063 = 0.6170732174748315)
Firing rl*prefer*rvt*predict-no*H0*4*H1*13
 -->
 (S1 ^operator O2064 = 0.4910065094545203)
Firing prefer*rvt*predict-no*H0*4*H1
 -->
Firing prefer*rvt*predict-yes*H0*3*H1
 -->
Firing elaborate*copy-see-to-output-link
 -->
 (I3 ^see 0 +)
Firing elaborate*reward*based*on*reward
 -->
 (R1036 ^value 1 +)
 (R1 ^reward R1036 +)
Firing propose*predict-yes
 -->
 (O2065 ^name predict-yes +)
 (S1 ^operator O2065 +)
Firing propose*predict-no
 -->
 (O2066 ^name predict-no +)
 (S1 ^operator O2066 +)
Firing rl*prefer*rvt*predict-no*H0*4
 -->
 (S1 ^operator O2064 = 0.1269767912163215)
Firing rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O2063 = 0.3829453632213463)
Firing prefer*rvt*predict-yes*H0
 -->
Firing prefer*rvt*predict-no*H0
 -->
Firing elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir R +)
 inner elaboration loop at bottom goal.
Retracting elaborate*copy-see-to-output-link
 -->
 (I3 ^see 0 +)
Retracting propose*predict-no
 -->
 (O2064 ^name predict-no +)
 (S1 ^operator O2064 +)
Retracting propose*predict-yes
 -->
 (O2063 ^name predict-yes +)
 (S1 ^operator O2063 +)
Retracting elaborate*reward*based*on*reward
 -->
 (R1035 ^value 1 +)
 (R1 ^reward R1035 +)
Retracting elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir L +)
Retracting rl*prefer*rvt*predict-no*H0*2*H1*12
 -->
 (S1 ^operator O2064 = 0.7449866897649052)
Retracting rl*prefer*rvt*predict-no*H0*2
 -->
 (S1 ^operator O2064 = 0.2550134055149972)
Retracting rl*prefer*rvt*predict-yes*H0*1*H1*21
 -->
 (S1 ^operator O2063 = 0.3)
Retracting rl*prefer*rvt*predict-yes*H0*1
 -->
 (S1 ^operator O2063 = 0.5231196142256334)
=>WM: (14511: S1 ^operator O2066 +)
=>WM: (14510: S1 ^operator O2065 +)
=>WM: (14509: I3 ^dir R)
=>WM: (14508: O2066 ^name predict-no)
=>WM: (14507: O2065 ^name predict-yes)
=>WM: (14506: R1036 ^value 1)
=>WM: (14505: R1 ^reward R1036)
<=WM: (14496: S1 ^operator O2063 +)
<=WM: (14497: S1 ^operator O2064 +)
<=WM: (14498: S1 ^operator O2064)
<=WM: (14482: I3 ^dir L)
<=WM: (14492: R1 ^reward R1035)
<=WM: (14495: O2064 ^name predict-no)
<=WM: (14494: O2063 ^name predict-yes)
<=WM: (14493: R1035 ^value 1)

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing prefer*rvt*predict-yes*H0
 -->
Firing rl*prefer*rvt*predict-yes*H0*3*H1*14
 -->
 (S1 ^operator O2065 = 0.6170732174748315)
Firing rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O2065 = 0.3829453632213463)
Firing prefer*rvt*predict-yes*H0*3*H1
 -->
Firing prefer*rvt*predict-no*H0
 -->
Firing rl*prefer*rvt*predict-no*H0*4*H1*13
 -->
 (S1 ^operator O2066 = 0.4910065094545203)
Firing rl*prefer*rvt*predict-no*H0*4
 -->
 (S1 ^operator O2066 = 0.1269767912163215)
Firing prefer*rvt*predict-no*H0*4*H1
 -->
 inner elaboration loop at bottom goal.
Retracting rl*prefer*rvt*predict-no*H0*4
 -->
 (S1 ^operator O2064 = 0.1269767912163215)
Retracting rl*prefer*rvt*predict-no*H0*4*H1*13
 -->
 (S1 ^operator O2064 = 0.4910065094545203)
Retracting rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O2063 = 0.3829453632213463)
Retracting rl*prefer*rvt*predict-yes*H0*3*H1*14
 -->
 (S1 ^operator O2063 = 0.6170732174748315)

--- END Proposal Phase ---

--- Decision Phase ---
RL update rl*prefer*rvt*predict-no*H0*2 0.631495 -0.376482 0.255013 -> 0.631495 -0.376482 0.255013(R,m,v=1,0.92,0.0739698)
RL update rl*prefer*rvt*predict-no*H0*2*H1*12 0.368505 0.376482 0.744987 -> 0.368505 0.376482 0.744987(R,m,v=1,1,0)
=>WM: (14512: S1 ^operator O2065)

  1033:    O: O2065 (predict-yes)
--- END Decision Phase ---

--- Application Phase ---
	--- Firing Productions (PE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing apply*operator
 -->
 (I3 ^predict-yes N1033 +  :O )
Firing apply*operator*complete
 -->
 (I3 ^predict-no N1032 -  :O )
 inner elaboration loop at bottom goal.
	--- Change Working Memory (PE) ---
=>WM: (14513: I3 ^predict-yes N1033)
<=WM: (14500: N1032 ^status complete)
<=WM: (14499: I3 ^predict-no N1032)
	--- Firing Productions (IE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing monitor*world
 -->

I see 1 and I'm going to do: predict-yes inner elaboration loop at bottom goal.
	--- Change Working Memory (IE) ---

--- END Application Phase ---
--- Output Phase ---
ENV: Agent did: predict-yes for direction R in state State-A
In  State-A moving R
ENV: (next state, see, prediction correct?) = (State-B, 1, True)
predict error 0
dir: dir isU
--- END Output Phase ---
/|\--- Input Phase --- 
=>WM: (14517: I2 ^dir U)
=>WM: (14516: I2 ^reward 1)
=>WM: (14515: I2 ^see 1)
=>WM: (14514: N1033 ^status complete)
<=WM: (14503: I2 ^dir R)
<=WM: (14502: I2 ^reward 1)
<=WM: (14501: I2 ^see 0)
=>WM: (14518: I2 ^level-1 R1-root)
<=WM: (14504: I2 ^level-1 L0-root)

--- END Input Phase --- 

--- Proposal Phase ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing elaborate*copy-see-to-output-link
 -->
 (I3 ^see 1 +)
Firing elaborate*reward*based*on*reward
 -->
 (R1037 ^value 1 +)
 (R1 ^reward R1037 +)
Firing propose*predict-yes
 -->
 (O2067 ^name predict-yes +)
 (S1 ^operator O2067 +)
Firing propose*predict-no
 -->
 (O2068 ^name predict-no +)
 (S1 ^operator O2068 +)
Firing rl*prefer*rvt*predict-no*H0*6
 -->
 (S1 ^operator O2066 = 0.9999999999999999)
Firing rl*prefer*rvt*predict-yes*H0*5
 -->
 (S1 ^operator O2065 = 0.)
Firing prefer*rvt*predict-yes*H0
 -->
Firing prefer*rvt*predict-no*H0
 -->
Firing elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir U +)
 inner elaboration loop at bottom goal.
Retracting elaborate*copy-see-to-output-link
 -->
 (I3 ^see 0 +)
Retracting propose*predict-no
 -->
 (O2066 ^name predict-no +)
 (S1 ^operator O2066 +)
Retracting propose*predict-yes
 -->
 (O2065 ^name predict-yes +)
 (S1 ^operator O2065 +)
Retracting elaborate*reward*based*on*reward
 -->
 (R1036 ^value 1 +)
 (R1 ^reward R1036 +)
Retracting elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir R +)
Retracting rl*prefer*rvt*predict-no*H0*4
 -->
 (S1 ^operator O2066 = 0.1269767912163215)
Retracting rl*prefer*rvt*predict-no*H0*4*H1*13
 -->
 (S1 ^operator O2066 = 0.4910065094545203)
Retracting rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O2065 = 0.3829453632213463)
Retracting rl*prefer*rvt*predict-yes*H0*3*H1*14
 -->
 (S1 ^operator O2065 = 0.6170732174748315)
=>WM: (14526: S1 ^operator O2068 +)
=>WM: (14525: S1 ^operator O2067 +)
=>WM: (14524: I3 ^dir U)
=>WM: (14523: O2068 ^name predict-no)
=>WM: (14522: O2067 ^name predict-yes)
=>WM: (14521: R1037 ^value 1)
=>WM: (14520: R1 ^reward R1037)
=>WM: (14519: I3 ^see 1)
<=WM: (14510: S1 ^operator O2065 +)
<=WM: (14512: S1 ^operator O2065)
<=WM: (14511: S1 ^operator O2066 +)
<=WM: (14509: I3 ^dir R)
<=WM: (14505: R1 ^reward R1036)
<=WM: (14477: I3 ^see 0)
<=WM: (14508: O2066 ^name predict-no)
<=WM: (14507: O2065 ^name predict-yes)
<=WM: (14506: R1036 ^value 1)

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing prefer*rvt*predict-yes*H0
 -->
Firing rl*prefer*rvt*predict-yes*H0*5
 -->
 (S1 ^operator O2067 = 0.)
Firing prefer*rvt*predict-no*H0
 -->
Firing rl*prefer*rvt*predict-no*H0*6
 -->
 (S1 ^operator O2068 = 0.9999999999999999)
 inner elaboration loop at bottom goal.
Retracting rl*prefer*rvt*predict-no*H0*6
 -->
 (S1 ^operator O2066 = 0.9999999999999999)
Retracting rl*prefer*rvt*predict-yes*H0*5
 -->
 (S1 ^operator O2065 = 0.)

--- END Proposal Phase ---

--- Decision Phase ---
RL update rl*prefer*rvt*predict-yes*H0*3 0.673138 -0.290193 0.382945 -> 0.673136 -0.290193 0.382943(R,m,v=1,0.962264,0.0365417)
RL update rl*prefer*rvt*predict-yes*H0*3*H1*14 0.326879 0.290194 0.617073 -> 0.326876 0.290194 0.61707(R,m,v=1,1,0)
=>WM: (14527: S1 ^operator O2068)

  1034:    O: O2068 (predict-no)
--- END Decision Phase ---

--- Application Phase ---
	--- Firing Productions (PE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing apply*operator
 -->
 (I3 ^predict-no N1034 +  :O )
Firing apply*operator*complete
 -->
 (I3 ^predict-yes N1033 -  :O )
 inner elaboration loop at bottom goal.
	--- Change Working Memory (PE) ---
=>WM: (14528: I3 ^predict-no N1034)
<=WM: (14514: N1033 ^status complete)
<=WM: (14513: I3 ^predict-yes N1033)
	--- Firing Productions (IE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing monitor*world
 -->

I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
	--- Change Working Memory (IE) ---

--- END Application Phase ---
--- Output Phase ---
ENV: Agent did: predict-no for direction U in state State-B
In  State-B moving U
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isR
--- END Output Phase ---
-/--- Input Phase --- 
=>WM: (14532: I2 ^dir R)
=>WM: (14531: I2 ^reward 1)
=>WM: (14530: I2 ^see 0)
=>WM: (14529: N1034 ^status complete)
<=WM: (14517: I2 ^dir U)
<=WM: (14516: I2 ^reward 1)
<=WM: (14515: I2 ^see 1)
=>WM: (14533: I2 ^level-1 R1-root)
<=WM: (14518: I2 ^level-1 R1-root)

--- END Input Phase --- 

--- Proposal Phase ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing rl*prefer*rvt*predict-yes*H0*3*H1*16
 -->
 (S1 ^operator O2067 = 0.08783148430849691)
Firing rl*prefer*rvt*predict-no*H0*4*H1*15
 -->
 (S1 ^operator O2068 = 0.8730233005215732)
Firing prefer*rvt*predict-no*H0*4*H1
 -->
Firing prefer*rvt*predict-yes*H0*3*H1
 -->
Firing elaborate*copy-see-to-output-link
 -->
 (I3 ^see 0 +)
Firing elaborate*reward*based*on*reward
 -->
 (R1038 ^value 1 +)
 (R1 ^reward R1038 +)
Firing propose*predict-yes
 -->
 (O2069 ^name predict-yes +)
 (S1 ^operator O2069 +)
Firing propose*predict-no
 -->
 (O2070 ^name predict-no +)
 (S1 ^operator O2070 +)
Firing rl*prefer*rvt*predict-no*H0*4
 -->
 (S1 ^operator O2068 = 0.1269767912163215)
Firing rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O2067 = 0.3829425761169197)
Firing prefer*rvt*predict-yes*H0
 -->
Firing prefer*rvt*predict-no*H0
 -->
Firing elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir R +)
 inner elaboration loop at bottom goal.
Retracting elaborate*copy-see-to-output-link
 -->
 (I3 ^see 1 +)
Retracting propose*predict-no
 -->
 (O2068 ^name predict-no +)
 (S1 ^operator O2068 +)
Retracting propose*predict-yes
 -->
 (O2067 ^name predict-yes +)
 (S1 ^operator O2067 +)
Retracting elaborate*reward*based*on*reward
 -->
 (R1037 ^value 1 +)
 (R1 ^reward R1037 +)
Retracting elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir U +)
Retracting rl*prefer*rvt*predict-no*H0*6
 -->
 (S1 ^operator O2068 = 0.9999999999999999)
Retracting rl*prefer*rvt*predict-yes*H0*5
 -->
 (S1 ^operator O2067 = 0.)
=>WM: (14541: S1 ^operator O2070 +)
=>WM: (14540: S1 ^operator O2069 +)
=>WM: (14539: I3 ^dir R)
=>WM: (14538: O2070 ^name predict-no)
=>WM: (14537: O2069 ^name predict-yes)
=>WM: (14536: R1038 ^value 1)
=>WM: (14535: R1 ^reward R1038)
=>WM: (14534: I3 ^see 0)
<=WM: (14525: S1 ^operator O2067 +)
<=WM: (14526: S1 ^operator O2068 +)
<=WM: (14527: S1 ^operator O2068)
<=WM: (14524: I3 ^dir U)
<=WM: (14520: R1 ^reward R1037)
<=WM: (14519: I3 ^see 1)
<=WM: (14523: O2068 ^name predict-no)
<=WM: (14522: O2067 ^name predict-yes)
<=WM: (14521: R1037 ^value 1)

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing prefer*rvt*predict-yes*H0
 -->
Firing rl*prefer*rvt*predict-yes*H0*3*H1*16
 -->
 (S1 ^operator O2069 = 0.08783148430849691)
Firing rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O2069 = 0.3829425761169197)
Firing prefer*rvt*predict-yes*H0*3*H1
 -->
Firing prefer*rvt*predict-no*H0
 -->
Firing rl*prefer*rvt*predict-no*H0*4*H1*15
 -->
 (S1 ^operator O2070 = 0.8730233005215732)
Firing rl*prefer*rvt*predict-no*H0*4
 -->
 (S1 ^operator O2070 = 0.1269767912163215)
Firing prefer*rvt*predict-no*H0*4*H1
 -->
 inner elaboration loop at bottom goal.
Retracting rl*prefer*rvt*predict-no*H0*4
 -->
 (S1 ^operator O2068 = 0.1269767912163215)
Retracting rl*prefer*rvt*predict-no*H0*4*H1*15
 -->
 (S1 ^operator O2068 = 0.8730233005215732)
Retracting rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O2067 = 0.3829425761169197)
Retracting rl*prefer*rvt*predict-yes*H0*3*H1*16
 -->
 (S1 ^operator O2067 = 0.08783148430849691)

--- END Proposal Phase ---

--- Decision Phase ---
RL update rl*prefer*rvt*predict-no*H0*6 1 0 1 -> 1 0 1(R,m,v=1,1,0)
=>WM: (14542: S1 ^operator O2070)

  1035:    O: O2070 (predict-no)
--- END Decision Phase ---

--- Application Phase ---
	--- Firing Productions (PE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing apply*operator
 -->
 (I3 ^predict-no N1035 +  :O )
Firing apply*operator*complete
 -->
 (I3 ^predict-no N1034 -  :O )
 inner elaboration loop at bottom goal.
	--- Change Working Memory (PE) ---
=>WM: (14543: I3 ^predict-no N1035)
<=WM: (14529: N1034 ^status complete)
<=WM: (14528: I3 ^predict-no N1034)
	--- Firing Productions (IE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing monitor*world
 -->

I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
	--- Change Working Memory (IE) ---

--- END Application Phase ---
--- Output Phase ---
ENV: Agent did: predict-no for direction R in state State-B
In  State-B moving R
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isR
--- END Output Phase ---
|\---- Input Phase --- 
=>WM: (14547: I2 ^dir R)
=>WM: (14546: I2 ^reward 1)
=>WM: (14545: I2 ^see 0)
=>WM: (14544: N1035 ^status complete)
<=WM: (14532: I2 ^dir R)
<=WM: (14531: I2 ^reward 1)
<=WM: (14530: I2 ^see 0)
=>WM: (14548: I2 ^level-1 R0-root)
<=WM: (14533: I2 ^level-1 R1-root)

--- END Input Phase --- 

--- Proposal Phase ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing rl*prefer*rvt*predict-yes*H0*3*H1*18
 -->
 (S1 ^operator O2069 = 0.2696941111808541)
Firing rl*prefer*rvt*predict-no*H0*4*H1*17
 -->
 (S1 ^operator O2070 = 0.8730230210936206)
Firing prefer*rvt*predict-no*H0*4*H1
 -->
Firing prefer*rvt*predict-yes*H0*3*H1
 -->
Firing elaborate*copy-see-to-output-link
 -->
 (I3 ^see 0 +)
Firing elaborate*reward*based*on*reward
 -->
 (R1039 ^value 1 +)
 (R1 ^reward R1039 +)
Firing propose*predict-yes
 -->
 (O2071 ^name predict-yes +)
 (S1 ^operator O2071 +)
Firing propose*predict-no
 -->
 (O2072 ^name predict-no +)
 (S1 ^operator O2072 +)
Firing rl*prefer*rvt*predict-no*H0*4
 -->
 (S1 ^operator O2070 = 0.1269767912163215)
Firing rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O2069 = 0.3829425761169197)
Firing prefer*rvt*predict-yes*H0
 -->
Firing prefer*rvt*predict-no*H0
 -->
Firing elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir R +)
 inner elaboration loop at bottom goal.
Retracting elaborate*copy-see-to-output-link
 -->
 (I3 ^see 0 +)
Retracting propose*predict-no
 -->
 (O2070 ^name predict-no +)
 (S1 ^operator O2070 +)
Retracting propose*predict-yes
 -->
 (O2069 ^name predict-yes +)
 (S1 ^operator O2069 +)
Retracting elaborate*reward*based*on*reward
 -->
 (R1038 ^value 1 +)
 (R1 ^reward R1038 +)
Retracting elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir R +)
Retracting rl*prefer*rvt*predict-no*H0*4
 -->
 (S1 ^operator O2070 = 0.1269767912163215)
Retracting rl*prefer*rvt*predict-no*H0*4*H1*15
 -->
 (S1 ^operator O2070 = 0.8730233005215732)
Retracting rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O2069 = 0.3829425761169197)
Retracting rl*prefer*rvt*predict-yes*H0*3*H1*16
 -->
 (S1 ^operator O2069 = 0.08783148430849691)
=>WM: (14554: S1 ^operator O2072 +)
=>WM: (14553: S1 ^operator O2071 +)
=>WM: (14552: O2072 ^name predict-no)
=>WM: (14551: O2071 ^name predict-yes)
=>WM: (14550: R1039 ^value 1)
=>WM: (14549: R1 ^reward R1039)
<=WM: (14540: S1 ^operator O2069 +)
<=WM: (14541: S1 ^operator O2070 +)
<=WM: (14542: S1 ^operator O2070)
<=WM: (14535: R1 ^reward R1038)
<=WM: (14538: O2070 ^name predict-no)
<=WM: (14537: O2069 ^name predict-yes)
<=WM: (14536: R1038 ^value 1)

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing prefer*rvt*predict-yes*H0
 -->
Firing rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O2071 = 0.3829425761169197)
Firing prefer*rvt*predict-yes*H0*3*H1
 -->
Firing rl*prefer*rvt*predict-yes*H0*3*H1*18
 -->
 (S1 ^operator O2071 = 0.2696941111808541)
Firing prefer*rvt*predict-no*H0
 -->
Firing rl*prefer*rvt*predict-no*H0*4
 -->
 (S1 ^operator O2072 = 0.1269767912163215)
Firing prefer*rvt*predict-no*H0*4*H1
 -->
Firing rl*prefer*rvt*predict-no*H0*4*H1*17
 -->
 (S1 ^operator O2072 = 0.8730230210936206)
 inner elaboration loop at bottom goal.
Retracting rl*prefer*rvt*predict-no*H0*4
 -->
 (S1 ^operator O2070 = 0.1269767912163215)
Retracting rl*prefer*rvt*predict-no*H0*4*H1*17
 -->
 (S1 ^operator O2070 = 0.8730230210936206)
Retracting rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O2069 = 0.3829425761169197)
Retracting rl*prefer*rvt*predict-yes*H0*3*H1*18
 -->
 (S1 ^operator O2069 = 0.2696941111808541)

--- END Proposal Phase ---

--- Decision Phase ---
RL update rl*prefer*rvt*predict-no*H0*4 0.814714 -0.687737 0.126977 -> 0.814714 -0.687737 0.126977(R,m,v=1,0.950549,0.0472649)
RL update rl*prefer*rvt*predict-no*H0*4*H1*15 0.185286 0.687737 0.873023 -> 0.185286 0.687737 0.873023(R,m,v=1,1,0)
=>WM: (14555: S1 ^operator O2072)

  1036:    O: O2072 (predict-no)
--- END Decision Phase ---

--- Application Phase ---
	--- Firing Productions (PE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing apply*operator
 -->
 (I3 ^predict-no N1036 +  :O )
Firing apply*operator*complete
 -->
 (I3 ^predict-no N1035 -  :O )
 inner elaboration loop at bottom goal.
	--- Change Working Memory (PE) ---
=>WM: (14556: I3 ^predict-no N1036)
<=WM: (14544: N1035 ^status complete)
<=WM: (14543: I3 ^predict-no N1035)
	--- Firing Productions (IE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing monitor*world
 -->

I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
	--- Change Working Memory (IE) ---

--- END Application Phase ---
--- Output Phase ---
ENV: Agent did: predict-no for direction R in state State-B
In  State-B moving R
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isL
--- END Output Phase ---
/|\--- Input Phase --- 
=>WM: (14560: I2 ^dir L)
=>WM: (14559: I2 ^reward 1)
=>WM: (14558: I2 ^see 0)
=>WM: (14557: N1036 ^status complete)
<=WM: (14547: I2 ^dir R)
<=WM: (14546: I2 ^reward 1)
<=WM: (14545: I2 ^see 0)
=>WM: (14561: I2 ^level-1 R0-root)
<=WM: (14548: I2 ^level-1 R0-root)

--- END Input Phase --- 

--- Proposal Phase ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing rl*prefer*rvt*predict-yes*H0*1*H1*19
 -->
 (S1 ^operator O2071 = 0.4768816476246801)
Firing rl*prefer*rvt*predict-no*H0*2*H1*7
 -->
 (S1 ^operator O2072 = 0.1700769046561409)
Firing prefer*rvt*predict-no*H0*2*H1
 -->
Firing prefer*rvt*predict-yes*H0*1*H1
 -->
Firing elaborate*copy-see-to-output-link
 -->
 (I3 ^see 0 +)
Firing elaborate*reward*based*on*reward
 -->
 (R1040 ^value 1 +)
 (R1 ^reward R1040 +)
Firing propose*predict-yes
 -->
 (O2073 ^name predict-yes +)
 (S1 ^operator O2073 +)
Firing propose*predict-no
 -->
 (O2074 ^name predict-no +)
 (S1 ^operator O2074 +)
Firing rl*prefer*rvt*predict-no*H0*2
 -->
 (S1 ^operator O2072 = 0.2550133912230119)
Firing rl*prefer*rvt*predict-yes*H0*1
 -->
 (S1 ^operator O2071 = 0.5231196142256334)
Firing prefer*rvt*predict-yes*H0
 -->
Firing prefer*rvt*predict-no*H0
 -->
Firing elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir L +)
 inner elaboration loop at bottom goal.
Retracting elaborate*copy-see-to-output-link
 -->
 (I3 ^see 0 +)
Retracting propose*predict-no
 -->
 (O2072 ^name predict-no +)
 (S1 ^operator O2072 +)
Retracting propose*predict-yes
 -->
 (O2071 ^name predict-yes +)
 (S1 ^operator O2071 +)
Retracting elaborate*reward*based*on*reward
 -->
 (R1039 ^value 1 +)
 (R1 ^reward R1039 +)
Retracting elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir R +)
Retracting rl*prefer*rvt*predict-no*H0*4*H1*17
 -->
 (S1 ^operator O2072 = 0.8730230210936206)
Retracting rl*prefer*rvt*predict-no*H0*4
 -->
 (S1 ^operator O2072 = 0.1269767774556373)
Retracting rl*prefer*rvt*predict-yes*H0*3*H1*18
 -->
 (S1 ^operator O2071 = 0.2696941111808541)
Retracting rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O2071 = 0.3829425761169197)
=>WM: (14568: S1 ^operator O2074 +)
=>WM: (14567: S1 ^operator O2073 +)
=>WM: (14566: I3 ^dir L)
=>WM: (14565: O2074 ^name predict-no)
=>WM: (14564: O2073 ^name predict-yes)
=>WM: (14563: R1040 ^value 1)
=>WM: (14562: R1 ^reward R1040)
<=WM: (14553: S1 ^operator O2071 +)
<=WM: (14554: S1 ^operator O2072 +)
<=WM: (14555: S1 ^operator O2072)
<=WM: (14539: I3 ^dir R)
<=WM: (14549: R1 ^reward R1039)
<=WM: (14552: O2072 ^name predict-no)
<=WM: (14551: O2071 ^name predict-yes)
<=WM: (14550: R1039 ^value 1)

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing prefer*rvt*predict-yes*H0
 -->
Firing rl*prefer*rvt*predict-yes*H0*1*H1*19
 -->
 (S1 ^operator O2073 = 0.4768816476246801)
Firing rl*prefer*rvt*predict-yes*H0*1
 -->
 (S1 ^operator O2073 = 0.5231196142256334)
Firing prefer*rvt*predict-yes*H0*1*H1
 -->
Firing prefer*rvt*predict-no*H0
 -->
Firing rl*prefer*rvt*predict-no*H0*2*H1*7
 -->
 (S1 ^operator O2074 = 0.1700769046561409)
Firing rl*prefer*rvt*predict-no*H0*2
 -->
 (S1 ^operator O2074 = 0.2550133912230119)
Firing prefer*rvt*predict-no*H0*2*H1
 -->
 inner elaboration loop at bottom goal.
Retracting rl*prefer*rvt*predict-no*H0*2
 -->
 (S1 ^operator O2072 = 0.2550133912230119)
Retracting rl*prefer*rvt*predict-no*H0*2*H1*7
 -->
 (S1 ^operator O2072 = 0.1700769046561409)
Retracting rl*prefer*rvt*predict-yes*H0*1
 -->
 (S1 ^operator O2071 = 0.5231196142256334)
Retracting rl*prefer*rvt*predict-yes*H0*1*H1*19
 -->
 (S1 ^operator O2071 = 0.4768816476246801)

--- END Proposal Phase ---

--- Decision Phase ---
RL update rl*prefer*rvt*predict-no*H0*4 0.814714 -0.687737 0.126977 -> 0.814714 -0.687737 0.126977(R,m,v=1,0.95082,0.0470186)
RL update rl*prefer*rvt*predict-no*H0*4*H1*17 0.185286 0.687737 0.873023 -> 0.185286 0.687737 0.873023(R,m,v=1,1,0)
=>WM: (14569: S1 ^operator O2073)

  1037:    O: O2073 (predict-yes)
--- END Decision Phase ---

--- Application Phase ---
	--- Firing Productions (PE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing apply*operator
 -->
 (I3 ^predict-yes N1037 +  :O )
Firing apply*operator*complete
 -->
 (I3 ^predict-no N1036 -  :O )
 inner elaboration loop at bottom goal.
	--- Change Working Memory (PE) ---
=>WM: (14570: I3 ^predict-yes N1037)
<=WM: (14557: N1036 ^status complete)
<=WM: (14556: I3 ^predict-no N1036)
	--- Firing Productions (IE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing monitor*world
 -->

I see 1 and I'm going to do: predict-yes inner elaboration loop at bottom goal.
	--- Change Working Memory (IE) ---

--- END Application Phase ---
--- Output Phase ---
ENV: Agent did: predict-yes for direction L in state State-B
In  State-B moving L
ENV: (next state, see, prediction correct?) = (State-A, 1, True)
predict error 0
dir: dir isU
--- END Output Phase ---
-/--- Input Phase --- 
=>WM: (14574: I2 ^dir U)
=>WM: (14573: I2 ^reward 1)
=>WM: (14572: I2 ^see 1)
=>WM: (14571: N1037 ^status complete)
<=WM: (14560: I2 ^dir L)
<=WM: (14559: I2 ^reward 1)
<=WM: (14558: I2 ^see 0)
=>WM: (14575: I2 ^level-1 L1-root)
<=WM: (14561: I2 ^level-1 R0-root)

--- END Input Phase --- 

--- Proposal Phase ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing elaborate*copy-see-to-output-link
 -->
 (I3 ^see 1 +)
Firing elaborate*reward*based*on*reward
 -->
 (R1041 ^value 1 +)
 (R1 ^reward R1041 +)
Firing propose*predict-yes
 -->
 (O2075 ^name predict-yes +)
 (S1 ^operator O2075 +)
Firing propose*predict-no
 -->
 (O2076 ^name predict-no +)
 (S1 ^operator O2076 +)
Firing rl*prefer*rvt*predict-no*H0*6
 -->
 (S1 ^operator O2074 = 0.9999999999999999)
Firing rl*prefer*rvt*predict-yes*H0*5
 -->
 (S1 ^operator O2073 = 0.)
Firing prefer*rvt*predict-yes*H0
 -->
Firing prefer*rvt*predict-no*H0
 -->
Firing elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir U +)
 inner elaboration loop at bottom goal.
Retracting elaborate*copy-see-to-output-link
 -->
 (I3 ^see 0 +)
Retracting propose*predict-no
 -->
 (O2074 ^name predict-no +)
 (S1 ^operator O2074 +)
Retracting propose*predict-yes
 -->
 (O2073 ^name predict-yes +)
 (S1 ^operator O2073 +)
Retracting elaborate*reward*based*on*reward
 -->
 (R1040 ^value 1 +)
 (R1 ^reward R1040 +)
Retracting elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir L +)
Retracting rl*prefer*rvt*predict-no*H0*2
 -->
 (S1 ^operator O2074 = 0.2550133912230119)
Retracting rl*prefer*rvt*predict-no*H0*2*H1*7
 -->
 (S1 ^operator O2074 = 0.1700769046561409)
Retracting rl*prefer*rvt*predict-yes*H0*1
 -->
 (S1 ^operator O2073 = 0.5231196142256334)
Retracting rl*prefer*rvt*predict-yes*H0*1*H1*19
 -->
 (S1 ^operator O2073 = 0.4768816476246801)
=>WM: (14583: S1 ^operator O2076 +)
=>WM: (14582: S1 ^operator O2075 +)
=>WM: (14581: I3 ^dir U)
=>WM: (14580: O2076 ^name predict-no)
=>WM: (14579: O2075 ^name predict-yes)
=>WM: (14578: R1041 ^value 1)
=>WM: (14577: R1 ^reward R1041)
=>WM: (14576: I3 ^see 1)
<=WM: (14567: S1 ^operator O2073 +)
<=WM: (14569: S1 ^operator O2073)
<=WM: (14568: S1 ^operator O2074 +)
<=WM: (14566: I3 ^dir L)
<=WM: (14562: R1 ^reward R1040)
<=WM: (14534: I3 ^see 0)
<=WM: (14565: O2074 ^name predict-no)
<=WM: (14564: O2073 ^name predict-yes)
<=WM: (14563: R1040 ^value 1)

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing prefer*rvt*predict-yes*H0
 -->
Firing rl*prefer*rvt*predict-yes*H0*5
 -->
 (S1 ^operator O2075 = 0.)
Firing prefer*rvt*predict-no*H0
 -->
Firing rl*prefer*rvt*predict-no*H0*6
 -->
 (S1 ^operator O2076 = 0.9999999999999999)
 inner elaboration loop at bottom goal.
Retracting rl*prefer*rvt*predict-no*H0*6
 -->
 (S1 ^operator O2074 = 0.9999999999999999)
Retracting rl*prefer*rvt*predict-yes*H0*5
 -->
 (S1 ^operator O2073 = 0.)

--- END Proposal Phase ---

--- Decision Phase ---
RL update rl*prefer*rvt*predict-yes*H0*1 0.727959 -0.20484 0.52312 -> 0.727959 -0.20484 0.523119(R,m,v=1,0.979866,0.0198621)
RL update rl*prefer*rvt*predict-yes*H0*1*H1*19 0.272042 0.204839 0.476882 -> 0.272042 0.204839 0.476881(R,m,v=1,1,0)
=>WM: (14584: S1 ^operator O2076)

  1038:    O: O2076 (predict-no)
--- END Decision Phase ---

--- Application Phase ---
	--- Firing Productions (PE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing apply*operator
 -->
 (I3 ^predict-no N1038 +  :O )
Firing apply*operator*complete
 -->
 (I3 ^predict-yes N1037 -  :O )
 inner elaboration loop at bottom goal.
	--- Change Working Memory (PE) ---
=>WM: (14585: I3 ^predict-no N1038)
<=WM: (14571: N1037 ^status complete)
<=WM: (14570: I3 ^predict-yes N1037)
	--- Firing Productions (IE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing monitor*world
 -->

I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
	--- Change Working Memory (IE) ---

--- END Application Phase ---
--- Output Phase ---
ENV: Agent did: predict-no for direction U in state State-A
In  State-A moving U
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isR
--- END Output Phase ---
|\---- Input Phase --- 
=>WM: (14589: I2 ^dir R)
=>WM: (14588: I2 ^reward 1)
=>WM: (14587: I2 ^see 0)
=>WM: (14586: N1038 ^status complete)
<=WM: (14574: I2 ^dir U)
<=WM: (14573: I2 ^reward 1)
<=WM: (14572: I2 ^see 1)
=>WM: (14590: I2 ^level-1 L1-root)
<=WM: (14575: I2 ^level-1 L1-root)

--- END Input Phase --- 

--- Proposal Phase ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing rl*prefer*rvt*predict-yes*H0*3*H1*9
 -->
 (S1 ^operator O2075 = 0.6170465502571644)
Firing rl*prefer*rvt*predict-no*H0*4*H1*8
 -->
 (S1 ^operator O2076 = 0.4901349546100854)
Firing prefer*rvt*predict-no*H0*4*H1
 -->
Firing prefer*rvt*predict-yes*H0*3*H1
 -->
Firing elaborate*copy-see-to-output-link
 -->
 (I3 ^see 0 +)
Firing elaborate*reward*based*on*reward
 -->
 (R1042 ^value 1 +)
 (R1 ^reward R1042 +)
Firing propose*predict-yes
 -->
 (O2077 ^name predict-yes +)
 (S1 ^operator O2077 +)
Firing propose*predict-no
 -->
 (O2078 ^name predict-no +)
 (S1 ^operator O2078 +)
Firing rl*prefer*rvt*predict-no*H0*4
 -->
 (S1 ^operator O2076 = 0.1269768076732486)
Firing rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O2075 = 0.3829425761169197)
Firing prefer*rvt*predict-yes*H0
 -->
Firing prefer*rvt*predict-no*H0
 -->
Firing elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir R +)
 inner elaboration loop at bottom goal.
Retracting elaborate*copy-see-to-output-link
 -->
 (I3 ^see 1 +)
Retracting propose*predict-no
 -->
 (O2076 ^name predict-no +)
 (S1 ^operator O2076 +)
Retracting propose*predict-yes
 -->
 (O2075 ^name predict-yes +)
 (S1 ^operator O2075 +)
Retracting elaborate*reward*based*on*reward
 -->
 (R1041 ^value 1 +)
 (R1 ^reward R1041 +)
Retracting elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir U +)
Retracting rl*prefer*rvt*predict-no*H0*6
 -->
 (S1 ^operator O2076 = 0.9999999999999999)
Retracting rl*prefer*rvt*predict-yes*H0*5
 -->
 (S1 ^operator O2075 = 0.)
=>WM: (14598: S1 ^operator O2078 +)
=>WM: (14597: S1 ^operator O2077 +)
=>WM: (14596: I3 ^dir R)
=>WM: (14595: O2078 ^name predict-no)
=>WM: (14594: O2077 ^name predict-yes)
=>WM: (14593: R1042 ^value 1)
=>WM: (14592: R1 ^reward R1042)
=>WM: (14591: I3 ^see 0)
<=WM: (14582: S1 ^operator O2075 +)
<=WM: (14583: S1 ^operator O2076 +)
<=WM: (14584: S1 ^operator O2076)
<=WM: (14581: I3 ^dir U)
<=WM: (14577: R1 ^reward R1041)
<=WM: (14576: I3 ^see 1)
<=WM: (14580: O2076 ^name predict-no)
<=WM: (14579: O2075 ^name predict-yes)
<=WM: (14578: R1041 ^value 1)

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing prefer*rvt*predict-yes*H0
 -->
Firing rl*prefer*rvt*predict-yes*H0*3*H1*9
 -->
 (S1 ^operator O2077 = 0.6170465502571644)
Firing rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O2077 = 0.3829425761169197)
Firing prefer*rvt*predict-yes*H0*3*H1
 -->
Firing prefer*rvt*predict-no*H0
 -->
Firing rl*prefer*rvt*predict-no*H0*4*H1*8
 -->
 (S1 ^operator O2078 = 0.4901349546100854)
Firing rl*prefer*rvt*predict-no*H0*4
 -->
 (S1 ^operator O2078 = 0.1269768076732486)
Firing prefer*rvt*predict-no*H0*4*H1
 -->
 inner elaboration loop at bottom goal.
Retracting rl*prefer*rvt*predict-no*H0*4
 -->
 (S1 ^operator O2076 = 0.1269768076732486)
Retracting rl*prefer*rvt*predict-no*H0*4*H1*8
 -->
 (S1 ^operator O2076 = 0.4901349546100854)
Retracting rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O2075 = 0.3829425761169197)
Retracting rl*prefer*rvt*predict-yes*H0*3*H1*9
 -->
 (S1 ^operator O2075 = 0.6170465502571644)

--- END Proposal Phase ---

--- Decision Phase ---
RL update rl*prefer*rvt*predict-no*H0*6 1 0 1 -> 1 0 1(R,m,v=1,1,0)
=>WM: (14599: S1 ^operator O2077)

  1039:    O: O2077 (predict-yes)
--- END Decision Phase ---

--- Application Phase ---
	--- Firing Productions (PE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing apply*operator
 -->
 (I3 ^predict-yes N1039 +  :O )
Firing apply*operator*complete
 -->
 (I3 ^predict-no N1038 -  :O )
 inner elaboration loop at bottom goal.
	--- Change Working Memory (PE) ---
=>WM: (14600: I3 ^predict-yes N1039)
<=WM: (14586: N1038 ^status complete)
<=WM: (14585: I3 ^predict-no N1038)
	--- Firing Productions (IE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing monitor*world
 -->

I see 1 and I'm going to do: predict-yes inner elaboration loop at bottom goal.
	--- Change Working Memory (IE) ---

--- END Application Phase ---
--- Output Phase ---
ENV: Agent did: predict-yes for direction R in state State-A
In  State-A moving R
ENV: (next state, see, prediction correct?) = (State-B, 1, True)
predict error 0
dir: dir isR
--- END Output Phase ---
/|\--- Input Phase --- 
=>WM: (14604: I2 ^dir R)
=>WM: (14603: I2 ^reward 1)
=>WM: (14602: I2 ^see 1)
=>WM: (14601: N1039 ^status complete)
<=WM: (14589: I2 ^dir R)
<=WM: (14588: I2 ^reward 1)
<=WM: (14587: I2 ^see 0)
=>WM: (14605: I2 ^level-1 R1-root)
<=WM: (14590: I2 ^level-1 L1-root)

--- END Input Phase --- 

--- Proposal Phase ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing rl*prefer*rvt*predict-yes*H0*3*H1*16
 -->
 (S1 ^operator O2077 = 0.08783148430849691)
Firing rl*prefer*rvt*predict-no*H0*4*H1*15
 -->
 (S1 ^operator O2078 = 0.8730232867608889)
Firing prefer*rvt*predict-no*H0*4*H1
 -->
Firing prefer*rvt*predict-yes*H0*3*H1
 -->
Firing elaborate*copy-see-to-output-link
 -->
 (I3 ^see 1 +)
Firing elaborate*reward*based*on*reward
 -->
 (R1043 ^value 1 +)
 (R1 ^reward R1043 +)
Firing propose*predict-yes
 -->
 (O2079 ^name predict-yes +)
 (S1 ^operator O2079 +)
Firing propose*predict-no
 -->
 (O2080 ^name predict-no +)
 (S1 ^operator O2080 +)
Firing rl*prefer*rvt*predict-no*H0*4
 -->
 (S1 ^operator O2078 = 0.1269768076732486)
Firing rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O2077 = 0.3829425761169197)
Firing prefer*rvt*predict-yes*H0
 -->
Firing prefer*rvt*predict-no*H0
 -->
Firing elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir R +)
 inner elaboration loop at bottom goal.
Retracting elaborate*copy-see-to-output-link
 -->
 (I3 ^see 0 +)
Retracting propose*predict-no
 -->
 (O2078 ^name predict-no +)
 (S1 ^operator O2078 +)
Retracting propose*predict-yes
 -->
 (O2077 ^name predict-yes +)
 (S1 ^operator O2077 +)
Retracting elaborate*reward*based*on*reward
 -->
 (R1042 ^value 1 +)
 (R1 ^reward R1042 +)
Retracting elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir R +)
Retracting rl*prefer*rvt*predict-no*H0*4
 -->
 (S1 ^operator O2078 = 0.1269768076732486)
Retracting rl*prefer*rvt*predict-no*H0*4*H1*8
 -->
 (S1 ^operator O2078 = 0.4901349546100854)
Retracting rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O2077 = 0.3829425761169197)
Retracting rl*prefer*rvt*predict-yes*H0*3*H1*9
 -->
 (S1 ^operator O2077 = 0.6170465502571644)
=>WM: (14612: S1 ^operator O2080 +)
=>WM: (14611: S1 ^operator O2079 +)
=>WM: (14610: O2080 ^name predict-no)
=>WM: (14609: O2079 ^name predict-yes)
=>WM: (14608: R1043 ^value 1)
=>WM: (14607: R1 ^reward R1043)
=>WM: (14606: I3 ^see 1)
<=WM: (14597: S1 ^operator O2077 +)
<=WM: (14599: S1 ^operator O2077)
<=WM: (14598: S1 ^operator O2078 +)
<=WM: (14592: R1 ^reward R1042)
<=WM: (14591: I3 ^see 0)
<=WM: (14595: O2078 ^name predict-no)
<=WM: (14594: O2077 ^name predict-yes)
<=WM: (14593: R1042 ^value 1)

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing prefer*rvt*predict-yes*H0
 -->
Firing rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O2079 = 0.3829425761169197)
Firing prefer*rvt*predict-yes*H0*3*H1
 -->
Firing rl*prefer*rvt*predict-yes*H0*3*H1*16
 -->
 (S1 ^operator O2079 = 0.08783148430849691)
Firing prefer*rvt*predict-no*H0
 -->
Firing rl*prefer*rvt*predict-no*H0*4
 -->
 (S1 ^operator O2080 = 0.1269768076732486)
Firing prefer*rvt*predict-no*H0*4*H1
 -->
Firing rl*prefer*rvt*predict-no*H0*4*H1*15
 -->
 (S1 ^operator O2080 = 0.8730232867608889)
 inner elaboration loop at bottom goal.
Retracting rl*prefer*rvt*predict-no*H0*4
 -->
 (S1 ^operator O2078 = 0.1269768076732486)
Retracting rl*prefer*rvt*predict-no*H0*4*H1*15
 -->
 (S1 ^operator O2078 = 0.8730232867608889)
Retracting rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O2077 = 0.3829425761169197)
Retracting rl*prefer*rvt*predict-yes*H0*3*H1*16
 -->
 (S1 ^operator O2077 = 0.08783148430849691)

--- END Proposal Phase ---

--- Decision Phase ---
RL update rl*prefer*rvt*predict-yes*H0*3 0.673136 -0.290193 0.382943 -> 0.673137 -0.290193 0.382944(R,m,v=1,0.9625,0.0363208)
RL update rl*prefer*rvt*predict-yes*H0*3*H1*9 0.326855 0.290192 0.617047 -> 0.326856 0.290192 0.617048(R,m,v=1,1,0)
=>WM: (14613: S1 ^operator O2080)

  1040:    O: O2080 (predict-no)
--- END Decision Phase ---

--- Application Phase ---
	--- Firing Productions (PE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing apply*operator
 -->
 (I3 ^predict-no N1040 +  :O )
Firing apply*operator*complete
 -->
 (I3 ^predict-yes N1039 -  :O )
 inner elaboration loop at bottom goal.
	--- Change Working Memory (PE) ---
=>WM: (14614: I3 ^predict-no N1040)
<=WM: (14601: N1039 ^status complete)
<=WM: (14600: I3 ^predict-yes N1039)
	--- Firing Productions (IE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing monitor*world
 -->

I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
	--- Change Working Memory (IE) ---

--- END Application Phase ---
--- Output Phase ---
ENV: Agent did: predict-no for direction R in state State-B
In  State-B moving R
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isR
--- END Output Phase ---
-/--- Input Phase --- 
=>WM: (14618: I2 ^dir R)
=>WM: (14617: I2 ^reward 1)
=>WM: (14616: I2 ^see 0)
=>WM: (14615: N1040 ^status complete)
<=WM: (14604: I2 ^dir R)
<=WM: (14603: I2 ^reward 1)
<=WM: (14602: I2 ^see 1)
=>WM: (14619: I2 ^level-1 R0-root)
<=WM: (14605: I2 ^level-1 R1-root)

--- END Input Phase --- 

--- Proposal Phase ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing rl*prefer*rvt*predict-yes*H0*3*H1*18
 -->
 (S1 ^operator O2079 = 0.2696941111808541)
Firing rl*prefer*rvt*predict-no*H0*4*H1*17
 -->
 (S1 ^operator O2080 = 0.8730230513112319)
Firing prefer*rvt*predict-no*H0*4*H1
 -->
Firing prefer*rvt*predict-yes*H0*3*H1
 -->
Firing elaborate*copy-see-to-output-link
 -->
 (I3 ^see 0 +)
Firing elaborate*reward*based*on*reward
 -->
 (R1044 ^value 1 +)
 (R1 ^reward R1044 +)
Firing propose*predict-yes
 -->
 (O2081 ^name predict-yes +)
 (S1 ^operator O2081 +)
Firing propose*predict-no
 -->
 (O2082 ^name predict-no +)
 (S1 ^operator O2082 +)
Firing rl*prefer*rvt*predict-no*H0*4
 -->
 (S1 ^operator O2080 = 0.1269768076732486)
Firing rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O2079 = 0.3829442071608071)
Firing prefer*rvt*predict-yes*H0
 -->
Firing prefer*rvt*predict-no*H0
 -->
Firing elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir R +)
 inner elaboration loop at bottom goal.
Retracting elaborate*copy-see-to-output-link
 -->
 (I3 ^see 1 +)
Retracting propose*predict-no
 -->
 (O2080 ^name predict-no +)
 (S1 ^operator O2080 +)
Retracting propose*predict-yes
 -->
 (O2079 ^name predict-yes +)
 (S1 ^operator O2079 +)
Retracting elaborate*reward*based*on*reward
 -->
 (R1043 ^value 1 +)
 (R1 ^reward R1043 +)
Retracting elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir R +)
Retracting rl*prefer*rvt*predict-no*H0*4*H1*15
 -->
 (S1 ^operator O2080 = 0.8730232867608889)
Retracting rl*prefer*rvt*predict-no*H0*4
 -->
 (S1 ^operator O2080 = 0.1269768076732486)
Retracting rl*prefer*rvt*predict-yes*H0*3*H1*16
 -->
 (S1 ^operator O2079 = 0.08783148430849691)
Retracting rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O2079 = 0.3829442071608071)
=>WM: (14626: S1 ^operator O2082 +)
=>WM: (14625: S1 ^operator O2081 +)
=>WM: (14624: O2082 ^name predict-no)
=>WM: (14623: O2081 ^name predict-yes)
=>WM: (14622: R1044 ^value 1)
=>WM: (14621: R1 ^reward R1044)
=>WM: (14620: I3 ^see 0)
<=WM: (14611: S1 ^operator O2079 +)
<=WM: (14612: S1 ^operator O2080 +)
<=WM: (14613: S1 ^operator O2080)
<=WM: (14607: R1 ^reward R1043)
<=WM: (14606: I3 ^see 1)
<=WM: (14610: O2080 ^name predict-no)
<=WM: (14609: O2079 ^name predict-yes)
<=WM: (14608: R1043 ^value 1)

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing prefer*rvt*predict-yes*H0
 -->
Firing rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O2081 = 0.3829442071608071)
Firing prefer*rvt*predict-yes*H0*3*H1
 -->
Firing rl*prefer*rvt*predict-yes*H0*3*H1*18
 -->
 (S1 ^operator O2081 = 0.2696941111808541)
Firing prefer*rvt*predict-no*H0
 -->
Firing rl*prefer*rvt*predict-no*H0*4
 -->
 (S1 ^operator O2082 = 0.1269768076732486)
Firing prefer*rvt*predict-no*H0*4*H1
 -->
Firing rl*prefer*rvt*predict-no*H0*4*H1*17
 -->
 (S1 ^operator O2082 = 0.8730230513112319)
 inner elaboration loop at bottom goal.
Retracting rl*prefer*rvt*predict-no*H0*4
 -->
 (S1 ^operator O2080 = 0.1269768076732486)
Retracting rl*prefer*rvt*predict-no*H0*4*H1*17
 -->
 (S1 ^operator O2080 = 0.8730230513112319)
Retracting rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O2079 = 0.3829442071608071)
Retracting rl*prefer*rvt*predict-yes*H0*3*H1*18
 -->
 (S1 ^operator O2079 = 0.2696941111808541)

--- END Proposal Phase ---

--- Decision Phase ---
RL update rl*prefer*rvt*predict-no*H0*4 0.814714 -0.687737 0.126977 -> 0.814714 -0.687737 0.126977(R,m,v=1,0.951087,0.0467748)
RL update rl*prefer*rvt*predict-no*H0*4*H1*15 0.185286 0.687737 0.873023 -> 0.185286 0.687737 0.873023(R,m,v=1,1,0)
=>WM: (14627: S1 ^operator O2082)

  1041:    O: O2082 (predict-no)
--- END Decision Phase ---

--- Application Phase ---
	--- Firing Productions (PE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing apply*operator
 -->
 (I3 ^predict-no N1041 +  :O )
Firing apply*operator*complete
 -->
 (I3 ^predict-no N1040 -  :O )
 inner elaboration loop at bottom goal.
	--- Change Working Memory (PE) ---
=>WM: (14628: I3 ^predict-no N1041)
<=WM: (14615: N1040 ^status complete)
<=WM: (14614: I3 ^predict-no N1040)
	--- Firing Productions (IE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing monitor*world
 -->

I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
	--- Change Working Memory (IE) ---

--- END Application Phase ---
--- Output Phase ---
ENV: Agent did: predict-no for direction R in state State-B
In  State-B moving R
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isU
--- END Output Phase ---
|--- Input Phase --- 
=>WM: (14632: I2 ^dir U)
=>WM: (14631: I2 ^reward 1)
=>WM: (14630: I2 ^see 0)
=>WM: (14629: N1041 ^status complete)
<=WM: (14618: I2 ^dir R)
<=WM: (14617: I2 ^reward 1)
<=WM: (14616: I2 ^see 0)
=>WM: (14633: I2 ^level-1 R0-root)
<=WM: (14619: I2 ^level-1 R0-root)

--- END Input Phase --- 

--- Proposal Phase ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing elaborate*copy-see-to-output-link
 -->
 (I3 ^see 0 +)
Firing elaborate*reward*based*on*reward
 -->
 (R1045 ^value 1 +)
 (R1 ^reward R1045 +)
Firing propose*predict-yes
 -->
 (O2083 ^name predict-yes +)
 (S1 ^operator O2083 +)
Firing propose*predict-no
 -->
 (O2084 ^name predict-no +)
 (S1 ^operator O2084 +)
Firing rl*prefer*rvt*predict-no*H0*6
 -->
 (S1 ^operator O2082 = 0.9999999999999999)
Firing rl*prefer*rvt*predict-yes*H0*5
 -->
 (S1 ^operator O2081 = 0.)
Firing prefer*rvt*predict-yes*H0
 -->
Firing prefer*rvt*predict-no*H0
 -->
Firing elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir U +)
 inner elaboration loop at bottom goal.
Retracting elaborate*copy-see-to-output-link
 -->
 (I3 ^see 0 +)
Retracting propose*predict-no
 -->
 (O2082 ^name predict-no +)
 (S1 ^operator O2082 +)
Retracting propose*predict-yes
 -->
 (O2081 ^name predict-yes +)
 (S1 ^operator O2081 +)
Retracting elaborate*reward*based*on*reward
 -->
 (R1044 ^value 1 +)
 (R1 ^reward R1044 +)
Retracting elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir R +)
Retracting rl*prefer*rvt*predict-no*H0*4*H1*17
 -->
 (S1 ^operator O2082 = 0.8730230513112319)
Retracting rl*prefer*rvt*predict-no*H0*4
 -->
 (S1 ^operator O2082 = 0.126976793508128)
Retracting rl*prefer*rvt*predict-yes*H0*3*H1*18
 -->
 (S1 ^operator O2081 = 0.2696941111808541)
Retracting rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O2081 = 0.3829442071608071)
=>WM: (14640: S1 ^operator O2084 +)
=>WM: (14639: S1 ^operator O2083 +)
=>WM: (14638: I3 ^dir U)
=>WM: (14637: O2084 ^name predict-no)
=>WM: (14636: O2083 ^name predict-yes)
=>WM: (14635: R1045 ^value 1)
=>WM: (14634: R1 ^reward R1045)
<=WM: (14625: S1 ^operator O2081 +)
<=WM: (14626: S1 ^operator O2082 +)
<=WM: (14627: S1 ^operator O2082)
<=WM: (14596: I3 ^dir R)
<=WM: (14621: R1 ^reward R1044)
<=WM: (14624: O2082 ^name predict-no)
<=WM: (14623: O2081 ^name predict-yes)
<=WM: (14622: R1044 ^value 1)

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing prefer*rvt*predict-yes*H0
 -->
Firing rl*prefer*rvt*predict-yes*H0*5
 -->
 (S1 ^operator O2083 = 0.)
Firing prefer*rvt*predict-no*H0
 -->
Firing rl*prefer*rvt*predict-no*H0*6
 -->
 (S1 ^operator O2084 = 0.9999999999999999)
 inner elaboration loop at bottom goal.
Retracting rl*prefer*rvt*predict-no*H0*6
 -->
 (S1 ^operator O2082 = 0.9999999999999999)
Retracting rl*prefer*rvt*predict-yes*H0*5
 -->
 (S1 ^operator O2081 = 0.)

--- END Proposal Phase ---

--- Decision Phase ---
RL update rl*prefer*rvt*predict-no*H0*4 0.814714 -0.687737 0.126977 -> 0.814714 -0.687737 0.126977(R,m,v=1,0.951351,0.0465335)
RL update rl*prefer*rvt*predict-no*H0*4*H1*17 0.185286 0.687737 0.873023 -> 0.185286 0.687737 0.873023(R,m,v=1,1,0)
=>WM: (14641: S1 ^operator O2084)

  1042:    O: O2084 (predict-no)
--- END Decision Phase ---

--- Application Phase ---
	--- Firing Productions (PE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing apply*operator
 -->
 (I3 ^predict-no N1042 +  :O )
Firing apply*operator*complete
 -->
 (I3 ^predict-no N1041 -  :O )
 inner elaboration loop at bottom goal.
	--- Change Working Memory (PE) ---
=>WM: (14642: I3 ^predict-no N1042)
<=WM: (14629: N1041 ^status complete)
<=WM: (14628: I3 ^predict-no N1041)
	--- Firing Productions (IE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing monitor*world
 -->

I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
	--- Change Working Memory (IE) ---

--- END Application Phase ---
--- Output Phase ---
ENV: Agent did: predict-no for direction U in state State-B
In  State-B moving U
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isU
--- END Output Phase ---
\---- Input Phase --- 
=>WM: (14646: I2 ^dir U)
=>WM: (14645: I2 ^reward 1)
=>WM: (14644: I2 ^see 0)
=>WM: (14643: N1042 ^status complete)
<=WM: (14632: I2 ^dir U)
<=WM: (14631: I2 ^reward 1)
<=WM: (14630: I2 ^see 0)
=>WM: (14647: I2 ^level-1 R0-root)
<=WM: (14633: I2 ^level-1 R0-root)

--- END Input Phase --- 

--- Proposal Phase ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing elaborate*copy-see-to-output-link
 -->
 (I3 ^see 0 +)
Firing elaborate*reward*based*on*reward
 -->
 (R1046 ^value 1 +)
 (R1 ^reward R1046 +)
Firing propose*predict-yes
 -->
 (O2085 ^name predict-yes +)
 (S1 ^operator O2085 +)
Firing propose*predict-no
 -->
 (O2086 ^name predict-no +)
 (S1 ^operator O2086 +)
Firing rl*prefer*rvt*predict-no*H0*6
 -->
 (S1 ^operator O2084 = 0.9999999999999999)
Firing rl*prefer*rvt*predict-yes*H0*5
 -->
 (S1 ^operator O2083 = 0.)
Firing prefer*rvt*predict-yes*H0
 -->
Firing prefer*rvt*predict-no*H0
 -->
Firing elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir U +)
 inner elaboration loop at bottom goal.
Retracting elaborate*copy-see-to-output-link
 -->
 (I3 ^see 0 +)
Retracting propose*predict-no
 -->
 (O2084 ^name predict-no +)
 (S1 ^operator O2084 +)
Retracting propose*predict-yes
 -->
 (O2083 ^name predict-yes +)
 (S1 ^operator O2083 +)
Retracting elaborate*reward*based*on*reward
 -->
 (R1045 ^value 1 +)
 (R1 ^reward R1045 +)
Retracting elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir U +)
Retracting rl*prefer*rvt*predict-no*H0*6
 -->
 (S1 ^operator O2084 = 0.9999999999999999)
Retracting rl*prefer*rvt*predict-yes*H0*5
 -->
 (S1 ^operator O2083 = 0.)
=>WM: (14653: S1 ^operator O2086 +)
=>WM: (14652: S1 ^operator O2085 +)
=>WM: (14651: O2086 ^name predict-no)
=>WM: (14650: O2085 ^name predict-yes)
=>WM: (14649: R1046 ^value 1)
=>WM: (14648: R1 ^reward R1046)
<=WM: (14639: S1 ^operator O2083 +)
<=WM: (14640: S1 ^operator O2084 +)
<=WM: (14641: S1 ^operator O2084)
<=WM: (14634: R1 ^reward R1045)
<=WM: (14637: O2084 ^name predict-no)
<=WM: (14636: O2083 ^name predict-yes)
<=WM: (14635: R1045 ^value 1)

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing prefer*rvt*predict-yes*H0
 -->
Firing rl*prefer*rvt*predict-yes*H0*5
 -->
 (S1 ^operator O2085 = 0.)
Firing prefer*rvt*predict-no*H0
 -->
Firing rl*prefer*rvt*predict-no*H0*6
 -->
 (S1 ^operator O2086 = 0.9999999999999999)
 inner elaboration loop at bottom goal.
Retracting rl*prefer*rvt*predict-no*H0*6
 -->
 (S1 ^operator O2084 = 0.9999999999999999)
Retracting rl*prefer*rvt*predict-yes*H0*5
 -->
 (S1 ^operator O2083 = 0.)

--- END Proposal Phase ---

--- Decision Phase ---
RL update rl*prefer*rvt*predict-no*H0*6 1 0 1 -> 1 0 1(R,m,v=1,1,0)
=>WM: (14654: S1 ^operator O2086)

  1043:    O: O2086 (predict-no)
--- END Decision Phase ---

--- Application Phase ---
	--- Firing Productions (PE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing apply*operator
 -->
 (I3 ^predict-no N1043 +  :O )
Firing apply*operator*complete
 -->
 (I3 ^predict-no N1042 -  :O )
 inner elaboration loop at bottom goal.
	--- Change Working Memory (PE) ---
=>WM: (14655: I3 ^predict-no N1043)
<=WM: (14643: N1042 ^status complete)
<=WM: (14642: I3 ^predict-no N1042)
	--- Firing Productions (IE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing monitor*world
 -->

I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
	--- Change Working Memory (IE) ---

--- END Application Phase ---
--- Output Phase ---
ENV: Agent did: predict-no for direction U in state State-B
In  State-B moving U
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isR
--- END Output Phase ---
/|--- Input Phase --- 
=>WM: (14659: I2 ^dir R)
=>WM: (14658: I2 ^reward 1)
=>WM: (14657: I2 ^see 0)
=>WM: (14656: N1043 ^status complete)
<=WM: (14646: I2 ^dir U)
<=WM: (14645: I2 ^reward 1)
<=WM: (14644: I2 ^see 0)
=>WM: (14660: I2 ^level-1 R0-root)
<=WM: (14647: I2 ^level-1 R0-root)

--- END Input Phase --- 

--- Proposal Phase ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing rl*prefer*rvt*predict-yes*H0*3*H1*18
 -->
 (S1 ^operator O2085 = 0.2696941111808541)
Firing rl*prefer*rvt*predict-no*H0*4*H1*17
 -->
 (S1 ^operator O2086 = 0.873023074588328)
Firing prefer*rvt*predict-no*H0*4*H1
 -->
Firing prefer*rvt*predict-yes*H0*3*H1
 -->
Firing elaborate*copy-see-to-output-link
 -->
 (I3 ^see 0 +)
Firing elaborate*reward*based*on*reward
 -->
 (R1047 ^value 1 +)
 (R1 ^reward R1047 +)
Firing propose*predict-yes
 -->
 (O2087 ^name predict-yes +)
 (S1 ^operator O2087 +)
Firing propose*predict-no
 -->
 (O2088 ^name predict-no +)
 (S1 ^operator O2088 +)
Firing rl*prefer*rvt*predict-no*H0*4
 -->
 (S1 ^operator O2086 = 0.126976816785224)
Firing rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O2085 = 0.3829442071608071)
Firing prefer*rvt*predict-yes*H0
 -->
Firing prefer*rvt*predict-no*H0
 -->
Firing elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir R +)
 inner elaboration loop at bottom goal.
Retracting elaborate*copy-see-to-output-link
 -->
 (I3 ^see 0 +)
Retracting propose*predict-no
 -->
 (O2086 ^name predict-no +)
 (S1 ^operator O2086 +)
Retracting propose*predict-yes
 -->
 (O2085 ^name predict-yes +)
 (S1 ^operator O2085 +)
Retracting elaborate*reward*based*on*reward
 -->
 (R1046 ^value 1 +)
 (R1 ^reward R1046 +)
Retracting elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir U +)
Retracting rl*prefer*rvt*predict-no*H0*6
 -->
 (S1 ^operator O2086 = 0.9999999999999999)
Retracting rl*prefer*rvt*predict-yes*H0*5
 -->
 (S1 ^operator O2085 = 0.)
=>WM: (14667: S1 ^operator O2088 +)
=>WM: (14666: S1 ^operator O2087 +)
=>WM: (14665: I3 ^dir R)
=>WM: (14664: O2088 ^name predict-no)
=>WM: (14663: O2087 ^name predict-yes)
=>WM: (14662: R1047 ^value 1)
=>WM: (14661: R1 ^reward R1047)
<=WM: (14652: S1 ^operator O2085 +)
<=WM: (14653: S1 ^operator O2086 +)
<=WM: (14654: S1 ^operator O2086)
<=WM: (14638: I3 ^dir U)
<=WM: (14648: R1 ^reward R1046)
<=WM: (14651: O2086 ^name predict-no)
<=WM: (14650: O2085 ^name predict-yes)
<=WM: (14649: R1046 ^value 1)

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing prefer*rvt*predict-yes*H0
 -->
Firing rl*prefer*rvt*predict-yes*H0*3*H1*18
 -->
 (S1 ^operator O2087 = 0.2696941111808541)
Firing rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O2087 = 0.3829442071608071)
Firing prefer*rvt*predict-yes*H0*3*H1
 -->
Firing prefer*rvt*predict-no*H0
 -->
Firing rl*prefer*rvt*predict-no*H0*4*H1*17
 -->
 (S1 ^operator O2088 = 0.873023074588328)
Firing rl*prefer*rvt*predict-no*H0*4
 -->
 (S1 ^operator O2088 = 0.126976816785224)
Firing prefer*rvt*predict-no*H0*4*H1
 -->
 inner elaboration loop at bottom goal.
Retracting rl*prefer*rvt*predict-no*H0*4
 -->
 (S1 ^operator O2086 = 0.126976816785224)
Retracting rl*prefer*rvt*predict-no*H0*4*H1*17
 -->
 (S1 ^operator O2086 = 0.873023074588328)
Retracting rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O2085 = 0.3829442071608071)
Retracting rl*prefer*rvt*predict-yes*H0*3*H1*18
 -->
 (S1 ^operator O2085 = 0.2696941111808541)

--- END Proposal Phase ---

--- Decision Phase ---
RL update rl*prefer*rvt*predict-no*H0*6 1 0 1 -> 1 0 1(R,m,v=1,1,0)
=>WM: (14668: S1 ^operator O2088)

  1044:    O: O2088 (predict-no)
--- END Decision Phase ---

--- Application Phase ---
	--- Firing Productions (PE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing apply*operator
 -->
 (I3 ^predict-no N1044 +  :O )
Firing apply*operator*complete
 -->
 (I3 ^predict-no N1043 -  :O )
 inner elaboration loop at bottom goal.
	--- Change Working Memory (PE) ---
=>WM: (14669: I3 ^predict-no N1044)
<=WM: (14656: N1043 ^status complete)
<=WM: (14655: I3 ^predict-no N1043)
	--- Firing Productions (IE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing monitor*world
 -->

I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
	--- Change Working Memory (IE) ---

--- END Application Phase ---
--- Output Phase ---
ENV: Agent did: predict-no for direction R in state State-B
In  State-B moving R
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isR
--- END Output Phase ---
\-/--- Input Phase --- 
=>WM: (14673: I2 ^dir R)
=>WM: (14672: I2 ^reward 1)
=>WM: (14671: I2 ^see 0)
=>WM: (14670: N1044 ^status complete)
<=WM: (14659: I2 ^dir R)
<=WM: (14658: I2 ^reward 1)
<=WM: (14657: I2 ^see 0)
=>WM: (14674: I2 ^level-1 R0-root)
<=WM: (14660: I2 ^level-1 R0-root)

--- END Input Phase --- 

--- Proposal Phase ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing rl*prefer*rvt*predict-yes*H0*3*H1*18
 -->
 (S1 ^operator O2087 = 0.2696941111808541)
Firing rl*prefer*rvt*predict-no*H0*4*H1*17
 -->
 (S1 ^operator O2088 = 0.873023074588328)
Firing prefer*rvt*predict-no*H0*4*H1
 -->
Firing prefer*rvt*predict-yes*H0*3*H1
 -->
Firing elaborate*copy-see-to-output-link
 -->
 (I3 ^see 0 +)
Firing elaborate*reward*based*on*reward
 -->
 (R1048 ^value 1 +)
 (R1 ^reward R1048 +)
Firing propose*predict-yes
 -->
 (O2089 ^name predict-yes +)
 (S1 ^operator O2089 +)
Firing propose*predict-no
 -->
 (O2090 ^name predict-no +)
 (S1 ^operator O2090 +)
Firing rl*prefer*rvt*predict-no*H0*4
 -->
 (S1 ^operator O2088 = 0.126976816785224)
Firing rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O2087 = 0.3829442071608071)
Firing prefer*rvt*predict-yes*H0
 -->
Firing prefer*rvt*predict-no*H0
 -->
Firing elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir R +)
 inner elaboration loop at bottom goal.
Retracting elaborate*copy-see-to-output-link
 -->
 (I3 ^see 0 +)
Retracting propose*predict-no
 -->
 (O2088 ^name predict-no +)
 (S1 ^operator O2088 +)
Retracting propose*predict-yes
 -->
 (O2087 ^name predict-yes +)
 (S1 ^operator O2087 +)
Retracting elaborate*reward*based*on*reward
 -->
 (R1047 ^value 1 +)
 (R1 ^reward R1047 +)
Retracting elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir R +)
Retracting rl*prefer*rvt*predict-no*H0*4
 -->
 (S1 ^operator O2088 = 0.126976816785224)
Retracting rl*prefer*rvt*predict-no*H0*4*H1*17
 -->
 (S1 ^operator O2088 = 0.873023074588328)
Retracting rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O2087 = 0.3829442071608071)
Retracting rl*prefer*rvt*predict-yes*H0*3*H1*18
 -->
 (S1 ^operator O2087 = 0.2696941111808541)
=>WM: (14680: S1 ^operator O2090 +)
=>WM: (14679: S1 ^operator O2089 +)
=>WM: (14678: O2090 ^name predict-no)
=>WM: (14677: O2089 ^name predict-yes)
=>WM: (14676: R1048 ^value 1)
=>WM: (14675: R1 ^reward R1048)
<=WM: (14666: S1 ^operator O2087 +)
<=WM: (14667: S1 ^operator O2088 +)
<=WM: (14668: S1 ^operator O2088)
<=WM: (14661: R1 ^reward R1047)
<=WM: (14664: O2088 ^name predict-no)
<=WM: (14663: O2087 ^name predict-yes)
<=WM: (14662: R1047 ^value 1)

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing prefer*rvt*predict-yes*H0
 -->
Firing rl*prefer*rvt*predict-yes*H0*3*H1*18
 -->
 (S1 ^operator O2089 = 0.2696941111808541)
Firing rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O2089 = 0.3829442071608071)
Firing prefer*rvt*predict-yes*H0*3*H1
 -->
Firing prefer*rvt*predict-no*H0
 -->
Firing rl*prefer*rvt*predict-no*H0*4*H1*17
 -->
 (S1 ^operator O2090 = 0.873023074588328)
Firing rl*prefer*rvt*predict-no*H0*4
 -->
 (S1 ^operator O2090 = 0.126976816785224)
Firing prefer*rvt*predict-no*H0*4*H1
 -->
 inner elaboration loop at bottom goal.
Retracting rl*prefer*rvt*predict-no*H0*4
 -->
 (S1 ^operator O2088 = 0.126976816785224)
Retracting rl*prefer*rvt*predict-no*H0*4*H1*17
 -->
 (S1 ^operator O2088 = 0.873023074588328)
Retracting rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O2087 = 0.3829442071608071)
Retracting rl*prefer*rvt*predict-yes*H0*3*H1*18
 -->
 (S1 ^operator O2087 = 0.2696941111808541)

--- END Proposal Phase ---

--- Decision Phase ---
RL update rl*prefer*rvt*predict-no*H0*4 0.814714 -0.687737 0.126977 -> 0.814714 -0.687737 0.126977(R,m,v=1,0.951613,0.0462947)
RL update rl*prefer*rvt*predict-no*H0*4*H1*17 0.185286 0.687737 0.873023 -> 0.185286 0.687737 0.873023(R,m,v=1,1,0)
=>WM: (14681: S1 ^operator O2090)

  1045:    O: O2090 (predict-no)
--- END Decision Phase ---

--- Application Phase ---
	--- Firing Productions (PE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing apply*operator
 -->
 (I3 ^predict-no N1045 +  :O )
Firing apply*operator*complete
 -->
 (I3 ^predict-no N1044 -  :O )
 inner elaboration loop at bottom goal.
	--- Change Working Memory (PE) ---
=>WM: (14682: I3 ^predict-no N1045)
<=WM: (14670: N1044 ^status complete)
<=WM: (14669: I3 ^predict-no N1044)
	--- Firing Productions (IE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing monitor*world
 -->

I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
	--- Change Working Memory (IE) ---

--- END Application Phase ---
--- Output Phase ---
ENV: Agent did: predict-no for direction R in state State-B
In  State-B moving R
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isR
--- END Output Phase ---
|\---- Input Phase --- 
=>WM: (14686: I2 ^dir R)
=>WM: (14685: I2 ^reward 1)
=>WM: (14684: I2 ^see 0)
=>WM: (14683: N1045 ^status complete)
<=WM: (14673: I2 ^dir R)
<=WM: (14672: I2 ^reward 1)
<=WM: (14671: I2 ^see 0)
=>WM: (14687: I2 ^level-1 R0-root)
<=WM: (14674: I2 ^level-1 R0-root)

--- END Input Phase --- 

--- Proposal Phase ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing rl*prefer*rvt*predict-yes*H0*3*H1*18
 -->
 (S1 ^operator O2089 = 0.2696941111808541)
Firing rl*prefer*rvt*predict-no*H0*4*H1*17
 -->
 (S1 ^operator O2090 = 0.8730230908822952)
Firing prefer*rvt*predict-no*H0*4*H1
 -->
Firing prefer*rvt*predict-yes*H0*3*H1
 -->
Firing elaborate*copy-see-to-output-link
 -->
 (I3 ^see 0 +)
Firing elaborate*reward*based*on*reward
 -->
 (R1049 ^value 1 +)
 (R1 ^reward R1049 +)
Firing propose*predict-yes
 -->
 (O2091 ^name predict-yes +)
 (S1 ^operator O2091 +)
Firing propose*predict-no
 -->
 (O2092 ^name predict-no +)
 (S1 ^operator O2092 +)
Firing rl*prefer*rvt*predict-no*H0*4
 -->
 (S1 ^operator O2090 = 0.1269768330791913)
Firing rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O2089 = 0.3829442071608071)
Firing prefer*rvt*predict-yes*H0
 -->
Firing prefer*rvt*predict-no*H0
 -->
Firing elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir R +)
 inner elaboration loop at bottom goal.
Retracting elaborate*copy-see-to-output-link
 -->
 (I3 ^see 0 +)
Retracting propose*predict-no
 -->
 (O2090 ^name predict-no +)
 (S1 ^operator O2090 +)
Retracting propose*predict-yes
 -->
 (O2089 ^name predict-yes +)
 (S1 ^operator O2089 +)
Retracting elaborate*reward*based*on*reward
 -->
 (R1048 ^value 1 +)
 (R1 ^reward R1048 +)
Retracting elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir R +)
Retracting rl*prefer*rvt*predict-no*H0*4
 -->
 (S1 ^operator O2090 = 0.1269768330791913)
Retracting rl*prefer*rvt*predict-no*H0*4*H1*17
 -->
 (S1 ^operator O2090 = 0.8730230908822952)
Retracting rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O2089 = 0.3829442071608071)
Retracting rl*prefer*rvt*predict-yes*H0*3*H1*18
 -->
 (S1 ^operator O2089 = 0.2696941111808541)
=>WM: (14693: S1 ^operator O2092 +)
=>WM: (14692: S1 ^operator O2091 +)
=>WM: (14691: O2092 ^name predict-no)
=>WM: (14690: O2091 ^name predict-yes)
=>WM: (14689: R1049 ^value 1)
=>WM: (14688: R1 ^reward R1049)
<=WM: (14679: S1 ^operator O2089 +)
<=WM: (14680: S1 ^operator O2090 +)
<=WM: (14681: S1 ^operator O2090)
<=WM: (14675: R1 ^reward R1048)
<=WM: (14678: O2090 ^name predict-no)
<=WM: (14677: O2089 ^name predict-yes)
<=WM: (14676: R1048 ^value 1)

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing prefer*rvt*predict-yes*H0
 -->
Firing rl*prefer*rvt*predict-yes*H0*3*H1*18
 -->
 (S1 ^operator O2091 = 0.2696941111808541)
Firing rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O2091 = 0.3829442071608071)
Firing prefer*rvt*predict-yes*H0*3*H1
 -->
Firing prefer*rvt*predict-no*H0
 -->
Firing rl*prefer*rvt*predict-no*H0*4*H1*17
 -->
 (S1 ^operator O2092 = 0.8730230908822952)
Firing rl*prefer*rvt*predict-no*H0*4
 -->
 (S1 ^operator O2092 = 0.1269768330791913)
Firing prefer*rvt*predict-no*H0*4*H1
 -->
 inner elaboration loop at bottom goal.
Retracting rl*prefer*rvt*predict-no*H0*4
 -->
 (S1 ^operator O2090 = 0.1269768330791913)
Retracting rl*prefer*rvt*predict-no*H0*4*H1*17
 -->
 (S1 ^operator O2090 = 0.8730230908822952)
Retracting rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O2089 = 0.3829442071608071)
Retracting rl*prefer*rvt*predict-yes*H0*3*H1*18
 -->
 (S1 ^operator O2089 = 0.2696941111808541)

--- END Proposal Phase ---

--- Decision Phase ---
RL update rl*prefer*rvt*predict-no*H0*4 0.814714 -0.687737 0.126977 -> 0.814714 -0.687737 0.126977(R,m,v=1,0.951872,0.0460583)
RL update rl*prefer*rvt*predict-no*H0*4*H1*17 0.185286 0.687737 0.873023 -> 0.185286 0.687737 0.873023(R,m,v=1,1,0)
=>WM: (14694: S1 ^operator O2092)

  1046:    O: O2092 (predict-no)
--- END Decision Phase ---

--- Application Phase ---
	--- Firing Productions (PE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing apply*operator
 -->
 (I3 ^predict-no N1046 +  :O )
Firing apply*operator*complete
 -->
 (I3 ^predict-no N1045 -  :O )
 inner elaboration loop at bottom goal.
	--- Change Working Memory (PE) ---
=>WM: (14695: I3 ^predict-no N1046)
<=WM: (14683: N1045 ^status complete)
<=WM: (14682: I3 ^predict-no N1045)
	--- Firing Productions (IE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing monitor*world
 -->

I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
	--- Change Working Memory (IE) ---

--- END Application Phase ---
--- Output Phase ---
ENV: Agent did: predict-no for direction R in state State-B
In  State-B moving R
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isL
--- END Output Phase ---
/|\--- Input Phase --- 
=>WM: (14699: I2 ^dir L)
=>WM: (14698: I2 ^reward 1)
=>WM: (14697: I2 ^see 0)
=>WM: (14696: N1046 ^status complete)
<=WM: (14686: I2 ^dir R)
<=WM: (14685: I2 ^reward 1)
<=WM: (14684: I2 ^see 0)
=>WM: (14700: I2 ^level-1 R0-root)
<=WM: (14687: I2 ^level-1 R0-root)

--- END Input Phase --- 

--- Proposal Phase ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing rl*prefer*rvt*predict-yes*H0*1*H1*19
 -->
 (S1 ^operator O2091 = 0.4768814583471331)
Firing rl*prefer*rvt*predict-no*H0*2*H1*7
 -->
 (S1 ^operator O2092 = 0.1700769046561409)
Firing prefer*rvt*predict-no*H0*2*H1
 -->
Firing prefer*rvt*predict-yes*H0*1*H1
 -->
Firing elaborate*copy-see-to-output-link
 -->
 (I3 ^see 0 +)
Firing elaborate*reward*based*on*reward
 -->
 (R1050 ^value 1 +)
 (R1 ^reward R1050 +)
Firing propose*predict-yes
 -->
 (O2093 ^name predict-yes +)
 (S1 ^operator O2093 +)
Firing propose*predict-no
 -->
 (O2094 ^name predict-no +)
 (S1 ^operator O2094 +)
Firing rl*prefer*rvt*predict-no*H0*2
 -->
 (S1 ^operator O2092 = 0.2550133912230119)
Firing rl*prefer*rvt*predict-yes*H0*1
 -->
 (S1 ^operator O2091 = 0.5231194249480864)
Firing prefer*rvt*predict-yes*H0
 -->
Firing prefer*rvt*predict-no*H0
 -->
Firing elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir L +)
 inner elaboration loop at bottom goal.
Retracting elaborate*copy-see-to-output-link
 -->
 (I3 ^see 0 +)
Retracting propose*predict-no
 -->
 (O2092 ^name predict-no +)
 (S1 ^operator O2092 +)
Retracting propose*predict-yes
 -->
 (O2091 ^name predict-yes +)
 (S1 ^operator O2091 +)
Retracting elaborate*reward*based*on*reward
 -->
 (R1049 ^value 1 +)
 (R1 ^reward R1049 +)
Retracting elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir R +)
Retracting rl*prefer*rvt*predict-no*H0*4
 -->
 (S1 ^operator O2092 = 0.1269768444849683)
Retracting rl*prefer*rvt*predict-no*H0*4*H1*17
 -->
 (S1 ^operator O2092 = 0.8730231022880722)
Retracting rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O2091 = 0.3829442071608071)
Retracting rl*prefer*rvt*predict-yes*H0*3*H1*18
 -->
 (S1 ^operator O2091 = 0.2696941111808541)
=>WM: (14707: S1 ^operator O2094 +)
=>WM: (14706: S1 ^operator O2093 +)
=>WM: (14705: I3 ^dir L)
=>WM: (14704: O2094 ^name predict-no)
=>WM: (14703: O2093 ^name predict-yes)
=>WM: (14702: R1050 ^value 1)
=>WM: (14701: R1 ^reward R1050)
<=WM: (14692: S1 ^operator O2091 +)
<=WM: (14693: S1 ^operator O2092 +)
<=WM: (14694: S1 ^operator O2092)
<=WM: (14665: I3 ^dir R)
<=WM: (14688: R1 ^reward R1049)
<=WM: (14691: O2092 ^name predict-no)
<=WM: (14690: O2091 ^name predict-yes)
<=WM: (14689: R1049 ^value 1)

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing prefer*rvt*predict-yes*H0
 -->
Firing rl*prefer*rvt*predict-yes*H0*1*H1*19
 -->
 (S1 ^operator O2093 = 0.4768814583471331)
Firing rl*prefer*rvt*predict-yes*H0*1
 -->
 (S1 ^operator O2093 = 0.5231194249480864)
Firing prefer*rvt*predict-yes*H0*1*H1
 -->
Firing prefer*rvt*predict-no*H0
 -->
Firing rl*prefer*rvt*predict-no*H0*2*H1*7
 -->
 (S1 ^operator O2094 = 0.1700769046561409)
Firing rl*prefer*rvt*predict-no*H0*2
 -->
 (S1 ^operator O2094 = 0.2550133912230119)
Firing prefer*rvt*predict-no*H0*2*H1
 -->
 inner elaboration loop at bottom goal.
Retracting rl*prefer*rvt*predict-no*H0*2
 -->
 (S1 ^operator O2092 = 0.2550133912230119)
Retracting rl*prefer*rvt*predict-no*H0*2*H1*7
 -->
 (S1 ^operator O2092 = 0.1700769046561409)
Retracting rl*prefer*rvt*predict-yes*H0*1
 -->
 (S1 ^operator O2091 = 0.5231194249480864)
Retracting rl*prefer*rvt*predict-yes*H0*1*H1*19
 -->
 (S1 ^operator O2091 = 0.4768814583471331)

--- END Proposal Phase ---

--- Decision Phase ---
RL update rl*prefer*rvt*predict-no*H0*4 0.814714 -0.687737 0.126977 -> 0.814714 -0.687737 0.126977(R,m,v=1,0.952128,0.0458243)
RL update rl*prefer*rvt*predict-no*H0*4*H1*17 0.185286 0.687737 0.873023 -> 0.185286 0.687737 0.873023(R,m,v=1,1,0)
=>WM: (14708: S1 ^operator O2093)

  1047:    O: O2093 (predict-yes)
--- END Decision Phase ---

--- Application Phase ---
	--- Firing Productions (PE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing apply*operator
 -->
 (I3 ^predict-yes N1047 +  :O )
Firing apply*operator*complete
 -->
 (I3 ^predict-no N1046 -  :O )
 inner elaboration loop at bottom goal.
	--- Change Working Memory (PE) ---
=>WM: (14709: I3 ^predict-yes N1047)
<=WM: (14696: N1046 ^status complete)
<=WM: (14695: I3 ^predict-no N1046)
	--- Firing Productions (IE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing monitor*world
 -->

I see 1 and I'm going to do: predict-yes inner elaboration loop at bottom goal.
	--- Change Working Memory (IE) ---

--- END Application Phase ---
--- Output Phase ---
ENV: Agent did: predict-yes for direction L in state State-B
In  State-B moving L
ENV: (next state, see, prediction correct?) = (State-A, 1, True)
predict error 0
dir: dir isR
--- END Output Phase ---
-/--- Input Phase --- 
=>WM: (14713: I2 ^dir R)
=>WM: (14712: I2 ^reward 1)
=>WM: (14711: I2 ^see 1)
=>WM: (14710: N1047 ^status complete)
<=WM: (14699: I2 ^dir L)
<=WM: (14698: I2 ^reward 1)
<=WM: (14697: I2 ^see 0)
=>WM: (14714: I2 ^level-1 L1-root)
<=WM: (14700: I2 ^level-1 R0-root)

--- END Input Phase --- 

--- Proposal Phase ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing rl*prefer*rvt*predict-yes*H0*3*H1*9
 -->
 (S1 ^operator O2093 = 0.6170481813010518)
Firing rl*prefer*rvt*predict-no*H0*4*H1*8
 -->
 (S1 ^operator O2094 = 0.4901349546100854)
Firing prefer*rvt*predict-no*H0*4*H1
 -->
Firing prefer*rvt*predict-yes*H0*3*H1
 -->
Firing elaborate*copy-see-to-output-link
 -->
 (I3 ^see 1 +)
Firing elaborate*reward*based*on*reward
 -->
 (R1051 ^value 1 +)
 (R1 ^reward R1051 +)
Firing propose*predict-yes
 -->
 (O2095 ^name predict-yes +)
 (S1 ^operator O2095 +)
Firing propose*predict-no
 -->
 (O2096 ^name predict-no +)
 (S1 ^operator O2096 +)
Firing rl*prefer*rvt*predict-no*H0*4
 -->
 (S1 ^operator O2094 = 0.1269768524690122)
Firing rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O2093 = 0.3829442071608071)
Firing prefer*rvt*predict-yes*H0
 -->
Firing prefer*rvt*predict-no*H0
 -->
Firing elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir R +)
 inner elaboration loop at bottom goal.
Retracting elaborate*copy-see-to-output-link
 -->
 (I3 ^see 0 +)
Retracting propose*predict-no
 -->
 (O2094 ^name predict-no +)
 (S1 ^operator O2094 +)
Retracting propose*predict-yes
 -->
 (O2093 ^name predict-yes +)
 (S1 ^operator O2093 +)
Retracting elaborate*reward*based*on*reward
 -->
 (R1050 ^value 1 +)
 (R1 ^reward R1050 +)
Retracting elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir L +)
Retracting rl*prefer*rvt*predict-no*H0*2
 -->
 (S1 ^operator O2094 = 0.2550133912230119)
Retracting rl*prefer*rvt*predict-no*H0*2*H1*7
 -->
 (S1 ^operator O2094 = 0.1700769046561409)
Retracting rl*prefer*rvt*predict-yes*H0*1
 -->
 (S1 ^operator O2093 = 0.5231194249480864)
Retracting rl*prefer*rvt*predict-yes*H0*1*H1*19
 -->
 (S1 ^operator O2093 = 0.4768814583471331)
=>WM: (14722: S1 ^operator O2096 +)
=>WM: (14721: S1 ^operator O2095 +)
=>WM: (14720: I3 ^dir R)
=>WM: (14719: O2096 ^name predict-no)
=>WM: (14718: O2095 ^name predict-yes)
=>WM: (14717: R1051 ^value 1)
=>WM: (14716: R1 ^reward R1051)
=>WM: (14715: I3 ^see 1)
<=WM: (14706: S1 ^operator O2093 +)
<=WM: (14708: S1 ^operator O2093)
<=WM: (14707: S1 ^operator O2094 +)
<=WM: (14705: I3 ^dir L)
<=WM: (14701: R1 ^reward R1050)
<=WM: (14620: I3 ^see 0)
<=WM: (14704: O2094 ^name predict-no)
<=WM: (14703: O2093 ^name predict-yes)
<=WM: (14702: R1050 ^value 1)

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing prefer*rvt*predict-yes*H0
 -->
Firing rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O2095 = 0.3829442071608071)
Firing prefer*rvt*predict-yes*H0*3*H1
 -->
Firing rl*prefer*rvt*predict-yes*H0*3*H1*9
 -->
 (S1 ^operator O2095 = 0.6170481813010518)
Firing prefer*rvt*predict-no*H0
 -->
Firing rl*prefer*rvt*predict-no*H0*4
 -->
 (S1 ^operator O2096 = 0.1269768524690122)
Firing prefer*rvt*predict-no*H0*4*H1
 -->
Firing rl*prefer*rvt*predict-no*H0*4*H1*8
 -->
 (S1 ^operator O2096 = 0.4901349546100854)
 inner elaboration loop at bottom goal.
Retracting rl*prefer*rvt*predict-no*H0*4
 -->
 (S1 ^operator O2094 = 0.1269768524690122)
Retracting rl*prefer*rvt*predict-no*H0*4*H1*8
 -->
 (S1 ^operator O2094 = 0.4901349546100854)
Retracting rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O2093 = 0.3829442071608071)
Retracting rl*prefer*rvt*predict-yes*H0*3*H1*9
 -->
 (S1 ^operator O2093 = 0.6170481813010518)

--- END Proposal Phase ---

--- Decision Phase ---
RL update rl*prefer*rvt*predict-yes*H0*1 0.727959 -0.20484 0.523119 -> 0.727959 -0.20484 0.523119(R,m,v=1,0.98,0.0197315)
RL update rl*prefer*rvt*predict-yes*H0*1*H1*19 0.272042 0.204839 0.476881 -> 0.272042 0.204839 0.476881(R,m,v=1,1,0)
=>WM: (14723: S1 ^operator O2095)

  1048:    O: O2095 (predict-yes)
--- END Decision Phase ---

--- Application Phase ---
	--- Firing Productions (PE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing apply*operator
 -->
 (I3 ^predict-yes N1048 +  :O )
Firing apply*operator*complete
 -->
 (I3 ^predict-yes N1047 -  :O )
 inner elaboration loop at bottom goal.
	--- Change Working Memory (PE) ---
=>WM: (14724: I3 ^predict-yes N1048)
<=WM: (14710: N1047 ^status complete)
<=WM: (14709: I3 ^predict-yes N1047)
	--- Firing Productions (IE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing monitor*world
 -->

I see 1 and I'm going to do: predict-yes inner elaboration loop at bottom goal.
	--- Change Working Memory (IE) ---

--- END Application Phase ---
--- Output Phase ---
ENV: Agent did: predict-yes for direction R in state State-A
In  State-A moving R
ENV: (next state, see, prediction correct?) = (State-B, 1, True)
predict error 0
dir: dir isU
--- END Output Phase ---
|\---- Input Phase --- 
=>WM: (14728: I2 ^dir U)
=>WM: (14727: I2 ^reward 1)
=>WM: (14726: I2 ^see 1)
=>WM: (14725: N1048 ^status complete)
<=WM: (14713: I2 ^dir R)
<=WM: (14712: I2 ^reward 1)
<=WM: (14711: I2 ^see 1)
=>WM: (14729: I2 ^level-1 R1-root)
<=WM: (14714: I2 ^level-1 L1-root)

--- END Input Phase --- 

--- Proposal Phase ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing elaborate*copy-see-to-output-link
 -->
 (I3 ^see 1 +)
Firing elaborate*reward*based*on*reward
 -->
 (R1052 ^value 1 +)
 (R1 ^reward R1052 +)
Firing propose*predict-yes
 -->
 (O2097 ^name predict-yes +)
 (S1 ^operator O2097 +)
Firing propose*predict-no
 -->
 (O2098 ^name predict-no +)
 (S1 ^operator O2098 +)
Firing rl*prefer*rvt*predict-no*H0*6
 -->
 (S1 ^operator O2096 = 0.9999999999999999)
Firing rl*prefer*rvt*predict-yes*H0*5
 -->
 (S1 ^operator O2095 = 0.)
Firing prefer*rvt*predict-yes*H0
 -->
Firing prefer*rvt*predict-no*H0
 -->
Firing elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir U +)
 inner elaboration loop at bottom goal.
Retracting elaborate*copy-see-to-output-link
 -->
 (I3 ^see 1 +)
Retracting propose*predict-no
 -->
 (O2096 ^name predict-no +)
 (S1 ^operator O2096 +)
Retracting propose*predict-yes
 -->
 (O2095 ^name predict-yes +)
 (S1 ^operator O2095 +)
Retracting elaborate*reward*based*on*reward
 -->
 (R1051 ^value 1 +)
 (R1 ^reward R1051 +)
Retracting elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir R +)
Retracting rl*prefer*rvt*predict-no*H0*4*H1*8
 -->
 (S1 ^operator O2096 = 0.4901349546100854)
Retracting rl*prefer*rvt*predict-no*H0*4
 -->
 (S1 ^operator O2096 = 0.1269768524690122)
Retracting rl*prefer*rvt*predict-yes*H0*3*H1*9
 -->
 (S1 ^operator O2095 = 0.6170481813010518)
Retracting rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O2095 = 0.3829442071608071)
=>WM: (14736: S1 ^operator O2098 +)
=>WM: (14735: S1 ^operator O2097 +)
=>WM: (14734: I3 ^dir U)
=>WM: (14733: O2098 ^name predict-no)
=>WM: (14732: O2097 ^name predict-yes)
=>WM: (14731: R1052 ^value 1)
=>WM: (14730: R1 ^reward R1052)
<=WM: (14721: S1 ^operator O2095 +)
<=WM: (14723: S1 ^operator O2095)
<=WM: (14722: S1 ^operator O2096 +)
<=WM: (14720: I3 ^dir R)
<=WM: (14716: R1 ^reward R1051)
<=WM: (14719: O2096 ^name predict-no)
<=WM: (14718: O2095 ^name predict-yes)
<=WM: (14717: R1051 ^value 1)

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing prefer*rvt*predict-yes*H0
 -->
Firing rl*prefer*rvt*predict-yes*H0*5
 -->
 (S1 ^operator O2097 = 0.)
Firing prefer*rvt*predict-no*H0
 -->
Firing rl*prefer*rvt*predict-no*H0*6
 -->
 (S1 ^operator O2098 = 0.9999999999999999)
 inner elaboration loop at bottom goal.
Retracting rl*prefer*rvt*predict-no*H0*6
 -->
 (S1 ^operator O2096 = 0.9999999999999999)
Retracting rl*prefer*rvt*predict-yes*H0*5
 -->
 (S1 ^operator O2095 = 0.)

--- END Proposal Phase ---

--- Decision Phase ---
RL update rl*prefer*rvt*predict-yes*H0*3 0.673137 -0.290193 0.382944 -> 0.673138 -0.290193 0.382945(R,m,v=1,0.962733,0.0361025)
RL update rl*prefer*rvt*predict-yes*H0*3*H1*9 0.326856 0.290192 0.617048 -> 0.326857 0.290192 0.617049(R,m,v=1,1,0)
=>WM: (14737: S1 ^operator O2098)

  1049:    O: O2098 (predict-no)
--- END Decision Phase ---

--- Application Phase ---
	--- Firing Productions (PE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing apply*operator
 -->
 (I3 ^predict-no N1049 +  :O )
Firing apply*operator*complete
 -->
 (I3 ^predict-yes N1048 -  :O )
 inner elaboration loop at bottom goal.
	--- Change Working Memory (PE) ---
=>WM: (14738: I3 ^predict-no N1049)
<=WM: (14725: N1048 ^status complete)
<=WM: (14724: I3 ^predict-yes N1048)
	--- Firing Productions (IE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing monitor*world
 -->

I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
	--- Change Working Memory (IE) ---

--- END Application Phase ---
--- Output Phase ---
ENV: Agent did: predict-no for direction U in state State-B
In  State-B moving U
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isU
--- END Output Phase ---
/|\--- Input Phase --- 
=>WM: (14742: I2 ^dir U)
=>WM: (14741: I2 ^reward 1)
=>WM: (14740: I2 ^see 0)
=>WM: (14739: N1049 ^status complete)
<=WM: (14728: I2 ^dir U)
<=WM: (14727: I2 ^reward 1)
<=WM: (14726: I2 ^see 1)
=>WM: (14743: I2 ^level-1 R1-root)
<=WM: (14729: I2 ^level-1 R1-root)

--- END Input Phase --- 

--- Proposal Phase ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing elaborate*copy-see-to-output-link
 -->
 (I3 ^see 0 +)
Firing elaborate*reward*based*on*reward
 -->
 (R1053 ^value 1 +)
 (R1 ^reward R1053 +)
Firing propose*predict-yes
 -->
 (O2099 ^name predict-yes +)
 (S1 ^operator O2099 +)
Firing propose*predict-no
 -->
 (O2100 ^name predict-no +)
 (S1 ^operator O2100 +)
Firing rl*prefer*rvt*predict-no*H0*6
 -->
 (S1 ^operator O2098 = 0.9999999999999999)
Firing rl*prefer*rvt*predict-yes*H0*5
 -->
 (S1 ^operator O2097 = 0.)
Firing prefer*rvt*predict-yes*H0
 -->
Firing prefer*rvt*predict-no*H0
 -->
Firing elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir U +)
 inner elaboration loop at bottom goal.
Retracting elaborate*copy-see-to-output-link
 -->
 (I3 ^see 1 +)
Retracting propose*predict-no
 -->
 (O2098 ^name predict-no +)
 (S1 ^operator O2098 +)
Retracting propose*predict-yes
 -->
 (O2097 ^name predict-yes +)
 (S1 ^operator O2097 +)
Retracting elaborate*reward*based*on*reward
 -->
 (R1052 ^value 1 +)
 (R1 ^reward R1052 +)
Retracting elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir U +)
Retracting rl*prefer*rvt*predict-no*H0*6
 -->
 (S1 ^operator O2098 = 0.9999999999999999)
Retracting rl*prefer*rvt*predict-yes*H0*5
 -->
 (S1 ^operator O2097 = 0.)
=>WM: (14750: S1 ^operator O2100 +)
=>WM: (14749: S1 ^operator O2099 +)
=>WM: (14748: O2100 ^name predict-no)
=>WM: (14747: O2099 ^name predict-yes)
=>WM: (14746: R1053 ^value 1)
=>WM: (14745: R1 ^reward R1053)
=>WM: (14744: I3 ^see 0)
<=WM: (14735: S1 ^operator O2097 +)
<=WM: (14736: S1 ^operator O2098 +)
<=WM: (14737: S1 ^operator O2098)
<=WM: (14730: R1 ^reward R1052)
<=WM: (14715: I3 ^see 1)
<=WM: (14733: O2098 ^name predict-no)
<=WM: (14732: O2097 ^name predict-yes)
<=WM: (14731: R1052 ^value 1)

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing prefer*rvt*predict-yes*H0
 -->
Firing rl*prefer*rvt*predict-yes*H0*5
 -->
 (S1 ^operator O2099 = 0.)
Firing prefer*rvt*predict-no*H0
 -->
Firing rl*prefer*rvt*predict-no*H0*6
 -->
 (S1 ^operator O2100 = 0.9999999999999999)
 inner elaboration loop at bottom goal.
Retracting rl*prefer*rvt*predict-no*H0*6
 -->
 (S1 ^operator O2098 = 0.9999999999999999)
Retracting rl*prefer*rvt*predict-yes*H0*5
 -->
 (S1 ^operator O2097 = 0.)

--- END Proposal Phase ---

--- Decision Phase ---
RL update rl*prefer*rvt*predict-no*H0*6 1 0 1 -> 1 0 1(R,m,v=1,1,0)
=>WM: (14751: S1 ^operator O2100)

  1050:    O: O2100 (predict-no)
--- END Decision Phase ---

--- Application Phase ---
	--- Firing Productions (PE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing apply*operator
 -->
 (I3 ^predict-no N1050 +  :O )
Firing apply*operator*complete
 -->
 (I3 ^predict-no N1049 -  :O )
 inner elaboration loop at bottom goal.
	--- Change Working Memory (PE) ---
=>WM: (14752: I3 ^predict-no N1050)
<=WM: (14739: N1049 ^status complete)
<=WM: (14738: I3 ^predict-no N1049)
	--- Firing Productions (IE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing monitor*world
 -->

I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
	--- Change Working Memory (IE) ---

--- END Application Phase ---
--- Output Phase ---
ENV: Agent did: predict-no for direction U in state State-B
In  State-B moving U
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isL
--- END Output Phase ---
-/|--- Input Phase --- 
=>WM: (14756: I2 ^dir L)
=>WM: (14755: I2 ^reward 1)
=>WM: (14754: I2 ^see 0)
=>WM: (14753: N1050 ^status complete)
<=WM: (14742: I2 ^dir U)
<=WM: (14741: I2 ^reward 1)
<=WM: (14740: I2 ^see 0)
=>WM: (14757: I2 ^level-1 R1-root)
<=WM: (14743: I2 ^level-1 R1-root)

--- END Input Phase --- 

--- Proposal Phase ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing rl*prefer*rvt*predict-yes*H0*1*H1*22
 -->
 (S1 ^operator O2099 = 0.4768786732073501)
Firing rl*prefer*rvt*predict-no*H0*2*H1*10
 -->
 (S1 ^operator O2100 = -0.01194930198035649)
Firing prefer*rvt*predict-no*H0*2*H1
 -->
Firing prefer*rvt*predict-yes*H0*1*H1
 -->
Firing elaborate*copy-see-to-output-link
 -->
 (I3 ^see 0 +)
Firing elaborate*reward*based*on*reward
 -->
 (R1054 ^value 1 +)
 (R1 ^reward R1054 +)
Firing propose*predict-yes
 -->
 (O2101 ^name predict-yes +)
 (S1 ^operator O2101 +)
Firing propose*predict-no
 -->
 (O2102 ^name predict-no +)
 (S1 ^operator O2102 +)
Firing rl*prefer*rvt*predict-no*H0*2
 -->
 (S1 ^operator O2100 = 0.2550133912230119)
Firing rl*prefer*rvt*predict-yes*H0*1
 -->
 (S1 ^operator O2099 = 0.5231192924538035)
Firing prefer*rvt*predict-yes*H0
 -->
Firing prefer*rvt*predict-no*H0
 -->
Firing elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir L +)
 inner elaboration loop at bottom goal.
Retracting elaborate*copy-see-to-output-link
 -->
 (I3 ^see 0 +)
Retracting propose*predict-no
 -->
 (O2100 ^name predict-no +)
 (S1 ^operator O2100 +)
Retracting propose*predict-yes
 -->
 (O2099 ^name predict-yes +)
 (S1 ^operator O2099 +)
Retracting elaborate*reward*based*on*reward
 -->
 (R1053 ^value 1 +)
 (R1 ^reward R1053 +)
Retracting elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir U +)
Retracting rl*prefer*rvt*predict-no*H0*6
 -->
 (S1 ^operator O2100 = 0.9999999999999999)
Retracting rl*prefer*rvt*predict-yes*H0*5
 -->
 (S1 ^operator O2099 = 0.)
=>WM: (14764: S1 ^operator O2102 +)
=>WM: (14763: S1 ^operator O2101 +)
=>WM: (14762: I3 ^dir L)
=>WM: (14761: O2102 ^name predict-no)
=>WM: (14760: O2101 ^name predict-yes)
=>WM: (14759: R1054 ^value 1)
=>WM: (14758: R1 ^reward R1054)
<=WM: (14749: S1 ^operator O2099 +)
<=WM: (14750: S1 ^operator O2100 +)
<=WM: (14751: S1 ^operator O2100)
<=WM: (14734: I3 ^dir U)
<=WM: (14745: R1 ^reward R1053)
<=WM: (14748: O2100 ^name predict-no)
<=WM: (14747: O2099 ^name predict-yes)
<=WM: (14746: R1053 ^value 1)

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing prefer*rvt*predict-yes*H0
 -->
Firing rl*prefer*rvt*predict-yes*H0*1*H1*22
 -->
 (S1 ^operator O2101 = 0.4768786732073501)
Firing rl*prefer*rvt*predict-yes*H0*1
 -->
 (S1 ^operator O2101 = 0.5231192924538035)
Firing prefer*rvt*predict-yes*H0*1*H1
 -->
Firing prefer*rvt*predict-no*H0
 -->
Firing rl*prefer*rvt*predict-no*H0*2*H1*10
 -->
 (S1 ^operator O2102 = -0.01194930198035649)
Firing rl*prefer*rvt*predict-no*H0*2
 -->
 (S1 ^operator O2102 = 0.2550133912230119)
Firing prefer*rvt*predict-no*H0*2*H1
 -->
 inner elaboration loop at bottom goal.
Retracting rl*prefer*rvt*predict-no*H0*2
 -->
 (S1 ^operator O2100 = 0.2550133912230119)
Retracting rl*prefer*rvt*predict-no*H0*2*H1*10
 -->
 (S1 ^operator O2100 = -0.01194930198035649)
Retracting rl*prefer*rvt*predict-yes*H0*1
 -->
 (S1 ^operator O2099 = 0.5231192924538035)
Retracting rl*prefer*rvt*predict-yes*H0*1*H1*22
 -->
 (S1 ^operator O2099 = 0.4768786732073501)

--- END Proposal Phase ---

--- Decision Phase ---
RL update rl*prefer*rvt*predict-no*H0*6 1 0 1 -> 1 0 1(R,m,v=1,1,0)
=>WM: (14765: S1 ^operator O2101)

  1051:    O: O2101 (predict-yes)
--- END Decision Phase ---

--- Application Phase ---
	--- Firing Productions (PE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing apply*operator
 -->
 (I3 ^predict-yes N1051 +  :O )
Firing apply*operator*complete
 -->
 (I3 ^predict-no N1050 -  :O )
 inner elaboration loop at bottom goal.
	--- Change Working Memory (PE) ---
=>WM: (14766: I3 ^predict-yes N1051)
<=WM: (14753: N1050 ^status complete)
<=WM: (14752: I3 ^predict-no N1050)
	--- Firing Productions (IE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing monitor*world
 -->

I see 1 and I'm going to do: predict-yes inner elaboration loop at bottom goal.
	--- Change Working Memory (IE) ---

--- END Application Phase ---
--- Output Phase ---
ENV: Agent did: predict-yes for direction L in state State-B
In  State-B moving L
ENV: (next state, see, prediction correct?) = (State-A, 1, True)
predict error 0
dir: dir isU
--- END Output Phase ---
\--- Input Phase --- 
=>WM: (14770: I2 ^dir U)
=>WM: (14769: I2 ^reward 1)
=>WM: (14768: I2 ^see 1)
=>WM: (14767: N1051 ^status complete)
<=WM: (14756: I2 ^dir L)
<=WM: (14755: I2 ^reward 1)
<=WM: (14754: I2 ^see 0)
=>WM: (14771: I2 ^level-1 L1-root)
<=WM: (14757: I2 ^level-1 R1-root)

--- END Input Phase --- 

--- Proposal Phase ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing elaborate*copy-see-to-output-link
 -->
 (I3 ^see 1 +)
Firing elaborate*reward*based*on*reward
 -->
 (R1055 ^value 1 +)
 (R1 ^reward R1055 +)
Firing propose*predict-yes
 -->
 (O2103 ^name predict-yes +)
 (S1 ^operator O2103 +)
Firing propose*predict-no
 -->
 (O2104 ^name predict-no +)
 (S1 ^operator O2104 +)
Firing rl*prefer*rvt*predict-no*H0*6
 -->
 (S1 ^operator O2102 = 0.9999999999999999)
Firing rl*prefer*rvt*predict-yes*H0*5
 -->
 (S1 ^operator O2101 = 0.)
Firing prefer*rvt*predict-yes*H0
 -->
Firing prefer*rvt*predict-no*H0
 -->
Firing elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir U +)
 inner elaboration loop at bottom goal.
Retracting elaborate*copy-see-to-output-link
 -->
 (I3 ^see 0 +)
Retracting propose*predict-no
 -->
 (O2102 ^name predict-no +)
 (S1 ^operator O2102 +)
Retracting propose*predict-yes
 -->
 (O2101 ^name predict-yes +)
 (S1 ^operator O2101 +)
Retracting elaborate*reward*based*on*reward
 -->
 (R1054 ^value 1 +)
 (R1 ^reward R1054 +)
Retracting elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir L +)
Retracting rl*prefer*rvt*predict-no*H0*2
 -->
 (S1 ^operator O2102 = 0.2550133912230119)
Retracting rl*prefer*rvt*predict-no*H0*2*H1*10
 -->
 (S1 ^operator O2102 = -0.01194930198035649)
Retracting rl*prefer*rvt*predict-yes*H0*1
 -->
 (S1 ^operator O2101 = 0.5231192924538035)
Retracting rl*prefer*rvt*predict-yes*H0*1*H1*22
 -->
 (S1 ^operator O2101 = 0.4768786732073501)
=>WM: (14779: S1 ^operator O2104 +)
=>WM: (14778: S1 ^operator O2103 +)
=>WM: (14777: I3 ^dir U)
=>WM: (14776: O2104 ^name predict-no)
=>WM: (14775: O2103 ^name predict-yes)
=>WM: (14774: R1055 ^value 1)
=>WM: (14773: R1 ^reward R1055)
=>WM: (14772: I3 ^see 1)
<=WM: (14763: S1 ^operator O2101 +)
<=WM: (14765: S1 ^operator O2101)
<=WM: (14764: S1 ^operator O2102 +)
<=WM: (14762: I3 ^dir L)
<=WM: (14758: R1 ^reward R1054)
<=WM: (14744: I3 ^see 0)
<=WM: (14761: O2102 ^name predict-no)
<=WM: (14760: O2101 ^name predict-yes)
<=WM: (14759: R1054 ^value 1)

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing prefer*rvt*predict-yes*H0
 -->
Firing rl*prefer*rvt*predict-yes*H0*5
 -->
 (S1 ^operator O2103 = 0.)
Firing prefer*rvt*predict-no*H0
 -->
Firing rl*prefer*rvt*predict-no*H0*6
 -->
 (S1 ^operator O2104 = 0.9999999999999999)
 inner elaboration loop at bottom goal.
Retracting rl*prefer*rvt*predict-no*H0*6
 -->
 (S1 ^operator O2102 = 0.9999999999999999)
Retracting rl*prefer*rvt*predict-yes*H0*5
 -->
 (S1 ^operator O2101 = 0.)

--- END Proposal Phase ---

--- Decision Phase ---
RL update rl*prefer*rvt*predict-yes*H0*1 0.727959 -0.20484 0.523119 -> 0.727959 -0.20484 0.52312(R,m,v=1,0.980132,0.0196026)
RL update rl*prefer*rvt*predict-yes*H0*1*H1*22 0.272038 0.20484 0.476879 -> 0.272039 0.20484 0.476879(R,m,v=1,1,0)
=>WM: (14780: S1 ^operator O2104)

  1052:    O: O2104 (predict-no)
--- END Decision Phase ---

--- Application Phase ---
	--- Firing Productions (PE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing apply*operator
 -->
 (I3 ^predict-no N1052 +  :O )
Firing apply*operator*complete
 -->
 (I3 ^predict-yes N1051 -  :O )
 inner elaboration loop at bottom goal.
	--- Change Working Memory (PE) ---
=>WM: (14781: I3 ^predict-no N1052)
<=WM: (14767: N1051 ^status complete)
<=WM: (14766: I3 ^predict-yes N1051)
	--- Firing Productions (IE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing monitor*world
 -->

I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
	--- Change Working Memory (IE) ---

--- END Application Phase ---
--- Output Phase ---
ENV: Agent did: predict-no for direction U in state State-A
In  State-A moving U
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isR
--- END Output Phase ---
-/|--- Input Phase --- 
=>WM: (14785: I2 ^dir R)
=>WM: (14784: I2 ^reward 1)
=>WM: (14783: I2 ^see 0)
=>WM: (14782: N1052 ^status complete)
<=WM: (14770: I2 ^dir U)
<=WM: (14769: I2 ^reward 1)
<=WM: (14768: I2 ^see 1)
=>WM: (14786: I2 ^level-1 L1-root)
<=WM: (14771: I2 ^level-1 L1-root)

--- END Input Phase --- 

--- Proposal Phase ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing rl*prefer*rvt*predict-yes*H0*3*H1*9
 -->
 (S1 ^operator O2103 = 0.6170493230317728)
Firing rl*prefer*rvt*predict-no*H0*4*H1*8
 -->
 (S1 ^operator O2104 = 0.4901349546100854)
Firing prefer*rvt*predict-no*H0*4*H1
 -->
Firing prefer*rvt*predict-yes*H0*3*H1
 -->
Firing elaborate*copy-see-to-output-link
 -->
 (I3 ^see 0 +)
Firing elaborate*reward*based*on*reward
 -->
 (R1056 ^value 1 +)
 (R1 ^reward R1056 +)
Firing propose*predict-yes
 -->
 (O2105 ^name predict-yes +)
 (S1 ^operator O2105 +)
Firing propose*predict-no
 -->
 (O2106 ^name predict-no +)
 (S1 ^operator O2106 +)
Firing rl*prefer*rvt*predict-no*H0*4
 -->
 (S1 ^operator O2104 = 0.1269768524690122)
Firing rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O2103 = 0.3829453488915282)
Firing prefer*rvt*predict-yes*H0
 -->
Firing prefer*rvt*predict-no*H0
 -->
Firing elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir R +)
 inner elaboration loop at bottom goal.
Retracting elaborate*copy-see-to-output-link
 -->
 (I3 ^see 1 +)
Retracting propose*predict-no
 -->
 (O2104 ^name predict-no +)
 (S1 ^operator O2104 +)
Retracting propose*predict-yes
 -->
 (O2103 ^name predict-yes +)
 (S1 ^operator O2103 +)
Retracting elaborate*reward*based*on*reward
 -->
 (R1055 ^value 1 +)
 (R1 ^reward R1055 +)
Retracting elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir U +)
Retracting rl*prefer*rvt*predict-no*H0*6
 -->
 (S1 ^operator O2104 = 0.9999999999999999)
Retracting rl*prefer*rvt*predict-yes*H0*5
 -->
 (S1 ^operator O2103 = 0.)
=>WM: (14794: S1 ^operator O2106 +)
=>WM: (14793: S1 ^operator O2105 +)
=>WM: (14792: I3 ^dir R)
=>WM: (14791: O2106 ^name predict-no)
=>WM: (14790: O2105 ^name predict-yes)
=>WM: (14789: R1056 ^value 1)
=>WM: (14788: R1 ^reward R1056)
=>WM: (14787: I3 ^see 0)
<=WM: (14778: S1 ^operator O2103 +)
<=WM: (14779: S1 ^operator O2104 +)
<=WM: (14780: S1 ^operator O2104)
<=WM: (14777: I3 ^dir U)
<=WM: (14773: R1 ^reward R1055)
<=WM: (14772: I3 ^see 1)
<=WM: (14776: O2104 ^name predict-no)
<=WM: (14775: O2103 ^name predict-yes)
<=WM: (14774: R1055 ^value 1)

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing prefer*rvt*predict-yes*H0
 -->
Firing rl*prefer*rvt*predict-yes*H0*3*H1*9
 -->
 (S1 ^operator O2105 = 0.6170493230317728)
Firing rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O2105 = 0.3829453488915282)
Firing prefer*rvt*predict-yes*H0*3*H1
 -->
Firing prefer*rvt*predict-no*H0
 -->
Firing rl*prefer*rvt*predict-no*H0*4*H1*8
 -->
 (S1 ^operator O2106 = 0.4901349546100854)
Firing rl*prefer*rvt*predict-no*H0*4
 -->
 (S1 ^operator O2106 = 0.1269768524690122)
Firing prefer*rvt*predict-no*H0*4*H1
 -->
 inner elaboration loop at bottom goal.
Retracting rl*prefer*rvt*predict-no*H0*4
 -->
 (S1 ^operator O2104 = 0.1269768524690122)
Retracting rl*prefer*rvt*predict-no*H0*4*H1*8
 -->
 (S1 ^operator O2104 = 0.4901349546100854)
Retracting rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O2103 = 0.3829453488915282)
Retracting rl*prefer*rvt*predict-yes*H0*3*H1*9
 -->
 (S1 ^operator O2103 = 0.6170493230317728)

--- END Proposal Phase ---

--- Decision Phase ---
RL update rl*prefer*rvt*predict-no*H0*6 1 0 1 -> 1 0 1(R,m,v=1,1,0)
=>WM: (14795: S1 ^operator O2105)

  1053:    O: O2105 (predict-yes)
--- END Decision Phase ---

--- Application Phase ---
	--- Firing Productions (PE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing apply*operator
 -->
 (I3 ^predict-yes N1053 +  :O )
Firing apply*operator*complete
 -->
 (I3 ^predict-no N1052 -  :O )
 inner elaboration loop at bottom goal.
	--- Change Working Memory (PE) ---
=>WM: (14796: I3 ^predict-yes N1053)
<=WM: (14782: N1052 ^status complete)
<=WM: (14781: I3 ^predict-no N1052)
	--- Firing Productions (IE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing monitor*world
 -->

I see 1 and I'm going to do: predict-yes inner elaboration loop at bottom goal.
	--- Change Working Memory (IE) ---

--- END Application Phase ---
--- Output Phase ---
ENV: Agent did: predict-yes for direction R in state State-A
In  State-A moving R
ENV: (next state, see, prediction correct?) = (State-B, 1, True)
predict error 0
dir: dir isU
--- END Output Phase ---
\-/|--- Input Phase --- 
=>WM: (14800: I2 ^dir U)
=>WM: (14799: I2 ^reward 1)
=>WM: (14798: I2 ^see 1)
=>WM: (14797: N1053 ^status complete)
<=WM: (14785: I2 ^dir R)
<=WM: (14784: I2 ^reward 1)
<=WM: (14783: I2 ^see 0)
=>WM: (14801: I2 ^level-1 R1-root)
<=WM: (14786: I2 ^level-1 L1-root)

--- END Input Phase --- 

--- Proposal Phase ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing elaborate*copy-see-to-output-link
 -->
 (I3 ^see 1 +)
Firing elaborate*reward*based*on*reward
 -->
 (R1057 ^value 1 +)
 (R1 ^reward R1057 +)
Firing propose*predict-yes
 -->
 (O2107 ^name predict-yes +)
 (S1 ^operator O2107 +)
Firing propose*predict-no
 -->
 (O2108 ^name predict-no +)
 (S1 ^operator O2108 +)
Firing rl*prefer*rvt*predict-no*H0*6
 -->
 (S1 ^operator O2106 = 0.9999999999999999)
Firing rl*prefer*rvt*predict-yes*H0*5
 -->
 (S1 ^operator O2105 = 0.)
Firing prefer*rvt*predict-yes*H0
 -->
Firing prefer*rvt*predict-no*H0
 -->
Firing elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir U +)
 inner elaboration loop at bottom goal.
Retracting elaborate*copy-see-to-output-link
 -->
 (I3 ^see 0 +)
Retracting propose*predict-no
 -->
 (O2106 ^name predict-no +)
 (S1 ^operator O2106 +)
Retracting propose*predict-yes
 -->
 (O2105 ^name predict-yes +)
 (S1 ^operator O2105 +)
Retracting elaborate*reward*based*on*reward
 -->
 (R1056 ^value 1 +)
 (R1 ^reward R1056 +)
Retracting elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir R +)
Retracting rl*prefer*rvt*predict-no*H0*4
 -->
 (S1 ^operator O2106 = 0.1269768524690122)
Retracting rl*prefer*rvt*predict-no*H0*4*H1*8
 -->
 (S1 ^operator O2106 = 0.4901349546100854)
Retracting rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O2105 = 0.3829453488915282)
Retracting rl*prefer*rvt*predict-yes*H0*3*H1*9
 -->
 (S1 ^operator O2105 = 0.6170493230317728)
=>WM: (14809: S1 ^operator O2108 +)
=>WM: (14808: S1 ^operator O2107 +)
=>WM: (14807: I3 ^dir U)
=>WM: (14806: O2108 ^name predict-no)
=>WM: (14805: O2107 ^name predict-yes)
=>WM: (14804: R1057 ^value 1)
=>WM: (14803: R1 ^reward R1057)
=>WM: (14802: I3 ^see 1)
<=WM: (14793: S1 ^operator O2105 +)
<=WM: (14795: S1 ^operator O2105)
<=WM: (14794: S1 ^operator O2106 +)
<=WM: (14792: I3 ^dir R)
<=WM: (14788: R1 ^reward R1056)
<=WM: (14787: I3 ^see 0)
<=WM: (14791: O2106 ^name predict-no)
<=WM: (14790: O2105 ^name predict-yes)
<=WM: (14789: R1056 ^value 1)

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing prefer*rvt*predict-yes*H0
 -->
Firing rl*prefer*rvt*predict-yes*H0*5
 -->
 (S1 ^operator O2107 = 0.)
Firing prefer*rvt*predict-no*H0
 -->
Firing rl*prefer*rvt*predict-no*H0*6
 -->
 (S1 ^operator O2108 = 0.9999999999999999)
 inner elaboration loop at bottom goal.
Retracting rl*prefer*rvt*predict-no*H0*6
 -->
 (S1 ^operator O2106 = 0.9999999999999999)
Retracting rl*prefer*rvt*predict-yes*H0*5
 -->
 (S1 ^operator O2105 = 0.)

--- END Proposal Phase ---

--- Decision Phase ---
RL update rl*prefer*rvt*predict-yes*H0*3 0.673138 -0.290193 0.382945 -> 0.673139 -0.290193 0.382946(R,m,v=1,0.962963,0.0358868)
RL update rl*prefer*rvt*predict-yes*H0*3*H1*9 0.326857 0.290192 0.617049 -> 0.326858 0.290192 0.61705(R,m,v=1,1,0)
=>WM: (14810: S1 ^operator O2108)

  1054:    O: O2108 (predict-no)
--- END Decision Phase ---

--- Application Phase ---
	--- Firing Productions (PE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing apply*operator
 -->
 (I3 ^predict-no N1054 +  :O )
Firing apply*operator*complete
 -->
 (I3 ^predict-yes N1053 -  :O )
 inner elaboration loop at bottom goal.
	--- Change Working Memory (PE) ---
=>WM: (14811: I3 ^predict-no N1054)
<=WM: (14797: N1053 ^status complete)
<=WM: (14796: I3 ^predict-yes N1053)
	--- Firing Productions (IE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing monitor*world
 -->

I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
	--- Change Working Memory (IE) ---

--- END Application Phase ---
--- Output Phase ---
ENV: Agent did: predict-no for direction U in state State-B
In  State-B moving U
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isR
--- END Output Phase ---
\---- Input Phase --- 
=>WM: (14815: I2 ^dir R)
=>WM: (14814: I2 ^reward 1)
=>WM: (14813: I2 ^see 0)
=>WM: (14812: N1054 ^status complete)
<=WM: (14800: I2 ^dir U)
<=WM: (14799: I2 ^reward 1)
<=WM: (14798: I2 ^see 1)
=>WM: (14816: I2 ^level-1 R1-root)
<=WM: (14801: I2 ^level-1 R1-root)

--- END Input Phase --- 

--- Proposal Phase ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing rl*prefer*rvt*predict-yes*H0*3*H1*16
 -->
 (S1 ^operator O2107 = 0.08783148430849691)
Firing rl*prefer*rvt*predict-no*H0*4*H1*15
 -->
 (S1 ^operator O2108 = 0.8730232725957683)
Firing prefer*rvt*predict-no*H0*4*H1
 -->
Firing prefer*rvt*predict-yes*H0*3*H1
 -->
Firing elaborate*copy-see-to-output-link
 -->
 (I3 ^see 0 +)
Firing elaborate*reward*based*on*reward
 -->
 (R1058 ^value 1 +)
 (R1 ^reward R1058 +)
Firing propose*predict-yes
 -->
 (O2109 ^name predict-yes +)
 (S1 ^operator O2109 +)
Firing propose*predict-no
 -->
 (O2110 ^name predict-no +)
 (S1 ^operator O2110 +)
Firing rl*prefer*rvt*predict-no*H0*4
 -->
 (S1 ^operator O2108 = 0.1269768524690122)
Firing rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O2107 = 0.382946148103033)
Firing prefer*rvt*predict-yes*H0
 -->
Firing prefer*rvt*predict-no*H0
 -->
Firing elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir R +)
 inner elaboration loop at bottom goal.
Retracting elaborate*copy-see-to-output-link
 -->
 (I3 ^see 1 +)
Retracting propose*predict-no
 -->
 (O2108 ^name predict-no +)
 (S1 ^operator O2108 +)
Retracting propose*predict-yes
 -->
 (O2107 ^name predict-yes +)
 (S1 ^operator O2107 +)
Retracting elaborate*reward*based*on*reward
 -->
 (R1057 ^value 1 +)
 (R1 ^reward R1057 +)
Retracting elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir U +)
Retracting rl*prefer*rvt*predict-no*H0*6
 -->
 (S1 ^operator O2108 = 0.9999999999999999)
Retracting rl*prefer*rvt*predict-yes*H0*5
 -->
 (S1 ^operator O2107 = 0.)
=>WM: (14824: S1 ^operator O2110 +)
=>WM: (14823: S1 ^operator O2109 +)
=>WM: (14822: I3 ^dir R)
=>WM: (14821: O2110 ^name predict-no)
=>WM: (14820: O2109 ^name predict-yes)
=>WM: (14819: R1058 ^value 1)
=>WM: (14818: R1 ^reward R1058)
=>WM: (14817: I3 ^see 0)
<=WM: (14808: S1 ^operator O2107 +)
<=WM: (14809: S1 ^operator O2108 +)
<=WM: (14810: S1 ^operator O2108)
<=WM: (14807: I3 ^dir U)
<=WM: (14803: R1 ^reward R1057)
<=WM: (14802: I3 ^see 1)
<=WM: (14806: O2108 ^name predict-no)
<=WM: (14805: O2107 ^name predict-yes)
<=WM: (14804: R1057 ^value 1)

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing prefer*rvt*predict-yes*H0
 -->
Firing rl*prefer*rvt*predict-yes*H0*3*H1*16
 -->
 (S1 ^operator O2109 = 0.08783148430849691)
Firing rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O2109 = 0.382946148103033)
Firing prefer*rvt*predict-yes*H0*3*H1
 -->
Firing prefer*rvt*predict-no*H0
 -->
Firing rl*prefer*rvt*predict-no*H0*4*H1*15
 -->
 (S1 ^operator O2110 = 0.8730232725957683)
Firing rl*prefer*rvt*predict-no*H0*4
 -->
 (S1 ^operator O2110 = 0.1269768524690122)
Firing prefer*rvt*predict-no*H0*4*H1
 -->
 inner elaboration loop at bottom goal.
Retracting rl*prefer*rvt*predict-no*H0*4
 -->
 (S1 ^operator O2108 = 0.1269768524690122)
Retracting rl*prefer*rvt*predict-no*H0*4*H1*15
 -->
 (S1 ^operator O2108 = 0.8730232725957683)
Retracting rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O2107 = 0.382946148103033)
Retracting rl*prefer*rvt*predict-yes*H0*3*H1*16
 -->
 (S1 ^operator O2107 = 0.08783148430849691)

--- END Proposal Phase ---

--- Decision Phase ---
RL update rl*prefer*rvt*predict-no*H0*6 1 0 1 -> 1 0 1(R,m,v=1,1,0)
=>WM: (14825: S1 ^operator O2110)

  1055:    O: O2110 (predict-no)
--- END Decision Phase ---

--- Application Phase ---
	--- Firing Productions (PE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing apply*operator
 -->
 (I3 ^predict-no N1055 +  :O )
Firing apply*operator*complete
 -->
 (I3 ^predict-no N1054 -  :O )
 inner elaboration loop at bottom goal.
	--- Change Working Memory (PE) ---
=>WM: (14826: I3 ^predict-no N1055)
<=WM: (14812: N1054 ^status complete)
<=WM: (14811: I3 ^predict-no N1054)
	--- Firing Productions (IE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing monitor*world
 -->

I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
	--- Change Working Memory (IE) ---

--- END Application Phase ---
--- Output Phase ---
ENV: Agent did: predict-no for direction R in state State-B
In  State-B moving R
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isL
--- END Output Phase ---
/|\--- Input Phase --- 
=>WM: (14830: I2 ^dir L)
=>WM: (14829: I2 ^reward 1)
=>WM: (14828: I2 ^see 0)
=>WM: (14827: N1055 ^status complete)
<=WM: (14815: I2 ^dir R)
<=WM: (14814: I2 ^reward 1)
<=WM: (14813: I2 ^see 0)
=>WM: (14831: I2 ^level-1 R0-root)
<=WM: (14816: I2 ^level-1 R1-root)

--- END Input Phase --- 

--- Proposal Phase ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing rl*prefer*rvt*predict-yes*H0*1*H1*19
 -->
 (S1 ^operator O2109 = 0.4768813258528501)
Firing rl*prefer*rvt*predict-no*H0*2*H1*7
 -->
 (S1 ^operator O2110 = 0.1700769046561409)
Firing prefer*rvt*predict-no*H0*2*H1
 -->
Firing prefer*rvt*predict-yes*H0*1*H1
 -->
Firing elaborate*copy-see-to-output-link
 -->
 (I3 ^see 0 +)
Firing elaborate*reward*based*on*reward
 -->
 (R1059 ^value 1 +)
 (R1 ^reward R1059 +)
Firing propose*predict-yes
 -->
 (O2111 ^name predict-yes +)
 (S1 ^operator O2111 +)
Firing propose*predict-no
 -->
 (O2112 ^name predict-no +)
 (S1 ^operator O2112 +)
Firing rl*prefer*rvt*predict-no*H0*2
 -->
 (S1 ^operator O2110 = 0.2550133912230119)
Firing rl*prefer*rvt*predict-yes*H0*1
 -->
 (S1 ^operator O2109 = 0.5231195976046303)
Firing prefer*rvt*predict-yes*H0
 -->
Firing prefer*rvt*predict-no*H0
 -->
Firing elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir L +)
 inner elaboration loop at bottom goal.
Retracting elaborate*copy-see-to-output-link
 -->
 (I3 ^see 0 +)
Retracting propose*predict-no
 -->
 (O2110 ^name predict-no +)
 (S1 ^operator O2110 +)
Retracting propose*predict-yes
 -->
 (O2109 ^name predict-yes +)
 (S1 ^operator O2109 +)
Retracting elaborate*reward*based*on*reward
 -->
 (R1058 ^value 1 +)
 (R1 ^reward R1058 +)
Retracting elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir R +)
Retracting rl*prefer*rvt*predict-no*H0*4
 -->
 (S1 ^operator O2110 = 0.1269768524690122)
Retracting rl*prefer*rvt*predict-no*H0*4*H1*15
 -->
 (S1 ^operator O2110 = 0.8730232725957683)
Retracting rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O2109 = 0.382946148103033)
Retracting rl*prefer*rvt*predict-yes*H0*3*H1*16
 -->
 (S1 ^operator O2109 = 0.08783148430849691)
=>WM: (14838: S1 ^operator O2112 +)
=>WM: (14837: S1 ^operator O2111 +)
=>WM: (14836: I3 ^dir L)
=>WM: (14835: O2112 ^name predict-no)
=>WM: (14834: O2111 ^name predict-yes)
=>WM: (14833: R1059 ^value 1)
=>WM: (14832: R1 ^reward R1059)
<=WM: (14823: S1 ^operator O2109 +)
<=WM: (14824: S1 ^operator O2110 +)
<=WM: (14825: S1 ^operator O2110)
<=WM: (14822: I3 ^dir R)
<=WM: (14818: R1 ^reward R1058)
<=WM: (14821: O2110 ^name predict-no)
<=WM: (14820: O2109 ^name predict-yes)
<=WM: (14819: R1058 ^value 1)

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing prefer*rvt*predict-yes*H0
 -->
Firing rl*prefer*rvt*predict-yes*H0*1
 -->
 (S1 ^operator O2111 = 0.5231195976046303)
Firing prefer*rvt*predict-yes*H0*1*H1
 -->
Firing rl*prefer*rvt*predict-yes*H0*1*H1*19
 -->
 (S1 ^operator O2111 = 0.4768813258528501)
Firing prefer*rvt*predict-no*H0
 -->
Firing rl*prefer*rvt*predict-no*H0*2
 -->
 (S1 ^operator O2112 = 0.2550133912230119)
Firing prefer*rvt*predict-no*H0*2*H1
 -->
Firing rl*prefer*rvt*predict-no*H0*2*H1*7
 -->
 (S1 ^operator O2112 = 0.1700769046561409)
 inner elaboration loop at bottom goal.
Retracting rl*prefer*rvt*predict-no*H0*2
 -->
 (S1 ^operator O2110 = 0.2550133912230119)
Retracting rl*prefer*rvt*predict-no*H0*2*H1*7
 -->
 (S1 ^operator O2110 = 0.1700769046561409)
Retracting rl*prefer*rvt*predict-yes*H0*1
 -->
 (S1 ^operator O2109 = 0.5231195976046303)
Retracting rl*prefer*rvt*predict-yes*H0*1*H1*19
 -->
 (S1 ^operator O2109 = 0.4768813258528501)

--- END Proposal Phase ---

--- Decision Phase ---
RL update rl*prefer*rvt*predict-no*H0*4 0.814714 -0.687737 0.126977 -> 0.814714 -0.687737 0.126977(R,m,v=1,0.952381,0.0455927)
RL update rl*prefer*rvt*predict-no*H0*4*H1*15 0.185286 0.687737 0.873023 -> 0.185286 0.687737 0.873023(R,m,v=1,1,0)
=>WM: (14839: S1 ^operator O2111)

  1056:    O: O2111 (predict-yes)
--- END Decision Phase ---

--- Application Phase ---
	--- Firing Productions (PE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing apply*operator
 -->
 (I3 ^predict-yes N1056 +  :O )
Firing apply*operator*complete
 -->
 (I3 ^predict-no N1055 -  :O )
 inner elaboration loop at bottom goal.
	--- Change Working Memory (PE) ---
=>WM: (14840: I3 ^predict-yes N1056)
<=WM: (14827: N1055 ^status complete)
<=WM: (14826: I3 ^predict-no N1055)
	--- Firing Productions (IE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing monitor*world
 -->

I see 1 and I'm going to do: predict-yes inner elaboration loop at bottom goal.
	--- Change Working Memory (IE) ---

--- END Application Phase ---
--- Output Phase ---
ENV: Agent did: predict-yes for direction L in state State-B
In  State-B moving L
ENV: (next state, see, prediction correct?) = (State-A, 1, True)
predict error 0
dir: dir isR
--- END Output Phase ---
-/|--- Input Phase --- 
=>WM: (14844: I2 ^dir R)
=>WM: (14843: I2 ^reward 1)
=>WM: (14842: I2 ^see 1)
=>WM: (14841: N1056 ^status complete)
<=WM: (14830: I2 ^dir L)
<=WM: (14829: I2 ^reward 1)
<=WM: (14828: I2 ^see 0)
=>WM: (14845: I2 ^level-1 L1-root)
<=WM: (14831: I2 ^level-1 R0-root)

--- END Input Phase --- 

--- Proposal Phase ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing rl*prefer*rvt*predict-yes*H0*3*H1*9
 -->
 (S1 ^operator O2111 = 0.6170501222432777)
Firing rl*prefer*rvt*predict-no*H0*4*H1*8
 -->
 (S1 ^operator O2112 = 0.4901349546100854)
Firing prefer*rvt*predict-no*H0*4*H1
 -->
Firing prefer*rvt*predict-yes*H0*3*H1
 -->
Firing elaborate*copy-see-to-output-link
 -->
 (I3 ^see 1 +)
Firing elaborate*reward*based*on*reward
 -->
 (R1060 ^value 1 +)
 (R1 ^reward R1060 +)
Firing propose*predict-yes
 -->
 (O2113 ^name predict-yes +)
 (S1 ^operator O2113 +)
Firing propose*predict-no
 -->
 (O2114 ^name predict-no +)
 (S1 ^operator O2114 +)
Firing rl*prefer*rvt*predict-no*H0*4
 -->
 (S1 ^operator O2112 = 0.1269768337092951)
Firing rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O2111 = 0.382946148103033)
Firing prefer*rvt*predict-yes*H0
 -->
Firing prefer*rvt*predict-no*H0
 -->
Firing elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir R +)
 inner elaboration loop at bottom goal.
Retracting elaborate*copy-see-to-output-link
 -->
 (I3 ^see 0 +)
Retracting propose*predict-no
 -->
 (O2112 ^name predict-no +)
 (S1 ^operator O2112 +)
Retracting propose*predict-yes
 -->
 (O2111 ^name predict-yes +)
 (S1 ^operator O2111 +)
Retracting elaborate*reward*based*on*reward
 -->
 (R1059 ^value 1 +)
 (R1 ^reward R1059 +)
Retracting elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir L +)
Retracting rl*prefer*rvt*predict-no*H0*2*H1*7
 -->
 (S1 ^operator O2112 = 0.1700769046561409)
Retracting rl*prefer*rvt*predict-no*H0*2
 -->
 (S1 ^operator O2112 = 0.2550133912230119)
Retracting rl*prefer*rvt*predict-yes*H0*1*H1*19
 -->
 (S1 ^operator O2111 = 0.4768813258528501)
Retracting rl*prefer*rvt*predict-yes*H0*1
 -->
 (S1 ^operator O2111 = 0.5231195976046303)
=>WM: (14853: S1 ^operator O2114 +)
=>WM: (14852: S1 ^operator O2113 +)
=>WM: (14851: I3 ^dir R)
=>WM: (14850: O2114 ^name predict-no)
=>WM: (14849: O2113 ^name predict-yes)
=>WM: (14848: R1060 ^value 1)
=>WM: (14847: R1 ^reward R1060)
=>WM: (14846: I3 ^see 1)
<=WM: (14837: S1 ^operator O2111 +)
<=WM: (14839: S1 ^operator O2111)
<=WM: (14838: S1 ^operator O2112 +)
<=WM: (14836: I3 ^dir L)
<=WM: (14832: R1 ^reward R1059)
<=WM: (14817: I3 ^see 0)
<=WM: (14835: O2112 ^name predict-no)
<=WM: (14834: O2111 ^name predict-yes)
<=WM: (14833: R1059 ^value 1)

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing prefer*rvt*predict-yes*H0
 -->
Firing rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O2113 = 0.382946148103033)
Firing prefer*rvt*predict-yes*H0*3*H1
 -->
Firing rl*prefer*rvt*predict-yes*H0*3*H1*9
 -->
 (S1 ^operator O2113 = 0.6170501222432777)
Firing prefer*rvt*predict-no*H0
 -->
Firing rl*prefer*rvt*predict-no*H0*4
 -->
 (S1 ^operator O2114 = 0.1269768337092951)
Firing prefer*rvt*predict-no*H0*4*H1
 -->
Firing rl*prefer*rvt*predict-no*H0*4*H1*8
 -->
 (S1 ^operator O2114 = 0.4901349546100854)
 inner elaboration loop at bottom goal.
Retracting rl*prefer*rvt*predict-no*H0*4
 -->
 (S1 ^operator O2112 = 0.1269768337092951)
Retracting rl*prefer*rvt*predict-no*H0*4*H1*8
 -->
 (S1 ^operator O2112 = 0.4901349546100854)
Retracting rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O2111 = 0.382946148103033)
Retracting rl*prefer*rvt*predict-yes*H0*3*H1*9
 -->
 (S1 ^operator O2111 = 0.6170501222432777)

--- END Proposal Phase ---

--- Decision Phase ---
RL update rl*prefer*rvt*predict-yes*H0*1 0.727959 -0.20484 0.52312 -> 0.727959 -0.20484 0.523119(R,m,v=1,0.980263,0.0194754)
RL update rl*prefer*rvt*predict-yes*H0*1*H1*19 0.272042 0.204839 0.476881 -> 0.272042 0.20484 0.476881(R,m,v=1,1,0)
=>WM: (14854: S1 ^operator O2113)

  1057:    O: O2113 (predict-yes)
--- END Decision Phase ---

--- Application Phase ---
	--- Firing Productions (PE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing apply*operator
 -->
 (I3 ^predict-yes N1057 +  :O )
Firing apply*operator*complete
 -->
 (I3 ^predict-yes N1056 -  :O )
 inner elaboration loop at bottom goal.
	--- Change Working Memory (PE) ---
=>WM: (14855: I3 ^predict-yes N1057)
<=WM: (14841: N1056 ^status complete)
<=WM: (14840: I3 ^predict-yes N1056)
	--- Firing Productions (IE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing monitor*world
 -->

I see 1 and I'm going to do: predict-yes inner elaboration loop at bottom goal.
	--- Change Working Memory (IE) ---

--- END Application Phase ---
--- Output Phase ---
ENV: Agent did: predict-yes for direction R in state State-A
In  State-A moving R
ENV: (next state, see, prediction correct?) = (State-B, 1, True)
predict error 0
dir: dir isU
--- END Output Phase ---
\---- Input Phase --- 
=>WM: (14859: I2 ^dir U)
=>WM: (14858: I2 ^reward 1)
=>WM: (14857: I2 ^see 1)
=>WM: (14856: N1057 ^status complete)
<=WM: (14844: I2 ^dir R)
<=WM: (14843: I2 ^reward 1)
<=WM: (14842: I2 ^see 1)
=>WM: (14860: I2 ^level-1 R1-root)
<=WM: (14845: I2 ^level-1 L1-root)

--- END Input Phase --- 

--- Proposal Phase ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing elaborate*copy-see-to-output-link
 -->
 (I3 ^see 1 +)
Firing elaborate*reward*based*on*reward
 -->
 (R1061 ^value 1 +)
 (R1 ^reward R1061 +)
Firing propose*predict-yes
 -->
 (O2115 ^name predict-yes +)
 (S1 ^operator O2115 +)
Firing propose*predict-no
 -->
 (O2116 ^name predict-no +)
 (S1 ^operator O2116 +)
Firing rl*prefer*rvt*predict-no*H0*6
 -->
 (S1 ^operator O2114 = 0.9999999999999999)
Firing rl*prefer*rvt*predict-yes*H0*5
 -->
 (S1 ^operator O2113 = 0.)
Firing prefer*rvt*predict-yes*H0
 -->
Firing prefer*rvt*predict-no*H0
 -->
Firing elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir U +)
 inner elaboration loop at bottom goal.
Retracting elaborate*copy-see-to-output-link
 -->
 (I3 ^see 1 +)
Retracting propose*predict-no
 -->
 (O2114 ^name predict-no +)
 (S1 ^operator O2114 +)
Retracting propose*predict-yes
 -->
 (O2113 ^name predict-yes +)
 (S1 ^operator O2113 +)
Retracting elaborate*reward*based*on*reward
 -->
 (R1060 ^value 1 +)
 (R1 ^reward R1060 +)
Retracting elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir R +)
Retracting rl*prefer*rvt*predict-no*H0*4*H1*8
 -->
 (S1 ^operator O2114 = 0.4901349546100854)
Retracting rl*prefer*rvt*predict-no*H0*4
 -->
 (S1 ^operator O2114 = 0.1269768337092951)
Retracting rl*prefer*rvt*predict-yes*H0*3*H1*9
 -->
 (S1 ^operator O2113 = 0.6170501222432777)
Retracting rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O2113 = 0.382946148103033)
=>WM: (14867: S1 ^operator O2116 +)
=>WM: (14866: S1 ^operator O2115 +)
=>WM: (14865: I3 ^dir U)
=>WM: (14864: O2116 ^name predict-no)
=>WM: (14863: O2115 ^name predict-yes)
=>WM: (14862: R1061 ^value 1)
=>WM: (14861: R1 ^reward R1061)
<=WM: (14852: S1 ^operator O2113 +)
<=WM: (14854: S1 ^operator O2113)
<=WM: (14853: S1 ^operator O2114 +)
<=WM: (14851: I3 ^dir R)
<=WM: (14847: R1 ^reward R1060)
<=WM: (14850: O2114 ^name predict-no)
<=WM: (14849: O2113 ^name predict-yes)
<=WM: (14848: R1060 ^value 1)

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing prefer*rvt*predict-yes*H0
 -->
Firing rl*prefer*rvt*predict-yes*H0*5
 -->
 (S1 ^operator O2115 = 0.)
Firing prefer*rvt*predict-no*H0
 -->
Firing rl*prefer*rvt*predict-no*H0*6
 -->
 (S1 ^operator O2116 = 0.9999999999999999)
 inner elaboration loop at bottom goal.
Retracting rl*prefer*rvt*predict-no*H0*6
 -->
 (S1 ^operator O2114 = 0.9999999999999999)
Retracting rl*prefer*rvt*predict-yes*H0*5
 -->
 (S1 ^operator O2113 = 0.)

--- END Proposal Phase ---

--- Decision Phase ---
RL update rl*prefer*rvt*predict-yes*H0*3 0.673139 -0.290193 0.382946 -> 0.673139 -0.290193 0.382947(R,m,v=1,0.96319,0.0356737)
RL update rl*prefer*rvt*predict-yes*H0*3*H1*9 0.326858 0.290192 0.61705 -> 0.326858 0.290192 0.617051(R,m,v=1,1,0)
=>WM: (14868: S1 ^operator O2116)

  1058:    O: O2116 (predict-no)
--- END Decision Phase ---

--- Application Phase ---
	--- Firing Productions (PE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing apply*operator
 -->
 (I3 ^predict-no N1058 +  :O )
Firing apply*operator*complete
 -->
 (I3 ^predict-yes N1057 -  :O )
 inner elaboration loop at bottom goal.
	--- Change Working Memory (PE) ---
=>WM: (14869: I3 ^predict-no N1058)
<=WM: (14856: N1057 ^status complete)
<=WM: (14855: I3 ^predict-yes N1057)
	--- Firing Productions (IE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing monitor*world
 -->

I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
	--- Change Working Memory (IE) ---

--- END Application Phase ---
--- Output Phase ---
ENV: Agent did: predict-no for direction U in state State-B
In  State-B moving U
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isR
--- END Output Phase ---
/|\--- Input Phase --- 
=>WM: (14873: I2 ^dir R)
=>WM: (14872: I2 ^reward 1)
=>WM: (14871: I2 ^see 0)
=>WM: (14870: N1058 ^status complete)
<=WM: (14859: I2 ^dir U)
<=WM: (14858: I2 ^reward 1)
<=WM: (14857: I2 ^see 1)
=>WM: (14874: I2 ^level-1 R1-root)
<=WM: (14860: I2 ^level-1 R1-root)

--- END Input Phase --- 

--- Proposal Phase ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing rl*prefer*rvt*predict-yes*H0*3*H1*16
 -->
 (S1 ^operator O2115 = 0.08783148430849691)
Firing rl*prefer*rvt*predict-no*H0*4*H1*15
 -->
 (S1 ^operator O2116 = 0.8730232538360513)
Firing prefer*rvt*predict-no*H0*4*H1
 -->
Firing prefer*rvt*predict-yes*H0*3*H1
 -->
Firing elaborate*copy-see-to-output-link
 -->
 (I3 ^see 0 +)
Firing elaborate*reward*based*on*reward
 -->
 (R1062 ^value 1 +)
 (R1 ^reward R1062 +)
Firing propose*predict-yes
 -->
 (O2117 ^name predict-yes +)
 (S1 ^operator O2117 +)
Firing propose*predict-no
 -->
 (O2118 ^name predict-no +)
 (S1 ^operator O2118 +)
Firing rl*prefer*rvt*predict-no*H0*4
 -->
 (S1 ^operator O2116 = 0.1269768337092951)
Firing rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O2115 = 0.3829467075510865)
Firing prefer*rvt*predict-yes*H0
 -->
Firing prefer*rvt*predict-no*H0
 -->
Firing elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir R +)
 inner elaboration loop at bottom goal.
Retracting elaborate*copy-see-to-output-link
 -->
 (I3 ^see 1 +)
Retracting propose*predict-no
 -->
 (O2116 ^name predict-no +)
 (S1 ^operator O2116 +)
Retracting propose*predict-yes
 -->
 (O2115 ^name predict-yes +)
 (S1 ^operator O2115 +)
Retracting elaborate*reward*based*on*reward
 -->
 (R1061 ^value 1 +)
 (R1 ^reward R1061 +)
Retracting elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir U +)
Retracting rl*prefer*rvt*predict-no*H0*6
 -->
 (S1 ^operator O2116 = 0.9999999999999999)
Retracting rl*prefer*rvt*predict-yes*H0*5
 -->
 (S1 ^operator O2115 = 0.)
=>WM: (14882: S1 ^operator O2118 +)
=>WM: (14881: S1 ^operator O2117 +)
=>WM: (14880: I3 ^dir R)
=>WM: (14879: O2118 ^name predict-no)
=>WM: (14878: O2117 ^name predict-yes)
=>WM: (14877: R1062 ^value 1)
=>WM: (14876: R1 ^reward R1062)
=>WM: (14875: I3 ^see 0)
<=WM: (14866: S1 ^operator O2115 +)
<=WM: (14867: S1 ^operator O2116 +)
<=WM: (14868: S1 ^operator O2116)
<=WM: (14865: I3 ^dir U)
<=WM: (14861: R1 ^reward R1061)
<=WM: (14846: I3 ^see 1)
<=WM: (14864: O2116 ^name predict-no)
<=WM: (14863: O2115 ^name predict-yes)
<=WM: (14862: R1061 ^value 1)

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing prefer*rvt*predict-yes*H0
 -->
Firing rl*prefer*rvt*predict-yes*H0*3*H1*16
 -->
 (S1 ^operator O2117 = 0.08783148430849691)
Firing rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O2117 = 0.3829467075510865)
Firing prefer*rvt*predict-yes*H0*3*H1
 -->
Firing prefer*rvt*predict-no*H0
 -->
Firing rl*prefer*rvt*predict-no*H0*4*H1*15
 -->
 (S1 ^operator O2118 = 0.8730232538360513)
Firing rl*prefer*rvt*predict-no*H0*4
 -->
 (S1 ^operator O2118 = 0.1269768337092951)
Firing prefer*rvt*predict-no*H0*4*H1
 -->
 inner elaboration loop at bottom goal.
Retracting rl*prefer*rvt*predict-no*H0*4
 -->
 (S1 ^operator O2116 = 0.1269768337092951)
Retracting rl*prefer*rvt*predict-no*H0*4*H1*15
 -->
 (S1 ^operator O2116 = 0.8730232538360513)
Retracting rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O2115 = 0.3829467075510865)
Retracting rl*prefer*rvt*predict-yes*H0*3*H1*16
 -->
 (S1 ^operator O2115 = 0.08783148430849691)

--- END Proposal Phase ---

--- Decision Phase ---
RL update rl*prefer*rvt*predict-no*H0*6 1 0 1 -> 1 0 1(R,m,v=1,1,0)
=>WM: (14883: S1 ^operator O2118)

  1059:    O: O2118 (predict-no)
--- END Decision Phase ---

--- Application Phase ---
	--- Firing Productions (PE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing apply*operator
 -->
 (I3 ^predict-no N1059 +  :O )
Firing apply*operator*complete
 -->
 (I3 ^predict-no N1058 -  :O )
 inner elaboration loop at bottom goal.
	--- Change Working Memory (PE) ---
=>WM: (14884: I3 ^predict-no N1059)
<=WM: (14870: N1058 ^status complete)
<=WM: (14869: I3 ^predict-no N1058)
	--- Firing Productions (IE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing monitor*world
 -->

I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
	--- Change Working Memory (IE) ---

--- END Application Phase ---
--- Output Phase ---
ENV: Agent did: predict-no for direction R in state State-B
In  State-B moving R
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isU
--- END Output Phase ---
-/--- Input Phase --- 
=>WM: (14888: I2 ^dir U)
=>WM: (14887: I2 ^reward 1)
=>WM: (14886: I2 ^see 0)
=>WM: (14885: N1059 ^status complete)
<=WM: (14873: I2 ^dir R)
<=WM: (14872: I2 ^reward 1)
<=WM: (14871: I2 ^see 0)
=>WM: (14889: I2 ^level-1 R0-root)
<=WM: (14874: I2 ^level-1 R1-root)

--- END Input Phase --- 

--- Proposal Phase ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing elaborate*copy-see-to-output-link
 -->
 (I3 ^see 0 +)
Firing elaborate*reward*based*on*reward
 -->
 (R1063 ^value 1 +)
 (R1 ^reward R1063 +)
Firing propose*predict-yes
 -->
 (O2119 ^name predict-yes +)
 (S1 ^operator O2119 +)
Firing propose*predict-no
 -->
 (O2120 ^name predict-no +)
 (S1 ^operator O2120 +)
Firing rl*prefer*rvt*predict-no*H0*6
 -->
 (S1 ^operator O2118 = 0.9999999999999999)
Firing rl*prefer*rvt*predict-yes*H0*5
 -->
 (S1 ^operator O2117 = 0.)
Firing prefer*rvt*predict-yes*H0
 -->
Firing prefer*rvt*predict-no*H0
 -->
Firing elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir U +)
 inner elaboration loop at bottom goal.
Retracting elaborate*copy-see-to-output-link
 -->
 (I3 ^see 0 +)
Retracting propose*predict-no
 -->
 (O2118 ^name predict-no +)
 (S1 ^operator O2118 +)
Retracting propose*predict-yes
 -->
 (O2117 ^name predict-yes +)
 (S1 ^operator O2117 +)
Retracting elaborate*reward*based*on*reward
 -->
 (R1062 ^value 1 +)
 (R1 ^reward R1062 +)
Retracting elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir R +)
Retracting rl*prefer*rvt*predict-no*H0*4
 -->
 (S1 ^operator O2118 = 0.1269768337092951)
Retracting rl*prefer*rvt*predict-no*H0*4*H1*15
 -->
 (S1 ^operator O2118 = 0.8730232538360513)
Retracting rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O2117 = 0.3829467075510865)
Retracting rl*prefer*rvt*predict-yes*H0*3*H1*16
 -->
 (S1 ^operator O2117 = 0.08783148430849691)
=>WM: (14896: S1 ^operator O2120 +)
=>WM: (14895: S1 ^operator O2119 +)
=>WM: (14894: I3 ^dir U)
=>WM: (14893: O2120 ^name predict-no)
=>WM: (14892: O2119 ^name predict-yes)
=>WM: (14891: R1063 ^value 1)
=>WM: (14890: R1 ^reward R1063)
<=WM: (14881: S1 ^operator O2117 +)
<=WM: (14882: S1 ^operator O2118 +)
<=WM: (14883: S1 ^operator O2118)
<=WM: (14880: I3 ^dir R)
<=WM: (14876: R1 ^reward R1062)
<=WM: (14879: O2118 ^name predict-no)
<=WM: (14878: O2117 ^name predict-yes)
<=WM: (14877: R1062 ^value 1)

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing prefer*rvt*predict-yes*H0
 -->
Firing rl*prefer*rvt*predict-yes*H0*5
 -->
 (S1 ^operator O2119 = 0.)
Firing prefer*rvt*predict-no*H0
 -->
Firing rl*prefer*rvt*predict-no*H0*6
 -->
 (S1 ^operator O2120 = 0.9999999999999999)
 inner elaboration loop at bottom goal.
Retracting rl*prefer*rvt*predict-no*H0*6
 -->
 (S1 ^operator O2118 = 0.9999999999999999)
Retracting rl*prefer*rvt*predict-yes*H0*5
 -->
 (S1 ^operator O2117 = 0.)

--- END Proposal Phase ---

--- Decision Phase ---
RL update rl*prefer*rvt*predict-no*H0*4 0.814714 -0.687737 0.126977 -> 0.814714 -0.687737 0.126977(R,m,v=1,0.952632,0.0453634)
RL update rl*prefer*rvt*predict-no*H0*4*H1*15 0.185286 0.687737 0.873023 -> 0.185286 0.687737 0.873023(R,m,v=1,1,0)
=>WM: (14897: S1 ^operator O2120)

  1060:    O: O2120 (predict-no)
--- END Decision Phase ---

--- Application Phase ---
	--- Firing Productions (PE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing apply*operator
 -->
 (I3 ^predict-no N1060 +  :O )
Firing apply*operator*complete
 -->
 (I3 ^predict-no N1059 -  :O )
 inner elaboration loop at bottom goal.
	--- Change Working Memory (PE) ---
=>WM: (14898: I3 ^predict-no N1060)
<=WM: (14885: N1059 ^status complete)
<=WM: (14884: I3 ^predict-no N1059)
	--- Firing Productions (IE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing monitor*world
 -->

I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
	--- Change Working Memory (IE) ---

--- END Application Phase ---
--- Output Phase ---
ENV: Agent did: predict-no for direction U in state State-B
In  State-B moving U
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isU
--- END Output Phase ---
|\---- Input Phase --- 
=>WM: (14902: I2 ^dir U)
=>WM: (14901: I2 ^reward 1)
=>WM: (14900: I2 ^see 0)
=>WM: (14899: N1060 ^status complete)
<=WM: (14888: I2 ^dir U)
<=WM: (14887: I2 ^reward 1)
<=WM: (14886: I2 ^see 0)
=>WM: (14903: I2 ^level-1 R0-root)
<=WM: (14889: I2 ^level-1 R0-root)

--- END Input Phase --- 

--- Proposal Phase ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing elaborate*copy-see-to-output-link
 -->
 (I3 ^see 0 +)
Firing elaborate*reward*based*on*reward
 -->
 (R1064 ^value 1 +)
 (R1 ^reward R1064 +)
Firing propose*predict-yes
 -->
 (O2121 ^name predict-yes +)
 (S1 ^operator O2121 +)
Firing propose*predict-no
 -->
 (O2122 ^name predict-no +)
 (S1 ^operator O2122 +)
Firing rl*prefer*rvt*predict-no*H0*6
 -->
 (S1 ^operator O2120 = 0.9999999999999999)
Firing rl*prefer*rvt*predict-yes*H0*5
 -->
 (S1 ^operator O2119 = 0.)
Firing prefer*rvt*predict-yes*H0
 -->
Firing prefer*rvt*predict-no*H0
 -->
Firing elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir U +)
 inner elaboration loop at bottom goal.
Retracting elaborate*copy-see-to-output-link
 -->
 (I3 ^see 0 +)
Retracting propose*predict-no
 -->
 (O2120 ^name predict-no +)
 (S1 ^operator O2120 +)
Retracting propose*predict-yes
 -->
 (O2119 ^name predict-yes +)
 (S1 ^operator O2119 +)
Retracting elaborate*reward*based*on*reward
 -->
 (R1063 ^value 1 +)
 (R1 ^reward R1063 +)
Retracting elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir U +)
Retracting rl*prefer*rvt*predict-no*H0*6
 -->
 (S1 ^operator O2120 = 0.9999999999999999)
Retracting rl*prefer*rvt*predict-yes*H0*5
 -->
 (S1 ^operator O2119 = 0.)
=>WM: (14909: S1 ^operator O2122 +)
=>WM: (14908: S1 ^operator O2121 +)
=>WM: (14907: O2122 ^name predict-no)
=>WM: (14906: O2121 ^name predict-yes)
=>WM: (14905: R1064 ^value 1)
=>WM: (14904: R1 ^reward R1064)
<=WM: (14895: S1 ^operator O2119 +)
<=WM: (14896: S1 ^operator O2120 +)
<=WM: (14897: S1 ^operator O2120)
<=WM: (14890: R1 ^reward R1063)
<=WM: (14893: O2120 ^name predict-no)
<=WM: (14892: O2119 ^name predict-yes)
<=WM: (14891: R1063 ^value 1)

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing prefer*rvt*predict-yes*H0
 -->
Firing rl*prefer*rvt*predict-yes*H0*5
 -->
 (S1 ^operator O2121 = 0.)
Firing prefer*rvt*predict-no*H0
 -->
Firing rl*prefer*rvt*predict-no*H0*6
 -->
 (S1 ^operator O2122 = 0.9999999999999999)
 inner elaboration loop at bottom goal.
Retracting rl*prefer*rvt*predict-no*H0*6
 -->
 (S1 ^operator O2120 = 0.9999999999999999)
Retracting rl*prefer*rvt*predict-yes*H0*5
 -->
 (S1 ^operator O2119 = 0.)

--- END Proposal Phase ---

--- Decision Phase ---
RL update rl*prefer*rvt*predict-no*H0*6 1 0 1 -> 1 0 1(R,m,v=1,1,0)
=>WM: (14910: S1 ^operator O2122)

  1061:    O: O2122 (predict-no)
--- END Decision Phase ---

--- Application Phase ---
	--- Firing Productions (PE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing apply*operator
 -->
 (I3 ^predict-no N1061 +  :O )
Firing apply*operator*complete
 -->
 (I3 ^predict-no N1060 -  :O )
 inner elaboration loop at bottom goal.
	--- Change Working Memory (PE) ---
=>WM: (14911: I3 ^predict-no N1061)
<=WM: (14899: N1060 ^status complete)
<=WM: (14898: I3 ^predict-no N1060)
	--- Firing Productions (IE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing monitor*world
 -->

I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
	--- Change Working Memory (IE) ---

--- END Application Phase ---
--- Output Phase ---
ENV: Agent did: predict-no for direction U in state State-B
In  State-B moving U
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isR
--- END Output Phase ---
/--- Input Phase --- 
=>WM: (14915: I2 ^dir R)
=>WM: (14914: I2 ^reward 1)
=>WM: (14913: I2 ^see 0)
=>WM: (14912: N1061 ^status complete)
<=WM: (14902: I2 ^dir U)
<=WM: (14901: I2 ^reward 1)
<=WM: (14900: I2 ^see 0)
=>WM: (14916: I2 ^level-1 R0-root)
<=WM: (14903: I2 ^level-1 R0-root)

--- END Input Phase --- 

--- Proposal Phase ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing rl*prefer*rvt*predict-yes*H0*3*H1*18
 -->
 (S1 ^operator O2121 = 0.2696941111808541)
Firing rl*prefer*rvt*predict-no*H0*4*H1*17
 -->
 (S1 ^operator O2122 = 0.8730231102721162)
Firing prefer*rvt*predict-no*H0*4*H1
 -->
Firing prefer*rvt*predict-yes*H0*3*H1
 -->
Firing elaborate*copy-see-to-output-link
 -->
 (I3 ^see 0 +)
Firing elaborate*reward*based*on*reward
 -->
 (R1065 ^value 1 +)
 (R1 ^reward R1065 +)
Firing propose*predict-yes
 -->
 (O2123 ^name predict-yes +)
 (S1 ^operator O2123 +)
Firing propose*predict-no
 -->
 (O2124 ^name predict-no +)
 (S1 ^operator O2124 +)
Firing rl*prefer*rvt*predict-no*H0*4
 -->
 (S1 ^operator O2122 = 0.1269768205774933)
Firing rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O2121 = 0.3829467075510865)
Firing prefer*rvt*predict-yes*H0
 -->
Firing prefer*rvt*predict-no*H0
 -->
Firing elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir R +)
 inner elaboration loop at bottom goal.
Retracting elaborate*copy-see-to-output-link
 -->
 (I3 ^see 0 +)
Retracting propose*predict-no
 -->
 (O2122 ^name predict-no +)
 (S1 ^operator O2122 +)
Retracting propose*predict-yes
 -->
 (O2121 ^name predict-yes +)
 (S1 ^operator O2121 +)
Retracting elaborate*reward*based*on*reward
 -->
 (R1064 ^value 1 +)
 (R1 ^reward R1064 +)
Retracting elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir U +)
Retracting rl*prefer*rvt*predict-no*H0*6
 -->
 (S1 ^operator O2122 = 0.9999999999999999)
Retracting rl*prefer*rvt*predict-yes*H0*5
 -->
 (S1 ^operator O2121 = 0.)
=>WM: (14923: S1 ^operator O2124 +)
=>WM: (14922: S1 ^operator O2123 +)
=>WM: (14921: I3 ^dir R)
=>WM: (14920: O2124 ^name predict-no)
=>WM: (14919: O2123 ^name predict-yes)
=>WM: (14918: R1065 ^value 1)
=>WM: (14917: R1 ^reward R1065)
<=WM: (14908: S1 ^operator O2121 +)
<=WM: (14909: S1 ^operator O2122 +)
<=WM: (14910: S1 ^operator O2122)
<=WM: (14894: I3 ^dir U)
<=WM: (14904: R1 ^reward R1064)
<=WM: (14907: O2122 ^name predict-no)
<=WM: (14906: O2121 ^name predict-yes)
<=WM: (14905: R1064 ^value 1)

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing prefer*rvt*predict-yes*H0
 -->
Firing rl*prefer*rvt*predict-yes*H0*3*H1*18
 -->
 (S1 ^operator O2123 = 0.2696941111808541)
Firing rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O2123 = 0.3829467075510865)
Firing prefer*rvt*predict-yes*H0*3*H1
 -->
Firing prefer*rvt*predict-no*H0
 -->
Firing rl*prefer*rvt*predict-no*H0*4*H1*17
 -->
 (S1 ^operator O2124 = 0.8730231102721162)
Firing rl*prefer*rvt*predict-no*H0*4
 -->
 (S1 ^operator O2124 = 0.1269768205774933)
Firing prefer*rvt*predict-no*H0*4*H1
 -->
 inner elaboration loop at bottom goal.
Retracting rl*prefer*rvt*predict-no*H0*4
 -->
 (S1 ^operator O2122 = 0.1269768205774933)
Retracting rl*prefer*rvt*predict-no*H0*4*H1*17
 -->
 (S1 ^operator O2122 = 0.8730231102721162)
Retracting rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O2121 = 0.3829467075510865)
Retracting rl*prefer*rvt*predict-yes*H0*3*H1*18
 -->
 (S1 ^operator O2121 = 0.2696941111808541)

--- END Proposal Phase ---

--- Decision Phase ---
RL update rl*prefer*rvt*predict-no*H0*6 1 0 1 -> 1 0 1(R,m,v=1,1,0)
=>WM: (14924: S1 ^operator O2124)

  1062:    O: O2124 (predict-no)
--- END Decision Phase ---

--- Application Phase ---
	--- Firing Productions (PE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing apply*operator
 -->
 (I3 ^predict-no N1062 +  :O )
Firing apply*operator*complete
 -->
 (I3 ^predict-no N1061 -  :O )
 inner elaboration loop at bottom goal.
	--- Change Working Memory (PE) ---
=>WM: (14925: I3 ^predict-no N1062)
<=WM: (14912: N1061 ^status complete)
<=WM: (14911: I3 ^predict-no N1061)
	--- Firing Productions (IE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing monitor*world
 -->

I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
	--- Change Working Memory (IE) ---

--- END Application Phase ---
--- Output Phase ---
ENV: Agent did: predict-no for direction R in state State-B
In  State-B moving R
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isL
--- END Output Phase ---
|\-/--- Input Phase --- 
=>WM: (14929: I2 ^dir L)
=>WM: (14928: I2 ^reward 1)
=>WM: (14927: I2 ^see 0)
=>WM: (14926: N1062 ^status complete)
<=WM: (14915: I2 ^dir R)
<=WM: (14914: I2 ^reward 1)
<=WM: (14913: I2 ^see 0)
=>WM: (14930: I2 ^level-1 R0-root)
<=WM: (14916: I2 ^level-1 R0-root)

--- END Input Phase --- 

--- Proposal Phase ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing rl*prefer*rvt*predict-yes*H0*1*H1*19
 -->
 (S1 ^operator O2123 = 0.4768811873342281)
Firing rl*prefer*rvt*predict-no*H0*2*H1*7
 -->
 (S1 ^operator O2124 = 0.1700769046561409)
Firing prefer*rvt*predict-no*H0*2*H1
 -->
Firing prefer*rvt*predict-yes*H0*1*H1
 -->
Firing elaborate*copy-see-to-output-link
 -->
 (I3 ^see 0 +)
Firing elaborate*reward*based*on*reward
 -->
 (R1066 ^value 1 +)
 (R1 ^reward R1066 +)
Firing propose*predict-yes
 -->
 (O2125 ^name predict-yes +)
 (S1 ^operator O2125 +)
Firing propose*predict-no
 -->
 (O2126 ^name predict-no +)
 (S1 ^operator O2126 +)
Firing rl*prefer*rvt*predict-no*H0*2
 -->
 (S1 ^operator O2124 = 0.2550133912230119)
Firing rl*prefer*rvt*predict-yes*H0*1
 -->
 (S1 ^operator O2123 = 0.5231194590860083)
Firing prefer*rvt*predict-yes*H0
 -->
Firing prefer*rvt*predict-no*H0
 -->
Firing elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir L +)
 inner elaboration loop at bottom goal.
Retracting elaborate*copy-see-to-output-link
 -->
 (I3 ^see 0 +)
Retracting propose*predict-no
 -->
 (O2124 ^name predict-no +)
 (S1 ^operator O2124 +)
Retracting propose*predict-yes
 -->
 (O2123 ^name predict-yes +)
 (S1 ^operator O2123 +)
Retracting elaborate*reward*based*on*reward
 -->
 (R1065 ^value 1 +)
 (R1 ^reward R1065 +)
Retracting elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir R +)
Retracting rl*prefer*rvt*predict-no*H0*4
 -->
 (S1 ^operator O2124 = 0.1269768205774933)
Retracting rl*prefer*rvt*predict-no*H0*4*H1*17
 -->
 (S1 ^operator O2124 = 0.8730231102721162)
Retracting rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O2123 = 0.3829467075510865)
Retracting rl*prefer*rvt*predict-yes*H0*3*H1*18
 -->
 (S1 ^operator O2123 = 0.2696941111808541)
=>WM: (14937: S1 ^operator O2126 +)
=>WM: (14936: S1 ^operator O2125 +)
=>WM: (14935: I3 ^dir L)
=>WM: (14934: O2126 ^name predict-no)
=>WM: (14933: O2125 ^name predict-yes)
=>WM: (14932: R1066 ^value 1)
=>WM: (14931: R1 ^reward R1066)
<=WM: (14922: S1 ^operator O2123 +)
<=WM: (14923: S1 ^operator O2124 +)
<=WM: (14924: S1 ^operator O2124)
<=WM: (14921: I3 ^dir R)
<=WM: (14917: R1 ^reward R1065)
<=WM: (14920: O2124 ^name predict-no)
<=WM: (14919: O2123 ^name predict-yes)
<=WM: (14918: R1065 ^value 1)

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing prefer*rvt*predict-yes*H0
 -->
Firing rl*prefer*rvt*predict-yes*H0*1*H1*19
 -->
 (S1 ^operator O2125 = 0.4768811873342281)
Firing rl*prefer*rvt*predict-yes*H0*1
 -->
 (S1 ^operator O2125 = 0.5231194590860083)
Firing prefer*rvt*predict-yes*H0*1*H1
 -->
Firing prefer*rvt*predict-no*H0
 -->
Firing rl*prefer*rvt*predict-no*H0*2*H1*7
 -->
 (S1 ^operator O2126 = 0.1700769046561409)
Firing rl*prefer*rvt*predict-no*H0*2
 -->
 (S1 ^operator O2126 = 0.2550133912230119)
Firing prefer*rvt*predict-no*H0*2*H1
 -->
 inner elaboration loop at bottom goal.
Retracting rl*prefer*rvt*predict-no*H0*2
 -->
 (S1 ^operator O2124 = 0.2550133912230119)
Retracting rl*prefer*rvt*predict-no*H0*2*H1*7
 -->
 (S1 ^operator O2124 = 0.1700769046561409)
Retracting rl*prefer*rvt*predict-yes*H0*1
 -->
 (S1 ^operator O2123 = 0.5231194590860083)
Retracting rl*prefer*rvt*predict-yes*H0*1*H1*19
 -->
 (S1 ^operator O2123 = 0.4768811873342281)

--- END Proposal Phase ---

--- Decision Phase ---
RL update rl*prefer*rvt*predict-no*H0*4 0.814714 -0.687737 0.126977 -> 0.814714 -0.687737 0.126977(R,m,v=1,0.95288,0.0451364)
RL update rl*prefer*rvt*predict-no*H0*4*H1*17 0.185286 0.687737 0.873023 -> 0.185286 0.687737 0.873023(R,m,v=1,1,0)
=>WM: (14938: S1 ^operator O2125)

  1063:    O: O2125 (predict-yes)
--- END Decision Phase ---

--- Application Phase ---
	--- Firing Productions (PE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing apply*operator
 -->
 (I3 ^predict-yes N1063 +  :O )
Firing apply*operator*complete
 -->
 (I3 ^predict-no N1062 -  :O )
 inner elaboration loop at bottom goal.
	--- Change Working Memory (PE) ---
=>WM: (14939: I3 ^predict-yes N1063)
<=WM: (14926: N1062 ^status complete)
<=WM: (14925: I3 ^predict-no N1062)
	--- Firing Productions (IE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing monitor*world
 -->

I see 1 and I'm going to do: predict-yes inner elaboration loop at bottom goal.
	--- Change Working Memory (IE) ---

--- END Application Phase ---
--- Output Phase ---
ENV: Agent did: predict-yes for direction L in state State-B
In  State-B moving L
ENV: (next state, see, prediction correct?) = (State-A, 1, True)
predict error 0
dir: dir isR
--- END Output Phase ---
|\---- Input Phase --- 
=>WM: (14943: I2 ^dir R)
=>WM: (14942: I2 ^reward 1)
=>WM: (14941: I2 ^see 1)
=>WM: (14940: N1063 ^status complete)
<=WM: (14929: I2 ^dir L)
<=WM: (14928: I2 ^reward 1)
<=WM: (14927: I2 ^see 0)
=>WM: (14944: I2 ^level-1 L1-root)
<=WM: (14930: I2 ^level-1 R0-root)

--- END Input Phase --- 

--- Proposal Phase ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing rl*prefer*rvt*predict-yes*H0*3*H1*9
 -->
 (S1 ^operator O2125 = 0.6170506816913311)
Firing rl*prefer*rvt*predict-no*H0*4*H1*8
 -->
 (S1 ^operator O2126 = 0.4901349546100854)
Firing prefer*rvt*predict-no*H0*4*H1
 -->
Firing prefer*rvt*predict-yes*H0*3*H1
 -->
Firing elaborate*copy-see-to-output-link
 -->
 (I3 ^see 1 +)
Firing elaborate*reward*based*on*reward
 -->
 (R1067 ^value 1 +)
 (R1 ^reward R1067 +)
Firing propose*predict-yes
 -->
 (O2127 ^name predict-yes +)
 (S1 ^operator O2127 +)
Firing propose*predict-no
 -->
 (O2128 ^name predict-no +)
 (S1 ^operator O2128 +)
Firing rl*prefer*rvt*predict-no*H0*4
 -->
 (S1 ^operator O2126 = 0.1269768309500519)
Firing rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O2125 = 0.3829467075510865)
Firing prefer*rvt*predict-yes*H0
 -->
Firing prefer*rvt*predict-no*H0
 -->
Firing elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir R +)
 inner elaboration loop at bottom goal.
Retracting elaborate*copy-see-to-output-link
 -->
 (I3 ^see 0 +)
Retracting propose*predict-no
 -->
 (O2126 ^name predict-no +)
 (S1 ^operator O2126 +)
Retracting propose*predict-yes
 -->
 (O2125 ^name predict-yes +)
 (S1 ^operator O2125 +)
Retracting elaborate*reward*based*on*reward
 -->
 (R1066 ^value 1 +)
 (R1 ^reward R1066 +)
Retracting elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir L +)
Retracting rl*prefer*rvt*predict-no*H0*2
 -->
 (S1 ^operator O2126 = 0.2550133912230119)
Retracting rl*prefer*rvt*predict-no*H0*2*H1*7
 -->
 (S1 ^operator O2126 = 0.1700769046561409)
Retracting rl*prefer*rvt*predict-yes*H0*1
 -->
 (S1 ^operator O2125 = 0.5231194590860083)
Retracting rl*prefer*rvt*predict-yes*H0*1*H1*19
 -->
 (S1 ^operator O2125 = 0.4768811873342281)
=>WM: (14952: S1 ^operator O2128 +)
=>WM: (14951: S1 ^operator O2127 +)
=>WM: (14950: I3 ^dir R)
=>WM: (14949: O2128 ^name predict-no)
=>WM: (14948: O2127 ^name predict-yes)
=>WM: (14947: R1067 ^value 1)
=>WM: (14946: R1 ^reward R1067)
=>WM: (14945: I3 ^see 1)
<=WM: (14936: S1 ^operator O2125 +)
<=WM: (14938: S1 ^operator O2125)
<=WM: (14937: S1 ^operator O2126 +)
<=WM: (14935: I3 ^dir L)
<=WM: (14931: R1 ^reward R1066)
<=WM: (14875: I3 ^see 0)
<=WM: (14934: O2126 ^name predict-no)
<=WM: (14933: O2125 ^name predict-yes)
<=WM: (14932: R1066 ^value 1)

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing prefer*rvt*predict-yes*H0
 -->
Firing rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O2127 = 0.3829467075510865)
Firing prefer*rvt*predict-yes*H0*3*H1
 -->
Firing rl*prefer*rvt*predict-yes*H0*3*H1*9
 -->
 (S1 ^operator O2127 = 0.6170506816913311)
Firing prefer*rvt*predict-no*H0
 -->
Firing rl*prefer*rvt*predict-no*H0*4
 -->
 (S1 ^operator O2128 = 0.1269768309500519)
Firing prefer*rvt*predict-no*H0*4*H1
 -->
Firing rl*prefer*rvt*predict-no*H0*4*H1*8
 -->
 (S1 ^operator O2128 = 0.4901349546100854)
 inner elaboration loop at bottom goal.
Retracting rl*prefer*rvt*predict-no*H0*4
 -->
 (S1 ^operator O2126 = 0.1269768309500519)
Retracting rl*prefer*rvt*predict-no*H0*4*H1*8
 -->
 (S1 ^operator O2126 = 0.4901349546100854)
Retracting rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O2125 = 0.3829467075510865)
Retracting rl*prefer*rvt*predict-yes*H0*3*H1*9
 -->
 (S1 ^operator O2125 = 0.6170506816913311)

--- END Proposal Phase ---

--- Decision Phase ---
RL update rl*prefer*rvt*predict-yes*H0*1 0.727959 -0.20484 0.523119 -> 0.727959 -0.20484 0.523119(R,m,v=1,0.980392,0.0193498)
RL update rl*prefer*rvt*predict-yes*H0*1*H1*19 0.272042 0.20484 0.476881 -> 0.272042 0.20484 0.476881(R,m,v=1,1,0)
=>WM: (14953: S1 ^operator O2127)

  1064:    O: O2127 (predict-yes)
--- END Decision Phase ---

--- Application Phase ---
	--- Firing Productions (PE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing apply*operator
 -->
 (I3 ^predict-yes N1064 +  :O )
Firing apply*operator*complete
 -->
 (I3 ^predict-yes N1063 -  :O )
 inner elaboration loop at bottom goal.
	--- Change Working Memory (PE) ---
=>WM: (14954: I3 ^predict-yes N1064)
<=WM: (14940: N1063 ^status complete)
<=WM: (14939: I3 ^predict-yes N1063)
	--- Firing Productions (IE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing monitor*world
 -->

I see 1 and I'm going to do: predict-yes inner elaboration loop at bottom goal.
	--- Change Working Memory (IE) ---

--- END Application Phase ---
--- Output Phase ---
ENV: Agent did: predict-yes for direction R in state State-A
In  State-A moving R
ENV: (next state, see, prediction correct?) = (State-B, 1, True)
predict error 0
dir: dir isR
--- END Output Phase ---
/|\---- Input Phase --- 
=>WM: (14958: I2 ^dir R)
=>WM: (14957: I2 ^reward 1)
=>WM: (14956: I2 ^see 1)
=>WM: (14955: N1064 ^status complete)
<=WM: (14943: I2 ^dir R)
<=WM: (14942: I2 ^reward 1)
<=WM: (14941: I2 ^see 1)
=>WM: (14959: I2 ^level-1 R1-root)
<=WM: (14944: I2 ^level-1 L1-root)

--- END Input Phase --- 

--- Proposal Phase ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing rl*prefer*rvt*predict-yes*H0*3*H1*16
 -->
 (S1 ^operator O2127 = 0.08783148430849691)
Firing rl*prefer*rvt*predict-no*H0*4*H1*15
 -->
 (S1 ^operator O2128 = 0.8730232407042493)
Firing prefer*rvt*predict-no*H0*4*H1
 -->
Firing prefer*rvt*predict-yes*H0*3*H1
 -->
Firing elaborate*copy-see-to-output-link
 -->
 (I3 ^see 1 +)
Firing elaborate*reward*based*on*reward
 -->
 (R1068 ^value 1 +)
 (R1 ^reward R1068 +)
Firing propose*predict-yes
 -->
 (O2129 ^name predict-yes +)
 (S1 ^operator O2129 +)
Firing propose*predict-no
 -->
 (O2130 ^name predict-no +)
 (S1 ^operator O2130 +)
Firing rl*prefer*rvt*predict-no*H0*4
 -->
 (S1 ^operator O2128 = 0.1269768309500519)
Firing rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O2127 = 0.3829467075510865)
Firing prefer*rvt*predict-yes*H0
 -->
Firing prefer*rvt*predict-no*H0
 -->
Firing elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir R +)
 inner elaboration loop at bottom goal.
Retracting elaborate*copy-see-to-output-link
 -->
 (I3 ^see 1 +)
Retracting propose*predict-no
 -->
 (O2128 ^name predict-no +)
 (S1 ^operator O2128 +)
Retracting propose*predict-yes
 -->
 (O2127 ^name predict-yes +)
 (S1 ^operator O2127 +)
Retracting elaborate*reward*based*on*reward
 -->
 (R1067 ^value 1 +)
 (R1 ^reward R1067 +)
Retracting elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir R +)
Retracting rl*prefer*rvt*predict-no*H0*4*H1*8
 -->
 (S1 ^operator O2128 = 0.4901349546100854)
Retracting rl*prefer*rvt*predict-no*H0*4
 -->
 (S1 ^operator O2128 = 0.1269768309500519)
Retracting rl*prefer*rvt*predict-yes*H0*3*H1*9
 -->
 (S1 ^operator O2127 = 0.6170506816913311)
Retracting rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O2127 = 0.3829467075510865)
=>WM: (14965: S1 ^operator O2130 +)
=>WM: (14964: S1 ^operator O2129 +)
=>WM: (14963: O2130 ^name predict-no)
=>WM: (14962: O2129 ^name predict-yes)
=>WM: (14961: R1068 ^value 1)
=>WM: (14960: R1 ^reward R1068)
<=WM: (14951: S1 ^operator O2127 +)
<=WM: (14953: S1 ^operator O2127)
<=WM: (14952: S1 ^operator O2128 +)
<=WM: (14946: R1 ^reward R1067)
<=WM: (14949: O2128 ^name predict-no)
<=WM: (14948: O2127 ^name predict-yes)
<=WM: (14947: R1067 ^value 1)

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing prefer*rvt*predict-yes*H0
 -->
Firing rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O2129 = 0.3829467075510865)
Firing prefer*rvt*predict-yes*H0*3*H1
 -->
Firing rl*prefer*rvt*predict-yes*H0*3*H1*16
 -->
 (S1 ^operator O2129 = 0.08783148430849691)
Firing prefer*rvt*predict-no*H0
 -->
Firing rl*prefer*rvt*predict-no*H0*4
 -->
 (S1 ^operator O2130 = 0.1269768309500519)
Firing prefer*rvt*predict-no*H0*4*H1
 -->
Firing rl*prefer*rvt*predict-no*H0*4*H1*15
 -->
 (S1 ^operator O2130 = 0.8730232407042493)
 inner elaboration loop at bottom goal.
Retracting rl*prefer*rvt*predict-no*H0*4
 -->
 (S1 ^operator O2128 = 0.1269768309500519)
Retracting rl*prefer*rvt*predict-no*H0*4*H1*15
 -->
 (S1 ^operator O2128 = 0.8730232407042493)
Retracting rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O2127 = 0.3829467075510865)
Retracting rl*prefer*rvt*predict-yes*H0*3*H1*16
 -->
 (S1 ^operator O2127 = 0.08783148430849691)

--- END Proposal Phase ---

--- Decision Phase ---
RL update rl*prefer*rvt*predict-yes*H0*3 0.673139 -0.290193 0.382947 -> 0.67314 -0.290193 0.382947(R,m,v=1,0.963415,0.0354631)
RL update rl*prefer*rvt*predict-yes*H0*3*H1*9 0.326858 0.290192 0.617051 -> 0.326859 0.290192 0.617051(R,m,v=1,1,0)
=>WM: (14966: S1 ^operator O2130)

  1065:    O: O2130 (predict-no)
--- END Decision Phase ---

--- Application Phase ---
	--- Firing Productions (PE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing apply*operator
 -->
 (I3 ^predict-no N1065 +  :O )
Firing apply*operator*complete
 -->
 (I3 ^predict-yes N1064 -  :O )
 inner elaboration loop at bottom goal.
	--- Change Working Memory (PE) ---
=>WM: (14967: I3 ^predict-no N1065)
<=WM: (14955: N1064 ^status complete)
<=WM: (14954: I3 ^predict-yes N1064)
	--- Firing Productions (IE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing monitor*world
 -->

I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
	--- Change Working Memory (IE) ---

--- END Application Phase ---
--- Output Phase ---
ENV: Agent did: predict-no for direction R in state State-B
In  State-B moving R
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isR
--- END Output Phase ---
/|\---- Input Phase --- 
=>WM: (14971: I2 ^dir R)
=>WM: (14970: I2 ^reward 1)
=>WM: (14969: I2 ^see 0)
=>WM: (14968: N1065 ^status complete)
<=WM: (14958: I2 ^dir R)
<=WM: (14957: I2 ^reward 1)
<=WM: (14956: I2 ^see 1)
=>WM: (14972: I2 ^level-1 R0-root)
<=WM: (14959: I2 ^level-1 R1-root)

--- END Input Phase --- 

--- Proposal Phase ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing rl*prefer*rvt*predict-yes*H0*3*H1*18
 -->
 (S1 ^operator O2129 = 0.2696941111808541)
Firing rl*prefer*rvt*predict-no*H0*4*H1*17
 -->
 (S1 ^operator O2130 = 0.8730231206446747)
Firing prefer*rvt*predict-no*H0*4*H1
 -->
Firing prefer*rvt*predict-yes*H0*3*H1
 -->
Firing elaborate*copy-see-to-output-link
 -->
 (I3 ^see 0 +)
Firing elaborate*reward*based*on*reward
 -->
 (R1069 ^value 1 +)
 (R1 ^reward R1069 +)
Firing propose*predict-yes
 -->
 (O2131 ^name predict-yes +)
 (S1 ^operator O2131 +)
Firing propose*predict-no
 -->
 (O2132 ^name predict-no +)
 (S1 ^operator O2132 +)
Firing rl*prefer*rvt*predict-no*H0*4
 -->
 (S1 ^operator O2130 = 0.1269768309500519)
Firing rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O2129 = 0.3829470991647237)
Firing prefer*rvt*predict-yes*H0
 -->
Firing prefer*rvt*predict-no*H0
 -->
Firing elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir R +)
 inner elaboration loop at bottom goal.
Retracting elaborate*copy-see-to-output-link
 -->
 (I3 ^see 1 +)
Retracting propose*predict-no
 -->
 (O2130 ^name predict-no +)
 (S1 ^operator O2130 +)
Retracting propose*predict-yes
 -->
 (O2129 ^name predict-yes +)
 (S1 ^operator O2129 +)
Retracting elaborate*reward*based*on*reward
 -->
 (R1068 ^value 1 +)
 (R1 ^reward R1068 +)
Retracting elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir R +)
Retracting rl*prefer*rvt*predict-no*H0*4*H1*15
 -->
 (S1 ^operator O2130 = 0.8730232407042493)
Retracting rl*prefer*rvt*predict-no*H0*4
 -->
 (S1 ^operator O2130 = 0.1269768309500519)
Retracting rl*prefer*rvt*predict-yes*H0*3*H1*16
 -->
 (S1 ^operator O2129 = 0.08783148430849691)
Retracting rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O2129 = 0.3829470991647237)
=>WM: (14979: S1 ^operator O2132 +)
=>WM: (14978: S1 ^operator O2131 +)
=>WM: (14977: O2132 ^name predict-no)
=>WM: (14976: O2131 ^name predict-yes)
=>WM: (14975: R1069 ^value 1)
=>WM: (14974: R1 ^reward R1069)
=>WM: (14973: I3 ^see 0)
<=WM: (14964: S1 ^operator O2129 +)
<=WM: (14965: S1 ^operator O2130 +)
<=WM: (14966: S1 ^operator O2130)
<=WM: (14960: R1 ^reward R1068)
<=WM: (14945: I3 ^see 1)
<=WM: (14963: O2130 ^name predict-no)
<=WM: (14962: O2129 ^name predict-yes)
<=WM: (14961: R1068 ^value 1)

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing prefer*rvt*predict-yes*H0
 -->
Firing rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O2131 = 0.3829470991647237)
Firing prefer*rvt*predict-yes*H0*3*H1
 -->
Firing rl*prefer*rvt*predict-yes*H0*3*H1*18
 -->
 (S1 ^operator O2131 = 0.2696941111808541)
Firing prefer*rvt*predict-no*H0
 -->
Firing rl*prefer*rvt*predict-no*H0*4
 -->
 (S1 ^operator O2132 = 0.1269768309500519)
Firing prefer*rvt*predict-no*H0*4*H1
 -->
Firing rl*prefer*rvt*predict-no*H0*4*H1*17
 -->
 (S1 ^operator O2132 = 0.8730231206446747)
 inner elaboration loop at bottom goal.
Retracting rl*prefer*rvt*predict-no*H0*4
 -->
 (S1 ^operator O2130 = 0.1269768309500519)
Retracting rl*prefer*rvt*predict-no*H0*4*H1*17
 -->
 (S1 ^operator O2130 = 0.8730231206446747)
Retracting rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O2129 = 0.3829470991647237)
Retracting rl*prefer*rvt*predict-yes*H0*3*H1*18
 -->
 (S1 ^operator O2129 = 0.2696941111808541)

--- END Proposal Phase ---

--- Decision Phase ---
RL update rl*prefer*rvt*predict-no*H0*4 0.814714 -0.687737 0.126977 -> 0.814714 -0.687737 0.126977(R,m,v=1,0.953125,0.0449116)
RL update rl*prefer*rvt*predict-no*H0*4*H1*15 0.185286 0.687737 0.873023 -> 0.185286 0.687737 0.873023(R,m,v=1,1,0)
=>WM: (14980: S1 ^operator O2132)

  1066:    O: O2132 (predict-no)
--- END Decision Phase ---

--- Application Phase ---
	--- Firing Productions (PE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing apply*operator
 -->
 (I3 ^predict-no N1066 +  :O )
Firing apply*operator*complete
 -->
 (I3 ^predict-no N1065 -  :O )
 inner elaboration loop at bottom goal.
	--- Change Working Memory (PE) ---
=>WM: (14981: I3 ^predict-no N1066)
<=WM: (14968: N1065 ^status complete)
<=WM: (14967: I3 ^predict-no N1065)
	--- Firing Productions (IE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing monitor*world
 -->

I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
	--- Change Working Memory (IE) ---

--- END Application Phase ---
--- Output Phase ---
ENV: Agent did: predict-no for direction R in state State-B
In  State-B moving R
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isR
--- END Output Phase ---
/|\--- Input Phase --- 
=>WM: (14985: I2 ^dir R)
=>WM: (14984: I2 ^reward 1)
=>WM: (14983: I2 ^see 0)
=>WM: (14982: N1066 ^status complete)
<=WM: (14971: I2 ^dir R)
<=WM: (14970: I2 ^reward 1)
<=WM: (14969: I2 ^see 0)
=>WM: (14986: I2 ^level-1 R0-root)
<=WM: (14972: I2 ^level-1 R0-root)

--- END Input Phase --- 

--- Proposal Phase ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing rl*prefer*rvt*predict-yes*H0*3*H1*18
 -->
 (S1 ^operator O2131 = 0.2696941111808541)
Firing rl*prefer*rvt*predict-no*H0*4*H1*17
 -->
 (S1 ^operator O2132 = 0.8730231206446747)
Firing prefer*rvt*predict-no*H0*4*H1
 -->
Firing prefer*rvt*predict-yes*H0*3*H1
 -->
Firing elaborate*copy-see-to-output-link
 -->
 (I3 ^see 0 +)
Firing elaborate*reward*based*on*reward
 -->
 (R1070 ^value 1 +)
 (R1 ^reward R1070 +)
Firing propose*predict-yes
 -->
 (O2133 ^name predict-yes +)
 (S1 ^operator O2133 +)
Firing propose*predict-no
 -->
 (O2134 ^name predict-no +)
 (S1 ^operator O2134 +)
Firing rl*prefer*rvt*predict-no*H0*4
 -->
 (S1 ^operator O2132 = 0.1269768202019067)
Firing rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O2131 = 0.3829470991647237)
Firing prefer*rvt*predict-yes*H0
 -->
Firing prefer*rvt*predict-no*H0
 -->
Firing elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir R +)
 inner elaboration loop at bottom goal.
Retracting elaborate*copy-see-to-output-link
 -->
 (I3 ^see 0 +)
Retracting propose*predict-no
 -->
 (O2132 ^name predict-no +)
 (S1 ^operator O2132 +)
Retracting propose*predict-yes
 -->
 (O2131 ^name predict-yes +)
 (S1 ^operator O2131 +)
Retracting elaborate*reward*based*on*reward
 -->
 (R1069 ^value 1 +)
 (R1 ^reward R1069 +)
Retracting elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir R +)
Retracting rl*prefer*rvt*predict-no*H0*4*H1*17
 -->
 (S1 ^operator O2132 = 0.8730231206446747)
Retracting rl*prefer*rvt*predict-no*H0*4
 -->
 (S1 ^operator O2132 = 0.1269768202019067)
Retracting rl*prefer*rvt*predict-yes*H0*3*H1*18
 -->
 (S1 ^operator O2131 = 0.2696941111808541)
Retracting rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O2131 = 0.3829470991647237)
=>WM: (14992: S1 ^operator O2134 +)
=>WM: (14991: S1 ^operator O2133 +)
=>WM: (14990: O2134 ^name predict-no)
=>WM: (14989: O2133 ^name predict-yes)
=>WM: (14988: R1070 ^value 1)
=>WM: (14987: R1 ^reward R1070)
<=WM: (14978: S1 ^operator O2131 +)
<=WM: (14979: S1 ^operator O2132 +)
<=WM: (14980: S1 ^operator O2132)
<=WM: (14974: R1 ^reward R1069)
<=WM: (14977: O2132 ^name predict-no)
<=WM: (14976: O2131 ^name predict-yes)
<=WM: (14975: R1069 ^value 1)

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing prefer*rvt*predict-yes*H0
 -->
Firing rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O2133 = 0.3829470991647237)
Firing prefer*rvt*predict-yes*H0*3*H1
 -->
Firing rl*prefer*rvt*predict-yes*H0*3*H1*18
 -->
 (S1 ^operator O2133 = 0.2696941111808541)
Firing prefer*rvt*predict-no*H0
 -->
Firing rl*prefer*rvt*predict-no*H0*4
 -->
 (S1 ^operator O2134 = 0.1269768202019067)
Firing prefer*rvt*predict-no*H0*4*H1
 -->
Firing rl*prefer*rvt*predict-no*H0*4*H1*17
 -->
 (S1 ^operator O2134 = 0.8730231206446747)
 inner elaboration loop at bottom goal.
Retracting rl*prefer*rvt*predict-no*H0*4
 -->
 (S1 ^operator O2132 = 0.1269768202019067)
Retracting rl*prefer*rvt*predict-no*H0*4*H1*17
 -->
 (S1 ^operator O2132 = 0.8730231206446747)
Retracting rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O2131 = 0.3829470991647237)
Retracting rl*prefer*rvt*predict-yes*H0*3*H1*18
 -->
 (S1 ^operator O2131 = 0.2696941111808541)

--- END Proposal Phase ---

--- Decision Phase ---
RL update rl*prefer*rvt*predict-no*H0*4 0.814714 -0.687737 0.126977 -> 0.814714 -0.687737 0.126977(R,m,v=1,0.953368,0.0446891)
RL update rl*prefer*rvt*predict-no*H0*4*H1*17 0.185286 0.687737 0.873023 -> 0.185286 0.687737 0.873023(R,m,v=1,1,0)
=>WM: (14993: S1 ^operator O2134)

  1067:    O: O2134 (predict-no)
--- END Decision Phase ---

--- Application Phase ---
	--- Firing Productions (PE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing apply*operator
 -->
 (I3 ^predict-no N1067 +  :O )
Firing apply*operator*complete
 -->
 (I3 ^predict-no N1066 -  :O )
 inner elaboration loop at bottom goal.
	--- Change Working Memory (PE) ---
=>WM: (14994: I3 ^predict-no N1067)
<=WM: (14982: N1066 ^status complete)
<=WM: (14981: I3 ^predict-no N1066)
	--- Firing Productions (IE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing monitor*world
 -->

I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
	--- Change Working Memory (IE) ---

--- END Application Phase ---
--- Output Phase ---
ENV: Agent did: predict-no for direction R in state State-B
In  State-B moving R
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isU
--- END Output Phase ---
-/|--- Input Phase --- 
=>WM: (14998: I2 ^dir U)
=>WM: (14997: I2 ^reward 1)
=>WM: (14996: I2 ^see 0)
=>WM: (14995: N1067 ^status complete)
<=WM: (14985: I2 ^dir R)
<=WM: (14984: I2 ^reward 1)
<=WM: (14983: I2 ^see 0)
=>WM: (14999: I2 ^level-1 R0-root)
<=WM: (14986: I2 ^level-1 R0-root)

--- END Input Phase --- 

--- Proposal Phase ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing elaborate*copy-see-to-output-link
 -->
 (I3 ^see 0 +)
Firing elaborate*reward*based*on*reward
 -->
 (R1071 ^value 1 +)
 (R1 ^reward R1071 +)
Firing propose*predict-yes
 -->
 (O2135 ^name predict-yes +)
 (S1 ^operator O2135 +)
Firing propose*predict-no
 -->
 (O2136 ^name predict-no +)
 (S1 ^operator O2136 +)
Firing rl*prefer*rvt*predict-no*H0*6
 -->
 (S1 ^operator O2134 = 0.9999999999999999)
Firing rl*prefer*rvt*predict-yes*H0*5
 -->
 (S1 ^operator O2133 = 0.)
Firing prefer*rvt*predict-yes*H0
 -->
Firing prefer*rvt*predict-no*H0
 -->
Firing elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir U +)
 inner elaboration loop at bottom goal.
Retracting elaborate*copy-see-to-output-link
 -->
 (I3 ^see 0 +)
Retracting propose*predict-no
 -->
 (O2134 ^name predict-no +)
 (S1 ^operator O2134 +)
Retracting propose*predict-yes
 -->
 (O2133 ^name predict-yes +)
 (S1 ^operator O2133 +)
Retracting elaborate*reward*based*on*reward
 -->
 (R1070 ^value 1 +)
 (R1 ^reward R1070 +)
Retracting elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir R +)
Retracting rl*prefer*rvt*predict-no*H0*4*H1*17
 -->
 (S1 ^operator O2134 = 0.8730231295176875)
Retracting rl*prefer*rvt*predict-no*H0*4
 -->
 (S1 ^operator O2134 = 0.1269768290749195)
Retracting rl*prefer*rvt*predict-yes*H0*3*H1*18
 -->
 (S1 ^operator O2133 = 0.2696941111808541)
Retracting rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O2133 = 0.3829470991647237)
=>WM: (15006: S1 ^operator O2136 +)
=>WM: (15005: S1 ^operator O2135 +)
=>WM: (15004: I3 ^dir U)
=>WM: (15003: O2136 ^name predict-no)
=>WM: (15002: O2135 ^name predict-yes)
=>WM: (15001: R1071 ^value 1)
=>WM: (15000: R1 ^reward R1071)
<=WM: (14991: S1 ^operator O2133 +)
<=WM: (14992: S1 ^operator O2134 +)
<=WM: (14993: S1 ^operator O2134)
<=WM: (14950: I3 ^dir R)
<=WM: (14987: R1 ^reward R1070)
<=WM: (14990: O2134 ^name predict-no)
<=WM: (14989: O2133 ^name predict-yes)
<=WM: (14988: R1070 ^value 1)

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing prefer*rvt*predict-yes*H0
 -->
Firing rl*prefer*rvt*predict-yes*H0*5
 -->
 (S1 ^operator O2135 = 0.)
Firing prefer*rvt*predict-no*H0
 -->
Firing rl*prefer*rvt*predict-no*H0*6
 -->
 (S1 ^operator O2136 = 0.9999999999999999)
 inner elaboration loop at bottom goal.
Retracting rl*prefer*rvt*predict-no*H0*6
 -->
 (S1 ^operator O2134 = 0.9999999999999999)
Retracting rl*prefer*rvt*predict-yes*H0*5
 -->
 (S1 ^operator O2133 = 0.)

--- END Proposal Phase ---

--- Decision Phase ---
RL update rl*prefer*rvt*predict-no*H0*4 0.814714 -0.687737 0.126977 -> 0.814714 -0.687737 0.126977(R,m,v=1,0.953608,0.0444688)
RL update rl*prefer*rvt*predict-no*H0*4*H1*17 0.185286 0.687737 0.873023 -> 0.185286 0.687737 0.873023(R,m,v=1,1,0)
=>WM: (15007: S1 ^operator O2136)

  1068:    O: O2136 (predict-no)
--- END Decision Phase ---

--- Application Phase ---
	--- Firing Productions (PE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing apply*operator
 -->
 (I3 ^predict-no N1068 +  :O )
Firing apply*operator*complete
 -->
 (I3 ^predict-no N1067 -  :O )
 inner elaboration loop at bottom goal.
	--- Change Working Memory (PE) ---
=>WM: (15008: I3 ^predict-no N1068)
<=WM: (14995: N1067 ^status complete)
<=WM: (14994: I3 ^predict-no N1067)
	--- Firing Productions (IE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing monitor*world
 -->

I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
	--- Change Working Memory (IE) ---

--- END Application Phase ---
--- Output Phase ---
ENV: Agent did: predict-no for direction U in state State-B
In  State-B moving U
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isR
--- END Output Phase ---
\-/--- Input Phase --- 
=>WM: (15012: I2 ^dir R)
=>WM: (15011: I2 ^reward 1)
=>WM: (15010: I2 ^see 0)
=>WM: (15009: N1068 ^status complete)
<=WM: (14998: I2 ^dir U)
<=WM: (14997: I2 ^reward 1)
<=WM: (14996: I2 ^see 0)
=>WM: (15013: I2 ^level-1 R0-root)
<=WM: (14999: I2 ^level-1 R0-root)

--- END Input Phase --- 

--- Proposal Phase ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing rl*prefer*rvt*predict-yes*H0*3*H1*18
 -->
 (S1 ^operator O2135 = 0.2696941111808541)
Firing rl*prefer*rvt*predict-no*H0*4*H1*17
 -->
 (S1 ^operator O2136 = 0.8730231357287965)
Firing prefer*rvt*predict-no*H0*4*H1
 -->
Firing prefer*rvt*predict-yes*H0*3*H1
 -->
Firing elaborate*copy-see-to-output-link
 -->
 (I3 ^see 0 +)
Firing elaborate*reward*based*on*reward
 -->
 (R1072 ^value 1 +)
 (R1 ^reward R1072 +)
Firing propose*predict-yes
 -->
 (O2137 ^name predict-yes +)
 (S1 ^operator O2137 +)
Firing propose*predict-no
 -->
 (O2138 ^name predict-no +)
 (S1 ^operator O2138 +)
Firing rl*prefer*rvt*predict-no*H0*4
 -->
 (S1 ^operator O2136 = 0.1269768352860284)
Firing rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O2135 = 0.3829470991647237)
Firing prefer*rvt*predict-yes*H0
 -->
Firing prefer*rvt*predict-no*H0
 -->
Firing elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir R +)
 inner elaboration loop at bottom goal.
Retracting elaborate*copy-see-to-output-link
 -->
 (I3 ^see 0 +)
Retracting propose*predict-no
 -->
 (O2136 ^name predict-no +)
 (S1 ^operator O2136 +)
Retracting propose*predict-yes
 -->
 (O2135 ^name predict-yes +)
 (S1 ^operator O2135 +)
Retracting elaborate*reward*based*on*reward
 -->
 (R1071 ^value 1 +)
 (R1 ^reward R1071 +)
Retracting elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir U +)
Retracting rl*prefer*rvt*predict-no*H0*6
 -->
 (S1 ^operator O2136 = 0.9999999999999999)
Retracting rl*prefer*rvt*predict-yes*H0*5
 -->
 (S1 ^operator O2135 = 0.)
=>WM: (15020: S1 ^operator O2138 +)
=>WM: (15019: S1 ^operator O2137 +)
=>WM: (15018: I3 ^dir R)
=>WM: (15017: O2138 ^name predict-no)
=>WM: (15016: O2137 ^name predict-yes)
=>WM: (15015: R1072 ^value 1)
=>WM: (15014: R1 ^reward R1072)
<=WM: (15005: S1 ^operator O2135 +)
<=WM: (15006: S1 ^operator O2136 +)
<=WM: (15007: S1 ^operator O2136)
<=WM: (15004: I3 ^dir U)
<=WM: (15000: R1 ^reward R1071)
<=WM: (15003: O2136 ^name predict-no)
<=WM: (15002: O2135 ^name predict-yes)
<=WM: (15001: R1071 ^value 1)

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing prefer*rvt*predict-yes*H0
 -->
Firing rl*prefer*rvt*predict-yes*H0*3*H1*18
 -->
 (S1 ^operator O2137 = 0.2696941111808541)
Firing rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O2137 = 0.3829470991647237)
Firing prefer*rvt*predict-yes*H0*3*H1
 -->
Firing prefer*rvt*predict-no*H0
 -->
Firing rl*prefer*rvt*predict-no*H0*4*H1*17
 -->
 (S1 ^operator O2138 = 0.8730231357287965)
Firing rl*prefer*rvt*predict-no*H0*4
 -->
 (S1 ^operator O2138 = 0.1269768352860284)
Firing prefer*rvt*predict-no*H0*4*H1
 -->
 inner elaboration loop at bottom goal.
Retracting rl*prefer*rvt*predict-no*H0*4
 -->
 (S1 ^operator O2136 = 0.1269768352860284)
Retracting rl*prefer*rvt*predict-no*H0*4*H1*17
 -->
 (S1 ^operator O2136 = 0.8730231357287965)
Retracting rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O2135 = 0.3829470991647237)
Retracting rl*prefer*rvt*predict-yes*H0*3*H1*18
 -->
 (S1 ^operator O2135 = 0.2696941111808541)

--- END Proposal Phase ---

--- Decision Phase ---
RL update rl*prefer*rvt*predict-no*H0*6 1 0 1 -> 1 0 1(R,m,v=1,1,0)
=>WM: (15021: S1 ^operator O2138)

  1069:    O: O2138 (predict-no)
--- END Decision Phase ---

--- Application Phase ---
	--- Firing Productions (PE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing apply*operator
 -->
 (I3 ^predict-no N1069 +  :O )
Firing apply*operator*complete
 -->
 (I3 ^predict-no N1068 -  :O )
 inner elaboration loop at bottom goal.
	--- Change Working Memory (PE) ---
=>WM: (15022: I3 ^predict-no N1069)
<=WM: (15009: N1068 ^status complete)
<=WM: (15008: I3 ^predict-no N1068)
	--- Firing Productions (IE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing monitor*world
 -->

I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
	--- Change Working Memory (IE) ---

--- END Application Phase ---
--- Output Phase ---
ENV: Agent did: predict-no for direction R in state State-B
In  State-B moving R
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isL
--- END Output Phase ---
|\---- Input Phase --- 
=>WM: (15026: I2 ^dir L)
=>WM: (15025: I2 ^reward 1)
=>WM: (15024: I2 ^see 0)
=>WM: (15023: N1069 ^status complete)
<=WM: (15012: I2 ^dir R)
<=WM: (15011: I2 ^reward 1)
<=WM: (15010: I2 ^see 0)
=>WM: (15027: I2 ^level-1 R0-root)
<=WM: (15013: I2 ^level-1 R0-root)

--- END Input Phase --- 

--- Proposal Phase ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing rl*prefer*rvt*predict-yes*H0*1*H1*19
 -->
 (S1 ^operator O2137 = 0.4768810903711926)
Firing rl*prefer*rvt*predict-no*H0*2*H1*7
 -->
 (S1 ^operator O2138 = 0.1700769046561409)
Firing prefer*rvt*predict-no*H0*2*H1
 -->
Firing prefer*rvt*predict-yes*H0*1*H1
 -->
Firing elaborate*copy-see-to-output-link
 -->
 (I3 ^see 0 +)
Firing elaborate*reward*based*on*reward
 -->
 (R1073 ^value 1 +)
 (R1 ^reward R1073 +)
Firing propose*predict-yes
 -->
 (O2139 ^name predict-yes +)
 (S1 ^operator O2139 +)
Firing propose*predict-no
 -->
 (O2140 ^name predict-no +)
 (S1 ^operator O2140 +)
Firing rl*prefer*rvt*predict-no*H0*2
 -->
 (S1 ^operator O2138 = 0.2550133912230119)
Firing rl*prefer*rvt*predict-yes*H0*1
 -->
 (S1 ^operator O2137 = 0.5231193621229728)
Firing prefer*rvt*predict-yes*H0
 -->
Firing prefer*rvt*predict-no*H0
 -->
Firing elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir L +)
 inner elaboration loop at bottom goal.
Retracting elaborate*copy-see-to-output-link
 -->
 (I3 ^see 0 +)
Retracting propose*predict-no
 -->
 (O2138 ^name predict-no +)
 (S1 ^operator O2138 +)
Retracting propose*predict-yes
 -->
 (O2137 ^name predict-yes +)
 (S1 ^operator O2137 +)
Retracting elaborate*reward*based*on*reward
 -->
 (R1072 ^value 1 +)
 (R1 ^reward R1072 +)
Retracting elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir R +)
Retracting rl*prefer*rvt*predict-no*H0*4
 -->
 (S1 ^operator O2138 = 0.1269768352860284)
Retracting rl*prefer*rvt*predict-no*H0*4*H1*17
 -->
 (S1 ^operator O2138 = 0.8730231357287965)
Retracting rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O2137 = 0.3829470991647237)
Retracting rl*prefer*rvt*predict-yes*H0*3*H1*18
 -->
 (S1 ^operator O2137 = 0.2696941111808541)
=>WM: (15034: S1 ^operator O2140 +)
=>WM: (15033: S1 ^operator O2139 +)
=>WM: (15032: I3 ^dir L)
=>WM: (15031: O2140 ^name predict-no)
=>WM: (15030: O2139 ^name predict-yes)
=>WM: (15029: R1073 ^value 1)
=>WM: (15028: R1 ^reward R1073)
<=WM: (15019: S1 ^operator O2137 +)
<=WM: (15020: S1 ^operator O2138 +)
<=WM: (15021: S1 ^operator O2138)
<=WM: (15018: I3 ^dir R)
<=WM: (15014: R1 ^reward R1072)
<=WM: (15017: O2138 ^name predict-no)
<=WM: (15016: O2137 ^name predict-yes)
<=WM: (15015: R1072 ^value 1)

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing prefer*rvt*predict-yes*H0
 -->
Firing rl*prefer*rvt*predict-yes*H0*1*H1*19
 -->
 (S1 ^operator O2139 = 0.4768810903711926)
Firing rl*prefer*rvt*predict-yes*H0*1
 -->
 (S1 ^operator O2139 = 0.5231193621229728)
Firing prefer*rvt*predict-yes*H0*1*H1
 -->
Firing prefer*rvt*predict-no*H0
 -->
Firing rl*prefer*rvt*predict-no*H0*2*H1*7
 -->
 (S1 ^operator O2140 = 0.1700769046561409)
Firing rl*prefer*rvt*predict-no*H0*2
 -->
 (S1 ^operator O2140 = 0.2550133912230119)
Firing prefer*rvt*predict-no*H0*2*H1
 -->
 inner elaboration loop at bottom goal.
Retracting rl*prefer*rvt*predict-no*H0*2
 -->
 (S1 ^operator O2138 = 0.2550133912230119)
Retracting rl*prefer*rvt*predict-no*H0*2*H1*7
 -->
 (S1 ^operator O2138 = 0.1700769046561409)
Retracting rl*prefer*rvt*predict-yes*H0*1
 -->
 (S1 ^operator O2137 = 0.5231193621229728)
Retracting rl*prefer*rvt*predict-yes*H0*1*H1*19
 -->
 (S1 ^operator O2137 = 0.4768810903711926)

--- END Proposal Phase ---

--- Decision Phase ---
RL update rl*prefer*rvt*predict-no*H0*4 0.814714 -0.687737 0.126977 -> 0.814714 -0.687737 0.126977(R,m,v=1,0.953846,0.0442506)
RL update rl*prefer*rvt*predict-no*H0*4*H1*17 0.185286 0.687737 0.873023 -> 0.185286 0.687737 0.873023(R,m,v=1,1,0)
=>WM: (15035: S1 ^operator O2139)

  1070:    O: O2139 (predict-yes)
--- END Decision Phase ---

--- Application Phase ---
	--- Firing Productions (PE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing apply*operator
 -->
 (I3 ^predict-yes N1070 +  :O )
Firing apply*operator*complete
 -->
 (I3 ^predict-no N1069 -  :O )
 inner elaboration loop at bottom goal.
	--- Change Working Memory (PE) ---
=>WM: (15036: I3 ^predict-yes N1070)
<=WM: (15023: N1069 ^status complete)
<=WM: (15022: I3 ^predict-no N1069)
	--- Firing Productions (IE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing monitor*world
 -->

I see 1 and I'm going to do: predict-yes inner elaboration loop at bottom goal.
	--- Change Working Memory (IE) ---

--- END Application Phase ---
--- Output Phase ---
ENV: Agent did: predict-yes for direction L in state State-B
In  State-B moving L
ENV: (next state, see, prediction correct?) = (State-A, 1, True)
predict error 0
dir: dir isL
--- END Output Phase ---
/|--- Input Phase --- 
=>WM: (15040: I2 ^dir L)
=>WM: (15039: I2 ^reward 1)
=>WM: (15038: I2 ^see 1)
=>WM: (15037: N1070 ^status complete)
<=WM: (15026: I2 ^dir L)
<=WM: (15025: I2 ^reward 1)
<=WM: (15024: I2 ^see 0)
=>WM: (15041: I2 ^level-1 L1-root)
<=WM: (15027: I2 ^level-1 R0-root)

--- END Input Phase --- 

--- Proposal Phase ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing rl*prefer*rvt*predict-yes*H0*1*H1*20
 -->
 (S1 ^operator O2139 = 0.1693592933936033)
Firing rl*prefer*rvt*predict-no*H0*2*H1*11
 -->
 (S1 ^operator O2140 = 0.744986509061307)
Firing prefer*rvt*predict-no*H0*2*H1
 -->
Firing prefer*rvt*predict-yes*H0*1*H1
 -->
Firing elaborate*copy-see-to-output-link
 -->
 (I3 ^see 1 +)
Firing elaborate*reward*based*on*reward
 -->
 (R1074 ^value 1 +)
 (R1 ^reward R1074 +)
Firing propose*predict-yes
 -->
 (O2141 ^name predict-yes +)
 (S1 ^operator O2141 +)
Firing propose*predict-no
 -->
 (O2142 ^name predict-no +)
 (S1 ^operator O2142 +)
Firing rl*prefer*rvt*predict-no*H0*2
 -->
 (S1 ^operator O2140 = 0.2550133912230119)
Firing rl*prefer*rvt*predict-yes*H0*1
 -->
 (S1 ^operator O2139 = 0.5231193621229728)
Firing prefer*rvt*predict-yes*H0
 -->
Firing prefer*rvt*predict-no*H0
 -->
Firing elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir L +)
 inner elaboration loop at bottom goal.
Retracting elaborate*copy-see-to-output-link
 -->
 (I3 ^see 0 +)
Retracting propose*predict-no
 -->
 (O2140 ^name predict-no +)
 (S1 ^operator O2140 +)
Retracting propose*predict-yes
 -->
 (O2139 ^name predict-yes +)
 (S1 ^operator O2139 +)
Retracting elaborate*reward*based*on*reward
 -->
 (R1073 ^value 1 +)
 (R1 ^reward R1073 +)
Retracting elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir L +)
Retracting rl*prefer*rvt*predict-no*H0*2
 -->
 (S1 ^operator O2140 = 0.2550133912230119)
Retracting rl*prefer*rvt*predict-no*H0*2*H1*7
 -->
 (S1 ^operator O2140 = 0.1700769046561409)
Retracting rl*prefer*rvt*predict-yes*H0*1
 -->
 (S1 ^operator O2139 = 0.5231193621229728)
Retracting rl*prefer*rvt*predict-yes*H0*1*H1*19
 -->
 (S1 ^operator O2139 = 0.4768810903711926)
=>WM: (15048: S1 ^operator O2142 +)
=>WM: (15047: S1 ^operator O2141 +)
=>WM: (15046: O2142 ^name predict-no)
=>WM: (15045: O2141 ^name predict-yes)
=>WM: (15044: R1074 ^value 1)
=>WM: (15043: R1 ^reward R1074)
=>WM: (15042: I3 ^see 1)
<=WM: (15033: S1 ^operator O2139 +)
<=WM: (15035: S1 ^operator O2139)
<=WM: (15034: S1 ^operator O2140 +)
<=WM: (15028: R1 ^reward R1073)
<=WM: (14973: I3 ^see 0)
<=WM: (15031: O2140 ^name predict-no)
<=WM: (15030: O2139 ^name predict-yes)
<=WM: (15029: R1073 ^value 1)

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing prefer*rvt*predict-yes*H0
 -->
Firing rl*prefer*rvt*predict-yes*H0*1
 -->
 (S1 ^operator O2141 = 0.5231193621229728)
Firing prefer*rvt*predict-yes*H0*1*H1
 -->
Firing rl*prefer*rvt*predict-yes*H0*1*H1*20
 -->
 (S1 ^operator O2141 = 0.1693592933936033)
Firing prefer*rvt*predict-no*H0
 -->
Firing rl*prefer*rvt*predict-no*H0*2
 -->
 (S1 ^operator O2142 = 0.2550133912230119)
Firing prefer*rvt*predict-no*H0*2*H1
 -->
Firing rl*prefer*rvt*predict-no*H0*2*H1*11
 -->
 (S1 ^operator O2142 = 0.744986509061307)
 inner elaboration loop at bottom goal.
Retracting rl*prefer*rvt*predict-no*H0*2
 -->
 (S1 ^operator O2140 = 0.2550133912230119)
Retracting rl*prefer*rvt*predict-no*H0*2*H1*11
 -->
 (S1 ^operator O2140 = 0.744986509061307)
Retracting rl*prefer*rvt*predict-yes*H0*1
 -->
 (S1 ^operator O2139 = 0.5231193621229728)
Retracting rl*prefer*rvt*predict-yes*H0*1*H1*20
 -->
 (S1 ^operator O2139 = 0.1693592933936033)

--- END Proposal Phase ---

--- Decision Phase ---
RL update rl*prefer*rvt*predict-yes*H0*1 0.727959 -0.20484 0.523119 -> 0.727959 -0.20484 0.523119(R,m,v=1,0.980519,0.0192259)
RL update rl*prefer*rvt*predict-yes*H0*1*H1*19 0.272042 0.20484 0.476881 -> 0.272041 0.20484 0.476881(R,m,v=1,1,0)
=>WM: (15049: S1 ^operator O2142)

  1071:    O: O2142 (predict-no)
--- END Decision Phase ---

--- Application Phase ---
	--- Firing Productions (PE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing apply*operator
 -->
 (I3 ^predict-no N1071 +  :O )
Firing apply*operator*complete
 -->
 (I3 ^predict-yes N1070 -  :O )
 inner elaboration loop at bottom goal.
	--- Change Working Memory (PE) ---
=>WM: (15050: I3 ^predict-no N1071)
<=WM: (15037: N1070 ^status complete)
<=WM: (15036: I3 ^predict-yes N1070)
	--- Firing Productions (IE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing monitor*world
 -->

I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
	--- Change Working Memory (IE) ---

--- END Application Phase ---
--- Output Phase ---
ENV: Agent did: predict-no for direction L in state State-A
In  State-A moving L
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isR
--- END Output Phase ---
\--- Input Phase --- 
=>WM: (15054: I2 ^dir R)
=>WM: (15053: I2 ^reward 1)
=>WM: (15052: I2 ^see 0)
=>WM: (15051: N1071 ^status complete)
<=WM: (15040: I2 ^dir L)
<=WM: (15039: I2 ^reward 1)
<=WM: (15038: I2 ^see 1)
=>WM: (15055: I2 ^level-1 L0-root)
<=WM: (15041: I2 ^level-1 L1-root)

--- END Input Phase --- 

--- Proposal Phase ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing rl*prefer*rvt*predict-yes*H0*3*H1*14
 -->
 (S1 ^operator O2141 = 0.6170704303704048)
Firing rl*prefer*rvt*predict-no*H0*4*H1*13
 -->
 (S1 ^operator O2142 = 0.4910065094545203)
Firing prefer*rvt*predict-no*H0*4*H1
 -->
Firing prefer*rvt*predict-yes*H0*3*H1
 -->
Firing elaborate*copy-see-to-output-link
 -->
 (I3 ^see 0 +)
Firing elaborate*reward*based*on*reward
 -->
 (R1075 ^value 1 +)
 (R1 ^reward R1075 +)
Firing propose*predict-yes
 -->
 (O2143 ^name predict-yes +)
 (S1 ^operator O2143 +)
Firing propose*predict-no
 -->
 (O2144 ^name predict-no +)
 (S1 ^operator O2144 +)
Firing rl*prefer*rvt*predict-no*H0*4
 -->
 (S1 ^operator O2142 = 0.1269768396338047)
Firing rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O2141 = 0.3829470991647237)
Firing prefer*rvt*predict-yes*H0
 -->
Firing prefer*rvt*predict-no*H0
 -->
Firing elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir R +)
 inner elaboration loop at bottom goal.
Retracting elaborate*copy-see-to-output-link
 -->
 (I3 ^see 1 +)
Retracting propose*predict-no
 -->
 (O2142 ^name predict-no +)
 (S1 ^operator O2142 +)
Retracting propose*predict-yes
 -->
 (O2141 ^name predict-yes +)
 (S1 ^operator O2141 +)
Retracting elaborate*reward*based*on*reward
 -->
 (R1074 ^value 1 +)
 (R1 ^reward R1074 +)
Retracting elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir L +)
Retracting rl*prefer*rvt*predict-no*H0*2*H1*11
 -->
 (S1 ^operator O2142 = 0.744986509061307)
Retracting rl*prefer*rvt*predict-no*H0*2
 -->
 (S1 ^operator O2142 = 0.2550133912230119)
Retracting rl*prefer*rvt*predict-yes*H0*1*H1*20
 -->
 (S1 ^operator O2141 = 0.1693592933936033)
Retracting rl*prefer*rvt*predict-yes*H0*1
 -->
 (S1 ^operator O2141 = 0.523119294248848)
=>WM: (15063: S1 ^operator O2144 +)
=>WM: (15062: S1 ^operator O2143 +)
=>WM: (15061: I3 ^dir R)
=>WM: (15060: O2144 ^name predict-no)
=>WM: (15059: O2143 ^name predict-yes)
=>WM: (15058: R1075 ^value 1)
=>WM: (15057: R1 ^reward R1075)
=>WM: (15056: I3 ^see 0)
<=WM: (15047: S1 ^operator O2141 +)
<=WM: (15048: S1 ^operator O2142 +)
<=WM: (15049: S1 ^operator O2142)
<=WM: (15032: I3 ^dir L)
<=WM: (15043: R1 ^reward R1074)
<=WM: (15042: I3 ^see 1)
<=WM: (15046: O2142 ^name predict-no)
<=WM: (15045: O2141 ^name predict-yes)
<=WM: (15044: R1074 ^value 1)

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing prefer*rvt*predict-yes*H0
 -->
Firing rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O2143 = 0.3829470991647237)
Firing prefer*rvt*predict-yes*H0*3*H1
 -->
Firing rl*prefer*rvt*predict-yes*H0*3*H1*14
 -->
 (S1 ^operator O2143 = 0.6170704303704048)
Firing prefer*rvt*predict-no*H0
 -->
Firing rl*prefer*rvt*predict-no*H0*4
 -->
 (S1 ^operator O2144 = 0.1269768396338047)
Firing prefer*rvt*predict-no*H0*4*H1
 -->
Firing rl*prefer*rvt*predict-no*H0*4*H1*13
 -->
 (S1 ^operator O2144 = 0.4910065094545203)
 inner elaboration loop at bottom goal.
Retracting rl*prefer*rvt*predict-no*H0*4
 -->
 (S1 ^operator O2142 = 0.1269768396338047)
Retracting rl*prefer*rvt*predict-no*H0*4*H1*13
 -->
 (S1 ^operator O2142 = 0.4910065094545203)
Retracting rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O2141 = 0.3829470991647237)
Retracting rl*prefer*rvt*predict-yes*H0*3*H1*14
 -->
 (S1 ^operator O2141 = 0.6170704303704048)

--- END Proposal Phase ---

--- Decision Phase ---
RL update rl*prefer*rvt*predict-no*H0*2 0.631495 -0.376482 0.255013 -> 0.631495 -0.376482 0.255013(R,m,v=1,0.920398,0.0736318)
RL update rl*prefer*rvt*predict-no*H0*2*H1*11 0.368505 0.376482 0.744987 -> 0.368505 0.376482 0.744987(R,m,v=1,1,0)
=>WM: (15064: S1 ^operator O2143)

  1072:    O: O2143 (predict-yes)
--- END Decision Phase ---

--- Application Phase ---
	--- Firing Productions (PE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing apply*operator
 -->
 (I3 ^predict-yes N1072 +  :O )
Firing apply*operator*complete
 -->
 (I3 ^predict-no N1071 -  :O )
 inner elaboration loop at bottom goal.
	--- Change Working Memory (PE) ---
=>WM: (15065: I3 ^predict-yes N1072)
<=WM: (15051: N1071 ^status complete)
<=WM: (15050: I3 ^predict-no N1071)
	--- Firing Productions (IE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing monitor*world
 -->

I see 1 and I'm going to do: predict-yes inner elaboration loop at bottom goal.
	--- Change Working Memory (IE) ---

--- END Application Phase ---
--- Output Phase ---
ENV: Agent did: predict-yes for direction R in state State-A
In  State-A moving R
ENV: (next state, see, prediction correct?) = (State-B, 1, True)
predict error 0
dir: dir isR
--- END Output Phase ---
-/|--- Input Phase --- 
=>WM: (15069: I2 ^dir R)
=>WM: (15068: I2 ^reward 1)
=>WM: (15067: I2 ^see 1)
=>WM: (15066: N1072 ^status complete)
<=WM: (15054: I2 ^dir R)
<=WM: (15053: I2 ^reward 1)
<=WM: (15052: I2 ^see 0)
=>WM: (15070: I2 ^level-1 R1-root)
<=WM: (15055: I2 ^level-1 L0-root)

--- END Input Phase --- 

--- Proposal Phase ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing rl*prefer*rvt*predict-yes*H0*3*H1*16
 -->
 (S1 ^operator O2143 = 0.08783148430849691)
Firing rl*prefer*rvt*predict-no*H0*4*H1*15
 -->
 (S1 ^operator O2144 = 0.8730232299561043)
Firing prefer*rvt*predict-no*H0*4*H1
 -->
Firing prefer*rvt*predict-yes*H0*3*H1
 -->
Firing elaborate*copy-see-to-output-link
 -->
 (I3 ^see 1 +)
Firing elaborate*reward*based*on*reward
 -->
 (R1076 ^value 1 +)
 (R1 ^reward R1076 +)
Firing propose*predict-yes
 -->
 (O2145 ^name predict-yes +)
 (S1 ^operator O2145 +)
Firing propose*predict-no
 -->
 (O2146 ^name predict-no +)
 (S1 ^operator O2146 +)
Firing rl*prefer*rvt*predict-no*H0*4
 -->
 (S1 ^operator O2144 = 0.1269768396338047)
Firing rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O2143 = 0.3829470991647237)
Firing prefer*rvt*predict-yes*H0
 -->
Firing prefer*rvt*predict-no*H0
 -->
Firing elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir R +)
 inner elaboration loop at bottom goal.
Retracting elaborate*copy-see-to-output-link
 -->
 (I3 ^see 0 +)
Retracting propose*predict-no
 -->
 (O2144 ^name predict-no +)
 (S1 ^operator O2144 +)
Retracting propose*predict-yes
 -->
 (O2143 ^name predict-yes +)
 (S1 ^operator O2143 +)
Retracting elaborate*reward*based*on*reward
 -->
 (R1075 ^value 1 +)
 (R1 ^reward R1075 +)
Retracting elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir R +)
Retracting rl*prefer*rvt*predict-no*H0*4*H1*13
 -->
 (S1 ^operator O2144 = 0.4910065094545203)
Retracting rl*prefer*rvt*predict-no*H0*4
 -->
 (S1 ^operator O2144 = 0.1269768396338047)
Retracting rl*prefer*rvt*predict-yes*H0*3*H1*14
 -->
 (S1 ^operator O2143 = 0.6170704303704048)
Retracting rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O2143 = 0.3829470991647237)
=>WM: (15077: S1 ^operator O2146 +)
=>WM: (15076: S1 ^operator O2145 +)
=>WM: (15075: O2146 ^name predict-no)
=>WM: (15074: O2145 ^name predict-yes)
=>WM: (15073: R1076 ^value 1)
=>WM: (15072: R1 ^reward R1076)
=>WM: (15071: I3 ^see 1)
<=WM: (15062: S1 ^operator O2143 +)
<=WM: (15064: S1 ^operator O2143)
<=WM: (15063: S1 ^operator O2144 +)
<=WM: (15057: R1 ^reward R1075)
<=WM: (15056: I3 ^see 0)
<=WM: (15060: O2144 ^name predict-no)
<=WM: (15059: O2143 ^name predict-yes)
<=WM: (15058: R1075 ^value 1)

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing prefer*rvt*predict-yes*H0
 -->
Firing rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O2145 = 0.3829470991647237)
Firing prefer*rvt*predict-yes*H0*3*H1
 -->
Firing rl*prefer*rvt*predict-yes*H0*3*H1*16
 -->
 (S1 ^operator O2145 = 0.08783148430849691)
Firing prefer*rvt*predict-no*H0
 -->
Firing rl*prefer*rvt*predict-no*H0*4
 -->
 (S1 ^operator O2146 = 0.1269768396338047)
Firing prefer*rvt*predict-no*H0*4*H1
 -->
Firing rl*prefer*rvt*predict-no*H0*4*H1*15
 -->
 (S1 ^operator O2146 = 0.8730232299561043)
 inner elaboration loop at bottom goal.
Retracting rl*prefer*rvt*predict-no*H0*4
 -->
 (S1 ^operator O2144 = 0.1269768396338047)
Retracting rl*prefer*rvt*predict-no*H0*4*H1*15
 -->
 (S1 ^operator O2144 = 0.8730232299561043)
Retracting rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O2143 = 0.3829470991647237)
Retracting rl*prefer*rvt*predict-yes*H0*3*H1*16
 -->
 (S1 ^operator O2143 = 0.08783148430849691)

--- END Proposal Phase ---

--- Decision Phase ---
RL update rl*prefer*rvt*predict-yes*H0*3 0.67314 -0.290193 0.382947 -> 0.673137 -0.290193 0.382944(R,m,v=1,0.963636,0.035255)
RL update rl*prefer*rvt*predict-yes*H0*3*H1*14 0.326876 0.290194 0.61707 -> 0.326874 0.290194 0.617068(R,m,v=1,1,0)
=>WM: (15078: S1 ^operator O2146)

  1073:    O: O2146 (predict-no)
--- END Decision Phase ---

--- Application Phase ---
	--- Firing Productions (PE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing apply*operator
 -->
 (I3 ^predict-no N1073 +  :O )
Firing apply*operator*complete
 -->
 (I3 ^predict-yes N1072 -  :O )
 inner elaboration loop at bottom goal.
	--- Change Working Memory (PE) ---
=>WM: (15079: I3 ^predict-no N1073)
<=WM: (15066: N1072 ^status complete)
<=WM: (15065: I3 ^predict-yes N1072)
	--- Firing Productions (IE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing monitor*world
 -->

I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
	--- Change Working Memory (IE) ---

--- END Application Phase ---
--- Output Phase ---
ENV: Agent did: predict-no for direction R in state State-B
In  State-B moving R
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isL
--- END Output Phase ---
\---- Input Phase --- 
=>WM: (15083: I2 ^dir L)
=>WM: (15082: I2 ^reward 1)
=>WM: (15081: I2 ^see 0)
=>WM: (15080: N1073 ^status complete)
<=WM: (15069: I2 ^dir R)
<=WM: (15068: I2 ^reward 1)
<=WM: (15067: I2 ^see 1)
=>WM: (15084: I2 ^level-1 R0-root)
<=WM: (15070: I2 ^level-1 R1-root)

--- END Input Phase --- 

--- Proposal Phase ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing rl*prefer*rvt*predict-yes*H0*1*H1*19
 -->
 (S1 ^operator O2145 = 0.4768810224970678)
Firing rl*prefer*rvt*predict-no*H0*2*H1*7
 -->
 (S1 ^operator O2146 = 0.1700769046561409)
Firing prefer*rvt*predict-no*H0*2*H1
 -->
Firing prefer*rvt*predict-yes*H0*1*H1
 -->
Firing elaborate*copy-see-to-output-link
 -->
 (I3 ^see 0 +)
Firing elaborate*reward*based*on*reward
 -->
 (R1077 ^value 1 +)
 (R1 ^reward R1077 +)
Firing propose*predict-yes
 -->
 (O2147 ^name predict-yes +)
 (S1 ^operator O2147 +)
Firing propose*predict-no
 -->
 (O2148 ^name predict-no +)
 (S1 ^operator O2148 +)
Firing rl*prefer*rvt*predict-no*H0*2
 -->
 (S1 ^operator O2146 = 0.255013406180364)
Firing rl*prefer*rvt*predict-yes*H0*1
 -->
 (S1 ^operator O2145 = 0.523119294248848)
Firing prefer*rvt*predict-yes*H0
 -->
Firing prefer*rvt*predict-no*H0
 -->
Firing elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir L +)
 inner elaboration loop at bottom goal.
Retracting elaborate*copy-see-to-output-link
 -->
 (I3 ^see 1 +)
Retracting propose*predict-no
 -->
 (O2146 ^name predict-no +)
 (S1 ^operator O2146 +)
Retracting propose*predict-yes
 -->
 (O2145 ^name predict-yes +)
 (S1 ^operator O2145 +)
Retracting elaborate*reward*based*on*reward
 -->
 (R1076 ^value 1 +)
 (R1 ^reward R1076 +)
Retracting elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir R +)
Retracting rl*prefer*rvt*predict-no*H0*4*H1*15
 -->
 (S1 ^operator O2146 = 0.8730232299561043)
Retracting rl*prefer*rvt*predict-no*H0*4
 -->
 (S1 ^operator O2146 = 0.1269768396338047)
Retracting rl*prefer*rvt*predict-yes*H0*3*H1*16
 -->
 (S1 ^operator O2145 = 0.08783148430849691)
Retracting rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O2145 = 0.3829444697344545)
=>WM: (15092: S1 ^operator O2148 +)
=>WM: (15091: S1 ^operator O2147 +)
=>WM: (15090: I3 ^dir L)
=>WM: (15089: O2148 ^name predict-no)
=>WM: (15088: O2147 ^name predict-yes)
=>WM: (15087: R1077 ^value 1)
=>WM: (15086: R1 ^reward R1077)
=>WM: (15085: I3 ^see 0)
<=WM: (15076: S1 ^operator O2145 +)
<=WM: (15077: S1 ^operator O2146 +)
<=WM: (15078: S1 ^operator O2146)
<=WM: (15061: I3 ^dir R)
<=WM: (15072: R1 ^reward R1076)
<=WM: (15071: I3 ^see 1)
<=WM: (15075: O2146 ^name predict-no)
<=WM: (15074: O2145 ^name predict-yes)
<=WM: (15073: R1076 ^value 1)

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing prefer*rvt*predict-yes*H0
 -->
Firing rl*prefer*rvt*predict-yes*H0*1
 -->
 (S1 ^operator O2147 = 0.523119294248848)
Firing prefer*rvt*predict-yes*H0*1*H1
 -->
Firing rl*prefer*rvt*predict-yes*H0*1*H1*19
 -->
 (S1 ^operator O2147 = 0.4768810224970678)
Firing prefer*rvt*predict-no*H0
 -->
Firing rl*prefer*rvt*predict-no*H0*2
 -->
 (S1 ^operator O2148 = 0.255013406180364)
Firing prefer*rvt*predict-no*H0*2*H1
 -->
Firing rl*prefer*rvt*predict-no*H0*2*H1*7
 -->
 (S1 ^operator O2148 = 0.1700769046561409)
 inner elaboration loop at bottom goal.
Retracting rl*prefer*rvt*predict-no*H0*2
 -->
 (S1 ^operator O2146 = 0.255013406180364)
Retracting rl*prefer*rvt*predict-no*H0*2*H1*7
 -->
 (S1 ^operator O2146 = 0.1700769046561409)
Retracting rl*prefer*rvt*predict-yes*H0*1
 -->
 (S1 ^operator O2145 = 0.523119294248848)
Retracting rl*prefer*rvt*predict-yes*H0*1*H1*19
 -->
 (S1 ^operator O2145 = 0.4768810224970678)

--- END Proposal Phase ---

--- Decision Phase ---
RL update rl*prefer*rvt*predict-no*H0*4 0.814714 -0.687737 0.126977 -> 0.814714 -0.687737 0.126977(R,m,v=1,0.954082,0.0440345)
RL update rl*prefer*rvt*predict-no*H0*4*H1*15 0.185286 0.687737 0.873023 -> 0.185286 0.687737 0.873023(R,m,v=1,1,0)
=>WM: (15093: S1 ^operator O2147)

  1074:    O: O2147 (predict-yes)
--- END Decision Phase ---

--- Application Phase ---
	--- Firing Productions (PE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing apply*operator
 -->
 (I3 ^predict-yes N1074 +  :O )
Firing apply*operator*complete
 -->
 (I3 ^predict-no N1073 -  :O )
 inner elaboration loop at bottom goal.
	--- Change Working Memory (PE) ---
=>WM: (15094: I3 ^predict-yes N1074)
<=WM: (15080: N1073 ^status complete)
<=WM: (15079: I3 ^predict-no N1073)
	--- Firing Productions (IE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing monitor*world
 -->

I see 1 and I'm going to do: predict-yes inner elaboration loop at bottom goal.
	--- Change Working Memory (IE) ---

--- END Application Phase ---
--- Output Phase ---
ENV: Agent did: predict-yes for direction L in state State-B
In  State-B moving L
ENV: (next state, see, prediction correct?) = (State-A, 1, True)
predict error 0
dir: dir isL
--- END Output Phase ---
/|\--- Input Phase --- 
=>WM: (15098: I2 ^dir L)
=>WM: (15097: I2 ^reward 1)
=>WM: (15096: I2 ^see 1)
=>WM: (15095: N1074 ^status complete)
<=WM: (15083: I2 ^dir L)
<=WM: (15082: I2 ^reward 1)
<=WM: (15081: I2 ^see 0)
=>WM: (15099: I2 ^level-1 L1-root)
<=WM: (15084: I2 ^level-1 R0-root)

--- END Input Phase --- 

--- Proposal Phase ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing rl*prefer*rvt*predict-yes*H0*1*H1*20
 -->
 (S1 ^operator O2147 = 0.1693592933936033)
Firing rl*prefer*rvt*predict-no*H0*2*H1*11
 -->
 (S1 ^operator O2148 = 0.7449865240186593)
Firing prefer*rvt*predict-no*H0*2*H1
 -->
Firing prefer*rvt*predict-yes*H0*1*H1
 -->
Firing elaborate*copy-see-to-output-link
 -->
 (I3 ^see 1 +)
Firing elaborate*reward*based*on*reward
 -->
 (R1078 ^value 1 +)
 (R1 ^reward R1078 +)
Firing propose*predict-yes
 -->
 (O2149 ^name predict-yes +)
 (S1 ^operator O2149 +)
Firing propose*predict-no
 -->
 (O2150 ^name predict-no +)
 (S1 ^operator O2150 +)
Firing rl*prefer*rvt*predict-no*H0*2
 -->
 (S1 ^operator O2148 = 0.255013406180364)
Firing rl*prefer*rvt*predict-yes*H0*1
 -->
 (S1 ^operator O2147 = 0.523119294248848)
Firing prefer*rvt*predict-yes*H0
 -->
Firing prefer*rvt*predict-no*H0
 -->
Firing elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir L +)
 inner elaboration loop at bottom goal.
Retracting elaborate*copy-see-to-output-link
 -->
 (I3 ^see 0 +)
Retracting propose*predict-no
 -->
 (O2148 ^name predict-no +)
 (S1 ^operator O2148 +)
Retracting propose*predict-yes
 -->
 (O2147 ^name predict-yes +)
 (S1 ^operator O2147 +)
Retracting elaborate*reward*based*on*reward
 -->
 (R1077 ^value 1 +)
 (R1 ^reward R1077 +)
Retracting elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir L +)
Retracting rl*prefer*rvt*predict-no*H0*2*H1*7
 -->
 (S1 ^operator O2148 = 0.1700769046561409)
Retracting rl*prefer*rvt*predict-no*H0*2
 -->
 (S1 ^operator O2148 = 0.255013406180364)
Retracting rl*prefer*rvt*predict-yes*H0*1*H1*19
 -->
 (S1 ^operator O2147 = 0.4768810224970678)
Retracting rl*prefer*rvt*predict-yes*H0*1
 -->
 (S1 ^operator O2147 = 0.523119294248848)
=>WM: (15106: S1 ^operator O2150 +)
=>WM: (15105: S1 ^operator O2149 +)
=>WM: (15104: O2150 ^name predict-no)
=>WM: (15103: O2149 ^name predict-yes)
=>WM: (15102: R1078 ^value 1)
=>WM: (15101: R1 ^reward R1078)
=>WM: (15100: I3 ^see 1)
<=WM: (15091: S1 ^operator O2147 +)
<=WM: (15093: S1 ^operator O2147)
<=WM: (15092: S1 ^operator O2148 +)
<=WM: (15086: R1 ^reward R1077)
<=WM: (15085: I3 ^see 0)
<=WM: (15089: O2148 ^name predict-no)
<=WM: (15088: O2147 ^name predict-yes)
<=WM: (15087: R1077 ^value 1)

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing prefer*rvt*predict-yes*H0
 -->
Firing rl*prefer*rvt*predict-yes*H0*1
 -->
 (S1 ^operator O2149 = 0.523119294248848)
Firing prefer*rvt*predict-yes*H0*1*H1
 -->
Firing rl*prefer*rvt*predict-yes*H0*1*H1*20
 -->
 (S1 ^operator O2149 = 0.1693592933936033)
Firing prefer*rvt*predict-no*H0
 -->
Firing rl*prefer*rvt*predict-no*H0*2
 -->
 (S1 ^operator O2150 = 0.255013406180364)
Firing prefer*rvt*predict-no*H0*2*H1
 -->
Firing rl*prefer*rvt*predict-no*H0*2*H1*11
 -->
 (S1 ^operator O2150 = 0.7449865240186593)
 inner elaboration loop at bottom goal.
Retracting rl*prefer*rvt*predict-no*H0*2
 -->
 (S1 ^operator O2148 = 0.255013406180364)
Retracting rl*prefer*rvt*predict-no*H0*2*H1*11
 -->
 (S1 ^operator O2148 = 0.7449865240186593)
Retracting rl*prefer*rvt*predict-yes*H0*1
 -->
 (S1 ^operator O2147 = 0.523119294248848)
Retracting rl*prefer*rvt*predict-yes*H0*1*H1*20
 -->
 (S1 ^operator O2147 = 0.1693592933936033)

--- END Proposal Phase ---

--- Decision Phase ---
RL update rl*prefer*rvt*predict-yes*H0*1 0.727959 -0.20484 0.523119 -> 0.727959 -0.20484 0.523119(R,m,v=1,0.980645,0.0191035)
RL update rl*prefer*rvt*predict-yes*H0*1*H1*19 0.272041 0.20484 0.476881 -> 0.272041 0.20484 0.476881(R,m,v=1,1,0)
=>WM: (15107: S1 ^operator O2150)

  1075:    O: O2150 (predict-no)
--- END Decision Phase ---

--- Application Phase ---
	--- Firing Productions (PE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing apply*operator
 -->
 (I3 ^predict-no N1075 +  :O )
Firing apply*operator*complete
 -->
 (I3 ^predict-yes N1074 -  :O )
 inner elaboration loop at bottom goal.
	--- Change Working Memory (PE) ---
=>WM: (15108: I3 ^predict-no N1075)
<=WM: (15095: N1074 ^status complete)
<=WM: (15094: I3 ^predict-yes N1074)
	--- Firing Productions (IE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing monitor*world
 -->

I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
	--- Change Working Memory (IE) ---

--- END Application Phase ---
--- Output Phase ---
ENV: Agent did: predict-no for direction L in state State-A
In  State-A moving L
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isL
--- END Output Phase ---
-/|--- Input Phase --- 
=>WM: (15112: I2 ^dir L)
=>WM: (15111: I2 ^reward 1)
=>WM: (15110: I2 ^see 0)
=>WM: (15109: N1075 ^status complete)
<=WM: (15098: I2 ^dir L)
<=WM: (15097: I2 ^reward 1)
<=WM: (15096: I2 ^see 1)
=>WM: (15113: I2 ^level-1 L0-root)
<=WM: (15099: I2 ^level-1 L1-root)

--- END Input Phase --- 

--- Proposal Phase ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing rl*prefer*rvt*predict-yes*H0*1*H1*21
 -->
 (S1 ^operator O2149 = 0.3)
Firing rl*prefer*rvt*predict-no*H0*2*H1*12
 -->
 (S1 ^operator O2150 = 0.74498667547292)
Firing prefer*rvt*predict-no*H0*2*H1
 -->
Firing prefer*rvt*predict-yes*H0*1*H1
 -->
Firing elaborate*copy-see-to-output-link
 -->
 (I3 ^see 0 +)
Firing elaborate*reward*based*on*reward
 -->
 (R1079 ^value 1 +)
 (R1 ^reward R1079 +)
Firing propose*predict-yes
 -->
 (O2151 ^name predict-yes +)
 (S1 ^operator O2151 +)
Firing propose*predict-no
 -->
 (O2152 ^name predict-no +)
 (S1 ^operator O2152 +)
Firing rl*prefer*rvt*predict-no*H0*2
 -->
 (S1 ^operator O2150 = 0.255013406180364)
Firing rl*prefer*rvt*predict-yes*H0*1
 -->
 (S1 ^operator O2149 = 0.5231192467369606)
Firing prefer*rvt*predict-yes*H0
 -->
Firing prefer*rvt*predict-no*H0
 -->
Firing elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir L +)
 inner elaboration loop at bottom goal.
Retracting elaborate*copy-see-to-output-link
 -->
 (I3 ^see 1 +)
Retracting propose*predict-no
 -->
 (O2150 ^name predict-no +)
 (S1 ^operator O2150 +)
Retracting propose*predict-yes
 -->
 (O2149 ^name predict-yes +)
 (S1 ^operator O2149 +)
Retracting elaborate*reward*based*on*reward
 -->
 (R1078 ^value 1 +)
 (R1 ^reward R1078 +)
Retracting elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir L +)
Retracting rl*prefer*rvt*predict-no*H0*2*H1*11
 -->
 (S1 ^operator O2150 = 0.7449865240186593)
Retracting rl*prefer*rvt*predict-no*H0*2
 -->
 (S1 ^operator O2150 = 0.255013406180364)
Retracting rl*prefer*rvt*predict-yes*H0*1*H1*20
 -->
 (S1 ^operator O2149 = 0.1693592933936033)
Retracting rl*prefer*rvt*predict-yes*H0*1
 -->
 (S1 ^operator O2149 = 0.5231192467369606)
=>WM: (15120: S1 ^operator O2152 +)
=>WM: (15119: S1 ^operator O2151 +)
=>WM: (15118: O2152 ^name predict-no)
=>WM: (15117: O2151 ^name predict-yes)
=>WM: (15116: R1079 ^value 1)
=>WM: (15115: R1 ^reward R1079)
=>WM: (15114: I3 ^see 0)
<=WM: (15105: S1 ^operator O2149 +)
<=WM: (15106: S1 ^operator O2150 +)
<=WM: (15107: S1 ^operator O2150)
<=WM: (15101: R1 ^reward R1078)
<=WM: (15100: I3 ^see 1)
<=WM: (15104: O2150 ^name predict-no)
<=WM: (15103: O2149 ^name predict-yes)
<=WM: (15102: R1078 ^value 1)

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing prefer*rvt*predict-yes*H0
 -->
Firing rl*prefer*rvt*predict-yes*H0*1
 -->
 (S1 ^operator O2151 = 0.5231192467369606)
Firing prefer*rvt*predict-yes*H0*1*H1
 -->
Firing rl*prefer*rvt*predict-yes*H0*1*H1*21
 -->
 (S1 ^operator O2151 = 0.3)
Firing prefer*rvt*predict-no*H0
 -->
Firing rl*prefer*rvt*predict-no*H0*2
 -->
 (S1 ^operator O2152 = 0.255013406180364)
Firing prefer*rvt*predict-no*H0*2*H1
 -->
Firing rl*prefer*rvt*predict-no*H0*2*H1*12
 -->
 (S1 ^operator O2152 = 0.74498667547292)
 inner elaboration loop at bottom goal.
Retracting rl*prefer*rvt*predict-no*H0*2
 -->
 (S1 ^operator O2150 = 0.255013406180364)
Retracting rl*prefer*rvt*predict-no*H0*2*H1*12
 -->
 (S1 ^operator O2150 = 0.74498667547292)
Retracting rl*prefer*rvt*predict-yes*H0*1
 -->
 (S1 ^operator O2149 = 0.5231192467369606)
Retracting rl*prefer*rvt*predict-yes*H0*1*H1*21
 -->
 (S1 ^operator O2149 = 0.3)

--- END Proposal Phase ---

--- Decision Phase ---
RL update rl*prefer*rvt*predict-no*H0*2 0.631495 -0.376482 0.255013 -> 0.631495 -0.376482 0.255013(R,m,v=1,0.920792,0.0732969)
RL update rl*prefer*rvt*predict-no*H0*2*H1*11 0.368505 0.376482 0.744987 -> 0.368505 0.376482 0.744987(R,m,v=1,1,0)
=>WM: (15121: S1 ^operator O2152)

  1076:    O: O2152 (predict-no)
--- END Decision Phase ---

--- Application Phase ---
	--- Firing Productions (PE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing apply*operator
 -->
 (I3 ^predict-no N1076 +  :O )
Firing apply*operator*complete
 -->
 (I3 ^predict-no N1075 -  :O )
 inner elaboration loop at bottom goal.
	--- Change Working Memory (PE) ---
=>WM: (15122: I3 ^predict-no N1076)
<=WM: (15109: N1075 ^status complete)
<=WM: (15108: I3 ^predict-no N1075)
	--- Firing Productions (IE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing monitor*world
 -->

I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
	--- Change Working Memory (IE) ---

--- END Application Phase ---
--- Output Phase ---
ENV: Agent did: predict-no for direction L in state State-A
In  State-A moving L
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isL
--- END Output Phase ---
\---- Input Phase --- 
=>WM: (15126: I2 ^dir L)
=>WM: (15125: I2 ^reward 1)
=>WM: (15124: I2 ^see 0)
=>WM: (15123: N1076 ^status complete)
<=WM: (15112: I2 ^dir L)
<=WM: (15111: I2 ^reward 1)
<=WM: (15110: I2 ^see 0)
=>WM: (15127: I2 ^level-1 L0-root)
<=WM: (15113: I2 ^level-1 L0-root)

--- END Input Phase --- 

--- Proposal Phase ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing rl*prefer*rvt*predict-yes*H0*1*H1*21
 -->
 (S1 ^operator O2151 = 0.3)
Firing rl*prefer*rvt*predict-no*H0*2*H1*12
 -->
 (S1 ^operator O2152 = 0.74498667547292)
Firing prefer*rvt*predict-no*H0*2*H1
 -->
Firing prefer*rvt*predict-yes*H0*1*H1
 -->
Firing elaborate*copy-see-to-output-link
 -->
 (I3 ^see 0 +)
Firing elaborate*reward*based*on*reward
 -->
 (R1080 ^value 1 +)
 (R1 ^reward R1080 +)
Firing propose*predict-yes
 -->
 (O2153 ^name predict-yes +)
 (S1 ^operator O2153 +)
Firing propose*predict-no
 -->
 (O2154 ^name predict-no +)
 (S1 ^operator O2154 +)
Firing rl*prefer*rvt*predict-no*H0*2
 -->
 (S1 ^operator O2152 = 0.2550134166505105)
Firing rl*prefer*rvt*predict-yes*H0*1
 -->
 (S1 ^operator O2151 = 0.5231192467369606)
Firing prefer*rvt*predict-yes*H0
 -->
Firing prefer*rvt*predict-no*H0
 -->
Firing elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir L +)
 inner elaboration loop at bottom goal.
Retracting elaborate*copy-see-to-output-link
 -->
 (I3 ^see 0 +)
Retracting propose*predict-no
 -->
 (O2152 ^name predict-no +)
 (S1 ^operator O2152 +)
Retracting propose*predict-yes
 -->
 (O2151 ^name predict-yes +)
 (S1 ^operator O2151 +)
Retracting elaborate*reward*based*on*reward
 -->
 (R1079 ^value 1 +)
 (R1 ^reward R1079 +)
Retracting elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir L +)
Retracting rl*prefer*rvt*predict-no*H0*2*H1*12
 -->
 (S1 ^operator O2152 = 0.74498667547292)
Retracting rl*prefer*rvt*predict-no*H0*2
 -->
 (S1 ^operator O2152 = 0.2550134166505105)
Retracting rl*prefer*rvt*predict-yes*H0*1*H1*21
 -->
 (S1 ^operator O2151 = 0.3)
Retracting rl*prefer*rvt*predict-yes*H0*1
 -->
 (S1 ^operator O2151 = 0.5231192467369606)
=>WM: (15133: S1 ^operator O2154 +)
=>WM: (15132: S1 ^operator O2153 +)
=>WM: (15131: O2154 ^name predict-no)
=>WM: (15130: O2153 ^name predict-yes)
=>WM: (15129: R1080 ^value 1)
=>WM: (15128: R1 ^reward R1080)
<=WM: (15119: S1 ^operator O2151 +)
<=WM: (15120: S1 ^operator O2152 +)
<=WM: (15121: S1 ^operator O2152)
<=WM: (15115: R1 ^reward R1079)
<=WM: (15118: O2152 ^name predict-no)
<=WM: (15117: O2151 ^name predict-yes)
<=WM: (15116: R1079 ^value 1)

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing prefer*rvt*predict-yes*H0
 -->
Firing rl*prefer*rvt*predict-yes*H0*1
 -->
 (S1 ^operator O2153 = 0.5231192467369606)
Firing prefer*rvt*predict-yes*H0*1*H1
 -->
Firing rl*prefer*rvt*predict-yes*H0*1*H1*21
 -->
 (S1 ^operator O2153 = 0.3)
Firing prefer*rvt*predict-no*H0
 -->
Firing rl*prefer*rvt*predict-no*H0*2
 -->
 (S1 ^operator O2154 = 0.2550134166505105)
Firing prefer*rvt*predict-no*H0*2*H1
 -->
Firing rl*prefer*rvt*predict-no*H0*2*H1*12
 -->
 (S1 ^operator O2154 = 0.74498667547292)
 inner elaboration loop at bottom goal.
Retracting rl*prefer*rvt*predict-no*H0*2
 -->
 (S1 ^operator O2152 = 0.2550134166505105)
Retracting rl*prefer*rvt*predict-no*H0*2*H1*12
 -->
 (S1 ^operator O2152 = 0.74498667547292)
Retracting rl*prefer*rvt*predict-yes*H0*1
 -->
 (S1 ^operator O2151 = 0.5231192467369606)
Retracting rl*prefer*rvt*predict-yes*H0*1*H1*21
 -->
 (S1 ^operator O2151 = 0.3)

--- END Proposal Phase ---

--- Decision Phase ---
RL update rl*prefer*rvt*predict-no*H0*2 0.631495 -0.376482 0.255013 -> 0.631495 -0.376482 0.255013(R,m,v=1,0.921182,0.0729649)
RL update rl*prefer*rvt*predict-no*H0*2*H1*12 0.368505 0.376482 0.744987 -> 0.368505 0.376482 0.744987(R,m,v=1,1,0)
=>WM: (15134: S1 ^operator O2154)

  1077:    O: O2154 (predict-no)
--- END Decision Phase ---

--- Application Phase ---
	--- Firing Productions (PE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing apply*operator
 -->
 (I3 ^predict-no N1077 +  :O )
Firing apply*operator*complete
 -->
 (I3 ^predict-no N1076 -  :O )
 inner elaboration loop at bottom goal.
	--- Change Working Memory (PE) ---
=>WM: (15135: I3 ^predict-no N1077)
<=WM: (15123: N1076 ^status complete)
<=WM: (15122: I3 ^predict-no N1076)
	--- Firing Productions (IE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing monitor*world
 -->

I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
	--- Change Working Memory (IE) ---

--- END Application Phase ---
--- Output Phase ---
ENV: Agent did: predict-no for direction L in state State-A
In  State-A moving L
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isL
--- END Output Phase ---
/|\--- Input Phase --- 
=>WM: (15139: I2 ^dir L)
=>WM: (15138: I2 ^reward 1)
=>WM: (15137: I2 ^see 0)
=>WM: (15136: N1077 ^status complete)
<=WM: (15126: I2 ^dir L)
<=WM: (15125: I2 ^reward 1)
<=WM: (15124: I2 ^see 0)
=>WM: (15140: I2 ^level-1 L0-root)
<=WM: (15127: I2 ^level-1 L0-root)

--- END Input Phase --- 

--- Proposal Phase ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing rl*prefer*rvt*predict-yes*H0*1*H1*21
 -->
 (S1 ^operator O2153 = 0.3)
Firing rl*prefer*rvt*predict-no*H0*2*H1*12
 -->
 (S1 ^operator O2154 = 0.7449866616544054)
Firing prefer*rvt*predict-no*H0*2*H1
 -->
Firing prefer*rvt*predict-yes*H0*1*H1
 -->
Firing elaborate*copy-see-to-output-link
 -->
 (I3 ^see 0 +)
Firing elaborate*reward*based*on*reward
 -->
 (R1081 ^value 1 +)
 (R1 ^reward R1081 +)
Firing propose*predict-yes
 -->
 (O2155 ^name predict-yes +)
 (S1 ^operator O2155 +)
Firing propose*predict-no
 -->
 (O2156 ^name predict-no +)
 (S1 ^operator O2156 +)
Firing rl*prefer*rvt*predict-no*H0*2
 -->
 (S1 ^operator O2154 = 0.2550134028319959)
Firing rl*prefer*rvt*predict-yes*H0*1
 -->
 (S1 ^operator O2153 = 0.5231192467369606)
Firing prefer*rvt*predict-yes*H0
 -->
Firing prefer*rvt*predict-no*H0
 -->
Firing elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir L +)
 inner elaboration loop at bottom goal.
Retracting elaborate*copy-see-to-output-link
 -->
 (I3 ^see 0 +)
Retracting propose*predict-no
 -->
 (O2154 ^name predict-no +)
 (S1 ^operator O2154 +)
Retracting propose*predict-yes
 -->
 (O2153 ^name predict-yes +)
 (S1 ^operator O2153 +)
Retracting elaborate*reward*based*on*reward
 -->
 (R1080 ^value 1 +)
 (R1 ^reward R1080 +)
Retracting elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir L +)
Retracting rl*prefer*rvt*predict-no*H0*2*H1*12
 -->
 (S1 ^operator O2154 = 0.7449866616544054)
Retracting rl*prefer*rvt*predict-no*H0*2
 -->
 (S1 ^operator O2154 = 0.2550134028319959)
Retracting rl*prefer*rvt*predict-yes*H0*1*H1*21
 -->
 (S1 ^operator O2153 = 0.3)
Retracting rl*prefer*rvt*predict-yes*H0*1
 -->
 (S1 ^operator O2153 = 0.5231192467369606)
=>WM: (15146: S1 ^operator O2156 +)
=>WM: (15145: S1 ^operator O2155 +)
=>WM: (15144: O2156 ^name predict-no)
=>WM: (15143: O2155 ^name predict-yes)
=>WM: (15142: R1081 ^value 1)
=>WM: (15141: R1 ^reward R1081)
<=WM: (15132: S1 ^operator O2153 +)
<=WM: (15133: S1 ^operator O2154 +)
<=WM: (15134: S1 ^operator O2154)
<=WM: (15128: R1 ^reward R1080)
<=WM: (15131: O2154 ^name predict-no)
<=WM: (15130: O2153 ^name predict-yes)
<=WM: (15129: R1080 ^value 1)

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing prefer*rvt*predict-yes*H0
 -->
Firing rl*prefer*rvt*predict-yes*H0*1
 -->
 (S1 ^operator O2155 = 0.5231192467369606)
Firing prefer*rvt*predict-yes*H0*1*H1
 -->
Firing rl*prefer*rvt*predict-yes*H0*1*H1*21
 -->
 (S1 ^operator O2155 = 0.3)
Firing prefer*rvt*predict-no*H0
 -->
Firing rl*prefer*rvt*predict-no*H0*2
 -->
 (S1 ^operator O2156 = 0.2550134028319959)
Firing prefer*rvt*predict-no*H0*2*H1
 -->
Firing rl*prefer*rvt*predict-no*H0*2*H1*12
 -->
 (S1 ^operator O2156 = 0.7449866616544054)
 inner elaboration loop at bottom goal.
Retracting rl*prefer*rvt*predict-no*H0*2
 -->
 (S1 ^operator O2154 = 0.2550134028319959)
Retracting rl*prefer*rvt*predict-no*H0*2*H1*12
 -->
 (S1 ^operator O2154 = 0.7449866616544054)
Retracting rl*prefer*rvt*predict-yes*H0*1
 -->
 (S1 ^operator O2153 = 0.5231192467369606)
Retracting rl*prefer*rvt*predict-yes*H0*1*H1*21
 -->
 (S1 ^operator O2153 = 0.3)

--- END Proposal Phase ---

--- Decision Phase ---
RL update rl*prefer*rvt*predict-no*H0*2 0.631495 -0.376482 0.255013 -> 0.631495 -0.376482 0.255013(R,m,v=1,0.921569,0.072636)
RL update rl*prefer*rvt*predict-no*H0*2*H1*12 0.368505 0.376482 0.744987 -> 0.368505 0.376482 0.744987(R,m,v=1,1,0)
=>WM: (15147: S1 ^operator O2156)

  1078:    O: O2156 (predict-no)
--- END Decision Phase ---

--- Application Phase ---
	--- Firing Productions (PE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing apply*operator
 -->
 (I3 ^predict-no N1078 +  :O )
Firing apply*operator*complete
 -->
 (I3 ^predict-no N1077 -  :O )
 inner elaboration loop at bottom goal.
	--- Change Working Memory (PE) ---
=>WM: (15148: I3 ^predict-no N1078)
<=WM: (15136: N1077 ^status complete)
<=WM: (15135: I3 ^predict-no N1077)
	--- Firing Productions (IE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing monitor*world
 -->

I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
	--- Change Working Memory (IE) ---

--- END Application Phase ---
--- Output Phase ---
ENV: Agent did: predict-no for direction L in state State-A
In  State-A moving L
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isR
--- END Output Phase ---
-/|--- Input Phase --- 
=>WM: (15152: I2 ^dir R)
=>WM: (15151: I2 ^reward 1)
=>WM: (15150: I2 ^see 0)
=>WM: (15149: N1078 ^status complete)
<=WM: (15139: I2 ^dir L)
<=WM: (15138: I2 ^reward 1)
<=WM: (15137: I2 ^see 0)
=>WM: (15153: I2 ^level-1 L0-root)
<=WM: (15140: I2 ^level-1 L0-root)

--- END Input Phase --- 

--- Proposal Phase ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing rl*prefer*rvt*predict-yes*H0*3*H1*14
 -->
 (S1 ^operator O2155 = 0.6170678009401356)
Firing rl*prefer*rvt*predict-no*H0*4*H1*13
 -->
 (S1 ^operator O2156 = 0.4910065094545203)
Firing prefer*rvt*predict-no*H0*4*H1
 -->
Firing prefer*rvt*predict-yes*H0*3*H1
 -->
Firing elaborate*copy-see-to-output-link
 -->
 (I3 ^see 0 +)
Firing elaborate*reward*based*on*reward
 -->
 (R1082 ^value 1 +)
 (R1 ^reward R1082 +)
Firing propose*predict-yes
 -->
 (O2157 ^name predict-yes +)
 (S1 ^operator O2157 +)
Firing propose*predict-no
 -->
 (O2158 ^name predict-no +)
 (S1 ^operator O2158 +)
Firing rl*prefer*rvt*predict-no*H0*4
 -->
 (S1 ^operator O2156 = 0.1269768291953184)
Firing rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O2155 = 0.3829444697344545)
Firing prefer*rvt*predict-yes*H0
 -->
Firing prefer*rvt*predict-no*H0
 -->
Firing elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir R +)
 inner elaboration loop at bottom goal.
Retracting elaborate*copy-see-to-output-link
 -->
 (I3 ^see 0 +)
Retracting propose*predict-no
 -->
 (O2156 ^name predict-no +)
 (S1 ^operator O2156 +)
Retracting propose*predict-yes
 -->
 (O2155 ^name predict-yes +)
 (S1 ^operator O2155 +)
Retracting elaborate*reward*based*on*reward
 -->
 (R1081 ^value 1 +)
 (R1 ^reward R1081 +)
Retracting elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir L +)
Retracting rl*prefer*rvt*predict-no*H0*2*H1*12
 -->
 (S1 ^operator O2156 = 0.7449866519814452)
Retracting rl*prefer*rvt*predict-no*H0*2
 -->
 (S1 ^operator O2156 = 0.2550133931590357)
Retracting rl*prefer*rvt*predict-yes*H0*1*H1*21
 -->
 (S1 ^operator O2155 = 0.3)
Retracting rl*prefer*rvt*predict-yes*H0*1
 -->
 (S1 ^operator O2155 = 0.5231192467369606)
=>WM: (15160: S1 ^operator O2158 +)
=>WM: (15159: S1 ^operator O2157 +)
=>WM: (15158: I3 ^dir R)
=>WM: (15157: O2158 ^name predict-no)
=>WM: (15156: O2157 ^name predict-yes)
=>WM: (15155: R1082 ^value 1)
=>WM: (15154: R1 ^reward R1082)
<=WM: (15145: S1 ^operator O2155 +)
<=WM: (15146: S1 ^operator O2156 +)
<=WM: (15147: S1 ^operator O2156)
<=WM: (15090: I3 ^dir L)
<=WM: (15141: R1 ^reward R1081)
<=WM: (15144: O2156 ^name predict-no)
<=WM: (15143: O2155 ^name predict-yes)
<=WM: (15142: R1081 ^value 1)

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing prefer*rvt*predict-yes*H0
 -->
Firing rl*prefer*rvt*predict-yes*H0*3*H1*14
 -->
 (S1 ^operator O2157 = 0.6170678009401356)
Firing rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O2157 = 0.3829444697344545)
Firing prefer*rvt*predict-yes*H0*3*H1
 -->
Firing prefer*rvt*predict-no*H0
 -->
Firing rl*prefer*rvt*predict-no*H0*4*H1*13
 -->
 (S1 ^operator O2158 = 0.4910065094545203)
Firing rl*prefer*rvt*predict-no*H0*4
 -->
 (S1 ^operator O2158 = 0.1269768291953184)
Firing prefer*rvt*predict-no*H0*4*H1
 -->
 inner elaboration loop at bottom goal.
Retracting rl*prefer*rvt*predict-no*H0*4
 -->
 (S1 ^operator O2156 = 0.1269768291953184)
Retracting rl*prefer*rvt*predict-no*H0*4*H1*13
 -->
 (S1 ^operator O2156 = 0.4910065094545203)
Retracting rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O2155 = 0.3829444697344545)
Retracting rl*prefer*rvt*predict-yes*H0*3*H1*14
 -->
 (S1 ^operator O2155 = 0.6170678009401356)

--- END Proposal Phase ---

--- Decision Phase ---
RL update rl*prefer*rvt*predict-no*H0*2 0.631495 -0.376482 0.255013 -> 0.631495 -0.376482 0.255013(R,m,v=1,0.921951,0.0723099)
RL update rl*prefer*rvt*predict-no*H0*2*H1*12 0.368505 0.376482 0.744987 -> 0.368505 0.376482 0.744987(R,m,v=1,1,0)
=>WM: (15161: S1 ^operator O2157)

  1079:    O: O2157 (predict-yes)
--- END Decision Phase ---

--- Application Phase ---
	--- Firing Productions (PE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing apply*operator
 -->
 (I3 ^predict-yes N1079 +  :O )
Firing apply*operator*complete
 -->
 (I3 ^predict-no N1078 -  :O )
 inner elaboration loop at bottom goal.
	--- Change Working Memory (PE) ---
=>WM: (15162: I3 ^predict-yes N1079)
<=WM: (15149: N1078 ^status complete)
<=WM: (15148: I3 ^predict-no N1078)
	--- Firing Productions (IE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing monitor*world
 -->

I see 1 and I'm going to do: predict-yes inner elaboration loop at bottom goal.
	--- Change Working Memory (IE) ---

--- END Application Phase ---
--- Output Phase ---
ENV: Agent did: predict-yes for direction R in state State-A
In  State-A moving R
ENV: (next state, see, prediction correct?) = (State-B, 1, True)
predict error 0
dir: dir isU
--- END Output Phase ---
\-/--- Input Phase --- 
=>WM: (15166: I2 ^dir U)
=>WM: (15165: I2 ^reward 1)
=>WM: (15164: I2 ^see 1)
=>WM: (15163: N1079 ^status complete)
<=WM: (15152: I2 ^dir R)
<=WM: (15151: I2 ^reward 1)
<=WM: (15150: I2 ^see 0)
=>WM: (15167: I2 ^level-1 R1-root)
<=WM: (15153: I2 ^level-1 L0-root)

--- END Input Phase --- 

--- Proposal Phase ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing elaborate*copy-see-to-output-link
 -->
 (I3 ^see 1 +)
Firing elaborate*reward*based*on*reward
 -->
 (R1083 ^value 1 +)
 (R1 ^reward R1083 +)
Firing propose*predict-yes
 -->
 (O2159 ^name predict-yes +)
 (S1 ^operator O2159 +)
Firing propose*predict-no
 -->
 (O2160 ^name predict-no +)
 (S1 ^operator O2160 +)
Firing rl*prefer*rvt*predict-no*H0*6
 -->
 (S1 ^operator O2158 = 0.9999999999999999)
Firing rl*prefer*rvt*predict-yes*H0*5
 -->
 (S1 ^operator O2157 = 0.)
Firing prefer*rvt*predict-yes*H0
 -->
Firing prefer*rvt*predict-no*H0
 -->
Firing elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir U +)
 inner elaboration loop at bottom goal.
Retracting elaborate*copy-see-to-output-link
 -->
 (I3 ^see 0 +)
Retracting propose*predict-no
 -->
 (O2158 ^name predict-no +)
 (S1 ^operator O2158 +)
Retracting propose*predict-yes
 -->
 (O2157 ^name predict-yes +)
 (S1 ^operator O2157 +)
Retracting elaborate*reward*based*on*reward
 -->
 (R1082 ^value 1 +)
 (R1 ^reward R1082 +)
Retracting elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir R +)
Retracting rl*prefer*rvt*predict-no*H0*4
 -->
 (S1 ^operator O2158 = 0.1269768291953184)
Retracting rl*prefer*rvt*predict-no*H0*4*H1*13
 -->
 (S1 ^operator O2158 = 0.4910065094545203)
Retracting rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O2157 = 0.3829444697344545)
Retracting rl*prefer*rvt*predict-yes*H0*3*H1*14
 -->
 (S1 ^operator O2157 = 0.6170678009401356)
=>WM: (15175: S1 ^operator O2160 +)
=>WM: (15174: S1 ^operator O2159 +)
=>WM: (15173: I3 ^dir U)
=>WM: (15172: O2160 ^name predict-no)
=>WM: (15171: O2159 ^name predict-yes)
=>WM: (15170: R1083 ^value 1)
=>WM: (15169: R1 ^reward R1083)
=>WM: (15168: I3 ^see 1)
<=WM: (15159: S1 ^operator O2157 +)
<=WM: (15161: S1 ^operator O2157)
<=WM: (15160: S1 ^operator O2158 +)
<=WM: (15158: I3 ^dir R)
<=WM: (15154: R1 ^reward R1082)
<=WM: (15114: I3 ^see 0)
<=WM: (15157: O2158 ^name predict-no)
<=WM: (15156: O2157 ^name predict-yes)
<=WM: (15155: R1082 ^value 1)

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing prefer*rvt*predict-yes*H0
 -->
Firing rl*prefer*rvt*predict-yes*H0*5
 -->
 (S1 ^operator O2159 = 0.)
Firing prefer*rvt*predict-no*H0
 -->
Firing rl*prefer*rvt*predict-no*H0*6
 -->
 (S1 ^operator O2160 = 0.9999999999999999)
 inner elaboration loop at bottom goal.
Retracting rl*prefer*rvt*predict-no*H0*6
 -->
 (S1 ^operator O2158 = 0.9999999999999999)
Retracting rl*prefer*rvt*predict-yes*H0*5
 -->
 (S1 ^operator O2157 = 0.)

--- END Proposal Phase ---

--- Decision Phase ---
RL update rl*prefer*rvt*predict-yes*H0*3 0.673137 -0.290193 0.382944 -> 0.673136 -0.290193 0.382943(R,m,v=1,0.963855,0.0350493)
RL update rl*prefer*rvt*predict-yes*H0*3*H1*14 0.326874 0.290194 0.617068 -> 0.326872 0.290194 0.617066(R,m,v=1,1,0)
=>WM: (15176: S1 ^operator O2160)

  1080:    O: O2160 (predict-no)
--- END Decision Phase ---

--- Application Phase ---
	--- Firing Productions (PE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing apply*operator
 -->
 (I3 ^predict-no N1080 +  :O )
Firing apply*operator*complete
 -->
 (I3 ^predict-yes N1079 -  :O )
 inner elaboration loop at bottom goal.
	--- Change Working Memory (PE) ---
=>WM: (15177: I3 ^predict-no N1080)
<=WM: (15163: N1079 ^status complete)
<=WM: (15162: I3 ^predict-yes N1079)
	--- Firing Productions (IE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing monitor*world
 -->

I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
	--- Change Working Memory (IE) ---

--- END Application Phase ---
--- Output Phase ---
ENV: Agent did: predict-no for direction U in state State-B
In  State-B moving U
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isR
--- END Output Phase ---
|\---- Input Phase --- 
=>WM: (15181: I2 ^dir R)
=>WM: (15180: I2 ^reward 1)
=>WM: (15179: I2 ^see 0)
=>WM: (15178: N1080 ^status complete)
<=WM: (15166: I2 ^dir U)
<=WM: (15165: I2 ^reward 1)
<=WM: (15164: I2 ^see 1)
=>WM: (15182: I2 ^level-1 R1-root)
<=WM: (15167: I2 ^level-1 R1-root)

--- END Input Phase --- 

--- Proposal Phase ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing rl*prefer*rvt*predict-yes*H0*3*H1*16
 -->
 (S1 ^operator O2159 = 0.08783148430849691)
Firing rl*prefer*rvt*predict-no*H0*4*H1*15
 -->
 (S1 ^operator O2160 = 0.8730232195176179)
Firing prefer*rvt*predict-no*H0*4*H1
 -->
Firing prefer*rvt*predict-yes*H0*3*H1
 -->
Firing elaborate*copy-see-to-output-link
 -->
 (I3 ^see 0 +)
Firing elaborate*reward*based*on*reward
 -->
 (R1084 ^value 1 +)
 (R1 ^reward R1084 +)
Firing propose*predict-yes
 -->
 (O2161 ^name predict-yes +)
 (S1 ^operator O2161 +)
Firing propose*predict-no
 -->
 (O2162 ^name predict-no +)
 (S1 ^operator O2162 +)
Firing rl*prefer*rvt*predict-no*H0*4
 -->
 (S1 ^operator O2160 = 0.1269768291953184)
Firing rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O2159 = 0.382942629133266)
Firing prefer*rvt*predict-yes*H0
 -->
Firing prefer*rvt*predict-no*H0
 -->
Firing elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir R +)
 inner elaboration loop at bottom goal.
Retracting elaborate*copy-see-to-output-link
 -->
 (I3 ^see 1 +)
Retracting propose*predict-no
 -->
 (O2160 ^name predict-no +)
 (S1 ^operator O2160 +)
Retracting propose*predict-yes
 -->
 (O2159 ^name predict-yes +)
 (S1 ^operator O2159 +)
Retracting elaborate*reward*based*on*reward
 -->
 (R1083 ^value 1 +)
 (R1 ^reward R1083 +)
Retracting elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir U +)
Retracting rl*prefer*rvt*predict-no*H0*6
 -->
 (S1 ^operator O2160 = 0.9999999999999999)
Retracting rl*prefer*rvt*predict-yes*H0*5
 -->
 (S1 ^operator O2159 = 0.)
=>WM: (15190: S1 ^operator O2162 +)
=>WM: (15189: S1 ^operator O2161 +)
=>WM: (15188: I3 ^dir R)
=>WM: (15187: O2162 ^name predict-no)
=>WM: (15186: O2161 ^name predict-yes)
=>WM: (15185: R1084 ^value 1)
=>WM: (15184: R1 ^reward R1084)
=>WM: (15183: I3 ^see 0)
<=WM: (15174: S1 ^operator O2159 +)
<=WM: (15175: S1 ^operator O2160 +)
<=WM: (15176: S1 ^operator O2160)
<=WM: (15173: I3 ^dir U)
<=WM: (15169: R1 ^reward R1083)
<=WM: (15168: I3 ^see 1)
<=WM: (15172: O2160 ^name predict-no)
<=WM: (15171: O2159 ^name predict-yes)
<=WM: (15170: R1083 ^value 1)

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing prefer*rvt*predict-yes*H0
 -->
Firing rl*prefer*rvt*predict-yes*H0*3*H1*16
 -->
 (S1 ^operator O2161 = 0.08783148430849691)
Firing rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O2161 = 0.382942629133266)
Firing prefer*rvt*predict-yes*H0*3*H1
 -->
Firing prefer*rvt*predict-no*H0
 -->
Firing rl*prefer*rvt*predict-no*H0*4*H1*15
 -->
 (S1 ^operator O2162 = 0.8730232195176179)
Firing rl*prefer*rvt*predict-no*H0*4
 -->
 (S1 ^operator O2162 = 0.1269768291953184)
Firing prefer*rvt*predict-no*H0*4*H1
 -->
 inner elaboration loop at bottom goal.
Retracting rl*prefer*rvt*predict-no*H0*4
 -->
 (S1 ^operator O2160 = 0.1269768291953184)
Retracting rl*prefer*rvt*predict-no*H0*4*H1*15
 -->
 (S1 ^operator O2160 = 0.8730232195176179)
Retracting rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O2159 = 0.382942629133266)
Retracting rl*prefer*rvt*predict-yes*H0*3*H1*16
 -->
 (S1 ^operator O2159 = 0.08783148430849691)

--- END Proposal Phase ---

--- Decision Phase ---
RL update rl*prefer*rvt*predict-no*H0*6 1 0 1 -> 1 0 1(R,m,v=1,1,0)
=>WM: (15191: S1 ^operator O2162)

  1081:    O: O2162 (predict-no)
--- END Decision Phase ---

--- Application Phase ---
	--- Firing Productions (PE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing apply*operator
 -->
 (I3 ^predict-no N1081 +  :O )
Firing apply*operator*complete
 -->
 (I3 ^predict-no N1080 -  :O )
 inner elaboration loop at bottom goal.
	--- Change Working Memory (PE) ---
=>WM: (15192: I3 ^predict-no N1081)
<=WM: (15178: N1080 ^status complete)
<=WM: (15177: I3 ^predict-no N1080)
	--- Firing Productions (IE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing monitor*world
 -->

I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
	--- Change Working Memory (IE) ---

--- END Application Phase ---
--- Output Phase ---
ENV: Agent did: predict-no for direction R in state State-B
In  State-B moving R
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isU
--- END Output Phase ---
/--- Input Phase --- 
=>WM: (15196: I2 ^dir U)
=>WM: (15195: I2 ^reward 1)
=>WM: (15194: I2 ^see 0)
=>WM: (15193: N1081 ^status complete)
<=WM: (15181: I2 ^dir R)
<=WM: (15180: I2 ^reward 1)
<=WM: (15179: I2 ^see 0)
=>WM: (15197: I2 ^level-1 R0-root)
<=WM: (15182: I2 ^level-1 R1-root)

--- END Input Phase --- 

--- Proposal Phase ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing elaborate*copy-see-to-output-link
 -->
 (I3 ^see 0 +)
Firing elaborate*reward*based*on*reward
 -->
 (R1085 ^value 1 +)
 (R1 ^reward R1085 +)
Firing propose*predict-yes
 -->
 (O2163 ^name predict-yes +)
 (S1 ^operator O2163 +)
Firing propose*predict-no
 -->
 (O2164 ^name predict-no +)
 (S1 ^operator O2164 +)
Firing rl*prefer*rvt*predict-no*H0*6
 -->
 (S1 ^operator O2162 = 0.9999999999999999)
Firing rl*prefer*rvt*predict-yes*H0*5
 -->
 (S1 ^operator O2161 = 0.)
Firing prefer*rvt*predict-yes*H0
 -->
Firing prefer*rvt*predict-no*H0
 -->
Firing elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir U +)
 inner elaboration loop at bottom goal.
Retracting elaborate*copy-see-to-output-link
 -->
 (I3 ^see 0 +)
Retracting propose*predict-no
 -->
 (O2162 ^name predict-no +)
 (S1 ^operator O2162 +)
Retracting propose*predict-yes
 -->
 (O2161 ^name predict-yes +)
 (S1 ^operator O2161 +)
Retracting elaborate*reward*based*on*reward
 -->
 (R1084 ^value 1 +)
 (R1 ^reward R1084 +)
Retracting elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir R +)
Retracting rl*prefer*rvt*predict-no*H0*4
 -->
 (S1 ^operator O2162 = 0.1269768291953184)
Retracting rl*prefer*rvt*predict-no*H0*4*H1*15
 -->
 (S1 ^operator O2162 = 0.8730232195176179)
Retracting rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O2161 = 0.382942629133266)
Retracting rl*prefer*rvt*predict-yes*H0*3*H1*16
 -->
 (S1 ^operator O2161 = 0.08783148430849691)
=>WM: (15204: S1 ^operator O2164 +)
=>WM: (15203: S1 ^operator O2163 +)
=>WM: (15202: I3 ^dir U)
=>WM: (15201: O2164 ^name predict-no)
=>WM: (15200: O2163 ^name predict-yes)
=>WM: (15199: R1085 ^value 1)
=>WM: (15198: R1 ^reward R1085)
<=WM: (15189: S1 ^operator O2161 +)
<=WM: (15190: S1 ^operator O2162 +)
<=WM: (15191: S1 ^operator O2162)
<=WM: (15188: I3 ^dir R)
<=WM: (15184: R1 ^reward R1084)
<=WM: (15187: O2162 ^name predict-no)
<=WM: (15186: O2161 ^name predict-yes)
<=WM: (15185: R1084 ^value 1)

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing prefer*rvt*predict-yes*H0
 -->
Firing rl*prefer*rvt*predict-yes*H0*5
 -->
 (S1 ^operator O2163 = 0.)
Firing prefer*rvt*predict-no*H0
 -->
Firing rl*prefer*rvt*predict-no*H0*6
 -->
 (S1 ^operator O2164 = 0.9999999999999999)
 inner elaboration loop at bottom goal.
Retracting rl*prefer*rvt*predict-no*H0*6
 -->
 (S1 ^operator O2162 = 0.9999999999999999)
Retracting rl*prefer*rvt*predict-yes*H0*5
 -->
 (S1 ^operator O2161 = 0.)

--- END Proposal Phase ---

--- Decision Phase ---
RL update rl*prefer*rvt*predict-no*H0*4 0.814714 -0.687737 0.126977 -> 0.814714 -0.687737 0.126977(R,m,v=1,0.954315,0.0438206)
RL update rl*prefer*rvt*predict-no*H0*4*H1*15 0.185286 0.687737 0.873023 -> 0.185286 0.687737 0.873023(R,m,v=1,1,0)
=>WM: (15205: S1 ^operator O2164)

  1082:    O: O2164 (predict-no)
--- END Decision Phase ---

--- Application Phase ---
	--- Firing Productions (PE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing apply*operator
 -->
 (I3 ^predict-no N1082 +  :O )
Firing apply*operator*complete
 -->
 (I3 ^predict-no N1081 -  :O )
 inner elaboration loop at bottom goal.
	--- Change Working Memory (PE) ---
=>WM: (15206: I3 ^predict-no N1082)
<=WM: (15193: N1081 ^status complete)
<=WM: (15192: I3 ^predict-no N1081)
	--- Firing Productions (IE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing monitor*world
 -->

I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
	--- Change Working Memory (IE) ---

--- END Application Phase ---
--- Output Phase ---
ENV: Agent did: predict-no for direction U in state State-B
In  State-B moving U
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isU
--- END Output Phase ---
|\---- Input Phase --- 
=>WM: (15210: I2 ^dir U)
=>WM: (15209: I2 ^reward 1)
=>WM: (15208: I2 ^see 0)
=>WM: (15207: N1082 ^status complete)
<=WM: (15196: I2 ^dir U)
<=WM: (15195: I2 ^reward 1)
<=WM: (15194: I2 ^see 0)
=>WM: (15211: I2 ^level-1 R0-root)
<=WM: (15197: I2 ^level-1 R0-root)

--- END Input Phase --- 

--- Proposal Phase ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing elaborate*copy-see-to-output-link
 -->
 (I3 ^see 0 +)
Firing elaborate*reward*based*on*reward
 -->
 (R1086 ^value 1 +)
 (R1 ^reward R1086 +)
Firing propose*predict-yes
 -->
 (O2165 ^name predict-yes +)
 (S1 ^operator O2165 +)
Firing propose*predict-no
 -->
 (O2166 ^name predict-no +)
 (S1 ^operator O2166 +)
Firing rl*prefer*rvt*predict-no*H0*6
 -->
 (S1 ^operator O2164 = 0.9999999999999999)
Firing rl*prefer*rvt*predict-yes*H0*5
 -->
 (S1 ^operator O2163 = 0.)
Firing prefer*rvt*predict-yes*H0
 -->
Firing prefer*rvt*predict-no*H0
 -->
Firing elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir U +)
 inner elaboration loop at bottom goal.
Retracting elaborate*copy-see-to-output-link
 -->
 (I3 ^see 0 +)
Retracting propose*predict-no
 -->
 (O2164 ^name predict-no +)
 (S1 ^operator O2164 +)
Retracting propose*predict-yes
 -->
 (O2163 ^name predict-yes +)
 (S1 ^operator O2163 +)
Retracting elaborate*reward*based*on*reward
 -->
 (R1085 ^value 1 +)
 (R1 ^reward R1085 +)
Retracting elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir U +)
Retracting rl*prefer*rvt*predict-no*H0*6
 -->
 (S1 ^operator O2164 = 0.9999999999999999)
Retracting rl*prefer*rvt*predict-yes*H0*5
 -->
 (S1 ^operator O2163 = 0.)
=>WM: (15217: S1 ^operator O2166 +)
=>WM: (15216: S1 ^operator O2165 +)
=>WM: (15215: O2166 ^name predict-no)
=>WM: (15214: O2165 ^name predict-yes)
=>WM: (15213: R1086 ^value 1)
=>WM: (15212: R1 ^reward R1086)
<=WM: (15203: S1 ^operator O2163 +)
<=WM: (15204: S1 ^operator O2164 +)
<=WM: (15205: S1 ^operator O2164)
<=WM: (15198: R1 ^reward R1085)
<=WM: (15201: O2164 ^name predict-no)
<=WM: (15200: O2163 ^name predict-yes)
<=WM: (15199: R1085 ^value 1)

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing prefer*rvt*predict-yes*H0
 -->
Firing rl*prefer*rvt*predict-yes*H0*5
 -->
 (S1 ^operator O2165 = 0.)
Firing prefer*rvt*predict-no*H0
 -->
Firing rl*prefer*rvt*predict-no*H0*6
 -->
 (S1 ^operator O2166 = 0.9999999999999999)
 inner elaboration loop at bottom goal.
Retracting rl*prefer*rvt*predict-no*H0*6
 -->
 (S1 ^operator O2164 = 0.9999999999999999)
Retracting rl*prefer*rvt*predict-yes*H0*5
 -->
 (S1 ^operator O2163 = 0.)

--- END Proposal Phase ---

--- Decision Phase ---
RL update rl*prefer*rvt*predict-no*H0*6 1 0 1 -> 1 0 1(R,m,v=1,1,0)
=>WM: (15218: S1 ^operator O2166)

  1083:    O: O2166 (predict-no)
--- END Decision Phase ---

--- Application Phase ---
	--- Firing Productions (PE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing apply*operator
 -->
 (I3 ^predict-no N1083 +  :O )
Firing apply*operator*complete
 -->
 (I3 ^predict-no N1082 -  :O )
 inner elaboration loop at bottom goal.
	--- Change Working Memory (PE) ---
=>WM: (15219: I3 ^predict-no N1083)
<=WM: (15207: N1082 ^status complete)
<=WM: (15206: I3 ^predict-no N1082)
	--- Firing Productions (IE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing monitor*world
 -->

I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
	--- Change Working Memory (IE) ---

--- END Application Phase ---
--- Output Phase ---
ENV: Agent did: predict-no for direction U in state State-B
In  State-B moving U
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isU
--- END Output Phase ---
/|\--- Input Phase --- 
=>WM: (15223: I2 ^dir U)
=>WM: (15222: I2 ^reward 1)
=>WM: (15221: I2 ^see 0)
=>WM: (15220: N1083 ^status complete)
<=WM: (15210: I2 ^dir U)
<=WM: (15209: I2 ^reward 1)
<=WM: (15208: I2 ^see 0)
=>WM: (15224: I2 ^level-1 R0-root)
<=WM: (15211: I2 ^level-1 R0-root)

--- END Input Phase --- 

--- Proposal Phase ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing elaborate*copy-see-to-output-link
 -->
 (I3 ^see 0 +)
Firing elaborate*reward*based*on*reward
 -->
 (R1087 ^value 1 +)
 (R1 ^reward R1087 +)
Firing propose*predict-yes
 -->
 (O2167 ^name predict-yes +)
 (S1 ^operator O2167 +)
Firing propose*predict-no
 -->
 (O2168 ^name predict-no +)
 (S1 ^operator O2168 +)
Firing rl*prefer*rvt*predict-no*H0*6
 -->
 (S1 ^operator O2166 = 0.9999999999999999)
Firing rl*prefer*rvt*predict-yes*H0*5
 -->
 (S1 ^operator O2165 = 0.)
Firing prefer*rvt*predict-yes*H0
 -->
Firing prefer*rvt*predict-no*H0
 -->
Firing elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir U +)
 inner elaboration loop at bottom goal.
Retracting elaborate*copy-see-to-output-link
 -->
 (I3 ^see 0 +)
Retracting propose*predict-no
 -->
 (O2166 ^name predict-no +)
 (S1 ^operator O2166 +)
Retracting propose*predict-yes
 -->
 (O2165 ^name predict-yes +)
 (S1 ^operator O2165 +)
Retracting elaborate*reward*based*on*reward
 -->
 (R1086 ^value 1 +)
 (R1 ^reward R1086 +)
Retracting elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir U +)
Retracting rl*prefer*rvt*predict-no*H0*6
 -->
 (S1 ^operator O2166 = 0.9999999999999999)
Retracting rl*prefer*rvt*predict-yes*H0*5
 -->
 (S1 ^operator O2165 = 0.)
=>WM: (15230: S1 ^operator O2168 +)
=>WM: (15229: S1 ^operator O2167 +)
=>WM: (15228: O2168 ^name predict-no)
=>WM: (15227: O2167 ^name predict-yes)
=>WM: (15226: R1087 ^value 1)
=>WM: (15225: R1 ^reward R1087)
<=WM: (15216: S1 ^operator O2165 +)
<=WM: (15217: S1 ^operator O2166 +)
<=WM: (15218: S1 ^operator O2166)
<=WM: (15212: R1 ^reward R1086)
<=WM: (15215: O2166 ^name predict-no)
<=WM: (15214: O2165 ^name predict-yes)
<=WM: (15213: R1086 ^value 1)

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing prefer*rvt*predict-yes*H0
 -->
Firing rl*prefer*rvt*predict-yes*H0*5
 -->
 (S1 ^operator O2167 = 0.)
Firing prefer*rvt*predict-no*H0
 -->
Firing rl*prefer*rvt*predict-no*H0*6
 -->
 (S1 ^operator O2168 = 0.9999999999999999)
 inner elaboration loop at bottom goal.
Retracting rl*prefer*rvt*predict-no*H0*6
 -->
 (S1 ^operator O2166 = 0.9999999999999999)
Retracting rl*prefer*rvt*predict-yes*H0*5
 -->
 (S1 ^operator O2165 = 0.)

--- END Proposal Phase ---

--- Decision Phase ---
RL update rl*prefer*rvt*predict-no*H0*6 1 0 1 -> 1 0 1(R,m,v=1,1,0)
=>WM: (15231: S1 ^operator O2168)

  1084:    O: O2168 (predict-no)
--- END Decision Phase ---

--- Application Phase ---
	--- Firing Productions (PE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing apply*operator
 -->
 (I3 ^predict-no N1084 +  :O )
Firing apply*operator*complete
 -->
 (I3 ^predict-no N1083 -  :O )
 inner elaboration loop at bottom goal.
	--- Change Working Memory (PE) ---
=>WM: (15232: I3 ^predict-no N1084)
<=WM: (15220: N1083 ^status complete)
<=WM: (15219: I3 ^predict-no N1083)
	--- Firing Productions (IE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing monitor*world
 -->

I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
	--- Change Working Memory (IE) ---

--- END Application Phase ---
--- Output Phase ---
ENV: Agent did: predict-no for direction U in state State-B
In  State-B moving U
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isU
--- END Output Phase ---
-/|\--- Input Phase --- 
=>WM: (15236: I2 ^dir U)
=>WM: (15235: I2 ^reward 1)
=>WM: (15234: I2 ^see 0)
=>WM: (15233: N1084 ^status complete)
<=WM: (15223: I2 ^dir U)
<=WM: (15222: I2 ^reward 1)
<=WM: (15221: I2 ^see 0)
=>WM: (15237: I2 ^level-1 R0-root)
<=WM: (15224: I2 ^level-1 R0-root)

--- END Input Phase --- 

--- Proposal Phase ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing elaborate*copy-see-to-output-link
 -->
 (I3 ^see 0 +)
Firing elaborate*reward*based*on*reward
 -->
 (R1088 ^value 1 +)
 (R1 ^reward R1088 +)
Firing propose*predict-yes
 -->
 (O2169 ^name predict-yes +)
 (S1 ^operator O2169 +)
Firing propose*predict-no
 -->
 (O2170 ^name predict-no +)
 (S1 ^operator O2170 +)
Firing rl*prefer*rvt*predict-no*H0*6
 -->
 (S1 ^operator O2168 = 0.9999999999999999)
Firing rl*prefer*rvt*predict-yes*H0*5
 -->
 (S1 ^operator O2167 = 0.)
Firing prefer*rvt*predict-yes*H0
 -->
Firing prefer*rvt*predict-no*H0
 -->
Firing elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir U +)
 inner elaboration loop at bottom goal.
Retracting elaborate*copy-see-to-output-link
 -->
 (I3 ^see 0 +)
Retracting propose*predict-no
 -->
 (O2168 ^name predict-no +)
 (S1 ^operator O2168 +)
Retracting propose*predict-yes
 -->
 (O2167 ^name predict-yes +)
 (S1 ^operator O2167 +)
Retracting elaborate*reward*based*on*reward
 -->
 (R1087 ^value 1 +)
 (R1 ^reward R1087 +)
Retracting elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir U +)
Retracting rl*prefer*rvt*predict-no*H0*6
 -->
 (S1 ^operator O2168 = 0.9999999999999999)
Retracting rl*prefer*rvt*predict-yes*H0*5
 -->
 (S1 ^operator O2167 = 0.)
=>WM: (15243: S1 ^operator O2170 +)
=>WM: (15242: S1 ^operator O2169 +)
=>WM: (15241: O2170 ^name predict-no)
=>WM: (15240: O2169 ^name predict-yes)
=>WM: (15239: R1088 ^value 1)
=>WM: (15238: R1 ^reward R1088)
<=WM: (15229: S1 ^operator O2167 +)
<=WM: (15230: S1 ^operator O2168 +)
<=WM: (15231: S1 ^operator O2168)
<=WM: (15225: R1 ^reward R1087)
<=WM: (15228: O2168 ^name predict-no)
<=WM: (15227: O2167 ^name predict-yes)
<=WM: (15226: R1087 ^value 1)

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing prefer*rvt*predict-yes*H0
 -->
Firing rl*prefer*rvt*predict-yes*H0*5
 -->
 (S1 ^operator O2169 = 0.)
Firing prefer*rvt*predict-no*H0
 -->
Firing rl*prefer*rvt*predict-no*H0*6
 -->
 (S1 ^operator O2170 = 0.9999999999999999)
 inner elaboration loop at bottom goal.
Retracting rl*prefer*rvt*predict-no*H0*6
 -->
 (S1 ^operator O2168 = 0.9999999999999999)
Retracting rl*prefer*rvt*predict-yes*H0*5
 -->
 (S1 ^operator O2167 = 0.)

--- END Proposal Phase ---

--- Decision Phase ---
RL update rl*prefer*rvt*predict-no*H0*6 1 0 1 -> 1 0 1(R,m,v=1,1,0)
=>WM: (15244: S1 ^operator O2170)

  1085:    O: O2170 (predict-no)
--- END Decision Phase ---

--- Application Phase ---
	--- Firing Productions (PE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing apply*operator
 -->
 (I3 ^predict-no N1085 +  :O )
Firing apply*operator*complete
 -->
 (I3 ^predict-no N1084 -  :O )
 inner elaboration loop at bottom goal.
	--- Change Working Memory (PE) ---
=>WM: (15245: I3 ^predict-no N1085)
<=WM: (15233: N1084 ^status complete)
<=WM: (15232: I3 ^predict-no N1084)
	--- Firing Productions (IE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing monitor*world
 -->

I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
	--- Change Working Memory (IE) ---

--- END Application Phase ---
--- Output Phase ---
ENV: Agent did: predict-no for direction U in state State-B
In  State-B moving U
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isR
--- END Output Phase ---
-/|--- Input Phase --- 
=>WM: (15249: I2 ^dir R)
=>WM: (15248: I2 ^reward 1)
=>WM: (15247: I2 ^see 0)
=>WM: (15246: N1085 ^status complete)
<=WM: (15236: I2 ^dir U)
<=WM: (15235: I2 ^reward 1)
<=WM: (15234: I2 ^see 0)
=>WM: (15250: I2 ^level-1 R0-root)
<=WM: (15237: I2 ^level-1 R0-root)

--- END Input Phase --- 

--- Proposal Phase ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing rl*prefer*rvt*predict-yes*H0*3*H1*18
 -->
 (S1 ^operator O2169 = 0.2696941111808541)
Firing rl*prefer*rvt*predict-no*H0*4*H1*17
 -->
 (S1 ^operator O2170 = 0.8730231400765728)
Firing prefer*rvt*predict-no*H0*4*H1
 -->
Firing prefer*rvt*predict-yes*H0*3*H1
 -->
Firing elaborate*copy-see-to-output-link
 -->
 (I3 ^see 0 +)
Firing elaborate*reward*based*on*reward
 -->
 (R1089 ^value 1 +)
 (R1 ^reward R1089 +)
Firing propose*predict-yes
 -->
 (O2171 ^name predict-yes +)
 (S1 ^operator O2171 +)
Firing propose*predict-no
 -->
 (O2172 ^name predict-no +)
 (S1 ^operator O2172 +)
Firing rl*prefer*rvt*predict-no*H0*4
 -->
 (S1 ^operator O2170 = 0.1269768218883779)
Firing rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O2169 = 0.382942629133266)
Firing prefer*rvt*predict-yes*H0
 -->
Firing prefer*rvt*predict-no*H0
 -->
Firing elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir R +)
 inner elaboration loop at bottom goal.
Retracting elaborate*copy-see-to-output-link
 -->
 (I3 ^see 0 +)
Retracting propose*predict-no
 -->
 (O2170 ^name predict-no +)
 (S1 ^operator O2170 +)
Retracting propose*predict-yes
 -->
 (O2169 ^name predict-yes +)
 (S1 ^operator O2169 +)
Retracting elaborate*reward*based*on*reward
 -->
 (R1088 ^value 1 +)
 (R1 ^reward R1088 +)
Retracting elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir U +)
Retracting rl*prefer*rvt*predict-no*H0*6
 -->
 (S1 ^operator O2170 = 0.9999999999999999)
Retracting rl*prefer*rvt*predict-yes*H0*5
 -->
 (S1 ^operator O2169 = 0.)
=>WM: (15257: S1 ^operator O2172 +)
=>WM: (15256: S1 ^operator O2171 +)
=>WM: (15255: I3 ^dir R)
=>WM: (15254: O2172 ^name predict-no)
=>WM: (15253: O2171 ^name predict-yes)
=>WM: (15252: R1089 ^value 1)
=>WM: (15251: R1 ^reward R1089)
<=WM: (15242: S1 ^operator O2169 +)
<=WM: (15243: S1 ^operator O2170 +)
<=WM: (15244: S1 ^operator O2170)
<=WM: (15202: I3 ^dir U)
<=WM: (15238: R1 ^reward R1088)
<=WM: (15241: O2170 ^name predict-no)
<=WM: (15240: O2169 ^name predict-yes)
<=WM: (15239: R1088 ^value 1)

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing prefer*rvt*predict-yes*H0
 -->
Firing rl*prefer*rvt*predict-yes*H0*3*H1*18
 -->
 (S1 ^operator O2171 = 0.2696941111808541)
Firing rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O2171 = 0.382942629133266)
Firing prefer*rvt*predict-yes*H0*3*H1
 -->
Firing prefer*rvt*predict-no*H0
 -->
Firing rl*prefer*rvt*predict-no*H0*4*H1*17
 -->
 (S1 ^operator O2172 = 0.8730231400765728)
Firing rl*prefer*rvt*predict-no*H0*4
 -->
 (S1 ^operator O2172 = 0.1269768218883779)
Firing prefer*rvt*predict-no*H0*4*H1
 -->
 inner elaboration loop at bottom goal.
Retracting rl*prefer*rvt*predict-no*H0*4
 -->
 (S1 ^operator O2170 = 0.1269768218883779)
Retracting rl*prefer*rvt*predict-no*H0*4*H1*17
 -->
 (S1 ^operator O2170 = 0.8730231400765728)
Retracting rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O2169 = 0.382942629133266)
Retracting rl*prefer*rvt*predict-yes*H0*3*H1*18
 -->
 (S1 ^operator O2169 = 0.2696941111808541)

--- END Proposal Phase ---

--- Decision Phase ---
RL update rl*prefer*rvt*predict-no*H0*6 1 0 1 -> 1 0 1(R,m,v=1,1,0)
=>WM: (15258: S1 ^operator O2172)

  1086:    O: O2172 (predict-no)
--- END Decision Phase ---

--- Application Phase ---
	--- Firing Productions (PE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing apply*operator
 -->
 (I3 ^predict-no N1086 +  :O )
Firing apply*operator*complete
 -->
 (I3 ^predict-no N1085 -  :O )
 inner elaboration loop at bottom goal.
	--- Change Working Memory (PE) ---
=>WM: (15259: I3 ^predict-no N1086)
<=WM: (15246: N1085 ^status complete)
<=WM: (15245: I3 ^predict-no N1085)
	--- Firing Productions (IE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing monitor*world
 -->

I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
	--- Change Working Memory (IE) ---

--- END Application Phase ---
--- Output Phase ---
ENV: Agent did: predict-no for direction R in state State-B
In  State-B moving R
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isU
--- END Output Phase ---
\---- Input Phase --- 
=>WM: (15263: I2 ^dir U)
=>WM: (15262: I2 ^reward 1)
=>WM: (15261: I2 ^see 0)
=>WM: (15260: N1086 ^status complete)
<=WM: (15249: I2 ^dir R)
<=WM: (15248: I2 ^reward 1)
<=WM: (15247: I2 ^see 0)
=>WM: (15264: I2 ^level-1 R0-root)
<=WM: (15250: I2 ^level-1 R0-root)

--- END Input Phase --- 

--- Proposal Phase ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing elaborate*copy-see-to-output-link
 -->
 (I3 ^see 0 +)
Firing elaborate*reward*based*on*reward
 -->
 (R1090 ^value 1 +)
 (R1 ^reward R1090 +)
Firing propose*predict-yes
 -->
 (O2173 ^name predict-yes +)
 (S1 ^operator O2173 +)
Firing propose*predict-no
 -->
 (O2174 ^name predict-no +)
 (S1 ^operator O2174 +)
Firing rl*prefer*rvt*predict-no*H0*6
 -->
 (S1 ^operator O2172 = 0.9999999999999999)
Firing rl*prefer*rvt*predict-yes*H0*5
 -->
 (S1 ^operator O2171 = 0.)
Firing prefer*rvt*predict-yes*H0
 -->
Firing prefer*rvt*predict-no*H0
 -->
Firing elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir U +)
 inner elaboration loop at bottom goal.
Retracting elaborate*copy-see-to-output-link
 -->
 (I3 ^see 0 +)
Retracting propose*predict-no
 -->
 (O2172 ^name predict-no +)
 (S1 ^operator O2172 +)
Retracting propose*predict-yes
 -->
 (O2171 ^name predict-yes +)
 (S1 ^operator O2171 +)
Retracting elaborate*reward*based*on*reward
 -->
 (R1089 ^value 1 +)
 (R1 ^reward R1089 +)
Retracting elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir R +)
Retracting rl*prefer*rvt*predict-no*H0*4
 -->
 (S1 ^operator O2172 = 0.1269768218883779)
Retracting rl*prefer*rvt*predict-no*H0*4*H1*17
 -->
 (S1 ^operator O2172 = 0.8730231400765728)
Retracting rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O2171 = 0.382942629133266)
Retracting rl*prefer*rvt*predict-yes*H0*3*H1*18
 -->
 (S1 ^operator O2171 = 0.2696941111808541)
=>WM: (15271: S1 ^operator O2174 +)
=>WM: (15270: S1 ^operator O2173 +)
=>WM: (15269: I3 ^dir U)
=>WM: (15268: O2174 ^name predict-no)
=>WM: (15267: O2173 ^name predict-yes)
=>WM: (15266: R1090 ^value 1)
=>WM: (15265: R1 ^reward R1090)
<=WM: (15256: S1 ^operator O2171 +)
<=WM: (15257: S1 ^operator O2172 +)
<=WM: (15258: S1 ^operator O2172)
<=WM: (15255: I3 ^dir R)
<=WM: (15251: R1 ^reward R1089)
<=WM: (15254: O2172 ^name predict-no)
<=WM: (15253: O2171 ^name predict-yes)
<=WM: (15252: R1089 ^value 1)

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing prefer*rvt*predict-yes*H0
 -->
Firing rl*prefer*rvt*predict-yes*H0*5
 -->
 (S1 ^operator O2173 = 0.)
Firing prefer*rvt*predict-no*H0
 -->
Firing rl*prefer*rvt*predict-no*H0*6
 -->
 (S1 ^operator O2174 = 0.9999999999999999)
 inner elaboration loop at bottom goal.
Retracting rl*prefer*rvt*predict-no*H0*6
 -->
 (S1 ^operator O2172 = 0.9999999999999999)
Retracting rl*prefer*rvt*predict-yes*H0*5
 -->
 (S1 ^operator O2171 = 0.)

--- END Proposal Phase ---

--- Decision Phase ---
RL update rl*prefer*rvt*predict-no*H0*4 0.814714 -0.687737 0.126977 -> 0.814714 -0.687737 0.126977(R,m,v=1,0.954545,0.0436087)
RL update rl*prefer*rvt*predict-no*H0*4*H1*17 0.185286 0.687737 0.873023 -> 0.185286 0.687737 0.873023(R,m,v=1,1,0)
=>WM: (15272: S1 ^operator O2174)

  1087:    O: O2174 (predict-no)
--- END Decision Phase ---

--- Application Phase ---
	--- Firing Productions (PE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing apply*operator
 -->
 (I3 ^predict-no N1087 +  :O )
Firing apply*operator*complete
 -->
 (I3 ^predict-no N1086 -  :O )
 inner elaboration loop at bottom goal.
	--- Change Working Memory (PE) ---
=>WM: (15273: I3 ^predict-no N1087)
<=WM: (15260: N1086 ^status complete)
<=WM: (15259: I3 ^predict-no N1086)
	--- Firing Productions (IE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing monitor*world
 -->

I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
	--- Change Working Memory (IE) ---

--- END Application Phase ---
--- Output Phase ---
ENV: Agent did: predict-no for direction U in state State-B
In  State-B moving U
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isL
--- END Output Phase ---
/|\--- Input Phase --- 
=>WM: (15277: I2 ^dir L)
=>WM: (15276: I2 ^reward 1)
=>WM: (15275: I2 ^see 0)
=>WM: (15274: N1087 ^status complete)
<=WM: (15263: I2 ^dir U)
<=WM: (15262: I2 ^reward 1)
<=WM: (15261: I2 ^see 0)
=>WM: (15278: I2 ^level-1 R0-root)
<=WM: (15264: I2 ^level-1 R0-root)

--- END Input Phase --- 

--- Proposal Phase ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing rl*prefer*rvt*predict-yes*H0*1*H1*19
 -->
 (S1 ^operator O2173 = 0.4768809749851805)
Firing rl*prefer*rvt*predict-no*H0*2*H1*7
 -->
 (S1 ^operator O2174 = 0.1700769046561409)
Firing prefer*rvt*predict-no*H0*2*H1
 -->
Firing prefer*rvt*predict-yes*H0*1*H1
 -->
Firing elaborate*copy-see-to-output-link
 -->
 (I3 ^see 0 +)
Firing elaborate*reward*based*on*reward
 -->
 (R1091 ^value 1 +)
 (R1 ^reward R1091 +)
Firing propose*predict-yes
 -->
 (O2175 ^name predict-yes +)
 (S1 ^operator O2175 +)
Firing propose*predict-no
 -->
 (O2176 ^name predict-no +)
 (S1 ^operator O2176 +)
Firing rl*prefer*rvt*predict-no*H0*2
 -->
 (S1 ^operator O2174 = 0.2550133863879636)
Firing rl*prefer*rvt*predict-yes*H0*1
 -->
 (S1 ^operator O2173 = 0.5231192467369606)
Firing prefer*rvt*predict-yes*H0
 -->
Firing prefer*rvt*predict-no*H0
 -->
Firing elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir L +)
 inner elaboration loop at bottom goal.
Retracting elaborate*copy-see-to-output-link
 -->
 (I3 ^see 0 +)
Retracting propose*predict-no
 -->
 (O2174 ^name predict-no +)
 (S1 ^operator O2174 +)
Retracting propose*predict-yes
 -->
 (O2173 ^name predict-yes +)
 (S1 ^operator O2173 +)
Retracting elaborate*reward*based*on*reward
 -->
 (R1090 ^value 1 +)
 (R1 ^reward R1090 +)
Retracting elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir U +)
Retracting rl*prefer*rvt*predict-no*H0*6
 -->
 (S1 ^operator O2174 = 0.9999999999999999)
Retracting rl*prefer*rvt*predict-yes*H0*5
 -->
 (S1 ^operator O2173 = 0.)
=>WM: (15285: S1 ^operator O2176 +)
=>WM: (15284: S1 ^operator O2175 +)
=>WM: (15283: I3 ^dir L)
=>WM: (15282: O2176 ^name predict-no)
=>WM: (15281: O2175 ^name predict-yes)
=>WM: (15280: R1091 ^value 1)
=>WM: (15279: R1 ^reward R1091)
<=WM: (15270: S1 ^operator O2173 +)
<=WM: (15271: S1 ^operator O2174 +)
<=WM: (15272: S1 ^operator O2174)
<=WM: (15269: I3 ^dir U)
<=WM: (15265: R1 ^reward R1090)
<=WM: (15268: O2174 ^name predict-no)
<=WM: (15267: O2173 ^name predict-yes)
<=WM: (15266: R1090 ^value 1)

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing prefer*rvt*predict-yes*H0
 -->
Firing rl*prefer*rvt*predict-yes*H0*1*H1*19
 -->
 (S1 ^operator O2175 = 0.4768809749851805)
Firing rl*prefer*rvt*predict-yes*H0*1
 -->
 (S1 ^operator O2175 = 0.5231192467369606)
Firing prefer*rvt*predict-yes*H0*1*H1
 -->
Firing prefer*rvt*predict-no*H0
 -->
Firing rl*prefer*rvt*predict-no*H0*2*H1*7
 -->
 (S1 ^operator O2176 = 0.1700769046561409)
Firing rl*prefer*rvt*predict-no*H0*2
 -->
 (S1 ^operator O2176 = 0.2550133863879636)
Firing prefer*rvt*predict-no*H0*2*H1
 -->
 inner elaboration loop at bottom goal.
Retracting rl*prefer*rvt*predict-no*H0*2
 -->
 (S1 ^operator O2174 = 0.2550133863879636)
Retracting rl*prefer*rvt*predict-no*H0*2*H1*7
 -->
 (S1 ^operator O2174 = 0.1700769046561409)
Retracting rl*prefer*rvt*predict-yes*H0*1
 -->
 (S1 ^operator O2173 = 0.5231192467369606)
Retracting rl*prefer*rvt*predict-yes*H0*1*H1*19
 -->
 (S1 ^operator O2173 = 0.4768809749851805)

--- END Proposal Phase ---

--- Decision Phase ---
RL update rl*prefer*rvt*predict-no*H0*6 1 0 1 -> 1 0 1(R,m,v=1,1,0)
=>WM: (15286: S1 ^operator O2175)

  1088:    O: O2175 (predict-yes)
--- END Decision Phase ---

--- Application Phase ---
	--- Firing Productions (PE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing apply*operator
 -->
 (I3 ^predict-yes N1088 +  :O )
Firing apply*operator*complete
 -->
 (I3 ^predict-no N1087 -  :O )
 inner elaboration loop at bottom goal.
	--- Change Working Memory (PE) ---
=>WM: (15287: I3 ^predict-yes N1088)
<=WM: (15274: N1087 ^status complete)
<=WM: (15273: I3 ^predict-no N1087)
	--- Firing Productions (IE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing monitor*world
 -->

I see 1 and I'm going to do: predict-yes inner elaboration loop at bottom goal.
	--- Change Working Memory (IE) ---

--- END Application Phase ---
--- Output Phase ---
ENV: Agent did: predict-yes for direction L in state State-B
In  State-B moving L
ENV: (next state, see, prediction correct?) = (State-A, 1, True)
predict error 0
dir: dir isU
--- END Output Phase ---
-/|--- Input Phase --- 
=>WM: (15291: I2 ^dir U)
=>WM: (15290: I2 ^reward 1)
=>WM: (15289: I2 ^see 1)
=>WM: (15288: N1088 ^status complete)
<=WM: (15277: I2 ^dir L)
<=WM: (15276: I2 ^reward 1)
<=WM: (15275: I2 ^see 0)
=>WM: (15292: I2 ^level-1 L1-root)
<=WM: (15278: I2 ^level-1 R0-root)

--- END Input Phase --- 

--- Proposal Phase ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing elaborate*copy-see-to-output-link
 -->
 (I3 ^see 1 +)
Firing elaborate*reward*based*on*reward
 -->
 (R1092 ^value 1 +)
 (R1 ^reward R1092 +)
Firing propose*predict-yes
 -->
 (O2177 ^name predict-yes +)
 (S1 ^operator O2177 +)
Firing propose*predict-no
 -->
 (O2178 ^name predict-no +)
 (S1 ^operator O2178 +)
Firing rl*prefer*rvt*predict-no*H0*6
 -->
 (S1 ^operator O2176 = 0.9999999999999999)
Firing rl*prefer*rvt*predict-yes*H0*5
 -->
 (S1 ^operator O2175 = 0.)
Firing prefer*rvt*predict-yes*H0
 -->
Firing prefer*rvt*predict-no*H0
 -->
Firing elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir U +)
 inner elaboration loop at bottom goal.
Retracting elaborate*copy-see-to-output-link
 -->
 (I3 ^see 0 +)
Retracting propose*predict-no
 -->
 (O2176 ^name predict-no +)
 (S1 ^operator O2176 +)
Retracting propose*predict-yes
 -->
 (O2175 ^name predict-yes +)
 (S1 ^operator O2175 +)
Retracting elaborate*reward*based*on*reward
 -->
 (R1091 ^value 1 +)
 (R1 ^reward R1091 +)
Retracting elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir L +)
Retracting rl*prefer*rvt*predict-no*H0*2
 -->
 (S1 ^operator O2176 = 0.2550133863879636)
Retracting rl*prefer*rvt*predict-no*H0*2*H1*7
 -->
 (S1 ^operator O2176 = 0.1700769046561409)
Retracting rl*prefer*rvt*predict-yes*H0*1
 -->
 (S1 ^operator O2175 = 0.5231192467369606)
Retracting rl*prefer*rvt*predict-yes*H0*1*H1*19
 -->
 (S1 ^operator O2175 = 0.4768809749851805)
=>WM: (15300: S1 ^operator O2178 +)
=>WM: (15299: S1 ^operator O2177 +)
=>WM: (15298: I3 ^dir U)
=>WM: (15297: O2178 ^name predict-no)
=>WM: (15296: O2177 ^name predict-yes)
=>WM: (15295: R1092 ^value 1)
=>WM: (15294: R1 ^reward R1092)
=>WM: (15293: I3 ^see 1)
<=WM: (15284: S1 ^operator O2175 +)
<=WM: (15286: S1 ^operator O2175)
<=WM: (15285: S1 ^operator O2176 +)
<=WM: (15283: I3 ^dir L)
<=WM: (15279: R1 ^reward R1091)
<=WM: (15183: I3 ^see 0)
<=WM: (15282: O2176 ^name predict-no)
<=WM: (15281: O2175 ^name predict-yes)
<=WM: (15280: R1091 ^value 1)

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing prefer*rvt*predict-yes*H0
 -->
Firing rl*prefer*rvt*predict-yes*H0*5
 -->
 (S1 ^operator O2177 = 0.)
Firing prefer*rvt*predict-no*H0
 -->
Firing rl*prefer*rvt*predict-no*H0*6
 -->
 (S1 ^operator O2178 = 0.9999999999999999)
 inner elaboration loop at bottom goal.
Retracting rl*prefer*rvt*predict-no*H0*6
 -->
 (S1 ^operator O2176 = 0.9999999999999999)
Retracting rl*prefer*rvt*predict-yes*H0*5
 -->
 (S1 ^operator O2175 = 0.)

--- END Proposal Phase ---

--- Decision Phase ---
RL update rl*prefer*rvt*predict-yes*H0*1 0.727959 -0.20484 0.523119 -> 0.727959 -0.20484 0.523119(R,m,v=1,0.980769,0.0189826)
RL update rl*prefer*rvt*predict-yes*H0*1*H1*19 0.272041 0.20484 0.476881 -> 0.272041 0.20484 0.476881(R,m,v=1,1,0)
=>WM: (15301: S1 ^operator O2178)

  1089:    O: O2178 (predict-no)
--- END Decision Phase ---

--- Application Phase ---
	--- Firing Productions (PE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing apply*operator
 -->
 (I3 ^predict-no N1089 +  :O )
Firing apply*operator*complete
 -->
 (I3 ^predict-yes N1088 -  :O )
 inner elaboration loop at bottom goal.
	--- Change Working Memory (PE) ---
=>WM: (15302: I3 ^predict-no N1089)
<=WM: (15288: N1088 ^status complete)
<=WM: (15287: I3 ^predict-yes N1088)
	--- Firing Productions (IE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing monitor*world
 -->

I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
	--- Change Working Memory (IE) ---

--- END Application Phase ---
--- Output Phase ---
ENV: Agent did: predict-no for direction U in state State-A
In  State-A moving U
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isR
--- END Output Phase ---
\-/--- Input Phase --- 
=>WM: (15306: I2 ^dir R)
=>WM: (15305: I2 ^reward 1)
=>WM: (15304: I2 ^see 0)
=>WM: (15303: N1089 ^status complete)
<=WM: (15291: I2 ^dir U)
<=WM: (15290: I2 ^reward 1)
<=WM: (15289: I2 ^see 1)
=>WM: (15307: I2 ^level-1 L1-root)
<=WM: (15292: I2 ^level-1 L1-root)

--- END Input Phase --- 

--- Proposal Phase ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing rl*prefer*rvt*predict-yes*H0*3*H1*9
 -->
 (S1 ^operator O2177 = 0.6170510733049686)
Firing rl*prefer*rvt*predict-no*H0*4*H1*8
 -->
 (S1 ^operator O2178 = 0.4901349546100854)
Firing prefer*rvt*predict-no*H0*4*H1
 -->
Firing prefer*rvt*predict-yes*H0*3*H1
 -->
Firing elaborate*copy-see-to-output-link
 -->
 (I3 ^see 0 +)
Firing elaborate*reward*based*on*reward
 -->
 (R1093 ^value 1 +)
 (R1 ^reward R1093 +)
Firing propose*predict-yes
 -->
 (O2179 ^name predict-yes +)
 (S1 ^operator O2179 +)
Firing propose*predict-no
 -->
 (O2180 ^name predict-no +)
 (S1 ^operator O2180 +)
Firing rl*prefer*rvt*predict-no*H0*4
 -->
 (S1 ^operator O2178 = 0.1269768275936353)
Firing rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O2177 = 0.382942629133266)
Firing prefer*rvt*predict-yes*H0
 -->
Firing prefer*rvt*predict-no*H0
 -->
Firing elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir R +)
 inner elaboration loop at bottom goal.
Retracting elaborate*copy-see-to-output-link
 -->
 (I3 ^see 1 +)
Retracting propose*predict-no
 -->
 (O2178 ^name predict-no +)
 (S1 ^operator O2178 +)
Retracting propose*predict-yes
 -->
 (O2177 ^name predict-yes +)
 (S1 ^operator O2177 +)
Retracting elaborate*reward*based*on*reward
 -->
 (R1092 ^value 1 +)
 (R1 ^reward R1092 +)
Retracting elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir U +)
Retracting rl*prefer*rvt*predict-no*H0*6
 -->
 (S1 ^operator O2178 = 0.9999999999999999)
Retracting rl*prefer*rvt*predict-yes*H0*5
 -->
 (S1 ^operator O2177 = 0.)
=>WM: (15315: S1 ^operator O2180 +)
=>WM: (15314: S1 ^operator O2179 +)
=>WM: (15313: I3 ^dir R)
=>WM: (15312: O2180 ^name predict-no)
=>WM: (15311: O2179 ^name predict-yes)
=>WM: (15310: R1093 ^value 1)
=>WM: (15309: R1 ^reward R1093)
=>WM: (15308: I3 ^see 0)
<=WM: (15299: S1 ^operator O2177 +)
<=WM: (15300: S1 ^operator O2178 +)
<=WM: (15301: S1 ^operator O2178)
<=WM: (15298: I3 ^dir U)
<=WM: (15294: R1 ^reward R1092)
<=WM: (15293: I3 ^see 1)
<=WM: (15297: O2178 ^name predict-no)
<=WM: (15296: O2177 ^name predict-yes)
<=WM: (15295: R1092 ^value 1)

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing prefer*rvt*predict-yes*H0
 -->
Firing rl*prefer*rvt*predict-yes*H0*3*H1*9
 -->
 (S1 ^operator O2179 = 0.6170510733049686)
Firing rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O2179 = 0.382942629133266)
Firing prefer*rvt*predict-yes*H0*3*H1
 -->
Firing prefer*rvt*predict-no*H0
 -->
Firing rl*prefer*rvt*predict-no*H0*4*H1*8
 -->
 (S1 ^operator O2180 = 0.4901349546100854)
Firing rl*prefer*rvt*predict-no*H0*4
 -->
 (S1 ^operator O2180 = 0.1269768275936353)
Firing prefer*rvt*predict-no*H0*4*H1
 -->
 inner elaboration loop at bottom goal.
Retracting rl*prefer*rvt*predict-no*H0*4
 -->
 (S1 ^operator O2178 = 0.1269768275936353)
Retracting rl*prefer*rvt*predict-no*H0*4*H1*8
 -->
 (S1 ^operator O2178 = 0.4901349546100854)
Retracting rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O2177 = 0.382942629133266)
Retracting rl*prefer*rvt*predict-yes*H0*3*H1*9
 -->
 (S1 ^operator O2177 = 0.6170510733049686)

--- END Proposal Phase ---

--- Decision Phase ---
RL update rl*prefer*rvt*predict-no*H0*6 1 0 1 -> 1 0 1(R,m,v=1,1,0)
=>WM: (15316: S1 ^operator O2179)

  1090:    O: O2179 (predict-yes)
--- END Decision Phase ---

--- Application Phase ---
	--- Firing Productions (PE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing apply*operator
 -->
 (I3 ^predict-yes N1090 +  :O )
Firing apply*operator*complete
 -->
 (I3 ^predict-no N1089 -  :O )
 inner elaboration loop at bottom goal.
	--- Change Working Memory (PE) ---
=>WM: (15317: I3 ^predict-yes N1090)
<=WM: (15303: N1089 ^status complete)
<=WM: (15302: I3 ^predict-no N1089)
	--- Firing Productions (IE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing monitor*world
 -->

I see 1 and I'm going to do: predict-yes inner elaboration loop at bottom goal.
	--- Change Working Memory (IE) ---

--- END Application Phase ---
--- Output Phase ---
ENV: Agent did: predict-yes for direction R in state State-A
In  State-A moving R
ENV: (next state, see, prediction correct?) = (State-B, 1, True)
predict error 0
dir: dir isR
--- END Output Phase ---
|\--- Input Phase --- 
=>WM: (15321: I2 ^dir R)
=>WM: (15320: I2 ^reward 1)
=>WM: (15319: I2 ^see 1)
=>WM: (15318: N1090 ^status complete)
<=WM: (15306: I2 ^dir R)
<=WM: (15305: I2 ^reward 1)
<=WM: (15304: I2 ^see 0)
=>WM: (15322: I2 ^level-1 R1-root)
<=WM: (15307: I2 ^level-1 L1-root)

--- END Input Phase --- 

--- Proposal Phase ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing rl*prefer*rvt*predict-yes*H0*3*H1*16
 -->
 (S1 ^operator O2179 = 0.08783148430849691)
Firing rl*prefer*rvt*predict-no*H0*4*H1*15
 -->
 (S1 ^operator O2180 = 0.8730232122106774)
Firing prefer*rvt*predict-no*H0*4*H1
 -->
Firing prefer*rvt*predict-yes*H0*3*H1
 -->
Firing elaborate*copy-see-to-output-link
 -->
 (I3 ^see 1 +)
Firing elaborate*reward*based*on*reward
 -->
 (R1094 ^value 1 +)
 (R1 ^reward R1094 +)
Firing propose*predict-yes
 -->
 (O2181 ^name predict-yes +)
 (S1 ^operator O2181 +)
Firing propose*predict-no
 -->
 (O2182 ^name predict-no +)
 (S1 ^operator O2182 +)
Firing rl*prefer*rvt*predict-no*H0*4
 -->
 (S1 ^operator O2180 = 0.1269768275936353)
Firing rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O2179 = 0.382942629133266)
Firing prefer*rvt*predict-yes*H0
 -->
Firing prefer*rvt*predict-no*H0
 -->
Firing elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir R +)
 inner elaboration loop at bottom goal.
Retracting elaborate*copy-see-to-output-link
 -->
 (I3 ^see 0 +)
Retracting propose*predict-no
 -->
 (O2180 ^name predict-no +)
 (S1 ^operator O2180 +)
Retracting propose*predict-yes
 -->
 (O2179 ^name predict-yes +)
 (S1 ^operator O2179 +)
Retracting elaborate*reward*based*on*reward
 -->
 (R1093 ^value 1 +)
 (R1 ^reward R1093 +)
Retracting elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir R +)
Retracting rl*prefer*rvt*predict-no*H0*4
 -->
 (S1 ^operator O2180 = 0.1269768275936353)
Retracting rl*prefer*rvt*predict-no*H0*4*H1*8
 -->
 (S1 ^operator O2180 = 0.4901349546100854)
Retracting rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O2179 = 0.382942629133266)
Retracting rl*prefer*rvt*predict-yes*H0*3*H1*9
 -->
 (S1 ^operator O2179 = 0.6170510733049686)
=>WM: (15329: S1 ^operator O2182 +)
=>WM: (15328: S1 ^operator O2181 +)
=>WM: (15327: O2182 ^name predict-no)
=>WM: (15326: O2181 ^name predict-yes)
=>WM: (15325: R1094 ^value 1)
=>WM: (15324: R1 ^reward R1094)
=>WM: (15323: I3 ^see 1)
<=WM: (15314: S1 ^operator O2179 +)
<=WM: (15316: S1 ^operator O2179)
<=WM: (15315: S1 ^operator O2180 +)
<=WM: (15309: R1 ^reward R1093)
<=WM: (15308: I3 ^see 0)
<=WM: (15312: O2180 ^name predict-no)
<=WM: (15311: O2179 ^name predict-yes)
<=WM: (15310: R1093 ^value 1)

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing prefer*rvt*predict-yes*H0
 -->
Firing rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O2181 = 0.382942629133266)
Firing prefer*rvt*predict-yes*H0*3*H1
 -->
Firing rl*prefer*rvt*predict-yes*H0*3*H1*16
 -->
 (S1 ^operator O2181 = 0.08783148430849691)
Firing prefer*rvt*predict-no*H0
 -->
Firing rl*prefer*rvt*predict-no*H0*4
 -->
 (S1 ^operator O2182 = 0.1269768275936353)
Firing prefer*rvt*predict-no*H0*4*H1
 -->
Firing rl*prefer*rvt*predict-no*H0*4*H1*15
 -->
 (S1 ^operator O2182 = 0.8730232122106774)
 inner elaboration loop at bottom goal.
Retracting rl*prefer*rvt*predict-no*H0*4
 -->
 (S1 ^operator O2180 = 0.1269768275936353)
Retracting rl*prefer*rvt*predict-no*H0*4*H1*15
 -->
 (S1 ^operator O2180 = 0.8730232122106774)
Retracting rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O2179 = 0.382942629133266)
Retracting rl*prefer*rvt*predict-yes*H0*3*H1*16
 -->
 (S1 ^operator O2179 = 0.08783148430849691)

--- END Proposal Phase ---

--- Decision Phase ---
RL update rl*prefer*rvt*predict-yes*H0*3 0.673136 -0.290193 0.382943 -> 0.673136 -0.290193 0.382944(R,m,v=1,0.964072,0.034846)
RL update rl*prefer*rvt*predict-yes*H0*3*H1*9 0.326859 0.290192 0.617051 -> 0.32686 0.290192 0.617052(R,m,v=1,1,0)
=>WM: (15330: S1 ^operator O2182)

  1091:    O: O2182 (predict-no)
--- END Decision Phase ---

--- Application Phase ---
	--- Firing Productions (PE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing apply*operator
 -->
 (I3 ^predict-no N1091 +  :O )
Firing apply*operator*complete
 -->
 (I3 ^predict-yes N1090 -  :O )
 inner elaboration loop at bottom goal.
	--- Change Working Memory (PE) ---
=>WM: (15331: I3 ^predict-no N1091)
<=WM: (15318: N1090 ^status complete)
<=WM: (15317: I3 ^predict-yes N1090)
	--- Firing Productions (IE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing monitor*world
 -->

I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
	--- Change Working Memory (IE) ---

--- END Application Phase ---
--- Output Phase ---
ENV: Agent did: predict-no for direction R in state State-B
In  State-B moving R
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isU
--- END Output Phase ---
---- Input Phase --- 
=>WM: (15335: I2 ^dir U)
=>WM: (15334: I2 ^reward 1)
=>WM: (15333: I2 ^see 0)
=>WM: (15332: N1091 ^status complete)
<=WM: (15321: I2 ^dir R)
<=WM: (15320: I2 ^reward 1)
<=WM: (15319: I2 ^see 1)
=>WM: (15336: I2 ^level-1 R0-root)
<=WM: (15322: I2 ^level-1 R1-root)

--- END Input Phase --- 

--- Proposal Phase ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing elaborate*copy-see-to-output-link
 -->
 (I3 ^see 0 +)
Firing elaborate*reward*based*on*reward
 -->
 (R1095 ^value 1 +)
 (R1 ^reward R1095 +)
Firing propose*predict-yes
 -->
 (O2183 ^name predict-yes +)
 (S1 ^operator O2183 +)
Firing propose*predict-no
 -->
 (O2184 ^name predict-no +)
 (S1 ^operator O2184 +)
Firing rl*prefer*rvt*predict-no*H0*6
 -->
 (S1 ^operator O2182 = 0.9999999999999999)
Firing rl*prefer*rvt*predict-yes*H0*5
 -->
 (S1 ^operator O2181 = 0.)
Firing prefer*rvt*predict-yes*H0
 -->
Firing prefer*rvt*predict-no*H0
 -->
Firing elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir U +)
 inner elaboration loop at bottom goal.
Retracting elaborate*copy-see-to-output-link
 -->
 (I3 ^see 1 +)
Retracting propose*predict-no
 -->
 (O2182 ^name predict-no +)
 (S1 ^operator O2182 +)
Retracting propose*predict-yes
 -->
 (O2181 ^name predict-yes +)
 (S1 ^operator O2181 +)
Retracting elaborate*reward*based*on*reward
 -->
 (R1094 ^value 1 +)
 (R1 ^reward R1094 +)
Retracting elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir R +)
Retracting rl*prefer*rvt*predict-no*H0*4*H1*15
 -->
 (S1 ^operator O2182 = 0.8730232122106774)
Retracting rl*prefer*rvt*predict-no*H0*4
 -->
 (S1 ^operator O2182 = 0.1269768275936353)
Retracting rl*prefer*rvt*predict-yes*H0*3*H1*16
 -->
 (S1 ^operator O2181 = 0.08783148430849691)
Retracting rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O2181 = 0.3829435737675308)
=>WM: (15344: S1 ^operator O2184 +)
=>WM: (15343: S1 ^operator O2183 +)
=>WM: (15342: I3 ^dir U)
=>WM: (15341: O2184 ^name predict-no)
=>WM: (15340: O2183 ^name predict-yes)
=>WM: (15339: R1095 ^value 1)
=>WM: (15338: R1 ^reward R1095)
=>WM: (15337: I3 ^see 0)
<=WM: (15328: S1 ^operator O2181 +)
<=WM: (15329: S1 ^operator O2182 +)
<=WM: (15330: S1 ^operator O2182)
<=WM: (15313: I3 ^dir R)
<=WM: (15324: R1 ^reward R1094)
<=WM: (15323: I3 ^see 1)
<=WM: (15327: O2182 ^name predict-no)
<=WM: (15326: O2181 ^name predict-yes)
<=WM: (15325: R1094 ^value 1)

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing prefer*rvt*predict-yes*H0
 -->
Firing rl*prefer*rvt*predict-yes*H0*5
 -->
 (S1 ^operator O2183 = 0.)
Firing prefer*rvt*predict-no*H0
 -->
Firing rl*prefer*rvt*predict-no*H0*6
 -->
 (S1 ^operator O2184 = 0.9999999999999999)
 inner elaboration loop at bottom goal.
Retracting rl*prefer*rvt*predict-no*H0*6
 -->
 (S1 ^operator O2182 = 0.9999999999999999)
Retracting rl*prefer*rvt*predict-yes*H0*5
 -->
 (S1 ^operator O2181 = 0.)

--- END Proposal Phase ---

--- Decision Phase ---
RL update rl*prefer*rvt*predict-no*H0*4 0.814714 -0.687737 0.126977 -> 0.814714 -0.687737 0.126977(R,m,v=1,0.954774,0.0433988)
RL update rl*prefer*rvt*predict-no*H0*4*H1*15 0.185286 0.687737 0.873023 -> 0.185286 0.687737 0.873023(R,m,v=1,1,0)
=>WM: (15345: S1 ^operator O2184)

  1092:    O: O2184 (predict-no)
--- END Decision Phase ---

--- Application Phase ---
	--- Firing Productions (PE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing apply*operator
 -->
 (I3 ^predict-no N1092 +  :O )
Firing apply*operator*complete
 -->
 (I3 ^predict-no N1091 -  :O )
 inner elaboration loop at bottom goal.
	--- Change Working Memory (PE) ---
=>WM: (15346: I3 ^predict-no N1092)
<=WM: (15332: N1091 ^status complete)
<=WM: (15331: I3 ^predict-no N1091)
	--- Firing Productions (IE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing monitor*world
 -->

I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
	--- Change Working Memory (IE) ---

--- END Application Phase ---
--- Output Phase ---
ENV: Agent did: predict-no for direction U in state State-B
In  State-B moving U
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isL
--- END Output Phase ---
/|\--- Input Phase --- 
=>WM: (15350: I2 ^dir L)
=>WM: (15349: I2 ^reward 1)
=>WM: (15348: I2 ^see 0)
=>WM: (15347: N1092 ^status complete)
<=WM: (15335: I2 ^dir U)
<=WM: (15334: I2 ^reward 1)
<=WM: (15333: I2 ^see 0)
=>WM: (15351: I2 ^level-1 R0-root)
<=WM: (15336: I2 ^level-1 R0-root)

--- END Input Phase --- 

--- Proposal Phase ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing rl*prefer*rvt*predict-yes*H0*1*H1*19
 -->
 (S1 ^operator O2183 = 0.4768809417268593)
Firing rl*prefer*rvt*predict-no*H0*2*H1*7
 -->
 (S1 ^operator O2184 = 0.1700769046561409)
Firing prefer*rvt*predict-no*H0*2*H1
 -->
Firing prefer*rvt*predict-yes*H0*1*H1
 -->
Firing elaborate*copy-see-to-output-link
 -->
 (I3 ^see 0 +)
Firing elaborate*reward*based*on*reward
 -->
 (R1096 ^value 1 +)
 (R1 ^reward R1096 +)
Firing propose*predict-yes
 -->
 (O2185 ^name predict-yes +)
 (S1 ^operator O2185 +)
Firing propose*predict-no
 -->
 (O2186 ^name predict-no +)
 (S1 ^operator O2186 +)
Firing rl*prefer*rvt*predict-no*H0*2
 -->
 (S1 ^operator O2184 = 0.2550133863879636)
Firing rl*prefer*rvt*predict-yes*H0*1
 -->
 (S1 ^operator O2183 = 0.5231192134786394)
Firing prefer*rvt*predict-yes*H0
 -->
Firing prefer*rvt*predict-no*H0
 -->
Firing elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir L +)
 inner elaboration loop at bottom goal.
Retracting elaborate*copy-see-to-output-link
 -->
 (I3 ^see 0 +)
Retracting propose*predict-no
 -->
 (O2184 ^name predict-no +)
 (S1 ^operator O2184 +)
Retracting propose*predict-yes
 -->
 (O2183 ^name predict-yes +)
 (S1 ^operator O2183 +)
Retracting elaborate*reward*based*on*reward
 -->
 (R1095 ^value 1 +)
 (R1 ^reward R1095 +)
Retracting elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir U +)
Retracting rl*prefer*rvt*predict-no*H0*6
 -->
 (S1 ^operator O2184 = 0.9999999999999999)
Retracting rl*prefer*rvt*predict-yes*H0*5
 -->
 (S1 ^operator O2183 = 0.)
=>WM: (15358: S1 ^operator O2186 +)
=>WM: (15357: S1 ^operator O2185 +)
=>WM: (15356: I3 ^dir L)
=>WM: (15355: O2186 ^name predict-no)
=>WM: (15354: O2185 ^name predict-yes)
=>WM: (15353: R1096 ^value 1)
=>WM: (15352: R1 ^reward R1096)
<=WM: (15343: S1 ^operator O2183 +)
<=WM: (15344: S1 ^operator O2184 +)
<=WM: (15345: S1 ^operator O2184)
<=WM: (15342: I3 ^dir U)
<=WM: (15338: R1 ^reward R1095)
<=WM: (15341: O2184 ^name predict-no)
<=WM: (15340: O2183 ^name predict-yes)
<=WM: (15339: R1095 ^value 1)

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing prefer*rvt*predict-yes*H0
 -->
Firing rl*prefer*rvt*predict-yes*H0*1*H1*19
 -->
 (S1 ^operator O2185 = 0.4768809417268593)
Firing rl*prefer*rvt*predict-yes*H0*1
 -->
 (S1 ^operator O2185 = 0.5231192134786394)
Firing prefer*rvt*predict-yes*H0*1*H1
 -->
Firing prefer*rvt*predict-no*H0
 -->
Firing rl*prefer*rvt*predict-no*H0*2*H1*7
 -->
 (S1 ^operator O2186 = 0.1700769046561409)
Firing rl*prefer*rvt*predict-no*H0*2
 -->
 (S1 ^operator O2186 = 0.2550133863879636)
Firing prefer*rvt*predict-no*H0*2*H1
 -->
 inner elaboration loop at bottom goal.
Retracting rl*prefer*rvt*predict-no*H0*2
 -->
 (S1 ^operator O2184 = 0.2550133863879636)
Retracting rl*prefer*rvt*predict-no*H0*2*H1*7
 -->
 (S1 ^operator O2184 = 0.1700769046561409)
Retracting rl*prefer*rvt*predict-yes*H0*1
 -->
 (S1 ^operator O2183 = 0.5231192134786394)
Retracting rl*prefer*rvt*predict-yes*H0*1*H1*19
 -->
 (S1 ^operator O2183 = 0.4768809417268593)

--- END Proposal Phase ---

--- Decision Phase ---
RL update rl*prefer*rvt*predict-no*H0*6 1 0 1 -> 1 0 1(R,m,v=1,1,0)
=>WM: (15359: S1 ^operator O2185)

  1093:    O: O2185 (predict-yes)
--- END Decision Phase ---

--- Application Phase ---
	--- Firing Productions (PE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing apply*operator
 -->
 (I3 ^predict-yes N1093 +  :O )
Firing apply*operator*complete
 -->
 (I3 ^predict-no N1092 -  :O )
 inner elaboration loop at bottom goal.
	--- Change Working Memory (PE) ---
=>WM: (15360: I3 ^predict-yes N1093)
<=WM: (15347: N1092 ^status complete)
<=WM: (15346: I3 ^predict-no N1092)
	--- Firing Productions (IE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing monitor*world
 -->

I see 1 and I'm going to do: predict-yes inner elaboration loop at bottom goal.
	--- Change Working Memory (IE) ---

--- END Application Phase ---
--- Output Phase ---
ENV: Agent did: predict-yes for direction L in state State-B
In  State-B moving L
ENV: (next state, see, prediction correct?) = (State-A, 1, True)
predict error 0
dir: dir isL
--- END Output Phase ---
-/|--- Input Phase --- 
=>WM: (15364: I2 ^dir L)
=>WM: (15363: I2 ^reward 1)
=>WM: (15362: I2 ^see 1)
=>WM: (15361: N1093 ^status complete)
<=WM: (15350: I2 ^dir L)
<=WM: (15349: I2 ^reward 1)
<=WM: (15348: I2 ^see 0)
=>WM: (15365: I2 ^level-1 L1-root)
<=WM: (15351: I2 ^level-1 R0-root)

--- END Input Phase --- 

--- Proposal Phase ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing rl*prefer*rvt*predict-yes*H0*1*H1*20
 -->
 (S1 ^operator O2185 = 0.1693592933936033)
Firing rl*prefer*rvt*predict-no*H0*2*H1*11
 -->
 (S1 ^operator O2186 = 0.7449865344888057)
Firing prefer*rvt*predict-no*H0*2*H1
 -->
Firing prefer*rvt*predict-yes*H0*1*H1
 -->
Firing elaborate*copy-see-to-output-link
 -->
 (I3 ^see 1 +)
Firing elaborate*reward*based*on*reward
 -->
 (R1097 ^value 1 +)
 (R1 ^reward R1097 +)
Firing propose*predict-yes
 -->
 (O2187 ^name predict-yes +)
 (S1 ^operator O2187 +)
Firing propose*predict-no
 -->
 (O2188 ^name predict-no +)
 (S1 ^operator O2188 +)
Firing rl*prefer*rvt*predict-no*H0*2
 -->
 (S1 ^operator O2186 = 0.2550133863879636)
Firing rl*prefer*rvt*predict-yes*H0*1
 -->
 (S1 ^operator O2185 = 0.5231192134786394)
Firing prefer*rvt*predict-yes*H0
 -->
Firing prefer*rvt*predict-no*H0
 -->
Firing elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir L +)
 inner elaboration loop at bottom goal.
Retracting elaborate*copy-see-to-output-link
 -->
 (I3 ^see 0 +)
Retracting propose*predict-no
 -->
 (O2186 ^name predict-no +)
 (S1 ^operator O2186 +)
Retracting propose*predict-yes
 -->
 (O2185 ^name predict-yes +)
 (S1 ^operator O2185 +)
Retracting elaborate*reward*based*on*reward
 -->
 (R1096 ^value 1 +)
 (R1 ^reward R1096 +)
Retracting elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir L +)
Retracting rl*prefer*rvt*predict-no*H0*2
 -->
 (S1 ^operator O2186 = 0.2550133863879636)
Retracting rl*prefer*rvt*predict-no*H0*2*H1*7
 -->
 (S1 ^operator O2186 = 0.1700769046561409)
Retracting rl*prefer*rvt*predict-yes*H0*1
 -->
 (S1 ^operator O2185 = 0.5231192134786394)
Retracting rl*prefer*rvt*predict-yes*H0*1*H1*19
 -->
 (S1 ^operator O2185 = 0.4768809417268593)
=>WM: (15372: S1 ^operator O2188 +)
=>WM: (15371: S1 ^operator O2187 +)
=>WM: (15370: O2188 ^name predict-no)
=>WM: (15369: O2187 ^name predict-yes)
=>WM: (15368: R1097 ^value 1)
=>WM: (15367: R1 ^reward R1097)
=>WM: (15366: I3 ^see 1)
<=WM: (15357: S1 ^operator O2185 +)
<=WM: (15359: S1 ^operator O2185)
<=WM: (15358: S1 ^operator O2186 +)
<=WM: (15352: R1 ^reward R1096)
<=WM: (15337: I3 ^see 0)
<=WM: (15355: O2186 ^name predict-no)
<=WM: (15354: O2185 ^name predict-yes)
<=WM: (15353: R1096 ^value 1)

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing prefer*rvt*predict-yes*H0
 -->
Firing rl*prefer*rvt*predict-yes*H0*1
 -->
 (S1 ^operator O2187 = 0.5231192134786394)
Firing prefer*rvt*predict-yes*H0*1*H1
 -->
Firing rl*prefer*rvt*predict-yes*H0*1*H1*20
 -->
 (S1 ^operator O2187 = 0.1693592933936033)
Firing prefer*rvt*predict-no*H0
 -->
Firing rl*prefer*rvt*predict-no*H0*2
 -->
 (S1 ^operator O2188 = 0.2550133863879636)
Firing prefer*rvt*predict-no*H0*2*H1
 -->
Firing rl*prefer*rvt*predict-no*H0*2*H1*11
 -->
 (S1 ^operator O2188 = 0.7449865344888057)
 inner elaboration loop at bottom goal.
Retracting rl*prefer*rvt*predict-no*H0*2
 -->
 (S1 ^operator O2186 = 0.2550133863879636)
Retracting rl*prefer*rvt*predict-no*H0*2*H1*11
 -->
 (S1 ^operator O2186 = 0.7449865344888057)
Retracting rl*prefer*rvt*predict-yes*H0*1
 -->
 (S1 ^operator O2185 = 0.5231192134786394)
Retracting rl*prefer*rvt*predict-yes*H0*1*H1*20
 -->
 (S1 ^operator O2185 = 0.1693592933936033)

--- END Proposal Phase ---

--- Decision Phase ---
RL update rl*prefer*rvt*predict-yes*H0*1 0.727959 -0.20484 0.523119 -> 0.727959 -0.20484 0.523119(R,m,v=1,0.980892,0.0188633)
RL update rl*prefer*rvt*predict-yes*H0*1*H1*19 0.272041 0.20484 0.476881 -> 0.272041 0.20484 0.476881(R,m,v=1,1,0)
=>WM: (15373: S1 ^operator O2188)

  1094:    O: O2188 (predict-no)
--- END Decision Phase ---

--- Application Phase ---
	--- Firing Productions (PE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing apply*operator
 -->
 (I3 ^predict-no N1094 +  :O )
Firing apply*operator*complete
 -->
 (I3 ^predict-yes N1093 -  :O )
 inner elaboration loop at bottom goal.
	--- Change Working Memory (PE) ---
=>WM: (15374: I3 ^predict-no N1094)
<=WM: (15361: N1093 ^status complete)
<=WM: (15360: I3 ^predict-yes N1093)
	--- Firing Productions (IE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing monitor*world
 -->

I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
	--- Change Working Memory (IE) ---

--- END Application Phase ---
--- Output Phase ---
ENV: Agent did: predict-no for direction L in state State-A
In  State-A moving L
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isU
--- END Output Phase ---
\-/--- Input Phase --- 
=>WM: (15378: I2 ^dir U)
=>WM: (15377: I2 ^reward 1)
=>WM: (15376: I2 ^see 0)
=>WM: (15375: N1094 ^status complete)
<=WM: (15364: I2 ^dir L)
<=WM: (15363: I2 ^reward 1)
<=WM: (15362: I2 ^see 1)
=>WM: (15379: I2 ^level-1 L0-root)
<=WM: (15365: I2 ^level-1 L1-root)

--- END Input Phase --- 

--- Proposal Phase ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing elaborate*copy-see-to-output-link
 -->
 (I3 ^see 0 +)
Firing elaborate*reward*based*on*reward
 -->
 (R1098 ^value 1 +)
 (R1 ^reward R1098 +)
Firing propose*predict-yes
 -->
 (O2189 ^name predict-yes +)
 (S1 ^operator O2189 +)
Firing propose*predict-no
 -->
 (O2190 ^name predict-no +)
 (S1 ^operator O2190 +)
Firing rl*prefer*rvt*predict-no*H0*6
 -->
 (S1 ^operator O2188 = 0.9999999999999999)
Firing rl*prefer*rvt*predict-yes*H0*5
 -->
 (S1 ^operator O2187 = 0.)
Firing prefer*rvt*predict-yes*H0
 -->
Firing prefer*rvt*predict-no*H0
 -->
Firing elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir U +)
 inner elaboration loop at bottom goal.
Retracting elaborate*copy-see-to-output-link
 -->
 (I3 ^see 1 +)
Retracting propose*predict-no
 -->
 (O2188 ^name predict-no +)
 (S1 ^operator O2188 +)
Retracting propose*predict-yes
 -->
 (O2187 ^name predict-yes +)
 (S1 ^operator O2187 +)
Retracting elaborate*reward*based*on*reward
 -->
 (R1097 ^value 1 +)
 (R1 ^reward R1097 +)
Retracting elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir L +)
Retracting rl*prefer*rvt*predict-no*H0*2*H1*11
 -->
 (S1 ^operator O2188 = 0.7449865344888057)
Retracting rl*prefer*rvt*predict-no*H0*2
 -->
 (S1 ^operator O2188 = 0.2550133863879636)
Retracting rl*prefer*rvt*predict-yes*H0*1*H1*20
 -->
 (S1 ^operator O2187 = 0.1693592933936033)
Retracting rl*prefer*rvt*predict-yes*H0*1
 -->
 (S1 ^operator O2187 = 0.5231191901978147)
=>WM: (15387: S1 ^operator O2190 +)
=>WM: (15386: S1 ^operator O2189 +)
=>WM: (15385: I3 ^dir U)
=>WM: (15384: O2190 ^name predict-no)
=>WM: (15383: O2189 ^name predict-yes)
=>WM: (15382: R1098 ^value 1)
=>WM: (15381: R1 ^reward R1098)
=>WM: (15380: I3 ^see 0)
<=WM: (15371: S1 ^operator O2187 +)
<=WM: (15372: S1 ^operator O2188 +)
<=WM: (15373: S1 ^operator O2188)
<=WM: (15356: I3 ^dir L)
<=WM: (15367: R1 ^reward R1097)
<=WM: (15366: I3 ^see 1)
<=WM: (15370: O2188 ^name predict-no)
<=WM: (15369: O2187 ^name predict-yes)
<=WM: (15368: R1097 ^value 1)

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing prefer*rvt*predict-yes*H0
 -->
Firing rl*prefer*rvt*predict-yes*H0*5
 -->
 (S1 ^operator O2189 = 0.)
Firing prefer*rvt*predict-no*H0
 -->
Firing rl*prefer*rvt*predict-no*H0*6
 -->
 (S1 ^operator O2190 = 0.9999999999999999)
 inner elaboration loop at bottom goal.
Retracting rl*prefer*rvt*predict-no*H0*6
 -->
 (S1 ^operator O2188 = 0.9999999999999999)
Retracting rl*prefer*rvt*predict-yes*H0*5
 -->
 (S1 ^operator O2187 = 0.)

--- END Proposal Phase ---

--- Decision Phase ---
RL update rl*prefer*rvt*predict-no*H0*2 0.631495 -0.376482 0.255013 -> 0.631495 -0.376482 0.255013(R,m,v=1,0.92233,0.0719867)
RL update rl*prefer*rvt*predict-no*H0*2*H1*11 0.368505 0.376482 0.744987 -> 0.368505 0.376482 0.744987(R,m,v=1,1,0)
=>WM: (15388: S1 ^operator O2190)

  1095:    O: O2190 (predict-no)
--- END Decision Phase ---

--- Application Phase ---
	--- Firing Productions (PE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing apply*operator
 -->
 (I3 ^predict-no N1095 +  :O )
Firing apply*operator*complete
 -->
 (I3 ^predict-no N1094 -  :O )
 inner elaboration loop at bottom goal.
	--- Change Working Memory (PE) ---
=>WM: (15389: I3 ^predict-no N1095)
<=WM: (15375: N1094 ^status complete)
<=WM: (15374: I3 ^predict-no N1094)
	--- Firing Productions (IE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing monitor*world
 -->

I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
	--- Change Working Memory (IE) ---

--- END Application Phase ---
--- Output Phase ---
ENV: Agent did: predict-no for direction U in state State-A
In  State-A moving U
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isR
--- END Output Phase ---
|\---- Input Phase --- 
=>WM: (15393: I2 ^dir R)
=>WM: (15392: I2 ^reward 1)
=>WM: (15391: I2 ^see 0)
=>WM: (15390: N1095 ^status complete)
<=WM: (15378: I2 ^dir U)
<=WM: (15377: I2 ^reward 1)
<=WM: (15376: I2 ^see 0)
=>WM: (15394: I2 ^level-1 L0-root)
<=WM: (15379: I2 ^level-1 L0-root)

--- END Input Phase --- 

--- Proposal Phase ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing rl*prefer*rvt*predict-yes*H0*3*H1*14
 -->
 (S1 ^operator O2189 = 0.617065960338947)
Firing rl*prefer*rvt*predict-no*H0*4*H1*13
 -->
 (S1 ^operator O2190 = 0.4910065094545203)
Firing prefer*rvt*predict-no*H0*4*H1
 -->
Firing prefer*rvt*predict-yes*H0*3*H1
 -->
Firing elaborate*copy-see-to-output-link
 -->
 (I3 ^see 0 +)
Firing elaborate*reward*based*on*reward
 -->
 (R1099 ^value 1 +)
 (R1 ^reward R1099 +)
Firing propose*predict-yes
 -->
 (O2191 ^name predict-yes +)
 (S1 ^operator O2191 +)
Firing propose*predict-no
 -->
 (O2192 ^name predict-no +)
 (S1 ^operator O2192 +)
Firing rl*prefer*rvt*predict-no*H0*4
 -->
 (S1 ^operator O2190 = 0.1269768216229884)
Firing rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O2189 = 0.3829435737675308)
Firing prefer*rvt*predict-yes*H0
 -->
Firing prefer*rvt*predict-no*H0
 -->
Firing elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir R +)
 inner elaboration loop at bottom goal.
Retracting elaborate*copy-see-to-output-link
 -->
 (I3 ^see 0 +)
Retracting propose*predict-no
 -->
 (O2190 ^name predict-no +)
 (S1 ^operator O2190 +)
Retracting propose*predict-yes
 -->
 (O2189 ^name predict-yes +)
 (S1 ^operator O2189 +)
Retracting elaborate*reward*based*on*reward
 -->
 (R1098 ^value 1 +)
 (R1 ^reward R1098 +)
Retracting elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir U +)
Retracting rl*prefer*rvt*predict-no*H0*6
 -->
 (S1 ^operator O2190 = 0.9999999999999999)
Retracting rl*prefer*rvt*predict-yes*H0*5
 -->
 (S1 ^operator O2189 = 0.)
=>WM: (15401: S1 ^operator O2192 +)
=>WM: (15400: S1 ^operator O2191 +)
=>WM: (15399: I3 ^dir R)
=>WM: (15398: O2192 ^name predict-no)
=>WM: (15397: O2191 ^name predict-yes)
=>WM: (15396: R1099 ^value 1)
=>WM: (15395: R1 ^reward R1099)
<=WM: (15386: S1 ^operator O2189 +)
<=WM: (15387: S1 ^operator O2190 +)
<=WM: (15388: S1 ^operator O2190)
<=WM: (15385: I3 ^dir U)
<=WM: (15381: R1 ^reward R1098)
<=WM: (15384: O2190 ^name predict-no)
<=WM: (15383: O2189 ^name predict-yes)
<=WM: (15382: R1098 ^value 1)

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing prefer*rvt*predict-yes*H0
 -->
Firing rl*prefer*rvt*predict-yes*H0*3*H1*14
 -->
 (S1 ^operator O2191 = 0.617065960338947)
Firing rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O2191 = 0.3829435737675308)
Firing prefer*rvt*predict-yes*H0*3*H1
 -->
Firing prefer*rvt*predict-no*H0
 -->
Firing rl*prefer*rvt*predict-no*H0*4*H1*13
 -->
 (S1 ^operator O2192 = 0.4910065094545203)
Firing rl*prefer*rvt*predict-no*H0*4
 -->
 (S1 ^operator O2192 = 0.1269768216229884)
Firing prefer*rvt*predict-no*H0*4*H1
 -->
 inner elaboration loop at bottom goal.
Retracting rl*prefer*rvt*predict-no*H0*4
 -->
 (S1 ^operator O2190 = 0.1269768216229884)
Retracting rl*prefer*rvt*predict-no*H0*4*H1*13
 -->
 (S1 ^operator O2190 = 0.4910065094545203)
Retracting rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O2189 = 0.3829435737675308)
Retracting rl*prefer*rvt*predict-yes*H0*3*H1*14
 -->
 (S1 ^operator O2189 = 0.617065960338947)

--- END Proposal Phase ---

--- Decision Phase ---
RL update rl*prefer*rvt*predict-no*H0*6 1 0 1 -> 1 0 1(R,m,v=1,1,0)
=>WM: (15402: S1 ^operator O2191)

  1096:    O: O2191 (predict-yes)
--- END Decision Phase ---

--- Application Phase ---
	--- Firing Productions (PE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing apply*operator
 -->
 (I3 ^predict-yes N1096 +  :O )
Firing apply*operator*complete
 -->
 (I3 ^predict-no N1095 -  :O )
 inner elaboration loop at bottom goal.
	--- Change Working Memory (PE) ---
=>WM: (15403: I3 ^predict-yes N1096)
<=WM: (15390: N1095 ^status complete)
<=WM: (15389: I3 ^predict-no N1095)
	--- Firing Productions (IE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing monitor*world
 -->

I see 1 and I'm going to do: predict-yes inner elaboration loop at bottom goal.
	--- Change Working Memory (IE) ---

--- END Application Phase ---
--- Output Phase ---
ENV: Agent did: predict-yes for direction R in state State-A
In  State-A moving R
ENV: (next state, see, prediction correct?) = (State-B, 1, True)
predict error 0
dir: dir isL
--- END Output Phase ---
/|--- Input Phase --- 
=>WM: (15407: I2 ^dir L)
=>WM: (15406: I2 ^reward 1)
=>WM: (15405: I2 ^see 1)
=>WM: (15404: N1096 ^status complete)
<=WM: (15393: I2 ^dir R)
<=WM: (15392: I2 ^reward 1)
<=WM: (15391: I2 ^see 0)
=>WM: (15408: I2 ^level-1 R1-root)
<=WM: (15394: I2 ^level-1 L0-root)

--- END Input Phase --- 

--- Proposal Phase ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing rl*prefer*rvt*predict-yes*H0*1*H1*22
 -->
 (S1 ^operator O2191 = 0.4768789783581771)
Firing rl*prefer*rvt*predict-no*H0*2*H1*10
 -->
 (S1 ^operator O2192 = -0.01194930198035649)
Firing prefer*rvt*predict-no*H0*2*H1
 -->
Firing prefer*rvt*predict-yes*H0*1*H1
 -->
Firing elaborate*copy-see-to-output-link
 -->
 (I3 ^see 1 +)
Firing elaborate*reward*based*on*reward
 -->
 (R1100 ^value 1 +)
 (R1 ^reward R1100 +)
Firing propose*predict-yes
 -->
 (O2193 ^name predict-yes +)
 (S1 ^operator O2193 +)
Firing propose*predict-no
 -->
 (O2194 ^name predict-no +)
 (S1 ^operator O2194 +)
Firing rl*prefer*rvt*predict-no*H0*2
 -->
 (S1 ^operator O2192 = 0.2550133982564481)
Firing rl*prefer*rvt*predict-yes*H0*1
 -->
 (S1 ^operator O2191 = 0.5231191901978147)
Firing prefer*rvt*predict-yes*H0
 -->
Firing prefer*rvt*predict-no*H0
 -->
Firing elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir L +)
 inner elaboration loop at bottom goal.
Retracting elaborate*copy-see-to-output-link
 -->
 (I3 ^see 0 +)
Retracting propose*predict-no
 -->
 (O2192 ^name predict-no +)
 (S1 ^operator O2192 +)
Retracting propose*predict-yes
 -->
 (O2191 ^name predict-yes +)
 (S1 ^operator O2191 +)
Retracting elaborate*reward*based*on*reward
 -->
 (R1099 ^value 1 +)
 (R1 ^reward R1099 +)
Retracting elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir R +)
Retracting rl*prefer*rvt*predict-no*H0*4
 -->
 (S1 ^operator O2192 = 0.1269768216229884)
Retracting rl*prefer*rvt*predict-no*H0*4*H1*13
 -->
 (S1 ^operator O2192 = 0.4910065094545203)
Retracting rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O2191 = 0.3829435737675308)
Retracting rl*prefer*rvt*predict-yes*H0*3*H1*14
 -->
 (S1 ^operator O2191 = 0.617065960338947)
=>WM: (15416: S1 ^operator O2194 +)
=>WM: (15415: S1 ^operator O2193 +)
=>WM: (15414: I3 ^dir L)
=>WM: (15413: O2194 ^name predict-no)
=>WM: (15412: O2193 ^name predict-yes)
=>WM: (15411: R1100 ^value 1)
=>WM: (15410: R1 ^reward R1100)
=>WM: (15409: I3 ^see 1)
<=WM: (15400: S1 ^operator O2191 +)
<=WM: (15402: S1 ^operator O2191)
<=WM: (15401: S1 ^operator O2192 +)
<=WM: (15399: I3 ^dir R)
<=WM: (15395: R1 ^reward R1099)
<=WM: (15380: I3 ^see 0)
<=WM: (15398: O2192 ^name predict-no)
<=WM: (15397: O2191 ^name predict-yes)
<=WM: (15396: R1099 ^value 1)

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing prefer*rvt*predict-yes*H0
 -->
Firing rl*prefer*rvt*predict-yes*H0*1
 -->
 (S1 ^operator O2193 = 0.5231191901978147)
Firing prefer*rvt*predict-yes*H0*1*H1
 -->
Firing rl*prefer*rvt*predict-yes*H0*1*H1*22
 -->
 (S1 ^operator O2193 = 0.4768789783581771)
Firing prefer*rvt*predict-no*H0
 -->
Firing rl*prefer*rvt*predict-no*H0*2
 -->
 (S1 ^operator O2194 = 0.2550133982564481)
Firing prefer*rvt*predict-no*H0*2*H1
 -->
Firing rl*prefer*rvt*predict-no*H0*2*H1*10
 -->
 (S1 ^operator O2194 = -0.01194930198035649)
 inner elaboration loop at bottom goal.
Retracting rl*prefer*rvt*predict-no*H0*2
 -->
 (S1 ^operator O2192 = 0.2550133982564481)
Retracting rl*prefer*rvt*predict-no*H0*2*H1*10
 -->
 (S1 ^operator O2192 = -0.01194930198035649)
Retracting rl*prefer*rvt*predict-yes*H0*1
 -->
 (S1 ^operator O2191 = 0.5231191901978147)
Retracting rl*prefer*rvt*predict-yes*H0*1*H1*22
 -->
 (S1 ^operator O2191 = 0.4768789783581771)

--- END Proposal Phase ---

--- Decision Phase ---
RL update rl*prefer*rvt*predict-yes*H0*3 0.673136 -0.290193 0.382944 -> 0.673135 -0.290193 0.382942(R,m,v=1,0.964286,0.034645)
RL update rl*prefer*rvt*predict-yes*H0*3*H1*14 0.326872 0.290194 0.617066 -> 0.326871 0.290194 0.617065(R,m,v=1,1,0)
=>WM: (15417: S1 ^operator O2193)

  1097:    O: O2193 (predict-yes)
--- END Decision Phase ---

--- Application Phase ---
	--- Firing Productions (PE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing apply*operator
 -->
 (I3 ^predict-yes N1097 +  :O )
Firing apply*operator*complete
 -->
 (I3 ^predict-yes N1096 -  :O )
 inner elaboration loop at bottom goal.
	--- Change Working Memory (PE) ---
=>WM: (15418: I3 ^predict-yes N1097)
<=WM: (15404: N1096 ^status complete)
<=WM: (15403: I3 ^predict-yes N1096)
	--- Firing Productions (IE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing monitor*world
 -->

I see 1 and I'm going to do: predict-yes inner elaboration loop at bottom goal.
	--- Change Working Memory (IE) ---

--- END Application Phase ---
--- Output Phase ---
ENV: Agent did: predict-yes for direction L in state State-B
In  State-B moving L
ENV: (next state, see, prediction correct?) = (State-A, 1, True)
predict error 0
dir: dir isL
--- END Output Phase ---
\-/--- Input Phase --- 
=>WM: (15422: I2 ^dir L)
=>WM: (15421: I2 ^reward 1)
=>WM: (15420: I2 ^see 1)
=>WM: (15419: N1097 ^status complete)
<=WM: (15407: I2 ^dir L)
<=WM: (15406: I2 ^reward 1)
<=WM: (15405: I2 ^see 1)
=>WM: (15423: I2 ^level-1 L1-root)
<=WM: (15408: I2 ^level-1 R1-root)

--- END Input Phase --- 

--- Proposal Phase ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing rl*prefer*rvt*predict-yes*H0*1*H1*20
 -->
 (S1 ^operator O2193 = 0.1693592933936033)
Firing rl*prefer*rvt*predict-no*H0*2*H1*11
 -->
 (S1 ^operator O2194 = 0.7449865463572902)
Firing prefer*rvt*predict-no*H0*2*H1
 -->
Firing prefer*rvt*predict-yes*H0*1*H1
 -->
Firing elaborate*copy-see-to-output-link
 -->
 (I3 ^see 1 +)
Firing elaborate*reward*based*on*reward
 -->
 (R1101 ^value 1 +)
 (R1 ^reward R1101 +)
Firing propose*predict-yes
 -->
 (O2195 ^name predict-yes +)
 (S1 ^operator O2195 +)
Firing propose*predict-no
 -->
 (O2196 ^name predict-no +)
 (S1 ^operator O2196 +)
Firing rl*prefer*rvt*predict-no*H0*2
 -->
 (S1 ^operator O2194 = 0.2550133982564481)
Firing rl*prefer*rvt*predict-yes*H0*1
 -->
 (S1 ^operator O2193 = 0.5231191901978147)
Firing prefer*rvt*predict-yes*H0
 -->
Firing prefer*rvt*predict-no*H0
 -->
Firing elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir L +)
 inner elaboration loop at bottom goal.
Retracting elaborate*copy-see-to-output-link
 -->
 (I3 ^see 1 +)
Retracting propose*predict-no
 -->
 (O2194 ^name predict-no +)
 (S1 ^operator O2194 +)
Retracting propose*predict-yes
 -->
 (O2193 ^name predict-yes +)
 (S1 ^operator O2193 +)
Retracting elaborate*reward*based*on*reward
 -->
 (R1100 ^value 1 +)
 (R1 ^reward R1100 +)
Retracting elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir L +)
Retracting rl*prefer*rvt*predict-no*H0*2*H1*10
 -->
 (S1 ^operator O2194 = -0.01194930198035649)
Retracting rl*prefer*rvt*predict-no*H0*2
 -->
 (S1 ^operator O2194 = 0.2550133982564481)
Retracting rl*prefer*rvt*predict-yes*H0*1*H1*22
 -->
 (S1 ^operator O2193 = 0.4768789783581771)
Retracting rl*prefer*rvt*predict-yes*H0*1
 -->
 (S1 ^operator O2193 = 0.5231191901978147)
=>WM: (15429: S1 ^operator O2196 +)
=>WM: (15428: S1 ^operator O2195 +)
=>WM: (15427: O2196 ^name predict-no)
=>WM: (15426: O2195 ^name predict-yes)
=>WM: (15425: R1101 ^value 1)
=>WM: (15424: R1 ^reward R1101)
<=WM: (15415: S1 ^operator O2193 +)
<=WM: (15417: S1 ^operator O2193)
<=WM: (15416: S1 ^operator O2194 +)
<=WM: (15410: R1 ^reward R1100)
<=WM: (15413: O2194 ^name predict-no)
<=WM: (15412: O2193 ^name predict-yes)
<=WM: (15411: R1100 ^value 1)

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing prefer*rvt*predict-yes*H0
 -->
Firing rl*prefer*rvt*predict-yes*H0*1
 -->
 (S1 ^operator O2195 = 0.5231191901978147)
Firing prefer*rvt*predict-yes*H0*1*H1
 -->
Firing rl*prefer*rvt*predict-yes*H0*1*H1*20
 -->
 (S1 ^operator O2195 = 0.1693592933936033)
Firing prefer*rvt*predict-no*H0
 -->
Firing rl*prefer*rvt*predict-no*H0*2
 -->
 (S1 ^operator O2196 = 0.2550133982564481)
Firing prefer*rvt*predict-no*H0*2*H1
 -->
Firing rl*prefer*rvt*predict-no*H0*2*H1*11
 -->
 (S1 ^operator O2196 = 0.7449865463572902)
 inner elaboration loop at bottom goal.
Retracting rl*prefer*rvt*predict-no*H0*2
 -->
 (S1 ^operator O2194 = 0.2550133982564481)
Retracting rl*prefer*rvt*predict-no*H0*2*H1*11
 -->
 (S1 ^operator O2194 = 0.7449865463572902)
Retracting rl*prefer*rvt*predict-yes*H0*1
 -->
 (S1 ^operator O2193 = 0.5231191901978147)
Retracting rl*prefer*rvt*predict-yes*H0*1*H1*20
 -->
 (S1 ^operator O2193 = 0.1693592933936033)

--- END Proposal Phase ---

--- Decision Phase ---
RL update rl*prefer*rvt*predict-yes*H0*1 0.727959 -0.20484 0.523119 -> 0.727959 -0.20484 0.523119(R,m,v=1,0.981013,0.0187455)
RL update rl*prefer*rvt*predict-yes*H0*1*H1*22 0.272039 0.20484 0.476879 -> 0.272039 0.20484 0.476879(R,m,v=1,1,0)
=>WM: (15430: S1 ^operator O2196)

  1098:    O: O2196 (predict-no)
--- END Decision Phase ---

--- Application Phase ---
	--- Firing Productions (PE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing apply*operator
 -->
 (I3 ^predict-no N1098 +  :O )
Firing apply*operator*complete
 -->
 (I3 ^predict-yes N1097 -  :O )
 inner elaboration loop at bottom goal.
	--- Change Working Memory (PE) ---
=>WM: (15431: I3 ^predict-no N1098)
<=WM: (15419: N1097 ^status complete)
<=WM: (15418: I3 ^predict-yes N1097)
	--- Firing Productions (IE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing monitor*world
 -->

I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
	--- Change Working Memory (IE) ---

--- END Application Phase ---
--- Output Phase ---
ENV: Agent did: predict-no for direction L in state State-A
In  State-A moving L
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isR
--- END Output Phase ---
|\---- Input Phase --- 
=>WM: (15435: I2 ^dir R)
=>WM: (15434: I2 ^reward 1)
=>WM: (15433: I2 ^see 0)
=>WM: (15432: N1098 ^status complete)
<=WM: (15422: I2 ^dir L)
<=WM: (15421: I2 ^reward 1)
<=WM: (15420: I2 ^see 1)
=>WM: (15436: I2 ^level-1 L0-root)
<=WM: (15423: I2 ^level-1 L1-root)

--- END Input Phase --- 

--- Proposal Phase ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing rl*prefer*rvt*predict-yes*H0*3*H1*14
 -->
 (S1 ^operator O2195 = 0.6170645302229754)
Firing rl*prefer*rvt*predict-no*H0*4*H1*13
 -->
 (S1 ^operator O2196 = 0.4910065094545203)
Firing prefer*rvt*predict-no*H0*4*H1
 -->
Firing prefer*rvt*predict-yes*H0*3*H1
 -->
Firing elaborate*copy-see-to-output-link
 -->
 (I3 ^see 0 +)
Firing elaborate*reward*based*on*reward
 -->
 (R1102 ^value 1 +)
 (R1 ^reward R1102 +)
Firing propose*predict-yes
 -->
 (O2197 ^name predict-yes +)
 (S1 ^operator O2197 +)
Firing propose*predict-no
 -->
 (O2198 ^name predict-no +)
 (S1 ^operator O2198 +)
Firing rl*prefer*rvt*predict-no*H0*4
 -->
 (S1 ^operator O2196 = 0.1269768216229884)
Firing rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O2195 = 0.3829421436515592)
Firing prefer*rvt*predict-yes*H0
 -->
Firing prefer*rvt*predict-no*H0
 -->
Firing elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir R +)
 inner elaboration loop at bottom goal.
Retracting elaborate*copy-see-to-output-link
 -->
 (I3 ^see 1 +)
Retracting propose*predict-no
 -->
 (O2196 ^name predict-no +)
 (S1 ^operator O2196 +)
Retracting propose*predict-yes
 -->
 (O2195 ^name predict-yes +)
 (S1 ^operator O2195 +)
Retracting elaborate*reward*based*on*reward
 -->
 (R1101 ^value 1 +)
 (R1 ^reward R1101 +)
Retracting elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir L +)
Retracting rl*prefer*rvt*predict-no*H0*2*H1*11
 -->
 (S1 ^operator O2196 = 0.7449865463572902)
Retracting rl*prefer*rvt*predict-no*H0*2
 -->
 (S1 ^operator O2196 = 0.2550133982564481)
Retracting rl*prefer*rvt*predict-yes*H0*1*H1*20
 -->
 (S1 ^operator O2195 = 0.1693592933936033)
Retracting rl*prefer*rvt*predict-yes*H0*1
 -->
 (S1 ^operator O2195 = 0.5231194649144159)
=>WM: (15444: S1 ^operator O2198 +)
=>WM: (15443: S1 ^operator O2197 +)
=>WM: (15442: I3 ^dir R)
=>WM: (15441: O2198 ^name predict-no)
=>WM: (15440: O2197 ^name predict-yes)
=>WM: (15439: R1102 ^value 1)
=>WM: (15438: R1 ^reward R1102)
=>WM: (15437: I3 ^see 0)
<=WM: (15428: S1 ^operator O2195 +)
<=WM: (15429: S1 ^operator O2196 +)
<=WM: (15430: S1 ^operator O2196)
<=WM: (15414: I3 ^dir L)
<=WM: (15424: R1 ^reward R1101)
<=WM: (15409: I3 ^see 1)
<=WM: (15427: O2196 ^name predict-no)
<=WM: (15426: O2195 ^name predict-yes)
<=WM: (15425: R1101 ^value 1)

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing prefer*rvt*predict-yes*H0
 -->
Firing rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O2197 = 0.3829421436515592)
Firing prefer*rvt*predict-yes*H0*3*H1
 -->
Firing rl*prefer*rvt*predict-yes*H0*3*H1*14
 -->
 (S1 ^operator O2197 = 0.6170645302229754)
Firing prefer*rvt*predict-no*H0
 -->
Firing rl*prefer*rvt*predict-no*H0*4
 -->
 (S1 ^operator O2198 = 0.1269768216229884)
Firing prefer*rvt*predict-no*H0*4*H1
 -->
Firing rl*prefer*rvt*predict-no*H0*4*H1*13
 -->
 (S1 ^operator O2198 = 0.4910065094545203)
 inner elaboration loop at bottom goal.
Retracting rl*prefer*rvt*predict-no*H0*4
 -->
 (S1 ^operator O2196 = 0.1269768216229884)
Retracting rl*prefer*rvt*predict-no*H0*4*H1*13
 -->
 (S1 ^operator O2196 = 0.4910065094545203)
Retracting rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O2195 = 0.3829421436515592)
Retracting rl*prefer*rvt*predict-yes*H0*3*H1*14
 -->
 (S1 ^operator O2195 = 0.6170645302229754)

--- END Proposal Phase ---

--- Decision Phase ---
RL update rl*prefer*rvt*predict-no*H0*2 0.631495 -0.376482 0.255013 -> 0.631495 -0.376482 0.255013(R,m,v=1,0.922705,0.0716664)
RL update rl*prefer*rvt*predict-no*H0*2*H1*11 0.368505 0.376482 0.744987 -> 0.368505 0.376482 0.744987(R,m,v=1,1,0)
=>WM: (15445: S1 ^operator O2197)

  1099:    O: O2197 (predict-yes)
--- END Decision Phase ---

--- Application Phase ---
	--- Firing Productions (PE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing apply*operator
 -->
 (I3 ^predict-yes N1099 +  :O )
Firing apply*operator*complete
 -->
 (I3 ^predict-no N1098 -  :O )
 inner elaboration loop at bottom goal.
	--- Change Working Memory (PE) ---
=>WM: (15446: I3 ^predict-yes N1099)
<=WM: (15432: N1098 ^status complete)
<=WM: (15431: I3 ^predict-no N1098)
	--- Firing Productions (IE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing monitor*world
 -->

I see 1 and I'm going to do: predict-yes inner elaboration loop at bottom goal.
	--- Change Working Memory (IE) ---

--- END Application Phase ---
--- Output Phase ---
ENV: Agent did: predict-yes for direction R in state State-A
In  State-A moving R
ENV: (next state, see, prediction correct?) = (State-B, 1, True)
predict error 0
dir: dir isL
--- END Output Phase ---
/|\---- Input Phase --- 
=>WM: (15450: I2 ^dir L)
=>WM: (15449: I2 ^reward 1)
=>WM: (15448: I2 ^see 1)
=>WM: (15447: N1099 ^status complete)
<=WM: (15435: I2 ^dir R)
<=WM: (15434: I2 ^reward 1)
<=WM: (15433: I2 ^see 0)
=>WM: (15451: I2 ^level-1 R1-root)
<=WM: (15436: I2 ^level-1 L0-root)

--- END Input Phase --- 

--- Proposal Phase ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing rl*prefer*rvt*predict-yes*H0*1*H1*22
 -->
 (S1 ^operator O2197 = 0.4768792530747783)
Firing rl*prefer*rvt*predict-no*H0*2*H1*10
 -->
 (S1 ^operator O2198 = -0.01194930198035649)
Firing prefer*rvt*predict-no*H0*2*H1
 -->
Firing prefer*rvt*predict-yes*H0*1*H1
 -->
Firing elaborate*copy-see-to-output-link
 -->
 (I3 ^see 1 +)
Firing elaborate*reward*based*on*reward
 -->
 (R1103 ^value 1 +)
 (R1 ^reward R1103 +)
Firing propose*predict-yes
 -->
 (O2199 ^name predict-yes +)
 (S1 ^operator O2199 +)
Firing propose*predict-no
 -->
 (O2200 ^name predict-no +)
 (S1 ^operator O2200 +)
Firing rl*prefer*rvt*predict-no*H0*2
 -->
 (S1 ^operator O2198 = 0.2550134065643873)
Firing rl*prefer*rvt*predict-yes*H0*1
 -->
 (S1 ^operator O2197 = 0.5231194649144159)
Firing prefer*rvt*predict-yes*H0
 -->
Firing prefer*rvt*predict-no*H0
 -->
Firing elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir L +)
 inner elaboration loop at bottom goal.
Retracting elaborate*copy-see-to-output-link
 -->
 (I3 ^see 0 +)
Retracting propose*predict-no
 -->
 (O2198 ^name predict-no +)
 (S1 ^operator O2198 +)
Retracting propose*predict-yes
 -->
 (O2197 ^name predict-yes +)
 (S1 ^operator O2197 +)
Retracting elaborate*reward*based*on*reward
 -->
 (R1102 ^value 1 +)
 (R1 ^reward R1102 +)
Retracting elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir R +)
Retracting rl*prefer*rvt*predict-no*H0*4*H1*13
 -->
 (S1 ^operator O2198 = 0.4910065094545203)
Retracting rl*prefer*rvt*predict-no*H0*4
 -->
 (S1 ^operator O2198 = 0.1269768216229884)
Retracting rl*prefer*rvt*predict-yes*H0*3*H1*14
 -->
 (S1 ^operator O2197 = 0.6170645302229754)
Retracting rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O2197 = 0.3829421436515592)
=>WM: (15459: S1 ^operator O2200 +)
=>WM: (15458: S1 ^operator O2199 +)
=>WM: (15457: I3 ^dir L)
=>WM: (15456: O2200 ^name predict-no)
=>WM: (15455: O2199 ^name predict-yes)
=>WM: (15454: R1103 ^value 1)
=>WM: (15453: R1 ^reward R1103)
=>WM: (15452: I3 ^see 1)
<=WM: (15443: S1 ^operator O2197 +)
<=WM: (15445: S1 ^operator O2197)
<=WM: (15444: S1 ^operator O2198 +)
<=WM: (15442: I3 ^dir R)
<=WM: (15438: R1 ^reward R1102)
<=WM: (15437: I3 ^see 0)
<=WM: (15441: O2198 ^name predict-no)
<=WM: (15440: O2197 ^name predict-yes)
<=WM: (15439: R1102 ^value 1)

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing prefer*rvt*predict-yes*H0
 -->
Firing rl*prefer*rvt*predict-yes*H0*1
 -->
 (S1 ^operator O2199 = 0.5231194649144159)
Firing prefer*rvt*predict-yes*H0*1*H1
 -->
Firing rl*prefer*rvt*predict-yes*H0*1*H1*22
 -->
 (S1 ^operator O2199 = 0.4768792530747783)
Firing prefer*rvt*predict-no*H0
 -->
Firing rl*prefer*rvt*predict-no*H0*2
 -->
 (S1 ^operator O2200 = 0.2550134065643873)
Firing prefer*rvt*predict-no*H0*2*H1
 -->
Firing rl*prefer*rvt*predict-no*H0*2*H1*10
 -->
 (S1 ^operator O2200 = -0.01194930198035649)
 inner elaboration loop at bottom goal.
Retracting rl*prefer*rvt*predict-no*H0*2
 -->
 (S1 ^operator O2198 = 0.2550134065643873)
Retracting rl*prefer*rvt*predict-no*H0*2*H1*10
 -->
 (S1 ^operator O2198 = -0.01194930198035649)
Retracting rl*prefer*rvt*predict-yes*H0*1
 -->
 (S1 ^operator O2197 = 0.5231194649144159)
Retracting rl*prefer*rvt*predict-yes*H0*1*H1*22
 -->
 (S1 ^operator O2197 = 0.4768792530747783)

--- END Proposal Phase ---

--- Decision Phase ---
RL update rl*prefer*rvt*predict-yes*H0*3 0.673135 -0.290193 0.382942 -> 0.673134 -0.290193 0.382941(R,m,v=1,0.964497,0.0344463)
RL update rl*prefer*rvt*predict-yes*H0*3*H1*14 0.326871 0.290194 0.617065 -> 0.32687 0.290193 0.617064(R,m,v=1,1,0)
=>WM: (15460: S1 ^operator O2199)

  1100:    O: O2199 (predict-yes)
--- END Decision Phase ---

--- Application Phase ---
	--- Firing Productions (PE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing apply*operator
 -->
 (I3 ^predict-yes N1100 +  :O )
Firing apply*operator*complete
 -->
 (I3 ^predict-yes N1099 -  :O )
 inner elaboration loop at bottom goal.
	--- Change Working Memory (PE) ---
=>WM: (15461: I3 ^predict-yes N1100)
<=WM: (15447: N1099 ^status complete)
<=WM: (15446: I3 ^predict-yes N1099)
	--- Firing Productions (IE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing monitor*world
 -->

I see 1 and I'm going to do: predict-yes inner elaboration loop at bottom goal.
	--- Change Working Memory (IE) ---

--- END Application Phase ---
--- Output Phase ---
ENV: Agent did: predict-yes for direction L in state State-B
In  State-B moving L
ENV: (next state, see, prediction correct?) = (State-A, 1, True)
predict error 0
dir: dir isU
--- END Output Phase ---
/|\--- Input Phase --- 
=>WM: (15465: I2 ^dir U)
=>WM: (15464: I2 ^reward 1)
=>WM: (15463: I2 ^see 1)
=>WM: (15462: N1100 ^status complete)
<=WM: (15450: I2 ^dir L)
<=WM: (15449: I2 ^reward 1)
<=WM: (15448: I2 ^see 1)
=>WM: (15466: I2 ^level-1 L1-root)
<=WM: (15451: I2 ^level-1 R1-root)

--- END Input Phase --- 

--- Proposal Phase ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing elaborate*copy-see-to-output-link
 -->
 (I3 ^see 1 +)
Firing elaborate*reward*based*on*reward
 -->
 (R1104 ^value 1 +)
 (R1 ^reward R1104 +)
Firing propose*predict-yes
 -->
 (O2201 ^name predict-yes +)
 (S1 ^operator O2201 +)
Firing propose*predict-no
 -->
 (O2202 ^name predict-no +)
 (S1 ^operator O2202 +)
Firing rl*prefer*rvt*predict-no*H0*6
 -->
 (S1 ^operator O2200 = 0.9999999999999999)
Firing rl*prefer*rvt*predict-yes*H0*5
 -->
 (S1 ^operator O2199 = 0.)
Firing prefer*rvt*predict-yes*H0
 -->
Firing prefer*rvt*predict-no*H0
 -->
Firing elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir U +)
 inner elaboration loop at bottom goal.
Retracting elaborate*copy-see-to-output-link
 -->
 (I3 ^see 1 +)
Retracting propose*predict-no
 -->
 (O2200 ^name predict-no +)
 (S1 ^operator O2200 +)
Retracting propose*predict-yes
 -->
 (O2199 ^name predict-yes +)
 (S1 ^operator O2199 +)
Retracting elaborate*reward*based*on*reward
 -->
 (R1103 ^value 1 +)
 (R1 ^reward R1103 +)
Retracting elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir L +)
Retracting rl*prefer*rvt*predict-no*H0*2*H1*10
 -->
 (S1 ^operator O2200 = -0.01194930198035649)
Retracting rl*prefer*rvt*predict-no*H0*2
 -->
 (S1 ^operator O2200 = 0.2550134065643873)
Retracting rl*prefer*rvt*predict-yes*H0*1*H1*22
 -->
 (S1 ^operator O2199 = 0.4768792530747783)
Retracting rl*prefer*rvt*predict-yes*H0*1
 -->
 (S1 ^operator O2199 = 0.5231194649144159)
=>WM: (15473: S1 ^operator O2202 +)
=>WM: (15472: S1 ^operator O2201 +)
=>WM: (15471: I3 ^dir U)
=>WM: (15470: O2202 ^name predict-no)
=>WM: (15469: O2201 ^name predict-yes)
=>WM: (15468: R1104 ^value 1)
=>WM: (15467: R1 ^reward R1104)
<=WM: (15458: S1 ^operator O2199 +)
<=WM: (15460: S1 ^operator O2199)
<=WM: (15459: S1 ^operator O2200 +)
<=WM: (15457: I3 ^dir L)
<=WM: (15453: R1 ^reward R1103)
<=WM: (15456: O2200 ^name predict-no)
<=WM: (15455: O2199 ^name predict-yes)
<=WM: (15454: R1103 ^value 1)

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing prefer*rvt*predict-yes*H0
 -->
Firing rl*prefer*rvt*predict-yes*H0*5
 -->
 (S1 ^operator O2201 = 0.)
Firing prefer*rvt*predict-no*H0
 -->
Firing rl*prefer*rvt*predict-no*H0*6
 -->
 (S1 ^operator O2202 = 0.9999999999999999)
 inner elaboration loop at bottom goal.
Retracting rl*prefer*rvt*predict-no*H0*6
 -->
 (S1 ^operator O2200 = 0.9999999999999999)
Retracting rl*prefer*rvt*predict-yes*H0*5
 -->
 (S1 ^operator O2199 = 0.)

--- END Proposal Phase ---

--- Decision Phase ---
RL update rl*prefer*rvt*predict-yes*H0*1 0.727959 -0.20484 0.523119 -> 0.727959 -0.20484 0.52312(R,m,v=1,0.981132,0.0186291)
RL update rl*prefer*rvt*predict-yes*H0*1*H1*22 0.272039 0.20484 0.476879 -> 0.272039 0.20484 0.476879(R,m,v=1,1,0)
=>WM: (15474: S1 ^operator O2202)

  1101:    O: O2202 (predict-no)
--- END Decision Phase ---

--- Application Phase ---
	--- Firing Productions (PE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing apply*operator
 -->
 (I3 ^predict-no N1101 +  :O )
Firing apply*operator*complete
 -->
 (I3 ^predict-yes N1100 -  :O )
 inner elaboration loop at bottom goal.
	--- Change Working Memory (PE) ---
=>WM: (15475: I3 ^predict-no N1101)
<=WM: (15462: N1100 ^status complete)
<=WM: (15461: I3 ^predict-yes N1100)
	--- Firing Productions (IE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing monitor*world
 -->

I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
	--- Change Working Memory (IE) ---

--- END Application Phase ---
--- Output Phase ---
ENV: Agent did: predict-no for direction U in state State-A
In  State-A moving U
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isL
--- END Output Phase ---
---- Input Phase --- 
=>WM: (15479: I2 ^dir L)
=>WM: (15478: I2 ^reward 1)
=>WM: (15477: I2 ^see 0)
=>WM: (15476: N1101 ^status complete)
<=WM: (15465: I2 ^dir U)
<=WM: (15464: I2 ^reward 1)
<=WM: (15463: I2 ^see 1)
=>WM: (15480: I2 ^level-1 L1-root)
<=WM: (15466: I2 ^level-1 L1-root)

--- END Input Phase --- 

--- Proposal Phase ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing rl*prefer*rvt*predict-yes*H0*1*H1*20
 -->
 (S1 ^operator O2201 = 0.1693592933936033)
Firing rl*prefer*rvt*predict-no*H0*2*H1*11
 -->
 (S1 ^operator O2202 = 0.7449865546652295)
Firing prefer*rvt*predict-no*H0*2*H1
 -->
Firing prefer*rvt*predict-yes*H0*1*H1
 -->
Firing elaborate*copy-see-to-output-link
 -->
 (I3 ^see 0 +)
Firing elaborate*reward*based*on*reward
 -->
 (R1105 ^value 1 +)
 (R1 ^reward R1105 +)
Firing propose*predict-yes
 -->
 (O2203 ^name predict-yes +)
 (S1 ^operator O2203 +)
Firing propose*predict-no
 -->
 (O2204 ^name predict-no +)
 (S1 ^operator O2204 +)
Firing rl*prefer*rvt*predict-no*H0*2
 -->
 (S1 ^operator O2202 = 0.2550134065643873)
Firing rl*prefer*rvt*predict-yes*H0*1
 -->
 (S1 ^operator O2201 = 0.5231196572160367)
Firing prefer*rvt*predict-yes*H0
 -->
Firing prefer*rvt*predict-no*H0
 -->
Firing elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir L +)
 inner elaboration loop at bottom goal.
Retracting elaborate*copy-see-to-output-link
 -->
 (I3 ^see 1 +)
Retracting propose*predict-no
 -->
 (O2202 ^name predict-no +)
 (S1 ^operator O2202 +)
Retracting propose*predict-yes
 -->
 (O2201 ^name predict-yes +)
 (S1 ^operator O2201 +)
Retracting elaborate*reward*based*on*reward
 -->
 (R1104 ^value 1 +)
 (R1 ^reward R1104 +)
Retracting elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir U +)
Retracting rl*prefer*rvt*predict-no*H0*6
 -->
 (S1 ^operator O2202 = 0.9999999999999999)
Retracting rl*prefer*rvt*predict-yes*H0*5
 -->
 (S1 ^operator O2201 = 0.)
=>WM: (15488: S1 ^operator O2204 +)
=>WM: (15487: S1 ^operator O2203 +)
=>WM: (15486: I3 ^dir L)
=>WM: (15485: O2204 ^name predict-no)
=>WM: (15484: O2203 ^name predict-yes)
=>WM: (15483: R1105 ^value 1)
=>WM: (15482: R1 ^reward R1105)
=>WM: (15481: I3 ^see 0)
<=WM: (15472: S1 ^operator O2201 +)
<=WM: (15473: S1 ^operator O2202 +)
<=WM: (15474: S1 ^operator O2202)
<=WM: (15471: I3 ^dir U)
<=WM: (15467: R1 ^reward R1104)
<=WM: (15452: I3 ^see 1)
<=WM: (15470: O2202 ^name predict-no)
<=WM: (15469: O2201 ^name predict-yes)
<=WM: (15468: R1104 ^value 1)

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing prefer*rvt*predict-yes*H0
 -->
Firing rl*prefer*rvt*predict-yes*H0*1*H1*20
 -->
 (S1 ^operator O2203 = 0.1693592933936033)
Firing rl*prefer*rvt*predict-yes*H0*1
 -->
 (S1 ^operator O2203 = 0.5231196572160367)
Firing prefer*rvt*predict-yes*H0*1*H1
 -->
Firing prefer*rvt*predict-no*H0
 -->
Firing rl*prefer*rvt*predict-no*H0*2*H1*11
 -->
 (S1 ^operator O2204 = 0.7449865546652295)
Firing rl*prefer*rvt*predict-no*H0*2
 -->
 (S1 ^operator O2204 = 0.2550134065643873)
Firing prefer*rvt*predict-no*H0*2*H1
 -->
 inner elaboration loop at bottom goal.
Retracting rl*prefer*rvt*predict-no*H0*2
 -->
 (S1 ^operator O2202 = 0.2550134065643873)
Retracting rl*prefer*rvt*predict-no*H0*2*H1*11
 -->
 (S1 ^operator O2202 = 0.7449865546652295)
Retracting rl*prefer*rvt*predict-yes*H0*1
 -->
 (S1 ^operator O2201 = 0.5231196572160367)
Retracting rl*prefer*rvt*predict-yes*H0*1*H1*20
 -->
 (S1 ^operator O2201 = 0.1693592933936033)

--- END Proposal Phase ---

--- Decision Phase ---
RL update rl*prefer*rvt*predict-no*H0*6 1 0 1 -> 1 0 1(R,m,v=1,1,0)
=>WM: (15489: S1 ^operator O2204)

  1102:    O: O2204 (predict-no)
--- END Decision Phase ---

--- Application Phase ---
	--- Firing Productions (PE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing apply*operator
 -->
 (I3 ^predict-no N1102 +  :O )
Firing apply*operator*complete
 -->
 (I3 ^predict-no N1101 -  :O )
 inner elaboration loop at bottom goal.
	--- Change Working Memory (PE) ---
=>WM: (15490: I3 ^predict-no N1102)
<=WM: (15476: N1101 ^status complete)
<=WM: (15475: I3 ^predict-no N1101)
	--- Firing Productions (IE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing monitor*world
 -->

I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
	--- Change Working Memory (IE) ---

--- END Application Phase ---
--- Output Phase ---
ENV: Agent did: predict-no for direction L in state State-A
In  State-A moving L
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isL
--- END Output Phase ---
/|--- Input Phase --- 
=>WM: (15494: I2 ^dir L)
=>WM: (15493: I2 ^reward 1)
=>WM: (15492: I2 ^see 0)
=>WM: (15491: N1102 ^status complete)
<=WM: (15479: I2 ^dir L)
<=WM: (15478: I2 ^reward 1)
<=WM: (15477: I2 ^see 0)
=>WM: (15495: I2 ^level-1 L0-root)
<=WM: (15480: I2 ^level-1 L1-root)

--- END Input Phase --- 

--- Proposal Phase ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing rl*prefer*rvt*predict-yes*H0*1*H1*21
 -->
 (S1 ^operator O2203 = 0.3)
Firing rl*prefer*rvt*predict-no*H0*2*H1*12
 -->
 (S1 ^operator O2204 = 0.7449866452103731)
Firing prefer*rvt*predict-no*H0*2*H1
 -->
Firing prefer*rvt*predict-yes*H0*1*H1
 -->
Firing elaborate*copy-see-to-output-link
 -->
 (I3 ^see 0 +)
Firing elaborate*reward*based*on*reward
 -->
 (R1106 ^value 1 +)
 (R1 ^reward R1106 +)
Firing propose*predict-yes
 -->
 (O2205 ^name predict-yes +)
 (S1 ^operator O2205 +)
Firing propose*predict-no
 -->
 (O2206 ^name predict-no +)
 (S1 ^operator O2206 +)
Firing rl*prefer*rvt*predict-no*H0*2
 -->
 (S1 ^operator O2204 = 0.2550134065643873)
Firing rl*prefer*rvt*predict-yes*H0*1
 -->
 (S1 ^operator O2203 = 0.5231196572160367)
Firing prefer*rvt*predict-yes*H0
 -->
Firing prefer*rvt*predict-no*H0
 -->
Firing elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir L +)
 inner elaboration loop at bottom goal.
Retracting elaborate*copy-see-to-output-link
 -->
 (I3 ^see 0 +)
Retracting propose*predict-no
 -->
 (O2204 ^name predict-no +)
 (S1 ^operator O2204 +)
Retracting propose*predict-yes
 -->
 (O2203 ^name predict-yes +)
 (S1 ^operator O2203 +)
Retracting elaborate*reward*based*on*reward
 -->
 (R1105 ^value 1 +)
 (R1 ^reward R1105 +)
Retracting elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir L +)
Retracting rl*prefer*rvt*predict-no*H0*2
 -->
 (S1 ^operator O2204 = 0.2550134065643873)
Retracting rl*prefer*rvt*predict-no*H0*2*H1*11
 -->
 (S1 ^operator O2204 = 0.7449865546652295)
Retracting rl*prefer*rvt*predict-yes*H0*1
 -->
 (S1 ^operator O2203 = 0.5231196572160367)
Retracting rl*prefer*rvt*predict-yes*H0*1*H1*20
 -->
 (S1 ^operator O2203 = 0.1693592933936033)
=>WM: (15501: S1 ^operator O2206 +)
=>WM: (15500: S1 ^operator O2205 +)
=>WM: (15499: O2206 ^name predict-no)
=>WM: (15498: O2205 ^name predict-yes)
=>WM: (15497: R1106 ^value 1)
=>WM: (15496: R1 ^reward R1106)
<=WM: (15487: S1 ^operator O2203 +)
<=WM: (15488: S1 ^operator O2204 +)
<=WM: (15489: S1 ^operator O2204)
<=WM: (15482: R1 ^reward R1105)
<=WM: (15485: O2204 ^name predict-no)
<=WM: (15484: O2203 ^name predict-yes)
<=WM: (15483: R1105 ^value 1)

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing prefer*rvt*predict-yes*H0
 -->
Firing rl*prefer*rvt*predict-yes*H0*1
 -->
 (S1 ^operator O2205 = 0.5231196572160367)
Firing prefer*rvt*predict-yes*H0*1*H1
 -->
Firing rl*prefer*rvt*predict-yes*H0*1*H1*21
 -->
 (S1 ^operator O2205 = 0.3)
Firing prefer*rvt*predict-no*H0
 -->
Firing rl*prefer*rvt*predict-no*H0*2
 -->
 (S1 ^operator O2206 = 0.2550134065643873)
Firing prefer*rvt*predict-no*H0*2*H1
 -->
Firing rl*prefer*rvt*predict-no*H0*2*H1*12
 -->
 (S1 ^operator O2206 = 0.7449866452103731)
 inner elaboration loop at bottom goal.
Retracting rl*prefer*rvt*predict-no*H0*2
 -->
 (S1 ^operator O2204 = 0.2550134065643873)
Retracting rl*prefer*rvt*predict-no*H0*2*H1*12
 -->
 (S1 ^operator O2204 = 0.7449866452103731)
Retracting rl*prefer*rvt*predict-yes*H0*1
 -->
 (S1 ^operator O2203 = 0.5231196572160367)
Retracting rl*prefer*rvt*predict-yes*H0*1*H1*21
 -->
 (S1 ^operator O2203 = 0.3)

--- END Proposal Phase ---

--- Decision Phase ---
RL update rl*prefer*rvt*predict-no*H0*2 0.631495 -0.376482 0.255013 -> 0.631495 -0.376482 0.255013(R,m,v=1,0.923077,0.0713489)
RL update rl*prefer*rvt*predict-no*H0*2*H1*11 0.368505 0.376482 0.744987 -> 0.368505 0.376482 0.744987(R,m,v=1,1,0)
=>WM: (15502: S1 ^operator O2206)

  1103:    O: O2206 (predict-no)
--- END Decision Phase ---

--- Application Phase ---
	--- Firing Productions (PE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing apply*operator
 -->
 (I3 ^predict-no N1103 +  :O )
Firing apply*operator*complete
 -->
 (I3 ^predict-no N1102 -  :O )
 inner elaboration loop at bottom goal.
	--- Change Working Memory (PE) ---
=>WM: (15503: I3 ^predict-no N1103)
<=WM: (15491: N1102 ^status complete)
<=WM: (15490: I3 ^predict-no N1102)
	--- Firing Productions (IE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing monitor*world
 -->

I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
	--- Change Working Memory (IE) ---

--- END Application Phase ---
--- Output Phase ---
ENV: Agent did: predict-no for direction L in state State-A
In  State-A moving L
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isR
--- END Output Phase ---
\-/--- Input Phase --- 
=>WM: (15507: I2 ^dir R)
=>WM: (15506: I2 ^reward 1)
=>WM: (15505: I2 ^see 0)
=>WM: (15504: N1103 ^status complete)
<=WM: (15494: I2 ^dir L)
<=WM: (15493: I2 ^reward 1)
<=WM: (15492: I2 ^see 0)
=>WM: (15508: I2 ^level-1 L0-root)
<=WM: (15495: I2 ^level-1 L0-root)

--- END Input Phase --- 

--- Proposal Phase ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing rl*prefer*rvt*predict-yes*H0*3*H1*14
 -->
 (S1 ^operator O2205 = 0.6170635291417952)
Firing rl*prefer*rvt*predict-no*H0*4*H1*13
 -->
 (S1 ^operator O2206 = 0.4910065094545203)
Firing prefer*rvt*predict-no*H0*4*H1
 -->
Firing prefer*rvt*predict-yes*H0*3*H1
 -->
Firing elaborate*copy-see-to-output-link
 -->
 (I3 ^see 0 +)
Firing elaborate*reward*based*on*reward
 -->
 (R1107 ^value 1 +)
 (R1 ^reward R1107 +)
Firing propose*predict-yes
 -->
 (O2207 ^name predict-yes +)
 (S1 ^operator O2207 +)
Firing propose*predict-no
 -->
 (O2208 ^name predict-no +)
 (S1 ^operator O2208 +)
Firing rl*prefer*rvt*predict-no*H0*4
 -->
 (S1 ^operator O2206 = 0.1269768216229884)
Firing rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O2205 = 0.382941142570379)
Firing prefer*rvt*predict-yes*H0
 -->
Firing prefer*rvt*predict-no*H0
 -->
Firing elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir R +)
 inner elaboration loop at bottom goal.
Retracting elaborate*copy-see-to-output-link
 -->
 (I3 ^see 0 +)
Retracting propose*predict-no
 -->
 (O2206 ^name predict-no +)
 (S1 ^operator O2206 +)
Retracting propose*predict-yes
 -->
 (O2205 ^name predict-yes +)
 (S1 ^operator O2205 +)
Retracting elaborate*reward*based*on*reward
 -->
 (R1106 ^value 1 +)
 (R1 ^reward R1106 +)
Retracting elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir L +)
Retracting rl*prefer*rvt*predict-no*H0*2*H1*12
 -->
 (S1 ^operator O2206 = 0.7449866452103731)
Retracting rl*prefer*rvt*predict-no*H0*2
 -->
 (S1 ^operator O2206 = 0.2550134123799448)
Retracting rl*prefer*rvt*predict-yes*H0*1*H1*21
 -->
 (S1 ^operator O2205 = 0.3)
Retracting rl*prefer*rvt*predict-yes*H0*1
 -->
 (S1 ^operator O2205 = 0.5231196572160367)
=>WM: (15515: S1 ^operator O2208 +)
=>WM: (15514: S1 ^operator O2207 +)
=>WM: (15513: I3 ^dir R)
=>WM: (15512: O2208 ^name predict-no)
=>WM: (15511: O2207 ^name predict-yes)
=>WM: (15510: R1107 ^value 1)
=>WM: (15509: R1 ^reward R1107)
<=WM: (15500: S1 ^operator O2205 +)
<=WM: (15501: S1 ^operator O2206 +)
<=WM: (15502: S1 ^operator O2206)
<=WM: (15486: I3 ^dir L)
<=WM: (15496: R1 ^reward R1106)
<=WM: (15499: O2206 ^name predict-no)
<=WM: (15498: O2205 ^name predict-yes)
<=WM: (15497: R1106 ^value 1)

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing prefer*rvt*predict-yes*H0
 -->
Firing rl*prefer*rvt*predict-yes*H0*3*H1*14
 -->
 (S1 ^operator O2207 = 0.6170635291417952)
Firing rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O2207 = 0.382941142570379)
Firing prefer*rvt*predict-yes*H0*3*H1
 -->
Firing prefer*rvt*predict-no*H0
 -->
Firing rl*prefer*rvt*predict-no*H0*4*H1*13
 -->
 (S1 ^operator O2208 = 0.4910065094545203)
Firing rl*prefer*rvt*predict-no*H0*4
 -->
 (S1 ^operator O2208 = 0.1269768216229884)
Firing prefer*rvt*predict-no*H0*4*H1
 -->
 inner elaboration loop at bottom goal.
Retracting rl*prefer*rvt*predict-no*H0*4
 -->
 (S1 ^operator O2206 = 0.1269768216229884)
Retracting rl*prefer*rvt*predict-no*H0*4*H1*13
 -->
 (S1 ^operator O2206 = 0.4910065094545203)
Retracting rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O2205 = 0.382941142570379)
Retracting rl*prefer*rvt*predict-yes*H0*3*H1*14
 -->
 (S1 ^operator O2205 = 0.6170635291417952)

--- END Proposal Phase ---

--- Decision Phase ---
RL update rl*prefer*rvt*predict-no*H0*2 0.631495 -0.376482 0.255013 -> 0.631495 -0.376482 0.255013(R,m,v=1,0.923445,0.0710342)
RL update rl*prefer*rvt*predict-no*H0*2*H1*12 0.368505 0.376482 0.744987 -> 0.368505 0.376482 0.744987(R,m,v=1,1,0)
=>WM: (15516: S1 ^operator O2207)

  1104:    O: O2207 (predict-yes)
--- END Decision Phase ---

--- Application Phase ---
	--- Firing Productions (PE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing apply*operator
 -->
 (I3 ^predict-yes N1104 +  :O )
Firing apply*operator*complete
 -->
 (I3 ^predict-no N1103 -  :O )
 inner elaboration loop at bottom goal.
	--- Change Working Memory (PE) ---
=>WM: (15517: I3 ^predict-yes N1104)
<=WM: (15504: N1103 ^status complete)
<=WM: (15503: I3 ^predict-no N1103)
	--- Firing Productions (IE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing monitor*world
 -->

I see 1 and I'm going to do: predict-yes inner elaboration loop at bottom goal.
	--- Change Working Memory (IE) ---

--- END Application Phase ---
--- Output Phase ---
ENV: Agent did: predict-yes for direction R in state State-A
In  State-A moving R
ENV: (next state, see, prediction correct?) = (State-B, 1, True)
predict error 0
dir: dir isR
--- END Output Phase ---
|\---- Input Phase --- 
=>WM: (15521: I2 ^dir R)
=>WM: (15520: I2 ^reward 1)
=>WM: (15519: I2 ^see 1)
=>WM: (15518: N1104 ^status complete)
<=WM: (15507: I2 ^dir R)
<=WM: (15506: I2 ^reward 1)
<=WM: (15505: I2 ^see 0)
=>WM: (15522: I2 ^level-1 R1-root)
<=WM: (15508: I2 ^level-1 L0-root)

--- END Input Phase --- 

--- Proposal Phase ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing rl*prefer*rvt*predict-yes*H0*3*H1*16
 -->
 (S1 ^operator O2207 = 0.08783148430849691)
Firing rl*prefer*rvt*predict-no*H0*4*H1*15
 -->
 (S1 ^operator O2208 = 0.8730232062400305)
Firing prefer*rvt*predict-no*H0*4*H1
 -->
Firing prefer*rvt*predict-yes*H0*3*H1
 -->
Firing elaborate*copy-see-to-output-link
 -->
 (I3 ^see 1 +)
Firing elaborate*reward*based*on*reward
 -->
 (R1108 ^value 1 +)
 (R1 ^reward R1108 +)
Firing propose*predict-yes
 -->
 (O2209 ^name predict-yes +)
 (S1 ^operator O2209 +)
Firing propose*predict-no
 -->
 (O2210 ^name predict-no +)
 (S1 ^operator O2210 +)
Firing rl*prefer*rvt*predict-no*H0*4
 -->
 (S1 ^operator O2208 = 0.1269768216229884)
Firing rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O2207 = 0.382941142570379)
Firing prefer*rvt*predict-yes*H0
 -->
Firing prefer*rvt*predict-no*H0
 -->
Firing elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir R +)
 inner elaboration loop at bottom goal.
Retracting elaborate*copy-see-to-output-link
 -->
 (I3 ^see 0 +)
Retracting propose*predict-no
 -->
 (O2208 ^name predict-no +)
 (S1 ^operator O2208 +)
Retracting propose*predict-yes
 -->
 (O2207 ^name predict-yes +)
 (S1 ^operator O2207 +)
Retracting elaborate*reward*based*on*reward
 -->
 (R1107 ^value 1 +)
 (R1 ^reward R1107 +)
Retracting elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir R +)
Retracting rl*prefer*rvt*predict-no*H0*4
 -->
 (S1 ^operator O2208 = 0.1269768216229884)
Retracting rl*prefer*rvt*predict-no*H0*4*H1*13
 -->
 (S1 ^operator O2208 = 0.4910065094545203)
Retracting rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O2207 = 0.382941142570379)
Retracting rl*prefer*rvt*predict-yes*H0*3*H1*14
 -->
 (S1 ^operator O2207 = 0.6170635291417952)
=>WM: (15529: S1 ^operator O2210 +)
=>WM: (15528: S1 ^operator O2209 +)
=>WM: (15527: O2210 ^name predict-no)
=>WM: (15526: O2209 ^name predict-yes)
=>WM: (15525: R1108 ^value 1)
=>WM: (15524: R1 ^reward R1108)
=>WM: (15523: I3 ^see 1)
<=WM: (15514: S1 ^operator O2207 +)
<=WM: (15516: S1 ^operator O2207)
<=WM: (15515: S1 ^operator O2208 +)
<=WM: (15509: R1 ^reward R1107)
<=WM: (15481: I3 ^see 0)
<=WM: (15512: O2208 ^name predict-no)
<=WM: (15511: O2207 ^name predict-yes)
<=WM: (15510: R1107 ^value 1)

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing prefer*rvt*predict-yes*H0
 -->
Firing rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O2209 = 0.382941142570379)
Firing prefer*rvt*predict-yes*H0*3*H1
 -->
Firing rl*prefer*rvt*predict-yes*H0*3*H1*16
 -->
 (S1 ^operator O2209 = 0.08783148430849691)
Firing prefer*rvt*predict-no*H0
 -->
Firing rl*prefer*rvt*predict-no*H0*4
 -->
 (S1 ^operator O2210 = 0.1269768216229884)
Firing prefer*rvt*predict-no*H0*4*H1
 -->
Firing rl*prefer*rvt*predict-no*H0*4*H1*15
 -->
 (S1 ^operator O2210 = 0.8730232062400305)
 inner elaboration loop at bottom goal.
Retracting rl*prefer*rvt*predict-no*H0*4
 -->
 (S1 ^operator O2208 = 0.1269768216229884)
Retracting rl*prefer*rvt*predict-no*H0*4*H1*15
 -->
 (S1 ^operator O2208 = 0.8730232062400305)
Retracting rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O2207 = 0.382941142570379)
Retracting rl*prefer*rvt*predict-yes*H0*3*H1*16
 -->
 (S1 ^operator O2207 = 0.08783148430849691)

--- END Proposal Phase ---

--- Decision Phase ---
RL update rl*prefer*rvt*predict-yes*H0*3 0.673134 -0.290193 0.382941 -> 0.673134 -0.290193 0.38294(R,m,v=1,0.964706,0.0342499)
RL update rl*prefer*rvt*predict-yes*H0*3*H1*14 0.32687 0.290193 0.617064 -> 0.326869 0.290193 0.617063(R,m,v=1,1,0)
=>WM: (15530: S1 ^operator O2210)

  1105:    O: O2210 (predict-no)
--- END Decision Phase ---

--- Application Phase ---
	--- Firing Productions (PE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing apply*operator
 -->
 (I3 ^predict-no N1105 +  :O )
Firing apply*operator*complete
 -->
 (I3 ^predict-yes N1104 -  :O )
 inner elaboration loop at bottom goal.
	--- Change Working Memory (PE) ---
=>WM: (15531: I3 ^predict-no N1105)
<=WM: (15518: N1104 ^status complete)
<=WM: (15517: I3 ^predict-yes N1104)
	--- Firing Productions (IE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing monitor*world
 -->

I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
	--- Change Working Memory (IE) ---

--- END Application Phase ---
--- Output Phase ---
ENV: Agent did: predict-no for direction R in state State-B
In  State-B moving R
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isR
--- END Output Phase ---
/|--- Input Phase --- 
=>WM: (15535: I2 ^dir R)
=>WM: (15534: I2 ^reward 1)
=>WM: (15533: I2 ^see 0)
=>WM: (15532: N1105 ^status complete)
<=WM: (15521: I2 ^dir R)
<=WM: (15520: I2 ^reward 1)
<=WM: (15519: I2 ^see 1)
=>WM: (15536: I2 ^level-1 R0-root)
<=WM: (15522: I2 ^level-1 R1-root)

--- END Input Phase --- 

--- Proposal Phase ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing rl*prefer*rvt*predict-yes*H0*3*H1*18
 -->
 (S1 ^operator O2209 = 0.2696941111808541)
Firing rl*prefer*rvt*predict-no*H0*4*H1*17
 -->
 (S1 ^operator O2210 = 0.8730231457818302)
Firing prefer*rvt*predict-no*H0*4*H1
 -->
Firing prefer*rvt*predict-yes*H0*3*H1
 -->
Firing elaborate*copy-see-to-output-link
 -->
 (I3 ^see 0 +)
Firing elaborate*reward*based*on*reward
 -->
 (R1109 ^value 1 +)
 (R1 ^reward R1109 +)
Firing propose*predict-yes
 -->
 (O2211 ^name predict-yes +)
 (S1 ^operator O2211 +)
Firing propose*predict-no
 -->
 (O2212 ^name predict-no +)
 (S1 ^operator O2212 +)
Firing rl*prefer*rvt*predict-no*H0*4
 -->
 (S1 ^operator O2210 = 0.1269768216229884)
Firing rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O2209 = 0.3829404418135529)
Firing prefer*rvt*predict-yes*H0
 -->
Firing prefer*rvt*predict-no*H0
 -->
Firing elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir R +)
 inner elaboration loop at bottom goal.
Retracting elaborate*copy-see-to-output-link
 -->
 (I3 ^see 1 +)
Retracting propose*predict-no
 -->
 (O2210 ^name predict-no +)
 (S1 ^operator O2210 +)
Retracting propose*predict-yes
 -->
 (O2209 ^name predict-yes +)
 (S1 ^operator O2209 +)
Retracting elaborate*reward*based*on*reward
 -->
 (R1108 ^value 1 +)
 (R1 ^reward R1108 +)
Retracting elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir R +)
Retracting rl*prefer*rvt*predict-no*H0*4*H1*15
 -->
 (S1 ^operator O2210 = 0.8730232062400305)
Retracting rl*prefer*rvt*predict-no*H0*4
 -->
 (S1 ^operator O2210 = 0.1269768216229884)
Retracting rl*prefer*rvt*predict-yes*H0*3*H1*16
 -->
 (S1 ^operator O2209 = 0.08783148430849691)
Retracting rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O2209 = 0.3829404418135529)
=>WM: (15543: S1 ^operator O2212 +)
=>WM: (15542: S1 ^operator O2211 +)
=>WM: (15541: O2212 ^name predict-no)
=>WM: (15540: O2211 ^name predict-yes)
=>WM: (15539: R1109 ^value 1)
=>WM: (15538: R1 ^reward R1109)
=>WM: (15537: I3 ^see 0)
<=WM: (15528: S1 ^operator O2209 +)
<=WM: (15529: S1 ^operator O2210 +)
<=WM: (15530: S1 ^operator O2210)
<=WM: (15524: R1 ^reward R1108)
<=WM: (15523: I3 ^see 1)
<=WM: (15527: O2210 ^name predict-no)
<=WM: (15526: O2209 ^name predict-yes)
<=WM: (15525: R1108 ^value 1)

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing prefer*rvt*predict-yes*H0
 -->
Firing rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O2211 = 0.3829404418135529)
Firing prefer*rvt*predict-yes*H0*3*H1
 -->
Firing rl*prefer*rvt*predict-yes*H0*3*H1*18
 -->
 (S1 ^operator O2211 = 0.2696941111808541)
Firing prefer*rvt*predict-no*H0
 -->
Firing rl*prefer*rvt*predict-no*H0*4
 -->
 (S1 ^operator O2212 = 0.1269768216229884)
Firing prefer*rvt*predict-no*H0*4*H1
 -->
Firing rl*prefer*rvt*predict-no*H0*4*H1*17
 -->
 (S1 ^operator O2212 = 0.8730231457818302)
 inner elaboration loop at bottom goal.
Retracting rl*prefer*rvt*predict-no*H0*4
 -->
 (S1 ^operator O2210 = 0.1269768216229884)
Retracting rl*prefer*rvt*predict-no*H0*4*H1*17
 -->
 (S1 ^operator O2210 = 0.8730231457818302)
Retracting rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O2209 = 0.3829404418135529)
Retracting rl*prefer*rvt*predict-yes*H0*3*H1*18
 -->
 (S1 ^operator O2209 = 0.2696941111808541)

--- END Proposal Phase ---

--- Decision Phase ---
RL update rl*prefer*rvt*predict-no*H0*4 0.814714 -0.687737 0.126977 -> 0.814714 -0.687737 0.126977(R,m,v=1,0.955,0.043191)
RL update rl*prefer*rvt*predict-no*H0*4*H1*15 0.185286 0.687737 0.873023 -> 0.185286 0.687737 0.873023(R,m,v=1,1,0)
=>WM: (15544: S1 ^operator O2212)

  1106:    O: O2212 (predict-no)
--- END Decision Phase ---

--- Application Phase ---
	--- Firing Productions (PE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing apply*operator
 -->
 (I3 ^predict-no N1106 +  :O )
Firing apply*operator*complete
 -->
 (I3 ^predict-no N1105 -  :O )
 inner elaboration loop at bottom goal.
	--- Change Working Memory (PE) ---
=>WM: (15545: I3 ^predict-no N1106)
<=WM: (15532: N1105 ^status complete)
<=WM: (15531: I3 ^predict-no N1105)
	--- Firing Productions (IE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing monitor*world
 -->

I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
	--- Change Working Memory (IE) ---

--- END Application Phase ---
--- Output Phase ---
ENV: Agent did: predict-no for direction R in state State-B
In  State-B moving R
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isR
--- END Output Phase ---
\-/--- Input Phase --- 
=>WM: (15549: I2 ^dir R)
=>WM: (15548: I2 ^reward 1)
=>WM: (15547: I2 ^see 0)
=>WM: (15546: N1106 ^status complete)
<=WM: (15535: I2 ^dir R)
<=WM: (15534: I2 ^reward 1)
<=WM: (15533: I2 ^see 0)
=>WM: (15550: I2 ^level-1 R0-root)
<=WM: (15536: I2 ^level-1 R0-root)

--- END Input Phase --- 

--- Proposal Phase ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing rl*prefer*rvt*predict-yes*H0*3*H1*18
 -->
 (S1 ^operator O2211 = 0.2696941111808541)
Firing rl*prefer*rvt*predict-no*H0*4*H1*17
 -->
 (S1 ^operator O2212 = 0.8730231457818302)
Firing prefer*rvt*predict-no*H0*4*H1
 -->
Firing prefer*rvt*predict-yes*H0*3*H1
 -->
Firing elaborate*copy-see-to-output-link
 -->
 (I3 ^see 0 +)
Firing elaborate*reward*based*on*reward
 -->
 (R1110 ^value 1 +)
 (R1 ^reward R1110 +)
Firing propose*predict-yes
 -->
 (O2213 ^name predict-yes +)
 (S1 ^operator O2213 +)
Firing propose*predict-no
 -->
 (O2214 ^name predict-no +)
 (S1 ^operator O2214 +)
Firing rl*prefer*rvt*predict-no*H0*4
 -->
 (S1 ^operator O2212 = 0.1269768174435356)
Firing rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O2211 = 0.3829404418135529)
Firing prefer*rvt*predict-yes*H0
 -->
Firing prefer*rvt*predict-no*H0
 -->
Firing elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir R +)
 inner elaboration loop at bottom goal.
Retracting elaborate*copy-see-to-output-link
 -->
 (I3 ^see 0 +)
Retracting propose*predict-no
 -->
 (O2212 ^name predict-no +)
 (S1 ^operator O2212 +)
Retracting propose*predict-yes
 -->
 (O2211 ^name predict-yes +)
 (S1 ^operator O2211 +)
Retracting elaborate*reward*based*on*reward
 -->
 (R1109 ^value 1 +)
 (R1 ^reward R1109 +)
Retracting elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir R +)
Retracting rl*prefer*rvt*predict-no*H0*4*H1*17
 -->
 (S1 ^operator O2212 = 0.8730231457818302)
Retracting rl*prefer*rvt*predict-no*H0*4
 -->
 (S1 ^operator O2212 = 0.1269768174435356)
Retracting rl*prefer*rvt*predict-yes*H0*3*H1*18
 -->
 (S1 ^operator O2211 = 0.2696941111808541)
Retracting rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O2211 = 0.3829404418135529)
=>WM: (15556: S1 ^operator O2214 +)
=>WM: (15555: S1 ^operator O2213 +)
=>WM: (15554: O2214 ^name predict-no)
=>WM: (15553: O2213 ^name predict-yes)
=>WM: (15552: R1110 ^value 1)
=>WM: (15551: R1 ^reward R1110)
<=WM: (15542: S1 ^operator O2211 +)
<=WM: (15543: S1 ^operator O2212 +)
<=WM: (15544: S1 ^operator O2212)
<=WM: (15538: R1 ^reward R1109)
<=WM: (15541: O2212 ^name predict-no)
<=WM: (15540: O2211 ^name predict-yes)
<=WM: (15539: R1109 ^value 1)

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing prefer*rvt*predict-yes*H0
 -->
Firing rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O2213 = 0.3829404418135529)
Firing prefer*rvt*predict-yes*H0*3*H1
 -->
Firing rl*prefer*rvt*predict-yes*H0*3*H1*18
 -->
 (S1 ^operator O2213 = 0.2696941111808541)
Firing prefer*rvt*predict-no*H0
 -->
Firing rl*prefer*rvt*predict-no*H0*4
 -->
 (S1 ^operator O2214 = 0.1269768174435356)
Firing prefer*rvt*predict-no*H0*4*H1
 -->
Firing rl*prefer*rvt*predict-no*H0*4*H1*17
 -->
 (S1 ^operator O2214 = 0.8730231457818302)
 inner elaboration loop at bottom goal.
Retracting rl*prefer*rvt*predict-no*H0*4
 -->
 (S1 ^operator O2212 = 0.1269768174435356)
Retracting rl*prefer*rvt*predict-no*H0*4*H1*17
 -->
 (S1 ^operator O2212 = 0.8730231457818302)
Retracting rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O2211 = 0.3829404418135529)
Retracting rl*prefer*rvt*predict-yes*H0*3*H1*18
 -->
 (S1 ^operator O2211 = 0.2696941111808541)

--- END Proposal Phase ---

--- Decision Phase ---
RL update rl*prefer*rvt*predict-no*H0*4 0.814714 -0.687737 0.126977 -> 0.814714 -0.687737 0.126977(R,m,v=1,0.955224,0.0429851)
RL update rl*prefer*rvt*predict-no*H0*4*H1*17 0.185286 0.687737 0.873023 -> 0.185286 0.687737 0.873023(R,m,v=1,1,0)
=>WM: (15557: S1 ^operator O2214)

  1107:    O: O2214 (predict-no)
--- END Decision Phase ---

--- Application Phase ---
	--- Firing Productions (PE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing apply*operator
 -->
 (I3 ^predict-no N1107 +  :O )
Firing apply*operator*complete
 -->
 (I3 ^predict-no N1106 -  :O )
 inner elaboration loop at bottom goal.
	--- Change Working Memory (PE) ---
=>WM: (15558: I3 ^predict-no N1107)
<=WM: (15546: N1106 ^status complete)
<=WM: (15545: I3 ^predict-no N1106)
	--- Firing Productions (IE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing monitor*world
 -->

I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
	--- Change Working Memory (IE) ---

--- END Application Phase ---
--- Output Phase ---
ENV: Agent did: predict-no for direction R in state State-B
In  State-B moving R
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isR
--- END Output Phase ---
|\---- Input Phase --- 
=>WM: (15562: I2 ^dir R)
=>WM: (15561: I2 ^reward 1)
=>WM: (15560: I2 ^see 0)
=>WM: (15559: N1107 ^status complete)
<=WM: (15549: I2 ^dir R)
<=WM: (15548: I2 ^reward 1)
<=WM: (15547: I2 ^see 0)
=>WM: (15563: I2 ^level-1 R0-root)
<=WM: (15550: I2 ^level-1 R0-root)

--- END Input Phase --- 

--- Proposal Phase ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing rl*prefer*rvt*predict-yes*H0*3*H1*18
 -->
 (S1 ^operator O2213 = 0.2696941111808541)
Firing rl*prefer*rvt*predict-no*H0*4*H1*17
 -->
 (S1 ^operator O2214 = 0.8730231512980253)
Firing prefer*rvt*predict-no*H0*4*H1
 -->
Firing prefer*rvt*predict-yes*H0*3*H1
 -->
Firing elaborate*copy-see-to-output-link
 -->
 (I3 ^see 0 +)
Firing elaborate*reward*based*on*reward
 -->
 (R1111 ^value 1 +)
 (R1 ^reward R1111 +)
Firing propose*predict-yes
 -->
 (O2215 ^name predict-yes +)
 (S1 ^operator O2215 +)
Firing propose*predict-no
 -->
 (O2216 ^name predict-no +)
 (S1 ^operator O2216 +)
Firing rl*prefer*rvt*predict-no*H0*4
 -->
 (S1 ^operator O2214 = 0.1269768229597308)
Firing rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O2213 = 0.3829404418135529)
Firing prefer*rvt*predict-yes*H0
 -->
Firing prefer*rvt*predict-no*H0
 -->
Firing elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir R +)
 inner elaboration loop at bottom goal.
Retracting elaborate*copy-see-to-output-link
 -->
 (I3 ^see 0 +)
Retracting propose*predict-no
 -->
 (O2214 ^name predict-no +)
 (S1 ^operator O2214 +)
Retracting propose*predict-yes
 -->
 (O2213 ^name predict-yes +)
 (S1 ^operator O2213 +)
Retracting elaborate*reward*based*on*reward
 -->
 (R1110 ^value 1 +)
 (R1 ^reward R1110 +)
Retracting elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir R +)
Retracting rl*prefer*rvt*predict-no*H0*4*H1*17
 -->
 (S1 ^operator O2214 = 0.8730231512980253)
Retracting rl*prefer*rvt*predict-no*H0*4
 -->
 (S1 ^operator O2214 = 0.1269768229597308)
Retracting rl*prefer*rvt*predict-yes*H0*3*H1*18
 -->
 (S1 ^operator O2213 = 0.2696941111808541)
Retracting rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O2213 = 0.3829404418135529)
=>WM: (15569: S1 ^operator O2216 +)
=>WM: (15568: S1 ^operator O2215 +)
=>WM: (15567: O2216 ^name predict-no)
=>WM: (15566: O2215 ^name predict-yes)
=>WM: (15565: R1111 ^value 1)
=>WM: (15564: R1 ^reward R1111)
<=WM: (15555: S1 ^operator O2213 +)
<=WM: (15556: S1 ^operator O2214 +)
<=WM: (15557: S1 ^operator O2214)
<=WM: (15551: R1 ^reward R1110)
<=WM: (15554: O2214 ^name predict-no)
<=WM: (15553: O2213 ^name predict-yes)
<=WM: (15552: R1110 ^value 1)

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing prefer*rvt*predict-yes*H0
 -->
Firing rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O2215 = 0.3829404418135529)
Firing prefer*rvt*predict-yes*H0*3*H1
 -->
Firing rl*prefer*rvt*predict-yes*H0*3*H1*18
 -->
 (S1 ^operator O2215 = 0.2696941111808541)
Firing prefer*rvt*predict-no*H0
 -->
Firing rl*prefer*rvt*predict-no*H0*4
 -->
 (S1 ^operator O2216 = 0.1269768229597308)
Firing prefer*rvt*predict-no*H0*4*H1
 -->
Firing rl*prefer*rvt*predict-no*H0*4*H1*17
 -->
 (S1 ^operator O2216 = 0.8730231512980253)
 inner elaboration loop at bottom goal.
Retracting rl*prefer*rvt*predict-no*H0*4
 -->
 (S1 ^operator O2214 = 0.1269768229597308)
Retracting rl*prefer*rvt*predict-no*H0*4*H1*17
 -->
 (S1 ^operator O2214 = 0.8730231512980253)
Retracting rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O2213 = 0.3829404418135529)
Retracting rl*prefer*rvt*predict-yes*H0*3*H1*18
 -->
 (S1 ^operator O2213 = 0.2696941111808541)

--- END Proposal Phase ---

--- Decision Phase ---
RL update rl*prefer*rvt*predict-no*H0*4 0.814714 -0.687737 0.126977 -> 0.814714 -0.687737 0.126977(R,m,v=1,0.955446,0.0427811)
RL update rl*prefer*rvt*predict-no*H0*4*H1*17 0.185286 0.687737 0.873023 -> 0.185286 0.687737 0.873023(R,m,v=1,1,0)
=>WM: (15570: S1 ^operator O2216)

  1108:    O: O2216 (predict-no)
--- END Decision Phase ---

--- Application Phase ---
	--- Firing Productions (PE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing apply*operator
 -->
 (I3 ^predict-no N1108 +  :O )
Firing apply*operator*complete
 -->
 (I3 ^predict-no N1107 -  :O )
 inner elaboration loop at bottom goal.
	--- Change Working Memory (PE) ---
=>WM: (15571: I3 ^predict-no N1108)
<=WM: (15559: N1107 ^status complete)
<=WM: (15558: I3 ^predict-no N1107)
	--- Firing Productions (IE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing monitor*world
 -->

I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
	--- Change Working Memory (IE) ---

--- END Application Phase ---
--- Output Phase ---
ENV: Agent did: predict-no for direction R in state State-B
In  State-B moving R
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isR
--- END Output Phase ---
/|\--- Input Phase --- 
=>WM: (15575: I2 ^dir R)
=>WM: (15574: I2 ^reward 1)
=>WM: (15573: I2 ^see 0)
=>WM: (15572: N1108 ^status complete)
<=WM: (15562: I2 ^dir R)
<=WM: (15561: I2 ^reward 1)
<=WM: (15560: I2 ^see 0)
=>WM: (15576: I2 ^level-1 R0-root)
<=WM: (15563: I2 ^level-1 R0-root)

--- END Input Phase --- 

--- Proposal Phase ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing rl*prefer*rvt*predict-yes*H0*3*H1*18
 -->
 (S1 ^operator O2215 = 0.2696941111808541)
Firing rl*prefer*rvt*predict-no*H0*4*H1*17
 -->
 (S1 ^operator O2216 = 0.8730231551593619)
Firing prefer*rvt*predict-no*H0*4*H1
 -->
Firing prefer*rvt*predict-yes*H0*3*H1
 -->
Firing elaborate*copy-see-to-output-link
 -->
 (I3 ^see 0 +)
Firing elaborate*reward*based*on*reward
 -->
 (R1112 ^value 1 +)
 (R1 ^reward R1112 +)
Firing propose*predict-yes
 -->
 (O2217 ^name predict-yes +)
 (S1 ^operator O2217 +)
Firing propose*predict-no
 -->
 (O2218 ^name predict-no +)
 (S1 ^operator O2218 +)
Firing rl*prefer*rvt*predict-no*H0*4
 -->
 (S1 ^operator O2216 = 0.1269768268210674)
Firing rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O2215 = 0.3829404418135529)
Firing prefer*rvt*predict-yes*H0
 -->
Firing prefer*rvt*predict-no*H0
 -->
Firing elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir R +)
 inner elaboration loop at bottom goal.
Retracting elaborate*copy-see-to-output-link
 -->
 (I3 ^see 0 +)
Retracting propose*predict-no
 -->
 (O2216 ^name predict-no +)
 (S1 ^operator O2216 +)
Retracting propose*predict-yes
 -->
 (O2215 ^name predict-yes +)
 (S1 ^operator O2215 +)
Retracting elaborate*reward*based*on*reward
 -->
 (R1111 ^value 1 +)
 (R1 ^reward R1111 +)
Retracting elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir R +)
Retracting rl*prefer*rvt*predict-no*H0*4*H1*17
 -->
 (S1 ^operator O2216 = 0.8730231551593619)
Retracting rl*prefer*rvt*predict-no*H0*4
 -->
 (S1 ^operator O2216 = 0.1269768268210674)
Retracting rl*prefer*rvt*predict-yes*H0*3*H1*18
 -->
 (S1 ^operator O2215 = 0.2696941111808541)
Retracting rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O2215 = 0.3829404418135529)
=>WM: (15582: S1 ^operator O2218 +)
=>WM: (15581: S1 ^operator O2217 +)
=>WM: (15580: O2218 ^name predict-no)
=>WM: (15579: O2217 ^name predict-yes)
=>WM: (15578: R1112 ^value 1)
=>WM: (15577: R1 ^reward R1112)
<=WM: (15568: S1 ^operator O2215 +)
<=WM: (15569: S1 ^operator O2216 +)
<=WM: (15570: S1 ^operator O2216)
<=WM: (15564: R1 ^reward R1111)
<=WM: (15567: O2216 ^name predict-no)
<=WM: (15566: O2215 ^name predict-yes)
<=WM: (15565: R1111 ^value 1)

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing prefer*rvt*predict-yes*H0
 -->
Firing rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O2217 = 0.3829404418135529)
Firing prefer*rvt*predict-yes*H0*3*H1
 -->
Firing rl*prefer*rvt*predict-yes*H0*3*H1*18
 -->
 (S1 ^operator O2217 = 0.2696941111808541)
Firing prefer*rvt*predict-no*H0
 -->
Firing rl*prefer*rvt*predict-no*H0*4
 -->
 (S1 ^operator O2218 = 0.1269768268210674)
Firing prefer*rvt*predict-no*H0*4*H1
 -->
Firing rl*prefer*rvt*predict-no*H0*4*H1*17
 -->
 (S1 ^operator O2218 = 0.8730231551593619)
 inner elaboration loop at bottom goal.
Retracting rl*prefer*rvt*predict-no*H0*4
 -->
 (S1 ^operator O2216 = 0.1269768268210674)
Retracting rl*prefer*rvt*predict-no*H0*4*H1*17
 -->
 (S1 ^operator O2216 = 0.8730231551593619)
Retracting rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O2215 = 0.3829404418135529)
Retracting rl*prefer*rvt*predict-yes*H0*3*H1*18
 -->
 (S1 ^operator O2215 = 0.2696941111808541)

--- END Proposal Phase ---

--- Decision Phase ---
RL update rl*prefer*rvt*predict-no*H0*4 0.814714 -0.687737 0.126977 -> 0.814714 -0.687737 0.126977(R,m,v=1,0.955665,0.0425791)
RL update rl*prefer*rvt*predict-no*H0*4*H1*17 0.185286 0.687737 0.873023 -> 0.185286 0.687737 0.873023(R,m,v=1,1,0)
=>WM: (15583: S1 ^operator O2218)

  1109:    O: O2218 (predict-no)
--- END Decision Phase ---

--- Application Phase ---
	--- Firing Productions (PE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing apply*operator
 -->
 (I3 ^predict-no N1109 +  :O )
Firing apply*operator*complete
 -->
 (I3 ^predict-no N1108 -  :O )
 inner elaboration loop at bottom goal.
	--- Change Working Memory (PE) ---
=>WM: (15584: I3 ^predict-no N1109)
<=WM: (15572: N1108 ^status complete)
<=WM: (15571: I3 ^predict-no N1108)
	--- Firing Productions (IE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing monitor*world
 -->

I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
	--- Change Working Memory (IE) ---

--- END Application Phase ---
--- Output Phase ---
ENV: Agent did: predict-no for direction R in state State-B
In  State-B moving R
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isL
--- END Output Phase ---
-/--- Input Phase --- 
=>WM: (15588: I2 ^dir L)
=>WM: (15587: I2 ^reward 1)
=>WM: (15586: I2 ^see 0)
=>WM: (15585: N1109 ^status complete)
<=WM: (15575: I2 ^dir R)
<=WM: (15574: I2 ^reward 1)
<=WM: (15573: I2 ^see 0)
=>WM: (15589: I2 ^level-1 R0-root)
<=WM: (15576: I2 ^level-1 R0-root)

--- END Input Phase --- 

--- Proposal Phase ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing rl*prefer*rvt*predict-yes*H0*1*H1*19
 -->
 (S1 ^operator O2217 = 0.4768809184460345)
Firing rl*prefer*rvt*predict-no*H0*2*H1*7
 -->
 (S1 ^operator O2218 = 0.1700769046561409)
Firing prefer*rvt*predict-no*H0*2*H1
 -->
Firing prefer*rvt*predict-yes*H0*1*H1
 -->
Firing elaborate*copy-see-to-output-link
 -->
 (I3 ^see 0 +)
Firing elaborate*reward*based*on*reward
 -->
 (R1113 ^value 1 +)
 (R1 ^reward R1113 +)
Firing propose*predict-yes
 -->
 (O2219 ^name predict-yes +)
 (S1 ^operator O2219 +)
Firing propose*predict-no
 -->
 (O2220 ^name predict-no +)
 (S1 ^operator O2220 +)
Firing rl*prefer*rvt*predict-no*H0*2
 -->
 (S1 ^operator O2218 = 0.2550134037413971)
Firing rl*prefer*rvt*predict-yes*H0*1
 -->
 (S1 ^operator O2217 = 0.5231196572160367)
Firing prefer*rvt*predict-yes*H0
 -->
Firing prefer*rvt*predict-no*H0
 -->
Firing elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir L +)
 inner elaboration loop at bottom goal.
Retracting elaborate*copy-see-to-output-link
 -->
 (I3 ^see 0 +)
Retracting propose*predict-no
 -->
 (O2218 ^name predict-no +)
 (S1 ^operator O2218 +)
Retracting propose*predict-yes
 -->
 (O2217 ^name predict-yes +)
 (S1 ^operator O2217 +)
Retracting elaborate*reward*based*on*reward
 -->
 (R1112 ^value 1 +)
 (R1 ^reward R1112 +)
Retracting elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir R +)
Retracting rl*prefer*rvt*predict-no*H0*4*H1*17
 -->
 (S1 ^operator O2218 = 0.8730231578622976)
Retracting rl*prefer*rvt*predict-no*H0*4
 -->
 (S1 ^operator O2218 = 0.1269768295240029)
Retracting rl*prefer*rvt*predict-yes*H0*3*H1*18
 -->
 (S1 ^operator O2217 = 0.2696941111808541)
Retracting rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O2217 = 0.3829404418135529)
=>WM: (15596: S1 ^operator O2220 +)
=>WM: (15595: S1 ^operator O2219 +)
=>WM: (15594: I3 ^dir L)
=>WM: (15593: O2220 ^name predict-no)
=>WM: (15592: O2219 ^name predict-yes)
=>WM: (15591: R1113 ^value 1)
=>WM: (15590: R1 ^reward R1113)
<=WM: (15581: S1 ^operator O2217 +)
<=WM: (15582: S1 ^operator O2218 +)
<=WM: (15583: S1 ^operator O2218)
<=WM: (15513: I3 ^dir R)
<=WM: (15577: R1 ^reward R1112)
<=WM: (15580: O2218 ^name predict-no)
<=WM: (15579: O2217 ^name predict-yes)
<=WM: (15578: R1112 ^value 1)

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing prefer*rvt*predict-yes*H0
 -->
Firing rl*prefer*rvt*predict-yes*H0*1*H1*19
 -->
 (S1 ^operator O2219 = 0.4768809184460345)
Firing rl*prefer*rvt*predict-yes*H0*1
 -->
 (S1 ^operator O2219 = 0.5231196572160367)
Firing prefer*rvt*predict-yes*H0*1*H1
 -->
Firing prefer*rvt*predict-no*H0
 -->
Firing rl*prefer*rvt*predict-no*H0*2*H1*7
 -->
 (S1 ^operator O2220 = 0.1700769046561409)
Firing rl*prefer*rvt*predict-no*H0*2
 -->
 (S1 ^operator O2220 = 0.2550134037413971)
Firing prefer*rvt*predict-no*H0*2*H1
 -->
 inner elaboration loop at bottom goal.
Retracting rl*prefer*rvt*predict-no*H0*2
 -->
 (S1 ^operator O2218 = 0.2550134037413971)
Retracting rl*prefer*rvt*predict-no*H0*2*H1*7
 -->
 (S1 ^operator O2218 = 0.1700769046561409)
Retracting rl*prefer*rvt*predict-yes*H0*1
 -->
 (S1 ^operator O2217 = 0.5231196572160367)
Retracting rl*prefer*rvt*predict-yes*H0*1*H1*19
 -->
 (S1 ^operator O2217 = 0.4768809184460345)

--- END Proposal Phase ---

--- Decision Phase ---
RL update rl*prefer*rvt*predict-no*H0*4 0.814714 -0.687737 0.126977 -> 0.814714 -0.687737 0.126977(R,m,v=1,0.955882,0.042379)
RL update rl*prefer*rvt*predict-no*H0*4*H1*17 0.185286 0.687737 0.873023 -> 0.185286 0.687737 0.873023(R,m,v=1,1,0)
=>WM: (15597: S1 ^operator O2219)

  1110:    O: O2219 (predict-yes)
--- END Decision Phase ---

--- Application Phase ---
	--- Firing Productions (PE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing apply*operator
 -->
 (I3 ^predict-yes N1110 +  :O )
Firing apply*operator*complete
 -->
 (I3 ^predict-no N1109 -  :O )
 inner elaboration loop at bottom goal.
	--- Change Working Memory (PE) ---
=>WM: (15598: I3 ^predict-yes N1110)
<=WM: (15585: N1109 ^status complete)
<=WM: (15584: I3 ^predict-no N1109)
	--- Firing Productions (IE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing monitor*world
 -->

I see 1 and I'm going to do: predict-yes inner elaboration loop at bottom goal.
	--- Change Working Memory (IE) ---

--- END Application Phase ---
--- Output Phase ---
ENV: Agent did: predict-yes for direction L in state State-B
In  State-B moving L
ENV: (next state, see, prediction correct?) = (State-A, 1, True)
predict error 0
dir: dir isU
--- END Output Phase ---
|\---- Input Phase --- 
=>WM: (15602: I2 ^dir U)
=>WM: (15601: I2 ^reward 1)
=>WM: (15600: I2 ^see 1)
=>WM: (15599: N1110 ^status complete)
<=WM: (15588: I2 ^dir L)
<=WM: (15587: I2 ^reward 1)
<=WM: (15586: I2 ^see 0)
=>WM: (15603: I2 ^level-1 L1-root)
<=WM: (15589: I2 ^level-1 R0-root)

--- END Input Phase --- 

--- Proposal Phase ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing elaborate*copy-see-to-output-link
 -->
 (I3 ^see 1 +)
Firing elaborate*reward*based*on*reward
 -->
 (R1114 ^value 1 +)
 (R1 ^reward R1114 +)
Firing propose*predict-yes
 -->
 (O2221 ^name predict-yes +)
 (S1 ^operator O2221 +)
Firing propose*predict-no
 -->
 (O2222 ^name predict-no +)
 (S1 ^operator O2222 +)
Firing rl*prefer*rvt*predict-no*H0*6
 -->
 (S1 ^operator O2220 = 0.9999999999999999)
Firing rl*prefer*rvt*predict-yes*H0*5
 -->
 (S1 ^operator O2219 = 0.)
Firing prefer*rvt*predict-yes*H0
 -->
Firing prefer*rvt*predict-no*H0
 -->
Firing elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir U +)
 inner elaboration loop at bottom goal.
Retracting elaborate*copy-see-to-output-link
 -->
 (I3 ^see 0 +)
Retracting propose*predict-no
 -->
 (O2220 ^name predict-no +)
 (S1 ^operator O2220 +)
Retracting propose*predict-yes
 -->
 (O2219 ^name predict-yes +)
 (S1 ^operator O2219 +)
Retracting elaborate*reward*based*on*reward
 -->
 (R1113 ^value 1 +)
 (R1 ^reward R1113 +)
Retracting elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir L +)
Retracting rl*prefer*rvt*predict-no*H0*2
 -->
 (S1 ^operator O2220 = 0.2550134037413971)
Retracting rl*prefer*rvt*predict-no*H0*2*H1*7
 -->
 (S1 ^operator O2220 = 0.1700769046561409)
Retracting rl*prefer*rvt*predict-yes*H0*1
 -->
 (S1 ^operator O2219 = 0.5231196572160367)
Retracting rl*prefer*rvt*predict-yes*H0*1*H1*19
 -->
 (S1 ^operator O2219 = 0.4768809184460345)
=>WM: (15611: S1 ^operator O2222 +)
=>WM: (15610: S1 ^operator O2221 +)
=>WM: (15609: I3 ^dir U)
=>WM: (15608: O2222 ^name predict-no)
=>WM: (15607: O2221 ^name predict-yes)
=>WM: (15606: R1114 ^value 1)
=>WM: (15605: R1 ^reward R1114)
=>WM: (15604: I3 ^see 1)
<=WM: (15595: S1 ^operator O2219 +)
<=WM: (15597: S1 ^operator O2219)
<=WM: (15596: S1 ^operator O2220 +)
<=WM: (15594: I3 ^dir L)
<=WM: (15590: R1 ^reward R1113)
<=WM: (15537: I3 ^see 0)
<=WM: (15593: O2220 ^name predict-no)
<=WM: (15592: O2219 ^name predict-yes)
<=WM: (15591: R1113 ^value 1)

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing prefer*rvt*predict-yes*H0
 -->
Firing rl*prefer*rvt*predict-yes*H0*5
 -->
 (S1 ^operator O2221 = 0.)
Firing prefer*rvt*predict-no*H0
 -->
Firing rl*prefer*rvt*predict-no*H0*6
 -->
 (S1 ^operator O2222 = 0.9999999999999999)
 inner elaboration loop at bottom goal.
Retracting rl*prefer*rvt*predict-no*H0*6
 -->
 (S1 ^operator O2220 = 0.9999999999999999)
Retracting rl*prefer*rvt*predict-yes*H0*5
 -->
 (S1 ^operator O2219 = 0.)

--- END Proposal Phase ---

--- Decision Phase ---
RL update rl*prefer*rvt*predict-yes*H0*1 0.727959 -0.20484 0.52312 -> 0.727959 -0.20484 0.52312(R,m,v=1,0.98125,0.0185142)
RL update rl*prefer*rvt*predict-yes*H0*1*H1*19 0.272041 0.20484 0.476881 -> 0.272041 0.20484 0.476881(R,m,v=1,1,0)
=>WM: (15612: S1 ^operator O2222)

  1111:    O: O2222 (predict-no)
--- END Decision Phase ---

--- Application Phase ---
	--- Firing Productions (PE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing apply*operator
 -->
 (I3 ^predict-no N1111 +  :O )
Firing apply*operator*complete
 -->
 (I3 ^predict-yes N1110 -  :O )
 inner elaboration loop at bottom goal.
	--- Change Working Memory (PE) ---
=>WM: (15613: I3 ^predict-no N1111)
<=WM: (15599: N1110 ^status complete)
<=WM: (15598: I3 ^predict-yes N1110)
	--- Firing Productions (IE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing monitor*world
 -->

I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
	--- Change Working Memory (IE) ---

--- END Application Phase ---
--- Output Phase ---
ENV: Agent did: predict-no for direction U in state State-A
In  State-A moving U
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isU
--- END Output Phase ---
/--- Input Phase --- 
=>WM: (15617: I2 ^dir U)
=>WM: (15616: I2 ^reward 1)
=>WM: (15615: I2 ^see 0)
=>WM: (15614: N1111 ^status complete)
<=WM: (15602: I2 ^dir U)
<=WM: (15601: I2 ^reward 1)
<=WM: (15600: I2 ^see 1)
=>WM: (15618: I2 ^level-1 L1-root)
<=WM: (15603: I2 ^level-1 L1-root)

--- END Input Phase --- 

--- Proposal Phase ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing elaborate*copy-see-to-output-link
 -->
 (I3 ^see 0 +)
Firing elaborate*reward*based*on*reward
 -->
 (R1115 ^value 1 +)
 (R1 ^reward R1115 +)
Firing propose*predict-yes
 -->
 (O2223 ^name predict-yes +)
 (S1 ^operator O2223 +)
Firing propose*predict-no
 -->
 (O2224 ^name predict-no +)
 (S1 ^operator O2224 +)
Firing rl*prefer*rvt*predict-no*H0*6
 -->
 (S1 ^operator O2222 = 0.9999999999999999)
Firing rl*prefer*rvt*predict-yes*H0*5
 -->
 (S1 ^operator O2221 = 0.)
Firing prefer*rvt*predict-yes*H0
 -->
Firing prefer*rvt*predict-no*H0
 -->
Firing elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir U +)
 inner elaboration loop at bottom goal.
Retracting elaborate*copy-see-to-output-link
 -->
 (I3 ^see 1 +)
Retracting propose*predict-no
 -->
 (O2222 ^name predict-no +)
 (S1 ^operator O2222 +)
Retracting propose*predict-yes
 -->
 (O2221 ^name predict-yes +)
 (S1 ^operator O2221 +)
Retracting elaborate*reward*based*on*reward
 -->
 (R1114 ^value 1 +)
 (R1 ^reward R1114 +)
Retracting elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir U +)
Retracting rl*prefer*rvt*predict-no*H0*6
 -->
 (S1 ^operator O2222 = 0.9999999999999999)
Retracting rl*prefer*rvt*predict-yes*H0*5
 -->
 (S1 ^operator O2221 = 0.)
=>WM: (15625: S1 ^operator O2224 +)
=>WM: (15624: S1 ^operator O2223 +)
=>WM: (15623: O2224 ^name predict-no)
=>WM: (15622: O2223 ^name predict-yes)
=>WM: (15621: R1115 ^value 1)
=>WM: (15620: R1 ^reward R1115)
=>WM: (15619: I3 ^see 0)
<=WM: (15610: S1 ^operator O2221 +)
<=WM: (15611: S1 ^operator O2222 +)
<=WM: (15612: S1 ^operator O2222)
<=WM: (15605: R1 ^reward R1114)
<=WM: (15604: I3 ^see 1)
<=WM: (15608: O2222 ^name predict-no)
<=WM: (15607: O2221 ^name predict-yes)
<=WM: (15606: R1114 ^value 1)

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing prefer*rvt*predict-yes*H0
 -->
Firing rl*prefer*rvt*predict-yes*H0*5
 -->
 (S1 ^operator O2223 = 0.)
Firing prefer*rvt*predict-no*H0
 -->
Firing rl*prefer*rvt*predict-no*H0*6
 -->
 (S1 ^operator O2224 = 0.9999999999999999)
 inner elaboration loop at bottom goal.
Retracting rl*prefer*rvt*predict-no*H0*6
 -->
 (S1 ^operator O2222 = 0.9999999999999999)
Retracting rl*prefer*rvt*predict-yes*H0*5
 -->
 (S1 ^operator O2221 = 0.)

--- END Proposal Phase ---

--- Decision Phase ---
RL update rl*prefer*rvt*predict-no*H0*6 1 0 1 -> 1 0 1(R,m,v=1,1,0)
=>WM: (15626: S1 ^operator O2224)

  1112:    O: O2224 (predict-no)
--- END Decision Phase ---

--- Application Phase ---
	--- Firing Productions (PE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing apply*operator
 -->
 (I3 ^predict-no N1112 +  :O )
Firing apply*operator*complete
 -->
 (I3 ^predict-no N1111 -  :O )
 inner elaboration loop at bottom goal.
	--- Change Working Memory (PE) ---
=>WM: (15627: I3 ^predict-no N1112)
<=WM: (15614: N1111 ^status complete)
<=WM: (15613: I3 ^predict-no N1111)
	--- Firing Productions (IE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing monitor*world
 -->

I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
	--- Change Working Memory (IE) ---

--- END Application Phase ---
--- Output Phase ---
ENV: Agent did: predict-no for direction U in state State-A
In  State-A moving U
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isL
--- END Output Phase ---
|\--- Input Phase --- 
=>WM: (15631: I2 ^dir L)
=>WM: (15630: I2 ^reward 1)
=>WM: (15629: I2 ^see 0)
=>WM: (15628: N1112 ^status complete)
<=WM: (15617: I2 ^dir U)
<=WM: (15616: I2 ^reward 1)
<=WM: (15615: I2 ^see 0)
=>WM: (15632: I2 ^level-1 L1-root)
<=WM: (15618: I2 ^level-1 L1-root)

--- END Input Phase --- 

--- Proposal Phase ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing rl*prefer*rvt*predict-yes*H0*1*H1*20
 -->
 (S1 ^operator O2223 = 0.1693592933936033)
Firing rl*prefer*rvt*predict-no*H0*2*H1*11
 -->
 (S1 ^operator O2224 = 0.744986560480787)
Firing prefer*rvt*predict-no*H0*2*H1
 -->
Firing prefer*rvt*predict-yes*H0*1*H1
 -->
Firing elaborate*copy-see-to-output-link
 -->
 (I3 ^see 0 +)
Firing elaborate*reward*based*on*reward
 -->
 (R1116 ^value 1 +)
 (R1 ^reward R1116 +)
Firing propose*predict-yes
 -->
 (O2225 ^name predict-yes +)
 (S1 ^operator O2225 +)
Firing propose*predict-no
 -->
 (O2226 ^name predict-no +)
 (S1 ^operator O2226 +)
Firing rl*prefer*rvt*predict-no*H0*2
 -->
 (S1 ^operator O2224 = 0.2550134037413971)
Firing rl*prefer*rvt*predict-yes*H0*1
 -->
 (S1 ^operator O2223 = 0.5231195708667261)
Firing prefer*rvt*predict-yes*H0
 -->
Firing prefer*rvt*predict-no*H0
 -->
Firing elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir L +)
 inner elaboration loop at bottom goal.
Retracting elaborate*copy-see-to-output-link
 -->
 (I3 ^see 0 +)
Retracting propose*predict-no
 -->
 (O2224 ^name predict-no +)
 (S1 ^operator O2224 +)
Retracting propose*predict-yes
 -->
 (O2223 ^name predict-yes +)
 (S1 ^operator O2223 +)
Retracting elaborate*reward*based*on*reward
 -->
 (R1115 ^value 1 +)
 (R1 ^reward R1115 +)
Retracting elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir U +)
Retracting rl*prefer*rvt*predict-no*H0*6
 -->
 (S1 ^operator O2224 = 0.9999999999999999)
Retracting rl*prefer*rvt*predict-yes*H0*5
 -->
 (S1 ^operator O2223 = 0.)
=>WM: (15639: S1 ^operator O2226 +)
=>WM: (15638: S1 ^operator O2225 +)
=>WM: (15637: I3 ^dir L)
=>WM: (15636: O2226 ^name predict-no)
=>WM: (15635: O2225 ^name predict-yes)
=>WM: (15634: R1116 ^value 1)
=>WM: (15633: R1 ^reward R1116)
<=WM: (15624: S1 ^operator O2223 +)
<=WM: (15625: S1 ^operator O2224 +)
<=WM: (15626: S1 ^operator O2224)
<=WM: (15609: I3 ^dir U)
<=WM: (15620: R1 ^reward R1115)
<=WM: (15623: O2224 ^name predict-no)
<=WM: (15622: O2223 ^name predict-yes)
<=WM: (15621: R1115 ^value 1)

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing prefer*rvt*predict-yes*H0
 -->
Firing rl*prefer*rvt*predict-yes*H0*1*H1*20
 -->
 (S1 ^operator O2225 = 0.1693592933936033)
Firing rl*prefer*rvt*predict-yes*H0*1
 -->
 (S1 ^operator O2225 = 0.5231195708667261)
Firing prefer*rvt*predict-yes*H0*1*H1
 -->
Firing prefer*rvt*predict-no*H0
 -->
Firing rl*prefer*rvt*predict-no*H0*2*H1*11
 -->
 (S1 ^operator O2226 = 0.744986560480787)
Firing rl*prefer*rvt*predict-no*H0*2
 -->
 (S1 ^operator O2226 = 0.2550134037413971)
Firing prefer*rvt*predict-no*H0*2*H1
 -->
 inner elaboration loop at bottom goal.
Retracting rl*prefer*rvt*predict-no*H0*2
 -->
 (S1 ^operator O2224 = 0.2550134037413971)
Retracting rl*prefer*rvt*predict-no*H0*2*H1*11
 -->
 (S1 ^operator O2224 = 0.744986560480787)
Retracting rl*prefer*rvt*predict-yes*H0*1
 -->
 (S1 ^operator O2223 = 0.5231195708667261)
Retracting rl*prefer*rvt*predict-yes*H0*1*H1*20
 -->
 (S1 ^operator O2223 = 0.1693592933936033)

--- END Proposal Phase ---

--- Decision Phase ---
RL update rl*prefer*rvt*predict-no*H0*6 1 0 1 -> 1 0 1(R,m,v=1,1,0)
=>WM: (15640: S1 ^operator O2226)

  1113:    O: O2226 (predict-no)
--- END Decision Phase ---

--- Application Phase ---
	--- Firing Productions (PE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing apply*operator
 -->
 (I3 ^predict-no N1113 +  :O )
Firing apply*operator*complete
 -->
 (I3 ^predict-no N1112 -  :O )
 inner elaboration loop at bottom goal.
	--- Change Working Memory (PE) ---
=>WM: (15641: I3 ^predict-no N1113)
<=WM: (15628: N1112 ^status complete)
<=WM: (15627: I3 ^predict-no N1112)
	--- Firing Productions (IE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing monitor*world
 -->

I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
	--- Change Working Memory (IE) ---

--- END Application Phase ---
--- Output Phase ---
ENV: Agent did: predict-no for direction L in state State-A
In  State-A moving L
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isR
--- END Output Phase ---
-/--- Input Phase --- 
=>WM: (15645: I2 ^dir R)
=>WM: (15644: I2 ^reward 1)
=>WM: (15643: I2 ^see 0)
=>WM: (15642: N1113 ^status complete)
<=WM: (15631: I2 ^dir L)
<=WM: (15630: I2 ^reward 1)
<=WM: (15629: I2 ^see 0)
=>WM: (15646: I2 ^level-1 L0-root)
<=WM: (15632: I2 ^level-1 L1-root)

--- END Input Phase --- 

--- Proposal Phase ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing rl*prefer*rvt*predict-yes*H0*3*H1*14
 -->
 (S1 ^operator O2225 = 0.6170628283849691)
Firing rl*prefer*rvt*predict-no*H0*4*H1*13
 -->
 (S1 ^operator O2226 = 0.4910065094545203)
Firing prefer*rvt*predict-no*H0*4*H1
 -->
Firing prefer*rvt*predict-yes*H0*3*H1
 -->
Firing elaborate*copy-see-to-output-link
 -->
 (I3 ^see 0 +)
Firing elaborate*reward*based*on*reward
 -->
 (R1117 ^value 1 +)
 (R1 ^reward R1117 +)
Firing propose*predict-yes
 -->
 (O2227 ^name predict-yes +)
 (S1 ^operator O2227 +)
Firing propose*predict-no
 -->
 (O2228 ^name predict-no +)
 (S1 ^operator O2228 +)
Firing rl*prefer*rvt*predict-no*H0*4
 -->
 (S1 ^operator O2226 = 0.1269768314160579)
Firing rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O2225 = 0.3829404418135529)
Firing prefer*rvt*predict-yes*H0
 -->
Firing prefer*rvt*predict-no*H0
 -->
Firing elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir R +)
 inner elaboration loop at bottom goal.
Retracting elaborate*copy-see-to-output-link
 -->
 (I3 ^see 0 +)
Retracting propose*predict-no
 -->
 (O2226 ^name predict-no +)
 (S1 ^operator O2226 +)
Retracting propose*predict-yes
 -->
 (O2225 ^name predict-yes +)
 (S1 ^operator O2225 +)
Retracting elaborate*reward*based*on*reward
 -->
 (R1116 ^value 1 +)
 (R1 ^reward R1116 +)
Retracting elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir L +)
Retracting rl*prefer*rvt*predict-no*H0*2
 -->
 (S1 ^operator O2226 = 0.2550134037413971)
Retracting rl*prefer*rvt*predict-no*H0*2*H1*11
 -->
 (S1 ^operator O2226 = 0.744986560480787)
Retracting rl*prefer*rvt*predict-yes*H0*1
 -->
 (S1 ^operator O2225 = 0.5231195708667261)
Retracting rl*prefer*rvt*predict-yes*H0*1*H1*20
 -->
 (S1 ^operator O2225 = 0.1693592933936033)
=>WM: (15653: S1 ^operator O2228 +)
=>WM: (15652: S1 ^operator O2227 +)
=>WM: (15651: I3 ^dir R)
=>WM: (15650: O2228 ^name predict-no)
=>WM: (15649: O2227 ^name predict-yes)
=>WM: (15648: R1117 ^value 1)
=>WM: (15647: R1 ^reward R1117)
<=WM: (15638: S1 ^operator O2225 +)
<=WM: (15639: S1 ^operator O2226 +)
<=WM: (15640: S1 ^operator O2226)
<=WM: (15637: I3 ^dir L)
<=WM: (15633: R1 ^reward R1116)
<=WM: (15636: O2226 ^name predict-no)
<=WM: (15635: O2225 ^name predict-yes)
<=WM: (15634: R1116 ^value 1)

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing prefer*rvt*predict-yes*H0
 -->
Firing rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O2227 = 0.3829404418135529)
Firing prefer*rvt*predict-yes*H0*3*H1
 -->
Firing rl*prefer*rvt*predict-yes*H0*3*H1*14
 -->
 (S1 ^operator O2227 = 0.6170628283849691)
Firing prefer*rvt*predict-no*H0
 -->
Firing rl*prefer*rvt*predict-no*H0*4
 -->
 (S1 ^operator O2228 = 0.1269768314160579)
Firing prefer*rvt*predict-no*H0*4*H1
 -->
Firing rl*prefer*rvt*predict-no*H0*4*H1*13
 -->
 (S1 ^operator O2228 = 0.4910065094545203)
 inner elaboration loop at bottom goal.
Retracting rl*prefer*rvt*predict-no*H0*4
 -->
 (S1 ^operator O2226 = 0.1269768314160579)
Retracting rl*prefer*rvt*predict-no*H0*4*H1*13
 -->
 (S1 ^operator O2226 = 0.4910065094545203)
Retracting rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O2225 = 0.3829404418135529)
Retracting rl*prefer*rvt*predict-yes*H0*3*H1*14
 -->
 (S1 ^operator O2225 = 0.6170628283849691)

--- END Proposal Phase ---

--- Decision Phase ---
RL update rl*prefer*rvt*predict-no*H0*2 0.631495 -0.376482 0.255013 -> 0.631495 -0.376482 0.255013(R,m,v=1,0.92381,0.0707223)
RL update rl*prefer*rvt*predict-no*H0*2*H1*11 0.368505 0.376482 0.744987 -> 0.368505 0.376482 0.744987(R,m,v=1,1,0)
=>WM: (15654: S1 ^operator O2227)

  1114:    O: O2227 (predict-yes)
--- END Decision Phase ---

--- Application Phase ---
	--- Firing Productions (PE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing apply*operator
 -->
 (I3 ^predict-yes N1114 +  :O )
Firing apply*operator*complete
 -->
 (I3 ^predict-no N1113 -  :O )
 inner elaboration loop at bottom goal.
	--- Change Working Memory (PE) ---
=>WM: (15655: I3 ^predict-yes N1114)
<=WM: (15642: N1113 ^status complete)
<=WM: (15641: I3 ^predict-no N1113)
	--- Firing Productions (IE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing monitor*world
 -->

I see 1 and I'm going to do: predict-yes inner elaboration loop at bottom goal.
	--- Change Working Memory (IE) ---

--- END Application Phase ---
--- Output Phase ---
ENV: Agent did: predict-yes for direction R in state State-A
In  State-A moving R
ENV: (next state, see, prediction correct?) = (State-B, 1, True)
predict error 0
dir: dir isU
--- END Output Phase ---
|\--- Input Phase --- 
=>WM: (15659: I2 ^dir U)
=>WM: (15658: I2 ^reward 1)
=>WM: (15657: I2 ^see 1)
=>WM: (15656: N1114 ^status complete)
<=WM: (15645: I2 ^dir R)
<=WM: (15644: I2 ^reward 1)
<=WM: (15643: I2 ^see 0)
=>WM: (15660: I2 ^level-1 R1-root)
<=WM: (15646: I2 ^level-1 L0-root)

--- END Input Phase --- 

--- Proposal Phase ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing elaborate*copy-see-to-output-link
 -->
 (I3 ^see 1 +)
Firing elaborate*reward*based*on*reward
 -->
 (R1118 ^value 1 +)
 (R1 ^reward R1118 +)
Firing propose*predict-yes
 -->
 (O2229 ^name predict-yes +)
 (S1 ^operator O2229 +)
Firing propose*predict-no
 -->
 (O2230 ^name predict-no +)
 (S1 ^operator O2230 +)
Firing rl*prefer*rvt*predict-no*H0*6
 -->
 (S1 ^operator O2228 = 0.9999999999999999)
Firing rl*prefer*rvt*predict-yes*H0*5
 -->
 (S1 ^operator O2227 = 0.)
Firing prefer*rvt*predict-yes*H0
 -->
Firing prefer*rvt*predict-no*H0
 -->
Firing elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir U +)
 inner elaboration loop at bottom goal.
Retracting elaborate*copy-see-to-output-link
 -->
 (I3 ^see 0 +)
Retracting propose*predict-no
 -->
 (O2228 ^name predict-no +)
 (S1 ^operator O2228 +)
Retracting propose*predict-yes
 -->
 (O2227 ^name predict-yes +)
 (S1 ^operator O2227 +)
Retracting elaborate*reward*based*on*reward
 -->
 (R1117 ^value 1 +)
 (R1 ^reward R1117 +)
Retracting elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir R +)
Retracting rl*prefer*rvt*predict-no*H0*4*H1*13
 -->
 (S1 ^operator O2228 = 0.4910065094545203)
Retracting rl*prefer*rvt*predict-no*H0*4
 -->
 (S1 ^operator O2228 = 0.1269768314160579)
Retracting rl*prefer*rvt*predict-yes*H0*3*H1*14
 -->
 (S1 ^operator O2227 = 0.6170628283849691)
Retracting rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O2227 = 0.3829404418135529)
=>WM: (15668: S1 ^operator O2230 +)
=>WM: (15667: S1 ^operator O2229 +)
=>WM: (15666: I3 ^dir U)
=>WM: (15665: O2230 ^name predict-no)
=>WM: (15664: O2229 ^name predict-yes)
=>WM: (15663: R1118 ^value 1)
=>WM: (15662: R1 ^reward R1118)
=>WM: (15661: I3 ^see 1)
<=WM: (15652: S1 ^operator O2227 +)
<=WM: (15654: S1 ^operator O2227)
<=WM: (15653: S1 ^operator O2228 +)
<=WM: (15651: I3 ^dir R)
<=WM: (15647: R1 ^reward R1117)
<=WM: (15619: I3 ^see 0)
<=WM: (15650: O2228 ^name predict-no)
<=WM: (15649: O2227 ^name predict-yes)
<=WM: (15648: R1117 ^value 1)

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing prefer*rvt*predict-yes*H0
 -->
Firing rl*prefer*rvt*predict-yes*H0*5
 -->
 (S1 ^operator O2229 = 0.)
Firing prefer*rvt*predict-no*H0
 -->
Firing rl*prefer*rvt*predict-no*H0*6
 -->
 (S1 ^operator O2230 = 0.9999999999999999)
 inner elaboration loop at bottom goal.
Retracting rl*prefer*rvt*predict-no*H0*6
 -->
 (S1 ^operator O2228 = 0.9999999999999999)
Retracting rl*prefer*rvt*predict-yes*H0*5
 -->
 (S1 ^operator O2227 = 0.)

--- END Proposal Phase ---

--- Decision Phase ---
RL update rl*prefer*rvt*predict-yes*H0*3 0.673134 -0.290193 0.38294 -> 0.673133 -0.290193 0.38294(R,m,v=1,0.964912,0.0340557)
RL update rl*prefer*rvt*predict-yes*H0*3*H1*14 0.326869 0.290193 0.617063 -> 0.326869 0.290193 0.617062(R,m,v=1,1,0)
=>WM: (15669: S1 ^operator O2230)

  1115:    O: O2230 (predict-no)
--- END Decision Phase ---

--- Application Phase ---
	--- Firing Productions (PE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing apply*operator
 -->
 (I3 ^predict-no N1115 +  :O )
Firing apply*operator*complete
 -->
 (I3 ^predict-yes N1114 -  :O )
 inner elaboration loop at bottom goal.
	--- Change Working Memory (PE) ---
=>WM: (15670: I3 ^predict-no N1115)
<=WM: (15656: N1114 ^status complete)
<=WM: (15655: I3 ^predict-yes N1114)
	--- Firing Productions (IE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing monitor*world
 -->

I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
	--- Change Working Memory (IE) ---

--- END Application Phase ---
--- Output Phase ---
ENV: Agent did: predict-no for direction U in state State-B
In  State-B moving U
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isU
--- END Output Phase ---
-/|\sleeping...
---- Input Phase --- 
=>WM: (15674: I2 ^dir U)
=>WM: (15673: I2 ^reward 1)
=>WM: (15672: I2 ^see 0)
=>WM: (15671: N1115 ^status complete)
<=WM: (15659: I2 ^dir U)
<=WM: (15658: I2 ^reward 1)
<=WM: (15657: I2 ^see 1)
=>WM: (15675: I2 ^level-1 R1-root)
<=WM: (15660: I2 ^level-1 R1-root)

--- END Input Phase --- 

--- Proposal Phase ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing elaborate*copy-see-to-output-link
 -->
 (I3 ^see 0 +)
Firing elaborate*reward*based*on*reward
 -->
 (R1119 ^value 1 +)
 (R1 ^reward R1119 +)
Firing propose*predict-yes
 -->
 (O2231 ^name predict-yes +)
 (S1 ^operator O2231 +)
Firing propose*predict-no
 -->
 (O2232 ^name predict-no +)
 (S1 ^operator O2232 +)
Firing rl*prefer*rvt*predict-no*H0*6
 -->
 (S1 ^operator O2230 = 0.9999999999999999)
Firing rl*prefer*rvt*predict-yes*H0*5
 -->
 (S1 ^operator O2229 = 0.)
Firing prefer*rvt*predict-yes*H0
 -->
Firing prefer*rvt*predict-no*H0
 -->
Firing elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir U +)
 inner elaboration loop at bottom goal.
Retracting elaborate*copy-see-to-output-link
 -->
 (I3 ^see 1 +)
Retracting propose*predict-no
 -->
 (O2230 ^name predict-no +)
 (S1 ^operator O2230 +)
Retracting propose*predict-yes
 -->
 (O2229 ^name predict-yes +)
 (S1 ^operator O2229 +)
Retracting elaborate*reward*based*on*reward
 -->
 (R1118 ^value 1 +)
 (R1 ^reward R1118 +)
Retracting elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir U +)
Retracting rl*prefer*rvt*predict-no*H0*6
 -->
 (S1 ^operator O2230 = 0.9999999999999999)
Retracting rl*prefer*rvt*predict-yes*H0*5
 -->
 (S1 ^operator O2229 = 0.)
=>WM: (15682: S1 ^operator O2232 +)
=>WM: (15681: S1 ^operator O2231 +)
=>WM: (15680: O2232 ^name predict-no)
=>WM: (15679: O2231 ^name predict-yes)
=>WM: (15678: R1119 ^value 1)
=>WM: (15677: R1 ^reward R1119)
=>WM: (15676: I3 ^see 0)
<=WM: (15667: S1 ^operator O2229 +)
<=WM: (15668: S1 ^operator O2230 +)
<=WM: (15669: S1 ^operator O2230)
<=WM: (15662: R1 ^reward R1118)
<=WM: (15661: I3 ^see 1)
<=WM: (15665: O2230 ^name predict-no)
<=WM: (15664: O2229 ^name predict-yes)
<=WM: (15663: R1118 ^value 1)

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing prefer*rvt*predict-yes*H0
 -->
Firing rl*prefer*rvt*predict-yes*H0*5
 -->
 (S1 ^operator O2231 = 0.)
Firing prefer*rvt*predict-no*H0
 -->
Firing rl*prefer*rvt*predict-no*H0*6
 -->
 (S1 ^operator O2232 = 0.9999999999999999)
 inner elaboration loop at bottom goal.
Retracting rl*prefer*rvt*predict-no*H0*6
 -->
 (S1 ^operator O2230 = 0.9999999999999999)
Retracting rl*prefer*rvt*predict-yes*H0*5
 -->
 (S1 ^operator O2229 = 0.)

--- END Proposal Phase ---

--- Decision Phase ---
RL update rl*prefer*rvt*predict-no*H0*6 1 0 1 -> 1 0 1(R,m,v=1,1,0)
=>WM: (15683: S1 ^operator O2232)

  1116:    O: O2232 (predict-no)
--- END Decision Phase ---

--- Application Phase ---
	--- Firing Productions (PE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing apply*operator
 -->
 (I3 ^predict-no N1116 +  :O )
Firing apply*operator*complete
 -->
 (I3 ^predict-no N1115 -  :O )
 inner elaboration loop at bottom goal.
	--- Change Working Memory (PE) ---
=>WM: (15684: I3 ^predict-no N1116)
<=WM: (15671: N1115 ^status complete)
<=WM: (15670: I3 ^predict-no N1115)
	--- Firing Productions (IE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing monitor*world
 -->

I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
	--- Change Working Memory (IE) ---

--- END Application Phase ---
--- Output Phase ---
ENV: Agent did: predict-no for direction U in state State-B
In  State-B moving U
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isL
--- END Output Phase ---
/|--- Input Phase --- 
=>WM: (15688: I2 ^dir L)
=>WM: (15687: I2 ^reward 1)
=>WM: (15686: I2 ^see 0)
=>WM: (15685: N1116 ^status complete)
<=WM: (15674: I2 ^dir U)
<=WM: (15673: I2 ^reward 1)
<=WM: (15672: I2 ^see 0)
=>WM: (15689: I2 ^level-1 R1-root)
<=WM: (15675: I2 ^level-1 R1-root)

--- END Input Phase --- 

--- Proposal Phase ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing rl*prefer*rvt*predict-yes*H0*1*H1*22
 -->
 (S1 ^operator O2231 = 0.4768794453763991)
Firing rl*prefer*rvt*predict-no*H0*2*H1*10
 -->
 (S1 ^operator O2232 = -0.01194930198035649)
Firing prefer*rvt*predict-no*H0*2*H1
 -->
Firing prefer*rvt*predict-yes*H0*1*H1
 -->
Firing elaborate*copy-see-to-output-link
 -->
 (I3 ^see 0 +)
Firing elaborate*reward*based*on*reward
 -->
 (R1120 ^value 1 +)
 (R1 ^reward R1120 +)
Firing propose*predict-yes
 -->
 (O2233 ^name predict-yes +)
 (S1 ^operator O2233 +)
Firing propose*predict-no
 -->
 (O2234 ^name predict-no +)
 (S1 ^operator O2234 +)
Firing rl*prefer*rvt*predict-no*H0*2
 -->
 (S1 ^operator O2232 = 0.2550134091080695)
Firing rl*prefer*rvt*predict-yes*H0*1
 -->
 (S1 ^operator O2231 = 0.5231195708667261)
Firing prefer*rvt*predict-yes*H0
 -->
Firing prefer*rvt*predict-no*H0
 -->
Firing elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir L +)
 inner elaboration loop at bottom goal.
Retracting elaborate*copy-see-to-output-link
 -->
 (I3 ^see 0 +)
Retracting propose*predict-no
 -->
 (O2232 ^name predict-no +)
 (S1 ^operator O2232 +)
Retracting propose*predict-yes
 -->
 (O2231 ^name predict-yes +)
 (S1 ^operator O2231 +)
Retracting elaborate*reward*based*on*reward
 -->
 (R1119 ^value 1 +)
 (R1 ^reward R1119 +)
Retracting elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir U +)
Retracting rl*prefer*rvt*predict-no*H0*6
 -->
 (S1 ^operator O2232 = 0.9999999999999999)
Retracting rl*prefer*rvt*predict-yes*H0*5
 -->
 (S1 ^operator O2231 = 0.)
=>WM: (15696: S1 ^operator O2234 +)
=>WM: (15695: S1 ^operator O2233 +)
=>WM: (15694: I3 ^dir L)
=>WM: (15693: O2234 ^name predict-no)
=>WM: (15692: O2233 ^name predict-yes)
=>WM: (15691: R1120 ^value 1)
=>WM: (15690: R1 ^reward R1120)
<=WM: (15681: S1 ^operator O2231 +)
<=WM: (15682: S1 ^operator O2232 +)
<=WM: (15683: S1 ^operator O2232)
<=WM: (15666: I3 ^dir U)
<=WM: (15677: R1 ^reward R1119)
<=WM: (15680: O2232 ^name predict-no)
<=WM: (15679: O2231 ^name predict-yes)
<=WM: (15678: R1119 ^value 1)

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing prefer*rvt*predict-yes*H0
 -->
Firing rl*prefer*rvt*predict-yes*H0*1*H1*22
 -->
 (S1 ^operator O2233 = 0.4768794453763991)
Firing rl*prefer*rvt*predict-yes*H0*1
 -->
 (S1 ^operator O2233 = 0.5231195708667261)
Firing prefer*rvt*predict-yes*H0*1*H1
 -->
Firing prefer*rvt*predict-no*H0
 -->
Firing rl*prefer*rvt*predict-no*H0*2*H1*10
 -->
 (S1 ^operator O2234 = -0.01194930198035649)
Firing rl*prefer*rvt*predict-no*H0*2
 -->
 (S1 ^operator O2234 = 0.2550134091080695)
Firing prefer*rvt*predict-no*H0*2*H1
 -->
 inner elaboration loop at bottom goal.
Retracting rl*prefer*rvt*predict-no*H0*2
 -->
 (S1 ^operator O2232 = 0.2550134091080695)
Retracting rl*prefer*rvt*predict-no*H0*2*H1*10
 -->
 (S1 ^operator O2232 = -0.01194930198035649)
Retracting rl*prefer*rvt*predict-yes*H0*1
 -->
 (S1 ^operator O2231 = 0.5231195708667261)
Retracting rl*prefer*rvt*predict-yes*H0*1*H1*22
 -->
 (S1 ^operator O2231 = 0.4768794453763991)

--- END Proposal Phase ---

--- Decision Phase ---
RL update rl*prefer*rvt*predict-no*H0*6 1 0 1 -> 1 0 1(R,m,v=1,1,0)
=>WM: (15697: S1 ^operator O2233)

  1117:    O: O2233 (predict-yes)
--- END Decision Phase ---

--- Application Phase ---
	--- Firing Productions (PE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing apply*operator
 -->
 (I3 ^predict-yes N1117 +  :O )
Firing apply*operator*complete
 -->
 (I3 ^predict-no N1116 -  :O )
 inner elaboration loop at bottom goal.
	--- Change Working Memory (PE) ---
=>WM: (15698: I3 ^predict-yes N1117)
<=WM: (15685: N1116 ^status complete)
<=WM: (15684: I3 ^predict-no N1116)
	--- Firing Productions (IE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing monitor*world
 -->

I see 1 and I'm going to do: predict-yes inner elaboration loop at bottom goal.
	--- Change Working Memory (IE) ---

--- END Application Phase ---
--- Output Phase ---
ENV: Agent did: predict-yes for direction L in state State-B
In  State-B moving L
ENV: (next state, see, prediction correct?) = (State-A, 1, True)
predict error 0
dir: dir isL
--- END Output Phase ---
\-/--- Input Phase --- 
=>WM: (15702: I2 ^dir L)
=>WM: (15701: I2 ^reward 1)
=>WM: (15700: I2 ^see 1)
=>WM: (15699: N1117 ^status complete)
<=WM: (15688: I2 ^dir L)
<=WM: (15687: I2 ^reward 1)
<=WM: (15686: I2 ^see 0)
=>WM: (15703: I2 ^level-1 L1-root)
<=WM: (15689: I2 ^level-1 R1-root)

--- END Input Phase --- 

--- Proposal Phase ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing rl*prefer*rvt*predict-yes*H0*1*H1*20
 -->
 (S1 ^operator O2233 = 0.1693592933936033)
Firing rl*prefer*rvt*predict-no*H0*2*H1*11
 -->
 (S1 ^operator O2234 = 0.7449865658474594)
Firing prefer*rvt*predict-no*H0*2*H1
 -->
Firing prefer*rvt*predict-yes*H0*1*H1
 -->
Firing elaborate*copy-see-to-output-link
 -->
 (I3 ^see 1 +)
Firing elaborate*reward*based*on*reward
 -->
 (R1121 ^value 1 +)
 (R1 ^reward R1121 +)
Firing propose*predict-yes
 -->
 (O2235 ^name predict-yes +)
 (S1 ^operator O2235 +)
Firing propose*predict-no
 -->
 (O2236 ^name predict-no +)
 (S1 ^operator O2236 +)
Firing rl*prefer*rvt*predict-no*H0*2
 -->
 (S1 ^operator O2234 = 0.2550134091080695)
Firing rl*prefer*rvt*predict-yes*H0*1
 -->
 (S1 ^operator O2233 = 0.5231195708667261)
Firing prefer*rvt*predict-yes*H0
 -->
Firing prefer*rvt*predict-no*H0
 -->
Firing elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir L +)
 inner elaboration loop at bottom goal.
Retracting elaborate*copy-see-to-output-link
 -->
 (I3 ^see 0 +)
Retracting propose*predict-no
 -->
 (O2234 ^name predict-no +)
 (S1 ^operator O2234 +)
Retracting propose*predict-yes
 -->
 (O2233 ^name predict-yes +)
 (S1 ^operator O2233 +)
Retracting elaborate*reward*based*on*reward
 -->
 (R1120 ^value 1 +)
 (R1 ^reward R1120 +)
Retracting elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir L +)
Retracting rl*prefer*rvt*predict-no*H0*2
 -->
 (S1 ^operator O2234 = 0.2550134091080695)
Retracting rl*prefer*rvt*predict-no*H0*2*H1*10
 -->
 (S1 ^operator O2234 = -0.01194930198035649)
Retracting rl*prefer*rvt*predict-yes*H0*1
 -->
 (S1 ^operator O2233 = 0.5231195708667261)
Retracting rl*prefer*rvt*predict-yes*H0*1*H1*22
 -->
 (S1 ^operator O2233 = 0.4768794453763991)
=>WM: (15710: S1 ^operator O2236 +)
=>WM: (15709: S1 ^operator O2235 +)
=>WM: (15708: O2236 ^name predict-no)
=>WM: (15707: O2235 ^name predict-yes)
=>WM: (15706: R1121 ^value 1)
=>WM: (15705: R1 ^reward R1121)
=>WM: (15704: I3 ^see 1)
<=WM: (15695: S1 ^operator O2233 +)
<=WM: (15697: S1 ^operator O2233)
<=WM: (15696: S1 ^operator O2234 +)
<=WM: (15690: R1 ^reward R1120)
<=WM: (15676: I3 ^see 0)
<=WM: (15693: O2234 ^name predict-no)
<=WM: (15692: O2233 ^name predict-yes)
<=WM: (15691: R1120 ^value 1)

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing prefer*rvt*predict-yes*H0
 -->
Firing rl*prefer*rvt*predict-yes*H0*1
 -->
 (S1 ^operator O2235 = 0.5231195708667261)
Firing prefer*rvt*predict-yes*H0*1*H1
 -->
Firing rl*prefer*rvt*predict-yes*H0*1*H1*20
 -->
 (S1 ^operator O2235 = 0.1693592933936033)
Firing prefer*rvt*predict-no*H0
 -->
Firing rl*prefer*rvt*predict-no*H0*2
 -->
 (S1 ^operator O2236 = 0.2550134091080695)
Firing prefer*rvt*predict-no*H0*2*H1
 -->
Firing rl*prefer*rvt*predict-no*H0*2*H1*11
 -->
 (S1 ^operator O2236 = 0.7449865658474594)
 inner elaboration loop at bottom goal.
Retracting rl*prefer*rvt*predict-no*H0*2
 -->
 (S1 ^operator O2234 = 0.2550134091080695)
Retracting rl*prefer*rvt*predict-no*H0*2*H1*11
 -->
 (S1 ^operator O2234 = 0.7449865658474594)
Retracting rl*prefer*rvt*predict-yes*H0*1
 -->
 (S1 ^operator O2233 = 0.5231195708667261)
Retracting rl*prefer*rvt*predict-yes*H0*1*H1*20
 -->
 (S1 ^operator O2233 = 0.1693592933936033)

--- END Proposal Phase ---

--- Decision Phase ---
RL update rl*prefer*rvt*predict-yes*H0*1 0.727959 -0.20484 0.52312 -> 0.72796 -0.20484 0.52312(R,m,v=1,0.981366,0.0184006)
RL update rl*prefer*rvt*predict-yes*H0*1*H1*22 0.272039 0.20484 0.476879 -> 0.27204 0.20484 0.47688(R,m,v=1,1,0)
=>WM: (15711: S1 ^operator O2236)

  1118:    O: O2236 (predict-no)
--- END Decision Phase ---

--- Application Phase ---
	--- Firing Productions (PE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing apply*operator
 -->
 (I3 ^predict-no N1118 +  :O )
Firing apply*operator*complete
 -->
 (I3 ^predict-yes N1117 -  :O )
 inner elaboration loop at bottom goal.
	--- Change Working Memory (PE) ---
=>WM: (15712: I3 ^predict-no N1118)
<=WM: (15699: N1117 ^status complete)
<=WM: (15698: I3 ^predict-yes N1117)
	--- Firing Productions (IE) For State At Depth 1 ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing monitor*world
 -->

I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
	--- Change Working Memory (IE) ---

--- END Application Phase ---
--- Output Phase ---
ENV: Agent did: predict-no for direction L in state State-A
In  State-A moving L
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isR
--- END Output Phase ---
|\---- Input Phase --- 
=>WM: (15716: I2 ^dir R)
=>WM: (15715: I2 ^reward 1)
=>WM: (15714: I2 ^see 0)
=>WM: (15713: N1118 ^status complete)
<=WM: (15702: I2 ^dir L)
<=WM: (15701: I2 ^reward 1)
<=WM: (15700: I2 ^see 1)
=>WM: (15717: I2 ^level-1 L0-root)
<=WM: (15703: I2 ^level-1 L1-root)

--- END Input Phase --- 

--- Proposal Phase ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing rl*prefer*rvt*predict-yes*H0*3*H1*14
 -->
 (S1 ^operator O2235 = 0.6170623378551907)
Firing rl*prefer*rvt*predict-no*H0*4*H1*13
 -->
 (S1 ^operator O2236 = 0.4910065094545203)
Firing prefer*rvt*predict-no*H0*4*H1
 -->
Firing prefer*rvt*predict-yes*H0*3*H1
 -->
Firing elaborate*copy-see-to-output-link
 -->
 (I3 ^see 0 +)
Firing elaborate*reward*based*on*reward
 -->
 (R1122 ^value 1 +)
 (R1 ^reward R1122 +)
Firing propose*predict-yes
 -->
 (O2237 ^name predict-yes +)
 (S1 ^operator O2237 +)
Firing propose*predict-no
 -->
 (O2238 ^name predict-no +)
 (S1 ^operator O2238 +)
Firing rl*prefer*rvt*predict-no*H0*4
 -->
 (S1 ^operator O2236 = 0.1269768314160579)
Firing rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O2235 =