/flipv2/20121112-100543-2.5K-ReLST-Wallace/stdout-flip-2.5K_0.txt

Seeding... 0
dir: dir isU
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 0 ...

soar> Entering slave mode:
  - log file 'rl-slave-2.5K_0.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: O1 (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 isU
rule alias: '*'

rule alias: '*'

\-/|\-/|2:    O: O4 (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
\-/3:    O: O5 (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
|\4:    O: O7 (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
-/|5:    O: O9 (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
\-/6:    O: O11 (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
|\-/sleeping...
|7:    O: O14 (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
\-8:    O: O15 (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
/|9:    O: O17 (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
\-/10:    O: O19 (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
|\-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-B
In  State-B moving U
ENV: (next state, see, prediction correct?) = (State-B, 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-B
In  State-B moving R
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isL
|\13:    O: O26 (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
-/|\14:    O: O28 (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
-/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-A
In  State-A moving R
ENV: (next state, see, prediction correct?) = (State-B, 1, False)
predict error 1
dir: dir isL
|\-16:    O: O31 (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 isU
/|\17:    O: O34 (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
-/|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-A
In  State-A moving U
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isU
\-/19:    O: O38 (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
|\-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-A
In  State-A moving U
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isL
/|\-21:    O: O41 (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
/22:    O: O44 (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
|\-23:    O: O46 (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
/|\24:    O: O48 (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
-/25:    O: O50 (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
|\-26:    O: O51 (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
/|27:    O: O53 (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
\-/28:    O: O55 (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
|\-29:    O: O57 (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 isU
/|30:    O: O60 (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 isR
\-/31:    O: O61 (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
|32:    O: O64 (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
\-33:    O: O65 (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
/|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-A
In  State-A moving U
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isR
\-/35:    O: O69 (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
|\36:    O: O71 (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
-/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-A
In  State-A moving U
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isR
|\38:    O: O75 (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
-/39:    O: O77 (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
|\-40:    O: O80 (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
/|\41:    O: O81 (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
-42:    O: O83 (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
/|\43:    O: O86 (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
-/44:    O: O87 (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
|\45:    O: O89 (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
-/|46:    O: O92 (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
\-/47:    O: O93 (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 isR
|\48:    O: O96 (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
-/|49:    O: O97 (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 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-A
In  State-A moving U
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isU
|\-/|\sleeping...
-sleeping...
/sleeping...
|sleeping...
\sleeping...
-sleeping...
/sleeping...
|sleeping...
\sleeping...
-sleeping...
/sleeping...
|sleeping...
\sleeping...
-sleeping...
/sleeping...
|sleeping...
\sleeping...
-sleeping...
/sleeping...
|sleeping...
\sleeping...
-sleeping...
/sleeping...
|sleeping...
\sleeping...
-sleeping...
/sleeping...
|sleeping...
\sleeping...
-sleeping...
/sleeping...
|sleeping...
\sleeping...
-sleeping...
/sleeping...
|sleeping...
\sleeping...
-sleeping...
/sleeping...
|sleeping...
\sleeping...
-sleeping...
/sleeping...
|sleeping...
\sleeping...
-sleeping...
/sleeping...
|sleeping...
\sleeping...
-sleeping...
/sleeping...
|sleeping...
\sleeping...
-sleeping...
/sleeping...
|sleeping...
\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-A
In  State-A moving U
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isR
/52:    O: O104 (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
|\-53:    O: O106 (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
/|\54:    O: O107 (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 isR
-/|55:    O: O109 (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
\-56:    O: O112 (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
/|\57:    O: O114 (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
-/58:    O: O115 (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
|\-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-B
In  State-B moving U
ENV: (next state, see, prediction correct?) = (State-B, 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-B
In  State-B moving R
ENV: (next state, see, prediction correct?) = (State-B, 0, False)
predict error 1
dir: dir isU
-/61:    O: O122 (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 isR
rule alias: '*'

rule alias: '*'

rule alias: '*'

rule alias: '*'

rule alias: '*'

rule alias: '*'

rule alias: '*'

rule alias: '*'

rule alias: '*'

rule alias: '*'

rule alias: '*'

|62:    O: O123 (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
\-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-B
In  State-B moving U
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isR
/|64:    O: O127 (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
\-65:    O: O129 (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 isR
/|\66:    O: O131 (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 isR
-/|\67:    O: O133 (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 isR
-/68:    O: O135 (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 isR
|\69:    O: O138 (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
-/|\70:    O: O139 (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
-/71:    O: O141 (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 isL
rule alias: '*'

rule alias: '*'

rule alias: '*'

rule alias: '*'

rule alias: '*'

|72:    O: O143 (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 isR
\-/73:    O: O146 (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
|\-74:    O: O147 (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 isR
/|\75:    O: O150 (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
-/|76:    O: O151 (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
\-/77:    O: O154 (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
|\78:    O: O156 (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
-/|79:    O: O158 (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
\-80:    O: O160 (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
/|81:    O: O162 (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
rule alias: '*'

rule alias: '*'

rule alias: '*'

\82:    O: O164 (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
-/|83:    O: O165 (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
\-/84:    O: O168 (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
|\-85:    O: O169 (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
/|\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-B
In  State-B moving L
ENV: (next state, see, prediction correct?) = (State-A, 1, False)
predict error 1
dir: dir isU
-/|87:    O: O174 (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
\-/88:    O: O176 (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
|\-89:    O: O178 (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
/|\90:    O: O180 (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
-/91:    O: O182 (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 isR
rule alias: '*'

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 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
\-93:    O: O186 (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
/|94:    O: O187 (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
\-/95:    O: O189 (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 isU
|\-96:    O: O192 (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
/|\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-B
In  State-B moving U
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isL
-/98:    O: O195 (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
|\-99:    O: O197 (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
/|\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 isU
rule alias: '*'

\-/|\-/|\-/|\-/|\-/|\-/|\-/|\-/|\sleeping...
-sleeping...
/sleeping...
|sleeping...
\sleeping...
-sleeping...
/sleeping...
|sleeping...
\sleeping...
-sleeping...
/sleeping...
|sleeping...
\sleeping...
-sleeping...
/sleeping...
|sleeping...
\sleeping...
-sleeping...
/102:    O: O204 (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
|\103:    O: O206 (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
-/|104:    O: O208 (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
\-/105:    O: O209 (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 isL
|\106:    O: O211 (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 isU
-/|107:    O: O214 (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
\-108:    O: O215 (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
/|\109:    O: O218 (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
-/110:    O: O219 (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 isL
|\-111:    O: O221 (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 isU
rule alias: '*'

rule alias: '*'

rule alias: '*'

/112:    O: O224 (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
|\-113:    O: O225 (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 isR
/|\114:    O: O228 (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 isU
-/|115:    O: O230 (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 isR
\-116:    O: O232 (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
/|117:    O: O234 (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
\-/118:    O: O235 (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
|\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-A
In  State-A moving R
ENV: (next state, see, prediction correct?) = (State-B, 1, False)
predict error 1
dir: dir isR
-/|120:    O: O239 (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 isR
\-/121:    O: O242 (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
rule alias: '*'

rule alias: '*'

rule alias: '*'

rule alias: '*'

rule alias: '*'

rule alias: '*'

rule alias: '*'

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 isR
\-123:    O: O245 (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
/|\124:    O: O248 (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
-/|125:    O: O249 (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
\-/126:    O: O251 (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
|\-127:    O: O254 (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
/|\128:    O: O255 (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 isL
-/|129:    O: O257 (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
\-/130:    O: O259 (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 isU
|\-131:    O: O262 (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
/132:    O: O264 (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
|\133:    O: O265 (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 isR
-/|134:    O: O268 (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
\-/135:    O: O269 (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
|\-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-A
In  State-A moving L
ENV: (next state, see, prediction correct?) = (State-A, 0, False)
predict error 1
dir: dir isL
/|\-sleeping...
/137:    O: O274 (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
|\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-A
In  State-A moving R
ENV: (next state, see, prediction correct?) = (State-B, 1, False)
predict error 1
dir: dir isR
-/|139:    O: O278 (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
\-/140:    O: O279 (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
|\-141:    O: O282 (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: '*'

/142:    O: O283 (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
|\143:    O: O286 (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
-/|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-A
In  State-A moving U
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isL
\-/145:    O: O290 (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
|\146:    O: O292 (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
-/|147:    O: O294 (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
\-/148:    O: O296 (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
|\149:    O: O298 (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
-/|150:    O: O299 (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
\-/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-A
In  State-A moving U
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isU
|152:    O: O304 (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
\-/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 isU
|\-154:    O: O308 (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
/|\-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-A
In  State-A moving U
ENV: (next state, see, prediction correct?) = (State-A, 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-A
In  State-A moving R
ENV: (next state, see, prediction correct?) = (State-B, 1, False)
predict error 1
dir: dir isL
\-/157:    O: O313 (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
|\-158:    O: O316 (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
/|159:    O: O318 (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
\-/160:    O: O319 (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
|\-161:    O: O322 (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
/162:    O: O324 (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
|\-163:    O: O326 (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
/|\164:    O: O328 (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
-/|165:    O: O329 (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
\166:    O: O332 (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
-/|167:    O: O334 (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
\-/168:    O: O335 (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
|\169:    O: O338 (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
-/|170:    O: O339 (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 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 isL
\-/173:    O: O345 (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
|\-174:    O: O348 (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
/|\175:    O: O350 (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
-/|176:    O: O352 (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
\177:    O: O353 (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
-/|178:    O: O355 (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
\-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 isU
/|\180:    O: O360 (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
-/|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 isR
\-/184:    O: O368 (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
|\-185:    O: O370 (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
/|\186:    O: O372 (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
-/187:    O: O373 (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
|\188:    O: O376 (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
-/|189:    O: O377 (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
\-/190:    O: O379 (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
|\-191:    O: O381 (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
/192:    O: O384 (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
|\-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-B
In  State-B moving U
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isR
/|\194:    O: O388 (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
-/195:    O: O390 (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
|\-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 isU
/|\197:    O: O394 (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
-/198:    O: O396 (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
|\-199:    O: O398 (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
/|\200:    O: O399 (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
-/|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 isL
/|\203:    O: O406 (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
-/|204:    O: O407 (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
\205:    O: O410 (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
-/206:    O: O412 (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
|\-207:    O: O414 (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
/|\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-B
In  State-B moving U
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isR
-/209:    O: O418 (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
|\-210:    O: O419 (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
/|\211:    O: O421 (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
-212:    O: O424 (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
/|\213:    O: O426 (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
-214:    O: O428 (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
/|\215:    O: O429 (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
-/|216:    O: O432 (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
\-217:    O: O433 (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
/|\218:    O: O435 (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
-/|219:    O: O437 (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
\-/220:    O: O440 (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
|\-221:    O: O441 (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
/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-B
In  State-B moving U
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isL
|\-223:    O: O445 (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
/|224:    O: O448 (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
\-/225:    O: O450 (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
|226:    O: O452 (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
\-/227:    O: O454 (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
|228:    O: O455 (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
\-/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 isL
|\-230:    O: O460 (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
/|\231:    O: O462 (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
-232:    O: O464 (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
/|\233:    O: O465 (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
-/|234:    O: O468 (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
\-/235:    O: O470 (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
|\-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-A
In  State-A moving U
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isR
/|\237:    O: O473 (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
-/238:    O: O475 (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
|\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 isU
\-/|241:    O: O482 (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
\242:    O: O484 (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
-/|243:    O: O485 (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
\-244:    O: O487 (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
/|\245:    O: O490 (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
-/|246:    O: O492 (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
\-247:    O: O494 (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
/|248:    O: O495 (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
\-249:    O: O498 (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
/|\250:    O: O500 (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
-/|251:    O: O502 (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
\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 isU
-/253:    O: O506 (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
|\254:    O: O508 (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
-255:    O: O510 (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
/|\256:    O: O511 (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
-/|257:    O: O514 (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
\-258:    O: O516 (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
/|259:    O: O517 (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
\-/260:    O: O519 (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
|\-261:    O: O522 (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 isR
/262:    O: O524 (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
|\-263:    O: O526 (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
/|\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 isR
/|\266:    O: O531 (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
-/|267:    O: O534 (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
\-/268:    O: O536 (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
|\-269:    O: O537 (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
/|\270:    O: O540 (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
-/|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: O543 (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
-273:    O: O546 (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
/|\274:    O: O547 (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
-/|275:    O: O550 (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
\-/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-A
In  State-A moving U
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isL
|\-277:    O: O554 (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
/|278:    O: O555 (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
\-/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: O559 (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
-/|281:    O: O561 (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
\282:    O: O564 (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
-/|283:    O: O565 (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
\-/284:    O: O568 (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
|\-285:    O: O569 (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
/|\286:    O: O571 (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
-/287:    O: O573 (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
|288:    O: O575 (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
\-/|289:    O: O577 (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
\-290:    O: O579 (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
/|291:    O: O582 (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
\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 isU
-/|293:    O: O585 (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
\-294:    O: O587 (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
/|\295:    O: O590 (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
-/|296:    O: O592 (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
\-/297:    O: O594 (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
|\-298:    O: O596 (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
/|\299:    O: O597 (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
-/|300:    O: O600 (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
\-/|\-301:    O: O602 (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
/302:    O: O604 (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
|\303:    O: O605 (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
-/|304:    O: O608 (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
\-/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-B
In  State-B moving U
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isR
|\-306:    O: O612 (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
/|\307:    O: O613 (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
-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 isR
/312:    O: O623 (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
|\-313:    O: O626 (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
/|\314:    O: O628 (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
-/|315:    O: O630 (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
\-/316:    O: O632 (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
|\-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-B
In  State-B moving U
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isR
/|318:    O: O636 (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
\319:    O: O638 (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
-/|320:    O: O640 (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
\-/321:    O: O641 (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
|322:    O: O644 (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
\-323:    O: O645 (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
/|\324:    O: O648 (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
-/325:    O: O649 (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
|\-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 isU
/|\327:    O: O653 (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
-/|328:    O: O656 (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
\-/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 isR
\332:    O: O663 (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
-/333:    O: O665 (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
|\334:    O: O668 (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
-/|335:    O: O670 (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
\-336:    O: O672 (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
/|\337:    O: O674 (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
-/|338:    O: O676 (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
\-/339:    O: O677 (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
|\340:    O: O680 (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
-/341:    O: O681 (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
|342:    O: O684 (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
\-/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-A
In  State-A moving U
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isL
|\-344:    O: O688 (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
/|\345:    O: O689 (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
-/|346:    O: O692 (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
\-/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-B
In  State-B moving U
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isR
|\348:    O: O696 (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
-/|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-B
In  State-B moving U
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isL
\-350:    O: O699 (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
/|\351:    O: O701 (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
-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 isR
|\-355:    O: O710 (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
/|\356:    O: O711 (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
-/|357:    O: O713 (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
\-/358:    O: O716 (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
|\359:    O: O718 (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
-/|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 isU
-/364:    O: O728 (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
|\-365:    O: O730 (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
/|\366:    O: O731 (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
-/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-B
In  State-B moving U
ENV: (next state, see, prediction correct?) = (State-B, 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-B
In  State-B moving U
ENV: (next state, see, prediction correct?) = (State-B, 0, False)
predict error 1
dir: dir isL
\369:    O: O737 (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
-/370:    O: O740 (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
|\-371:    O: O742 (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
/372:    O: O744 (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
|\-373:    O: O746 (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
/|\374:    O: O748 (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
-/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 isU
|\376:    O: O752 (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
-/|377:    O: O754 (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
\-/378:    O: O756 (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
|\-379:    O: O758 (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
/|\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 isU
-/|381:    O: O762 (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
\382:    O: O764 (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
-/|383:    O: O766 (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
\-/384:    O: O768 (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
|385:    O: O770 (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
\-/386:    O: O772 (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
|\387:    O: O774 (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
-/|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 isU
/|\390:    O: O780 (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
-/391:    O: O782 (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
|392:    O: O784 (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
\-393:    O: O785 (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 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 isR
/|\396:    O: O792 (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
-/397:    O: O794 (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
|\398:    O: O796 (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
-/|399:    O: O798 (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
\-/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-B
In  State-B moving U
ENV: (next state, see, prediction correct?) = (State-B, 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-B
In  State-B moving U
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isR
/402:    O: O804 (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
|\-403:    O: O805 (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
/|\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 isR
-/405:    O: O809 (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
|\406:    O: O811 (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
-/|407:    O: O813 (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
\-/408:    O: O816 (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
|\-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 isL
/|\410:    O: O820 (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
-/|411:    O: O821 (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
\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-B
In  State-B moving U
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isL
-/|413:    O: O825 (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
\-/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 isL
|\-415:    O: O829 (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
/|\416:    O: O832 (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
-/417:    O: O834 (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
|\418:    O: O836 (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
-/|419:    O: O838 (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
\-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: O843 (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
/|423:    O: O846 (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
\-/424:    O: O848 (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
|\425:    O: O850 (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
-/|426:    O: O852 (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
\-/427:    O: O853 (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
|\-428:    O: O856 (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
/|\429:    O: O858 (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
-/|430:    O: O860 (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
\-/|431:    O: O861 (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 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: O868 (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
-/|435:    O: O870 (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
\-/436:    O: O871 (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
|\-437:    O: O873 (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
/|438:    O: O876 (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
\-/439:    O: O878 (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
|\-440:    O: O879 (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
/|\441:    O: O882 (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 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 isR
/|\443:    O: O886 (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
-/|444:    O: O888 (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
\-445:    O: O890 (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
/|446:    O: O892 (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
\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 isR
\-/449:    O: O897 (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
|\-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-B
In  State-B moving U
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isL
/451:    O: O901 (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
|452:    O: O904 (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
\-/453:    O: O906 (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
|\-454:    O: O908 (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
/|\-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-A
In  State-A moving U
ENV: (next state, see, prediction correct?) = (State-A, 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-A
In  State-A moving U
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isU
-/|457:    O: O914 (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
\-/458:    O: O915 (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
|\459:    O: O918 (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
-/460:    O: O919 (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
|\-461:    O: O922 (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
/462:    O: O923 (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
|\-463:    O: O926 (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
/|\464:    O: O928 (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
-/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-B
In  State-B moving U
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isL
|\466:    O: O931 (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
-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 isU
|\-470:    O: O940 (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
/|\471:    O: O942 (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
-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 isR
/|\473:    O: O946 (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
-/474:    O: O947 (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
|\-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 isU
|\-478:    O: O956 (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
/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-A
In  State-A moving U
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isR
|\-480:    O: O959 (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
/|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 isL
\482:    O: O964 (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
-/483:    O: O965 (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
|\-484:    O: O968 (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
/|\485:    O: O970 (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
-/|486:    O: O972 (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
\-487:    O: O974 (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
/|488:    O: O975 (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
\-/489:    O: O978 (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
|\-490:    O: O979 (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
/|\491:    O: O982 (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
-492:    O: O983 (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
/|\493:    O: O986 (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
-/|494:    O: O987 (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
\-495:    O: O990 (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
/|496:    O: O992 (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
\-/497:    O: O994 (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
|\-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 isL
/|\-499:    O: O998 (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
/|500:    O: O999 (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
\-/|\-501:    O: O1001 (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
/502:    O: O1003 (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
|\-503:    O: O1005 (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
/|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-A
In  State-A moving U
ENV: (next state, see, prediction correct?) = (State-A, 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-A
In  State-A moving U
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isL
/506:    O: O1012 (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
|\-507:    O: O1014 (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
/|508:    O: O1016 (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
\-/509:    O: O1018 (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
|\-510:    O: O1020 (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
/|\511:    O: O1022 (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
-512:    O: O1024 (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
/|\513:    O: O1026 (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
-/|514:    O: O1027 (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
\-/515:    O: O1029 (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
|516:    O: O1031 (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
\-/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-B
In  State-B moving U
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isL
|\-518:    O: O1035 (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
/|\-519:    O: O1038 (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
/|\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 isU
-/|521:    O: O1042 (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
\522:    O: O1043 (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
-/523:    O: O1046 (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
|\-524:    O: O1048 (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
/|\525:    O: O1050 (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
-/|526:    O: O1052 (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
\-/527:    O: O1054 (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
|\-528:    O: O1056 (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
/|\529:    O: O1057 (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
-/|530:    O: O1059 (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
\-/531:    O: O1062 (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
|532:    O: O1063 (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 isR
\-/533:    O: O1065 (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 isL
|\-534:    O: O1067 (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
/535:    O: O1070 (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
|\-/536:    O: O1072 (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
|\-537:    O: O1074 (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
/|\538:    O: O1076 (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
-/|539:    O: O1078 (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
\-/540:    O: O1080 (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
|\-541:    O: O1082 (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
/542:    O: O1083 (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
|\-543:    O: O1085 (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
/|544:    O: O1088 (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
\-/545:    O: O1090 (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
|\-546:    O: O1092 (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
/|\547:    O: O1094 (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
-/|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 isR
\-/549:    O: O1098 (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
|\550:    O: O1100 (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
-/551:    O: O1102 (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
|552:    O: O1103 (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 isR
\-/553:    O: O1106 (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
|\554:    O: O1107 (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
-/555:    O: O1109 (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
|556:    O: O1112 (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
\-/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-B
In  State-B moving U
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isL
|\-558:    O: O1115 (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
/|\559:    O: O1117 (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
-/|560:    O: O1120 (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
\-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 isL
/562:    O: O1123 (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
|\563:    O: O1126 (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
-/|564:    O: O1128 (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
\-565:    O: O1129 (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
/|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 isL
|\-568:    O: O1135 (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
/|\569:    O: O1137 (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
-/|570:    O: O1140 (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
\-/571:    O: O1142 (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
|572:    O: O1144 (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
\-/573:    O: O1146 (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
|\-574:    O: O1148 (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
/|\575:    O: O1150 (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
-/|576:    O: O1151 (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
\-577:    O: O1153 (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
/|578:    O: O1156 (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
\-/579:    O: O1157 (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
|\-580:    O: O1159 (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
/|581:    O: O1162 (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
\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-B
In  State-B moving R
ENV: (next state, see, prediction correct?) = (State-B, 0, False)
predict error 1
dir: dir isL
-/|583:    O: O1165 (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
\-584:    O: O1168 (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
/|\585:    O: O1170 (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
-/|586:    O: O1171 (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
\-/587:    O: O1173 (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
|\588:    O: O1176 (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
-/589:    O: O1178 (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
|\590:    O: O1179 (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
-/|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 isU
-/593:    O: O1186 (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
|\-594:    O: O1187 (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
/|\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-B
In  State-B moving U
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isU
-/596:    O: O1192 (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
|\597:    O: O1193 (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
-/598:    O: O1196 (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
|\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 isU
-/|600:    O: O1200 (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
\-/601:    O: O1202 (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
|602:    O: O1204 (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
\-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 isR
-/|605:    O: O1209 (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
\-/606:    O: O1212 (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
|\-607:    O: O1214 (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
/|608:    O: O1215 (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
\-/609:    O: O1218 (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
|\-610:    O: O1220 (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
/|\-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-A
In  State-A moving U
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isU
/612:    O: O1224 (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
|\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 isL
-/614:    O: O1227 (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
|\-615:    O: O1230 (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
/|\616:    O: O1232 (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
-/|617:    O: O1233 (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
\-/618:    O: O1236 (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
|\-619:    O: O1237 (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
/|620:    O: O1240 (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
\-/621:    O: O1242 (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
|622:    O: O1243 (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
\-/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 isR
|\624:    O: O1247 (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
-/|625:    O: O1250 (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
\-626:    O: O1252 (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
/|\627:    O: O1254 (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
-/628:    O: O1256 (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
|\-629:    O: O1258 (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
/|630:    O: O1260 (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
\-/631:    O: O1262 (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
|632:    O: O1264 (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
\-633:    O: O1265 (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
/|\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 isR
\-/638:    O: O1275 (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
|639:    O: O1278 (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
\-/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 isU
|\-641:    O: O1282 (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
/642:    O: O1283 (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
|\-643:    O: O1286 (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
/|644:    O: O1288 (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
\-/645:    O: O1290 (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
|\-646:    O: O1292 (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
/|\647:    O: O1294 (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
-/648:    O: O1295 (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 isL
|\-649:    O: O1297 (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
/|\650:    O: O1300 (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
-/|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-A
In  State-A moving U
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isL
\652:    O: O1303 (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 isR
-/653:    O: O1305 (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 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 isR
\-/655:    O: O1309 (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
|\-656:    O: O1312 (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
/|\657:    O: O1313 (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
-/|658:    O: O1315 (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
\-/659:    O: O1317 (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
|\-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 isU
/|\661:    O: O1322 (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
-662:    O: O1324 (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
/663:    O: O1326 (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
|\-664:    O: O1328 (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
/|\665:    O: O1330 (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
-/|666:    O: O1331 (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
\-/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-B
In  State-B moving U
ENV: (next state, see, prediction correct?) = (State-B, 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-B
In  State-B moving U
ENV: (next state, see, prediction correct?) = (State-B, 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-B
In  State-B moving U
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isU
\-/670:    O: O1340 (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
|\-671:    O: O1341 (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
/672:    O: O1344 (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
|\-673:    O: O1346 (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
/|\674:    O: O1348 (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
-/675:    O: O1349 (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
|\676:    O: O1351 (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
-/|677:    O: O1354 (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
\-/678:    O: O1355 (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
|\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-B
In  State-B moving U
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isR
-/|680:    O: O1360 (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
\-/681:    O: O1362 (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
|682:    O: O1364 (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
\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 isR
|\-686:    O: O1371 (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
/|\687:    O: O1374 (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
-/|688:    O: O1376 (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
\-/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 isR
|\-690:    O: O1380 (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
/|\691:    O: O1381 (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
-692:    O: O1384 (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
/|\693:    O: O1386 (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
-/694:    O: O1387 (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
|\695:    O: O1389 (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
-/|696:    O: O1391 (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
\-/697:    O: O1393 (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
|\698:    O: O1396 (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
-/|699:    O: O1398 (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
\-/700:    O: O1400 (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
|\-701:    O: O1401 (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
/702:    O: O1403 (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
|\-703:    O: O1405 (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
/|\704:    O: O1408 (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
-/|705:    O: O1410 (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
\-706:    O: O1412 (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
/|\707:    O: O1413 (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
-/|708:    O: O1416 (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
\-/709:    O: O1417 (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
|\-710:    O: O1420 (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
/|\711:    O: O1422 (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
-712:    O: O1424 (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
/|713:    O: O1426 (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
\-/714:    O: O1428 (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
|\-715:    O: O1430 (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
/|\-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-B
In  State-B moving U
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isR
/|717:    O: O1434 (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
\-/718:    O: O1436 (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
|\-719:    O: O1438 (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
/|\720:    O: O1439 (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
-/|721:    O: O1442 (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
\722:    O: O1444 (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
-/|723:    O: O1446 (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
\-724:    O: O1448 (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
/|\725:    O: O1449 (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
-/|726:    O: O1451 (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
\-/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 isU
|\728:    O: O1456 (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
-/|729:    O: O1458 (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
\-/730:    O: O1459 (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
|\-731:    O: O1462 (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
/732:    O: O1464 (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
|\-733:    O: O1466 (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
/|\734:    O: O1467 (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
-/|735:    O: O1470 (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
\-/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 isL
|\-737:    O: O1474 (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
/|\738:    O: O1475 (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
-/|739:    O: O1477 (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
\-740:    O: O1480 (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
/|\741:    O: O1482 (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
-742:    O: O1483 (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
/|\743:    O: O1485 (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
-/744:    O: O1487 (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
|745:    O: O1489 (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
\-/746:    O: O1492 (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
|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-A
In  State-A moving U
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isU
\-/748:    O: O1496 (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
|\-749:    O: O1498 (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
/|\750:    O: O1500 (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
-/|751:    O: O1502 (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
\752:    O: O1503 (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
-/|753:    O: O1506 (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
\-754:    O: O1507 (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
/|755:    O: O1510 (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
\-756:    O: O1512 (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
/|\757:    O: O1513 (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
-/|758:    O: O1516 (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
\-/759:    O: O1517 (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
|\-760:    O: O1520 (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
/761:    O: O1522 (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
|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 isL
\-/763:    O: O1525 (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
|\-/sleeping...
|764:    O: O1528 (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
\-765:    O: O1530 (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
/|\766:    O: O1532 (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
-/767:    O: O1533 (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
|\-768:    O: O1536 (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
/|\769:    O: O1538 (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
-/770:    O: O1540 (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
|\-771:    O: O1541 (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
/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-B
In  State-B moving U
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isU
|\-773:    O: O1546 (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
/|\774:    O: O1547 (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
-/775:    O: O1550 (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
|\776:    O: O1551 (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
-/|777:    O: O1553 (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
\-/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-A
In  State-A moving U
ENV: (next state, see, prediction correct?) = (State-A, 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-A
In  State-A moving U
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isL
/|\780:    O: O1560 (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
-/|781:    O: O1561 (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
\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 isL
-/783:    O: O1565 (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
|\-784:    O: O1567 (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
/|\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 isL
-/786:    O: O1572 (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
|\-787:    O: O1573 (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
/|788:    O: O1576 (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
\-/789:    O: O1578 (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
|\-790:    O: O1579 (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
/|\791:    O: O1582 (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
-792:    O: O1584 (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
/|\793:    O: O1586 (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
-/794:    O: O1588 (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
|\795:    O: O1590 (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
-/|796:    O: O1592 (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
\-/797:    O: O1594 (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
|\-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-A
In  State-A moving U
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isR
/|799:    O: O1597 (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
\-/800:    O: O1600 (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
|\801:    O: O1602 (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
-802:    O: O1604 (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
/|\803:    O: O1605 (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
-/804:    O: O1607 (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
|\-805:    O: O1609 (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
/|\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 isR
-/|807:    O: O1613 (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
\-/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-B
In  State-B moving U
ENV: (next state, see, prediction correct?) = (State-B, 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-B
In  State-B moving U
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isR
/|810:    O: O1620 (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
\-/811:    O: O1621 (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
|812:    O: O1624 (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
\-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 isU
-/|815:    O: O1630 (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
\-/816:    O: O1631 (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
|\-817:    O: O1633 (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
/|\818:    O: O1635 (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
-/|819:    O: O1638 (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
\-/820:    O: O1640 (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
|\-821:    O: O1641 (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
/822:    O: O1643 (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
|\823:    O: O1645 (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
-/|824:    O: O1647 (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
\-/825:    O: O1650 (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
|\826:    O: O1651 (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
-/|827:    O: O1654 (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
\-/828:    O: O1656 (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
|\-829:    O: O1657 (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
/|\-830:    O: O1660 (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
/|\831:    O: O1662 (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
-832:    O: O1664 (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
/|833:    O: O1665 (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
\-834:    O: O1668 (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
/|\835:    O: O1669 (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
-/|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-A
In  State-A moving U
ENV: (next state, see, prediction correct?) = (State-A, 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-A
In  State-A moving U
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isU
|\-838:    O: O1676 (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
/|\839:    O: O1677 (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
-/840:    O: O1680 (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
|\-841:    O: O1682 (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
/842:    O: O1684 (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
|\-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 isU
/|844:    O: O1688 (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
\-/845:    O: O1689 (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
|\-846:    O: O1692 (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
/|\847:    O: O1694 (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
-/848:    O: O1695 (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
|\-849:    O: O1698 (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
/|\850:    O: O1699 (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
-/|851:    O: O1702 (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
\852:    O: O1704 (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
-/853:    O: O1706 (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
|854:    O: O1708 (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
\-/855:    O: O1709 (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
|\-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-A
In  State-A moving U
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isL
/|\857:    O: O1714 (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
-/858:    O: O1715 (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
|\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-B
In  State-B moving U
ENV: (next state, see, prediction correct?) = (State-B, 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-B
In  State-B moving U
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isU
-/861:    O: O1722 (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
|862:    O: O1724 (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
\-/863:    O: O1725 (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
|\-864:    O: O1728 (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
/|\865:    O: O1730 (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
-/|866:    O: O1732 (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
\-/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 isR
|\-868:    O: O1736 (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
/|\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 isL
|\871:    O: O1741 (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
-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-A
In  State-A moving U
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isL
/873:    O: O1746 (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
|\874:    O: O1747 (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
-/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 isU
|\-876:    O: O1752 (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
/|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 isR
|\-879:    O: O1757 (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
/|\880:    O: O1759 (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
-/|881:    O: O1762 (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
\882:    O: O1764 (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
-/|883:    O: O1765 (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
\-884:    O: O1767 (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
/|\885:    O: O1770 (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
-/886:    O: O1772 (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
|\-887:    O: O1773 (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
/|888:    O: O1776 (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
\-/889:    O: O1777 (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
|\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 isL
|892:    O: O1783 (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
\-/893:    O: O1786 (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
|\-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-A
In  State-A moving U
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isU
/|\895:    O: O1790 (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
-/896:    O: O1791 (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
|\-/897:    O: O1794 (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
|\898:    O: O1795 (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
-/|899:    O: O1797 (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
\-/900:    O: O1800 (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
|\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-B
In  State-B moving U
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isR
-902:    O: O1804 (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
/|\903:    O: O1805 (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
-/|\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 isL
/|907:    O: O1813 (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
\-/908:    O: O1816 (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
|\-909:    O: O1818 (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
/|\910:    O: O1819 (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
-/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-B
In  State-B moving U
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isL
|912:    O: O1823 (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
\-/913:    O: O1826 (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
|\-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-A
In  State-A moving U
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isU
/|\915:    O: O1830 (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
-/|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 isL
\-/|917:    O: O1834 (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
\-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 isU
-/|920:    O: O1840 (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
\-921:    O: O1842 (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
/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 isR
-/925:    O: O1849 (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
|\926:    O: O1852 (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
-/|927:    O: O1854 (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
\-928:    O: O1855 (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
/|\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 isL
-/|930:    O: O1859 (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
\-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-A
In  State-A moving U
ENV: (next state, see, prediction correct?) = (State-A, 0, True)
predict error 0
dir: dir isU
/932:    O: O1864 (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
|\-933:    O: O1866 (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
/|\-934:    O: O1868 (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
/|\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 isL
-/|936:    O: O1872 (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
\-/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 isL
/|\939:    O: O1878 (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
-/|940:    O: O1879 (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
\-/|941:    O: O1882 (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
\942:    O: O1884 (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
-/|943:    O: O1885 (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
\-/944:    O: O1887 (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
|\945:    O: O1890 (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
-/|946:    O: O1891 (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
\-/947:    O: O1894 (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
|\-948:    O: O1895 (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
/|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-B
In  State-B moving U
ENV: (next state, see, prediction correct?) = (State-B, 0, True)
predict error 0
dir: dir isU
\-/950:    O: O1900 (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
|\-/|\-/|\--- Input Phase --- 
=>WM: (13382: I2 ^dir R)
=>WM: (13381: I2 ^reward 1)
=>WM: (13380: I2 ^see 0)
=>WM: (13379: N950 ^status complete)
<=WM: (13368: I2 ^dir U)
<=WM: (13367: I2 ^reward 1)
<=WM: (13366: I2 ^see 0)
=>WM: (13383: I2 ^level-1 R1-root)
<=WM: (13369: 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*v1*H1*36
 -->
 (S1 ^operator O1899 = -0.1070236389116304)
Firing rl*prefer*rvt*predict-no*H0*4*v1*H1*35
 -->
 (S1 ^operator O1900 = 0.66025212945601)
Firing prefer*rvt*predict-no*H0*4*v1*H1
 -->
Firing prefer*rvt*predict-yes*H0*3*v1*H1
 -->
Firing elaborate*copy-see-to-output-link
 -->
 (I3 ^see 0 +)
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*4
 -->
 (S1 ^operator O1900 = 0.3397665963572414)
Firing rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O1899 = 0.3377110766337923)
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
 -->
 (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 U +)
Retracting rl*prefer*rvt*predict-no*H0*2
 -->
 (S1 ^operator O1900 = 1.)
Retracting rl*prefer*rvt*predict-yes*H0*1
 -->
 (S1 ^operator O1899 = 0.)
=>WM: (13390: S1 ^operator O1902 +)
=>WM: (13389: S1 ^operator O1901 +)
=>WM: (13388: I3 ^dir R)
=>WM: (13387: O1902 ^name predict-no)
=>WM: (13386: O1901 ^name predict-yes)
=>WM: (13385: R954 ^value 1)
=>WM: (13384: R1 ^reward R954)
<=WM: (13375: S1 ^operator O1899 +)
<=WM: (13376: S1 ^operator O1900 +)
<=WM: (13377: S1 ^operator O1900)
<=WM: (13360: I3 ^dir U)
<=WM: (13371: R1 ^reward R953)
<=WM: (13374: O1900 ^name predict-no)
<=WM: (13373: O1899 ^name predict-yes)
<=WM: (13372: R953 ^value 1)

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing prefer*rvt*predict-yes*H0
 -->
Firing rl*prefer*rvt*predict-yes*H0*3*v1*H1*36
 -->
 (S1 ^operator O1901 = -0.1070236389116304)
Firing rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O1901 = 0.3377110766337923)
Firing prefer*rvt*predict-yes*H0*3*v1*H1
 -->
Firing prefer*rvt*predict-no*H0
 -->
Firing rl*prefer*rvt*predict-no*H0*4*v1*H1*35
 -->
 (S1 ^operator O1902 = 0.66025212945601)
Firing rl*prefer*rvt*predict-no*H0*4
 -->
 (S1 ^operator O1902 = 0.3397665963572414)
Firing prefer*rvt*predict-no*H0*4*v1*H1
 -->
 inner elaboration loop at bottom goal.
Retracting rl*prefer*rvt*predict-no*H0*4
 -->
 (S1 ^operator O1900 = 0.3397665963572414)
Retracting rl*prefer*rvt*predict-no*H0*4*v1*H1*35
 -->
 (S1 ^operator O1900 = 0.66025212945601)
Retracting rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O1899 = 0.3377110766337923)
Retracting rl*prefer*rvt*predict-yes*H0*3*v1*H1*36
 -->
 (S1 ^operator O1899 = -0.1070236389116304)

--- END Proposal Phase ---

--- Decision Phase ---
RL update rl*prefer*rvt*predict-no*H0*2 1 0 1 -> 1 0 1(R,m,v=1,1,0)
=>WM: (13391: S1 ^operator O1902)

   951:    O: O1902 (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 N951 +  :O )
Firing apply*operator*complete
 -->
 (I3 ^predict-no N950 -  :O )
 inner elaboration loop at bottom goal.
	--- Change Working Memory (PE) ---
=>WM: (13392: I3 ^predict-no N951)
<=WM: (13379: N950 ^status complete)
<=WM: (13378: I3 ^predict-no 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-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: (13396: I2 ^dir L)
=>WM: (13395: I2 ^reward 1)
=>WM: (13394: I2 ^see 0)
=>WM: (13393: N951 ^status complete)
<=WM: (13382: I2 ^dir R)
<=WM: (13381: I2 ^reward 1)
<=WM: (13380: I2 ^see 0)
=>WM: (13397: I2 ^level-1 R0-root)
<=WM: (13383: I2 ^level-1 R1-root)

--- END Input Phase --- 

--- Proposal Phase ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing rl*prefer*rvt*predict-yes*H0*5*v1*H1*30
 -->
 (S1 ^operator O1901 = 0.735786774178754)
Firing prefer*rvt*predict-yes*H0*5*v1*H1
 -->
Firing elaborate*copy-see-to-output-link
 -->
 (I3 ^see 0 +)
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*6
 -->
 (S1 ^operator O1902 = 0.9996367744406318)
Firing rl*prefer*rvt*predict-yes*H0*5
 -->
 (S1 ^operator O1901 = 0.2640533371018167)
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
 -->
 (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 R +)
Retracting rl*prefer*rvt*predict-no*H0*4
 -->
 (S1 ^operator O1902 = 0.3397665963572414)
Retracting rl*prefer*rvt*predict-no*H0*4*v1*H1*35
 -->
 (S1 ^operator O1902 = 0.66025212945601)
Retracting rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O1901 = 0.3377110766337923)
Retracting rl*prefer*rvt*predict-yes*H0*3*v1*H1*36
 -->
 (S1 ^operator O1901 = -0.1070236389116304)
=>WM: (13404: S1 ^operator O1904 +)
=>WM: (13403: S1 ^operator O1903 +)
=>WM: (13402: I3 ^dir L)
=>WM: (13401: O1904 ^name predict-no)
=>WM: (13400: O1903 ^name predict-yes)
=>WM: (13399: R955 ^value 1)
=>WM: (13398: R1 ^reward R955)
<=WM: (13389: S1 ^operator O1901 +)
<=WM: (13390: S1 ^operator O1902 +)
<=WM: (13391: S1 ^operator O1902)
<=WM: (13388: I3 ^dir R)
<=WM: (13384: R1 ^reward R954)
<=WM: (13387: O1902 ^name predict-no)
<=WM: (13386: O1901 ^name predict-yes)
<=WM: (13385: R954 ^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 O1903 = 0.2640533371018167)
Firing prefer*rvt*predict-yes*H0*5*v1*H1
 -->
Firing rl*prefer*rvt*predict-yes*H0*5*v1*H1*30
 -->
 (S1 ^operator O1903 = 0.735786774178754)
Firing prefer*rvt*predict-no*H0
 -->
Firing rl*prefer*rvt*predict-no*H0*6
 -->
 (S1 ^operator O1904 = 0.9996367744406318)
 inner elaboration loop at bottom goal.
Retracting rl*prefer*rvt*predict-no*H0*6
 -->
 (S1 ^operator O1902 = 0.9996367744406318)
Retracting rl*prefer*rvt*predict-yes*H0*5
 -->
 (S1 ^operator O1901 = 0.2640533371018167)
Retracting rl*prefer*rvt*predict-yes*H0*5*v1*H1*30
 -->
 (S1 ^operator O1901 = 0.735786774178754)

--- END Proposal Phase ---

--- Decision Phase ---
RL update rl*prefer*rvt*predict-no*H0*4 0.57025 -0.230483 0.339767 -> 0.570248 -0.230483 0.339765(R,m,v=1,0.87037,0.113527)
RL update rl*prefer*rvt*predict-no*H0*4*v1*H1*35 0.42977 0.230482 0.660252 -> 0.429768 0.230482 0.66025(R,m,v=1,1,0)
=>WM: (13405: S1 ^operator O1903)

   952:    O: O1903 (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 N952 +  :O )
Firing apply*operator*complete
 -->
 (I3 ^predict-no N951 -  :O )
 inner elaboration loop at bottom goal.
	--- Change Working Memory (PE) ---
=>WM: (13406: I3 ^predict-yes N952)
<=WM: (13393: N951 ^status complete)
<=WM: (13392: I3 ^predict-no 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-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: (13410: I2 ^dir U)
=>WM: (13409: I2 ^reward 1)
=>WM: (13408: I2 ^see 1)
=>WM: (13407: N952 ^status complete)
<=WM: (13396: I2 ^dir L)
<=WM: (13395: I2 ^reward 1)
<=WM: (13394: I2 ^see 0)
=>WM: (13411: I2 ^level-1 L1-root)
<=WM: (13397: 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
 -->
 (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*2
 -->
 (S1 ^operator O1904 = 1.)
Firing rl*prefer*rvt*predict-yes*H0*1
 -->
 (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 0 +)
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*6
 -->
 (S1 ^operator O1904 = 0.9996367744406318)
Retracting rl*prefer*rvt*predict-yes*H0*5*v1*H1*30
 -->
 (S1 ^operator O1903 = 0.735786774178754)
Retracting rl*prefer*rvt*predict-yes*H0*5
 -->
 (S1 ^operator O1903 = 0.2640533371018167)
=>WM: (13419: S1 ^operator O1906 +)
=>WM: (13418: S1 ^operator O1905 +)
=>WM: (13417: I3 ^dir U)
=>WM: (13416: O1906 ^name predict-no)
=>WM: (13415: O1905 ^name predict-yes)
=>WM: (13414: R956 ^value 1)
=>WM: (13413: R1 ^reward R956)
=>WM: (13412: I3 ^see 1)
<=WM: (13403: S1 ^operator O1903 +)
<=WM: (13405: S1 ^operator O1903)
<=WM: (13404: S1 ^operator O1904 +)
<=WM: (13402: I3 ^dir L)
<=WM: (13398: R1 ^reward R955)
<=WM: (13370: I3 ^see 0)
<=WM: (13401: O1904 ^name predict-no)
<=WM: (13400: O1903 ^name predict-yes)
<=WM: (13399: R955 ^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 O1905 = 0.)
Firing prefer*rvt*predict-no*H0
 -->
Firing rl*prefer*rvt*predict-no*H0*2
 -->
 (S1 ^operator O1906 = 1.)
 inner elaboration loop at bottom goal.
Retracting rl*prefer*rvt*predict-no*H0*2
 -->
 (S1 ^operator O1904 = 1.)
Retracting rl*prefer*rvt*predict-yes*H0*1
 -->
 (S1 ^operator O1903 = 0.)

--- END Proposal Phase ---

--- Decision Phase ---
RL update rl*prefer*rvt*predict-yes*H0*5 0.554438 -0.290385 0.264053 -> 0.554451 -0.290385 0.264066(R,m,v=1,0.872093,0.112199)
RL update rl*prefer*rvt*predict-yes*H0*5*v1*H1*30 0.445404 0.290382 0.735787 -> 0.44542 0.290383 0.735802(R,m,v=1,1,0)
=>WM: (13420: 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-yes N952 -  :O )
 inner elaboration loop at bottom goal.
	--- Change Working Memory (PE) ---
=>WM: (13421: I3 ^predict-no N953)
<=WM: (13407: N952 ^status complete)
<=WM: (13406: I3 ^predict-yes 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 isR
--- END Output Phase ---
\-/--- Input Phase --- 
=>WM: (13425: I2 ^dir R)
=>WM: (13424: I2 ^reward 1)
=>WM: (13423: I2 ^see 0)
=>WM: (13422: N953 ^status complete)
<=WM: (13410: I2 ^dir U)
<=WM: (13409: I2 ^reward 1)
<=WM: (13408: I2 ^see 1)
=>WM: (13426: I2 ^level-1 L1-root)
<=WM: (13411: I2 ^level-1 L1-root)

--- END Input Phase --- 

--- Proposal Phase ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing rl*prefer*rvt*predict-no*H0*4*v1*H1*37
 -->
 (S1 ^operator O1906 = -0.2714224023553999)
Firing rl*prefer*rvt*predict-yes*H0*3*v1*H1*38
 -->
 (S1 ^operator O1905 = 0.6621942993402632)
Firing prefer*rvt*predict-no*H0*4*v1*H1
 -->
Firing prefer*rvt*predict-yes*H0*3*v1*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*4
 -->
 (S1 ^operator O1906 = 0.3397650583271044)
Firing rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O1905 = 0.3377110766337923)
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
 -->
 (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*2
 -->
 (S1 ^operator O1906 = 1.)
Retracting rl*prefer*rvt*predict-yes*H0*1
 -->
 (S1 ^operator O1905 = 0.)
=>WM: (13434: S1 ^operator O1908 +)
=>WM: (13433: S1 ^operator O1907 +)
=>WM: (13432: I3 ^dir R)
=>WM: (13431: O1908 ^name predict-no)
=>WM: (13430: O1907 ^name predict-yes)
=>WM: (13429: R957 ^value 1)
=>WM: (13428: R1 ^reward R957)
=>WM: (13427: I3 ^see 0)
<=WM: (13418: S1 ^operator O1905 +)
<=WM: (13419: S1 ^operator O1906 +)
<=WM: (13420: S1 ^operator O1906)
<=WM: (13417: I3 ^dir U)
<=WM: (13413: R1 ^reward R956)
<=WM: (13412: I3 ^see 1)
<=WM: (13416: O1906 ^name predict-no)
<=WM: (13415: O1905 ^name predict-yes)
<=WM: (13414: R956 ^value 1)

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing prefer*rvt*predict-yes*H0
 -->
Firing rl*prefer*rvt*predict-yes*H0*3*v1*H1*38
 -->
 (S1 ^operator O1907 = 0.6621942993402632)
Firing rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O1907 = 0.3377110766337923)
Firing prefer*rvt*predict-yes*H0*3*v1*H1
 -->
Firing prefer*rvt*predict-no*H0
 -->
Firing rl*prefer*rvt*predict-no*H0*4*v1*H1*37
 -->
 (S1 ^operator O1908 = -0.2714224023553999)
Firing rl*prefer*rvt*predict-no*H0*4
 -->
 (S1 ^operator O1908 = 0.3397650583271044)
Firing prefer*rvt*predict-no*H0*4*v1*H1
 -->
 inner elaboration loop at bottom goal.
Retracting rl*prefer*rvt*predict-no*H0*4
 -->
 (S1 ^operator O1906 = 0.3397650583271044)
Retracting rl*prefer*rvt*predict-no*H0*4*v1*H1*37
 -->
 (S1 ^operator O1906 = -0.2714224023553999)
Retracting rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O1905 = 0.3377110766337923)
Retracting rl*prefer*rvt*predict-yes*H0*3*v1*H1*38
 -->
 (S1 ^operator O1905 = 0.6621942993402632)

--- END Proposal Phase ---

--- Decision Phase ---
RL update rl*prefer*rvt*predict-no*H0*2 1 0 1 -> 1 0 1(R,m,v=1,1,0)
=>WM: (13435: S1 ^operator O1907)

   954:    O: O1907 (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 N954 +  :O )
Firing apply*operator*complete
 -->
 (I3 ^predict-no N953 -  :O )
 inner elaboration loop at bottom goal.
	--- Change Working Memory (PE) ---
=>WM: (13436: I3 ^predict-yes N954)
<=WM: (13422: N953 ^status complete)
<=WM: (13421: 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-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: (13440: I2 ^dir U)
=>WM: (13439: I2 ^reward 1)
=>WM: (13438: I2 ^see 1)
=>WM: (13437: N954 ^status complete)
<=WM: (13425: I2 ^dir R)
<=WM: (13424: I2 ^reward 1)
<=WM: (13423: I2 ^see 0)
=>WM: (13441: I2 ^level-1 R1-root)
<=WM: (13426: 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
 -->
 (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 = 1.)
Firing rl*prefer*rvt*predict-yes*H0*1
 -->
 (S1 ^operator O1907 = 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
 -->
 (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 R +)
Retracting rl*prefer*rvt*predict-no*H0*4
 -->
 (S1 ^operator O1908 = 0.3397650583271044)
Retracting rl*prefer*rvt*predict-no*H0*4*v1*H1*37
 -->
 (S1 ^operator O1908 = -0.2714224023553999)
Retracting rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O1907 = 0.3377110766337923)
Retracting rl*prefer*rvt*predict-yes*H0*3*v1*H1*38
 -->
 (S1 ^operator O1907 = 0.6621942993402632)
=>WM: (13449: S1 ^operator O1910 +)
=>WM: (13448: S1 ^operator O1909 +)
=>WM: (13447: I3 ^dir U)
=>WM: (13446: O1910 ^name predict-no)
=>WM: (13445: O1909 ^name predict-yes)
=>WM: (13444: R958 ^value 1)
=>WM: (13443: R1 ^reward R958)
=>WM: (13442: I3 ^see 1)
<=WM: (13433: S1 ^operator O1907 +)
<=WM: (13435: S1 ^operator O1907)
<=WM: (13434: S1 ^operator O1908 +)
<=WM: (13432: I3 ^dir R)
<=WM: (13428: R1 ^reward R957)
<=WM: (13427: I3 ^see 0)
<=WM: (13431: O1908 ^name predict-no)
<=WM: (13430: O1907 ^name predict-yes)
<=WM: (13429: R957 ^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 O1909 = 0.)
Firing prefer*rvt*predict-no*H0
 -->
Firing rl*prefer*rvt*predict-no*H0*2
 -->
 (S1 ^operator O1910 = 1.)
 inner elaboration loop at bottom goal.
Retracting rl*prefer*rvt*predict-no*H0*2
 -->
 (S1 ^operator O1908 = 1.)
Retracting rl*prefer*rvt*predict-yes*H0*1
 -->
 (S1 ^operator O1907 = 0.)

--- END Proposal Phase ---

--- Decision Phase ---
RL update rl*prefer*rvt*predict-yes*H0*3 0.590111 -0.2524 0.337711 -> 0.59012 -0.252401 0.337719(R,m,v=1,0.89441,0.0950311)
RL update rl*prefer*rvt*predict-yes*H0*3*v1*H1*38 0.40978 0.252415 0.662194 -> 0.40979 0.252413 0.662203(R,m,v=1,1,0)
=>WM: (13450: 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-yes N954 -  :O )
 inner elaboration loop at bottom goal.
	--- Change Working Memory (PE) ---
=>WM: (13451: I3 ^predict-no N955)
<=WM: (13437: N954 ^status complete)
<=WM: (13436: I3 ^predict-yes 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 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: (13455: I2 ^dir R)
=>WM: (13454: I2 ^reward 1)
=>WM: (13453: I2 ^see 0)
=>WM: (13452: N955 ^status complete)
<=WM: (13440: I2 ^dir U)
<=WM: (13439: I2 ^reward 1)
<=WM: (13438: I2 ^see 1)
=>WM: (13456: I2 ^level-1 R1-root)
<=WM: (13441: 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*v1*H1*36
 -->
 (S1 ^operator O1909 = -0.1070236389116304)
Firing rl*prefer*rvt*predict-no*H0*4*v1*H1*35
 -->
 (S1 ^operator O1910 = 0.6602503199844459)
Firing prefer*rvt*predict-no*H0*4*v1*H1
 -->
Firing prefer*rvt*predict-yes*H0*3*v1*H1
 -->
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*4
 -->
 (S1 ^operator O1910 = 0.3397650583271044)
Firing rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O1909 = 0.3377188564178903)
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
 -->
 (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 U +)
Retracting rl*prefer*rvt*predict-no*H0*2
 -->
 (S1 ^operator O1910 = 1.)
Retracting rl*prefer*rvt*predict-yes*H0*1
 -->
 (S1 ^operator O1909 = 0.)
=>WM: (13464: S1 ^operator O1912 +)
=>WM: (13463: S1 ^operator O1911 +)
=>WM: (13462: I3 ^dir R)
=>WM: (13461: O1912 ^name predict-no)
=>WM: (13460: O1911 ^name predict-yes)
=>WM: (13459: R959 ^value 1)
=>WM: (13458: R1 ^reward R959)
=>WM: (13457: I3 ^see 0)
<=WM: (13448: S1 ^operator O1909 +)
<=WM: (13449: S1 ^operator O1910 +)
<=WM: (13450: S1 ^operator O1910)
<=WM: (13447: I3 ^dir U)
<=WM: (13443: R1 ^reward R958)
<=WM: (13442: I3 ^see 1)
<=WM: (13446: O1910 ^name predict-no)
<=WM: (13445: O1909 ^name predict-yes)
<=WM: (13444: R958 ^value 1)

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing prefer*rvt*predict-yes*H0
 -->
Firing rl*prefer*rvt*predict-yes*H0*3*v1*H1*36
 -->
 (S1 ^operator O1911 = -0.1070236389116304)
Firing rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O1911 = 0.3377188564178903)
Firing prefer*rvt*predict-yes*H0*3*v1*H1
 -->
Firing prefer*rvt*predict-no*H0
 -->
Firing rl*prefer*rvt*predict-no*H0*4*v1*H1*35
 -->
 (S1 ^operator O1912 = 0.6602503199844459)
Firing rl*prefer*rvt*predict-no*H0*4
 -->
 (S1 ^operator O1912 = 0.3397650583271044)
Firing prefer*rvt*predict-no*H0*4*v1*H1
 -->
 inner elaboration loop at bottom goal.
Retracting rl*prefer*rvt*predict-no*H0*4
 -->
 (S1 ^operator O1910 = 0.3397650583271044)
Retracting rl*prefer*rvt*predict-no*H0*4*v1*H1*35
 -->
 (S1 ^operator O1910 = 0.6602503199844459)
Retracting rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O1909 = 0.3377188564178903)
Retracting rl*prefer*rvt*predict-yes*H0*3*v1*H1*36
 -->
 (S1 ^operator O1909 = -0.1070236389116304)

--- END Proposal Phase ---

--- Decision Phase ---
RL update rl*prefer*rvt*predict-no*H0*2 1 0 1 -> 1 0 1(R,m,v=1,1,0)
=>WM: (13465: 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: (13466: I3 ^predict-no N956)
<=WM: (13452: N955 ^status complete)
<=WM: (13451: 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 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: (13470: I2 ^dir R)
=>WM: (13469: I2 ^reward 1)
=>WM: (13468: I2 ^see 0)
=>WM: (13467: N956 ^status complete)
<=WM: (13455: I2 ^dir R)
<=WM: (13454: I2 ^reward 1)
<=WM: (13453: I2 ^see 0)
=>WM: (13471: I2 ^level-1 R0-root)
<=WM: (13456: I2 ^level-1 R1-root)

--- END Input Phase --- 

--- Proposal Phase ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing rl*prefer*rvt*predict-no*H0*4*v1*H1*39
 -->
 (S1 ^operator O1912 = 0.6601435952544124)
Firing rl*prefer*rvt*predict-yes*H0*3*v1*H1*40
 -->
 (S1 ^operator O1911 = -0.1028953566115423)
Firing prefer*rvt*predict-no*H0*4*v1*H1
 -->
Firing prefer*rvt*predict-yes*H0*3*v1*H1
 -->
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*4
 -->
 (S1 ^operator O1912 = 0.3397650583271044)
Firing rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O1911 = 0.3377188564178903)
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
 -->
 (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 R +)
Retracting rl*prefer*rvt*predict-no*H0*4
 -->
 (S1 ^operator O1912 = 0.3397650583271044)
Retracting rl*prefer*rvt*predict-no*H0*4*v1*H1*35
 -->
 (S1 ^operator O1912 = 0.6602503199844459)
Retracting rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O1911 = 0.3377188564178903)
Retracting rl*prefer*rvt*predict-yes*H0*3*v1*H1*36
 -->
 (S1 ^operator O1911 = -0.1070236389116304)
=>WM: (13477: S1 ^operator O1914 +)
=>WM: (13476: S1 ^operator O1913 +)
=>WM: (13475: O1914 ^name predict-no)
=>WM: (13474: O1913 ^name predict-yes)
=>WM: (13473: R960 ^value 1)
=>WM: (13472: R1 ^reward R960)
<=WM: (13463: S1 ^operator O1911 +)
<=WM: (13464: S1 ^operator O1912 +)
<=WM: (13465: S1 ^operator O1912)
<=WM: (13458: R1 ^reward R959)
<=WM: (13461: O1912 ^name predict-no)
<=WM: (13460: O1911 ^name predict-yes)
<=WM: (13459: R959 ^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 O1913 = 0.3377188564178903)
Firing prefer*rvt*predict-yes*H0*3*v1*H1
 -->
Firing rl*prefer*rvt*predict-yes*H0*3*v1*H1*40
 -->
 (S1 ^operator O1913 = -0.1028953566115423)
Firing prefer*rvt*predict-no*H0
 -->
Firing rl*prefer*rvt*predict-no*H0*4
 -->
 (S1 ^operator O1914 = 0.3397650583271044)
Firing prefer*rvt*predict-no*H0*4*v1*H1
 -->
Firing rl*prefer*rvt*predict-no*H0*4*v1*H1*39
 -->
 (S1 ^operator O1914 = 0.6601435952544124)
 inner elaboration loop at bottom goal.
Retracting rl*prefer*rvt*predict-no*H0*4
 -->
 (S1 ^operator O1912 = 0.3397650583271044)
Retracting rl*prefer*rvt*predict-no*H0*4*v1*H1*39
 -->
 (S1 ^operator O1912 = 0.6601435952544124)
Retracting rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O1911 = 0.3377188564178903)
Retracting rl*prefer*rvt*predict-yes*H0*3*v1*H1*40
 -->
 (S1 ^operator O1911 = -0.1028953566115423)

--- END Proposal Phase ---

--- Decision Phase ---
RL update rl*prefer*rvt*predict-no*H0*4 0.570248 -0.230483 0.339765 -> 0.570247 -0.230483 0.339764(R,m,v=1,0.871166,0.112929)
RL update rl*prefer*rvt*predict-no*H0*4*v1*H1*35 0.429768 0.230482 0.66025 -> 0.429766 0.230483 0.660249(R,m,v=1,1,0)
=>WM: (13478: 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: (13479: I3 ^predict-no N957)
<=WM: (13467: N956 ^status complete)
<=WM: (13466: 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 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: (13483: I2 ^dir L)
=>WM: (13482: I2 ^reward 1)
=>WM: (13481: I2 ^see 0)
=>WM: (13480: N957 ^status complete)
<=WM: (13470: I2 ^dir R)
<=WM: (13469: I2 ^reward 1)
<=WM: (13468: I2 ^see 0)
=>WM: (13484: I2 ^level-1 R0-root)
<=WM: (13471: I2 ^level-1 R0-root)

--- END Input Phase --- 

--- Proposal Phase ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing rl*prefer*rvt*predict-yes*H0*5*v1*H1*30
 -->
 (S1 ^operator O1913 = 0.7358024669452599)
Firing prefer*rvt*predict-yes*H0*5*v1*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*6
 -->
 (S1 ^operator O1914 = 0.9996367744406318)
Firing rl*prefer*rvt*predict-yes*H0*5
 -->
 (S1 ^operator O1913 = 0.2640663414827097)
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 R +)
Retracting rl*prefer*rvt*predict-no*H0*4*v1*H1*39
 -->
 (S1 ^operator O1914 = 0.6601435952544124)
Retracting rl*prefer*rvt*predict-no*H0*4
 -->
 (S1 ^operator O1914 = 0.3397637965169674)
Retracting rl*prefer*rvt*predict-yes*H0*3*v1*H1*40
 -->
 (S1 ^operator O1913 = -0.1028953566115423)
Retracting rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O1913 = 0.3377188564178903)
=>WM: (13491: S1 ^operator O1916 +)
=>WM: (13490: S1 ^operator O1915 +)
=>WM: (13489: I3 ^dir L)
=>WM: (13488: O1916 ^name predict-no)
=>WM: (13487: O1915 ^name predict-yes)
=>WM: (13486: R961 ^value 1)
=>WM: (13485: R1 ^reward R961)
<=WM: (13476: S1 ^operator O1913 +)
<=WM: (13477: S1 ^operator O1914 +)
<=WM: (13478: S1 ^operator O1914)
<=WM: (13462: I3 ^dir R)
<=WM: (13472: R1 ^reward R960)
<=WM: (13475: O1914 ^name predict-no)
<=WM: (13474: O1913 ^name predict-yes)
<=WM: (13473: R960 ^value 1)

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing prefer*rvt*predict-yes*H0
 -->
Firing rl*prefer*rvt*predict-yes*H0*5*v1*H1*30
 -->
 (S1 ^operator O1915 = 0.7358024669452599)
Firing rl*prefer*rvt*predict-yes*H0*5
 -->
 (S1 ^operator O1915 = 0.2640663414827097)
Firing prefer*rvt*predict-yes*H0*5*v1*H1
 -->
Firing prefer*rvt*predict-no*H0
 -->
Firing rl*prefer*rvt*predict-no*H0*6
 -->
 (S1 ^operator O1916 = 0.9996367744406318)
 inner elaboration loop at bottom goal.
Retracting rl*prefer*rvt*predict-no*H0*6
 -->
 (S1 ^operator O1914 = 0.9996367744406318)
Retracting rl*prefer*rvt*predict-yes*H0*5
 -->
 (S1 ^operator O1913 = 0.2640663414827097)
Retracting rl*prefer*rvt*predict-yes*H0*5*v1*H1*30
 -->
 (S1 ^operator O1913 = 0.7358024669452599)

--- END Proposal Phase ---

--- Decision Phase ---
RL update rl*prefer*rvt*predict-no*H0*4 0.570247 -0.230483 0.339764 -> 0.570255 -0.230484 0.339771(R,m,v=1,0.871951,0.112337)
RL update rl*prefer*rvt*predict-no*H0*4*v1*H1*39 0.429656 0.230488 0.660144 -> 0.429665 0.230487 0.660152(R,m,v=1,1,0)
=>WM: (13492: S1 ^operator O1915)

   958:    O: O1915 (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 N958 +  :O )
Firing apply*operator*complete
 -->
 (I3 ^predict-no N957 -  :O )
 inner elaboration loop at bottom goal.
	--- Change Working Memory (PE) ---
=>WM: (13493: I3 ^predict-yes N958)
<=WM: (13480: N957 ^status complete)
<=WM: (13479: 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-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: (13497: I2 ^dir U)
=>WM: (13496: I2 ^reward 1)
=>WM: (13495: I2 ^see 1)
=>WM: (13494: N958 ^status complete)
<=WM: (13483: I2 ^dir L)
<=WM: (13482: I2 ^reward 1)
<=WM: (13481: I2 ^see 0)
=>WM: (13498: I2 ^level-1 L1-root)
<=WM: (13484: 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
 -->
 (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*2
 -->
 (S1 ^operator O1916 = 1.)
Firing rl*prefer*rvt*predict-yes*H0*1
 -->
 (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*6
 -->
 (S1 ^operator O1916 = 0.9996367744406318)
Retracting rl*prefer*rvt*predict-yes*H0*5
 -->
 (S1 ^operator O1915 = 0.2640663414827097)
Retracting rl*prefer*rvt*predict-yes*H0*5*v1*H1*30
 -->
 (S1 ^operator O1915 = 0.7358024669452599)
=>WM: (13506: S1 ^operator O1918 +)
=>WM: (13505: S1 ^operator O1917 +)
=>WM: (13504: I3 ^dir U)
=>WM: (13503: O1918 ^name predict-no)
=>WM: (13502: O1917 ^name predict-yes)
=>WM: (13501: R962 ^value 1)
=>WM: (13500: R1 ^reward R962)
=>WM: (13499: I3 ^see 1)
<=WM: (13490: S1 ^operator O1915 +)
<=WM: (13492: S1 ^operator O1915)
<=WM: (13491: S1 ^operator O1916 +)
<=WM: (13489: I3 ^dir L)
<=WM: (13485: R1 ^reward R961)
<=WM: (13457: I3 ^see 0)
<=WM: (13488: O1916 ^name predict-no)
<=WM: (13487: O1915 ^name predict-yes)
<=WM: (13486: R961 ^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 O1917 = 0.)
Firing prefer*rvt*predict-no*H0
 -->
Firing rl*prefer*rvt*predict-no*H0*2
 -->
 (S1 ^operator O1918 = 1.)
 inner elaboration loop at bottom goal.
Retracting rl*prefer*rvt*predict-no*H0*2
 -->
 (S1 ^operator O1916 = 1.)
Retracting rl*prefer*rvt*predict-yes*H0*1
 -->
 (S1 ^operator O1915 = 0.)

--- END Proposal Phase ---

--- Decision Phase ---
RL update rl*prefer*rvt*predict-yes*H0*5 0.554451 -0.290385 0.264066 -> 0.554462 -0.290385 0.264077(R,m,v=1,0.872832,0.111641)
RL update rl*prefer*rvt*predict-yes*H0*5*v1*H1*30 0.44542 0.290383 0.735802 -> 0.445432 0.290383 0.735815(R,m,v=1,1,0)
=>WM: (13507: 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-yes N958 -  :O )
 inner elaboration loop at bottom goal.
	--- Change Working Memory (PE) ---
=>WM: (13508: I3 ^predict-no N959)
<=WM: (13494: N958 ^status complete)
<=WM: (13493: I3 ^predict-yes 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 isL
--- END Output Phase ---
\-/--- Input Phase --- 
=>WM: (13512: I2 ^dir L)
=>WM: (13511: I2 ^reward 1)
=>WM: (13510: I2 ^see 0)
=>WM: (13509: N959 ^status complete)
<=WM: (13497: I2 ^dir U)
<=WM: (13496: I2 ^reward 1)
<=WM: (13495: I2 ^see 1)
=>WM: (13513: I2 ^level-1 L1-root)
<=WM: (13498: I2 ^level-1 L1-root)

--- END Input Phase --- 

--- Proposal Phase ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing rl*prefer*rvt*predict-yes*H0*5*v1*H1*31
 -->
 (S1 ^operator O1917 = -0.181727099742844)
Firing prefer*rvt*predict-yes*H0*5*v1*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*6
 -->
 (S1 ^operator O1918 = 0.9996367744406318)
Firing rl*prefer*rvt*predict-yes*H0*5
 -->
 (S1 ^operator O1917 = 0.2640770017585976)
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
 -->
 (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*2
 -->
 (S1 ^operator O1918 = 1.)
Retracting rl*prefer*rvt*predict-yes*H0*1
 -->
 (S1 ^operator O1917 = 0.)
=>WM: (13521: S1 ^operator O1920 +)
=>WM: (13520: S1 ^operator O1919 +)
=>WM: (13519: I3 ^dir L)
=>WM: (13518: O1920 ^name predict-no)
=>WM: (13517: O1919 ^name predict-yes)
=>WM: (13516: R963 ^value 1)
=>WM: (13515: R1 ^reward R963)
=>WM: (13514: I3 ^see 0)
<=WM: (13505: S1 ^operator O1917 +)
<=WM: (13506: S1 ^operator O1918 +)
<=WM: (13507: S1 ^operator O1918)
<=WM: (13504: I3 ^dir U)
<=WM: (13500: R1 ^reward R962)
<=WM: (13499: I3 ^see 1)
<=WM: (13503: O1918 ^name predict-no)
<=WM: (13502: O1917 ^name predict-yes)
<=WM: (13501: R962 ^value 1)

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing prefer*rvt*predict-yes*H0
 -->
Firing rl*prefer*rvt*predict-yes*H0*5*v1*H1*31
 -->
 (S1 ^operator O1919 = -0.181727099742844)
Firing rl*prefer*rvt*predict-yes*H0*5
 -->
 (S1 ^operator O1919 = 0.2640770017585976)
Firing prefer*rvt*predict-yes*H0*5*v1*H1
 -->
Firing prefer*rvt*predict-no*H0
 -->
Firing rl*prefer*rvt*predict-no*H0*6
 -->
 (S1 ^operator O1920 = 0.9996367744406318)
 inner elaboration loop at bottom goal.
Retracting rl*prefer*rvt*predict-no*H0*6
 -->
 (S1 ^operator O1918 = 0.9996367744406318)
Retracting rl*prefer*rvt*predict-yes*H0*5
 -->
 (S1 ^operator O1917 = 0.2640770017585976)
Retracting rl*prefer*rvt*predict-yes*H0*5*v1*H1*31
 -->
 (S1 ^operator O1917 = -0.181727099742844)

--- END Proposal Phase ---

--- Decision Phase ---
RL update rl*prefer*rvt*predict-no*H0*2 1 0 1 -> 1 0 1(R,m,v=1,1,0)
=>WM: (13522: S1 ^operator O1920)

   960:    O: O1920 (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 N960 +  :O )
Firing apply*operator*complete
 -->
 (I3 ^predict-no N959 -  :O )
 inner elaboration loop at bottom goal.
	--- Change Working Memory (PE) ---
=>WM: (13523: I3 ^predict-no N960)
<=WM: (13509: N959 ^status complete)
<=WM: (13508: 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-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: (13527: I2 ^dir U)
=>WM: (13526: I2 ^reward 1)
=>WM: (13525: I2 ^see 0)
=>WM: (13524: N960 ^status complete)
<=WM: (13512: I2 ^dir L)
<=WM: (13511: I2 ^reward 1)
<=WM: (13510: I2 ^see 0)
=>WM: (13528: I2 ^level-1 L0-root)
<=WM: (13513: 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
 -->
 (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*2
 -->
 (S1 ^operator O1920 = 1.)
Firing rl*prefer*rvt*predict-yes*H0*1
 -->
 (S1 ^operator O1919 = 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
 -->
 (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 L +)
Retracting rl*prefer*rvt*predict-no*H0*6
 -->
 (S1 ^operator O1920 = 0.9996367744406318)
Retracting rl*prefer*rvt*predict-yes*H0*5
 -->
 (S1 ^operator O1919 = 0.2640770017585976)
Retracting rl*prefer*rvt*predict-yes*H0*5*v1*H1*31
 -->
 (S1 ^operator O1919 = -0.181727099742844)
=>WM: (13535: S1 ^operator O1922 +)
=>WM: (13534: S1 ^operator O1921 +)
=>WM: (13533: I3 ^dir U)
=>WM: (13532: O1922 ^name predict-no)
=>WM: (13531: O1921 ^name predict-yes)
=>WM: (13530: R964 ^value 1)
=>WM: (13529: R1 ^reward R964)
<=WM: (13520: S1 ^operator O1919 +)
<=WM: (13521: S1 ^operator O1920 +)
<=WM: (13522: S1 ^operator O1920)
<=WM: (13519: I3 ^dir L)
<=WM: (13515: R1 ^reward R963)
<=WM: (13518: O1920 ^name predict-no)
<=WM: (13517: O1919 ^name predict-yes)
<=WM: (13516: R963 ^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 O1921 = 0.)
Firing prefer*rvt*predict-no*H0
 -->
Firing rl*prefer*rvt*predict-no*H0*2
 -->
 (S1 ^operator O1922 = 1.)
 inner elaboration loop at bottom goal.
Retracting rl*prefer*rvt*predict-no*H0*2
 -->
 (S1 ^operator O1920 = 1.)
Retracting rl*prefer*rvt*predict-yes*H0*1
 -->
 (S1 ^operator O1919 = 0.)

--- END Proposal Phase ---

--- Decision Phase ---
RL update rl*prefer*rvt*predict-no*H0*6 0.999637 0 0.999637 -> 0.999698 0 0.999698(R,m,v=1,0.903448,0.0878352)
=>WM: (13536: 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-no N960 -  :O )
 inner elaboration loop at bottom goal.
	--- Change Working Memory (PE) ---
=>WM: (13537: I3 ^predict-no N961)
<=WM: (13524: N960 ^status complete)
<=WM: (13523: I3 ^predict-no 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 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: (13541: I2 ^dir R)
=>WM: (13540: I2 ^reward 1)
=>WM: (13539: I2 ^see 0)
=>WM: (13538: N961 ^status complete)
<=WM: (13527: I2 ^dir U)
<=WM: (13526: I2 ^reward 1)
<=WM: (13525: I2 ^see 0)
=>WM: (13542: I2 ^level-1 L0-root)
<=WM: (13528: I2 ^level-1 L0-root)

--- END Input Phase --- 

--- Proposal Phase ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing rl*prefer*rvt*predict-no*H0*4*v1*H1*33
 -->
 (S1 ^operator O1922 = -0.2817060109291377)
Firing rl*prefer*rvt*predict-yes*H0*3*v1*H1*34
 -->
 (S1 ^operator O1921 = 0.6623767743575877)
Firing prefer*rvt*predict-no*H0*4*v1*H1
 -->
Firing prefer*rvt*predict-yes*H0*3*v1*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*4
 -->
 (S1 ^operator O1922 = 0.3397713875215998)
Firing rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O1921 = 0.3377188564178903)
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
 -->
 (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 U +)
Retracting rl*prefer*rvt*predict-no*H0*2
 -->
 (S1 ^operator O1922 = 1.)
Retracting rl*prefer*rvt*predict-yes*H0*1
 -->
 (S1 ^operator O1921 = 0.)
=>WM: (13549: S1 ^operator O1924 +)
=>WM: (13548: S1 ^operator O1923 +)
=>WM: (13547: I3 ^dir R)
=>WM: (13546: O1924 ^name predict-no)
=>WM: (13545: O1923 ^name predict-yes)
=>WM: (13544: R965 ^value 1)
=>WM: (13543: R1 ^reward R965)
<=WM: (13534: S1 ^operator O1921 +)
<=WM: (13535: S1 ^operator O1922 +)
<=WM: (13536: S1 ^operator O1922)
<=WM: (13533: I3 ^dir U)
<=WM: (13529: R1 ^reward R964)
<=WM: (13532: O1922 ^name predict-no)
<=WM: (13531: O1921 ^name predict-yes)
<=WM: (13530: R964 ^value 1)

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing prefer*rvt*predict-yes*H0
 -->
Firing rl*prefer*rvt*predict-yes*H0*3*v1*H1*34
 -->
 (S1 ^operator O1923 = 0.6623767743575877)
Firing rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O1923 = 0.3377188564178903)
Firing prefer*rvt*predict-yes*H0*3*v1*H1
 -->
Firing prefer*rvt*predict-no*H0
 -->
Firing rl*prefer*rvt*predict-no*H0*4*v1*H1*33
 -->
 (S1 ^operator O1924 = -0.2817060109291377)
Firing rl*prefer*rvt*predict-no*H0*4
 -->
 (S1 ^operator O1924 = 0.3397713875215998)
Firing prefer*rvt*predict-no*H0*4*v1*H1
 -->
 inner elaboration loop at bottom goal.
Retracting rl*prefer*rvt*predict-no*H0*4
 -->
 (S1 ^operator O1922 = 0.3397713875215998)
Retracting rl*prefer*rvt*predict-no*H0*4*v1*H1*33
 -->
 (S1 ^operator O1922 = -0.2817060109291377)
Retracting rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O1921 = 0.3377188564178903)
Retracting rl*prefer*rvt*predict-yes*H0*3*v1*H1*34
 -->
 (S1 ^operator O1921 = 0.6623767743575877)

--- END Proposal Phase ---

--- Decision Phase ---
RL update rl*prefer*rvt*predict-no*H0*2 1 0 1 -> 1 0 1(R,m,v=1,1,0)
=>WM: (13550: 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: (13551: I3 ^predict-yes N962)
<=WM: (13538: N961 ^status complete)
<=WM: (13537: 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 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: (13555: I2 ^dir U)
=>WM: (13554: I2 ^reward 1)
=>WM: (13553: I2 ^see 1)
=>WM: (13552: N962 ^status complete)
<=WM: (13541: I2 ^dir R)
<=WM: (13540: I2 ^reward 1)
<=WM: (13539: I2 ^see 0)
=>WM: (13556: I2 ^level-1 R1-root)
<=WM: (13542: 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
 -->
 (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*2
 -->
 (S1 ^operator O1924 = 1.)
Firing rl*prefer*rvt*predict-yes*H0*1
 -->
 (S1 ^operator O1923 = 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
 -->
 (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 R +)
Retracting rl*prefer*rvt*predict-no*H0*4
 -->
 (S1 ^operator O1924 = 0.3397713875215998)
Retracting rl*prefer*rvt*predict-no*H0*4*v1*H1*33
 -->
 (S1 ^operator O1924 = -0.2817060109291377)
Retracting rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O1923 = 0.3377188564178903)
Retracting rl*prefer*rvt*predict-yes*H0*3*v1*H1*34
 -->
 (S1 ^operator O1923 = 0.6623767743575877)
=>WM: (13564: S1 ^operator O1926 +)
=>WM: (13563: S1 ^operator O1925 +)
=>WM: (13562: I3 ^dir U)
=>WM: (13561: O1926 ^name predict-no)
=>WM: (13560: O1925 ^name predict-yes)
=>WM: (13559: R966 ^value 1)
=>WM: (13558: R1 ^reward R966)
=>WM: (13557: I3 ^see 1)
<=WM: (13548: S1 ^operator O1923 +)
<=WM: (13550: S1 ^operator O1923)
<=WM: (13549: S1 ^operator O1924 +)
<=WM: (13547: I3 ^dir R)
<=WM: (13543: R1 ^reward R965)
<=WM: (13514: I3 ^see 0)
<=WM: (13546: O1924 ^name predict-no)
<=WM: (13545: O1923 ^name predict-yes)
<=WM: (13544: R965 ^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 O1925 = 0.)
Firing prefer*rvt*predict-no*H0
 -->
Firing rl*prefer*rvt*predict-no*H0*2
 -->
 (S1 ^operator O1926 = 1.)
 inner elaboration loop at bottom goal.
Retracting rl*prefer*rvt*predict-no*H0*2
 -->
 (S1 ^operator O1924 = 1.)
Retracting rl*prefer*rvt*predict-yes*H0*1
 -->
 (S1 ^operator O1923 = 0.)

--- END Proposal Phase ---

--- Decision Phase ---
RL update rl*prefer*rvt*predict-yes*H0*3 0.59012 -0.252401 0.337719 -> 0.590111 -0.2524 0.337711(R,m,v=1,0.895062,0.0945096)
RL update rl*prefer*rvt*predict-yes*H0*3*v1*H1*34 0.40999 0.252387 0.662377 -> 0.409979 0.252388 0.662368(R,m,v=1,1,0)
=>WM: (13565: S1 ^operator O1926)

   963:    O: O1926 (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 N963 +  :O )
Firing apply*operator*complete
 -->
 (I3 ^predict-yes N962 -  :O )
 inner elaboration loop at bottom goal.
	--- Change Working Memory (PE) ---
=>WM: (13566: I3 ^predict-no N963)
<=WM: (13552: N962 ^status complete)
<=WM: (13551: 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-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: (13570: I2 ^dir L)
=>WM: (13569: I2 ^reward 1)
=>WM: (13568: I2 ^see 0)
=>WM: (13567: N963 ^status complete)
<=WM: (13555: I2 ^dir U)
<=WM: (13554: I2 ^reward 1)
<=WM: (13553: I2 ^see 1)
=>WM: (13571: I2 ^level-1 R1-root)
<=WM: (13556: I2 ^level-1 R1-root)

--- END Input Phase --- 

--- Proposal Phase ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing rl*prefer*rvt*predict-yes*H0*5*v1*H1*41
 -->
 (S1 ^operator O1925 = 0.7363235474336447)
Firing prefer*rvt*predict-yes*H0*5*v1*H1
 -->
Firing elaborate*copy-see-to-output-link
 -->
 (I3 ^see 0 +)
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 = 0.9996975476948911)
Firing rl*prefer*rvt*predict-yes*H0*5
 -->
 (S1 ^operator O1925 = 0.2640770017585976)
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
 -->
 (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 U +)
Retracting rl*prefer*rvt*predict-no*H0*2
 -->
 (S1 ^operator O1926 = 1.)
Retracting rl*prefer*rvt*predict-yes*H0*1
 -->
 (S1 ^operator O1925 = 0.)
=>WM: (13579: S1 ^operator O1928 +)
=>WM: (13578: S1 ^operator O1927 +)
=>WM: (13577: I3 ^dir L)
=>WM: (13576: O1928 ^name predict-no)
=>WM: (13575: O1927 ^name predict-yes)
=>WM: (13574: R967 ^value 1)
=>WM: (13573: R1 ^reward R967)
=>WM: (13572: I3 ^see 0)
<=WM: (13563: S1 ^operator O1925 +)
<=WM: (13564: S1 ^operator O1926 +)
<=WM: (13565: S1 ^operator O1926)
<=WM: (13562: I3 ^dir U)
<=WM: (13558: R1 ^reward R966)
<=WM: (13557: I3 ^see 1)
<=WM: (13561: O1926 ^name predict-no)
<=WM: (13560: O1925 ^name predict-yes)
<=WM: (13559: R966 ^value 1)

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing prefer*rvt*predict-yes*H0
 -->
Firing rl*prefer*rvt*predict-yes*H0*5*v1*H1*41
 -->
 (S1 ^operator O1927 = 0.7363235474336447)
Firing rl*prefer*rvt*predict-yes*H0*5
 -->
 (S1 ^operator O1927 = 0.2640770017585976)
Firing prefer*rvt*predict-yes*H0*5*v1*H1
 -->
Firing prefer*rvt*predict-no*H0
 -->
Firing rl*prefer*rvt*predict-no*H0*6
 -->
 (S1 ^operator O1928 = 0.9996975476948911)
 inner elaboration loop at bottom goal.
Retracting rl*prefer*rvt*predict-no*H0*6
 -->
 (S1 ^operator O1926 = 0.9996975476948911)
Retracting rl*prefer*rvt*predict-yes*H0*5
 -->
 (S1 ^operator O1925 = 0.2640770017585976)
Retracting rl*prefer*rvt*predict-yes*H0*5*v1*H1*41
 -->
 (S1 ^operator O1925 = 0.7363235474336447)

--- END Proposal Phase ---

--- Decision Phase ---
RL update rl*prefer*rvt*predict-no*H0*2 1 0 1 -> 1 0 1(R,m,v=1,1,0)
=>WM: (13580: S1 ^operator O1927)

   964:    O: O1927 (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 N964 +  :O )
Firing apply*operator*complete
 -->
 (I3 ^predict-no N963 -  :O )
 inner elaboration loop at bottom goal.
	--- Change Working Memory (PE) ---
=>WM: (13581: I3 ^predict-yes N964)
<=WM: (13567: N963 ^status complete)
<=WM: (13566: I3 ^predict-no 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-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: (13585: I2 ^dir U)
=>WM: (13584: I2 ^reward 1)
=>WM: (13583: I2 ^see 1)
=>WM: (13582: N964 ^status complete)
<=WM: (13570: I2 ^dir L)
<=WM: (13569: I2 ^reward 1)
<=WM: (13568: I2 ^see 0)
=>WM: (13586: I2 ^level-1 L1-root)
<=WM: (13571: 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
 -->
 (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 = 1.)
Firing rl*prefer*rvt*predict-yes*H0*1
 -->
 (S1 ^operator O1927 = 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
 -->
 (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 L +)
Retracting rl*prefer*rvt*predict-no*H0*6
 -->
 (S1 ^operator O1928 = 0.9996975476948911)
Retracting rl*prefer*rvt*predict-yes*H0*5
 -->
 (S1 ^operator O1927 = 0.2640770017585976)
Retracting rl*prefer*rvt*predict-yes*H0*5*v1*H1*41
 -->
 (S1 ^operator O1927 = 0.7363235474336447)
=>WM: (13594: S1 ^operator O1930 +)
=>WM: (13593: S1 ^operator O1929 +)
=>WM: (13592: I3 ^dir U)
=>WM: (13591: O1930 ^name predict-no)
=>WM: (13590: O1929 ^name predict-yes)
=>WM: (13589: R968 ^value 1)
=>WM: (13588: R1 ^reward R968)
=>WM: (13587: I3 ^see 1)
<=WM: (13578: S1 ^operator O1927 +)
<=WM: (13580: S1 ^operator O1927)
<=WM: (13579: S1 ^operator O1928 +)
<=WM: (13577: I3 ^dir L)
<=WM: (13573: R1 ^reward R967)
<=WM: (13572: I3 ^see 0)
<=WM: (13576: O1928 ^name predict-no)
<=WM: (13575: O1927 ^name predict-yes)
<=WM: (13574: R967 ^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 O1929 = 0.)
Firing prefer*rvt*predict-no*H0
 -->
Firing rl*prefer*rvt*predict-no*H0*2
 -->
 (S1 ^operator O1930 = 1.)
 inner elaboration loop at bottom goal.
Retracting rl*prefer*rvt*predict-no*H0*2
 -->
 (S1 ^operator O1928 = 1.)
Retracting rl*prefer*rvt*predict-yes*H0*1
 -->
 (S1 ^operator O1927 = 0.)

--- END Proposal Phase ---

--- Decision Phase ---
RL update rl*prefer*rvt*predict-yes*H0*5 0.554462 -0.290385 0.264077 -> 0.55443 -0.290385 0.264044(R,m,v=1,0.873563,0.111089)
RL update rl*prefer*rvt*predict-yes*H0*5*v1*H1*41 0.445932 0.290392 0.736324 -> 0.445895 0.290391 0.736286(R,m,v=1,1,0)
=>WM: (13595: S1 ^operator O1930)

   965:    O: O1930 (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 N965 +  :O )
Firing apply*operator*complete
 -->
 (I3 ^predict-yes N964 -  :O )
 inner elaboration loop at bottom goal.
	--- Change Working Memory (PE) ---
=>WM: (13596: I3 ^predict-no N965)
<=WM: (13582: N964 ^status complete)
<=WM: (13581: I3 ^predict-yes 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-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: (13600: I2 ^dir L)
=>WM: (13599: I2 ^reward 1)
=>WM: (13598: I2 ^see 0)
=>WM: (13597: N965 ^status complete)
<=WM: (13585: I2 ^dir U)
<=WM: (13584: I2 ^reward 1)
<=WM: (13583: I2 ^see 1)
=>WM: (13601: I2 ^level-1 L1-root)
<=WM: (13586: I2 ^level-1 L1-root)

--- END Input Phase --- 

--- Proposal Phase ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing rl*prefer*rvt*predict-yes*H0*5*v1*H1*31
 -->
 (S1 ^operator O1929 = -0.181727099742844)
Firing prefer*rvt*predict-yes*H0*5*v1*H1
 -->
Firing elaborate*copy-see-to-output-link
 -->
 (I3 ^see 0 +)
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*6
 -->
 (S1 ^operator O1930 = 0.9996975476948911)
Firing rl*prefer*rvt*predict-yes*H0*5
 -->
 (S1 ^operator O1929 = 0.2640444846619989)
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
 -->
 (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 U +)
Retracting rl*prefer*rvt*predict-no*H0*2
 -->
 (S1 ^operator O1930 = 1.)
Retracting rl*prefer*rvt*predict-yes*H0*1
 -->
 (S1 ^operator O1929 = 0.)
=>WM: (13609: S1 ^operator O1932 +)
=>WM: (13608: S1 ^operator O1931 +)
=>WM: (13607: I3 ^dir L)
=>WM: (13606: O1932 ^name predict-no)
=>WM: (13605: O1931 ^name predict-yes)
=>WM: (13604: R969 ^value 1)
=>WM: (13603: R1 ^reward R969)
=>WM: (13602: I3 ^see 0)
<=WM: (13593: S1 ^operator O1929 +)
<=WM: (13594: S1 ^operator O1930 +)
<=WM: (13595: S1 ^operator O1930)
<=WM: (13592: I3 ^dir U)
<=WM: (13588: R1 ^reward R968)
<=WM: (13587: I3 ^see 1)
<=WM: (13591: O1930 ^name predict-no)
<=WM: (13590: O1929 ^name predict-yes)
<=WM: (13589: R968 ^value 1)

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing prefer*rvt*predict-yes*H0
 -->
Firing rl*prefer*rvt*predict-yes*H0*5*v1*H1*31
 -->
 (S1 ^operator O1931 = -0.181727099742844)
Firing rl*prefer*rvt*predict-yes*H0*5
 -->
 (S1 ^operator O1931 = 0.2640444846619989)
Firing prefer*rvt*predict-yes*H0*5*v1*H1
 -->
Firing prefer*rvt*predict-no*H0
 -->
Firing rl*prefer*rvt*predict-no*H0*6
 -->
 (S1 ^operator O1932 = 0.9996975476948911)
 inner elaboration loop at bottom goal.
Retracting rl*prefer*rvt*predict-no*H0*6
 -->
 (S1 ^operator O1930 = 0.9996975476948911)
Retracting rl*prefer*rvt*predict-yes*H0*5
 -->
 (S1 ^operator O1929 = 0.2640444846619989)
Retracting rl*prefer*rvt*predict-yes*H0*5*v1*H1*31
 -->
 (S1 ^operator O1929 = -0.181727099742844)

--- END Proposal Phase ---

--- Decision Phase ---
RL update rl*prefer*rvt*predict-no*H0*2 1 0 1 -> 1 0 1(R,m,v=1,1,0)
=>WM: (13610: 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-no N965 -  :O )
 inner elaboration loop at bottom goal.
	--- Change Working Memory (PE) ---
=>WM: (13611: I3 ^predict-no N966)
<=WM: (13597: N965 ^status complete)
<=WM: (13596: I3 ^predict-no 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 isR
--- END Output Phase ---
\-/--- Input Phase --- 
=>WM: (13615: I2 ^dir R)
=>WM: (13614: I2 ^reward 1)
=>WM: (13613: I2 ^see 0)
=>WM: (13612: N966 ^status complete)
<=WM: (13600: I2 ^dir L)
<=WM: (13599: I2 ^reward 1)
<=WM: (13598: I2 ^see 0)
=>WM: (13616: I2 ^level-1 L0-root)
<=WM: (13601: I2 ^level-1 L1-root)

--- END Input Phase --- 

--- Proposal Phase ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing rl*prefer*rvt*predict-no*H0*4*v1*H1*33
 -->
 (S1 ^operator O1932 = -0.2817060109291377)
Firing rl*prefer*rvt*predict-yes*H0*3*v1*H1*34
 -->
 (S1 ^operator O1931 = 0.6623675607605151)
Firing prefer*rvt*predict-no*H0*4*v1*H1
 -->
Firing prefer*rvt*predict-yes*H0*3*v1*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*4
 -->
 (S1 ^operator O1932 = 0.3397713875215998)
Firing rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O1931 = 0.3377110018583719)
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
 -->
 (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*6
 -->
 (S1 ^operator O1932 = 0.9996975476948911)
Retracting rl*prefer*rvt*predict-yes*H0*5
 -->
 (S1 ^operator O1931 = 0.2640444846619989)
Retracting rl*prefer*rvt*predict-yes*H0*5*v1*H1*31
 -->
 (S1 ^operator O1931 = -0.181727099742844)
=>WM: (13623: S1 ^operator O1934 +)
=>WM: (13622: S1 ^operator O1933 +)
=>WM: (13621: I3 ^dir R)
=>WM: (13620: O1934 ^name predict-no)
=>WM: (13619: O1933 ^name predict-yes)
=>WM: (13618: R970 ^value 1)
=>WM: (13617: R1 ^reward R970)
<=WM: (13608: S1 ^operator O1931 +)
<=WM: (13609: S1 ^operator O1932 +)
<=WM: (13610: S1 ^operator O1932)
<=WM: (13607: I3 ^dir L)
<=WM: (13603: R1 ^reward R969)
<=WM: (13606: O1932 ^name predict-no)
<=WM: (13605: O1931 ^name predict-yes)
<=WM: (13604: R969 ^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 O1933 = 0.3377110018583719)
Firing prefer*rvt*predict-yes*H0*3*v1*H1
 -->
Firing rl*prefer*rvt*predict-yes*H0*3*v1*H1*34
 -->
 (S1 ^operator O1933 = 0.6623675607605151)
Firing prefer*rvt*predict-no*H0
 -->
Firing rl*prefer*rvt*predict-no*H0*4
 -->
 (S1 ^operator O1934 = 0.3397713875215998)
Firing prefer*rvt*predict-no*H0*4*v1*H1
 -->
Firing rl*prefer*rvt*predict-no*H0*4*v1*H1*33
 -->
 (S1 ^operator O1934 = -0.2817060109291377)
 inner elaboration loop at bottom goal.
Retracting rl*prefer*rvt*predict-no*H0*4
 -->
 (S1 ^operator O1932 = 0.3397713875215998)
Retracting rl*prefer*rvt*predict-no*H0*4*v1*H1*33
 -->
 (S1 ^operator O1932 = -0.2817060109291377)
Retracting rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O1931 = 0.3377110018583719)
Retracting rl*prefer*rvt*predict-yes*H0*3*v1*H1*34
 -->
 (S1 ^operator O1931 = 0.6623675607605151)

--- END Proposal Phase ---

--- Decision Phase ---
RL update rl*prefer*rvt*predict-no*H0*6 0.999698 0 0.999698 -> 0.999748 0 0.999748(R,m,v=1,0.90411,0.0872933)
=>WM: (13624: S1 ^operator O1933)

   967:    O: O1933 (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 N967 +  :O )
Firing apply*operator*complete
 -->
 (I3 ^predict-no N966 -  :O )
 inner elaboration loop at bottom goal.
	--- Change Working Memory (PE) ---
=>WM: (13625: I3 ^predict-yes N967)
<=WM: (13612: N966 ^status complete)
<=WM: (13611: 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-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: (13629: I2 ^dir R)
=>WM: (13628: I2 ^reward 1)
=>WM: (13627: I2 ^see 1)
=>WM: (13626: N967 ^status complete)
<=WM: (13615: I2 ^dir R)
<=WM: (13614: I2 ^reward 1)
<=WM: (13613: I2 ^see 0)
=>WM: (13630: I2 ^level-1 R1-root)
<=WM: (13616: 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*v1*H1*36
 -->
 (S1 ^operator O1933 = -0.1070236389116304)
Firing rl*prefer*rvt*predict-no*H0*4*v1*H1*35
 -->
 (S1 ^operator O1934 = 0.6602488383529777)
Firing prefer*rvt*predict-no*H0*4*v1*H1
 -->
Firing prefer*rvt*predict-yes*H0*3*v1*H1
 -->
Firing elaborate*copy-see-to-output-link
 -->
 (I3 ^see 1 +)
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*4
 -->
 (S1 ^operator O1934 = 0.3397713875215998)
Firing rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O1933 = 0.3377110018583719)
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
 -->
 (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 R +)
Retracting rl*prefer*rvt*predict-no*H0*4*v1*H1*33
 -->
 (S1 ^operator O1934 = -0.2817060109291377)
Retracting rl*prefer*rvt*predict-no*H0*4
 -->
 (S1 ^operator O1934 = 0.3397713875215998)
Retracting rl*prefer*rvt*predict-yes*H0*3*v1*H1*34
 -->
 (S1 ^operator O1933 = 0.6623675607605151)
Retracting rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O1933 = 0.3377110018583719)
=>WM: (13637: S1 ^operator O1936 +)
=>WM: (13636: S1 ^operator O1935 +)
=>WM: (13635: O1936 ^name predict-no)
=>WM: (13634: O1935 ^name predict-yes)
=>WM: (13633: R971 ^value 1)
=>WM: (13632: R1 ^reward R971)
=>WM: (13631: I3 ^see 1)
<=WM: (13622: S1 ^operator O1933 +)
<=WM: (13624: S1 ^operator O1933)
<=WM: (13623: S1 ^operator O1934 +)
<=WM: (13617: R1 ^reward R970)
<=WM: (13602: I3 ^see 0)
<=WM: (13620: O1934 ^name predict-no)
<=WM: (13619: O1933 ^name predict-yes)
<=WM: (13618: R970 ^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 O1935 = 0.3377110018583719)
Firing prefer*rvt*predict-yes*H0*3*v1*H1
 -->
Firing rl*prefer*rvt*predict-yes*H0*3*v1*H1*36
 -->
 (S1 ^operator O1935 = -0.1070236389116304)
Firing prefer*rvt*predict-no*H0
 -->
Firing rl*prefer*rvt*predict-no*H0*4
 -->
 (S1 ^operator O1936 = 0.3397713875215998)
Firing prefer*rvt*predict-no*H0*4*v1*H1
 -->
Firing rl*prefer*rvt*predict-no*H0*4*v1*H1*35
 -->
 (S1 ^operator O1936 = 0.6602488383529777)
 inner elaboration loop at bottom goal.
Retracting rl*prefer*rvt*predict-no*H0*4
 -->
 (S1 ^operator O1934 = 0.3397713875215998)
Retracting rl*prefer*rvt*predict-no*H0*4*v1*H1*35
 -->
 (S1 ^operator O1934 = 0.6602488383529777)
Retracting rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O1933 = 0.3377110018583719)
Retracting rl*prefer*rvt*predict-yes*H0*3*v1*H1*36
 -->
 (S1 ^operator O1933 = -0.1070236389116304)

--- END Proposal Phase ---

--- Decision Phase ---
RL update rl*prefer*rvt*predict-yes*H0*3 0.590111 -0.2524 0.337711 -> 0.590104 -0.252399 0.337705(R,m,v=1,0.895706,0.0939938)
RL update rl*prefer*rvt*predict-yes*H0*3*v1*H1*34 0.409979 0.252388 0.662368 -> 0.409971 0.252389 0.66236(R,m,v=1,1,0)
=>WM: (13638: 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-yes N967 -  :O )
 inner elaboration loop at bottom goal.
	--- Change Working Memory (PE) ---
=>WM: (13639: I3 ^predict-no N968)
<=WM: (13626: N967 ^status complete)
<=WM: (13625: I3 ^predict-yes 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 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: (13643: I2 ^dir U)
=>WM: (13642: I2 ^reward 1)
=>WM: (13641: I2 ^see 0)
=>WM: (13640: N968 ^status complete)
<=WM: (13629: I2 ^dir R)
<=WM: (13628: I2 ^reward 1)
<=WM: (13627: I2 ^see 1)
=>WM: (13644: I2 ^level-1 R0-root)
<=WM: (13630: 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
 -->
 (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*2
 -->
 (S1 ^operator O1936 = 1.)
Firing rl*prefer*rvt*predict-yes*H0*1
 -->
 (S1 ^operator O1935 = 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
 -->
 (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 R +)
Retracting rl*prefer*rvt*predict-no*H0*4*v1*H1*35
 -->
 (S1 ^operator O1936 = 0.6602488383529777)
Retracting rl*prefer*rvt*predict-no*H0*4
 -->
 (S1 ^operator O1936 = 0.3397713875215998)
Retracting rl*prefer*rvt*predict-yes*H0*3*v1*H1*36
 -->
 (S1 ^operator O1935 = -0.1070236389116304)
Retracting rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O1935 = 0.3377045556949833)
=>WM: (13652: S1 ^operator O1938 +)
=>WM: (13651: S1 ^operator O1937 +)
=>WM: (13650: I3 ^dir U)
=>WM: (13649: O1938 ^name predict-no)
=>WM: (13648: O1937 ^name predict-yes)
=>WM: (13647: R972 ^value 1)
=>WM: (13646: R1 ^reward R972)
=>WM: (13645: I3 ^see 0)
<=WM: (13636: S1 ^operator O1935 +)
<=WM: (13637: S1 ^operator O1936 +)
<=WM: (13638: S1 ^operator O1936)
<=WM: (13621: I3 ^dir R)
<=WM: (13632: R1 ^reward R971)
<=WM: (13631: I3 ^see 1)
<=WM: (13635: O1936 ^name predict-no)
<=WM: (13634: O1935 ^name predict-yes)
<=WM: (13633: R971 ^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 O1937 = 0.)
Firing prefer*rvt*predict-no*H0
 -->
Firing rl*prefer*rvt*predict-no*H0*2
 -->
 (S1 ^operator O1938 = 1.)
 inner elaboration loop at bottom goal.
Retracting rl*prefer*rvt*predict-no*H0*2
 -->
 (S1 ^operator O1936 = 1.)
Retracting rl*prefer*rvt*predict-yes*H0*1
 -->
 (S1 ^operator O1935 = 0.)

--- END Proposal Phase ---

--- Decision Phase ---
RL update rl*prefer*rvt*predict-no*H0*4 0.570255 -0.230484 0.339771 -> 0.570253 -0.230483 0.33977(R,m,v=1,0.872727,0.111752)
RL update rl*prefer*rvt*predict-no*H0*4*v1*H1*35 0.429766 0.230483 0.660249 -> 0.429764 0.230483 0.660247(R,m,v=1,1,0)
=>WM: (13653: S1 ^operator O1938)

   969:    O: O1938 (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 N969 +  :O )
Firing apply*operator*complete
 -->
 (I3 ^predict-no N968 -  :O )
 inner elaboration loop at bottom goal.
	--- Change Working Memory (PE) ---
=>WM: (13654: I3 ^predict-no N969)
<=WM: (13640: N968 ^status complete)
<=WM: (13639: 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-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: (13658: I2 ^dir U)
=>WM: (13657: I2 ^reward 1)
=>WM: (13656: I2 ^see 0)
=>WM: (13655: N969 ^status complete)
<=WM: (13643: I2 ^dir U)
<=WM: (13642: I2 ^reward 1)
<=WM: (13641: I2 ^see 0)
=>WM: (13659: I2 ^level-1 R0-root)
<=WM: (13644: 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
 -->
 (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*2
 -->
 (S1 ^operator O1938 = 1.)
Firing rl*prefer*rvt*predict-yes*H0*1
 -->
 (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 U +)
Retracting rl*prefer*rvt*predict-no*H0*2
 -->
 (S1 ^operator O1938 = 1.)
Retracting rl*prefer*rvt*predict-yes*H0*1
 -->
 (S1 ^operator O1937 = 0.)
=>WM: (13665: S1 ^operator O1940 +)
=>WM: (13664: S1 ^operator O1939 +)
=>WM: (13663: O1940 ^name predict-no)
=>WM: (13662: O1939 ^name predict-yes)
=>WM: (13661: R973 ^value 1)
=>WM: (13660: R1 ^reward R973)
<=WM: (13651: S1 ^operator O1937 +)
<=WM: (13652: S1 ^operator O1938 +)
<=WM: (13653: S1 ^operator O1938)
<=WM: (13646: R1 ^reward R972)
<=WM: (13649: O1938 ^name predict-no)
<=WM: (13648: O1937 ^name predict-yes)
<=WM: (13647: R972 ^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 O1939 = 0.)
Firing prefer*rvt*predict-no*H0
 -->
Firing rl*prefer*rvt*predict-no*H0*2
 -->
 (S1 ^operator O1940 = 1.)
 inner elaboration loop at bottom goal.
Retracting rl*prefer*rvt*predict-no*H0*2
 -->
 (S1 ^operator O1938 = 1.)
Retracting rl*prefer*rvt*predict-yes*H0*1
 -->
 (S1 ^operator O1937 = 0.)

--- END Proposal Phase ---

--- Decision Phase ---
RL update rl*prefer*rvt*predict-no*H0*2 1 0 1 -> 1 0 1(R,m,v=1,1,0)
=>WM: (13666: 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-no N969 -  :O )
 inner elaboration loop at bottom goal.
	--- Change Working Memory (PE) ---
=>WM: (13667: I3 ^predict-no N970)
<=WM: (13655: N969 ^status complete)
<=WM: (13654: I3 ^predict-no 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: (13671: I2 ^dir L)
=>WM: (13670: I2 ^reward 1)
=>WM: (13669: I2 ^see 0)
=>WM: (13668: N970 ^status complete)
<=WM: (13658: I2 ^dir U)
<=WM: (13657: I2 ^reward 1)
<=WM: (13656: I2 ^see 0)
=>WM: (13672: I2 ^level-1 R0-root)
<=WM: (13659: I2 ^level-1 R0-root)

--- END Input Phase --- 

--- Proposal Phase ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing rl*prefer*rvt*predict-yes*H0*5*v1*H1*30
 -->
 (S1 ^operator O1939 = 0.735815301499146)
Firing prefer*rvt*predict-yes*H0*5*v1*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*6
 -->
 (S1 ^operator O1940 = 0.9997480945179411)
Firing rl*prefer*rvt*predict-yes*H0*5
 -->
 (S1 ^operator O1939 = 0.2640444846619989)
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
 -->
 (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*2
 -->
 (S1 ^operator O1940 = 1.)
Retracting rl*prefer*rvt*predict-yes*H0*1
 -->
 (S1 ^operator O1939 = 0.)
=>WM: (13679: S1 ^operator O1942 +)
=>WM: (13678: S1 ^operator O1941 +)
=>WM: (13677: I3 ^dir L)
=>WM: (13676: O1942 ^name predict-no)
=>WM: (13675: O1941 ^name predict-yes)
=>WM: (13674: R974 ^value 1)
=>WM: (13673: R1 ^reward R974)
<=WM: (13664: S1 ^operator O1939 +)
<=WM: (13665: S1 ^operator O1940 +)
<=WM: (13666: S1 ^operator O1940)
<=WM: (13650: I3 ^dir U)
<=WM: (13660: R1 ^reward R973)
<=WM: (13663: O1940 ^name predict-no)
<=WM: (13662: O1939 ^name predict-yes)
<=WM: (13661: R973 ^value 1)

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing prefer*rvt*predict-yes*H0
 -->
Firing rl*prefer*rvt*predict-yes*H0*5*v1*H1*30
 -->
 (S1 ^operator O1941 = 0.735815301499146)
Firing rl*prefer*rvt*predict-yes*H0*5
 -->
 (S1 ^operator O1941 = 0.2640444846619989)
Firing prefer*rvt*predict-yes*H0*5*v1*H1
 -->
Firing prefer*rvt*predict-no*H0
 -->
Firing rl*prefer*rvt*predict-no*H0*6
 -->
 (S1 ^operator O1942 = 0.9997480945179411)
 inner elaboration loop at bottom goal.
Retracting rl*prefer*rvt*predict-no*H0*6
 -->
 (S1 ^operator O1940 = 0.9997480945179411)
Retracting rl*prefer*rvt*predict-yes*H0*5
 -->
 (S1 ^operator O1939 = 0.2640444846619989)
Retracting rl*prefer*rvt*predict-yes*H0*5*v1*H1*30
 -->
 (S1 ^operator O1939 = 0.735815301499146)

--- END Proposal Phase ---

--- Decision Phase ---
RL update rl*prefer*rvt*predict-no*H0*2 1 0 1 -> 1 0 1(R,m,v=1,1,0)
=>WM: (13680: 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: (13681: I3 ^predict-yes N971)
<=WM: (13668: N970 ^status complete)
<=WM: (13667: 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 isR
--- END Output Phase ---
---- Input Phase --- 
=>WM: (13685: I2 ^dir R)
=>WM: (13684: I2 ^reward 1)
=>WM: (13683: I2 ^see 1)
=>WM: (13682: N971 ^status complete)
<=WM: (13671: I2 ^dir L)
<=WM: (13670: I2 ^reward 1)
<=WM: (13669: I2 ^see 0)
=>WM: (13686: I2 ^level-1 L1-root)
<=WM: (13672: I2 ^level-1 R0-root)

--- END Input Phase --- 

--- Proposal Phase ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing rl*prefer*rvt*predict-no*H0*4*v1*H1*37
 -->
 (S1 ^operator O1942 = -0.2714224023553999)
Firing rl*prefer*rvt*predict-yes*H0*3*v1*H1*38
 -->
 (S1 ^operator O1941 = 0.6622033637991441)
Firing prefer*rvt*predict-no*H0*4*v1*H1
 -->
Firing prefer*rvt*predict-yes*H0*3*v1*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*4
 -->
 (S1 ^operator O1942 = 0.339769731277316)
Firing rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O1941 = 0.3377045556949833)
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
 -->
 (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*6
 -->
 (S1 ^operator O1942 = 0.9997480945179411)
Retracting rl*prefer*rvt*predict-yes*H0*5
 -->
 (S1 ^operator O1941 = 0.2640444846619989)
Retracting rl*prefer*rvt*predict-yes*H0*5*v1*H1*30
 -->
 (S1 ^operator O1941 = 0.735815301499146)
=>WM: (13694: S1 ^operator O1944 +)
=>WM: (13693: S1 ^operator O1943 +)
=>WM: (13692: I3 ^dir R)
=>WM: (13691: O1944 ^name predict-no)
=>WM: (13690: O1943 ^name predict-yes)
=>WM: (13689: R975 ^value 1)
=>WM: (13688: R1 ^reward R975)
=>WM: (13687: I3 ^see 1)
<=WM: (13678: S1 ^operator O1941 +)
<=WM: (13680: S1 ^operator O1941)
<=WM: (13679: S1 ^operator O1942 +)
<=WM: (13677: I3 ^dir L)
<=WM: (13673: R1 ^reward R974)
<=WM: (13645: I3 ^see 0)
<=WM: (13676: O1942 ^name predict-no)
<=WM: (13675: O1941 ^name predict-yes)
<=WM: (13674: R974 ^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 O1943 = 0.3377045556949833)
Firing prefer*rvt*predict-yes*H0*3*v1*H1
 -->
Firing rl*prefer*rvt*predict-yes*H0*3*v1*H1*38
 -->
 (S1 ^operator O1943 = 0.6622033637991441)
Firing prefer*rvt*predict-no*H0
 -->
Firing rl*prefer*rvt*predict-no*H0*4
 -->
 (S1 ^operator O1944 = 0.339769731277316)
Firing prefer*rvt*predict-no*H0*4*v1*H1
 -->
Firing rl*prefer*rvt*predict-no*H0*4*v1*H1*37
 -->
 (S1 ^operator O1944 = -0.2714224023553999)
 inner elaboration loop at bottom goal.
Retracting rl*prefer*rvt*predict-no*H0*4
 -->
 (S1 ^operator O1942 = 0.339769731277316)
Retracting rl*prefer*rvt*predict-no*H0*4*v1*H1*37
 -->
 (S1 ^operator O1942 = -0.2714224023553999)
Retracting rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O1941 = 0.3377045556949833)
Retracting rl*prefer*rvt*predict-yes*H0*3*v1*H1*38
 -->
 (S1 ^operator O1941 = 0.6622033637991441)

--- END Proposal Phase ---

--- Decision Phase ---
RL update rl*prefer*rvt*predict-yes*H0*5 0.55443 -0.290385 0.264044 -> 0.554441 -0.290385 0.264056(R,m,v=1,0.874286,0.110542)
RL update rl*prefer*rvt*predict-yes*H0*5*v1*H1*30 0.445432 0.290383 0.735815 -> 0.445446 0.290383 0.735829(R,m,v=1,1,0)
=>WM: (13695: S1 ^operator O1943)

   972:    O: O1943 (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 N972 +  :O )
Firing apply*operator*complete
 -->
 (I3 ^predict-yes N971 -  :O )
 inner elaboration loop at bottom goal.
	--- Change Working Memory (PE) ---
=>WM: (13696: I3 ^predict-yes N972)
<=WM: (13682: N971 ^status complete)
<=WM: (13681: 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-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: (13700: I2 ^dir L)
=>WM: (13699: I2 ^reward 1)
=>WM: (13698: I2 ^see 1)
=>WM: (13697: N972 ^status complete)
<=WM: (13685: I2 ^dir R)
<=WM: (13684: I2 ^reward 1)
<=WM: (13683: I2 ^see 1)
=>WM: (13701: I2 ^level-1 R1-root)
<=WM: (13686: I2 ^level-1 L1-root)

--- END Input Phase --- 

--- Proposal Phase ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing rl*prefer*rvt*predict-yes*H0*5*v1*H1*41
 -->
 (S1 ^operator O1943 = 0.7362862485154646)
Firing prefer*rvt*predict-yes*H0*5*v1*H1
 -->
Firing elaborate*copy-see-to-output-link
 -->
 (I3 ^see 1 +)
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 = 0.9997480945179411)
Firing rl*prefer*rvt*predict-yes*H0*5
 -->
 (S1 ^operator O1943 = 0.2640558568198847)
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
 -->
 (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 R +)
Retracting rl*prefer*rvt*predict-no*H0*4*v1*H1*37
 -->
 (S1 ^operator O1944 = -0.2714224023553999)
Retracting rl*prefer*rvt*predict-no*H0*4
 -->
 (S1 ^operator O1944 = 0.339769731277316)
Retracting rl*prefer*rvt*predict-yes*H0*3*v1*H1*38
 -->
 (S1 ^operator O1943 = 0.6622033637991441)
Retracting rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O1943 = 0.3377045556949833)
=>WM: (13708: S1 ^operator O1946 +)
=>WM: (13707: S1 ^operator O1945 +)
=>WM: (13706: I3 ^dir L)
=>WM: (13705: O1946 ^name predict-no)
=>WM: (13704: O1945 ^name predict-yes)
=>WM: (13703: R976 ^value 1)
=>WM: (13702: R1 ^reward R976)
<=WM: (13693: S1 ^operator O1943 +)
<=WM: (13695: S1 ^operator O1943)
<=WM: (13694: S1 ^operator O1944 +)
<=WM: (13692: I3 ^dir R)
<=WM: (13688: R1 ^reward R975)
<=WM: (13691: O1944 ^name predict-no)
<=WM: (13690: O1943 ^name predict-yes)
<=WM: (13689: 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 = 0.2640558568198847)
Firing prefer*rvt*predict-yes*H0*5*v1*H1
 -->
Firing rl*prefer*rvt*predict-yes*H0*5*v1*H1*41
 -->
 (S1 ^operator O1945 = 0.7362862485154646)
Firing prefer*rvt*predict-no*H0
 -->
Firing rl*prefer*rvt*predict-no*H0*6
 -->
 (S1 ^operator O1946 = 0.9997480945179411)
 inner elaboration loop at bottom goal.
Retracting rl*prefer*rvt*predict-no*H0*6
 -->
 (S1 ^operator O1944 = 0.9997480945179411)
Retracting rl*prefer*rvt*predict-yes*H0*5
 -->
 (S1 ^operator O1943 = 0.2640558568198847)
Retracting rl*prefer*rvt*predict-yes*H0*5*v1*H1*41
 -->
 (S1 ^operator O1943 = 0.7362862485154646)

--- END Proposal Phase ---

--- Decision Phase ---
RL update rl*prefer*rvt*predict-yes*H0*3 0.590104 -0.252399 0.337705 -> 0.590112 -0.2524 0.337712(R,m,v=1,0.896341,0.0934835)
RL update rl*prefer*rvt*predict-yes*H0*3*v1*H1*38 0.40979 0.252413 0.662203 -> 0.4098 0.252412 0.662212(R,m,v=1,1,0)
=>WM: (13709: S1 ^operator O1945)

   973:    O: O1945 (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 N973 +  :O )
Firing apply*operator*complete
 -->
 (I3 ^predict-yes N972 -  :O )
 inner elaboration loop at bottom goal.
	--- Change Working Memory (PE) ---
=>WM: (13710: I3 ^predict-yes N973)
<=WM: (13697: N972 ^status complete)
<=WM: (13696: I3 ^predict-yes 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-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: (13714: I2 ^dir U)
=>WM: (13713: I2 ^reward 1)
=>WM: (13712: I2 ^see 1)
=>WM: (13711: N973 ^status complete)
<=WM: (13700: I2 ^dir L)
<=WM: (13699: I2 ^reward 1)
<=WM: (13698: I2 ^see 1)
=>WM: (13715: I2 ^level-1 L1-root)
<=WM: (13701: 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
 -->
 (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*2
 -->
 (S1 ^operator O1946 = 1.)
Firing rl*prefer*rvt*predict-yes*H0*1
 -->
 (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 1 +)
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 L +)
Retracting rl*prefer*rvt*predict-no*H0*6
 -->
 (S1 ^operator O1946 = 0.9997480945179411)
Retracting rl*prefer*rvt*predict-yes*H0*5*v1*H1*41
 -->
 (S1 ^operator O1945 = 0.7362862485154646)
Retracting rl*prefer*rvt*predict-yes*H0*5
 -->
 (S1 ^operator O1945 = 0.2640558568198847)
=>WM: (13722: S1 ^operator O1948 +)
=>WM: (13721: S1 ^operator O1947 +)
=>WM: (13720: I3 ^dir U)
=>WM: (13719: O1948 ^name predict-no)
=>WM: (13718: O1947 ^name predict-yes)
=>WM: (13717: R977 ^value 1)
=>WM: (13716: R1 ^reward R977)
<=WM: (13707: S1 ^operator O1945 +)
<=WM: (13709: S1 ^operator O1945)
<=WM: (13708: S1 ^operator O1946 +)
<=WM: (13706: I3 ^dir L)
<=WM: (13702: R1 ^reward R976)
<=WM: (13705: O1946 ^name predict-no)
<=WM: (13704: O1945 ^name predict-yes)
<=WM: (13703: R976 ^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 O1947 = 0.)
Firing prefer*rvt*predict-no*H0
 -->
Firing rl*prefer*rvt*predict-no*H0*2
 -->
 (S1 ^operator O1948 = 1.)
 inner elaboration loop at bottom goal.
Retracting rl*prefer*rvt*predict-no*H0*2
 -->
 (S1 ^operator O1946 = 1.)
Retracting rl*prefer*rvt*predict-yes*H0*1
 -->
 (S1 ^operator O1945 = 0.)

--- END Proposal Phase ---

--- Decision Phase ---
RL update rl*prefer*rvt*predict-yes*H0*5 0.554441 -0.290385 0.264056 -> 0.554414 -0.290386 0.264028(R,m,v=1,0.875,0.11)
RL update rl*prefer*rvt*predict-yes*H0*5*v1*H1*41 0.445895 0.290391 0.736286 -> 0.445864 0.29039 0.736254(R,m,v=1,1,0)
=>WM: (13723: 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-yes N973 -  :O )
 inner elaboration loop at bottom goal.
	--- Change Working Memory (PE) ---
=>WM: (13724: I3 ^predict-no N974)
<=WM: (13711: N973 ^status complete)
<=WM: (13710: I3 ^predict-yes 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: (13728: I2 ^dir U)
=>WM: (13727: I2 ^reward 1)
=>WM: (13726: I2 ^see 0)
=>WM: (13725: N974 ^status complete)
<=WM: (13714: I2 ^dir U)
<=WM: (13713: I2 ^reward 1)
<=WM: (13712: I2 ^see 1)
=>WM: (13729: I2 ^level-1 L1-root)
<=WM: (13715: 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
 -->
 (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*2
 -->
 (S1 ^operator O1948 = 1.)
Firing rl*prefer*rvt*predict-yes*H0*1
 -->
 (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 1 +)
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*2
 -->
 (S1 ^operator O1948 = 1.)
Retracting rl*prefer*rvt*predict-yes*H0*1
 -->
 (S1 ^operator O1947 = 0.)
=>WM: (13736: S1 ^operator O1950 +)
=>WM: (13735: S1 ^operator O1949 +)
=>WM: (13734: O1950 ^name predict-no)
=>WM: (13733: O1949 ^name predict-yes)
=>WM: (13732: R978 ^value 1)
=>WM: (13731: R1 ^reward R978)
=>WM: (13730: I3 ^see 0)
<=WM: (13721: S1 ^operator O1947 +)
<=WM: (13722: S1 ^operator O1948 +)
<=WM: (13723: S1 ^operator O1948)
<=WM: (13716: R1 ^reward R977)
<=WM: (13687: I3 ^see 1)
<=WM: (13719: O1948 ^name predict-no)
<=WM: (13718: O1947 ^name predict-yes)
<=WM: (13717: R977 ^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 O1949 = 0.)
Firing prefer*rvt*predict-no*H0
 -->
Firing rl*prefer*rvt*predict-no*H0*2
 -->
 (S1 ^operator O1950 = 1.)
 inner elaboration loop at bottom goal.
Retracting rl*prefer*rvt*predict-no*H0*2
 -->
 (S1 ^operator O1948 = 1.)
Retracting rl*prefer*rvt*predict-yes*H0*1
 -->
 (S1 ^operator O1947 = 0.)

--- END Proposal Phase ---

--- Decision Phase ---
RL update rl*prefer*rvt*predict-no*H0*2 1 0 1 -> 1 0 1(R,m,v=1,1,0)
=>WM: (13737: 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: (13738: I3 ^predict-no N975)
<=WM: (13725: N974 ^status complete)
<=WM: (13724: 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 isR
--- END Output Phase ---
|\---- Input Phase --- 
=>WM: (13742: I2 ^dir R)
=>WM: (13741: I2 ^reward 1)
=>WM: (13740: I2 ^see 0)
=>WM: (13739: N975 ^status complete)
<=WM: (13728: I2 ^dir U)
<=WM: (13727: I2 ^reward 1)
<=WM: (13726: I2 ^see 0)
=>WM: (13743: I2 ^level-1 L1-root)
<=WM: (13729: I2 ^level-1 L1-root)

--- END Input Phase --- 

--- Proposal Phase ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing rl*prefer*rvt*predict-no*H0*4*v1*H1*37
 -->
 (S1 ^operator O1950 = -0.2714224023553999)
Firing rl*prefer*rvt*predict-yes*H0*3*v1*H1*38
 -->
 (S1 ^operator O1949 = 0.6622121600001568)
Firing prefer*rvt*predict-no*H0*4*v1*H1
 -->
Firing prefer*rvt*predict-yes*H0*3*v1*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*4
 -->
 (S1 ^operator O1950 = 0.339769731277316)
Firing rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O1949 = 0.3377121034427055)
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
 -->
 (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*2
 -->
 (S1 ^operator O1950 = 1.)
Retracting rl*prefer*rvt*predict-yes*H0*1
 -->
 (S1 ^operator O1949 = 0.)
=>WM: (13750: S1 ^operator O1952 +)
=>WM: (13749: S1 ^operator O1951 +)
=>WM: (13748: I3 ^dir R)
=>WM: (13747: O1952 ^name predict-no)
=>WM: (13746: O1951 ^name predict-yes)
=>WM: (13745: R979 ^value 1)
=>WM: (13744: R1 ^reward R979)
<=WM: (13735: S1 ^operator O1949 +)
<=WM: (13736: S1 ^operator O1950 +)
<=WM: (13737: S1 ^operator O1950)
<=WM: (13720: I3 ^dir U)
<=WM: (13731: R1 ^reward R978)
<=WM: (13734: O1950 ^name predict-no)
<=WM: (13733: O1949 ^name predict-yes)
<=WM: (13732: R978 ^value 1)

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing prefer*rvt*predict-yes*H0
 -->
Firing rl*prefer*rvt*predict-yes*H0*3*v1*H1*38
 -->
 (S1 ^operator O1951 = 0.6622121600001568)
Firing rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O1951 = 0.3377121034427055)
Firing prefer*rvt*predict-yes*H0*3*v1*H1
 -->
Firing prefer*rvt*predict-no*H0
 -->
Firing rl*prefer*rvt*predict-no*H0*4*v1*H1*37
 -->
 (S1 ^operator O1952 = -0.2714224023553999)
Firing rl*prefer*rvt*predict-no*H0*4
 -->
 (S1 ^operator O1952 = 0.339769731277316)
Firing prefer*rvt*predict-no*H0*4*v1*H1
 -->
 inner elaboration loop at bottom goal.
Retracting rl*prefer*rvt*predict-no*H0*4
 -->
 (S1 ^operator O1950 = 0.339769731277316)
Retracting rl*prefer*rvt*predict-no*H0*4*v1*H1*37
 -->
 (S1 ^operator O1950 = -0.2714224023553999)
Retracting rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O1949 = 0.3377121034427055)
Retracting rl*prefer*rvt*predict-yes*H0*3*v1*H1*38
 -->
 (S1 ^operator O1949 = 0.6622121600001568)

--- END Proposal Phase ---

--- Decision Phase ---
RL update rl*prefer*rvt*predict-no*H0*2 1 0 1 -> 1 0 1(R,m,v=1,1,0)
=>WM: (13751: S1 ^operator O1951)

   976:    O: O1951 (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 N976 +  :O )
Firing apply*operator*complete
 -->
 (I3 ^predict-no N975 -  :O )
 inner elaboration loop at bottom goal.
	--- Change Working Memory (PE) ---
=>WM: (13752: I3 ^predict-yes N976)
<=WM: (13739: N975 ^status complete)
<=WM: (13738: 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-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: (13756: I2 ^dir U)
=>WM: (13755: I2 ^reward 1)
=>WM: (13754: I2 ^see 1)
=>WM: (13753: N976 ^status complete)
<=WM: (13742: I2 ^dir R)
<=WM: (13741: I2 ^reward 1)
<=WM: (13740: I2 ^see 0)
=>WM: (13757: I2 ^level-1 R1-root)
<=WM: (13743: 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
 -->
 (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*2
 -->
 (S1 ^operator O1952 = 1.)
Firing rl*prefer*rvt*predict-yes*H0*1
 -->
 (S1 ^operator O1951 = 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
 -->
 (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 R +)
Retracting rl*prefer*rvt*predict-no*H0*4
 -->
 (S1 ^operator O1952 = 0.339769731277316)
Retracting rl*prefer*rvt*predict-no*H0*4*v1*H1*37
 -->
 (S1 ^operator O1952 = -0.2714224023553999)
Retracting rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O1951 = 0.3377121034427055)
Retracting rl*prefer*rvt*predict-yes*H0*3*v1*H1*38
 -->
 (S1 ^operator O1951 = 0.6622121600001568)
=>WM: (13765: S1 ^operator O1954 +)
=>WM: (13764: S1 ^operator O1953 +)
=>WM: (13763: I3 ^dir U)
=>WM: (13762: O1954 ^name predict-no)
=>WM: (13761: O1953 ^name predict-yes)
=>WM: (13760: R980 ^value 1)
=>WM: (13759: R1 ^reward R980)
=>WM: (13758: I3 ^see 1)
<=WM: (13749: S1 ^operator O1951 +)
<=WM: (13751: S1 ^operator O1951)
<=WM: (13750: S1 ^operator O1952 +)
<=WM: (13748: I3 ^dir R)
<=WM: (13744: R1 ^reward R979)
<=WM: (13730: I3 ^see 0)
<=WM: (13747: O1952 ^name predict-no)
<=WM: (13746: O1951 ^name predict-yes)
<=WM: (13745: R979 ^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 O1953 = 0.)
Firing prefer*rvt*predict-no*H0
 -->
Firing rl*prefer*rvt*predict-no*H0*2
 -->
 (S1 ^operator O1954 = 1.)
 inner elaboration loop at bottom goal.
Retracting rl*prefer*rvt*predict-no*H0*2
 -->
 (S1 ^operator O1952 = 1.)
Retracting rl*prefer*rvt*predict-yes*H0*1
 -->
 (S1 ^operator O1951 = 0.)

--- END Proposal Phase ---

--- Decision Phase ---
RL update rl*prefer*rvt*predict-yes*H0*3 0.590112 -0.2524 0.337712 -> 0.59012 -0.252401 0.337718(R,m,v=1,0.89697,0.0929786)
RL update rl*prefer*rvt*predict-yes*H0*3*v1*H1*38 0.4098 0.252412 0.662212 -> 0.409809 0.252411 0.662219(R,m,v=1,1,0)
=>WM: (13766: S1 ^operator O1954)

   977:    O: O1954 (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 N977 +  :O )
Firing apply*operator*complete
 -->
 (I3 ^predict-yes N976 -  :O )
 inner elaboration loop at bottom goal.
	--- Change Working Memory (PE) ---
=>WM: (13767: I3 ^predict-no N977)
<=WM: (13753: N976 ^status complete)
<=WM: (13752: I3 ^predict-yes 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-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: (13771: I2 ^dir U)
=>WM: (13770: I2 ^reward 1)
=>WM: (13769: I2 ^see 0)
=>WM: (13768: N977 ^status complete)
<=WM: (13756: I2 ^dir U)
<=WM: (13755: I2 ^reward 1)
<=WM: (13754: I2 ^see 1)
=>WM: (13772: I2 ^level-1 R1-root)
<=WM: (13757: 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
 -->
 (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*2
 -->
 (S1 ^operator O1954 = 1.)
Firing rl*prefer*rvt*predict-yes*H0*1
 -->
 (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 1 +)
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 U +)
Retracting rl*prefer*rvt*predict-no*H0*2
 -->
 (S1 ^operator O1954 = 1.)
Retracting rl*prefer*rvt*predict-yes*H0*1
 -->
 (S1 ^operator O1953 = 0.)
=>WM: (13779: S1 ^operator O1956 +)
=>WM: (13778: S1 ^operator O1955 +)
=>WM: (13777: O1956 ^name predict-no)
=>WM: (13776: O1955 ^name predict-yes)
=>WM: (13775: R981 ^value 1)
=>WM: (13774: R1 ^reward R981)
=>WM: (13773: I3 ^see 0)
<=WM: (13764: S1 ^operator O1953 +)
<=WM: (13765: S1 ^operator O1954 +)
<=WM: (13766: S1 ^operator O1954)
<=WM: (13759: R1 ^reward R980)
<=WM: (13758: I3 ^see 1)
<=WM: (13762: O1954 ^name predict-no)
<=WM: (13761: O1953 ^name predict-yes)
<=WM: (13760: R980 ^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 O1955 = 0.)
Firing prefer*rvt*predict-no*H0
 -->
Firing rl*prefer*rvt*predict-no*H0*2
 -->
 (S1 ^operator O1956 = 1.)
 inner elaboration loop at bottom goal.
Retracting rl*prefer*rvt*predict-no*H0*2
 -->
 (S1 ^operator O1954 = 1.)
Retracting rl*prefer*rvt*predict-yes*H0*1
 -->
 (S1 ^operator O1953 = 0.)

--- END Proposal Phase ---

--- Decision Phase ---
RL update rl*prefer*rvt*predict-no*H0*2 1 0 1 -> 1 0 1(R,m,v=1,1,0)
=>WM: (13780: 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-no N977 -  :O )
 inner elaboration loop at bottom goal.
	--- Change Working Memory (PE) ---
=>WM: (13781: I3 ^predict-no N978)
<=WM: (13768: N977 ^status complete)
<=WM: (13767: I3 ^predict-no 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: (13785: I2 ^dir R)
=>WM: (13784: I2 ^reward 1)
=>WM: (13783: I2 ^see 0)
=>WM: (13782: N978 ^status complete)
<=WM: (13771: I2 ^dir U)
<=WM: (13770: I2 ^reward 1)
<=WM: (13769: I2 ^see 0)
=>WM: (13786: I2 ^level-1 R1-root)
<=WM: (13772: 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*v1*H1*36
 -->
 (S1 ^operator O1955 = -0.1070236389116304)
Firing rl*prefer*rvt*predict-no*H0*4*v1*H1*35
 -->
 (S1 ^operator O1956 = 0.6602468953107985)
Firing prefer*rvt*predict-no*H0*4*v1*H1
 -->
Firing prefer*rvt*predict-yes*H0*3*v1*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 = 0.339769731277316)
Firing rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O1955 = 0.3377183053124619)
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
 -->
 (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*2
 -->
 (S1 ^operator O1956 = 1.)
Retracting rl*prefer*rvt*predict-yes*H0*1
 -->
 (S1 ^operator O1955 = 0.)
=>WM: (13793: S1 ^operator O1958 +)
=>WM: (13792: S1 ^operator O1957 +)
=>WM: (13791: I3 ^dir R)
=>WM: (13790: O1958 ^name predict-no)
=>WM: (13789: O1957 ^name predict-yes)
=>WM: (13788: R982 ^value 1)
=>WM: (13787: R1 ^reward R982)
<=WM: (13778: S1 ^operator O1955 +)
<=WM: (13779: S1 ^operator O1956 +)
<=WM: (13780: S1 ^operator O1956)
<=WM: (13763: I3 ^dir U)
<=WM: (13774: R1 ^reward R981)
<=WM: (13777: O1956 ^name predict-no)
<=WM: (13776: O1955 ^name predict-yes)
<=WM: (13775: R981 ^value 1)

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing prefer*rvt*predict-yes*H0
 -->
Firing rl*prefer*rvt*predict-yes*H0*3*v1*H1*36
 -->
 (S1 ^operator O1957 = -0.1070236389116304)
Firing rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O1957 = 0.3377183053124619)
Firing prefer*rvt*predict-yes*H0*3*v1*H1
 -->
Firing prefer*rvt*predict-no*H0
 -->
Firing rl*prefer*rvt*predict-no*H0*4*v1*H1*35
 -->
 (S1 ^operator O1958 = 0.6602468953107985)
Firing rl*prefer*rvt*predict-no*H0*4
 -->
 (S1 ^operator O1958 = 0.339769731277316)
Firing prefer*rvt*predict-no*H0*4*v1*H1
 -->
 inner elaboration loop at bottom goal.
Retracting rl*prefer*rvt*predict-no*H0*4
 -->
 (S1 ^operator O1956 = 0.339769731277316)
Retracting rl*prefer*rvt*predict-no*H0*4*v1*H1*35
 -->
 (S1 ^operator O1956 = 0.6602468953107985)
Retracting rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O1955 = 0.3377183053124619)
Retracting rl*prefer*rvt*predict-yes*H0*3*v1*H1*36
 -->
 (S1 ^operator O1955 = -0.1070236389116304)

--- END Proposal Phase ---

--- Decision Phase ---
RL update rl*prefer*rvt*predict-no*H0*2 1 0 1 -> 1 0 1(R,m,v=1,1,0)
=>WM: (13794: 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: (13795: I3 ^predict-no N979)
<=WM: (13782: N978 ^status complete)
<=WM: (13781: 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: (13799: I2 ^dir U)
=>WM: (13798: I2 ^reward 1)
=>WM: (13797: I2 ^see 0)
=>WM: (13796: N979 ^status complete)
<=WM: (13785: I2 ^dir R)
<=WM: (13784: I2 ^reward 1)
<=WM: (13783: I2 ^see 0)
=>WM: (13800: I2 ^level-1 R0-root)
<=WM: (13786: 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*2
 -->
 (S1 ^operator O1958 = 1.)
Firing rl*prefer*rvt*predict-yes*H0*1
 -->
 (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 = 0.339769731277316)
Retracting rl*prefer*rvt*predict-no*H0*4*v1*H1*35
 -->
 (S1 ^operator O1958 = 0.6602468953107985)
Retracting rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O1957 = 0.3377183053124619)
Retracting rl*prefer*rvt*predict-yes*H0*3*v1*H1*36
 -->
 (S1 ^operator O1957 = -0.1070236389116304)
=>WM: (13807: S1 ^operator O1960 +)
=>WM: (13806: S1 ^operator O1959 +)
=>WM: (13805: I3 ^dir U)
=>WM: (13804: O1960 ^name predict-no)
=>WM: (13803: O1959 ^name predict-yes)
=>WM: (13802: R983 ^value 1)
=>WM: (13801: R1 ^reward R983)
<=WM: (13792: S1 ^operator O1957 +)
<=WM: (13793: S1 ^operator O1958 +)
<=WM: (13794: S1 ^operator O1958)
<=WM: (13791: I3 ^dir R)
<=WM: (13787: R1 ^reward R982)
<=WM: (13790: O1958 ^name predict-no)
<=WM: (13789: O1957 ^name predict-yes)
<=WM: (13788: R982 ^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 O1959 = 0.)
Firing prefer*rvt*predict-no*H0
 -->
Firing rl*prefer*rvt*predict-no*H0*2
 -->
 (S1 ^operator O1960 = 1.)
 inner elaboration loop at bottom goal.
Retracting rl*prefer*rvt*predict-no*H0*2
 -->
 (S1 ^operator O1958 = 1.)
Retracting rl*prefer*rvt*predict-yes*H0*1
 -->
 (S1 ^operator O1957 = 0.)

--- END Proposal Phase ---

--- Decision Phase ---
RL update rl*prefer*rvt*predict-no*H0*4 0.570253 -0.230483 0.33977 -> 0.570252 -0.230483 0.339768(R,m,v=1,0.873494,0.111172)
RL update rl*prefer*rvt*predict-no*H0*4*v1*H1*35 0.429764 0.230483 0.660247 -> 0.429763 0.230483 0.660245(R,m,v=1,1,0)
=>WM: (13808: 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: (13809: I3 ^predict-no N980)
<=WM: (13796: N979 ^status complete)
<=WM: (13795: 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 isU
--- END Output Phase ---
|\---- Input Phase --- 
=>WM: (13813: I2 ^dir U)
=>WM: (13812: I2 ^reward 1)
=>WM: (13811: I2 ^see 0)
=>WM: (13810: N980 ^status complete)
<=WM: (13799: I2 ^dir U)
<=WM: (13798: I2 ^reward 1)
<=WM: (13797: I2 ^see 0)
=>WM: (13814: I2 ^level-1 R0-root)
<=WM: (13800: 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
 -->
 (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 = 1.)
Firing rl*prefer*rvt*predict-yes*H0*1
 -->
 (S1 ^operator O1959 = 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
 -->
 (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*2
 -->
 (S1 ^operator O1960 = 1.)
Retracting rl*prefer*rvt*predict-yes*H0*1
 -->
 (S1 ^operator O1959 = 0.)
=>WM: (13820: S1 ^operator O1962 +)
=>WM: (13819: S1 ^operator O1961 +)
=>WM: (13818: O1962 ^name predict-no)
=>WM: (13817: O1961 ^name predict-yes)
=>WM: (13816: R984 ^value 1)
=>WM: (13815: R1 ^reward R984)
<=WM: (13806: S1 ^operator O1959 +)
<=WM: (13807: S1 ^operator O1960 +)
<=WM: (13808: S1 ^operator O1960)
<=WM: (13801: R1 ^reward R983)
<=WM: (13804: O1960 ^name predict-no)
<=WM: (13803: O1959 ^name predict-yes)
<=WM: (13802: R983 ^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 O1961 = 0.)
Firing prefer*rvt*predict-no*H0
 -->
Firing rl*prefer*rvt*predict-no*H0*2
 -->
 (S1 ^operator O1962 = 1.)
 inner elaboration loop at bottom goal.
Retracting rl*prefer*rvt*predict-no*H0*2
 -->
 (S1 ^operator O1960 = 1.)
Retracting rl*prefer*rvt*predict-yes*H0*1
 -->
 (S1 ^operator O1959 = 0.)

--- END Proposal Phase ---

--- Decision Phase ---
RL update rl*prefer*rvt*predict-no*H0*2 1 0 1 -> 1 0 1(R,m,v=1,1,0)
=>WM: (13821: S1 ^operator O1962)

   981:    O: O1962 (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 N981 +  :O )
Firing apply*operator*complete
 -->
 (I3 ^predict-no N980 -  :O )
 inner elaboration loop at bottom goal.
	--- Change Working Memory (PE) ---
=>WM: (13822: I3 ^predict-no N981)
<=WM: (13810: N980 ^status complete)
<=WM: (13809: 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-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: (13826: I2 ^dir L)
=>WM: (13825: I2 ^reward 1)
=>WM: (13824: I2 ^see 0)
=>WM: (13823: N981 ^status complete)
<=WM: (13813: I2 ^dir U)
<=WM: (13812: I2 ^reward 1)
<=WM: (13811: I2 ^see 0)
=>WM: (13827: I2 ^level-1 R0-root)
<=WM: (13814: I2 ^level-1 R0-root)

--- END Input Phase --- 

--- Proposal Phase ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing rl*prefer*rvt*predict-yes*H0*5*v1*H1*30
 -->
 (S1 ^operator O1961 = 0.7358289752034343)
Firing prefer*rvt*predict-yes*H0*5*v1*H1
 -->
Firing elaborate*copy-see-to-output-link
 -->
 (I3 ^see 0 +)
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*6
 -->
 (S1 ^operator O1962 = 0.9997480945179411)
Firing rl*prefer*rvt*predict-yes*H0*5
 -->
 (S1 ^operator O1961 = 0.2640281357095451)
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 U +)
Retracting rl*prefer*rvt*predict-no*H0*2
 -->
 (S1 ^operator O1962 = 1.)
Retracting rl*prefer*rvt*predict-yes*H0*1
 -->
 (S1 ^operator O1961 = 0.)
=>WM: (13834: S1 ^operator O1964 +)
=>WM: (13833: S1 ^operator O1963 +)
=>WM: (13832: I3 ^dir L)
=>WM: (13831: O1964 ^name predict-no)
=>WM: (13830: O1963 ^name predict-yes)
=>WM: (13829: R985 ^value 1)
=>WM: (13828: R1 ^reward R985)
<=WM: (13819: S1 ^operator O1961 +)
<=WM: (13820: S1 ^operator O1962 +)
<=WM: (13821: S1 ^operator O1962)
<=WM: (13805: I3 ^dir U)
<=WM: (13815: R1 ^reward R984)
<=WM: (13818: O1962 ^name predict-no)
<=WM: (13817: O1961 ^name predict-yes)
<=WM: (13816: R984 ^value 1)

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing prefer*rvt*predict-yes*H0
 -->
Firing rl*prefer*rvt*predict-yes*H0*5*v1*H1*30
 -->
 (S1 ^operator O1963 = 0.7358289752034343)
Firing rl*prefer*rvt*predict-yes*H0*5
 -->
 (S1 ^operator O1963 = 0.2640281357095451)
Firing prefer*rvt*predict-yes*H0*5*v1*H1
 -->
Firing prefer*rvt*predict-no*H0
 -->
Firing rl*prefer*rvt*predict-no*H0*6
 -->
 (S1 ^operator O1964 = 0.9997480945179411)
 inner elaboration loop at bottom goal.
Retracting rl*prefer*rvt*predict-no*H0*6
 -->
 (S1 ^operator O1962 = 0.9997480945179411)
Retracting rl*prefer*rvt*predict-yes*H0*5
 -->
 (S1 ^operator O1961 = 0.2640281357095451)
Retracting rl*prefer*rvt*predict-yes*H0*5*v1*H1*30
 -->
 (S1 ^operator O1961 = 0.7358289752034343)

--- END Proposal Phase ---

--- Decision Phase ---
RL update rl*prefer*rvt*predict-no*H0*2 1 0 1 -> 1 0 1(R,m,v=1,1,0)
=>WM: (13835: S1 ^operator O1963)

   982:    O: O1963 (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 N982 +  :O )
Firing apply*operator*complete
 -->
 (I3 ^predict-no N981 -  :O )
 inner elaboration loop at bottom goal.
	--- Change Working Memory (PE) ---
=>WM: (13836: I3 ^predict-yes N982)
<=WM: (13823: N981 ^status complete)
<=WM: (13822: I3 ^predict-no 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-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: (13840: I2 ^dir U)
=>WM: (13839: I2 ^reward 1)
=>WM: (13838: I2 ^see 1)
=>WM: (13837: N982 ^status complete)
<=WM: (13826: I2 ^dir L)
<=WM: (13825: I2 ^reward 1)
<=WM: (13824: I2 ^see 0)
=>WM: (13841: I2 ^level-1 L1-root)
<=WM: (13827: 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
 -->
 (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*2
 -->
 (S1 ^operator O1964 = 1.)
Firing rl*prefer*rvt*predict-yes*H0*1
 -->
 (S1 ^operator O1963 = 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
 -->
 (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*6
 -->
 (S1 ^operator O1964 = 0.9997480945179411)
Retracting rl*prefer*rvt*predict-yes*H0*5
 -->
 (S1 ^operator O1963 = 0.2640281357095451)
Retracting rl*prefer*rvt*predict-yes*H0*5*v1*H1*30
 -->
 (S1 ^operator O1963 = 0.7358289752034343)
=>WM: (13849: S1 ^operator O1966 +)
=>WM: (13848: S1 ^operator O1965 +)
=>WM: (13847: I3 ^dir U)
=>WM: (13846: O1966 ^name predict-no)
=>WM: (13845: O1965 ^name predict-yes)
=>WM: (13844: R986 ^value 1)
=>WM: (13843: R1 ^reward R986)
=>WM: (13842: I3 ^see 1)
<=WM: (13833: S1 ^operator O1963 +)
<=WM: (13835: S1 ^operator O1963)
<=WM: (13834: S1 ^operator O1964 +)
<=WM: (13832: I3 ^dir L)
<=WM: (13828: R1 ^reward R985)
<=WM: (13773: I3 ^see 0)
<=WM: (13831: O1964 ^name predict-no)
<=WM: (13830: O1963 ^name predict-yes)
<=WM: (13829: R985 ^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 O1965 = 0.)
Firing prefer*rvt*predict-no*H0
 -->
Firing rl*prefer*rvt*predict-no*H0*2
 -->
 (S1 ^operator O1966 = 1.)
 inner elaboration loop at bottom goal.
Retracting rl*prefer*rvt*predict-no*H0*2
 -->
 (S1 ^operator O1964 = 1.)
Retracting rl*prefer*rvt*predict-yes*H0*1
 -->
 (S1 ^operator O1963 = 0.)

--- END Proposal Phase ---

--- Decision Phase ---
RL update rl*prefer*rvt*predict-yes*H0*5 0.554414 -0.290386 0.264028 -> 0.554425 -0.290385 0.26404(R,m,v=1,0.875706,0.109463)
RL update rl*prefer*rvt*predict-yes*H0*5*v1*H1*30 0.445446 0.290383 0.735829 -> 0.44546 0.290383 0.735843(R,m,v=1,1,0)
=>WM: (13850: S1 ^operator O1966)

   983:    O: O1966 (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 N983 +  :O )
Firing apply*operator*complete
 -->
 (I3 ^predict-yes N982 -  :O )
 inner elaboration loop at bottom goal.
	--- Change Working Memory (PE) ---
=>WM: (13851: I3 ^predict-no N983)
<=WM: (13837: N982 ^status complete)
<=WM: (13836: I3 ^predict-yes 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-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: (13855: I2 ^dir L)
=>WM: (13854: I2 ^reward 1)
=>WM: (13853: I2 ^see 0)
=>WM: (13852: N983 ^status complete)
<=WM: (13840: I2 ^dir U)
<=WM: (13839: I2 ^reward 1)
<=WM: (13838: I2 ^see 1)
=>WM: (13856: I2 ^level-1 L1-root)
<=WM: (13841: I2 ^level-1 L1-root)

--- END Input Phase --- 

--- Proposal Phase ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing rl*prefer*rvt*predict-yes*H0*5*v1*H1*31
 -->
 (S1 ^operator O1965 = -0.181727099742844)
Firing prefer*rvt*predict-yes*H0*5*v1*H1
 -->
Firing elaborate*copy-see-to-output-link
 -->
 (I3 ^see 0 +)
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 = 0.9997480945179411)
Firing rl*prefer*rvt*predict-yes*H0*5
 -->
 (S1 ^operator O1965 = 0.264039703522277)
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
 -->
 (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 U +)
Retracting rl*prefer*rvt*predict-no*H0*2
 -->
 (S1 ^operator O1966 = 1.)
Retracting rl*prefer*rvt*predict-yes*H0*1
 -->
 (S1 ^operator O1965 = 0.)
=>WM: (13864: S1 ^operator O1968 +)
=>WM: (13863: S1 ^operator O1967 +)
=>WM: (13862: I3 ^dir L)
=>WM: (13861: O1968 ^name predict-no)
=>WM: (13860: O1967 ^name predict-yes)
=>WM: (13859: R987 ^value 1)
=>WM: (13858: R1 ^reward R987)
=>WM: (13857: I3 ^see 0)
<=WM: (13848: S1 ^operator O1965 +)
<=WM: (13849: S1 ^operator O1966 +)
<=WM: (13850: S1 ^operator O1966)
<=WM: (13847: I3 ^dir U)
<=WM: (13843: R1 ^reward R986)
<=WM: (13842: I3 ^see 1)
<=WM: (13846: O1966 ^name predict-no)
<=WM: (13845: O1965 ^name predict-yes)
<=WM: (13844: R986 ^value 1)

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing prefer*rvt*predict-yes*H0
 -->
Firing rl*prefer*rvt*predict-yes*H0*5*v1*H1*31
 -->
 (S1 ^operator O1967 = -0.181727099742844)
Firing rl*prefer*rvt*predict-yes*H0*5
 -->
 (S1 ^operator O1967 = 0.264039703522277)
Firing prefer*rvt*predict-yes*H0*5*v1*H1
 -->
Firing prefer*rvt*predict-no*H0
 -->
Firing rl*prefer*rvt*predict-no*H0*6
 -->
 (S1 ^operator O1968 = 0.9997480945179411)
 inner elaboration loop at bottom goal.
Retracting rl*prefer*rvt*predict-no*H0*6
 -->
 (S1 ^operator O1966 = 0.9997480945179411)
Retracting rl*prefer*rvt*predict-yes*H0*5
 -->
 (S1 ^operator O1965 = 0.264039703522277)
Retracting rl*prefer*rvt*predict-yes*H0*5*v1*H1*31
 -->
 (S1 ^operator O1965 = -0.181727099742844)

--- END Proposal Phase ---

--- Decision Phase ---
RL update rl*prefer*rvt*predict-no*H0*2 1 0 1 -> 1 0 1(R,m,v=1,1,0)
=>WM: (13865: 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-no N983 -  :O )
 inner elaboration loop at bottom goal.
	--- Change Working Memory (PE) ---
=>WM: (13866: I3 ^predict-no N984)
<=WM: (13852: N983 ^status complete)
<=WM: (13851: I3 ^predict-no 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 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: (13870: I2 ^dir U)
=>WM: (13869: I2 ^reward 1)
=>WM: (13868: I2 ^see 0)
=>WM: (13867: N984 ^status complete)
<=WM: (13855: I2 ^dir L)
<=WM: (13854: I2 ^reward 1)
<=WM: (13853: I2 ^see 0)
=>WM: (13871: I2 ^level-1 L0-root)
<=WM: (13856: 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
 -->
 (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*2
 -->
 (S1 ^operator O1968 = 1.)
Firing rl*prefer*rvt*predict-yes*H0*1
 -->
 (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 0 +)
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 L +)
Retracting rl*prefer*rvt*predict-no*H0*6
 -->
 (S1 ^operator O1968 = 0.9997480945179411)
Retracting rl*prefer*rvt*predict-yes*H0*5
 -->
 (S1 ^operator O1967 = 0.264039703522277)
Retracting rl*prefer*rvt*predict-yes*H0*5*v1*H1*31
 -->
 (S1 ^operator O1967 = -0.181727099742844)
=>WM: (13878: S1 ^operator O1970 +)
=>WM: (13877: S1 ^operator O1969 +)
=>WM: (13876: I3 ^dir U)
=>WM: (13875: O1970 ^name predict-no)
=>WM: (13874: O1969 ^name predict-yes)
=>WM: (13873: R988 ^value 1)
=>WM: (13872: R1 ^reward R988)
<=WM: (13863: S1 ^operator O1967 +)
<=WM: (13864: S1 ^operator O1968 +)
<=WM: (13865: S1 ^operator O1968)
<=WM: (13862: I3 ^dir L)
<=WM: (13858: R1 ^reward R987)
<=WM: (13861: O1968 ^name predict-no)
<=WM: (13860: O1967 ^name predict-yes)
<=WM: (13859: R987 ^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 O1969 = 0.)
Firing prefer*rvt*predict-no*H0
 -->
Firing rl*prefer*rvt*predict-no*H0*2
 -->
 (S1 ^operator O1970 = 1.)
 inner elaboration loop at bottom goal.
Retracting rl*prefer*rvt*predict-no*H0*2
 -->
 (S1 ^operator O1968 = 1.)
Retracting rl*prefer*rvt*predict-yes*H0*1
 -->
 (S1 ^operator O1967 = 0.)

--- END Proposal Phase ---

--- Decision Phase ---
RL update rl*prefer*rvt*predict-no*H0*6 0.999748 0 0.999748 -> 0.99979 0 0.99979(R,m,v=1,0.904762,0.086758)
=>WM: (13879: 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: (13880: I3 ^predict-no N985)
<=WM: (13867: N984 ^status complete)
<=WM: (13866: 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-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: (13884: I2 ^dir R)
=>WM: (13883: I2 ^reward 1)
=>WM: (13882: I2 ^see 0)
=>WM: (13881: N985 ^status complete)
<=WM: (13870: I2 ^dir U)
<=WM: (13869: I2 ^reward 1)
<=WM: (13868: I2 ^see 0)
=>WM: (13885: I2 ^level-1 L0-root)
<=WM: (13871: I2 ^level-1 L0-root)

--- END Input Phase --- 

--- Proposal Phase ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing rl*prefer*rvt*predict-no*H0*4*v1*H1*33
 -->
 (S1 ^operator O1970 = -0.2817060109291377)
Firing rl*prefer*rvt*predict-yes*H0*3*v1*H1*34
 -->
 (S1 ^operator O1969 = 0.6623600134734193)
Firing prefer*rvt*predict-no*H0*4*v1*H1
 -->
Firing prefer*rvt*predict-yes*H0*3*v1*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 = 0.3397683711152304)
Firing rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O1969 = 0.3377183053124619)
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*2
 -->
 (S1 ^operator O1970 = 1.)
Retracting rl*prefer*rvt*predict-yes*H0*1
 -->
 (S1 ^operator O1969 = 0.)
=>WM: (13892: S1 ^operator O1972 +)
=>WM: (13891: S1 ^operator O1971 +)
=>WM: (13890: I3 ^dir R)
=>WM: (13889: O1972 ^name predict-no)
=>WM: (13888: O1971 ^name predict-yes)
=>WM: (13887: R989 ^value 1)
=>WM: (13886: R1 ^reward R989)
<=WM: (13877: S1 ^operator O1969 +)
<=WM: (13878: S1 ^operator O1970 +)
<=WM: (13879: S1 ^operator O1970)
<=WM: (13876: I3 ^dir U)
<=WM: (13872: R1 ^reward R988)
<=WM: (13875: O1970 ^name predict-no)
<=WM: (13874: O1969 ^name predict-yes)
<=WM: (13873: R988 ^value 1)

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing prefer*rvt*predict-yes*H0
 -->
Firing rl*prefer*rvt*predict-yes*H0*3*v1*H1*34
 -->
 (S1 ^operator O1971 = 0.6623600134734193)
Firing rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O1971 = 0.3377183053124619)
Firing prefer*rvt*predict-yes*H0*3*v1*H1
 -->
Firing prefer*rvt*predict-no*H0
 -->
Firing rl*prefer*rvt*predict-no*H0*4*v1*H1*33
 -->
 (S1 ^operator O1972 = -0.2817060109291377)
Firing rl*prefer*rvt*predict-no*H0*4
 -->
 (S1 ^operator O1972 = 0.3397683711152304)
Firing prefer*rvt*predict-no*H0*4*v1*H1
 -->
 inner elaboration loop at bottom goal.
Retracting rl*prefer*rvt*predict-no*H0*4
 -->
 (S1 ^operator O1970 = 0.3397683711152304)
Retracting rl*prefer*rvt*predict-no*H0*4*v1*H1*33
 -->
 (S1 ^operator O1970 = -0.2817060109291377)
Retracting rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O1969 = 0.3377183053124619)
Retracting rl*prefer*rvt*predict-yes*H0*3*v1*H1*34
 -->
 (S1 ^operator O1969 = 0.6623600134734193)

--- END Proposal Phase ---

--- Decision Phase ---
RL update rl*prefer*rvt*predict-no*H0*2 1 0 1 -> 1 0 1(R,m,v=1,1,0)
=>WM: (13893: S1 ^operator O1971)

   986:    O: O1971 (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 N986 +  :O )
Firing apply*operator*complete
 -->
 (I3 ^predict-no N985 -  :O )
 inner elaboration loop at bottom goal.
	--- Change Working Memory (PE) ---
=>WM: (13894: I3 ^predict-yes N986)
<=WM: (13881: N985 ^status complete)
<=WM: (13880: 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-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: (13898: I2 ^dir U)
=>WM: (13897: I2 ^reward 1)
=>WM: (13896: I2 ^see 1)
=>WM: (13895: N986 ^status complete)
<=WM: (13884: I2 ^dir R)
<=WM: (13883: I2 ^reward 1)
<=WM: (13882: I2 ^see 0)
=>WM: (13899: I2 ^level-1 R1-root)
<=WM: (13885: 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
 -->
 (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*2
 -->
 (S1 ^operator O1972 = 1.)
Firing rl*prefer*rvt*predict-yes*H0*1
 -->
 (S1 ^operator O1971 = 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
 -->
 (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 = 0.3397683711152304)
Retracting rl*prefer*rvt*predict-no*H0*4*v1*H1*33
 -->
 (S1 ^operator O1972 = -0.2817060109291377)
Retracting rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O1971 = 0.3377183053124619)
Retracting rl*prefer*rvt*predict-yes*H0*3*v1*H1*34
 -->
 (S1 ^operator O1971 = 0.6623600134734193)
=>WM: (13907: S1 ^operator O1974 +)
=>WM: (13906: S1 ^operator O1973 +)
=>WM: (13905: I3 ^dir U)
=>WM: (13904: O1974 ^name predict-no)
=>WM: (13903: O1973 ^name predict-yes)
=>WM: (13902: R990 ^value 1)
=>WM: (13901: R1 ^reward R990)
=>WM: (13900: I3 ^see 1)
<=WM: (13891: S1 ^operator O1971 +)
<=WM: (13893: S1 ^operator O1971)
<=WM: (13892: S1 ^operator O1972 +)
<=WM: (13890: I3 ^dir R)
<=WM: (13886: R1 ^reward R989)
<=WM: (13857: I3 ^see 0)
<=WM: (13889: O1972 ^name predict-no)
<=WM: (13888: O1971 ^name predict-yes)
<=WM: (13887: R989 ^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 O1973 = 0.)
Firing prefer*rvt*predict-no*H0
 -->
Firing rl*prefer*rvt*predict-no*H0*2
 -->
 (S1 ^operator O1974 = 1.)
 inner elaboration loop at bottom goal.
Retracting rl*prefer*rvt*predict-no*H0*2
 -->
 (S1 ^operator O1972 = 1.)
Retracting rl*prefer*rvt*predict-yes*H0*1
 -->
 (S1 ^operator O1971 = 0.)

--- END Proposal Phase ---

--- Decision Phase ---
RL update rl*prefer*rvt*predict-yes*H0*3 0.59012 -0.252401 0.337718 -> 0.590112 -0.2524 0.337712(R,m,v=1,0.89759,0.092479)
RL update rl*prefer*rvt*predict-yes*H0*3*v1*H1*34 0.409971 0.252389 0.66236 -> 0.409962 0.25239 0.662353(R,m,v=1,1,0)
=>WM: (13908: 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-yes N986 -  :O )
 inner elaboration loop at bottom goal.
	--- Change Working Memory (PE) ---
=>WM: (13909: I3 ^predict-no N987)
<=WM: (13895: N986 ^status complete)
<=WM: (13894: I3 ^predict-yes 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 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: (13913: I2 ^dir R)
=>WM: (13912: I2 ^reward 1)
=>WM: (13911: I2 ^see 0)
=>WM: (13910: N987 ^status complete)
<=WM: (13898: I2 ^dir U)
<=WM: (13897: I2 ^reward 1)
<=WM: (13896: I2 ^see 1)
=>WM: (13914: I2 ^level-1 R1-root)
<=WM: (13899: 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*v1*H1*36
 -->
 (S1 ^operator O1973 = -0.1070236389116304)
Firing rl*prefer*rvt*predict-no*H0*4*v1*H1*35
 -->
 (S1 ^operator O1974 = 0.6602453025755203)
Firing prefer*rvt*predict-no*H0*4*v1*H1
 -->
Firing prefer*rvt*predict-yes*H0*3*v1*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 = 0.3397683711152304)
Firing rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O1973 = 0.3377118983309207)
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
 -->
 (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 U +)
Retracting rl*prefer*rvt*predict-no*H0*2
 -->
 (S1 ^operator O1974 = 1.)
Retracting rl*prefer*rvt*predict-yes*H0*1
 -->
 (S1 ^operator O1973 = 0.)
=>WM: (13922: S1 ^operator O1976 +)
=>WM: (13921: S1 ^operator O1975 +)
=>WM: (13920: I3 ^dir R)
=>WM: (13919: O1976 ^name predict-no)
=>WM: (13918: O1975 ^name predict-yes)
=>WM: (13917: R991 ^value 1)
=>WM: (13916: R1 ^reward R991)
=>WM: (13915: I3 ^see 0)
<=WM: (13906: S1 ^operator O1973 +)
<=WM: (13907: S1 ^operator O1974 +)
<=WM: (13908: S1 ^operator O1974)
<=WM: (13905: I3 ^dir U)
<=WM: (13901: R1 ^reward R990)
<=WM: (13900: I3 ^see 1)
<=WM: (13904: O1974 ^name predict-no)
<=WM: (13903: O1973 ^name predict-yes)
<=WM: (13902: R990 ^value 1)

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing prefer*rvt*predict-yes*H0
 -->
Firing rl*prefer*rvt*predict-yes*H0*3*v1*H1*36
 -->
 (S1 ^operator O1975 = -0.1070236389116304)
Firing rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O1975 = 0.3377118983309207)
Firing prefer*rvt*predict-yes*H0*3*v1*H1
 -->
Firing prefer*rvt*predict-no*H0
 -->
Firing rl*prefer*rvt*predict-no*H0*4*v1*H1*35
 -->
 (S1 ^operator O1976 = 0.6602453025755203)
Firing rl*prefer*rvt*predict-no*H0*4
 -->
 (S1 ^operator O1976 = 0.3397683711152304)
Firing prefer*rvt*predict-no*H0*4*v1*H1
 -->
 inner elaboration loop at bottom goal.
Retracting rl*prefer*rvt*predict-no*H0*4
 -->
 (S1 ^operator O1974 = 0.3397683711152304)
Retracting rl*prefer*rvt*predict-no*H0*4*v1*H1*35
 -->
 (S1 ^operator O1974 = 0.6602453025755203)
Retracting rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O1973 = 0.3377118983309207)
Retracting rl*prefer*rvt*predict-yes*H0*3*v1*H1*36
 -->
 (S1 ^operator O1973 = -0.1070236389116304)

--- END Proposal Phase ---

--- Decision Phase ---
RL update rl*prefer*rvt*predict-no*H0*2 1 0 1 -> 1 0 1(R,m,v=1,1,0)
=>WM: (13923: 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: (13924: I3 ^predict-no N988)
<=WM: (13910: N987 ^status complete)
<=WM: (13909: 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: (13928: I2 ^dir R)
=>WM: (13927: I2 ^reward 1)
=>WM: (13926: I2 ^see 0)
=>WM: (13925: N988 ^status complete)
<=WM: (13913: I2 ^dir R)
<=WM: (13912: I2 ^reward 1)
<=WM: (13911: I2 ^see 0)
=>WM: (13929: I2 ^level-1 R0-root)
<=WM: (13914: I2 ^level-1 R1-root)

--- END Input Phase --- 

--- Proposal Phase ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing rl*prefer*rvt*predict-no*H0*4*v1*H1*39
 -->
 (S1 ^operator O1976 = 0.660152441867348)
Firing rl*prefer*rvt*predict-yes*H0*3*v1*H1*40
 -->
 (S1 ^operator O1975 = -0.1028953566115423)
Firing prefer*rvt*predict-no*H0*4*v1*H1
 -->
Firing prefer*rvt*predict-yes*H0*3*v1*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 = 0.3397683711152304)
Firing rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O1975 = 0.3377118983309207)
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
 -->
 (S1 ^operator O1976 = 0.3397683711152304)
Retracting rl*prefer*rvt*predict-no*H0*4*v1*H1*35
 -->
 (S1 ^operator O1976 = 0.6602453025755203)
Retracting rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O1975 = 0.3377118983309207)
Retracting rl*prefer*rvt*predict-yes*H0*3*v1*H1*36
 -->
 (S1 ^operator O1975 = -0.1070236389116304)
=>WM: (13935: S1 ^operator O1978 +)
=>WM: (13934: S1 ^operator O1977 +)
=>WM: (13933: O1978 ^name predict-no)
=>WM: (13932: O1977 ^name predict-yes)
=>WM: (13931: R992 ^value 1)
=>WM: (13930: R1 ^reward R992)
<=WM: (13921: S1 ^operator O1975 +)
<=WM: (13922: S1 ^operator O1976 +)
<=WM: (13923: S1 ^operator O1976)
<=WM: (13916: R1 ^reward R991)
<=WM: (13919: O1976 ^name predict-no)
<=WM: (13918: O1975 ^name predict-yes)
<=WM: (13917: 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 = 0.3377118983309207)
Firing prefer*rvt*predict-yes*H0*3*v1*H1
 -->
Firing rl*prefer*rvt*predict-yes*H0*3*v1*H1*40
 -->
 (S1 ^operator O1977 = -0.1028953566115423)
Firing prefer*rvt*predict-no*H0
 -->
Firing rl*prefer*rvt*predict-no*H0*4
 -->
 (S1 ^operator O1978 = 0.3397683711152304)
Firing prefer*rvt*predict-no*H0*4*v1*H1
 -->
Firing rl*prefer*rvt*predict-no*H0*4*v1*H1*39
 -->
 (S1 ^operator O1978 = 0.660152441867348)
 inner elaboration loop at bottom goal.
Retracting rl*prefer*rvt*predict-no*H0*4
 -->
 (S1 ^operator O1976 = 0.3397683711152304)
Retracting rl*prefer*rvt*predict-no*H0*4*v1*H1*39
 -->
 (S1 ^operator O1976 = 0.660152441867348)
Retracting rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O1975 = 0.3377118983309207)
Retracting rl*prefer*rvt*predict-yes*H0*3*v1*H1*40
 -->
 (S1 ^operator O1975 = -0.1028953566115423)

--- END Proposal Phase ---

--- Decision Phase ---
RL update rl*prefer*rvt*predict-no*H0*4 0.570252 -0.230483 0.339768 -> 0.570251 -0.230483 0.339767(R,m,v=1,0.874251,0.110598)
RL update rl*prefer*rvt*predict-no*H0*4*v1*H1*35 0.429763 0.230483 0.660245 -> 0.429761 0.230483 0.660244(R,m,v=1,1,0)
=>WM: (13936: 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: (13937: I3 ^predict-no N989)
<=WM: (13925: N988 ^status complete)
<=WM: (13924: 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 isL
--- END Output Phase ---
-/|--- Input Phase --- 
=>WM: (13941: I2 ^dir L)
=>WM: (13940: I2 ^reward 1)
=>WM: (13939: I2 ^see 0)
=>WM: (13938: N989 ^status complete)
<=WM: (13928: I2 ^dir R)
<=WM: (13927: I2 ^reward 1)
<=WM: (13926: I2 ^see 0)
=>WM: (13942: I2 ^level-1 R0-root)
<=WM: (13929: I2 ^level-1 R0-root)

--- END Input Phase --- 

--- Proposal Phase ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing rl*prefer*rvt*predict-yes*H0*5*v1*H1*30
 -->
 (S1 ^operator O1977 = 0.7358428664482317)
Firing prefer*rvt*predict-yes*H0*5*v1*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*6
 -->
 (S1 ^operator O1978 = 0.999790145818646)
Firing rl*prefer*rvt*predict-yes*H0*5
 -->
 (S1 ^operator O1977 = 0.264039703522277)
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
 -->
 (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*v1*H1*39
 -->
 (S1 ^operator O1978 = 0.660152441867348)
Retracting rl*prefer*rvt*predict-no*H0*4
 -->
 (S1 ^operator O1978 = 0.339767253617308)
Retracting rl*prefer*rvt*predict-yes*H0*3*v1*H1*40
 -->
 (S1 ^operator O1977 = -0.1028953566115423)
Retracting rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O1977 = 0.3377118983309207)
=>WM: (13949: S1 ^operator O1980 +)
=>WM: (13948: S1 ^operator O1979 +)
=>WM: (13947: I3 ^dir L)
=>WM: (13946: O1980 ^name predict-no)
=>WM: (13945: O1979 ^name predict-yes)
=>WM: (13944: R993 ^value 1)
=>WM: (13943: R1 ^reward R993)
<=WM: (13934: S1 ^operator O1977 +)
<=WM: (13935: S1 ^operator O1978 +)
<=WM: (13936: S1 ^operator O1978)
<=WM: (13920: I3 ^dir R)
<=WM: (13930: R1 ^reward R992)
<=WM: (13933: O1978 ^name predict-no)
<=WM: (13932: O1977 ^name predict-yes)
<=WM: (13931: R992 ^value 1)

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing prefer*rvt*predict-yes*H0
 -->
Firing rl*prefer*rvt*predict-yes*H0*5*v1*H1*30
 -->
 (S1 ^operator O1979 = 0.7358428664482317)
Firing rl*prefer*rvt*predict-yes*H0*5
 -->
 (S1 ^operator O1979 = 0.264039703522277)
Firing prefer*rvt*predict-yes*H0*5*v1*H1
 -->
Firing prefer*rvt*predict-no*H0
 -->
Firing rl*prefer*rvt*predict-no*H0*6
 -->
 (S1 ^operator O1980 = 0.999790145818646)
 inner elaboration loop at bottom goal.
Retracting rl*prefer*rvt*predict-no*H0*6
 -->
 (S1 ^operator O1978 = 0.999790145818646)
Retracting rl*prefer*rvt*predict-yes*H0*5
 -->
 (S1 ^operator O1977 = 0.264039703522277)
Retracting rl*prefer*rvt*predict-yes*H0*5*v1*H1*30
 -->
 (S1 ^operator O1977 = 0.7358428664482317)

--- END Proposal Phase ---

--- Decision Phase ---
RL update rl*prefer*rvt*predict-no*H0*4 0.570251 -0.230483 0.339767 -> 0.570257 -0.230484 0.339774(R,m,v=1,0.875,0.11003)
RL update rl*prefer*rvt*predict-no*H0*4*v1*H1*39 0.429665 0.230487 0.660152 -> 0.429673 0.230487 0.66016(R,m,v=1,1,0)
=>WM: (13950: S1 ^operator O1979)

   990:    O: O1979 (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 N990 +  :O )
Firing apply*operator*complete
 -->
 (I3 ^predict-no N989 -  :O )
 inner elaboration loop at bottom goal.
	--- Change Working Memory (PE) ---
=>WM: (13951: I3 ^predict-yes N990)
<=WM: (13938: N989 ^status complete)
<=WM: (13937: 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-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: (13955: I2 ^dir U)
=>WM: (13954: I2 ^reward 1)
=>WM: (13953: I2 ^see 1)
=>WM: (13952: N990 ^status complete)
<=WM: (13941: I2 ^dir L)
<=WM: (13940: I2 ^reward 1)
<=WM: (13939: I2 ^see 0)
=>WM: (13956: I2 ^level-1 L1-root)
<=WM: (13942: 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
 -->
 (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*2
 -->
 (S1 ^operator O1980 = 1.)
Firing rl*prefer*rvt*predict-yes*H0*1
 -->
 (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 L +)
Retracting rl*prefer*rvt*predict-no*H0*6
 -->
 (S1 ^operator O1980 = 0.999790145818646)
Retracting rl*prefer*rvt*predict-yes*H0*5
 -->
 (S1 ^operator O1979 = 0.264039703522277)
Retracting rl*prefer*rvt*predict-yes*H0*5*v1*H1*30
 -->
 (S1 ^operator O1979 = 0.7358428664482317)
=>WM: (13964: S1 ^operator O1982 +)
=>WM: (13963: S1 ^operator O1981 +)
=>WM: (13962: I3 ^dir U)
=>WM: (13961: O1982 ^name predict-no)
=>WM: (13960: O1981 ^name predict-yes)
=>WM: (13959: R994 ^value 1)
=>WM: (13958: R1 ^reward R994)
=>WM: (13957: I3 ^see 1)
<=WM: (13948: S1 ^operator O1979 +)
<=WM: (13950: S1 ^operator O1979)
<=WM: (13949: S1 ^operator O1980 +)
<=WM: (13947: I3 ^dir L)
<=WM: (13943: R1 ^reward R993)
<=WM: (13915: I3 ^see 0)
<=WM: (13946: O1980 ^name predict-no)
<=WM: (13945: O1979 ^name predict-yes)
<=WM: (13944: R993 ^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 O1981 = 0.)
Firing prefer*rvt*predict-no*H0
 -->
Firing rl*prefer*rvt*predict-no*H0*2
 -->
 (S1 ^operator O1982 = 1.)
 inner elaboration loop at bottom goal.
Retracting rl*prefer*rvt*predict-no*H0*2
 -->
 (S1 ^operator O1980 = 1.)
Retracting rl*prefer*rvt*predict-yes*H0*1
 -->
 (S1 ^operator O1979 = 0.)

--- END Proposal Phase ---

--- Decision Phase ---
RL update rl*prefer*rvt*predict-yes*H0*5 0.554425 -0.290385 0.26404 -> 0.554434 -0.290385 0.264049(R,m,v=1,0.876404,0.108932)
RL update rl*prefer*rvt*predict-yes*H0*5*v1*H1*30 0.44546 0.290383 0.735843 -> 0.445471 0.290384 0.735854(R,m,v=1,1,0)
=>WM: (13965: 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-yes N990 -  :O )
 inner elaboration loop at bottom goal.
	--- Change Working Memory (PE) ---
=>WM: (13966: I3 ^predict-no N991)
<=WM: (13952: N990 ^status complete)
<=WM: (13951: I3 ^predict-yes 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-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: (13970: I2 ^dir R)
=>WM: (13969: I2 ^reward 1)
=>WM: (13968: I2 ^see 0)
=>WM: (13967: N991 ^status complete)
<=WM: (13955: I2 ^dir U)
<=WM: (13954: I2 ^reward 1)
<=WM: (13953: I2 ^see 1)
=>WM: (13971: I2 ^level-1 L1-root)
<=WM: (13956: I2 ^level-1 L1-root)

--- END Input Phase --- 

--- Proposal Phase ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing rl*prefer*rvt*predict-no*H0*4*v1*H1*37
 -->
 (S1 ^operator O1982 = -0.2714224023553999)
Firing rl*prefer*rvt*predict-yes*H0*3*v1*H1*38
 -->
 (S1 ^operator O1981 = 0.662219375073587)
Firing prefer*rvt*predict-no*H0*4*v1*H1
 -->
Firing prefer*rvt*predict-yes*H0*3*v1*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*4
 -->
 (S1 ^operator O1982 = 0.339773810196969)
Firing rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O1981 = 0.3377118983309207)
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
 -->
 (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*2
 -->
 (S1 ^operator O1982 = 1.)
Retracting rl*prefer*rvt*predict-yes*H0*1
 -->
 (S1 ^operator O1981 = 0.)
=>WM: (13979: S1 ^operator O1984 +)
=>WM: (13978: S1 ^operator O1983 +)
=>WM: (13977: I3 ^dir R)
=>WM: (13976: O1984 ^name predict-no)
=>WM: (13975: O1983 ^name predict-yes)
=>WM: (13974: R995 ^value 1)
=>WM: (13973: R1 ^reward R995)
=>WM: (13972: I3 ^see 0)
<=WM: (13963: S1 ^operator O1981 +)
<=WM: (13964: S1 ^operator O1982 +)
<=WM: (13965: S1 ^operator O1982)
<=WM: (13962: I3 ^dir U)
<=WM: (13958: R1 ^reward R994)
<=WM: (13957: I3 ^see 1)
<=WM: (13961: O1982 ^name predict-no)
<=WM: (13960: O1981 ^name predict-yes)
<=WM: (13959: R994 ^value 1)

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing prefer*rvt*predict-yes*H0
 -->
Firing rl*prefer*rvt*predict-yes*H0*3*v1*H1*38
 -->
 (S1 ^operator O1983 = 0.662219375073587)
Firing rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O1983 = 0.3377118983309207)
Firing prefer*rvt*predict-yes*H0*3*v1*H1
 -->
Firing prefer*rvt*predict-no*H0
 -->
Firing rl*prefer*rvt*predict-no*H0*4*v1*H1*37
 -->
 (S1 ^operator O1984 = -0.2714224023553999)
Firing rl*prefer*rvt*predict-no*H0*4
 -->
 (S1 ^operator O1984 = 0.339773810196969)
Firing prefer*rvt*predict-no*H0*4*v1*H1
 -->
 inner elaboration loop at bottom goal.
Retracting rl*prefer*rvt*predict-no*H0*4
 -->
 (S1 ^operator O1982 = 0.339773810196969)
Retracting rl*prefer*rvt*predict-no*H0*4*v1*H1*37
 -->
 (S1 ^operator O1982 = -0.2714224023553999)
Retracting rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O1981 = 0.3377118983309207)
Retracting rl*prefer*rvt*predict-yes*H0*3*v1*H1*38
 -->
 (S1 ^operator O1981 = 0.662219375073587)

--- END Proposal Phase ---

--- Decision Phase ---
RL update rl*prefer*rvt*predict-no*H0*2 1 0 1 -> 1 0 1(R,m,v=1,1,0)
=>WM: (13980: 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: (13981: I3 ^predict-yes N992)
<=WM: (13967: N991 ^status complete)
<=WM: (13966: 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 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: (13985: I2 ^dir U)
=>WM: (13984: I2 ^reward 1)
=>WM: (13983: I2 ^see 1)
=>WM: (13982: N992 ^status complete)
<=WM: (13970: I2 ^dir R)
<=WM: (13969: I2 ^reward 1)
<=WM: (13968: I2 ^see 0)
=>WM: (13986: I2 ^level-1 R1-root)
<=WM: (13971: 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
 -->
 (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*2
 -->
 (S1 ^operator O1984 = 1.)
Firing rl*prefer*rvt*predict-yes*H0*1
 -->
 (S1 ^operator O1983 = 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
 -->
 (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 R +)
Retracting rl*prefer*rvt*predict-no*H0*4
 -->
 (S1 ^operator O1984 = 0.339773810196969)
Retracting rl*prefer*rvt*predict-no*H0*4*v1*H1*37
 -->
 (S1 ^operator O1984 = -0.2714224023553999)
Retracting rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O1983 = 0.3377118983309207)
Retracting rl*prefer*rvt*predict-yes*H0*3*v1*H1*38
 -->
 (S1 ^operator O1983 = 0.662219375073587)
=>WM: (13994: S1 ^operator O1986 +)
=>WM: (13993: S1 ^operator O1985 +)
=>WM: (13992: I3 ^dir U)
=>WM: (13991: O1986 ^name predict-no)
=>WM: (13990: O1985 ^name predict-yes)
=>WM: (13989: R996 ^value 1)
=>WM: (13988: R1 ^reward R996)
=>WM: (13987: I3 ^see 1)
<=WM: (13978: S1 ^operator O1983 +)
<=WM: (13980: S1 ^operator O1983)
<=WM: (13979: S1 ^operator O1984 +)
<=WM: (13977: I3 ^dir R)
<=WM: (13973: R1 ^reward R995)
<=WM: (13972: I3 ^see 0)
<=WM: (13976: O1984 ^name predict-no)
<=WM: (13975: O1983 ^name predict-yes)
<=WM: (13974: R995 ^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 O1985 = 0.)
Firing prefer*rvt*predict-no*H0
 -->
Firing rl*prefer*rvt*predict-no*H0*2
 -->
 (S1 ^operator O1986 = 1.)
 inner elaboration loop at bottom goal.
Retracting rl*prefer*rvt*predict-no*H0*2
 -->
 (S1 ^operator O1984 = 1.)
Retracting rl*prefer*rvt*predict-yes*H0*1
 -->
 (S1 ^operator O1983 = 0.)

--- END Proposal Phase ---

--- Decision Phase ---
RL update rl*prefer*rvt*predict-yes*H0*3 0.590112 -0.2524 0.337712 -> 0.590119 -0.252401 0.337718(R,m,v=1,0.898204,0.0919847)
RL update rl*prefer*rvt*predict-yes*H0*3*v1*H1*38 0.409809 0.252411 0.662219 -> 0.409816 0.25241 0.662226(R,m,v=1,1,0)
=>WM: (13995: S1 ^operator O1986)

   993:    O: O1986 (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 N993 +  :O )
Firing apply*operator*complete
 -->
 (I3 ^predict-yes N992 -  :O )
 inner elaboration loop at bottom goal.
	--- Change Working Memory (PE) ---
=>WM: (13996: I3 ^predict-no N993)
<=WM: (13982: N992 ^status complete)
<=WM: (13981: 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-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: (14000: I2 ^dir L)
=>WM: (13999: I2 ^reward 1)
=>WM: (13998: I2 ^see 0)
=>WM: (13997: N993 ^status complete)
<=WM: (13985: I2 ^dir U)
<=WM: (13984: I2 ^reward 1)
<=WM: (13983: I2 ^see 1)
=>WM: (14001: I2 ^level-1 R1-root)
<=WM: (13986: I2 ^level-1 R1-root)

--- END Input Phase --- 

--- Proposal Phase ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing rl*prefer*rvt*predict-yes*H0*5*v1*H1*41
 -->
 (S1 ^operator O1985 = 0.7362544663116062)
Firing prefer*rvt*predict-yes*H0*5*v1*H1
 -->
Firing elaborate*copy-see-to-output-link
 -->
 (I3 ^see 0 +)
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 = 0.999790145818646)
Firing rl*prefer*rvt*predict-yes*H0*5
 -->
 (S1 ^operator O1985 = 0.2640492015925779)
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
 -->
 (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 U +)
Retracting rl*prefer*rvt*predict-no*H0*2
 -->
 (S1 ^operator O1986 = 1.)
Retracting rl*prefer*rvt*predict-yes*H0*1
 -->
 (S1 ^operator O1985 = 0.)
=>WM: (14009: S1 ^operator O1988 +)
=>WM: (14008: S1 ^operator O1987 +)
=>WM: (14007: I3 ^dir L)
=>WM: (14006: O1988 ^name predict-no)
=>WM: (14005: O1987 ^name predict-yes)
=>WM: (14004: R997 ^value 1)
=>WM: (14003: R1 ^reward R997)
=>WM: (14002: I3 ^see 0)
<=WM: (13993: S1 ^operator O1985 +)
<=WM: (13994: S1 ^operator O1986 +)
<=WM: (13995: S1 ^operator O1986)
<=WM: (13992: I3 ^dir U)
<=WM: (13988: R1 ^reward R996)
<=WM: (13987: I3 ^see 1)
<=WM: (13991: O1986 ^name predict-no)
<=WM: (13990: O1985 ^name predict-yes)
<=WM: (13989: R996 ^value 1)

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing prefer*rvt*predict-yes*H0
 -->
Firing rl*prefer*rvt*predict-yes*H0*5*v1*H1*41
 -->
 (S1 ^operator O1987 = 0.7362544663116062)
Firing rl*prefer*rvt*predict-yes*H0*5
 -->
 (S1 ^operator O1987 = 0.2640492015925779)
Firing prefer*rvt*predict-yes*H0*5*v1*H1
 -->
Firing prefer*rvt*predict-no*H0
 -->
Firing rl*prefer*rvt*predict-no*H0*6
 -->
 (S1 ^operator O1988 = 0.999790145818646)
 inner elaboration loop at bottom goal.
Retracting rl*prefer*rvt*predict-no*H0*6
 -->
 (S1 ^operator O1986 = 0.999790145818646)
Retracting rl*prefer*rvt*predict-yes*H0*5
 -->
 (S1 ^operator O1985 = 0.2640492015925779)
Retracting rl*prefer*rvt*predict-yes*H0*5*v1*H1*41
 -->
 (S1 ^operator O1985 = 0.7362544663116062)

--- END Proposal Phase ---

--- Decision Phase ---
RL update rl*prefer*rvt*predict-no*H0*2 1 0 1 -> 1 0 1(R,m,v=1,1,0)
=>WM: (14010: S1 ^operator O1987)

   994:    O: O1987 (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 N994 +  :O )
Firing apply*operator*complete
 -->
 (I3 ^predict-no N993 -  :O )
 inner elaboration loop at bottom goal.
	--- Change Working Memory (PE) ---
=>WM: (14011: I3 ^predict-yes N994)
<=WM: (13997: N993 ^status complete)
<=WM: (13996: I3 ^predict-no 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-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: (14015: I2 ^dir L)
=>WM: (14014: I2 ^reward 1)
=>WM: (14013: I2 ^see 1)
=>WM: (14012: N994 ^status complete)
<=WM: (14000: I2 ^dir L)
<=WM: (13999: I2 ^reward 1)
<=WM: (13998: I2 ^see 0)
=>WM: (14016: I2 ^level-1 L1-root)
<=WM: (14001: I2 ^level-1 R1-root)

--- END Input Phase --- 

--- Proposal Phase ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing rl*prefer*rvt*predict-yes*H0*5*v1*H1*31
 -->
 (S1 ^operator O1987 = -0.181727099742844)
Firing prefer*rvt*predict-yes*H0*5*v1*H1
 -->
Firing elaborate*copy-see-to-output-link
 -->
 (I3 ^see 1 +)
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 = 0.999790145818646)
Firing rl*prefer*rvt*predict-yes*H0*5
 -->
 (S1 ^operator O1987 = 0.2640492015925779)
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
 -->
 (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 L +)
Retracting rl*prefer*rvt*predict-no*H0*6
 -->
 (S1 ^operator O1988 = 0.999790145818646)
Retracting rl*prefer*rvt*predict-yes*H0*5
 -->
 (S1 ^operator O1987 = 0.2640492015925779)
Retracting rl*prefer*rvt*predict-yes*H0*5*v1*H1*41
 -->
 (S1 ^operator O1987 = 0.7362544663116062)
=>WM: (14023: S1 ^operator O1990 +)
=>WM: (14022: S1 ^operator O1989 +)
=>WM: (14021: O1990 ^name predict-no)
=>WM: (14020: O1989 ^name predict-yes)
=>WM: (14019: R998 ^value 1)
=>WM: (14018: R1 ^reward R998)
=>WM: (14017: I3 ^see 1)
<=WM: (14008: S1 ^operator O1987 +)
<=WM: (14010: S1 ^operator O1987)
<=WM: (14009: S1 ^operator O1988 +)
<=WM: (14003: R1 ^reward R997)
<=WM: (14002: I3 ^see 0)
<=WM: (14006: O1988 ^name predict-no)
<=WM: (14005: O1987 ^name predict-yes)
<=WM: (14004: 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 = 0.2640492015925779)
Firing prefer*rvt*predict-yes*H0*5*v1*H1
 -->
Firing rl*prefer*rvt*predict-yes*H0*5*v1*H1*31
 -->
 (S1 ^operator O1989 = -0.181727099742844)
Firing prefer*rvt*predict-no*H0
 -->
Firing rl*prefer*rvt*predict-no*H0*6
 -->
 (S1 ^operator O1990 = 0.999790145818646)
 inner elaboration loop at bottom goal.
Retracting rl*prefer*rvt*predict-no*H0*6
 -->
 (S1 ^operator O1988 = 0.999790145818646)
Retracting rl*prefer*rvt*predict-yes*H0*5
 -->
 (S1 ^operator O1987 = 0.2640492015925779)
Retracting rl*prefer*rvt*predict-yes*H0*5*v1*H1*31
 -->
 (S1 ^operator O1987 = -0.181727099742844)

--- END Proposal Phase ---

--- Decision Phase ---
RL update rl*prefer*rvt*predict-yes*H0*5 0.554434 -0.290385 0.264049 -> 0.55441 -0.290386 0.264025(R,m,v=1,0.877095,0.108405)
RL update rl*prefer*rvt*predict-yes*H0*5*v1*H1*41 0.445864 0.29039 0.736254 -> 0.445836 0.29039 0.736226(R,m,v=1,1,0)
=>WM: (14024: 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-yes N994 -  :O )
 inner elaboration loop at bottom goal.
	--- Change Working Memory (PE) ---
=>WM: (14025: I3 ^predict-no N995)
<=WM: (14012: N994 ^status complete)
<=WM: (14011: I3 ^predict-yes 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 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: (14029: I2 ^dir L)
=>WM: (14028: I2 ^reward 1)
=>WM: (14027: I2 ^see 0)
=>WM: (14026: N995 ^status complete)
<=WM: (14015: I2 ^dir L)
<=WM: (14014: I2 ^reward 1)
<=WM: (14013: I2 ^see 1)
=>WM: (14030: I2 ^level-1 L0-root)
<=WM: (14016: I2 ^level-1 L1-root)

--- END Input Phase --- 

--- Proposal Phase ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing rl*prefer*rvt*predict-yes*H0*5*v1*H1*32
 -->
 (S1 ^operator O1989 = -0.1386470047172653)
Firing prefer*rvt*predict-yes*H0*5*v1*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*6
 -->
 (S1 ^operator O1990 = 0.999790145818646)
Firing rl*prefer*rvt*predict-yes*H0*5
 -->
 (S1 ^operator O1989 = 0.2640246623191502)
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
 -->
 (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 L +)
Retracting rl*prefer*rvt*predict-no*H0*6
 -->
 (S1 ^operator O1990 = 0.999790145818646)
Retracting rl*prefer*rvt*predict-yes*H0*5*v1*H1*31
 -->
 (S1 ^operator O1989 = -0.181727099742844)
Retracting rl*prefer*rvt*predict-yes*H0*5
 -->
 (S1 ^operator O1989 = 0.2640246623191502)
=>WM: (14037: S1 ^operator O1992 +)
=>WM: (14036: S1 ^operator O1991 +)
=>WM: (14035: O1992 ^name predict-no)
=>WM: (14034: O1991 ^name predict-yes)
=>WM: (14033: R999 ^value 1)
=>WM: (14032: R1 ^reward R999)
=>WM: (14031: I3 ^see 0)
<=WM: (14022: S1 ^operator O1989 +)
<=WM: (14023: S1 ^operator O1990 +)
<=WM: (14024: S1 ^operator O1990)
<=WM: (14018: R1 ^reward R998)
<=WM: (14017: I3 ^see 1)
<=WM: (14021: O1990 ^name predict-no)
<=WM: (14020: O1989 ^name predict-yes)
<=WM: (14019: R998 ^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 O1991 = 0.2640246623191502)
Firing prefer*rvt*predict-yes*H0*5*v1*H1
 -->
Firing rl*prefer*rvt*predict-yes*H0*5*v1*H1*32
 -->
 (S1 ^operator O1991 = -0.1386470047172653)
Firing prefer*rvt*predict-no*H0
 -->
Firing rl*prefer*rvt*predict-no*H0*6
 -->
 (S1 ^operator O1992 = 0.999790145818646)
 inner elaboration loop at bottom goal.
Retracting rl*prefer*rvt*predict-no*H0*6
 -->
 (S1 ^operator O1990 = 0.999790145818646)
Retracting rl*prefer*rvt*predict-yes*H0*5
 -->
 (S1 ^operator O1989 = 0.2640246623191502)
Retracting rl*prefer*rvt*predict-yes*H0*5*v1*H1*32
 -->
 (S1 ^operator O1989 = -0.1386470047172653)

--- END Proposal Phase ---

--- Decision Phase ---
RL update rl*prefer*rvt*predict-no*H0*6 0.99979 0 0.99979 -> 0.999825 0 0.999825(R,m,v=1,0.905405,0.0862291)
=>WM: (14038: S1 ^operator O1992)

   996:    O: O1992 (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 N996 +  :O )
Firing apply*operator*complete
 -->
 (I3 ^predict-no N995 -  :O )
 inner elaboration loop at bottom goal.
	--- Change Working Memory (PE) ---
=>WM: (14039: I3 ^predict-no N996)
<=WM: (14026: N995 ^status complete)
<=WM: (14025: 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-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: (14043: I2 ^dir L)
=>WM: (14042: I2 ^reward 1)
=>WM: (14041: I2 ^see 0)
=>WM: (14040: N996 ^status complete)
<=WM: (14029: I2 ^dir L)
<=WM: (14028: I2 ^reward 1)
<=WM: (14027: I2 ^see 0)
=>WM: (14044: I2 ^level-1 L0-root)
<=WM: (14030: I2 ^level-1 L0-root)

--- END Input Phase --- 

--- Proposal Phase ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing rl*prefer*rvt*predict-yes*H0*5*v1*H1*32
 -->
 (S1 ^operator O1991 = -0.1386470047172653)
Firing prefer*rvt*predict-yes*H0*5*v1*H1
 -->
Firing elaborate*copy-see-to-output-link
 -->
 (I3 ^see 0 +)
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 = 0.9998251377735368)
Firing rl*prefer*rvt*predict-yes*H0*5
 -->
 (S1 ^operator O1991 = 0.2640246623191502)
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
 -->
 (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*6
 -->
 (S1 ^operator O1992 = 0.9998251377735368)
Retracting rl*prefer*rvt*predict-yes*H0*5*v1*H1*32
 -->
 (S1 ^operator O1991 = -0.1386470047172653)
Retracting rl*prefer*rvt*predict-yes*H0*5
 -->
 (S1 ^operator O1991 = 0.2640246623191502)
=>WM: (14050: S1 ^operator O1994 +)
=>WM: (14049: S1 ^operator O1993 +)
=>WM: (14048: O1994 ^name predict-no)
=>WM: (14047: O1993 ^name predict-yes)
=>WM: (14046: R1000 ^value 1)
=>WM: (14045: R1 ^reward R1000)
<=WM: (14036: S1 ^operator O1991 +)
<=WM: (14037: S1 ^operator O1992 +)
<=WM: (14038: S1 ^operator O1992)
<=WM: (14032: R1 ^reward R999)
<=WM: (14035: O1992 ^name predict-no)
<=WM: (14034: O1991 ^name predict-yes)
<=WM: (14033: 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 = 0.2640246623191502)
Firing prefer*rvt*predict-yes*H0*5*v1*H1
 -->
Firing rl*prefer*rvt*predict-yes*H0*5*v1*H1*32
 -->
 (S1 ^operator O1993 = -0.1386470047172653)
Firing prefer*rvt*predict-no*H0
 -->
Firing rl*prefer*rvt*predict-no*H0*6
 -->
 (S1 ^operator O1994 = 0.9998251377735368)
 inner elaboration loop at bottom goal.
Retracting rl*prefer*rvt*predict-no*H0*6
 -->
 (S1 ^operator O1992 = 0.9998251377735368)
Retracting rl*prefer*rvt*predict-yes*H0*5
 -->
 (S1 ^operator O1991 = 0.2640246623191502)
Retracting rl*prefer*rvt*predict-yes*H0*5*v1*H1*32
 -->
 (S1 ^operator O1991 = -0.1386470047172653)

--- END Proposal Phase ---

--- Decision Phase ---
RL update rl*prefer*rvt*predict-no*H0*6 0.999825 0 0.999825 -> 0.999854 0 0.999854(R,m,v=1,0.90604,0.0857065)
=>WM: (14051: 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-no N996 -  :O )
 inner elaboration loop at bottom goal.
	--- Change Working Memory (PE) ---
=>WM: (14052: I3 ^predict-no N997)
<=WM: (14040: N996 ^status complete)
<=WM: (14039: I3 ^predict-no 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 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: (14056: I2 ^dir U)
=>WM: (14055: I2 ^reward 1)
=>WM: (14054: I2 ^see 0)
=>WM: (14053: N997 ^status complete)
<=WM: (14043: I2 ^dir L)
<=WM: (14042: I2 ^reward 1)
<=WM: (14041: I2 ^see 0)
=>WM: (14057: I2 ^level-1 L0-root)
<=WM: (14044: 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
 -->
 (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*2
 -->
 (S1 ^operator O1994 = 1.)
Firing rl*prefer*rvt*predict-yes*H0*1
 -->
 (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 0 +)
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 L +)
Retracting rl*prefer*rvt*predict-no*H0*6
 -->
 (S1 ^operator O1994 = 0.9998542623222174)
Retracting rl*prefer*rvt*predict-yes*H0*5*v1*H1*32
 -->
 (S1 ^operator O1993 = -0.1386470047172653)
Retracting rl*prefer*rvt*predict-yes*H0*5
 -->
 (S1 ^operator O1993 = 0.2640246623191502)
=>WM: (14064: S1 ^operator O1996 +)
=>WM: (14063: S1 ^operator O1995 +)
=>WM: (14062: I3 ^dir U)
=>WM: (14061: O1996 ^name predict-no)
=>WM: (14060: O1995 ^name predict-yes)
=>WM: (14059: R1001 ^value 1)
=>WM: (14058: R1 ^reward R1001)
<=WM: (14049: S1 ^operator O1993 +)
<=WM: (14050: S1 ^operator O1994 +)
<=WM: (14051: S1 ^operator O1994)
<=WM: (14007: I3 ^dir L)
<=WM: (14045: R1 ^reward R1000)
<=WM: (14048: O1994 ^name predict-no)
<=WM: (14047: O1993 ^name predict-yes)
<=WM: (14046: R1000 ^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 O1995 = 0.)
Firing prefer*rvt*predict-no*H0
 -->
Firing rl*prefer*rvt*predict-no*H0*2
 -->
 (S1 ^operator O1996 = 1.)
 inner elaboration loop at bottom goal.
Retracting rl*prefer*rvt*predict-no*H0*2
 -->
 (S1 ^operator O1994 = 1.)
Retracting rl*prefer*rvt*predict-yes*H0*1
 -->
 (S1 ^operator O1993 = 0.)

--- END Proposal Phase ---

--- Decision Phase ---
RL update rl*prefer*rvt*predict-no*H0*6 0.999854 0 0.999854 -> 0.999879 0 0.999879(R,m,v=1,0.906667,0.0851902)
=>WM: (14065: 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: (14066: I3 ^predict-no N998)
<=WM: (14053: N997 ^status complete)
<=WM: (14052: 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 isU
--- END Output Phase ---
/|--- Input Phase --- 
=>WM: (14070: I2 ^dir U)
=>WM: (14069: I2 ^reward 1)
=>WM: (14068: I2 ^see 0)
=>WM: (14067: N998 ^status complete)
<=WM: (14056: I2 ^dir U)
<=WM: (14055: I2 ^reward 1)
<=WM: (14054: I2 ^see 0)
=>WM: (14071: I2 ^level-1 L0-root)
<=WM: (14057: 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
 -->
 (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 = 1.)
Firing rl*prefer*rvt*predict-yes*H0*1
 -->
 (S1 ^operator O1995 = 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
 -->
 (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*2
 -->
 (S1 ^operator O1996 = 1.)
Retracting rl*prefer*rvt*predict-yes*H0*1
 -->
 (S1 ^operator O1995 = 0.)
=>WM: (14077: S1 ^operator O1998 +)
=>WM: (14076: S1 ^operator O1997 +)
=>WM: (14075: O1998 ^name predict-no)
=>WM: (14074: O1997 ^name predict-yes)
=>WM: (14073: R1002 ^value 1)
=>WM: (14072: R1 ^reward R1002)
<=WM: (14063: S1 ^operator O1995 +)
<=WM: (14064: S1 ^operator O1996 +)
<=WM: (14065: S1 ^operator O1996)
<=WM: (14058: R1 ^reward R1001)
<=WM: (14061: O1996 ^name predict-no)
<=WM: (14060: O1995 ^name predict-yes)
<=WM: (14059: R1001 ^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 O1997 = 0.)
Firing prefer*rvt*predict-no*H0
 -->
Firing rl*prefer*rvt*predict-no*H0*2
 -->
 (S1 ^operator O1998 = 1.)
 inner elaboration loop at bottom goal.
Retracting rl*prefer*rvt*predict-no*H0*2
 -->
 (S1 ^operator O1996 = 1.)
Retracting rl*prefer*rvt*predict-yes*H0*1
 -->
 (S1 ^operator O1995 = 0.)

--- END Proposal Phase ---

--- Decision Phase ---
RL update rl*prefer*rvt*predict-no*H0*2 1 0 1 -> 1 0 1(R,m,v=1,1,0)
=>WM: (14078: 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: (14079: I3 ^predict-no N999)
<=WM: (14067: N998 ^status complete)
<=WM: (14066: 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 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: (14083: I2 ^dir R)
=>WM: (14082: I2 ^reward 1)
=>WM: (14081: I2 ^see 0)
=>WM: (14080: N999 ^status complete)
<=WM: (14070: I2 ^dir U)
<=WM: (14069: I2 ^reward 1)
<=WM: (14068: I2 ^see 0)
=>WM: (14084: I2 ^level-1 L0-root)
<=WM: (14071: I2 ^level-1 L0-root)

--- END Input Phase --- 

--- Proposal Phase ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing rl*prefer*rvt*predict-no*H0*4*v1*H1*33
 -->
 (S1 ^operator O1998 = -0.2817060109291377)
Firing rl*prefer*rvt*predict-yes*H0*3*v1*H1*34
 -->
 (S1 ^operator O1997 = 0.6623525109664488)
Firing prefer*rvt*predict-no*H0*4*v1*H1
 -->
Firing prefer*rvt*predict-yes*H0*3*v1*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*4
 -->
 (S1 ^operator O1998 = 0.339773810196969)
Firing rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O1997 = 0.337717515090074)
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
 -->
 (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 U +)
Retracting rl*prefer*rvt*predict-no*H0*2
 -->
 (S1 ^operator O1998 = 1.)
Retracting rl*prefer*rvt*predict-yes*H0*1
 -->
 (S1 ^operator O1997 = 0.)
=>WM: (14091: S1 ^operator O2000 +)
=>WM: (14090: S1 ^operator O1999 +)
=>WM: (14089: I3 ^dir R)
=>WM: (14088: O2000 ^name predict-no)
=>WM: (14087: O1999 ^name predict-yes)
=>WM: (14086: R1003 ^value 1)
=>WM: (14085: R1 ^reward R1003)
<=WM: (14076: S1 ^operator O1997 +)
<=WM: (14077: S1 ^operator O1998 +)
<=WM: (14078: S1 ^operator O1998)
<=WM: (14062: I3 ^dir U)
<=WM: (14072: R1 ^reward R1002)
<=WM: (14075: O1998 ^name predict-no)
<=WM: (14074: O1997 ^name predict-yes)
<=WM: (14073: R1002 ^value 1)

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing prefer*rvt*predict-yes*H0
 -->
Firing rl*prefer*rvt*predict-yes*H0*3*v1*H1*34
 -->
 (S1 ^operator O1999 = 0.6623525109664488)
Firing rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O1999 = 0.337717515090074)
Firing prefer*rvt*predict-yes*H0*3*v1*H1
 -->
Firing prefer*rvt*predict-no*H0
 -->
Firing rl*prefer*rvt*predict-no*H0*4*v1*H1*33
 -->
 (S1 ^operator O2000 = -0.2817060109291377)
Firing rl*prefer*rvt*predict-no*H0*4
 -->
 (S1 ^operator O2000 = 0.339773810196969)
Firing prefer*rvt*predict-no*H0*4*v1*H1
 -->
 inner elaboration loop at bottom goal.
Retracting rl*prefer*rvt*predict-no*H0*4
 -->
 (S1 ^operator O1998 = 0.339773810196969)
Retracting rl*prefer*rvt*predict-no*H0*4*v1*H1*33
 -->
 (S1 ^operator O1998 = -0.2817060109291377)
Retracting rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O1997 = 0.337717515090074)
Retracting rl*prefer*rvt*predict-yes*H0*3*v1*H1*34
 -->
 (S1 ^operator O1997 = 0.6623525109664488)

--- END Proposal Phase ---

--- Decision Phase ---
RL update rl*prefer*rvt*predict-no*H0*2 1 0 1 -> 1 0 1(R,m,v=1,1,0)
=>WM: (14092: S1 ^operator O1999)

  1000:    O: O1999 (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 N1000 +  :O )
Firing apply*operator*complete
 -->
 (I3 ^predict-no N999 -  :O )
 inner elaboration loop at bottom goal.
	--- Change Working Memory (PE) ---
=>WM: (14093: I3 ^predict-yes N1000)
<=WM: (14080: N999 ^status complete)
<=WM: (14079: 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-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: (14097: I2 ^dir U)
=>WM: (14096: I2 ^reward 1)
=>WM: (14095: I2 ^see 1)
=>WM: (14094: N1000 ^status complete)
<=WM: (14083: I2 ^dir R)
<=WM: (14082: I2 ^reward 1)
<=WM: (14081: I2 ^see 0)
=>WM: (14098: I2 ^level-1 R1-root)
<=WM: (14084: 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
 -->
 (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 = 1.)
Firing rl*prefer*rvt*predict-yes*H0*1
 -->
 (S1 ^operator O1999 = 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
 -->
 (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 R +)
Retracting rl*prefer*rvt*predict-no*H0*4
 -->
 (S1 ^operator O2000 = 0.339773810196969)
Retracting rl*prefer*rvt*predict-no*H0*4*v1*H1*33
 -->
 (S1 ^operator O2000 = -0.2817060109291377)
Retracting rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O1999 = 0.337717515090074)
Retracting rl*prefer*rvt*predict-yes*H0*3*v1*H1*34
 -->
 (S1 ^operator O1999 = 0.6623525109664488)
=>WM: (14106: S1 ^operator O2002 +)
=>WM: (14105: S1 ^operator O2001 +)
=>WM: (14104: I3 ^dir U)
=>WM: (14103: O2002 ^name predict-no)
=>WM: (14102: O2001 ^name predict-yes)
=>WM: (14101: R1004 ^value 1)
=>WM: (14100: R1 ^reward R1004)
=>WM: (14099: I3 ^see 1)
<=WM: (14090: S1 ^operator O1999 +)
<=WM: (14092: S1 ^operator O1999)
<=WM: (14091: S1 ^operator O2000 +)
<=WM: (14089: I3 ^dir R)
<=WM: (14085: R1 ^reward R1003)
<=WM: (14031: I3 ^see 0)
<=WM: (14088: O2000 ^name predict-no)
<=WM: (14087: O1999 ^name predict-yes)
<=WM: (14086: 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.)
Firing prefer*rvt*predict-no*H0
 -->
Firing rl*prefer*rvt*predict-no*H0*2
 -->
 (S1 ^operator O2002 = 1.)
 inner elaboration loop at bottom goal.
Retracting rl*prefer*rvt*predict-no*H0*2
 -->
 (S1 ^operator O2000 = 1.)
Retracting rl*prefer*rvt*predict-yes*H0*1
 -->
 (S1 ^operator O1999 = 0.)

--- END Proposal Phase ---

--- Decision Phase ---
RL update rl*prefer*rvt*predict-yes*H0*3 0.590119 -0.252401 0.337718 -> 0.590112 -0.2524 0.337712(R,m,v=1,0.89881,0.0914956)
RL update rl*prefer*rvt*predict-yes*H0*3*v1*H1*34 0.409962 0.25239 0.662353 -> 0.409954 0.252391 0.662346(R,m,v=1,1,0)
=>WM: (14107: 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-yes N1000 -  :O )
 inner elaboration loop at bottom goal.
	--- Change Working Memory (PE) ---
=>WM: (14108: I3 ^predict-no N1001)
<=WM: (14094: N1000 ^status complete)
<=WM: (14093: I3 ^predict-yes 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 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: (14112: I2 ^dir U)
=>WM: (14111: I2 ^reward 1)
=>WM: (14110: I2 ^see 0)
=>WM: (14109: N1001 ^status complete)
<=WM: (14097: I2 ^dir U)
<=WM: (14096: I2 ^reward 1)
<=WM: (14095: I2 ^see 1)
=>WM: (14113: I2 ^level-1 R1-root)
<=WM: (14098: 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
 -->
 (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 = 1.)
Firing rl*prefer*rvt*predict-yes*H0*1
 -->
 (S1 ^operator O2001 = 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
 -->
 (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 U +)
Retracting rl*prefer*rvt*predict-no*H0*2
 -->
 (S1 ^operator O2002 = 1.)
Retracting rl*prefer*rvt*predict-yes*H0*1
 -->
 (S1 ^operator O2001 = 0.)
=>WM: (14120: S1 ^operator O2004 +)
=>WM: (14119: S1 ^operator O2003 +)
=>WM: (14118: O2004 ^name predict-no)
=>WM: (14117: O2003 ^name predict-yes)
=>WM: (14116: R1005 ^value 1)
=>WM: (14115: R1 ^reward R1005)
=>WM: (14114: I3 ^see 0)
<=WM: (14105: S1 ^operator O2001 +)
<=WM: (14106: S1 ^operator O2002 +)
<=WM: (14107: S1 ^operator O2002)
<=WM: (14100: R1 ^reward R1004)
<=WM: (14099: I3 ^see 1)
<=WM: (14103: O2002 ^name predict-no)
<=WM: (14102: O2001 ^name predict-yes)
<=WM: (14101: 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.)
Firing prefer*rvt*predict-no*H0
 -->
Firing rl*prefer*rvt*predict-no*H0*2
 -->
 (S1 ^operator O2004 = 1.)
 inner elaboration loop at bottom goal.
Retracting rl*prefer*rvt*predict-no*H0*2
 -->
 (S1 ^operator O2002 = 1.)
Retracting rl*prefer*rvt*predict-yes*H0*1
 -->
 (S1 ^operator O2001 = 0.)

--- END Proposal Phase ---

--- Decision Phase ---
RL update rl*prefer*rvt*predict-no*H0*2 1 0 1 -> 1 0 1(R,m,v=1,1,0)
=>WM: (14121: 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: (14122: I3 ^predict-no N1002)
<=WM: (14109: N1001 ^status complete)
<=WM: (14108: 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 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: (14126: I2 ^dir U)
=>WM: (14125: I2 ^reward 1)
=>WM: (14124: I2 ^see 0)
=>WM: (14123: N1002 ^status complete)
<=WM: (14112: I2 ^dir U)
<=WM: (14111: I2 ^reward 1)
<=WM: (14110: I2 ^see 0)
=>WM: (14127: I2 ^level-1 R1-root)
<=WM: (14113: 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
 -->
 (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*2
 -->
 (S1 ^operator O2004 = 1.)
Firing rl*prefer*rvt*predict-yes*H0*1
 -->
 (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 U +)
Retracting rl*prefer*rvt*predict-no*H0*2
 -->
 (S1 ^operator O2004 = 1.)
Retracting rl*prefer*rvt*predict-yes*H0*1
 -->
 (S1 ^operator O2003 = 0.)
=>WM: (14133: S1 ^operator O2006 +)
=>WM: (14132: S1 ^operator O2005 +)
=>WM: (14131: O2006 ^name predict-no)
=>WM: (14130: O2005 ^name predict-yes)
=>WM: (14129: R1006 ^value 1)
=>WM: (14128: R1 ^reward R1006)
<=WM: (14119: S1 ^operator O2003 +)
<=WM: (14120: S1 ^operator O2004 +)
<=WM: (14121: S1 ^operator O2004)
<=WM: (14115: R1 ^reward R1005)
<=WM: (14118: O2004 ^name predict-no)
<=WM: (14117: O2003 ^name predict-yes)
<=WM: (14116: R1005 ^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 O2005 = 0.)
Firing prefer*rvt*predict-no*H0
 -->
Firing rl*prefer*rvt*predict-no*H0*2
 -->
 (S1 ^operator O2006 = 1.)
 inner elaboration loop at bottom goal.
Retracting rl*prefer*rvt*predict-no*H0*2
 -->
 (S1 ^operator O2004 = 1.)
Retracting rl*prefer*rvt*predict-yes*H0*1
 -->
 (S1 ^operator O2003 = 0.)

--- END Proposal Phase ---

--- Decision Phase ---
RL update rl*prefer*rvt*predict-no*H0*2 1 0 1 -> 1 0 1(R,m,v=1,1,0)
=>WM: (14134: 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: (14135: I3 ^predict-no N1003)
<=WM: (14123: N1002 ^status complete)
<=WM: (14122: 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-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: (14139: I2 ^dir U)
=>WM: (14138: I2 ^reward 1)
=>WM: (14137: I2 ^see 0)
=>WM: (14136: N1003 ^status complete)
<=WM: (14126: I2 ^dir U)
<=WM: (14125: I2 ^reward 1)
<=WM: (14124: I2 ^see 0)
=>WM: (14140: I2 ^level-1 R1-root)
<=WM: (14127: 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
 -->
 (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*2
 -->
 (S1 ^operator O2006 = 1.)
Firing rl*prefer*rvt*predict-yes*H0*1
 -->
 (S1 ^operator O2005 = 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
 -->
 (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*2
 -->
 (S1 ^operator O2006 = 1.)
Retracting rl*prefer*rvt*predict-yes*H0*1
 -->
 (S1 ^operator O2005 = 0.)
=>WM: (14146: S1 ^operator O2008 +)
=>WM: (14145: S1 ^operator O2007 +)
=>WM: (14144: O2008 ^name predict-no)
=>WM: (14143: O2007 ^name predict-yes)
=>WM: (14142: R1007 ^value 1)
=>WM: (14141: R1 ^reward R1007)
<=WM: (14132: S1 ^operator O2005 +)
<=WM: (14133: S1 ^operator O2006 +)
<=WM: (14134: S1 ^operator O2006)
<=WM: (14128: R1 ^reward R1006)
<=WM: (14131: O2006 ^name predict-no)
<=WM: (14130: O2005 ^name predict-yes)
<=WM: (14129: R1006 ^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 O2007 = 0.)
Firing prefer*rvt*predict-no*H0
 -->
Firing rl*prefer*rvt*predict-no*H0*2
 -->
 (S1 ^operator O2008 = 1.)
 inner elaboration loop at bottom goal.
Retracting rl*prefer*rvt*predict-no*H0*2
 -->
 (S1 ^operator O2006 = 1.)
Retracting rl*prefer*rvt*predict-yes*H0*1
 -->
 (S1 ^operator O2005 = 0.)

--- END Proposal Phase ---

--- Decision Phase ---
RL update rl*prefer*rvt*predict-no*H0*2 1 0 1 -> 1 0 1(R,m,v=1,1,0)
=>WM: (14147: S1 ^operator O2008)

  1004:    O: O2008 (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 N1004 +  :O )
Firing apply*operator*complete
 -->
 (I3 ^predict-no N1003 -  :O )
 inner elaboration loop at bottom goal.
	--- Change Working Memory (PE) ---
=>WM: (14148: I3 ^predict-no N1004)
<=WM: (14136: N1003 ^status complete)
<=WM: (14135: 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-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: (14152: I2 ^dir L)
=>WM: (14151: I2 ^reward 1)
=>WM: (14150: I2 ^see 0)
=>WM: (14149: N1004 ^status complete)
<=WM: (14139: I2 ^dir U)
<=WM: (14138: I2 ^reward 1)
<=WM: (14137: I2 ^see 0)
=>WM: (14153: I2 ^level-1 R1-root)
<=WM: (14140: I2 ^level-1 R1-root)

--- END Input Phase --- 

--- Proposal Phase ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing rl*prefer*rvt*predict-yes*H0*5*v1*H1*41
 -->
 (S1 ^operator O2007 = 0.7362263199804909)
Firing prefer*rvt*predict-yes*H0*5*v1*H1
 -->
Firing elaborate*copy-see-to-output-link
 -->
 (I3 ^see 0 +)
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 = 0.9998785089568328)
Firing rl*prefer*rvt*predict-yes*H0*5
 -->
 (S1 ^operator O2007 = 0.2640246623191502)
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
 -->
 (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 U +)
Retracting rl*prefer*rvt*predict-no*H0*2
 -->
 (S1 ^operator O2008 = 1.)
Retracting rl*prefer*rvt*predict-yes*H0*1
 -->
 (S1 ^operator O2007 = 0.)
=>WM: (14160: S1 ^operator O2010 +)
=>WM: (14159: S1 ^operator O2009 +)
=>WM: (14158: I3 ^dir L)
=>WM: (14157: O2010 ^name predict-no)
=>WM: (14156: O2009 ^name predict-yes)
=>WM: (14155: R1008 ^value 1)
=>WM: (14154: R1 ^reward R1008)
<=WM: (14145: S1 ^operator O2007 +)
<=WM: (14146: S1 ^operator O2008 +)
<=WM: (14147: S1 ^operator O2008)
<=WM: (14104: I3 ^dir U)
<=WM: (14141: R1 ^reward R1007)
<=WM: (14144: O2008 ^name predict-no)
<=WM: (14143: O2007 ^name predict-yes)
<=WM: (14142: R1007 ^value 1)

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing prefer*rvt*predict-yes*H0
 -->
Firing rl*prefer*rvt*predict-yes*H0*5*v1*H1*41
 -->
 (S1 ^operator O2009 = 0.7362263199804909)
Firing rl*prefer*rvt*predict-yes*H0*5
 -->
 (S1 ^operator O2009 = 0.2640246623191502)
Firing prefer*rvt*predict-yes*H0*5*v1*H1
 -->
Firing prefer*rvt*predict-no*H0
 -->
Firing rl*prefer*rvt*predict-no*H0*6
 -->
 (S1 ^operator O2010 = 0.9998785089568328)
 inner elaboration loop at bottom goal.
Retracting rl*prefer*rvt*predict-no*H0*6
 -->
 (S1 ^operator O2008 = 0.9998785089568328)
Retracting rl*prefer*rvt*predict-yes*H0*5
 -->
 (S1 ^operator O2007 = 0.2640246623191502)
Retracting rl*prefer*rvt*predict-yes*H0*5*v1*H1*41
 -->
 (S1 ^operator O2007 = 0.7362263199804909)

--- END Proposal Phase ---

--- Decision Phase ---
RL update rl*prefer*rvt*predict-no*H0*2 1 0 1 -> 1 0 1(R,m,v=1,1,0)
=>WM: (14161: S1 ^operator O2009)

  1005:    O: O2009 (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 N1005 +  :O )
Firing apply*operator*complete
 -->
 (I3 ^predict-no N1004 -  :O )
 inner elaboration loop at bottom goal.
	--- Change Working Memory (PE) ---
=>WM: (14162: I3 ^predict-yes N1005)
<=WM: (14149: N1004 ^status complete)
<=WM: (14148: I3 ^predict-no 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-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: (14166: I2 ^dir R)
=>WM: (14165: I2 ^reward 1)
=>WM: (14164: I2 ^see 1)
=>WM: (14163: N1005 ^status complete)
<=WM: (14152: I2 ^dir L)
<=WM: (14151: I2 ^reward 1)
<=WM: (14150: I2 ^see 0)
=>WM: (14167: I2 ^level-1 L1-root)
<=WM: (14153: I2 ^level-1 R1-root)

--- END Input Phase --- 

--- Proposal Phase ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing rl*prefer*rvt*predict-no*H0*4*v1*H1*37
 -->
 (S1 ^operator O2010 = -0.2714224023553999)
Firing rl*prefer*rvt*predict-yes*H0*3*v1*H1*38
 -->
 (S1 ^operator O2009 = 0.6622259046932006)
Firing prefer*rvt*predict-no*H0*4*v1*H1
 -->
Firing prefer*rvt*predict-yes*H0*3*v1*H1
 -->
Firing elaborate*copy-see-to-output-link
 -->
 (I3 ^see 1 +)
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*4
 -->
 (S1 ^operator O2010 = 0.339773810196969)
Firing rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O2009 = 0.3377117977102235)
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
 -->
 (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 L +)
Retracting rl*prefer*rvt*predict-no*H0*6
 -->
 (S1 ^operator O2010 = 0.9998785089568328)
Retracting rl*prefer*rvt*predict-yes*H0*5
 -->
 (S1 ^operator O2009 = 0.2640246623191502)
Retracting rl*prefer*rvt*predict-yes*H0*5*v1*H1*41
 -->
 (S1 ^operator O2009 = 0.7362263199804909)
=>WM: (14175: S1 ^operator O2012 +)
=>WM: (14174: S1 ^operator O2011 +)
=>WM: (14173: I3 ^dir R)
=>WM: (14172: O2012 ^name predict-no)
=>WM: (14171: O2011 ^name predict-yes)
=>WM: (14170: R1009 ^value 1)
=>WM: (14169: R1 ^reward R1009)
=>WM: (14168: I3 ^see 1)
<=WM: (14159: S1 ^operator O2009 +)
<=WM: (14161: S1 ^operator O2009)
<=WM: (14160: S1 ^operator O2010 +)
<=WM: (14158: I3 ^dir L)
<=WM: (14154: R1 ^reward R1008)
<=WM: (14114: I3 ^see 0)
<=WM: (14157: O2010 ^name predict-no)
<=WM: (14156: O2009 ^name predict-yes)
<=WM: (14155: R1008 ^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 O2011 = 0.3377117977102235)
Firing prefer*rvt*predict-yes*H0*3*v1*H1
 -->
Firing rl*prefer*rvt*predict-yes*H0*3*v1*H1*38
 -->
 (S1 ^operator O2011 = 0.6622259046932006)
Firing prefer*rvt*predict-no*H0
 -->
Firing rl*prefer*rvt*predict-no*H0*4
 -->
 (S1 ^operator O2012 = 0.339773810196969)
Firing prefer*rvt*predict-no*H0*4*v1*H1
 -->
Firing rl*prefer*rvt*predict-no*H0*4*v1*H1*37
 -->
 (S1 ^operator O2012 = -0.2714224023553999)
 inner elaboration loop at bottom goal.
Retracting rl*prefer*rvt*predict-no*H0*4
 -->
 (S1 ^operator O2010 = 0.339773810196969)
Retracting rl*prefer*rvt*predict-no*H0*4*v1*H1*37
 -->
 (S1 ^operator O2010 = -0.2714224023553999)
Retracting rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O2009 = 0.3377117977102235)
Retracting rl*prefer*rvt*predict-yes*H0*3*v1*H1*38
 -->
 (S1 ^operator O2009 = 0.6622259046932006)

--- END Proposal Phase ---

--- Decision Phase ---
RL update rl*prefer*rvt*predict-yes*H0*5 0.55441 -0.290386 0.264025 -> 0.55439 -0.290386 0.264004(R,m,v=1,0.877778,0.107883)
RL update rl*prefer*rvt*predict-yes*H0*5*v1*H1*41 0.445836 0.29039 0.736226 -> 0.445814 0.290389 0.736203(R,m,v=1,1,0)
=>WM: (14176: 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-yes N1005 -  :O )
 inner elaboration loop at bottom goal.
	--- Change Working Memory (PE) ---
=>WM: (14177: I3 ^predict-yes N1006)
<=WM: (14163: N1005 ^status complete)
<=WM: (14162: I3 ^predict-yes 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 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: (14181: I2 ^dir R)
=>WM: (14180: I2 ^reward 1)
=>WM: (14179: I2 ^see 1)
=>WM: (14178: N1006 ^status complete)
<=WM: (14166: I2 ^dir R)
<=WM: (14165: I2 ^reward 1)
<=WM: (14164: I2 ^see 1)
=>WM: (14182: I2 ^level-1 R1-root)
<=WM: (14167: 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*v1*H1*36
 -->
 (S1 ^operator O2011 = -0.1070236389116304)
Firing rl*prefer*rvt*predict-no*H0*4*v1*H1*35
 -->
 (S1 ^operator O2012 = 0.6602439963649246)
Firing prefer*rvt*predict-no*H0*4*v1*H1
 -->
Firing prefer*rvt*predict-yes*H0*3*v1*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*4
 -->
 (S1 ^operator O2012 = 0.339773810196969)
Firing rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O2011 = 0.3377117977102235)
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
 -->
 (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 R +)
Retracting rl*prefer*rvt*predict-no*H0*4*v1*H1*37
 -->
 (S1 ^operator O2012 = -0.2714224023553999)
Retracting rl*prefer*rvt*predict-no*H0*4
 -->
 (S1 ^operator O2012 = 0.339773810196969)
Retracting rl*prefer*rvt*predict-yes*H0*3*v1*H1*38
 -->
 (S1 ^operator O2011 = 0.6622259046932006)
Retracting rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O2011 = 0.3377117977102235)
=>WM: (14188: S1 ^operator O2014 +)
=>WM: (14187: S1 ^operator O2013 +)
=>WM: (14186: O2014 ^name predict-no)
=>WM: (14185: O2013 ^name predict-yes)
=>WM: (14184: R1010 ^value 1)
=>WM: (14183: R1 ^reward R1010)
<=WM: (14174: S1 ^operator O2011 +)
<=WM: (14176: S1 ^operator O2011)
<=WM: (14175: S1 ^operator O2012 +)
<=WM: (14169: R1 ^reward R1009)
<=WM: (14172: O2012 ^name predict-no)
<=WM: (14171: O2011 ^name predict-yes)
<=WM: (14170: R1009 ^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 O2013 = 0.3377117977102235)
Firing prefer*rvt*predict-yes*H0*3*v1*H1
 -->
Firing rl*prefer*rvt*predict-yes*H0*3*v1*H1*36
 -->
 (S1 ^operator O2013 = -0.1070236389116304)
Firing prefer*rvt*predict-no*H0
 -->
Firing rl*prefer*rvt*predict-no*H0*4
 -->
 (S1 ^operator O2014 = 0.339773810196969)
Firing prefer*rvt*predict-no*H0*4*v1*H1
 -->
Firing rl*prefer*rvt*predict-no*H0*4*v1*H1*35
 -->
 (S1 ^operator O2014 = 0.6602439963649246)
 inner elaboration loop at bottom goal.
Retracting rl*prefer*rvt*predict-no*H0*4
 -->
 (S1 ^operator O2012 = 0.339773810196969)
Retracting rl*prefer*rvt*predict-no*H0*4*v1*H1*35
 -->
 (S1 ^operator O2012 = 0.6602439963649246)
Retracting rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O2011 = 0.3377117977102235)
Retracting rl*prefer*rvt*predict-yes*H0*3*v1*H1*36
 -->
 (S1 ^operator O2011 = -0.1070236389116304)

--- END Proposal Phase ---

--- Decision Phase ---
RL update rl*prefer*rvt*predict-yes*H0*3 0.590112 -0.2524 0.337712 -> 0.590118 -0.252401 0.337717(R,m,v=1,0.899408,0.0910116)
RL update rl*prefer*rvt*predict-yes*H0*3*v1*H1*38 0.409816 0.25241 0.662226 -> 0.409823 0.252409 0.662232(R,m,v=1,1,0)
=>WM: (14189: 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: (14190: I3 ^predict-no N1007)
<=WM: (14178: N1006 ^status complete)
<=WM: (14177: 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 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: (14194: I2 ^dir U)
=>WM: (14193: I2 ^reward 1)
=>WM: (14192: I2 ^see 0)
=>WM: (14191: N1007 ^status complete)
<=WM: (14181: I2 ^dir R)
<=WM: (14180: I2 ^reward 1)
<=WM: (14179: I2 ^see 1)
=>WM: (14195: I2 ^level-1 R0-root)
<=WM: (14182: 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
 -->
 (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*2
 -->
 (S1 ^operator O2014 = 1.)
Firing rl*prefer*rvt*predict-yes*H0*1
 -->
 (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 R +)
Retracting rl*prefer*rvt*predict-no*H0*4*v1*H1*35
 -->
 (S1 ^operator O2014 = 0.6602439963649246)
Retracting rl*prefer*rvt*predict-no*H0*4
 -->
 (S1 ^operator O2014 = 0.339773810196969)
Retracting rl*prefer*rvt*predict-yes*H0*3*v1*H1*36
 -->
 (S1 ^operator O2013 = -0.1070236389116304)
Retracting rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O2013 = 0.3377168791642142)
=>WM: (14203: S1 ^operator O2016 +)
=>WM: (14202: S1 ^operator O2015 +)
=>WM: (14201: I3 ^dir U)
=>WM: (14200: O2016 ^name predict-no)
=>WM: (14199: O2015 ^name predict-yes)
=>WM: (14198: R1011 ^value 1)
=>WM: (14197: R1 ^reward R1011)
=>WM: (14196: I3 ^see 0)
<=WM: (14187: S1 ^operator O2013 +)
<=WM: (14188: S1 ^operator O2014 +)
<=WM: (14189: S1 ^operator O2014)
<=WM: (14173: I3 ^dir R)
<=WM: (14183: R1 ^reward R1010)
<=WM: (14168: I3 ^see 1)
<=WM: (14186: O2014 ^name predict-no)
<=WM: (14185: O2013 ^name predict-yes)
<=WM: (14184: R1010 ^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 O2015 = 0.)
Firing prefer*rvt*predict-no*H0
 -->
Firing rl*prefer*rvt*predict-no*H0*2
 -->
 (S1 ^operator O2016 = 1.)
 inner elaboration loop at bottom goal.
Retracting rl*prefer*rvt*predict-no*H0*2
 -->
 (S1 ^operator O2014 = 1.)
Retracting rl*prefer*rvt*predict-yes*H0*1
 -->
 (S1 ^operator O2013 = 0.)

--- END Proposal Phase ---

--- Decision Phase ---
RL update rl*prefer*rvt*predict-no*H0*4 0.570257 -0.230484 0.339774 -> 0.570256 -0.230484 0.339772(R,m,v=1,0.87574,0.109467)
RL update rl*prefer*rvt*predict-no*H0*4*v1*H1*35 0.429761 0.230483 0.660244 -> 0.429759 0.230483 0.660242(R,m,v=1,1,0)
=>WM: (14204: 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: (14205: I3 ^predict-no N1008)
<=WM: (14191: N1007 ^status complete)
<=WM: (14190: 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-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: (14209: I2 ^dir L)
=>WM: (14208: I2 ^reward 1)
=>WM: (14207: I2 ^see 0)
=>WM: (14206: N1008 ^status complete)
<=WM: (14194: I2 ^dir U)
<=WM: (14193: I2 ^reward 1)
<=WM: (14192: I2 ^see 0)
=>WM: (14210: I2 ^level-1 R0-root)
<=WM: (14195: I2 ^level-1 R0-root)

--- END Input Phase --- 

--- Proposal Phase ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing rl*prefer*rvt*predict-yes*H0*5*v1*H1*30
 -->
 (S1 ^operator O2015 = 0.7358542477906264)
Firing prefer*rvt*predict-yes*H0*5*v1*H1
 -->
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 = 0.9998785089568328)
Firing rl*prefer*rvt*predict-yes*H0*5
 -->
 (S1 ^operator O2015 = 0.2640043987919141)
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
 -->
 (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*2
 -->
 (S1 ^operator O2016 = 1.)
Retracting rl*prefer*rvt*predict-yes*H0*1
 -->
 (S1 ^operator O2015 = 0.)
=>WM: (14217: S1 ^operator O2018 +)
=>WM: (14216: S1 ^operator O2017 +)
=>WM: (14215: I3 ^dir L)
=>WM: (14214: O2018 ^name predict-no)
=>WM: (14213: O2017 ^name predict-yes)
=>WM: (14212: R1012 ^value 1)
=>WM: (14211: R1 ^reward R1012)
<=WM: (14202: S1 ^operator O2015 +)
<=WM: (14203: S1 ^operator O2016 +)
<=WM: (14204: S1 ^operator O2016)
<=WM: (14201: I3 ^dir U)
<=WM: (14197: R1 ^reward R1011)
<=WM: (14200: O2016 ^name predict-no)
<=WM: (14199: O2015 ^name predict-yes)
<=WM: (14198: R1011 ^value 1)

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing prefer*rvt*predict-yes*H0
 -->
Firing rl*prefer*rvt*predict-yes*H0*5*v1*H1*30
 -->
 (S1 ^operator O2017 = 0.7358542477906264)
Firing rl*prefer*rvt*predict-yes*H0*5
 -->
 (S1 ^operator O2017 = 0.2640043987919141)
Firing prefer*rvt*predict-yes*H0*5*v1*H1
 -->
Firing prefer*rvt*predict-no*H0
 -->
Firing rl*prefer*rvt*predict-no*H0*6
 -->
 (S1 ^operator O2018 = 0.9998785089568328)
 inner elaboration loop at bottom goal.
Retracting rl*prefer*rvt*predict-no*H0*6
 -->
 (S1 ^operator O2016 = 0.9998785089568328)
Retracting rl*prefer*rvt*predict-yes*H0*5
 -->
 (S1 ^operator O2015 = 0.2640043987919141)
Retracting rl*prefer*rvt*predict-yes*H0*5*v1*H1*30
 -->
 (S1 ^operator O2015 = 0.7358542477906264)

--- END Proposal Phase ---

--- Decision Phase ---
RL update rl*prefer*rvt*predict-no*H0*2 1 0 1 -> 1 0 1(R,m,v=1,1,0)
=>WM: (14218: 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: (14219: I3 ^predict-no N1009)
<=WM: (14206: N1008 ^status complete)
<=WM: (14205: 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 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
--- END Output Phase ---
/|\--- Input Phase --- 
=>WM: (14223: I2 ^dir L)
=>WM: (14222: I2 ^reward 0)
=>WM: (14221: I2 ^see 1)
=>WM: (14220: N1009 ^status complete)
<=WM: (14209: I2 ^dir L)
<=WM: (14208: I2 ^reward 1)
<=WM: (14207: I2 ^see 0)
=>WM: (14224: I2 ^level-1 L1-root)
<=WM: (14210: I2 ^level-1 R0-root)

--- END Input Phase --- 

--- Proposal Phase ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing rl*prefer*rvt*predict-yes*H0*5*v1*H1*31
 -->
 (S1 ^operator O2017 = -0.181727099742844)
Firing prefer*rvt*predict-yes*H0*5*v1*H1
 -->
Firing elaborate*copy-see-to-output-link
 -->
 (I3 ^see 1 +)
Firing elaborate*reward*based*on*reward
 -->
 (R1013 ^value 0 +)
 (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 = 0.9998785089568328)
Firing rl*prefer*rvt*predict-yes*H0*5
 -->
 (S1 ^operator O2017 = 0.2640043987919141)
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
 -->
 (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 L +)
Retracting rl*prefer*rvt*predict-no*H0*6
 -->
 (S1 ^operator O2018 = 0.9998785089568328)
Retracting rl*prefer*rvt*predict-yes*H0*5
 -->
 (S1 ^operator O2017 = 0.2640043987919141)
Retracting rl*prefer*rvt*predict-yes*H0*5*v1*H1*30
 -->
 (S1 ^operator O2017 = 0.7358542477906264)
=>WM: (14231: S1 ^operator O2020 +)
=>WM: (14230: S1 ^operator O2019 +)
=>WM: (14229: O2020 ^name predict-no)
=>WM: (14228: O2019 ^name predict-yes)
=>WM: (14227: R1013 ^value 0)
=>WM: (14226: R1 ^reward R1013)
=>WM: (14225: I3 ^see 1)
<=WM: (14216: S1 ^operator O2017 +)
<=WM: (14217: S1 ^operator O2018 +)
<=WM: (14218: S1 ^operator O2018)
<=WM: (14211: R1 ^reward R1012)
<=WM: (14196: I3 ^see 0)
<=WM: (14214: O2018 ^name predict-no)
<=WM: (14213: O2017 ^name predict-yes)
<=WM: (14212: 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 = 0.2640043987919141)
Firing prefer*rvt*predict-yes*H0*5*v1*H1
 -->
Firing rl*prefer*rvt*predict-yes*H0*5*v1*H1*31
 -->
 (S1 ^operator O2019 = -0.181727099742844)
Firing prefer*rvt*predict-no*H0
 -->
Firing rl*prefer*rvt*predict-no*H0*6
 -->
 (S1 ^operator O2020 = 0.9998785089568328)
 inner elaboration loop at bottom goal.
Retracting rl*prefer*rvt*predict-no*H0*6
 -->
 (S1 ^operator O2018 = 0.9998785089568328)
Retracting rl*prefer*rvt*predict-yes*H0*5
 -->
 (S1 ^operator O2017 = 0.2640043987919141)
Retracting rl*prefer*rvt*predict-yes*H0*5*v1*H1*31
 -->
 (S1 ^operator O2017 = -0.181727099742844)

--- END Proposal Phase ---

--- Decision Phase ---
RL update rl*prefer*rvt*predict-no*H0*6 0.999879 0 0.999879 -> 0.833711 0 0.833711(R,m,v=0,0.900662,0.0900662)
=>WM: (14232: 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: (14233: I3 ^predict-no N1010)
<=WM: (14220: N1009 ^status complete)
<=WM: (14219: I3 ^predict-no N1009)
	--- Firing Productions (IE) For State At Depth 1 ---

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

I see 0 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: (14237: I2 ^dir R)
=>WM: (14236: I2 ^reward 1)
=>WM: (14235: I2 ^see 0)
=>WM: (14234: N1010 ^status complete)
<=WM: (14223: I2 ^dir L)
<=WM: (14222: I2 ^reward 0)
<=WM: (14221: I2 ^see 1)
=>WM: (14238: I2 ^level-1 L0-root)
<=WM: (14224: I2 ^level-1 L1-root)

--- END Input Phase --- 

--- Proposal Phase ---

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing rl*prefer*rvt*predict-no*H0*4*v1*H1*33
 -->
 (S1 ^operator O2020 = -0.2817060109291377)
Firing rl*prefer*rvt*predict-yes*H0*3*v1*H1*34
 -->
 (S1 ^operator O2019 = 0.6623458215671729)
Firing prefer*rvt*predict-no*H0*4*v1*H1
 -->
Firing prefer*rvt*predict-yes*H0*3*v1*H1
 -->
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*4
 -->
 (S1 ^operator O2020 = 0.3397723577617232)
Firing rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O2019 = 0.3377168791642142)
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
 -->
 (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 0 +)
 (R1 ^reward R1013 +)
Retracting elaborate*copy-dir-to-output-link
 -->
 (I3 ^dir L +)
Retracting rl*prefer*rvt*predict-no*H0*6
 -->
 (S1 ^operator O2020 = 0.8337106497126315)
Retracting rl*prefer*rvt*predict-yes*H0*5*v1*H1*31
 -->
 (S1 ^operator O2019 = -0.181727099742844)
Retracting rl*prefer*rvt*predict-yes*H0*5
 -->
 (S1 ^operator O2019 = 0.2640043987919141)
=>WM: (14246: S1 ^operator O2022 +)
=>WM: (14245: S1 ^operator O2021 +)
=>WM: (14244: I3 ^dir R)
=>WM: (14243: O2022 ^name predict-no)
=>WM: (14242: O2021 ^name predict-yes)
=>WM: (14241: R1014 ^value 1)
=>WM: (14240: R1 ^reward R1014)
=>WM: (14239: I3 ^see 0)
<=WM: (14230: S1 ^operator O2019 +)
<=WM: (14231: S1 ^operator O2020 +)
<=WM: (14232: S1 ^operator O2020)
<=WM: (14215: I3 ^dir L)
<=WM: (14226: R1 ^reward R1013)
<=WM: (14225: I3 ^see 1)
<=WM: (14229: O2020 ^name predict-no)
<=WM: (14228: O2019 ^name predict-yes)
<=WM: (14227: R1013 ^value 0)

--- Inner Elaboration Phase, active level 1 (S1) ---
Firing prefer*rvt*predict-yes*H0
 -->
Firing rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O2021 = 0.3377168791642142)
Firing prefer*rvt*predict-yes*H0*3*v1*H1
 -->
Firing rl*prefer*rvt*predict-yes*H0*3*v1*H1*34
 -->
 (S1 ^operator O2021 = 0.6623458215671729)
Firing prefer*rvt*predict-no*H0
 -->
Firing rl*prefer*rvt*predict-no*H0*4
 -->
 (S1 ^operator O2022 = 0.3397723577617232)
Firing prefer*rvt*predict-no*H0*4*v1*H1
 -->
Firing rl*prefer*rvt*predict-no*H0*4*v1*H1*33
 -->
 (S1 ^operator O2022 = -0.2817060109291377)
 inner elaboration loop at bottom goal.
Retracting rl*prefer*rvt*predict-no*H0*4
 -->
 (S1 ^operator O2020 = 0.3397723577617232)
Retracting rl*prefer*rvt*predict-no*H0*4*v1*H1*33
 -->
 (S1 ^operator O2020 = -0.2817060109291377)
Retracting rl*prefer*rvt*predict-yes*H0*3
 -->
 (S1 ^operator O2019 = 0.3377168791642142)
Retracting rl*prefer*rvt*predict-yes*H0*3*v1*H1*34
 -->
 (S1 ^operator O2019 = 0.6623458215671729)

--- END Proposal Phase ---

--- Decision Phase ---
RL update rl*prefer*rvt*predict-no*H0*6 0.833711 0 0.833711 -> 0.861316 0 0.861316(R,m,v=1,0.901316,0.0895347)
=>WM: (14247: S1 ^operator O2021)

  1011:    O: O2021 (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 N1011 +  :O )
Firing apply*operator*complete
 -->
 (I3 ^predict-no N1010 -  :O )
 inner elaboration loop at bottom goal.
	--- Change Working Memory (PE) ---
=>WM: (14248: I3 ^predict-yes N1011)
<=WM: (14234: N1010 ^status complete)
<=WM: (14233: I3 ^predict-no N1010)