PageRenderTime 140ms CodeModel.GetById 19ms RepoModel.GetById 1ms app.codeStats 0ms

/flipv2/20121113-091142-2.5K-ReLST-asneeded_epochs_50_5runs_noalphadecay/stdout-flip-2.5K_4.txt

https://bitbucket.org/evan13579b/soar-ziggurat
Plain Text | 16322 lines | 15596 code | 726 blank | 0 comment | 0 complexity | d3a0179b931f9256445520fb852fb030 MD5 | raw file
Possible License(s): BSD-3-Clause
  1. Seeding... 4
  2. dir: dir isL
  3. Python-Soar Flip environment.
  4. To accept commands from an external sml process, you'll need to
  5. type 'slave <log file> <n decisons>' at the prompt...
  6. sourcing 'flip_predict.soar'
  7. ***********
  8. Total: 11 productions sourced.
  9. seeding Soar with 4 ...
  10. soar> Entering slave mode:
  11. - log file 'rl-slave-2.5K_4.log'....
  12. - will exit slave mode after 2500 decisions
  13. waiting for commands from an externally connected sml process...
  14. -/|sleeping...
  15. \sleeping...
  16. -sleeping...
  17. /sleeping...
  18. |sleeping...
  19. \-/|\-/|\-/|sleeping...
  20. \-/|\-/sleeping...
  21. |1: O: O2 (predict-no)
  22. I see 0 and I'm going to do: predict-no
  23. ENV: Agent did: predict-no for direction L in state State-A
  24. In State-A moving L
  25. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  26. predict error 0
  27. dir: dir isL
  28. rule alias: '*'
  29. rule alias: '*'
  30. \-/|\-/2: O: O3 (predict-yes)
  31. I see 1 and I'm going to do: predict-yes
  32. ENV: Agent did: predict-yes for direction L in state State-A
  33. In State-A moving L
  34. ENV: (next state, see, prediction correct?) = (State-A, 0, False)
  35. predict error 1
  36. dir: dir isR
  37. |\-3: O: O6 (predict-no)
  38. I see 0 and I'm going to do: predict-no
  39. ENV: Agent did: predict-no for direction R in state State-A
  40. In State-A moving R
  41. ENV: (next state, see, prediction correct?) = (State-B, 1, False)
  42. predict error 1
  43. dir: dir isL
  44. /|\4: O: O8 (predict-no)
  45. I see 0 and I'm going to do: predict-no
  46. ENV: Agent did: predict-no for direction L in state State-B
  47. In State-B moving L
  48. ENV: (next state, see, prediction correct?) = (State-A, 1, False)
  49. predict error 1
  50. dir: dir isL
  51. -/5: O: O10 (predict-no)
  52. I see 0 and I'm going to do: predict-no
  53. ENV: Agent did: predict-no for direction L in state State-A
  54. In State-A moving L
  55. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  56. predict error 0
  57. dir: dir isR
  58. |\-6: O: O11 (predict-yes)
  59. I see 1 and I'm going to do: predict-yes
  60. ENV: Agent did: predict-yes for direction R in state State-A
  61. In State-A moving R
  62. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  63. predict error 0
  64. dir: dir isU
  65. /|7: O: O14 (predict-no)
  66. I see 1 and I'm going to do: predict-no
  67. ENV: Agent did: predict-no for direction U in state State-B
  68. In State-B moving U
  69. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  70. predict error 0
  71. dir: dir isU
  72. \-/8: O: O15 (predict-yes)
  73. I see 1 and I'm going to do: predict-yes
  74. ENV: Agent did: predict-yes for direction U in state State-B
  75. In State-B moving U
  76. ENV: (next state, see, prediction correct?) = (State-B, 0, False)
  77. predict error 1
  78. dir: dir isU
  79. |\-9: O: O17 (predict-yes)
  80. I see 0 and I'm going to do: predict-yes
  81. ENV: Agent did: predict-yes for direction U in state State-B
  82. In State-B moving U
  83. ENV: (next state, see, prediction correct?) = (State-B, 0, False)
  84. predict error 1
  85. dir: dir isL
  86. /|\-10: O: O19 (predict-yes)
  87. I see 0 and I'm going to do: predict-yes
  88. ENV: Agent did: predict-yes for direction L in state State-B
  89. In State-B moving L
  90. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  91. predict error 0
  92. dir: dir isR
  93. /|\11: O: O21 (predict-yes)
  94. I see 1 and I'm going to do: predict-yes
  95. ENV: Agent did: predict-yes for direction R in state State-A
  96. In State-A moving R
  97. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  98. predict error 0
  99. dir: dir isL
  100. rule alias: '*'
  101. rule alias: '*'
  102. rule alias: '*'
  103. rule alias: '*'
  104. -12: O: O24 (predict-no)
  105. I see 1 and I'm going to do: predict-no
  106. ENV: Agent did: predict-no for direction L in state State-B
  107. In State-B moving L
  108. ENV: (next state, see, prediction correct?) = (State-A, 1, False)
  109. predict error 1
  110. dir: dir isL
  111. /|\13: O: O26 (predict-no)
  112. I see 0 and I'm going to do: predict-no
  113. ENV: Agent did: predict-no for direction L in state State-A
  114. In State-A moving L
  115. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  116. predict error 0
  117. dir: dir isL
  118. -/|14: O: O28 (predict-no)
  119. I see 1 and I'm going to do: predict-no
  120. ENV: Agent did: predict-no for direction L in state State-A
  121. In State-A moving L
  122. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  123. predict error 0
  124. dir: dir isL
  125. \-/15: O: O30 (predict-no)
  126. I see 1 and I'm going to do: predict-no
  127. ENV: Agent did: predict-no for direction L in state State-A
  128. In State-A moving L
  129. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  130. predict error 0
  131. dir: dir isU
  132. |\-16: O: O32 (predict-no)
  133. I see 1 and I'm going to do: predict-no
  134. ENV: Agent did: predict-no for direction U in state State-A
  135. In State-A moving U
  136. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  137. predict error 0
  138. dir: dir isU
  139. /|17: O: O34 (predict-no)
  140. I see 1 and I'm going to do: predict-no
  141. ENV: Agent did: predict-no for direction U in state State-A
  142. In State-A moving U
  143. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  144. predict error 0
  145. dir: dir isU
  146. \-18: O: O36 (predict-no)
  147. I see 1 and I'm going to do: predict-no
  148. ENV: Agent did: predict-no for direction U in state State-A
  149. In State-A moving U
  150. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  151. predict error 0
  152. dir: dir isU
  153. /|\19: O: O38 (predict-no)
  154. I see 1 and I'm going to do: predict-no
  155. ENV: Agent did: predict-no for direction U in state State-A
  156. In State-A moving U
  157. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  158. predict error 0
  159. dir: dir isL
  160. -/|20: O: O39 (predict-yes)
  161. I see 1 and I'm going to do: predict-yes
  162. ENV: Agent did: predict-yes for direction L in state State-A
  163. In State-A moving L
  164. ENV: (next state, see, prediction correct?) = (State-A, 0, False)
  165. predict error 1
  166. dir: dir isL
  167. \-/|sleeping...
  168. \21: O: O42 (predict-no)
  169. I see 0 and I'm going to do: predict-no
  170. ENV: Agent did: predict-no for direction L in state State-A
  171. In State-A moving L
  172. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  173. predict error 0
  174. dir: dir isR
  175. -22: O: O43 (predict-yes)
  176. I see 1 and I'm going to do: predict-yes
  177. ENV: Agent did: predict-yes for direction R in state State-A
  178. In State-A moving R
  179. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  180. predict error 0
  181. dir: dir isU
  182. /|23: O: O45 (predict-yes)
  183. I see 1 and I'm going to do: predict-yes
  184. ENV: Agent did: predict-yes for direction U in state State-B
  185. In State-B moving U
  186. ENV: (next state, see, prediction correct?) = (State-B, 0, False)
  187. predict error 1
  188. dir: dir isU
  189. \-/24: O: O48 (predict-no)
  190. I see 0 and I'm going to do: predict-no
  191. ENV: Agent did: predict-no for direction U in state State-B
  192. In State-B moving U
  193. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  194. predict error 0
  195. dir: dir isU
  196. |\-25: O: O50 (predict-no)
  197. I see 1 and I'm going to do: predict-no
  198. ENV: Agent did: predict-no for direction U in state State-B
  199. In State-B moving U
  200. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  201. predict error 0
  202. dir: dir isL
  203. /|\-26: O: O52 (predict-no)
  204. I see 1 and I'm going to do: predict-no
  205. ENV: Agent did: predict-no for direction L in state State-B
  206. In State-B moving L
  207. ENV: (next state, see, prediction correct?) = (State-A, 1, False)
  208. predict error 1
  209. dir: dir isR
  210. /|27: O: O53 (predict-yes)
  211. I see 0 and I'm going to do: predict-yes
  212. ENV: Agent did: predict-yes for direction R in state State-A
  213. In State-A moving R
  214. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  215. predict error 0
  216. dir: dir isU
  217. \-/28: O: O56 (predict-no)
  218. I see 1 and I'm going to do: predict-no
  219. ENV: Agent did: predict-no for direction U in state State-B
  220. In State-B moving U
  221. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  222. predict error 0
  223. dir: dir isR
  224. |\-29: O: O57 (predict-yes)
  225. I see 1 and I'm going to do: predict-yes
  226. ENV: Agent did: predict-yes for direction R in state State-B
  227. In State-B moving R
  228. ENV: (next state, see, prediction correct?) = (State-B, 0, False)
  229. predict error 1
  230. dir: dir isL
  231. /|\30: O: O60 (predict-no)
  232. I see 0 and I'm going to do: predict-no
  233. ENV: Agent did: predict-no for direction L in state State-B
  234. In State-B moving L
  235. ENV: (next state, see, prediction correct?) = (State-A, 1, False)
  236. predict error 1
  237. dir: dir isR
  238. -31: O: O61 (predict-yes)
  239. I see 0 and I'm going to do: predict-yes
  240. ENV: Agent did: predict-yes for direction R in state State-A
  241. In State-A moving R
  242. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  243. predict error 0
  244. dir: dir isL
  245. /32: O: O64 (predict-no)
  246. I see 1 and I'm going to do: predict-no
  247. ENV: Agent did: predict-no for direction L in state State-B
  248. In State-B moving L
  249. ENV: (next state, see, prediction correct?) = (State-A, 1, False)
  250. predict error 1
  251. dir: dir isU
  252. |\-33: O: O66 (predict-no)
  253. I see 0 and I'm going to do: predict-no
  254. ENV: Agent did: predict-no for direction U in state State-A
  255. In State-A moving U
  256. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  257. predict error 0
  258. dir: dir isU
  259. /|\34: O: O68 (predict-no)
  260. I see 1 and I'm going to do: predict-no
  261. ENV: Agent did: predict-no for direction U in state State-A
  262. In State-A moving U
  263. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  264. predict error 0
  265. dir: dir isR
  266. -/|35: O: O69 (predict-yes)
  267. I see 1 and I'm going to do: predict-yes
  268. ENV: Agent did: predict-yes for direction R in state State-A
  269. In State-A moving R
  270. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  271. predict error 0
  272. dir: dir isL
  273. \-36: O: O72 (predict-no)
  274. I see 1 and I'm going to do: predict-no
  275. ENV: Agent did: predict-no for direction L in state State-B
  276. In State-B moving L
  277. ENV: (next state, see, prediction correct?) = (State-A, 1, False)
  278. predict error 1
  279. dir: dir isU
  280. /|\37: O: O74 (predict-no)
  281. I see 0 and I'm going to do: predict-no
  282. ENV: Agent did: predict-no for direction U in state State-A
  283. In State-A moving U
  284. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  285. predict error 0
  286. dir: dir isR
  287. -/|38: O: O76 (predict-no)
  288. I see 1 and I'm going to do: predict-no
  289. ENV: Agent did: predict-no for direction R in state State-A
  290. In State-A moving R
  291. ENV: (next state, see, prediction correct?) = (State-B, 1, False)
  292. predict error 1
  293. dir: dir isU
  294. \-/39: O: O78 (predict-no)
  295. I see 0 and I'm going to do: predict-no
  296. ENV: Agent did: predict-no for direction U in state State-B
  297. In State-B moving U
  298. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  299. predict error 0
  300. dir: dir isU
  301. |\-40: O: O80 (predict-no)
  302. I see 1 and I'm going to do: predict-no
  303. ENV: Agent did: predict-no for direction U in state State-B
  304. In State-B moving U
  305. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  306. predict error 0
  307. dir: dir isR
  308. /|\-41: O: O81 (predict-yes)
  309. I see 1 and I'm going to do: predict-yes
  310. ENV: Agent did: predict-yes for direction R in state State-B
  311. In State-B moving R
  312. ENV: (next state, see, prediction correct?) = (State-B, 0, False)
  313. predict error 1
  314. dir: dir isR
  315. /42: O: O83 (predict-yes)
  316. I see 0 and I'm going to do: predict-yes
  317. ENV: Agent did: predict-yes for direction R in state State-B
  318. In State-B moving R
  319. ENV: (next state, see, prediction correct?) = (State-B, 0, False)
  320. predict error 1
  321. dir: dir isR
  322. |\-/43: O: O85 (predict-yes)
  323. I see 0 and I'm going to do: predict-yes
  324. ENV: Agent did: predict-yes for direction R in state State-B
  325. In State-B moving R
  326. ENV: (next state, see, prediction correct?) = (State-B, 0, False)
  327. predict error 1
  328. dir: dir isR
  329. |\-44: O: O87 (predict-yes)
  330. I see 0 and I'm going to do: predict-yes
  331. ENV: Agent did: predict-yes for direction R in state State-B
  332. In State-B moving R
  333. ENV: (next state, see, prediction correct?) = (State-B, 0, False)
  334. predict error 1
  335. dir: dir isL
  336. /|\45: O: O89 (predict-yes)
  337. I see 0 and I'm going to do: predict-yes
  338. ENV: Agent did: predict-yes for direction L in state State-B
  339. In State-B moving L
  340. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  341. predict error 0
  342. dir: dir isL
  343. -/|46: O: O91 (predict-yes)
  344. I see 1 and I'm going to do: predict-yes
  345. ENV: Agent did: predict-yes for direction L in state State-A
  346. In State-A moving L
  347. ENV: (next state, see, prediction correct?) = (State-A, 0, False)
  348. predict error 1
  349. dir: dir isU
  350. \-/47: O: O94 (predict-no)
  351. I see 0 and I'm going to do: predict-no
  352. ENV: Agent did: predict-no for direction U in state State-A
  353. In State-A moving U
  354. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  355. predict error 0
  356. dir: dir isL
  357. |\48: O: O95 (predict-yes)
  358. I see 1 and I'm going to do: predict-yes
  359. ENV: Agent did: predict-yes for direction L in state State-A
  360. In State-A moving L
  361. ENV: (next state, see, prediction correct?) = (State-A, 0, False)
  362. predict error 1
  363. dir: dir isL
  364. -/49: O: O97 (predict-yes)
  365. I see 0 and I'm going to do: predict-yes
  366. ENV: Agent did: predict-yes for direction L in state State-A
  367. In State-A moving L
  368. ENV: (next state, see, prediction correct?) = (State-A, 0, False)
  369. predict error 1
  370. dir: dir isR
  371. |\-/50: O: O99 (predict-yes)
  372. I see 0 and I'm going to do: predict-yes
  373. ENV: Agent did: predict-yes for direction R in state State-A
  374. In State-A moving R
  375. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  376. predict error 0
  377. dir: dir isL
  378. |\-/|\-sleeping...
  379. /sleeping...
  380. |51: O: O102 (predict-no)
  381. I see 1 and I'm going to do: predict-no
  382. ENV: Agent did: predict-no for direction L in state State-B
  383. In State-B moving L
  384. ENV: (next state, see, prediction correct?) = (State-A, 1, False)
  385. predict error 1
  386. dir: dir isR
  387. rule alias: '*'
  388. rule alias: '*'
  389. \52: O: O103 (predict-yes)
  390. I see 0 and I'm going to do: predict-yes
  391. ENV: Agent did: predict-yes for direction R in state State-A
  392. In State-A moving R
  393. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  394. predict error 0
  395. dir: dir isR
  396. -/53: O: O106 (predict-no)
  397. I see 1 and I'm going to do: predict-no
  398. ENV: Agent did: predict-no for direction R in state State-B
  399. In State-B moving R
  400. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  401. predict error 0
  402. dir: dir isR
  403. |\-54: O: O107 (predict-yes)
  404. I see 1 and I'm going to do: predict-yes
  405. ENV: Agent did: predict-yes for direction R in state State-B
  406. In State-B moving R
  407. ENV: (next state, see, prediction correct?) = (State-B, 0, False)
  408. predict error 1
  409. dir: dir isU
  410. /|\55: O: O110 (predict-no)
  411. I see 0 and I'm going to do: predict-no
  412. ENV: Agent did: predict-no for direction U in state State-B
  413. In State-B moving U
  414. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  415. predict error 0
  416. dir: dir isL
  417. -/|\sleeping...
  418. -56: O: O112 (predict-no)
  419. I see 1 and I'm going to do: predict-no
  420. ENV: Agent did: predict-no for direction L in state State-B
  421. In State-B moving L
  422. ENV: (next state, see, prediction correct?) = (State-A, 1, False)
  423. predict error 1
  424. dir: dir isR
  425. /|57: O: O113 (predict-yes)
  426. I see 0 and I'm going to do: predict-yes
  427. ENV: Agent did: predict-yes for direction R in state State-A
  428. In State-A moving R
  429. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  430. predict error 0
  431. dir: dir isL
  432. \-58: O: O115 (predict-yes)
  433. I see 1 and I'm going to do: predict-yes
  434. ENV: Agent did: predict-yes for direction L in state State-B
  435. In State-B moving L
  436. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  437. predict error 0
  438. dir: dir isR
  439. /|59: O: O117 (predict-yes)
  440. I see 1 and I'm going to do: predict-yes
  441. ENV: Agent did: predict-yes for direction R in state State-A
  442. In State-A moving R
  443. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  444. predict error 0
  445. dir: dir isL
  446. \-/60: O: O119 (predict-yes)
  447. I see 1 and I'm going to do: predict-yes
  448. ENV: Agent did: predict-yes for direction L in state State-B
  449. In State-B moving L
  450. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  451. predict error 0
  452. dir: dir isR
  453. |\-/61: O: O121 (predict-yes)
  454. I see 1 and I'm going to do: predict-yes
  455. ENV: Agent did: predict-yes for direction R in state State-A
  456. In State-A moving R
  457. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  458. predict error 0
  459. dir: dir isU
  460. rule alias: '*'
  461. rule alias: '*'
  462. rule alias: '*'
  463. rule alias: '*'
  464. rule alias: '*'
  465. rule alias: '*'
  466. |62: O: O124 (predict-no)
  467. I see 1 and I'm going to do: predict-no
  468. ENV: Agent did: predict-no for direction U in state State-B
  469. In State-B moving U
  470. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  471. predict error 0
  472. dir: dir isL
  473. \-/63: O: O125 (predict-yes)
  474. I see 1 and I'm going to do: predict-yes
  475. ENV: Agent did: predict-yes for direction L in state State-B
  476. In State-B moving L
  477. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  478. predict error 0
  479. dir: dir isR
  480. |\-64: O: O127 (predict-yes)
  481. I see 1 and I'm going to do: predict-yes
  482. ENV: Agent did: predict-yes for direction R in state State-A
  483. In State-A moving R
  484. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  485. predict error 0
  486. dir: dir isU
  487. /|65: O: O130 (predict-no)
  488. I see 1 and I'm going to do: predict-no
  489. ENV: Agent did: predict-no for direction U in state State-B
  490. In State-B moving U
  491. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  492. predict error 0
  493. dir: dir isL
  494. \-/66: O: O131 (predict-yes)
  495. I see 1 and I'm going to do: predict-yes
  496. ENV: Agent did: predict-yes for direction L in state State-B
  497. In State-B moving L
  498. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  499. predict error 0
  500. dir: dir isL
  501. |\-67: O: O133 (predict-yes)
  502. I see 1 and I'm going to do: predict-yes
  503. ENV: Agent did: predict-yes for direction L in state State-A
  504. In State-A moving L
  505. ENV: (next state, see, prediction correct?) = (State-A, 0, False)
  506. predict error 1
  507. dir: dir isL
  508. /|\68: O: O135 (predict-yes)
  509. I see 0 and I'm going to do: predict-yes
  510. ENV: Agent did: predict-yes for direction L in state State-A
  511. In State-A moving L
  512. ENV: (next state, see, prediction correct?) = (State-A, 0, False)
  513. predict error 1
  514. dir: dir isU
  515. -/|69: O: O138 (predict-no)
  516. I see 0 and I'm going to do: predict-no
  517. ENV: Agent did: predict-no for direction U in state State-A
  518. In State-A moving U
  519. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  520. predict error 0
  521. dir: dir isR
  522. \-70: O: O140 (predict-no)
  523. I see 1 and I'm going to do: predict-no
  524. ENV: Agent did: predict-no for direction R in state State-A
  525. In State-A moving R
  526. ENV: (next state, see, prediction correct?) = (State-B, 1, False)
  527. predict error 1
  528. dir: dir isL
  529. /|\-71: O: O141 (predict-yes)
  530. I see 0 and I'm going to do: predict-yes
  531. ENV: Agent did: predict-yes for direction L in state State-B
  532. In State-B moving L
  533. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  534. predict error 0
  535. dir: dir isL
  536. rule alias: '*'
  537. rule alias: '*'
  538. rule alias: '*'
  539. rule alias: '*'
  540. rule alias: '*'
  541. rule alias: '*'
  542. rule alias: '*'
  543. rule alias: '*'
  544. /72: O: O143 (predict-yes)
  545. I see 1 and I'm going to do: predict-yes
  546. ENV: Agent did: predict-yes for direction L in state State-A
  547. In State-A moving L
  548. ENV: (next state, see, prediction correct?) = (State-A, 0, False)
  549. predict error 1
  550. dir: dir isL
  551. |\-73: O: O145 (predict-yes)
  552. I see 0 and I'm going to do: predict-yes
  553. ENV: Agent did: predict-yes for direction L in state State-A
  554. In State-A moving L
  555. ENV: (next state, see, prediction correct?) = (State-A, 0, False)
  556. predict error 1
  557. dir: dir isR
  558. /|\74: O: O147 (predict-yes)
  559. I see 0 and I'm going to do: predict-yes
  560. ENV: Agent did: predict-yes for direction R in state State-A
  561. In State-A moving R
  562. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  563. predict error 0
  564. dir: dir isL
  565. -/75: O: O149 (predict-yes)
  566. I see 1 and I'm going to do: predict-yes
  567. ENV: Agent did: predict-yes for direction L in state State-B
  568. In State-B moving L
  569. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  570. predict error 0
  571. dir: dir isU
  572. |\-76: O: O151 (predict-yes)
  573. I see 1 and I'm going to do: predict-yes
  574. ENV: Agent did: predict-yes for direction U in state State-A
  575. In State-A moving U
  576. ENV: (next state, see, prediction correct?) = (State-A, 0, False)
  577. predict error 1
  578. dir: dir isU
  579. /|\77: O: O154 (predict-no)
  580. I see 0 and I'm going to do: predict-no
  581. ENV: Agent did: predict-no for direction U in state State-A
  582. In State-A moving U
  583. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  584. predict error 0
  585. dir: dir isU
  586. -/|\78: O: O156 (predict-no)
  587. I see 1 and I'm going to do: predict-no
  588. ENV: Agent did: predict-no for direction U in state State-A
  589. In State-A moving U
  590. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  591. predict error 0
  592. dir: dir isU
  593. -79: O: O158 (predict-no)
  594. I see 1 and I'm going to do: predict-no
  595. ENV: Agent did: predict-no for direction U in state State-A
  596. In State-A moving U
  597. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  598. predict error 0
  599. dir: dir isU
  600. /|\80: O: O159 (predict-yes)
  601. I see 1 and I'm going to do: predict-yes
  602. ENV: Agent did: predict-yes for direction U in state State-A
  603. In State-A moving U
  604. ENV: (next state, see, prediction correct?) = (State-A, 0, False)
  605. predict error 1
  606. dir: dir isL
  607. -/|\81: O: O161 (predict-yes)
  608. I see 0 and I'm going to do: predict-yes
  609. ENV: Agent did: predict-yes for direction L in state State-A
  610. In State-A moving L
  611. ENV: (next state, see, prediction correct?) = (State-A, 0, False)
  612. predict error 1
  613. dir: dir isL
  614. rule alias: '*'
  615. rule alias: '*'
  616. rule alias: '*'
  617. rule alias: '*'
  618. -82: O: O163 (predict-yes)
  619. I see 0 and I'm going to do: predict-yes
  620. ENV: Agent did: predict-yes for direction L in state State-A
  621. In State-A moving L
  622. ENV: (next state, see, prediction correct?) = (State-A, 0, False)
  623. predict error 1
  624. dir: dir isU
  625. /|\83: O: O166 (predict-no)
  626. I see 0 and I'm going to do: predict-no
  627. ENV: Agent did: predict-no for direction U in state State-A
  628. In State-A moving U
  629. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  630. predict error 0
  631. dir: dir isU
  632. -/|\84: O: O168 (predict-no)
  633. I see 1 and I'm going to do: predict-no
  634. ENV: Agent did: predict-no for direction U in state State-A
  635. In State-A moving U
  636. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  637. predict error 0
  638. dir: dir isR
  639. -/85: O: O169 (predict-yes)
  640. I see 1 and I'm going to do: predict-yes
  641. ENV: Agent did: predict-yes for direction R in state State-A
  642. In State-A moving R
  643. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  644. predict error 0
  645. dir: dir isU
  646. |\-/86: O: O172 (predict-no)
  647. I see 1 and I'm going to do: predict-no
  648. ENV: Agent did: predict-no for direction U in state State-B
  649. In State-B moving U
  650. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  651. predict error 0
  652. dir: dir isR
  653. |\87: O: O173 (predict-yes)
  654. I see 1 and I'm going to do: predict-yes
  655. ENV: Agent did: predict-yes for direction R in state State-B
  656. In State-B moving R
  657. ENV: (next state, see, prediction correct?) = (State-B, 0, False)
  658. predict error 1
  659. dir: dir isU
  660. -/88: O: O176 (predict-no)
  661. I see 0 and I'm going to do: predict-no
  662. ENV: Agent did: predict-no for direction U in state State-B
  663. In State-B moving U
  664. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  665. predict error 0
  666. dir: dir isL
  667. |\-89: O: O177 (predict-yes)
  668. I see 1 and I'm going to do: predict-yes
  669. ENV: Agent did: predict-yes for direction L in state State-B
  670. In State-B moving L
  671. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  672. predict error 0
  673. dir: dir isL
  674. /|90: O: O180 (predict-no)
  675. I see 1 and I'm going to do: predict-no
  676. ENV: Agent did: predict-no for direction L in state State-A
  677. In State-A moving L
  678. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  679. predict error 0
  680. dir: dir isR
  681. \-/91: O: O181 (predict-yes)
  682. I see 1 and I'm going to do: predict-yes
  683. ENV: Agent did: predict-yes for direction R in state State-A
  684. In State-A moving R
  685. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  686. predict error 0
  687. dir: dir isL
  688. rule alias: '*'
  689. rule alias: '*'
  690. rule alias: '*'
  691. rule alias: '*'
  692. |92: O: O183 (predict-yes)
  693. I see 1 and I'm going to do: predict-yes
  694. ENV: Agent did: predict-yes for direction L in state State-B
  695. In State-B moving L
  696. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  697. predict error 0
  698. dir: dir isR
  699. \-/93: O: O185 (predict-yes)
  700. I see 1 and I'm going to do: predict-yes
  701. ENV: Agent did: predict-yes for direction R in state State-A
  702. In State-A moving R
  703. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  704. predict error 0
  705. dir: dir isU
  706. |\-94: O: O188 (predict-no)
  707. I see 1 and I'm going to do: predict-no
  708. ENV: Agent did: predict-no for direction U in state State-B
  709. In State-B moving U
  710. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  711. predict error 0
  712. dir: dir isL
  713. /|\95: O: O189 (predict-yes)
  714. I see 1 and I'm going to do: predict-yes
  715. ENV: Agent did: predict-yes for direction L in state State-B
  716. In State-B moving L
  717. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  718. predict error 0
  719. dir: dir isL
  720. -/|\96: O: O192 (predict-no)
  721. I see 1 and I'm going to do: predict-no
  722. ENV: Agent did: predict-no for direction L in state State-A
  723. In State-A moving L
  724. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  725. predict error 0
  726. dir: dir isL
  727. -/|97: O: O194 (predict-no)
  728. I see 1 and I'm going to do: predict-no
  729. ENV: Agent did: predict-no for direction L in state State-A
  730. In State-A moving L
  731. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  732. predict error 0
  733. dir: dir isL
  734. \-/98: O: O196 (predict-no)
  735. I see 1 and I'm going to do: predict-no
  736. ENV: Agent did: predict-no for direction L in state State-A
  737. In State-A moving L
  738. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  739. predict error 0
  740. dir: dir isU
  741. |\99: O: O198 (predict-no)
  742. I see 1 and I'm going to do: predict-no
  743. ENV: Agent did: predict-no for direction U in state State-A
  744. In State-A moving U
  745. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  746. predict error 0
  747. dir: dir isR
  748. -100: O: O199 (predict-yes)
  749. I see 1 and I'm going to do: predict-yes
  750. ENV: Agent did: predict-yes for direction R in state State-A
  751. In State-A moving R
  752. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  753. predict error 0
  754. dir: dir isL
  755. /|\101: O: O201 (predict-yes)
  756. I see 1 and I'm going to do: predict-yes
  757. ENV: Agent did: predict-yes for direction L in state State-B
  758. In State-B moving L
  759. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  760. predict error 0
  761. dir: dir isL
  762. -/|\-/|\-/|\-/|\-/|\-/|\-/|\-/|\-/|sleeping...
  763. \102: O: O204 (predict-no)
  764. I see 1 and I'm going to do: predict-no
  765. ENV: Agent did: predict-no for direction L in state State-A
  766. In State-A moving L
  767. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  768. predict error 0
  769. dir: dir isU
  770. -/|\103: O: O206 (predict-no)
  771. I see 1 and I'm going to do: predict-no
  772. ENV: Agent did: predict-no for direction U in state State-A
  773. In State-A moving U
  774. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  775. predict error 0
  776. dir: dir isR
  777. -/|104: O: O208 (predict-no)
  778. I see 1 and I'm going to do: predict-no
  779. ENV: Agent did: predict-no for direction R in state State-A
  780. In State-A moving R
  781. ENV: (next state, see, prediction correct?) = (State-B, 1, False)
  782. predict error 1
  783. dir: dir isL
  784. \-105: O: O209 (predict-yes)
  785. I see 0 and I'm going to do: predict-yes
  786. ENV: Agent did: predict-yes for direction L in state State-B
  787. In State-B moving L
  788. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  789. predict error 0
  790. dir: dir isL
  791. /106: O: O211 (predict-yes)
  792. I see 1 and I'm going to do: predict-yes
  793. ENV: Agent did: predict-yes for direction L in state State-A
  794. In State-A moving L
  795. ENV: (next state, see, prediction correct?) = (State-A, 0, False)
  796. predict error 1
  797. dir: dir isL
  798. |\107: O: O214 (predict-no)
  799. I see 0 and I'm going to do: predict-no
  800. ENV: Agent did: predict-no for direction L in state State-A
  801. In State-A moving L
  802. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  803. predict error 0
  804. dir: dir isL
  805. -/108: O: O216 (predict-no)
  806. I see 1 and I'm going to do: predict-no
  807. ENV: Agent did: predict-no for direction L in state State-A
  808. In State-A moving L
  809. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  810. predict error 0
  811. dir: dir isU
  812. |\-109: O: O218 (predict-no)
  813. I see 1 and I'm going to do: predict-no
  814. ENV: Agent did: predict-no for direction U in state State-A
  815. In State-A moving U
  816. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  817. predict error 0
  818. dir: dir isL
  819. /|110: O: O220 (predict-no)
  820. I see 1 and I'm going to do: predict-no
  821. ENV: Agent did: predict-no for direction L in state State-A
  822. In State-A moving L
  823. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  824. predict error 0
  825. dir: dir isL
  826. \-111: O: O221 (predict-yes)
  827. I see 1 and I'm going to do: predict-yes
  828. ENV: Agent did: predict-yes for direction L in state State-A
  829. In State-A moving L
  830. ENV: (next state, see, prediction correct?) = (State-A, 0, False)
  831. predict error 1
  832. dir: dir isR
  833. rule alias: '*'
  834. rule alias: '*'
  835. rule alias: '*'
  836. rule alias: '*'
  837. rule alias: '*'
  838. rule alias: '*'
  839. rule alias: '*'
  840. rule alias: '*'
  841. /112: O: O223 (predict-yes)
  842. I see 0 and I'm going to do: predict-yes
  843. ENV: Agent did: predict-yes for direction R in state State-A
  844. In State-A moving R
  845. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  846. predict error 0
  847. dir: dir isL
  848. |\-113: O: O226 (predict-no)
  849. I see 1 and I'm going to do: predict-no
  850. ENV: Agent did: predict-no for direction L in state State-B
  851. In State-B moving L
  852. ENV: (next state, see, prediction correct?) = (State-A, 1, False)
  853. predict error 1
  854. dir: dir isU
  855. /|\114: O: O228 (predict-no)
  856. I see 0 and I'm going to do: predict-no
  857. ENV: Agent did: predict-no for direction U in state State-A
  858. In State-A moving U
  859. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  860. predict error 0
  861. dir: dir isL
  862. -/115: O: O229 (predict-yes)
  863. I see 1 and I'm going to do: predict-yes
  864. ENV: Agent did: predict-yes for direction L in state State-A
  865. In State-A moving L
  866. ENV: (next state, see, prediction correct?) = (State-A, 0, False)
  867. predict error 1
  868. dir: dir isR
  869. |\-116: O: O231 (predict-yes)
  870. I see 0 and I'm going to do: predict-yes
  871. ENV: Agent did: predict-yes for direction R in state State-A
  872. In State-A moving R
  873. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  874. predict error 0
  875. dir: dir isU
  876. /|\117: O: O234 (predict-no)
  877. I see 1 and I'm going to do: predict-no
  878. ENV: Agent did: predict-no for direction U in state State-B
  879. In State-B moving U
  880. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  881. predict error 0
  882. dir: dir isR
  883. -/|118: O: O235 (predict-yes)
  884. I see 1 and I'm going to do: predict-yes
  885. ENV: Agent did: predict-yes for direction R in state State-B
  886. In State-B moving R
  887. ENV: (next state, see, prediction correct?) = (State-B, 0, False)
  888. predict error 1
  889. dir: dir isU
  890. \-/119: O: O238 (predict-no)
  891. I see 0 and I'm going to do: predict-no
  892. ENV: Agent did: predict-no for direction U in state State-B
  893. In State-B moving U
  894. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  895. predict error 0
  896. dir: dir isR
  897. |\-120: O: O239 (predict-yes)
  898. I see 1 and I'm going to do: predict-yes
  899. ENV: Agent did: predict-yes for direction R in state State-B
  900. In State-B moving R
  901. ENV: (next state, see, prediction correct?) = (State-B, 0, False)
  902. predict error 1
  903. dir: dir isL
  904. /|\121: O: O242 (predict-no)
  905. I see 0 and I'm going to do: predict-no
  906. ENV: Agent did: predict-no for direction L in state State-B
  907. In State-B moving L
  908. ENV: (next state, see, prediction correct?) = (State-A, 1, False)
  909. predict error 1
  910. dir: dir isR
  911. rule alias: '*'
  912. rule alias: '*'
  913. rule alias: '*'
  914. rule alias: '*'
  915. rule alias: '*'
  916. rule alias: '*'
  917. -122: O: O243 (predict-yes)
  918. I see 0 and I'm going to do: predict-yes
  919. ENV: Agent did: predict-yes for direction R in state State-A
  920. In State-A moving R
  921. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  922. predict error 0
  923. dir: dir isL
  924. /|\-123: O: O245 (predict-yes)
  925. I see 1 and I'm going to do: predict-yes
  926. ENV: Agent did: predict-yes for direction L in state State-B
  927. In State-B moving L
  928. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  929. predict error 0
  930. dir: dir isR
  931. /|\124: O: O248 (predict-no)
  932. I see 1 and I'm going to do: predict-no
  933. ENV: Agent did: predict-no for direction R in state State-A
  934. In State-A moving R
  935. ENV: (next state, see, prediction correct?) = (State-B, 1, False)
  936. predict error 1
  937. dir: dir isL
  938. -125: O: O249 (predict-yes)
  939. I see 0 and I'm going to do: predict-yes
  940. ENV: Agent did: predict-yes for direction L in state State-B
  941. In State-B moving L
  942. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  943. predict error 0
  944. dir: dir isU
  945. /|\126: O: O252 (predict-no)
  946. I see 1 and I'm going to do: predict-no
  947. ENV: Agent did: predict-no for direction U in state State-A
  948. In State-A moving U
  949. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  950. predict error 0
  951. dir: dir isU
  952. -/|\127: O: O254 (predict-no)
  953. I see 1 and I'm going to do: predict-no
  954. ENV: Agent did: predict-no for direction U in state State-A
  955. In State-A moving U
  956. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  957. predict error 0
  958. dir: dir isR
  959. -/|\128: O: O255 (predict-yes)
  960. I see 1 and I'm going to do: predict-yes
  961. ENV: Agent did: predict-yes for direction R in state State-A
  962. In State-A moving R
  963. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  964. predict error 0
  965. dir: dir isL
  966. -/129: O: O257 (predict-yes)
  967. I see 1 and I'm going to do: predict-yes
  968. ENV: Agent did: predict-yes for direction L in state State-B
  969. In State-B moving L
  970. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  971. predict error 0
  972. dir: dir isL
  973. |\-130: O: O259 (predict-yes)
  974. I see 1 and I'm going to do: predict-yes
  975. ENV: Agent did: predict-yes for direction L in state State-A
  976. In State-A moving L
  977. ENV: (next state, see, prediction correct?) = (State-A, 0, False)
  978. predict error 1
  979. dir: dir isL
  980. /|131: O: O262 (predict-no)
  981. I see 0 and I'm going to do: predict-no
  982. ENV: Agent did: predict-no for direction L in state State-A
  983. In State-A moving L
  984. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  985. predict error 0
  986. dir: dir isL
  987. rule alias: '*'
  988. rule alias: '*'
  989. \132: O: O264 (predict-no)
  990. I see 1 and I'm going to do: predict-no
  991. ENV: Agent did: predict-no for direction L in state State-A
  992. In State-A moving L
  993. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  994. predict error 0
  995. dir: dir isL
  996. -/133: O: O266 (predict-no)
  997. I see 1 and I'm going to do: predict-no
  998. ENV: Agent did: predict-no for direction L in state State-A
  999. In State-A moving L
  1000. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  1001. predict error 0
  1002. dir: dir isU
  1003. |\-134: O: O268 (predict-no)
  1004. I see 1 and I'm going to do: predict-no
  1005. ENV: Agent did: predict-no for direction U in state State-A
  1006. In State-A moving U
  1007. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  1008. predict error 0
  1009. dir: dir isL
  1010. /|135: O: O270 (predict-no)
  1011. I see 1 and I'm going to do: predict-no
  1012. ENV: Agent did: predict-no for direction L in state State-A
  1013. In State-A moving L
  1014. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  1015. predict error 0
  1016. dir: dir isL
  1017. \-/|136: O: O272 (predict-no)
  1018. I see 1 and I'm going to do: predict-no
  1019. ENV: Agent did: predict-no for direction L in state State-A
  1020. In State-A moving L
  1021. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  1022. predict error 0
  1023. dir: dir isU
  1024. \-137: O: O274 (predict-no)
  1025. I see 1 and I'm going to do: predict-no
  1026. ENV: Agent did: predict-no for direction U in state State-A
  1027. In State-A moving U
  1028. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  1029. predict error 0
  1030. dir: dir isR
  1031. /|\138: O: O275 (predict-yes)
  1032. I see 1 and I'm going to do: predict-yes
  1033. ENV: Agent did: predict-yes for direction R in state State-A
  1034. In State-A moving R
  1035. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  1036. predict error 0
  1037. dir: dir isU
  1038. -/|\139: O: O278 (predict-no)
  1039. I see 1 and I'm going to do: predict-no
  1040. ENV: Agent did: predict-no for direction U in state State-B
  1041. In State-B moving U
  1042. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  1043. predict error 0
  1044. dir: dir isR
  1045. -/140: O: O279 (predict-yes)
  1046. I see 1 and I'm going to do: predict-yes
  1047. ENV: Agent did: predict-yes for direction R in state State-B
  1048. In State-B moving R
  1049. ENV: (next state, see, prediction correct?) = (State-B, 0, False)
  1050. predict error 1
  1051. dir: dir isU
  1052. |\141: O: O282 (predict-no)
  1053. I see 0 and I'm going to do: predict-no
  1054. ENV: Agent did: predict-no for direction U in state State-B
  1055. In State-B moving U
  1056. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  1057. predict error 0
  1058. dir: dir isR
  1059. -142: O: O283 (predict-yes)
  1060. I see 1 and I'm going to do: predict-yes
  1061. ENV: Agent did: predict-yes for direction R in state State-B
  1062. In State-B moving R
  1063. ENV: (next state, see, prediction correct?) = (State-B, 0, False)
  1064. predict error 1
  1065. dir: dir isU
  1066. /|\143: O: O286 (predict-no)
  1067. I see 0 and I'm going to do: predict-no
  1068. ENV: Agent did: predict-no for direction U in state State-B
  1069. In State-B moving U
  1070. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  1071. predict error 0
  1072. dir: dir isU
  1073. -/144: O: O288 (predict-no)
  1074. I see 1 and I'm going to do: predict-no
  1075. ENV: Agent did: predict-no for direction U in state State-B
  1076. In State-B moving U
  1077. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  1078. predict error 0
  1079. dir: dir isR
  1080. |\-145: O: O289 (predict-yes)
  1081. I see 1 and I'm going to do: predict-yes
  1082. ENV: Agent did: predict-yes for direction R in state State-B
  1083. In State-B moving R
  1084. ENV: (next state, see, prediction correct?) = (State-B, 0, False)
  1085. predict error 1
  1086. dir: dir isL
  1087. /|146: O: O291 (predict-yes)
  1088. I see 0 and I'm going to do: predict-yes
  1089. ENV: Agent did: predict-yes for direction L in state State-B
  1090. In State-B moving L
  1091. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  1092. predict error 0
  1093. dir: dir isL
  1094. \-/|147: O: O293 (predict-yes)
  1095. I see 1 and I'm going to do: predict-yes
  1096. ENV: Agent did: predict-yes for direction L in state State-A
  1097. In State-A moving L
  1098. ENV: (next state, see, prediction correct?) = (State-A, 0, False)
  1099. predict error 1
  1100. dir: dir isU
  1101. \-/|148: O: O296 (predict-no)
  1102. I see 0 and I'm going to do: predict-no
  1103. ENV: Agent did: predict-no for direction U in state State-A
  1104. In State-A moving U
  1105. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  1106. predict error 0
  1107. dir: dir isU
  1108. \-149: O: O298 (predict-no)
  1109. I see 1 and I'm going to do: predict-no
  1110. ENV: Agent did: predict-no for direction U in state State-A
  1111. In State-A moving U
  1112. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  1113. predict error 0
  1114. dir: dir isU
  1115. /|150: O: O300 (predict-no)
  1116. I see 1 and I'm going to do: predict-no
  1117. ENV: Agent did: predict-no for direction U in state State-A
  1118. In State-A moving U
  1119. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  1120. predict error 0
  1121. dir: dir isR
  1122. \-151: O: O301 (predict-yes)
  1123. I see 1 and I'm going to do: predict-yes
  1124. ENV: Agent did: predict-yes for direction R in state State-A
  1125. In State-A moving R
  1126. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  1127. predict error 0
  1128. dir: dir isR
  1129. /152: O: O303 (predict-yes)
  1130. I see 1 and I'm going to do: predict-yes
  1131. ENV: Agent did: predict-yes for direction R in state State-B
  1132. In State-B moving R
  1133. ENV: (next state, see, prediction correct?) = (State-B, 0, False)
  1134. predict error 1
  1135. dir: dir isU
  1136. |\-/153: O: O306 (predict-no)
  1137. I see 0 and I'm going to do: predict-no
  1138. ENV: Agent did: predict-no for direction U in state State-B
  1139. In State-B moving U
  1140. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  1141. predict error 0
  1142. dir: dir isR
  1143. |\-/154: O: O307 (predict-yes)
  1144. I see 1 and I'm going to do: predict-yes
  1145. ENV: Agent did: predict-yes for direction R in state State-B
  1146. In State-B moving R
  1147. ENV: (next state, see, prediction correct?) = (State-B, 0, False)
  1148. predict error 1
  1149. dir: dir isU
  1150. |\-/sleeping...
  1151. |155: O: O310 (predict-no)
  1152. I see 0 and I'm going to do: predict-no
  1153. ENV: Agent did: predict-no for direction U in state State-B
  1154. In State-B moving U
  1155. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  1156. predict error 0
  1157. dir: dir isR
  1158. \-/156: O: O312 (predict-no)
  1159. I see 1 and I'm going to do: predict-no
  1160. ENV: Agent did: predict-no for direction R in state State-B
  1161. In State-B moving R
  1162. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  1163. predict error 0
  1164. dir: dir isR
  1165. |\157: O: O314 (predict-no)
  1166. I see 1 and I'm going to do: predict-no
  1167. ENV: Agent did: predict-no for direction R in state State-B
  1168. In State-B moving R
  1169. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  1170. predict error 0
  1171. dir: dir isU
  1172. -/|158: O: O315 (predict-yes)
  1173. I see 1 and I'm going to do: predict-yes
  1174. ENV: Agent did: predict-yes for direction U in state State-B
  1175. In State-B moving U
  1176. ENV: (next state, see, prediction correct?) = (State-B, 0, False)
  1177. predict error 1
  1178. dir: dir isL
  1179. \-/159: O: O318 (predict-no)
  1180. I see 0 and I'm going to do: predict-no
  1181. ENV: Agent did: predict-no for direction L in state State-B
  1182. In State-B moving L
  1183. ENV: (next state, see, prediction correct?) = (State-A, 1, False)
  1184. predict error 1
  1185. dir: dir isU
  1186. |\-/160: O: O319 (predict-yes)
  1187. I see 0 and I'm going to do: predict-yes
  1188. ENV: Agent did: predict-yes for direction U in state State-A
  1189. In State-A moving U
  1190. ENV: (next state, see, prediction correct?) = (State-A, 0, False)
  1191. predict error 1
  1192. dir: dir isU
  1193. |\-161: O: O321 (predict-yes)
  1194. I see 0 and I'm going to do: predict-yes
  1195. ENV: Agent did: predict-yes for direction U in state State-A
  1196. In State-A moving U
  1197. ENV: (next state, see, prediction correct?) = (State-A, 0, False)
  1198. predict error 1
  1199. dir: dir isL
  1200. /162: O: O323 (predict-yes)
  1201. I see 0 and I'm going to do: predict-yes
  1202. ENV: Agent did: predict-yes for direction L in state State-A
  1203. In State-A moving L
  1204. ENV: (next state, see, prediction correct?) = (State-A, 0, False)
  1205. predict error 1
  1206. dir: dir isU
  1207. |\-163: O: O326 (predict-no)
  1208. I see 0 and I'm going to do: predict-no
  1209. ENV: Agent did: predict-no for direction U in state State-A
  1210. In State-A moving U
  1211. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  1212. predict error 0
  1213. dir: dir isU
  1214. /|\-164: O: O327 (predict-yes)
  1215. I see 1 and I'm going to do: predict-yes
  1216. ENV: Agent did: predict-yes for direction U in state State-A
  1217. In State-A moving U
  1218. ENV: (next state, see, prediction correct?) = (State-A, 0, False)
  1219. predict error 1
  1220. dir: dir isU
  1221. /|\165: O: O330 (predict-no)
  1222. I see 0 and I'm going to do: predict-no
  1223. ENV: Agent did: predict-no for direction U in state State-A
  1224. In State-A moving U
  1225. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  1226. predict error 0
  1227. dir: dir isL
  1228. -/166: O: O332 (predict-no)
  1229. I see 1 and I'm going to do: predict-no
  1230. ENV: Agent did: predict-no for direction L in state State-A
  1231. In State-A moving L
  1232. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  1233. predict error 0
  1234. dir: dir isU
  1235. |\167: O: O334 (predict-no)
  1236. I see 1 and I'm going to do: predict-no
  1237. ENV: Agent did: predict-no for direction U in state State-A
  1238. In State-A moving U
  1239. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  1240. predict error 0
  1241. dir: dir isL
  1242. -/|168: O: O336 (predict-no)
  1243. I see 1 and I'm going to do: predict-no
  1244. ENV: Agent did: predict-no for direction L in state State-A
  1245. In State-A moving L
  1246. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  1247. predict error 0
  1248. dir: dir isU
  1249. \-/169: O: O338 (predict-no)
  1250. I see 1 and I'm going to do: predict-no
  1251. ENV: Agent did: predict-no for direction U in state State-A
  1252. In State-A moving U
  1253. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  1254. predict error 0
  1255. dir: dir isU
  1256. |\-170: O: O340 (predict-no)
  1257. I see 1 and I'm going to do: predict-no
  1258. ENV: Agent did: predict-no for direction U in state State-A
  1259. In State-A moving U
  1260. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  1261. predict error 0
  1262. dir: dir isL
  1263. /|\-171: O: O342 (predict-no)
  1264. I see 1 and I'm going to do: predict-no
  1265. ENV: Agent did: predict-no for direction L in state State-A
  1266. In State-A moving L
  1267. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  1268. predict error 0
  1269. dir: dir isL
  1270. /172: O: O344 (predict-no)
  1271. I see 1 and I'm going to do: predict-no
  1272. ENV: Agent did: predict-no for direction L in state State-A
  1273. In State-A moving L
  1274. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  1275. predict error 0
  1276. dir: dir isR
  1277. |\173: O: O345 (predict-yes)
  1278. I see 1 and I'm going to do: predict-yes
  1279. ENV: Agent did: predict-yes for direction R in state State-A
  1280. In State-A moving R
  1281. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  1282. predict error 0
  1283. dir: dir isR
  1284. -/174: O: O348 (predict-no)
  1285. I see 1 and I'm going to do: predict-no
  1286. ENV: Agent did: predict-no for direction R in state State-B
  1287. In State-B moving R
  1288. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  1289. predict error 0
  1290. dir: dir isU
  1291. |\-175: O: O350 (predict-no)
  1292. I see 1 and I'm going to do: predict-no
  1293. ENV: Agent did: predict-no for direction U in state State-B
  1294. In State-B moving U
  1295. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  1296. predict error 0
  1297. dir: dir isU
  1298. /|176: O: O352 (predict-no)
  1299. I see 1 and I'm going to do: predict-no
  1300. ENV: Agent did: predict-no for direction U in state State-B
  1301. In State-B moving U
  1302. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  1303. predict error 0
  1304. dir: dir isL
  1305. \-/177: O: O353 (predict-yes)
  1306. I see 1 and I'm going to do: predict-yes
  1307. ENV: Agent did: predict-yes for direction L in state State-B
  1308. In State-B moving L
  1309. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  1310. predict error 0
  1311. dir: dir isL
  1312. |\178: O: O356 (predict-no)
  1313. I see 1 and I'm going to do: predict-no
  1314. ENV: Agent did: predict-no for direction L in state State-A
  1315. In State-A moving L
  1316. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  1317. predict error 0
  1318. dir: dir isU
  1319. -/|179: O: O358 (predict-no)
  1320. I see 1 and I'm going to do: predict-no
  1321. ENV: Agent did: predict-no for direction U in state State-A
  1322. In State-A moving U
  1323. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  1324. predict error 0
  1325. dir: dir isL
  1326. \-/180: O: O360 (predict-no)
  1327. I see 1 and I'm going to do: predict-no
  1328. ENV: Agent did: predict-no for direction L in state State-A
  1329. In State-A moving L
  1330. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  1331. predict error 0
  1332. dir: dir isU
  1333. |\-181: O: O362 (predict-no)
  1334. I see 1 and I'm going to do: predict-no
  1335. ENV: Agent did: predict-no for direction U in state State-A
  1336. In State-A moving U
  1337. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  1338. predict error 0
  1339. dir: dir isL
  1340. /182: O: O364 (predict-no)
  1341. I see 1 and I'm going to do: predict-no
  1342. ENV: Agent did: predict-no for direction L in state State-A
  1343. In State-A moving L
  1344. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  1345. predict error 0
  1346. dir: dir isU
  1347. |\-183: O: O366 (predict-no)
  1348. I see 1 and I'm going to do: predict-no
  1349. ENV: Agent did: predict-no for direction U in state State-A
  1350. In State-A moving U
  1351. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  1352. predict error 0
  1353. dir: dir isU
  1354. /|184: O: O368 (predict-no)
  1355. I see 1 and I'm going to do: predict-no
  1356. ENV: Agent did: predict-no for direction U in state State-A
  1357. In State-A moving U
  1358. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  1359. predict error 0
  1360. dir: dir isU
  1361. \-/185: O: O370 (predict-no)
  1362. I see 1 and I'm going to do: predict-no
  1363. ENV: Agent did: predict-no for direction U in state State-A
  1364. In State-A moving U
  1365. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  1366. predict error 0
  1367. dir: dir isR
  1368. |\186: O: O371 (predict-yes)
  1369. I see 1 and I'm going to do: predict-yes
  1370. ENV: Agent did: predict-yes for direction R in state State-A
  1371. In State-A moving R
  1372. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  1373. predict error 0
  1374. dir: dir isU
  1375. -/|187: O: O374 (predict-no)
  1376. I see 1 and I'm going to do: predict-no
  1377. ENV: Agent did: predict-no for direction U in state State-B
  1378. In State-B moving U
  1379. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  1380. predict error 0
  1381. dir: dir isL
  1382. \-188: O: O375 (predict-yes)
  1383. I see 1 and I'm going to do: predict-yes
  1384. ENV: Agent did: predict-yes for direction L in state State-B
  1385. In State-B moving L
  1386. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  1387. predict error 0
  1388. dir: dir isU
  1389. /|\189: O: O378 (predict-no)
  1390. I see 1 and I'm going to do: predict-no
  1391. ENV: Agent did: predict-no for direction U in state State-A
  1392. In State-A moving U
  1393. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  1394. predict error 0
  1395. dir: dir isL
  1396. -/|190: O: O380 (predict-no)
  1397. I see 1 and I'm going to do: predict-no
  1398. ENV: Agent did: predict-no for direction L in state State-A
  1399. In State-A moving L
  1400. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  1401. predict error 0
  1402. dir: dir isU
  1403. \-191: O: O381 (predict-yes)
  1404. I see 1 and I'm going to do: predict-yes
  1405. ENV: Agent did: predict-yes for direction U in state State-A
  1406. In State-A moving U
  1407. ENV: (next state, see, prediction correct?) = (State-A, 0, False)
  1408. predict error 1
  1409. dir: dir isU
  1410. /192: O: O384 (predict-no)
  1411. I see 0 and I'm going to do: predict-no
  1412. ENV: Agent did: predict-no for direction U in state State-A
  1413. In State-A moving U
  1414. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  1415. predict error 0
  1416. dir: dir isR
  1417. |\193: O: O385 (predict-yes)
  1418. I see 1 and I'm going to do: predict-yes
  1419. ENV: Agent did: predict-yes for direction R in state State-A
  1420. In State-A moving R
  1421. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  1422. predict error 0
  1423. dir: dir isR
  1424. -/|194: O: O387 (predict-yes)
  1425. I see 1 and I'm going to do: predict-yes
  1426. ENV: Agent did: predict-yes for direction R in state State-B
  1427. In State-B moving R
  1428. ENV: (next state, see, prediction correct?) = (State-B, 0, False)
  1429. predict error 1
  1430. dir: dir isL
  1431. \-/|sleeping...
  1432. \195: O: O390 (predict-no)
  1433. I see 0 and I'm going to do: predict-no
  1434. ENV: Agent did: predict-no for direction L in state State-B
  1435. In State-B moving L
  1436. ENV: (next state, see, prediction correct?) = (State-A, 1, False)
  1437. predict error 1
  1438. dir: dir isL
  1439. -/|\196: O: O392 (predict-no)
  1440. I see 0 and I'm going to do: predict-no
  1441. ENV: Agent did: predict-no for direction L in state State-A
  1442. In State-A moving L
  1443. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  1444. predict error 0
  1445. dir: dir isR
  1446. -/|197: O: O394 (predict-no)
  1447. I see 1 and I'm going to do: predict-no
  1448. ENV: Agent did: predict-no for direction R in state State-A
  1449. In State-A moving R
  1450. ENV: (next state, see, prediction correct?) = (State-B, 1, False)
  1451. predict error 1
  1452. dir: dir isR
  1453. \-/198: O: O396 (predict-no)
  1454. I see 0 and I'm going to do: predict-no
  1455. ENV: Agent did: predict-no for direction R in state State-B
  1456. In State-B moving R
  1457. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  1458. predict error 0
  1459. dir: dir isU
  1460. |\-199: O: O398 (predict-no)
  1461. I see 1 and I'm going to do: predict-no
  1462. ENV: Agent did: predict-no for direction U in state State-B
  1463. In State-B moving U
  1464. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  1465. predict error 0
  1466. dir: dir isR
  1467. /|\200: O: O400 (predict-no)
  1468. I see 1 and I'm going to do: predict-no
  1469. ENV: Agent did: predict-no for direction R in state State-B
  1470. In State-B moving R
  1471. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  1472. predict error 0
  1473. dir: dir isL
  1474. -/|201: O: O401 (predict-yes)
  1475. I see 1 and I'm going to do: predict-yes
  1476. ENV: Agent did: predict-yes for direction L in state State-B
  1477. In State-B moving L
  1478. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  1479. predict error 0
  1480. dir: dir isR
  1481. \-202: O: O403 (predict-yes)
  1482. I see 1 and I'm going to do: predict-yes
  1483. ENV: Agent did: predict-yes for direction R in state State-A
  1484. In State-A moving R
  1485. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  1486. predict error 0
  1487. dir: dir isU
  1488. /|\203: O: O406 (predict-no)
  1489. I see 1 and I'm going to do: predict-no
  1490. ENV: Agent did: predict-no for direction U in state State-B
  1491. In State-B moving U
  1492. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  1493. predict error 0
  1494. dir: dir isR
  1495. -/|204: O: O408 (predict-no)
  1496. I see 1 and I'm going to do: predict-no
  1497. ENV: Agent did: predict-no for direction R in state State-B
  1498. In State-B moving R
  1499. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  1500. predict error 0
  1501. dir: dir isL
  1502. \-205: O: O409 (predict-yes)
  1503. I see 1 and I'm going to do: predict-yes
  1504. ENV: Agent did: predict-yes for direction L in state State-B
  1505. In State-B moving L
  1506. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  1507. predict error 0
  1508. dir: dir isU
  1509. /|\-206: O: O412 (predict-no)
  1510. I see 1 and I'm going to do: predict-no
  1511. ENV: Agent did: predict-no for direction U in state State-A
  1512. In State-A moving U
  1513. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  1514. predict error 0
  1515. dir: dir isU
  1516. /|\207: O: O414 (predict-no)
  1517. I see 1 and I'm going to do: predict-no
  1518. ENV: Agent did: predict-no for direction U in state State-A
  1519. In State-A moving U
  1520. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  1521. predict error 0
  1522. dir: dir isL
  1523. -208: O: O416 (predict-no)
  1524. I see 1 and I'm going to do: predict-no
  1525. ENV: Agent did: predict-no for direction L in state State-A
  1526. In State-A moving L
  1527. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  1528. predict error 0
  1529. dir: dir isR
  1530. /|\209: O: O417 (predict-yes)
  1531. I see 1 and I'm going to do: predict-yes
  1532. ENV: Agent did: predict-yes for direction R in state State-A
  1533. In State-A moving R
  1534. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  1535. predict error 0
  1536. dir: dir isR
  1537. -/|210: O: O420 (predict-no)
  1538. I see 1 and I'm going to do: predict-no
  1539. ENV: Agent did: predict-no for direction R in state State-B
  1540. In State-B moving R
  1541. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  1542. predict error 0
  1543. dir: dir isU
  1544. \-/211: O: O422 (predict-no)
  1545. I see 1 and I'm going to do: predict-no
  1546. ENV: Agent did: predict-no for direction U in state State-B
  1547. In State-B moving U
  1548. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  1549. predict error 0
  1550. dir: dir isL
  1551. |212: O: O423 (predict-yes)
  1552. I see 1 and I'm going to do: predict-yes
  1553. ENV: Agent did: predict-yes for direction L in state State-B
  1554. In State-B moving L
  1555. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  1556. predict error 0
  1557. dir: dir isL
  1558. \-/213: O: O426 (predict-no)
  1559. I see 1 and I'm going to do: predict-no
  1560. ENV: Agent did: predict-no for direction L in state State-A
  1561. In State-A moving L
  1562. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  1563. predict error 0
  1564. dir: dir isR
  1565. |\-214: O: O428 (predict-no)
  1566. I see 1 and I'm going to do: predict-no
  1567. ENV: Agent did: predict-no for direction R in state State-A
  1568. In State-A moving R
  1569. ENV: (next state, see, prediction correct?) = (State-B, 1, False)
  1570. predict error 1
  1571. dir: dir isU
  1572. /|\215: O: O430 (predict-no)
  1573. I see 0 and I'm going to do: predict-no
  1574. ENV: Agent did: predict-no for direction U in state State-B
  1575. In State-B moving U
  1576. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  1577. predict error 0
  1578. dir: dir isL
  1579. -/216: O: O431 (predict-yes)
  1580. I see 1 and I'm going to do: predict-yes
  1581. ENV: Agent did: predict-yes for direction L in state State-B
  1582. In State-B moving L
  1583. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  1584. predict error 0
  1585. dir: dir isL
  1586. |\-217: O: O434 (predict-no)
  1587. I see 1 and I'm going to do: predict-no
  1588. ENV: Agent did: predict-no for direction L in state State-A
  1589. In State-A moving L
  1590. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  1591. predict error 0
  1592. dir: dir isR
  1593. /|\218: O: O435 (predict-yes)
  1594. I see 1 and I'm going to do: predict-yes
  1595. ENV: Agent did: predict-yes for direction R in state State-A
  1596. In State-A moving R
  1597. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  1598. predict error 0
  1599. dir: dir isU
  1600. -/|219: O: O438 (predict-no)
  1601. I see 1 and I'm going to do: predict-no
  1602. ENV: Agent did: predict-no for direction U in state State-B
  1603. In State-B moving U
  1604. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  1605. predict error 0
  1606. dir: dir isR
  1607. \-/220: O: O440 (predict-no)
  1608. I see 1 and I'm going to do: predict-no
  1609. ENV: Agent did: predict-no for direction R in state State-B
  1610. In State-B moving R
  1611. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  1612. predict error 0
  1613. dir: dir isR
  1614. |\221: O: O442 (predict-no)
  1615. I see 1 and I'm going to do: predict-no
  1616. ENV: Agent did: predict-no for direction R in state State-B
  1617. In State-B moving R
  1618. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  1619. predict error 0
  1620. dir: dir isU
  1621. -222: O: O444 (predict-no)
  1622. I see 1 and I'm going to do: predict-no
  1623. ENV: Agent did: predict-no for direction U in state State-B
  1624. In State-B moving U
  1625. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  1626. predict error 0
  1627. dir: dir isU
  1628. /|\223: O: O446 (predict-no)
  1629. I see 1 and I'm going to do: predict-no
  1630. ENV: Agent did: predict-no for direction U in state State-B
  1631. In State-B moving U
  1632. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  1633. predict error 0
  1634. dir: dir isL
  1635. -/224: O: O447 (predict-yes)
  1636. I see 1 and I'm going to do: predict-yes
  1637. ENV: Agent did: predict-yes for direction L in state State-B
  1638. In State-B moving L
  1639. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  1640. predict error 0
  1641. dir: dir isU
  1642. |225: O: O450 (predict-no)
  1643. I see 1 and I'm going to do: predict-no
  1644. ENV: Agent did: predict-no for direction U in state State-A
  1645. In State-A moving U
  1646. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  1647. predict error 0
  1648. dir: dir isL
  1649. \-226: O: O452 (predict-no)
  1650. I see 1 and I'm going to do: predict-no
  1651. ENV: Agent did: predict-no for direction L in state State-A
  1652. In State-A moving L
  1653. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  1654. predict error 0
  1655. dir: dir isL
  1656. /|\227: O: O454 (predict-no)
  1657. I see 1 and I'm going to do: predict-no
  1658. ENV: Agent did: predict-no for direction L in state State-A
  1659. In State-A moving L
  1660. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  1661. predict error 0
  1662. dir: dir isU
  1663. -/|228: O: O456 (predict-no)
  1664. I see 1 and I'm going to do: predict-no
  1665. ENV: Agent did: predict-no for direction U in state State-A
  1666. In State-A moving U
  1667. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  1668. predict error 0
  1669. dir: dir isR
  1670. \-229: O: O457 (predict-yes)
  1671. I see 1 and I'm going to do: predict-yes
  1672. ENV: Agent did: predict-yes for direction R in state State-A
  1673. In State-A moving R
  1674. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  1675. predict error 0
  1676. dir: dir isU
  1677. /|\230: O: O460 (predict-no)
  1678. I see 1 and I'm going to do: predict-no
  1679. ENV: Agent did: predict-no for direction U in state State-B
  1680. In State-B moving U
  1681. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  1682. predict error 0
  1683. dir: dir isL
  1684. -/|\231: O: O461 (predict-yes)
  1685. I see 1 and I'm going to do: predict-yes
  1686. ENV: Agent did: predict-yes for direction L in state State-B
  1687. In State-B moving L
  1688. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  1689. predict error 0
  1690. dir: dir isU
  1691. -232: O: O463 (predict-yes)
  1692. I see 1 and I'm going to do: predict-yes
  1693. ENV: Agent did: predict-yes for direction U in state State-A
  1694. In State-A moving U
  1695. ENV: (next state, see, prediction correct?) = (State-A, 0, False)
  1696. predict error 1
  1697. dir: dir isL
  1698. /|\233: O: O466 (predict-no)
  1699. I see 0 and I'm going to do: predict-no
  1700. ENV: Agent did: predict-no for direction L in state State-A
  1701. In State-A moving L
  1702. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  1703. predict error 0
  1704. dir: dir isL
  1705. -/|234: O: O468 (predict-no)
  1706. I see 1 and I'm going to do: predict-no
  1707. ENV: Agent did: predict-no for direction L in state State-A
  1708. In State-A moving L
  1709. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  1710. predict error 0
  1711. dir: dir isR
  1712. \-/|235: O: O469 (predict-yes)
  1713. I see 1 and I'm going to do: predict-yes
  1714. ENV: Agent did: predict-yes for direction R in state State-A
  1715. In State-A moving R
  1716. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  1717. predict error 0
  1718. dir: dir isR
  1719. \-/236: O: O472 (predict-no)
  1720. I see 1 and I'm going to do: predict-no
  1721. ENV: Agent did: predict-no for direction R in state State-B
  1722. In State-B moving R
  1723. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  1724. predict error 0
  1725. dir: dir isR
  1726. |\-/237: O: O474 (predict-no)
  1727. I see 1 and I'm going to do: predict-no
  1728. ENV: Agent did: predict-no for direction R in state State-B
  1729. In State-B moving R
  1730. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  1731. predict error 0
  1732. dir: dir isU
  1733. |\-238: O: O475 (predict-yes)
  1734. I see 1 and I'm going to do: predict-yes
  1735. ENV: Agent did: predict-yes for direction U in state State-B
  1736. In State-B moving U
  1737. ENV: (next state, see, prediction correct?) = (State-B, 0, False)
  1738. predict error 1
  1739. dir: dir isU
  1740. /|\-239: O: O477 (predict-yes)
  1741. I see 0 and I'm going to do: predict-yes
  1742. ENV: Agent did: predict-yes for direction U in state State-B
  1743. In State-B moving U
  1744. ENV: (next state, see, prediction correct?) = (State-B, 0, False)
  1745. predict error 1
  1746. dir: dir isL
  1747. /|\240: O: O479 (predict-yes)
  1748. I see 0 and I'm going to do: predict-yes
  1749. ENV: Agent did: predict-yes for direction L in state State-B
  1750. In State-B moving L
  1751. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  1752. predict error 0
  1753. dir: dir isL
  1754. -/241: O: O482 (predict-no)
  1755. I see 1 and I'm going to do: predict-no
  1756. ENV: Agent did: predict-no for direction L in state State-A
  1757. In State-A moving L
  1758. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  1759. predict error 0
  1760. dir: dir isR
  1761. |242: O: O483 (predict-yes)
  1762. I see 1 and I'm going to do: predict-yes
  1763. ENV: Agent did: predict-yes for direction R in state State-A
  1764. In State-A moving R
  1765. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  1766. predict error 0
  1767. dir: dir isR
  1768. \-/243: O: O485 (predict-yes)
  1769. I see 1 and I'm going to do: predict-yes
  1770. ENV: Agent did: predict-yes for direction R in state State-B
  1771. In State-B moving R
  1772. ENV: (next state, see, prediction correct?) = (State-B, 0, False)
  1773. predict error 1
  1774. dir: dir isU
  1775. |\244: O: O488 (predict-no)
  1776. I see 0 and I'm going to do: predict-no
  1777. ENV: Agent did: predict-no for direction U in state State-B
  1778. In State-B moving U
  1779. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  1780. predict error 0
  1781. dir: dir isR
  1782. -/|\245: O: O490 (predict-no)
  1783. I see 1 and I'm going to do: predict-no
  1784. ENV: Agent did: predict-no for direction R in state State-B
  1785. In State-B moving R
  1786. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  1787. predict error 0
  1788. dir: dir isL
  1789. -/|246: O: O491 (predict-yes)
  1790. I see 1 and I'm going to do: predict-yes
  1791. ENV: Agent did: predict-yes for direction L in state State-B
  1792. In State-B moving L
  1793. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  1794. predict error 0
  1795. dir: dir isL
  1796. \-/|247: O: O494 (predict-no)
  1797. I see 1 and I'm going to do: predict-no
  1798. ENV: Agent did: predict-no for direction L in state State-A
  1799. In State-A moving L
  1800. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  1801. predict error 0
  1802. dir: dir isU
  1803. \-248: O: O496 (predict-no)
  1804. I see 1 and I'm going to do: predict-no
  1805. ENV: Agent did: predict-no for direction U in state State-A
  1806. In State-A moving U
  1807. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  1808. predict error 0
  1809. dir: dir isR
  1810. /|249: O: O497 (predict-yes)
  1811. I see 1 and I'm going to do: predict-yes
  1812. ENV: Agent did: predict-yes for direction R in state State-A
  1813. In State-A moving R
  1814. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  1815. predict error 0
  1816. dir: dir isU
  1817. \-/250: O: O500 (predict-no)
  1818. I see 1 and I'm going to do: predict-no
  1819. ENV: Agent did: predict-no for direction U in state State-B
  1820. In State-B moving U
  1821. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  1822. predict error 0
  1823. dir: dir isU
  1824. |\-/251: O: O502 (predict-no)
  1825. I see 1 and I'm going to do: predict-no
  1826. ENV: Agent did: predict-no for direction U in state State-B
  1827. In State-B moving U
  1828. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  1829. predict error 0
  1830. dir: dir isR
  1831. |252: O: O504 (predict-no)
  1832. I see 1 and I'm going to do: predict-no
  1833. ENV: Agent did: predict-no for direction R in state State-B
  1834. In State-B moving R
  1835. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  1836. predict error 0
  1837. dir: dir isU
  1838. \-/253: O: O506 (predict-no)
  1839. I see 1 and I'm going to do: predict-no
  1840. ENV: Agent did: predict-no for direction U in state State-B
  1841. In State-B moving U
  1842. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  1843. predict error 0
  1844. dir: dir isR
  1845. |\-254: O: O508 (predict-no)
  1846. I see 1 and I'm going to do: predict-no
  1847. ENV: Agent did: predict-no for direction R in state State-B
  1848. In State-B moving R
  1849. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  1850. predict error 0
  1851. dir: dir isL
  1852. /|\-255: O: O509 (predict-yes)
  1853. I see 1 and I'm going to do: predict-yes
  1854. ENV: Agent did: predict-yes for direction L in state State-B
  1855. In State-B moving L
  1856. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  1857. predict error 0
  1858. dir: dir isU
  1859. /|\256: O: O512 (predict-no)
  1860. I see 1 and I'm going to do: predict-no
  1861. ENV: Agent did: predict-no for direction U in state State-A
  1862. In State-A moving U
  1863. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  1864. predict error 0
  1865. dir: dir isR
  1866. -/|257: O: O513 (predict-yes)
  1867. I see 1 and I'm going to do: predict-yes
  1868. ENV: Agent did: predict-yes for direction R in state State-A
  1869. In State-A moving R
  1870. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  1871. predict error 0
  1872. dir: dir isU
  1873. \-/|258: O: O516 (predict-no)
  1874. I see 1 and I'm going to do: predict-no
  1875. ENV: Agent did: predict-no for direction U in state State-B
  1876. In State-B moving U
  1877. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  1878. predict error 0
  1879. dir: dir isL
  1880. \-/259: O: O517 (predict-yes)
  1881. I see 1 and I'm going to do: predict-yes
  1882. ENV: Agent did: predict-yes for direction L in state State-B
  1883. In State-B moving L
  1884. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  1885. predict error 0
  1886. dir: dir isU
  1887. |\-260: O: O520 (predict-no)
  1888. I see 1 and I'm going to do: predict-no
  1889. ENV: Agent did: predict-no for direction U in state State-A
  1890. In State-A moving U
  1891. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  1892. predict error 0
  1893. dir: dir isU
  1894. /|\261: O: O522 (predict-no)
  1895. I see 1 and I'm going to do: predict-no
  1896. ENV: Agent did: predict-no for direction U in state State-A
  1897. In State-A moving U
  1898. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  1899. predict error 0
  1900. dir: dir isR
  1901. -262: O: O523 (predict-yes)
  1902. I see 1 and I'm going to do: predict-yes
  1903. ENV: Agent did: predict-yes for direction R in state State-A
  1904. In State-A moving R
  1905. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  1906. predict error 0
  1907. dir: dir isR
  1908. /|263: O: O526 (predict-no)
  1909. I see 1 and I'm going to do: predict-no
  1910. ENV: Agent did: predict-no for direction R in state State-B
  1911. In State-B moving R
  1912. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  1913. predict error 0
  1914. dir: dir isL
  1915. \-/264: O: O527 (predict-yes)
  1916. I see 1 and I'm going to do: predict-yes
  1917. ENV: Agent did: predict-yes for direction L in state State-B
  1918. In State-B moving L
  1919. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  1920. predict error 0
  1921. dir: dir isU
  1922. |\-/265: O: O530 (predict-no)
  1923. I see 1 and I'm going to do: predict-no
  1924. ENV: Agent did: predict-no for direction U in state State-A
  1925. In State-A moving U
  1926. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  1927. predict error 0
  1928. dir: dir isR
  1929. |\-266: O: O531 (predict-yes)
  1930. I see 1 and I'm going to do: predict-yes
  1931. ENV: Agent did: predict-yes for direction R in state State-A
  1932. In State-A moving R
  1933. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  1934. predict error 0
  1935. dir: dir isR
  1936. /267: O: O534 (predict-no)
  1937. I see 1 and I'm going to do: predict-no
  1938. ENV: Agent did: predict-no for direction R in state State-B
  1939. In State-B moving R
  1940. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  1941. predict error 0
  1942. dir: dir isL
  1943. |268: O: O535 (predict-yes)
  1944. I see 1 and I'm going to do: predict-yes
  1945. ENV: Agent did: predict-yes for direction L in state State-B
  1946. In State-B moving L
  1947. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  1948. predict error 0
  1949. dir: dir isL
  1950. \-/|269: O: O538 (predict-no)
  1951. I see 1 and I'm going to do: predict-no
  1952. ENV: Agent did: predict-no for direction L in state State-A
  1953. In State-A moving L
  1954. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  1955. predict error 0
  1956. dir: dir isL
  1957. \-/270: O: O540 (predict-no)
  1958. I see 1 and I'm going to do: predict-no
  1959. ENV: Agent did: predict-no for direction L in state State-A
  1960. In State-A moving L
  1961. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  1962. predict error 0
  1963. dir: dir isU
  1964. |\271: O: O542 (predict-no)
  1965. I see 1 and I'm going to do: predict-no
  1966. ENV: Agent did: predict-no for direction U in state State-A
  1967. In State-A moving U
  1968. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  1969. predict error 0
  1970. dir: dir isL
  1971. -272: O: O543 (predict-yes)
  1972. I see 1 and I'm going to do: predict-yes
  1973. ENV: Agent did: predict-yes for direction L in state State-A
  1974. In State-A moving L
  1975. ENV: (next state, see, prediction correct?) = (State-A, 0, False)
  1976. predict error 1
  1977. dir: dir isU
  1978. /|\273: O: O546 (predict-no)
  1979. I see 0 and I'm going to do: predict-no
  1980. ENV: Agent did: predict-no for direction U in state State-A
  1981. In State-A moving U
  1982. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  1983. predict error 0
  1984. dir: dir isR
  1985. -/|274: O: O547 (predict-yes)
  1986. I see 1 and I'm going to do: predict-yes
  1987. ENV: Agent did: predict-yes for direction R in state State-A
  1988. In State-A moving R
  1989. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  1990. predict error 0
  1991. dir: dir isR
  1992. \-/275: O: O550 (predict-no)
  1993. I see 1 and I'm going to do: predict-no
  1994. ENV: Agent did: predict-no for direction R in state State-B
  1995. In State-B moving R
  1996. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  1997. predict error 0
  1998. dir: dir isR
  1999. |\276: O: O552 (predict-no)
  2000. I see 1 and I'm going to do: predict-no
  2001. ENV: Agent did: predict-no for direction R in state State-B
  2002. In State-B moving R
  2003. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2004. predict error 0
  2005. dir: dir isR
  2006. -/|277: O: O554 (predict-no)
  2007. I see 1 and I'm going to do: predict-no
  2008. ENV: Agent did: predict-no for direction R in state State-B
  2009. In State-B moving R
  2010. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2011. predict error 0
  2012. dir: dir isL
  2013. \-/278: O: O555 (predict-yes)
  2014. I see 1 and I'm going to do: predict-yes
  2015. ENV: Agent did: predict-yes for direction L in state State-B
  2016. In State-B moving L
  2017. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  2018. predict error 0
  2019. dir: dir isR
  2020. |\-279: O: O557 (predict-yes)
  2021. I see 1 and I'm going to do: predict-yes
  2022. ENV: Agent did: predict-yes for direction R in state State-A
  2023. In State-A moving R
  2024. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  2025. predict error 0
  2026. dir: dir isU
  2027. /|\280: O: O560 (predict-no)
  2028. I see 1 and I'm going to do: predict-no
  2029. ENV: Agent did: predict-no for direction U in state State-B
  2030. In State-B moving U
  2031. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2032. predict error 0
  2033. dir: dir isL
  2034. -/|281: O: O561 (predict-yes)
  2035. I see 1 and I'm going to do: predict-yes
  2036. ENV: Agent did: predict-yes for direction L in state State-B
  2037. In State-B moving L
  2038. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  2039. predict error 0
  2040. dir: dir isR
  2041. \282: O: O564 (predict-no)
  2042. I see 1 and I'm going to do: predict-no
  2043. ENV: Agent did: predict-no for direction R in state State-A
  2044. In State-A moving R
  2045. ENV: (next state, see, prediction correct?) = (State-B, 1, False)
  2046. predict error 1
  2047. dir: dir isL
  2048. -/|283: O: O565 (predict-yes)
  2049. I see 0 and I'm going to do: predict-yes
  2050. ENV: Agent did: predict-yes for direction L in state State-B
  2051. In State-B moving L
  2052. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  2053. predict error 0
  2054. dir: dir isL
  2055. \-/284: O: O568 (predict-no)
  2056. I see 1 and I'm going to do: predict-no
  2057. ENV: Agent did: predict-no for direction L in state State-A
  2058. In State-A moving L
  2059. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  2060. predict error 0
  2061. dir: dir isL
  2062. |\285: O: O570 (predict-no)
  2063. I see 1 and I'm going to do: predict-no
  2064. ENV: Agent did: predict-no for direction L in state State-A
  2065. In State-A moving L
  2066. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  2067. predict error 0
  2068. dir: dir isL
  2069. -/|286: O: O572 (predict-no)
  2070. I see 1 and I'm going to do: predict-no
  2071. ENV: Agent did: predict-no for direction L in state State-A
  2072. In State-A moving L
  2073. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  2074. predict error 0
  2075. dir: dir isU
  2076. \-/287: O: O574 (predict-no)
  2077. I see 1 and I'm going to do: predict-no
  2078. ENV: Agent did: predict-no for direction U in state State-A
  2079. In State-A moving U
  2080. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  2081. predict error 0
  2082. dir: dir isU
  2083. |\288: O: O576 (predict-no)
  2084. I see 1 and I'm going to do: predict-no
  2085. ENV: Agent did: predict-no for direction U in state State-A
  2086. In State-A moving U
  2087. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  2088. predict error 0
  2089. dir: dir isU
  2090. -/|289: O: O577 (predict-yes)
  2091. I see 1 and I'm going to do: predict-yes
  2092. ENV: Agent did: predict-yes for direction U in state State-A
  2093. In State-A moving U
  2094. ENV: (next state, see, prediction correct?) = (State-A, 0, False)
  2095. predict error 1
  2096. dir: dir isU
  2097. \290: O: O579 (predict-yes)
  2098. I see 0 and I'm going to do: predict-yes
  2099. ENV: Agent did: predict-yes for direction U in state State-A
  2100. In State-A moving U
  2101. ENV: (next state, see, prediction correct?) = (State-A, 0, False)
  2102. predict error 1
  2103. dir: dir isU
  2104. -/291: O: O582 (predict-no)
  2105. I see 0 and I'm going to do: predict-no
  2106. ENV: Agent did: predict-no for direction U in state State-A
  2107. In State-A moving U
  2108. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  2109. predict error 0
  2110. dir: dir isL
  2111. |292: O: O584 (predict-no)
  2112. I see 1 and I'm going to do: predict-no
  2113. ENV: Agent did: predict-no for direction L in state State-A
  2114. In State-A moving L
  2115. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  2116. predict error 0
  2117. dir: dir isR
  2118. \-/293: O: O585 (predict-yes)
  2119. I see 1 and I'm going to do: predict-yes
  2120. ENV: Agent did: predict-yes for direction R in state State-A
  2121. In State-A moving R
  2122. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  2123. predict error 0
  2124. dir: dir isR
  2125. |\-294: O: O588 (predict-no)
  2126. I see 1 and I'm going to do: predict-no
  2127. ENV: Agent did: predict-no for direction R in state State-B
  2128. In State-B moving R
  2129. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2130. predict error 0
  2131. dir: dir isR
  2132. /|295: O: O590 (predict-no)
  2133. I see 1 and I'm going to do: predict-no
  2134. ENV: Agent did: predict-no for direction R in state State-B
  2135. In State-B moving R
  2136. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2137. predict error 0
  2138. dir: dir isU
  2139. \-296: O: O592 (predict-no)
  2140. I see 1 and I'm going to do: predict-no
  2141. ENV: Agent did: predict-no for direction U in state State-B
  2142. In State-B moving U
  2143. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2144. predict error 0
  2145. dir: dir isU
  2146. /|297: O: O594 (predict-no)
  2147. I see 1 and I'm going to do: predict-no
  2148. ENV: Agent did: predict-no for direction U in state State-B
  2149. In State-B moving U
  2150. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2151. predict error 0
  2152. dir: dir isU
  2153. \-/298: O: O596 (predict-no)
  2154. I see 1 and I'm going to do: predict-no
  2155. ENV: Agent did: predict-no for direction U in state State-B
  2156. In State-B moving U
  2157. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2158. predict error 0
  2159. dir: dir isL
  2160. |\-/299: O: O597 (predict-yes)
  2161. I see 1 and I'm going to do: predict-yes
  2162. ENV: Agent did: predict-yes for direction L in state State-B
  2163. In State-B moving L
  2164. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  2165. predict error 0
  2166. dir: dir isR
  2167. |\-300: O: O599 (predict-yes)
  2168. I see 1 and I'm going to do: predict-yes
  2169. ENV: Agent did: predict-yes for direction R in state State-A
  2170. In State-A moving R
  2171. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  2172. predict error 0
  2173. dir: dir isU
  2174. /|\-/|301: O: O602 (predict-no)
  2175. I see 1 and I'm going to do: predict-no
  2176. ENV: Agent did: predict-no for direction U in state State-B
  2177. In State-B moving U
  2178. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2179. predict error 0
  2180. dir: dir isU
  2181. \302: O: O604 (predict-no)
  2182. I see 1 and I'm going to do: predict-no
  2183. ENV: Agent did: predict-no for direction U in state State-B
  2184. In State-B moving U
  2185. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2186. predict error 0
  2187. dir: dir isR
  2188. -303: O: O606 (predict-no)
  2189. I see 1 and I'm going to do: predict-no
  2190. ENV: Agent did: predict-no for direction R in state State-B
  2191. In State-B moving R
  2192. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2193. predict error 0
  2194. dir: dir isU
  2195. /|\304: O: O608 (predict-no)
  2196. I see 1 and I'm going to do: predict-no
  2197. ENV: Agent did: predict-no for direction U in state State-B
  2198. In State-B moving U
  2199. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2200. predict error 0
  2201. dir: dir isL
  2202. -/|305: O: O609 (predict-yes)
  2203. I see 1 and I'm going to do: predict-yes
  2204. ENV: Agent did: predict-yes for direction L in state State-B
  2205. In State-B moving L
  2206. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  2207. predict error 0
  2208. dir: dir isU
  2209. \-/|306: O: O612 (predict-no)
  2210. I see 1 and I'm going to do: predict-no
  2211. ENV: Agent did: predict-no for direction U in state State-A
  2212. In State-A moving U
  2213. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  2214. predict error 0
  2215. dir: dir isR
  2216. \-/307: O: O613 (predict-yes)
  2217. I see 1 and I'm going to do: predict-yes
  2218. ENV: Agent did: predict-yes for direction R in state State-A
  2219. In State-A moving R
  2220. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  2221. predict error 0
  2222. dir: dir isR
  2223. |\-308: O: O616 (predict-no)
  2224. I see 1 and I'm going to do: predict-no
  2225. ENV: Agent did: predict-no for direction R in state State-B
  2226. In State-B moving R
  2227. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2228. predict error 0
  2229. dir: dir isU
  2230. /|\309: O: O618 (predict-no)
  2231. I see 1 and I'm going to do: predict-no
  2232. ENV: Agent did: predict-no for direction U in state State-B
  2233. In State-B moving U
  2234. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2235. predict error 0
  2236. dir: dir isU
  2237. -/|310: O: O620 (predict-no)
  2238. I see 1 and I'm going to do: predict-no
  2239. ENV: Agent did: predict-no for direction U in state State-B
  2240. In State-B moving U
  2241. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2242. predict error 0
  2243. dir: dir isL
  2244. \-311: O: O621 (predict-yes)
  2245. I see 1 and I'm going to do: predict-yes
  2246. ENV: Agent did: predict-yes for direction L in state State-B
  2247. In State-B moving L
  2248. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  2249. predict error 0
  2250. dir: dir isL
  2251. /312: O: O624 (predict-no)
  2252. I see 1 and I'm going to do: predict-no
  2253. ENV: Agent did: predict-no for direction L in state State-A
  2254. In State-A moving L
  2255. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  2256. predict error 0
  2257. dir: dir isL
  2258. |\313: O: O626 (predict-no)
  2259. I see 1 and I'm going to do: predict-no
  2260. ENV: Agent did: predict-no for direction L in state State-A
  2261. In State-A moving L
  2262. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  2263. predict error 0
  2264. dir: dir isR
  2265. -/|314: O: O627 (predict-yes)
  2266. I see 1 and I'm going to do: predict-yes
  2267. ENV: Agent did: predict-yes for direction R in state State-A
  2268. In State-A moving R
  2269. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  2270. predict error 0
  2271. dir: dir isU
  2272. \-315: O: O630 (predict-no)
  2273. I see 1 and I'm going to do: predict-no
  2274. ENV: Agent did: predict-no for direction U in state State-B
  2275. In State-B moving U
  2276. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2277. predict error 0
  2278. dir: dir isU
  2279. /|\316: O: O632 (predict-no)
  2280. I see 1 and I'm going to do: predict-no
  2281. ENV: Agent did: predict-no for direction U in state State-B
  2282. In State-B moving U
  2283. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2284. predict error 0
  2285. dir: dir isR
  2286. -/|317: O: O634 (predict-no)
  2287. I see 1 and I'm going to do: predict-no
  2288. ENV: Agent did: predict-no for direction R in state State-B
  2289. In State-B moving R
  2290. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2291. predict error 0
  2292. dir: dir isR
  2293. \-/318: O: O636 (predict-no)
  2294. I see 1 and I'm going to do: predict-no
  2295. ENV: Agent did: predict-no for direction R in state State-B
  2296. In State-B moving R
  2297. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2298. predict error 0
  2299. dir: dir isU
  2300. |\-319: O: O638 (predict-no)
  2301. I see 1 and I'm going to do: predict-no
  2302. ENV: Agent did: predict-no for direction U in state State-B
  2303. In State-B moving U
  2304. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2305. predict error 0
  2306. dir: dir isL
  2307. /|320: O: O639 (predict-yes)
  2308. I see 1 and I'm going to do: predict-yes
  2309. ENV: Agent did: predict-yes for direction L in state State-B
  2310. In State-B moving L
  2311. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  2312. predict error 0
  2313. dir: dir isR
  2314. \-/|321: O: O641 (predict-yes)
  2315. I see 1 and I'm going to do: predict-yes
  2316. ENV: Agent did: predict-yes for direction R in state State-A
  2317. In State-A moving R
  2318. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  2319. predict error 0
  2320. dir: dir isL
  2321. \322: O: O643 (predict-yes)
  2322. I see 1 and I'm going to do: predict-yes
  2323. ENV: Agent did: predict-yes for direction L in state State-B
  2324. In State-B moving L
  2325. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  2326. predict error 0
  2327. dir: dir isL
  2328. -323: O: O646 (predict-no)
  2329. I see 1 and I'm going to do: predict-no
  2330. ENV: Agent did: predict-no for direction L in state State-A
  2331. In State-A moving L
  2332. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  2333. predict error 0
  2334. dir: dir isR
  2335. /|\324: O: O647 (predict-yes)
  2336. I see 1 and I'm going to do: predict-yes
  2337. ENV: Agent did: predict-yes for direction R in state State-A
  2338. In State-A moving R
  2339. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  2340. predict error 0
  2341. dir: dir isU
  2342. -/|325: O: O650 (predict-no)
  2343. I see 1 and I'm going to do: predict-no
  2344. ENV: Agent did: predict-no for direction U in state State-B
  2345. In State-B moving U
  2346. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2347. predict error 0
  2348. dir: dir isR
  2349. \-/326: O: O652 (predict-no)
  2350. I see 1 and I'm going to do: predict-no
  2351. ENV: Agent did: predict-no for direction R in state State-B
  2352. In State-B moving R
  2353. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2354. predict error 0
  2355. dir: dir isR
  2356. |\-/327: O: O653 (predict-yes)
  2357. I see 1 and I'm going to do: predict-yes
  2358. ENV: Agent did: predict-yes for direction R in state State-B
  2359. In State-B moving R
  2360. ENV: (next state, see, prediction correct?) = (State-B, 0, False)
  2361. predict error 1
  2362. dir: dir isU
  2363. |\-328: O: O656 (predict-no)
  2364. I see 0 and I'm going to do: predict-no
  2365. ENV: Agent did: predict-no for direction U in state State-B
  2366. In State-B moving U
  2367. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2368. predict error 0
  2369. dir: dir isR
  2370. /|\329: O: O658 (predict-no)
  2371. I see 1 and I'm going to do: predict-no
  2372. ENV: Agent did: predict-no for direction R in state State-B
  2373. In State-B moving R
  2374. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2375. predict error 0
  2376. dir: dir isL
  2377. -/330: O: O659 (predict-yes)
  2378. I see 1 and I'm going to do: predict-yes
  2379. ENV: Agent did: predict-yes for direction L in state State-B
  2380. In State-B moving L
  2381. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  2382. predict error 0
  2383. dir: dir isL
  2384. |\331: O: O662 (predict-no)
  2385. I see 1 and I'm going to do: predict-no
  2386. ENV: Agent did: predict-no for direction L in state State-A
  2387. In State-A moving L
  2388. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  2389. predict error 0
  2390. dir: dir isU
  2391. -332: O: O664 (predict-no)
  2392. I see 1 and I'm going to do: predict-no
  2393. ENV: Agent did: predict-no for direction U in state State-A
  2394. In State-A moving U
  2395. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  2396. predict error 0
  2397. dir: dir isU
  2398. /|\-333: O: O666 (predict-no)
  2399. I see 1 and I'm going to do: predict-no
  2400. ENV: Agent did: predict-no for direction U in state State-A
  2401. In State-A moving U
  2402. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  2403. predict error 0
  2404. dir: dir isU
  2405. /|\334: O: O668 (predict-no)
  2406. I see 1 and I'm going to do: predict-no
  2407. ENV: Agent did: predict-no for direction U in state State-A
  2408. In State-A moving U
  2409. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  2410. predict error 0
  2411. dir: dir isR
  2412. -/|335: O: O669 (predict-yes)
  2413. I see 1 and I'm going to do: predict-yes
  2414. ENV: Agent did: predict-yes for direction R in state State-A
  2415. In State-A moving R
  2416. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  2417. predict error 0
  2418. dir: dir isL
  2419. \-/336: O: O671 (predict-yes)
  2420. I see 1 and I'm going to do: predict-yes
  2421. ENV: Agent did: predict-yes for direction L in state State-B
  2422. In State-B moving L
  2423. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  2424. predict error 0
  2425. dir: dir isL
  2426. |\-/337: O: O674 (predict-no)
  2427. I see 1 and I'm going to do: predict-no
  2428. ENV: Agent did: predict-no for direction L in state State-A
  2429. In State-A moving L
  2430. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  2431. predict error 0
  2432. dir: dir isL
  2433. |\-338: O: O676 (predict-no)
  2434. I see 1 and I'm going to do: predict-no
  2435. ENV: Agent did: predict-no for direction L in state State-A
  2436. In State-A moving L
  2437. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  2438. predict error 0
  2439. dir: dir isL
  2440. /|\339: O: O678 (predict-no)
  2441. I see 1 and I'm going to do: predict-no
  2442. ENV: Agent did: predict-no for direction L in state State-A
  2443. In State-A moving L
  2444. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  2445. predict error 0
  2446. dir: dir isU
  2447. -/340: O: O680 (predict-no)
  2448. I see 1 and I'm going to do: predict-no
  2449. ENV: Agent did: predict-no for direction U in state State-A
  2450. In State-A moving U
  2451. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  2452. predict error 0
  2453. dir: dir isU
  2454. |\-/341: O: O682 (predict-no)
  2455. I see 1 and I'm going to do: predict-no
  2456. ENV: Agent did: predict-no for direction U in state State-A
  2457. In State-A moving U
  2458. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  2459. predict error 0
  2460. dir: dir isU
  2461. |342: O: O684 (predict-no)
  2462. I see 1 and I'm going to do: predict-no
  2463. ENV: Agent did: predict-no for direction U in state State-A
  2464. In State-A moving U
  2465. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  2466. predict error 0
  2467. dir: dir isL
  2468. \-/|343: O: O686 (predict-no)
  2469. I see 1 and I'm going to do: predict-no
  2470. ENV: Agent did: predict-no for direction L in state State-A
  2471. In State-A moving L
  2472. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  2473. predict error 0
  2474. dir: dir isL
  2475. \-/344: O: O688 (predict-no)
  2476. I see 1 and I'm going to do: predict-no
  2477. ENV: Agent did: predict-no for direction L in state State-A
  2478. In State-A moving L
  2479. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  2480. predict error 0
  2481. dir: dir isL
  2482. |\-/345: O: O690 (predict-no)
  2483. I see 1 and I'm going to do: predict-no
  2484. ENV: Agent did: predict-no for direction L in state State-A
  2485. In State-A moving L
  2486. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  2487. predict error 0
  2488. dir: dir isU
  2489. |\-346: O: O691 (predict-yes)
  2490. I see 1 and I'm going to do: predict-yes
  2491. ENV: Agent did: predict-yes for direction U in state State-A
  2492. In State-A moving U
  2493. ENV: (next state, see, prediction correct?) = (State-A, 0, False)
  2494. predict error 1
  2495. dir: dir isL
  2496. /|347: O: O694 (predict-no)
  2497. I see 0 and I'm going to do: predict-no
  2498. ENV: Agent did: predict-no for direction L in state State-A
  2499. In State-A moving L
  2500. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  2501. predict error 0
  2502. dir: dir isU
  2503. \-348: O: O696 (predict-no)
  2504. I see 1 and I'm going to do: predict-no
  2505. ENV: Agent did: predict-no for direction U in state State-A
  2506. In State-A moving U
  2507. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  2508. predict error 0
  2509. dir: dir isU
  2510. /|\-sleeping...
  2511. /349: O: O698 (predict-no)
  2512. I see 1 and I'm going to do: predict-no
  2513. ENV: Agent did: predict-no for direction U in state State-A
  2514. In State-A moving U
  2515. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  2516. predict error 0
  2517. dir: dir isR
  2518. |\-/350: O: O699 (predict-yes)
  2519. I see 1 and I'm going to do: predict-yes
  2520. ENV: Agent did: predict-yes for direction R in state State-A
  2521. In State-A moving R
  2522. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  2523. predict error 0
  2524. dir: dir isU
  2525. |\351: O: O702 (predict-no)
  2526. I see 1 and I'm going to do: predict-no
  2527. ENV: Agent did: predict-no for direction U in state State-B
  2528. In State-B moving U
  2529. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2530. predict error 0
  2531. dir: dir isL
  2532. -352: O: O703 (predict-yes)
  2533. I see 1 and I'm going to do: predict-yes
  2534. ENV: Agent did: predict-yes for direction L in state State-B
  2535. In State-B moving L
  2536. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  2537. predict error 0
  2538. dir: dir isR
  2539. /|353: O: O705 (predict-yes)
  2540. I see 1 and I'm going to do: predict-yes
  2541. ENV: Agent did: predict-yes for direction R in state State-A
  2542. In State-A moving R
  2543. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  2544. predict error 0
  2545. dir: dir isL
  2546. \-354: O: O707 (predict-yes)
  2547. I see 1 and I'm going to do: predict-yes
  2548. ENV: Agent did: predict-yes for direction L in state State-B
  2549. In State-B moving L
  2550. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  2551. predict error 0
  2552. dir: dir isL
  2553. /|\355: O: O710 (predict-no)
  2554. I see 1 and I'm going to do: predict-no
  2555. ENV: Agent did: predict-no for direction L in state State-A
  2556. In State-A moving L
  2557. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  2558. predict error 0
  2559. dir: dir isL
  2560. -/|\356: O: O712 (predict-no)
  2561. I see 1 and I'm going to do: predict-no
  2562. ENV: Agent did: predict-no for direction L in state State-A
  2563. In State-A moving L
  2564. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  2565. predict error 0
  2566. dir: dir isL
  2567. -/|\sleeping...
  2568. -357: O: O714 (predict-no)
  2569. I see 1 and I'm going to do: predict-no
  2570. ENV: Agent did: predict-no for direction L in state State-A
  2571. In State-A moving L
  2572. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  2573. predict error 0
  2574. dir: dir isL
  2575. /|\-358: O: O716 (predict-no)
  2576. I see 1 and I'm going to do: predict-no
  2577. ENV: Agent did: predict-no for direction L in state State-A
  2578. In State-A moving L
  2579. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  2580. predict error 0
  2581. dir: dir isL
  2582. /|\359: O: O718 (predict-no)
  2583. I see 1 and I'm going to do: predict-no
  2584. ENV: Agent did: predict-no for direction L in state State-A
  2585. In State-A moving L
  2586. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  2587. predict error 0
  2588. dir: dir isU
  2589. -/|\360: O: O720 (predict-no)
  2590. I see 1 and I'm going to do: predict-no
  2591. ENV: Agent did: predict-no for direction U in state State-A
  2592. In State-A moving U
  2593. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  2594. predict error 0
  2595. dir: dir isL
  2596. -/|361: O: O722 (predict-no)
  2597. I see 1 and I'm going to do: predict-no
  2598. ENV: Agent did: predict-no for direction L in state State-A
  2599. In State-A moving L
  2600. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  2601. predict error 0
  2602. dir: dir isU
  2603. \362: O: O724 (predict-no)
  2604. I see 1 and I'm going to do: predict-no
  2605. ENV: Agent did: predict-no for direction U in state State-A
  2606. In State-A moving U
  2607. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  2608. predict error 0
  2609. dir: dir isU
  2610. -/|363: O: O726 (predict-no)
  2611. I see 1 and I'm going to do: predict-no
  2612. ENV: Agent did: predict-no for direction U in state State-A
  2613. In State-A moving U
  2614. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  2615. predict error 0
  2616. dir: dir isU
  2617. \-364: O: O728 (predict-no)
  2618. I see 1 and I'm going to do: predict-no
  2619. ENV: Agent did: predict-no for direction U in state State-A
  2620. In State-A moving U
  2621. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  2622. predict error 0
  2623. dir: dir isR
  2624. /|\365: O: O729 (predict-yes)
  2625. I see 1 and I'm going to do: predict-yes
  2626. ENV: Agent did: predict-yes for direction R in state State-A
  2627. In State-A moving R
  2628. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  2629. predict error 0
  2630. dir: dir isU
  2631. -/|366: O: O732 (predict-no)
  2632. I see 1 and I'm going to do: predict-no
  2633. ENV: Agent did: predict-no for direction U in state State-B
  2634. In State-B moving U
  2635. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2636. predict error 0
  2637. dir: dir isU
  2638. \-/367: O: O734 (predict-no)
  2639. I see 1 and I'm going to do: predict-no
  2640. ENV: Agent did: predict-no for direction U in state State-B
  2641. In State-B moving U
  2642. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2643. predict error 0
  2644. dir: dir isU
  2645. |\-/368: O: O736 (predict-no)
  2646. I see 1 and I'm going to do: predict-no
  2647. ENV: Agent did: predict-no for direction U in state State-B
  2648. In State-B moving U
  2649. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2650. predict error 0
  2651. dir: dir isR
  2652. |\-369: O: O738 (predict-no)
  2653. I see 1 and I'm going to do: predict-no
  2654. ENV: Agent did: predict-no for direction R in state State-B
  2655. In State-B moving R
  2656. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2657. predict error 0
  2658. dir: dir isU
  2659. /|\370: O: O740 (predict-no)
  2660. I see 1 and I'm going to do: predict-no
  2661. ENV: Agent did: predict-no for direction U in state State-B
  2662. In State-B moving U
  2663. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2664. predict error 0
  2665. dir: dir isU
  2666. -/|371: O: O742 (predict-no)
  2667. I see 1 and I'm going to do: predict-no
  2668. ENV: Agent did: predict-no for direction U in state State-B
  2669. In State-B moving U
  2670. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2671. predict error 0
  2672. dir: dir isR
  2673. \372: O: O744 (predict-no)
  2674. I see 1 and I'm going to do: predict-no
  2675. ENV: Agent did: predict-no for direction R in state State-B
  2676. In State-B moving R
  2677. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2678. predict error 0
  2679. dir: dir isR
  2680. -/373: O: O746 (predict-no)
  2681. I see 1 and I'm going to do: predict-no
  2682. ENV: Agent did: predict-no for direction R in state State-B
  2683. In State-B moving R
  2684. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2685. predict error 0
  2686. dir: dir isL
  2687. |\-374: O: O747 (predict-yes)
  2688. I see 1 and I'm going to do: predict-yes
  2689. ENV: Agent did: predict-yes for direction L in state State-B
  2690. In State-B moving L
  2691. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  2692. predict error 0
  2693. dir: dir isU
  2694. /|\375: O: O750 (predict-no)
  2695. I see 1 and I'm going to do: predict-no
  2696. ENV: Agent did: predict-no for direction U in state State-A
  2697. In State-A moving U
  2698. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  2699. predict error 0
  2700. dir: dir isR
  2701. -/|376: O: O751 (predict-yes)
  2702. I see 1 and I'm going to do: predict-yes
  2703. ENV: Agent did: predict-yes for direction R in state State-A
  2704. In State-A moving R
  2705. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  2706. predict error 0
  2707. dir: dir isL
  2708. \-377: O: O753 (predict-yes)
  2709. I see 1 and I'm going to do: predict-yes
  2710. ENV: Agent did: predict-yes for direction L in state State-B
  2711. In State-B moving L
  2712. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  2713. predict error 0
  2714. dir: dir isL
  2715. /|\378: O: O756 (predict-no)
  2716. I see 1 and I'm going to do: predict-no
  2717. ENV: Agent did: predict-no for direction L in state State-A
  2718. In State-A moving L
  2719. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  2720. predict error 0
  2721. dir: dir isU
  2722. -/|\379: O: O758 (predict-no)
  2723. I see 1 and I'm going to do: predict-no
  2724. ENV: Agent did: predict-no for direction U in state State-A
  2725. In State-A moving U
  2726. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  2727. predict error 0
  2728. dir: dir isL
  2729. -/|380: O: O760 (predict-no)
  2730. I see 1 and I'm going to do: predict-no
  2731. ENV: Agent did: predict-no for direction L in state State-A
  2732. In State-A moving L
  2733. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  2734. predict error 0
  2735. dir: dir isR
  2736. \-381: O: O761 (predict-yes)
  2737. I see 1 and I'm going to do: predict-yes
  2738. ENV: Agent did: predict-yes for direction R in state State-A
  2739. In State-A moving R
  2740. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  2741. predict error 0
  2742. dir: dir isU
  2743. /382: O: O764 (predict-no)
  2744. I see 1 and I'm going to do: predict-no
  2745. ENV: Agent did: predict-no for direction U in state State-B
  2746. In State-B moving U
  2747. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2748. predict error 0
  2749. dir: dir isU
  2750. |\-383: O: O766 (predict-no)
  2751. I see 1 and I'm going to do: predict-no
  2752. ENV: Agent did: predict-no for direction U in state State-B
  2753. In State-B moving U
  2754. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2755. predict error 0
  2756. dir: dir isL
  2757. /|\-384: O: O767 (predict-yes)
  2758. I see 1 and I'm going to do: predict-yes
  2759. ENV: Agent did: predict-yes for direction L in state State-B
  2760. In State-B moving L
  2761. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  2762. predict error 0
  2763. dir: dir isR
  2764. /|\385: O: O769 (predict-yes)
  2765. I see 1 and I'm going to do: predict-yes
  2766. ENV: Agent did: predict-yes for direction R in state State-A
  2767. In State-A moving R
  2768. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  2769. predict error 0
  2770. dir: dir isR
  2771. -/|\386: O: O772 (predict-no)
  2772. I see 1 and I'm going to do: predict-no
  2773. ENV: Agent did: predict-no for direction R in state State-B
  2774. In State-B moving R
  2775. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2776. predict error 0
  2777. dir: dir isL
  2778. -/387: O: O773 (predict-yes)
  2779. I see 1 and I'm going to do: predict-yes
  2780. ENV: Agent did: predict-yes for direction L in state State-B
  2781. In State-B moving L
  2782. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  2783. predict error 0
  2784. dir: dir isU
  2785. |\-388: O: O776 (predict-no)
  2786. I see 1 and I'm going to do: predict-no
  2787. ENV: Agent did: predict-no for direction U in state State-A
  2788. In State-A moving U
  2789. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  2790. predict error 0
  2791. dir: dir isL
  2792. /|\389: O: O778 (predict-no)
  2793. I see 1 and I'm going to do: predict-no
  2794. ENV: Agent did: predict-no for direction L in state State-A
  2795. In State-A moving L
  2796. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  2797. predict error 0
  2798. dir: dir isU
  2799. -/|390: O: O780 (predict-no)
  2800. I see 1 and I'm going to do: predict-no
  2801. ENV: Agent did: predict-no for direction U in state State-A
  2802. In State-A moving U
  2803. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  2804. predict error 0
  2805. dir: dir isL
  2806. \-/|391: O: O782 (predict-no)
  2807. I see 1 and I'm going to do: predict-no
  2808. ENV: Agent did: predict-no for direction L in state State-A
  2809. In State-A moving L
  2810. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  2811. predict error 0
  2812. dir: dir isL
  2813. \392: O: O784 (predict-no)
  2814. I see 1 and I'm going to do: predict-no
  2815. ENV: Agent did: predict-no for direction L in state State-A
  2816. In State-A moving L
  2817. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  2818. predict error 0
  2819. dir: dir isU
  2820. -/|393: O: O786 (predict-no)
  2821. I see 1 and I'm going to do: predict-no
  2822. ENV: Agent did: predict-no for direction U in state State-A
  2823. In State-A moving U
  2824. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  2825. predict error 0
  2826. dir: dir isU
  2827. \-/|394: O: O787 (predict-yes)
  2828. I see 1 and I'm going to do: predict-yes
  2829. ENV: Agent did: predict-yes for direction U in state State-A
  2830. In State-A moving U
  2831. ENV: (next state, see, prediction correct?) = (State-A, 0, False)
  2832. predict error 1
  2833. dir: dir isL
  2834. \-/395: O: O790 (predict-no)
  2835. I see 0 and I'm going to do: predict-no
  2836. ENV: Agent did: predict-no for direction L in state State-A
  2837. In State-A moving L
  2838. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  2839. predict error 0
  2840. dir: dir isR
  2841. |\-396: O: O791 (predict-yes)
  2842. I see 1 and I'm going to do: predict-yes
  2843. ENV: Agent did: predict-yes for direction R in state State-A
  2844. In State-A moving R
  2845. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  2846. predict error 0
  2847. dir: dir isR
  2848. /|\397: O: O794 (predict-no)
  2849. I see 1 and I'm going to do: predict-no
  2850. ENV: Agent did: predict-no for direction R in state State-B
  2851. In State-B moving R
  2852. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2853. predict error 0
  2854. dir: dir isU
  2855. -/|398: O: O795 (predict-yes)
  2856. I see 1 and I'm going to do: predict-yes
  2857. ENV: Agent did: predict-yes for direction U in state State-B
  2858. In State-B moving U
  2859. ENV: (next state, see, prediction correct?) = (State-B, 0, False)
  2860. predict error 1
  2861. dir: dir isL
  2862. \-/399: O: O797 (predict-yes)
  2863. I see 0 and I'm going to do: predict-yes
  2864. ENV: Agent did: predict-yes for direction L in state State-B
  2865. In State-B moving L
  2866. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  2867. predict error 0
  2868. dir: dir isU
  2869. |\400: O: O800 (predict-no)
  2870. I see 1 and I'm going to do: predict-no
  2871. ENV: Agent did: predict-no for direction U in state State-A
  2872. In State-A moving U
  2873. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  2874. predict error 0
  2875. dir: dir isU
  2876. -/|\401: O: O802 (predict-no)
  2877. I see 1 and I'm going to do: predict-no
  2878. ENV: Agent did: predict-no for direction U in state State-A
  2879. In State-A moving U
  2880. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  2881. predict error 0
  2882. dir: dir isU
  2883. -402: O: O804 (predict-no)
  2884. I see 1 and I'm going to do: predict-no
  2885. ENV: Agent did: predict-no for direction U in state State-A
  2886. In State-A moving U
  2887. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  2888. predict error 0
  2889. dir: dir isU
  2890. /|\403: O: O806 (predict-no)
  2891. I see 1 and I'm going to do: predict-no
  2892. ENV: Agent did: predict-no for direction U in state State-A
  2893. In State-A moving U
  2894. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  2895. predict error 0
  2896. dir: dir isU
  2897. -/|404: O: O808 (predict-no)
  2898. I see 1 and I'm going to do: predict-no
  2899. ENV: Agent did: predict-no for direction U in state State-A
  2900. In State-A moving U
  2901. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  2902. predict error 0
  2903. dir: dir isR
  2904. \-/405: O: O809 (predict-yes)
  2905. I see 1 and I'm going to do: predict-yes
  2906. ENV: Agent did: predict-yes for direction R in state State-A
  2907. In State-A moving R
  2908. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  2909. predict error 0
  2910. dir: dir isU
  2911. |\-406: O: O812 (predict-no)
  2912. I see 1 and I'm going to do: predict-no
  2913. ENV: Agent did: predict-no for direction U in state State-B
  2914. In State-B moving U
  2915. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2916. predict error 0
  2917. dir: dir isU
  2918. /407: O: O814 (predict-no)
  2919. I see 1 and I'm going to do: predict-no
  2920. ENV: Agent did: predict-no for direction U in state State-B
  2921. In State-B moving U
  2922. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2923. predict error 0
  2924. dir: dir isR
  2925. |\-408: O: O816 (predict-no)
  2926. I see 1 and I'm going to do: predict-no
  2927. ENV: Agent did: predict-no for direction R in state State-B
  2928. In State-B moving R
  2929. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2930. predict error 0
  2931. dir: dir isL
  2932. /|\409: O: O817 (predict-yes)
  2933. I see 1 and I'm going to do: predict-yes
  2934. ENV: Agent did: predict-yes for direction L in state State-B
  2935. In State-B moving L
  2936. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  2937. predict error 0
  2938. dir: dir isR
  2939. -/410: O: O819 (predict-yes)
  2940. I see 1 and I'm going to do: predict-yes
  2941. ENV: Agent did: predict-yes for direction R in state State-A
  2942. In State-A moving R
  2943. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  2944. predict error 0
  2945. dir: dir isU
  2946. |\-411: O: O822 (predict-no)
  2947. I see 1 and I'm going to do: predict-no
  2948. ENV: Agent did: predict-no for direction U in state State-B
  2949. In State-B moving U
  2950. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2951. predict error 0
  2952. dir: dir isL
  2953. /412: O: O823 (predict-yes)
  2954. I see 1 and I'm going to do: predict-yes
  2955. ENV: Agent did: predict-yes for direction L in state State-B
  2956. In State-B moving L
  2957. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  2958. predict error 0
  2959. dir: dir isR
  2960. |\-413: O: O825 (predict-yes)
  2961. I see 1 and I'm going to do: predict-yes
  2962. ENV: Agent did: predict-yes for direction R in state State-A
  2963. In State-A moving R
  2964. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  2965. predict error 0
  2966. dir: dir isU
  2967. /|\414: O: O828 (predict-no)
  2968. I see 1 and I'm going to do: predict-no
  2969. ENV: Agent did: predict-no for direction U in state State-B
  2970. In State-B moving U
  2971. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2972. predict error 0
  2973. dir: dir isR
  2974. -/|415: O: O830 (predict-no)
  2975. I see 1 and I'm going to do: predict-no
  2976. ENV: Agent did: predict-no for direction R in state State-B
  2977. In State-B moving R
  2978. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2979. predict error 0
  2980. dir: dir isL
  2981. \-/416: O: O831 (predict-yes)
  2982. I see 1 and I'm going to do: predict-yes
  2983. ENV: Agent did: predict-yes for direction L in state State-B
  2984. In State-B moving L
  2985. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  2986. predict error 0
  2987. dir: dir isR
  2988. |\-417: O: O833 (predict-yes)
  2989. I see 1 and I'm going to do: predict-yes
  2990. ENV: Agent did: predict-yes for direction R in state State-A
  2991. In State-A moving R
  2992. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  2993. predict error 0
  2994. dir: dir isL
  2995. /|\418: O: O835 (predict-yes)
  2996. I see 1 and I'm going to do: predict-yes
  2997. ENV: Agent did: predict-yes for direction L in state State-B
  2998. In State-B moving L
  2999. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  3000. predict error 0
  3001. dir: dir isU
  3002. -/|419: O: O838 (predict-no)
  3003. I see 1 and I'm going to do: predict-no
  3004. ENV: Agent did: predict-no for direction U in state State-A
  3005. In State-A moving U
  3006. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3007. predict error 0
  3008. dir: dir isR
  3009. \-420: O: O839 (predict-yes)
  3010. I see 1 and I'm going to do: predict-yes
  3011. ENV: Agent did: predict-yes for direction R in state State-A
  3012. In State-A moving R
  3013. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  3014. predict error 0
  3015. dir: dir isL
  3016. /|\421: O: O841 (predict-yes)
  3017. I see 1 and I'm going to do: predict-yes
  3018. ENV: Agent did: predict-yes for direction L in state State-B
  3019. In State-B moving L
  3020. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  3021. predict error 0
  3022. dir: dir isU
  3023. -422: O: O844 (predict-no)
  3024. I see 1 and I'm going to do: predict-no
  3025. ENV: Agent did: predict-no for direction U in state State-A
  3026. In State-A moving U
  3027. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3028. predict error 0
  3029. dir: dir isR
  3030. /|\423: O: O846 (predict-no)
  3031. I see 1 and I'm going to do: predict-no
  3032. ENV: Agent did: predict-no for direction R in state State-A
  3033. In State-A moving R
  3034. ENV: (next state, see, prediction correct?) = (State-B, 1, False)
  3035. predict error 1
  3036. dir: dir isR
  3037. -/|\424: O: O848 (predict-no)
  3038. I see 0 and I'm going to do: predict-no
  3039. ENV: Agent did: predict-no for direction R in state State-B
  3040. In State-B moving R
  3041. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3042. predict error 0
  3043. dir: dir isU
  3044. -/|\425: O: O850 (predict-no)
  3045. I see 1 and I'm going to do: predict-no
  3046. ENV: Agent did: predict-no for direction U in state State-B
  3047. In State-B moving U
  3048. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3049. predict error 0
  3050. dir: dir isU
  3051. -/426: O: O852 (predict-no)
  3052. I see 1 and I'm going to do: predict-no
  3053. ENV: Agent did: predict-no for direction U in state State-B
  3054. In State-B moving U
  3055. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3056. predict error 0
  3057. dir: dir isU
  3058. |\-427: O: O854 (predict-no)
  3059. I see 1 and I'm going to do: predict-no
  3060. ENV: Agent did: predict-no for direction U in state State-B
  3061. In State-B moving U
  3062. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3063. predict error 0
  3064. dir: dir isU
  3065. /|\428: O: O856 (predict-no)
  3066. I see 1 and I'm going to do: predict-no
  3067. ENV: Agent did: predict-no for direction U in state State-B
  3068. In State-B moving U
  3069. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3070. predict error 0
  3071. dir: dir isR
  3072. -/|\429: O: O858 (predict-no)
  3073. I see 1 and I'm going to do: predict-no
  3074. ENV: Agent did: predict-no for direction R in state State-B
  3075. In State-B moving R
  3076. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3077. predict error 0
  3078. dir: dir isU
  3079. -/430: O: O860 (predict-no)
  3080. I see 1 and I'm going to do: predict-no
  3081. ENV: Agent did: predict-no for direction U in state State-B
  3082. In State-B moving U
  3083. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3084. predict error 0
  3085. dir: dir isR
  3086. |\431: O: O862 (predict-no)
  3087. I see 1 and I'm going to do: predict-no
  3088. ENV: Agent did: predict-no for direction R in state State-B
  3089. In State-B moving R
  3090. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3091. predict error 0
  3092. dir: dir isR
  3093. -432: O: O864 (predict-no)
  3094. I see 1 and I'm going to do: predict-no
  3095. ENV: Agent did: predict-no for direction R in state State-B
  3096. In State-B moving R
  3097. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3098. predict error 0
  3099. dir: dir isU
  3100. /|\-433: O: O866 (predict-no)
  3101. I see 1 and I'm going to do: predict-no
  3102. ENV: Agent did: predict-no for direction U in state State-B
  3103. In State-B moving U
  3104. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3105. predict error 0
  3106. dir: dir isR
  3107. /|\434: O: O868 (predict-no)
  3108. I see 1 and I'm going to do: predict-no
  3109. ENV: Agent did: predict-no for direction R in state State-B
  3110. In State-B moving R
  3111. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3112. predict error 0
  3113. dir: dir isL
  3114. -/|\435: O: O869 (predict-yes)
  3115. I see 1 and I'm going to do: predict-yes
  3116. ENV: Agent did: predict-yes for direction L in state State-B
  3117. In State-B moving L
  3118. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  3119. predict error 0
  3120. dir: dir isU
  3121. -/|436: O: O872 (predict-no)
  3122. I see 1 and I'm going to do: predict-no
  3123. ENV: Agent did: predict-no for direction U in state State-A
  3124. In State-A moving U
  3125. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3126. predict error 0
  3127. dir: dir isR
  3128. \-437: O: O873 (predict-yes)
  3129. I see 1 and I'm going to do: predict-yes
  3130. ENV: Agent did: predict-yes for direction R in state State-A
  3131. In State-A moving R
  3132. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  3133. predict error 0
  3134. dir: dir isR
  3135. /|\438: O: O876 (predict-no)
  3136. I see 1 and I'm going to do: predict-no
  3137. ENV: Agent did: predict-no for direction R in state State-B
  3138. In State-B moving R
  3139. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3140. predict error 0
  3141. dir: dir isR
  3142. -/|\439: O: O878 (predict-no)
  3143. I see 1 and I'm going to do: predict-no
  3144. ENV: Agent did: predict-no for direction R in state State-B
  3145. In State-B moving R
  3146. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3147. predict error 0
  3148. dir: dir isL
  3149. -/|\440: O: O879 (predict-yes)
  3150. I see 1 and I'm going to do: predict-yes
  3151. ENV: Agent did: predict-yes for direction L in state State-B
  3152. In State-B moving L
  3153. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  3154. predict error 0
  3155. dir: dir isL
  3156. -/|441: O: O882 (predict-no)
  3157. I see 1 and I'm going to do: predict-no
  3158. ENV: Agent did: predict-no for direction L in state State-A
  3159. In State-A moving L
  3160. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3161. predict error 0
  3162. dir: dir isL
  3163. \442: O: O884 (predict-no)
  3164. I see 1 and I'm going to do: predict-no
  3165. ENV: Agent did: predict-no for direction L in state State-A
  3166. In State-A moving L
  3167. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3168. predict error 0
  3169. dir: dir isU
  3170. -/443: O: O886 (predict-no)
  3171. I see 1 and I'm going to do: predict-no
  3172. ENV: Agent did: predict-no for direction U in state State-A
  3173. In State-A moving U
  3174. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3175. predict error 0
  3176. dir: dir isU
  3177. |\444: O: O888 (predict-no)
  3178. I see 1 and I'm going to do: predict-no
  3179. ENV: Agent did: predict-no for direction U in state State-A
  3180. In State-A moving U
  3181. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3182. predict error 0
  3183. dir: dir isU
  3184. -445: O: O890 (predict-no)
  3185. I see 1 and I'm going to do: predict-no
  3186. ENV: Agent did: predict-no for direction U in state State-A
  3187. In State-A moving U
  3188. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3189. predict error 0
  3190. dir: dir isL
  3191. /|\446: O: O892 (predict-no)
  3192. I see 1 and I'm going to do: predict-no
  3193. ENV: Agent did: predict-no for direction L in state State-A
  3194. In State-A moving L
  3195. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3196. predict error 0
  3197. dir: dir isU
  3198. -/447: O: O894 (predict-no)
  3199. I see 1 and I'm going to do: predict-no
  3200. ENV: Agent did: predict-no for direction U in state State-A
  3201. In State-A moving U
  3202. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3203. predict error 0
  3204. dir: dir isU
  3205. |\-448: O: O896 (predict-no)
  3206. I see 1 and I'm going to do: predict-no
  3207. ENV: Agent did: predict-no for direction U in state State-A
  3208. In State-A moving U
  3209. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3210. predict error 0
  3211. dir: dir isR
  3212. /|\449: O: O897 (predict-yes)
  3213. I see 1 and I'm going to do: predict-yes
  3214. ENV: Agent did: predict-yes for direction R in state State-A
  3215. In State-A moving R
  3216. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  3217. predict error 0
  3218. dir: dir isL
  3219. -/|\450: O: O899 (predict-yes)
  3220. I see 1 and I'm going to do: predict-yes
  3221. ENV: Agent did: predict-yes for direction L in state State-B
  3222. In State-B moving L
  3223. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  3224. predict error 0
  3225. dir: dir isU
  3226. -/|451: O: O902 (predict-no)
  3227. I see 1 and I'm going to do: predict-no
  3228. ENV: Agent did: predict-no for direction U in state State-A
  3229. In State-A moving U
  3230. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3231. predict error 0
  3232. dir: dir isR
  3233. \452: O: O903 (predict-yes)
  3234. I see 1 and I'm going to do: predict-yes
  3235. ENV: Agent did: predict-yes for direction R in state State-A
  3236. In State-A moving R
  3237. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  3238. predict error 0
  3239. dir: dir isR
  3240. -/453: O: O906 (predict-no)
  3241. I see 1 and I'm going to do: predict-no
  3242. ENV: Agent did: predict-no for direction R in state State-B
  3243. In State-B moving R
  3244. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3245. predict error 0
  3246. dir: dir isL
  3247. |\-454: O: O907 (predict-yes)
  3248. I see 1 and I'm going to do: predict-yes
  3249. ENV: Agent did: predict-yes for direction L in state State-B
  3250. In State-B moving L
  3251. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  3252. predict error 0
  3253. dir: dir isU
  3254. /|\-455: O: O910 (predict-no)
  3255. I see 1 and I'm going to do: predict-no
  3256. ENV: Agent did: predict-no for direction U in state State-A
  3257. In State-A moving U
  3258. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3259. predict error 0
  3260. dir: dir isL
  3261. /|456: O: O912 (predict-no)
  3262. I see 1 and I'm going to do: predict-no
  3263. ENV: Agent did: predict-no for direction L in state State-A
  3264. In State-A moving L
  3265. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3266. predict error 0
  3267. dir: dir isR
  3268. \-457: O: O913 (predict-yes)
  3269. I see 1 and I'm going to do: predict-yes
  3270. ENV: Agent did: predict-yes for direction R in state State-A
  3271. In State-A moving R
  3272. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  3273. predict error 0
  3274. dir: dir isL
  3275. /|458: O: O915 (predict-yes)
  3276. I see 1 and I'm going to do: predict-yes
  3277. ENV: Agent did: predict-yes for direction L in state State-B
  3278. In State-B moving L
  3279. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  3280. predict error 0
  3281. dir: dir isR
  3282. \-/459: O: O917 (predict-yes)
  3283. I see 1 and I'm going to do: predict-yes
  3284. ENV: Agent did: predict-yes for direction R in state State-A
  3285. In State-A moving R
  3286. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  3287. predict error 0
  3288. dir: dir isU
  3289. |\460: O: O920 (predict-no)
  3290. I see 1 and I'm going to do: predict-no
  3291. ENV: Agent did: predict-no for direction U in state State-B
  3292. In State-B moving U
  3293. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3294. predict error 0
  3295. dir: dir isU
  3296. -/461: O: O921 (predict-yes)
  3297. I see 1 and I'm going to do: predict-yes
  3298. ENV: Agent did: predict-yes for direction U in state State-B
  3299. In State-B moving U
  3300. ENV: (next state, see, prediction correct?) = (State-B, 0, False)
  3301. predict error 1
  3302. dir: dir isU
  3303. |462: O: O924 (predict-no)
  3304. I see 0 and I'm going to do: predict-no
  3305. ENV: Agent did: predict-no for direction U in state State-B
  3306. In State-B moving U
  3307. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3308. predict error 0
  3309. dir: dir isL
  3310. \-/463: O: O925 (predict-yes)
  3311. I see 1 and I'm going to do: predict-yes
  3312. ENV: Agent did: predict-yes for direction L in state State-B
  3313. In State-B moving L
  3314. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  3315. predict error 0
  3316. dir: dir isR
  3317. |\-464: O: O927 (predict-yes)
  3318. I see 1 and I'm going to do: predict-yes
  3319. ENV: Agent did: predict-yes for direction R in state State-A
  3320. In State-A moving R
  3321. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  3322. predict error 0
  3323. dir: dir isR
  3324. /|465: O: O930 (predict-no)
  3325. I see 1 and I'm going to do: predict-no
  3326. ENV: Agent did: predict-no for direction R in state State-B
  3327. In State-B moving R
  3328. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3329. predict error 0
  3330. dir: dir isL
  3331. \-466: O: O931 (predict-yes)
  3332. I see 1 and I'm going to do: predict-yes
  3333. ENV: Agent did: predict-yes for direction L in state State-B
  3334. In State-B moving L
  3335. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  3336. predict error 0
  3337. dir: dir isR
  3338. /|\467: O: O933 (predict-yes)
  3339. I see 1 and I'm going to do: predict-yes
  3340. ENV: Agent did: predict-yes for direction R in state State-A
  3341. In State-A moving R
  3342. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  3343. predict error 0
  3344. dir: dir isU
  3345. -/|468: O: O936 (predict-no)
  3346. I see 1 and I'm going to do: predict-no
  3347. ENV: Agent did: predict-no for direction U in state State-B
  3348. In State-B moving U
  3349. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3350. predict error 0
  3351. dir: dir isU
  3352. \-469: O: O938 (predict-no)
  3353. I see 1 and I'm going to do: predict-no
  3354. ENV: Agent did: predict-no for direction U in state State-B
  3355. In State-B moving U
  3356. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3357. predict error 0
  3358. dir: dir isU
  3359. /|470: O: O940 (predict-no)
  3360. I see 1 and I'm going to do: predict-no
  3361. ENV: Agent did: predict-no for direction U in state State-B
  3362. In State-B moving U
  3363. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3364. predict error 0
  3365. dir: dir isL
  3366. \-471: O: O941 (predict-yes)
  3367. I see 1 and I'm going to do: predict-yes
  3368. ENV: Agent did: predict-yes for direction L in state State-B
  3369. In State-B moving L
  3370. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  3371. predict error 0
  3372. dir: dir isU
  3373. /472: O: O944 (predict-no)
  3374. I see 1 and I'm going to do: predict-no
  3375. ENV: Agent did: predict-no for direction U in state State-A
  3376. In State-A moving U
  3377. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3378. predict error 0
  3379. dir: dir isU
  3380. |\473: O: O946 (predict-no)
  3381. I see 1 and I'm going to do: predict-no
  3382. ENV: Agent did: predict-no for direction U in state State-A
  3383. In State-A moving U
  3384. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3385. predict error 0
  3386. dir: dir isU
  3387. -/|474: O: O948 (predict-no)
  3388. I see 1 and I'm going to do: predict-no
  3389. ENV: Agent did: predict-no for direction U in state State-A
  3390. In State-A moving U
  3391. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3392. predict error 0
  3393. dir: dir isR
  3394. \-/|475: O: O949 (predict-yes)
  3395. I see 1 and I'm going to do: predict-yes
  3396. ENV: Agent did: predict-yes for direction R in state State-A
  3397. In State-A moving R
  3398. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  3399. predict error 0
  3400. dir: dir isL
  3401. \-/476: O: O951 (predict-yes)
  3402. I see 1 and I'm going to do: predict-yes
  3403. ENV: Agent did: predict-yes for direction L in state State-B
  3404. In State-B moving L
  3405. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  3406. predict error 0
  3407. dir: dir isL
  3408. |\477: O: O954 (predict-no)
  3409. I see 1 and I'm going to do: predict-no
  3410. ENV: Agent did: predict-no for direction L in state State-A
  3411. In State-A moving L
  3412. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3413. predict error 0
  3414. dir: dir isU
  3415. -/|478: O: O956 (predict-no)
  3416. I see 1 and I'm going to do: predict-no
  3417. ENV: Agent did: predict-no for direction U in state State-A
  3418. In State-A moving U
  3419. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3420. predict error 0
  3421. dir: dir isU
  3422. \-/479: O: O958 (predict-no)
  3423. I see 1 and I'm going to do: predict-no
  3424. ENV: Agent did: predict-no for direction U in state State-A
  3425. In State-A moving U
  3426. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3427. predict error 0
  3428. dir: dir isL
  3429. |\-480: O: O960 (predict-no)
  3430. I see 1 and I'm going to do: predict-no
  3431. ENV: Agent did: predict-no for direction L in state State-A
  3432. In State-A moving L
  3433. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3434. predict error 0
  3435. dir: dir isU
  3436. /|\481: O: O962 (predict-no)
  3437. I see 1 and I'm going to do: predict-no
  3438. ENV: Agent did: predict-no for direction U in state State-A
  3439. In State-A moving U
  3440. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3441. predict error 0
  3442. dir: dir isR
  3443. -482: O: O963 (predict-yes)
  3444. I see 1 and I'm going to do: predict-yes
  3445. ENV: Agent did: predict-yes for direction R in state State-A
  3446. In State-A moving R
  3447. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  3448. predict error 0
  3449. dir: dir isR
  3450. /|\-sleeping...
  3451. /483: O: O966 (predict-no)
  3452. I see 1 and I'm going to do: predict-no
  3453. ENV: Agent did: predict-no for direction R in state State-B
  3454. In State-B moving R
  3455. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3456. predict error 0
  3457. dir: dir isU
  3458. |\-484: O: O968 (predict-no)
  3459. I see 1 and I'm going to do: predict-no
  3460. ENV: Agent did: predict-no for direction U in state State-B
  3461. In State-B moving U
  3462. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3463. predict error 0
  3464. dir: dir isL
  3465. /|485: O: O969 (predict-yes)
  3466. I see 1 and I'm going to do: predict-yes
  3467. ENV: Agent did: predict-yes for direction L in state State-B
  3468. In State-B moving L
  3469. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  3470. predict error 0
  3471. dir: dir isR
  3472. \-/486: O: O971 (predict-yes)
  3473. I see 1 and I'm going to do: predict-yes
  3474. ENV: Agent did: predict-yes for direction R in state State-A
  3475. In State-A moving R
  3476. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  3477. predict error 0
  3478. dir: dir isL
  3479. |\-487: O: O973 (predict-yes)
  3480. I see 1 and I'm going to do: predict-yes
  3481. ENV: Agent did: predict-yes for direction L in state State-B
  3482. In State-B moving L
  3483. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  3484. predict error 0
  3485. dir: dir isR
  3486. /|\488: O: O975 (predict-yes)
  3487. I see 1 and I'm going to do: predict-yes
  3488. ENV: Agent did: predict-yes for direction R in state State-A
  3489. In State-A moving R
  3490. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  3491. predict error 0
  3492. dir: dir isL
  3493. -/|489: O: O977 (predict-yes)
  3494. I see 1 and I'm going to do: predict-yes
  3495. ENV: Agent did: predict-yes for direction L in state State-B
  3496. In State-B moving L
  3497. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  3498. predict error 0
  3499. dir: dir isL
  3500. \-490: O: O980 (predict-no)
  3501. I see 1 and I'm going to do: predict-no
  3502. ENV: Agent did: predict-no for direction L in state State-A
  3503. In State-A moving L
  3504. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3505. predict error 0
  3506. dir: dir isL
  3507. /|491: O: O982 (predict-no)
  3508. I see 1 and I'm going to do: predict-no
  3509. ENV: Agent did: predict-no for direction L in state State-A
  3510. In State-A moving L
  3511. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3512. predict error 0
  3513. dir: dir isU
  3514. \492: O: O984 (predict-no)
  3515. I see 1 and I'm going to do: predict-no
  3516. ENV: Agent did: predict-no for direction U in state State-A
  3517. In State-A moving U
  3518. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3519. predict error 0
  3520. dir: dir isL
  3521. -/493: O: O986 (predict-no)
  3522. I see 1 and I'm going to do: predict-no
  3523. ENV: Agent did: predict-no for direction L in state State-A
  3524. In State-A moving L
  3525. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3526. predict error 0
  3527. dir: dir isU
  3528. |\-494: O: O988 (predict-no)
  3529. I see 1 and I'm going to do: predict-no
  3530. ENV: Agent did: predict-no for direction U in state State-A
  3531. In State-A moving U
  3532. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3533. predict error 0
  3534. dir: dir isL
  3535. /|\495: O: O990 (predict-no)
  3536. I see 1 and I'm going to do: predict-no
  3537. ENV: Agent did: predict-no for direction L in state State-A
  3538. In State-A moving L
  3539. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3540. predict error 0
  3541. dir: dir isU
  3542. -/|496: O: O992 (predict-no)
  3543. I see 1 and I'm going to do: predict-no
  3544. ENV: Agent did: predict-no for direction U in state State-A
  3545. In State-A moving U
  3546. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3547. predict error 0
  3548. dir: dir isL
  3549. \-/|497: O: O994 (predict-no)
  3550. I see 1 and I'm going to do: predict-no
  3551. ENV: Agent did: predict-no for direction L in state State-A
  3552. In State-A moving L
  3553. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3554. predict error 0
  3555. dir: dir isL
  3556. \-498: O: O996 (predict-no)
  3557. I see 1 and I'm going to do: predict-no
  3558. ENV: Agent did: predict-no for direction L in state State-A
  3559. In State-A moving L
  3560. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3561. predict error 0
  3562. dir: dir isL
  3563. /|\499: O: O998 (predict-no)
  3564. I see 1 and I'm going to do: predict-no
  3565. ENV: Agent did: predict-no for direction L in state State-A
  3566. In State-A moving L
  3567. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3568. predict error 0
  3569. dir: dir isU
  3570. -/|500: O: O1000 (predict-no)
  3571. I see 1 and I'm going to do: predict-no
  3572. ENV: Agent did: predict-no for direction U in state State-A
  3573. In State-A moving U
  3574. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3575. predict error 0
  3576. dir: dir isU
  3577. \-/|\-501: O: O1002 (predict-no)
  3578. I see 1 and I'm going to do: predict-no
  3579. ENV: Agent did: predict-no for direction U in state State-A
  3580. In State-A moving U
  3581. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3582. predict error 0
  3583. dir: dir isU
  3584. /502: O: O1004 (predict-no)
  3585. I see 1 and I'm going to do: predict-no
  3586. ENV: Agent did: predict-no for direction U in state State-A
  3587. In State-A moving U
  3588. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3589. predict error 0
  3590. dir: dir isR
  3591. |\-503: O: O1005 (predict-yes)
  3592. I see 1 and I'm going to do: predict-yes
  3593. ENV: Agent did: predict-yes for direction R in state State-A
  3594. In State-A moving R
  3595. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  3596. predict error 0
  3597. dir: dir isL
  3598. /|\504: O: O1007 (predict-yes)
  3599. I see 1 and I'm going to do: predict-yes
  3600. ENV: Agent did: predict-yes for direction L in state State-B
  3601. In State-B moving L
  3602. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  3603. predict error 0
  3604. dir: dir isR
  3605. -505: O: O1009 (predict-yes)
  3606. I see 1 and I'm going to do: predict-yes
  3607. ENV: Agent did: predict-yes for direction R in state State-A
  3608. In State-A moving R
  3609. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  3610. predict error 0
  3611. dir: dir isR
  3612. /|\506: O: O1012 (predict-no)
  3613. I see 1 and I'm going to do: predict-no
  3614. ENV: Agent did: predict-no for direction R in state State-B
  3615. In State-B moving R
  3616. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3617. predict error 0
  3618. dir: dir isU
  3619. -/|507: O: O1014 (predict-no)
  3620. I see 1 and I'm going to do: predict-no
  3621. ENV: Agent did: predict-no for direction U in state State-B
  3622. In State-B moving U
  3623. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3624. predict error 0
  3625. dir: dir isL
  3626. \-508: O: O1015 (predict-yes)
  3627. I see 1 and I'm going to do: predict-yes
  3628. ENV: Agent did: predict-yes for direction L in state State-B
  3629. In State-B moving L
  3630. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  3631. predict error 0
  3632. dir: dir isL
  3633. /|509: O: O1018 (predict-no)
  3634. I see 1 and I'm going to do: predict-no
  3635. ENV: Agent did: predict-no for direction L in state State-A
  3636. In State-A moving L
  3637. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3638. predict error 0
  3639. dir: dir isU
  3640. \-/510: O: O1020 (predict-no)
  3641. I see 1 and I'm going to do: predict-no
  3642. ENV: Agent did: predict-no for direction U in state State-A
  3643. In State-A moving U
  3644. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3645. predict error 0
  3646. dir: dir isL
  3647. |\-511: O: O1022 (predict-no)
  3648. I see 1 and I'm going to do: predict-no
  3649. ENV: Agent did: predict-no for direction L in state State-A
  3650. In State-A moving L
  3651. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3652. predict error 0
  3653. dir: dir isU
  3654. /512: O: O1024 (predict-no)
  3655. I see 1 and I'm going to do: predict-no
  3656. ENV: Agent did: predict-no for direction U in state State-A
  3657. In State-A moving U
  3658. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3659. predict error 0
  3660. dir: dir isL
  3661. |\-513: O: O1026 (predict-no)
  3662. I see 1 and I'm going to do: predict-no
  3663. ENV: Agent did: predict-no for direction L in state State-A
  3664. In State-A moving L
  3665. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3666. predict error 0
  3667. dir: dir isR
  3668. /|\514: O: O1027 (predict-yes)
  3669. I see 1 and I'm going to do: predict-yes
  3670. ENV: Agent did: predict-yes for direction R in state State-A
  3671. In State-A moving R
  3672. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  3673. predict error 0
  3674. dir: dir isR
  3675. -/515: O: O1030 (predict-no)
  3676. I see 1 and I'm going to do: predict-no
  3677. ENV: Agent did: predict-no for direction R in state State-B
  3678. In State-B moving R
  3679. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3680. predict error 0
  3681. dir: dir isU
  3682. |\-/516: O: O1032 (predict-no)
  3683. I see 1 and I'm going to do: predict-no
  3684. ENV: Agent did: predict-no for direction U in state State-B
  3685. In State-B moving U
  3686. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3687. predict error 0
  3688. dir: dir isL
  3689. |\517: O: O1033 (predict-yes)
  3690. I see 1 and I'm going to do: predict-yes
  3691. ENV: Agent did: predict-yes for direction L in state State-B
  3692. In State-B moving L
  3693. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  3694. predict error 0
  3695. dir: dir isU
  3696. -/|518: O: O1036 (predict-no)
  3697. I see 1 and I'm going to do: predict-no
  3698. ENV: Agent did: predict-no for direction U in state State-A
  3699. In State-A moving U
  3700. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3701. predict error 0
  3702. dir: dir isL
  3703. \-519: O: O1038 (predict-no)
  3704. I see 1 and I'm going to do: predict-no
  3705. ENV: Agent did: predict-no for direction L in state State-A
  3706. In State-A moving L
  3707. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3708. predict error 0
  3709. dir: dir isU
  3710. /|\520: O: O1040 (predict-no)
  3711. I see 1 and I'm going to do: predict-no
  3712. ENV: Agent did: predict-no for direction U in state State-A
  3713. In State-A moving U
  3714. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3715. predict error 0
  3716. dir: dir isL
  3717. -/521: O: O1042 (predict-no)
  3718. I see 1 and I'm going to do: predict-no
  3719. ENV: Agent did: predict-no for direction L in state State-A
  3720. In State-A moving L
  3721. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3722. predict error 0
  3723. dir: dir isU
  3724. |522: O: O1044 (predict-no)
  3725. I see 1 and I'm going to do: predict-no
  3726. ENV: Agent did: predict-no for direction U in state State-A
  3727. In State-A moving U
  3728. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3729. predict error 0
  3730. dir: dir isL
  3731. \-/523: O: O1046 (predict-no)
  3732. I see 1 and I'm going to do: predict-no
  3733. ENV: Agent did: predict-no for direction L in state State-A
  3734. In State-A moving L
  3735. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3736. predict error 0
  3737. dir: dir isL
  3738. |\-/524: O: O1048 (predict-no)
  3739. I see 1 and I'm going to do: predict-no
  3740. ENV: Agent did: predict-no for direction L in state State-A
  3741. In State-A moving L
  3742. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3743. predict error 0
  3744. dir: dir isL
  3745. |\-525: O: O1050 (predict-no)
  3746. I see 1 and I'm going to do: predict-no
  3747. ENV: Agent did: predict-no for direction L in state State-A
  3748. In State-A moving L
  3749. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3750. predict error 0
  3751. dir: dir isL
  3752. /|\-526: O: O1052 (predict-no)
  3753. I see 1 and I'm going to do: predict-no
  3754. ENV: Agent did: predict-no for direction L in state State-A
  3755. In State-A moving L
  3756. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3757. predict error 0
  3758. dir: dir isL
  3759. /|\527: O: O1054 (predict-no)
  3760. I see 1 and I'm going to do: predict-no
  3761. ENV: Agent did: predict-no for direction L in state State-A
  3762. In State-A moving L
  3763. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3764. predict error 0
  3765. dir: dir isU
  3766. -/528: O: O1056 (predict-no)
  3767. I see 1 and I'm going to do: predict-no
  3768. ENV: Agent did: predict-no for direction U in state State-A
  3769. In State-A moving U
  3770. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3771. predict error 0
  3772. dir: dir isR
  3773. |\-/529: O: O1057 (predict-yes)
  3774. I see 1 and I'm going to do: predict-yes
  3775. ENV: Agent did: predict-yes for direction R in state State-A
  3776. In State-A moving R
  3777. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  3778. predict error 0
  3779. dir: dir isR
  3780. |\-530: O: O1060 (predict-no)
  3781. I see 1 and I'm going to do: predict-no
  3782. ENV: Agent did: predict-no for direction R in state State-B
  3783. In State-B moving R
  3784. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3785. predict error 0
  3786. dir: dir isU
  3787. /|\-531: O: O1062 (predict-no)
  3788. I see 1 and I'm going to do: predict-no
  3789. ENV: Agent did: predict-no for direction U in state State-B
  3790. In State-B moving U
  3791. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3792. predict error 0
  3793. dir: dir isL
  3794. /532: O: O1063 (predict-yes)
  3795. I see 1 and I'm going to do: predict-yes
  3796. ENV: Agent did: predict-yes for direction L in state State-B
  3797. In State-B moving L
  3798. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  3799. predict error 0
  3800. dir: dir isL
  3801. |533: O: O1066 (predict-no)
  3802. I see 1 and I'm going to do: predict-no
  3803. ENV: Agent did: predict-no for direction L in state State-A
  3804. In State-A moving L
  3805. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3806. predict error 0
  3807. dir: dir isU
  3808. \-/534: O: O1068 (predict-no)
  3809. I see 1 and I'm going to do: predict-no
  3810. ENV: Agent did: predict-no for direction U in state State-A
  3811. In State-A moving U
  3812. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3813. predict error 0
  3814. dir: dir isU
  3815. |\535: O: O1070 (predict-no)
  3816. I see 1 and I'm going to do: predict-no
  3817. ENV: Agent did: predict-no for direction U in state State-A
  3818. In State-A moving U
  3819. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3820. predict error 0
  3821. dir: dir isU
  3822. -/|536: O: O1072 (predict-no)
  3823. I see 1 and I'm going to do: predict-no
  3824. ENV: Agent did: predict-no for direction U in state State-A
  3825. In State-A moving U
  3826. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3827. predict error 0
  3828. dir: dir isU
  3829. \-537: O: O1074 (predict-no)
  3830. I see 1 and I'm going to do: predict-no
  3831. ENV: Agent did: predict-no for direction U in state State-A
  3832. In State-A moving U
  3833. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3834. predict error 0
  3835. dir: dir isL
  3836. /|538: O: O1076 (predict-no)
  3837. I see 1 and I'm going to do: predict-no
  3838. ENV: Agent did: predict-no for direction L in state State-A
  3839. In State-A moving L
  3840. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3841. predict error 0
  3842. dir: dir isU
  3843. \-/539: O: O1078 (predict-no)
  3844. I see 1 and I'm going to do: predict-no
  3845. ENV: Agent did: predict-no for direction U in state State-A
  3846. In State-A moving U
  3847. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3848. predict error 0
  3849. dir: dir isU
  3850. |\-540: O: O1080 (predict-no)
  3851. I see 1 and I'm going to do: predict-no
  3852. ENV: Agent did: predict-no for direction U in state State-A
  3853. In State-A moving U
  3854. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3855. predict error 0
  3856. dir: dir isU
  3857. /|\541: O: O1082 (predict-no)
  3858. I see 1 and I'm going to do: predict-no
  3859. ENV: Agent did: predict-no for direction U in state State-A
  3860. In State-A moving U
  3861. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3862. predict error 0
  3863. dir: dir isU
  3864. -542: O: O1084 (predict-no)
  3865. I see 1 and I'm going to do: predict-no
  3866. ENV: Agent did: predict-no for direction U in state State-A
  3867. In State-A moving U
  3868. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3869. predict error 0
  3870. dir: dir isL
  3871. /|\-543: O: O1086 (predict-no)
  3872. I see 1 and I'm going to do: predict-no
  3873. ENV: Agent did: predict-no for direction L in state State-A
  3874. In State-A moving L
  3875. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3876. predict error 0
  3877. dir: dir isL
  3878. /|\-544: O: O1088 (predict-no)
  3879. I see 1 and I'm going to do: predict-no
  3880. ENV: Agent did: predict-no for direction L in state State-A
  3881. In State-A moving L
  3882. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3883. predict error 0
  3884. dir: dir isL
  3885. /|545: O: O1090 (predict-no)
  3886. I see 1 and I'm going to do: predict-no
  3887. ENV: Agent did: predict-no for direction L in state State-A
  3888. In State-A moving L
  3889. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3890. predict error 0
  3891. dir: dir isR
  3892. \-/546: O: O1091 (predict-yes)
  3893. I see 1 and I'm going to do: predict-yes
  3894. ENV: Agent did: predict-yes for direction R in state State-A
  3895. In State-A moving R
  3896. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  3897. predict error 0
  3898. dir: dir isR
  3899. |\-547: O: O1094 (predict-no)
  3900. I see 1 and I'm going to do: predict-no
  3901. ENV: Agent did: predict-no for direction R in state State-B
  3902. In State-B moving R
  3903. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3904. predict error 0
  3905. dir: dir isR
  3906. /|\548: O: O1096 (predict-no)
  3907. I see 1 and I'm going to do: predict-no
  3908. ENV: Agent did: predict-no for direction R in state State-B
  3909. In State-B moving R
  3910. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3911. predict error 0
  3912. dir: dir isR
  3913. -/|549: O: O1098 (predict-no)
  3914. I see 1 and I'm going to do: predict-no
  3915. ENV: Agent did: predict-no for direction R in state State-B
  3916. In State-B moving R
  3917. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3918. predict error 0
  3919. dir: dir isU
  3920. \-/550: O: O1100 (predict-no)
  3921. I see 1 and I'm going to do: predict-no
  3922. ENV: Agent did: predict-no for direction U in state State-B
  3923. In State-B moving U
  3924. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3925. predict error 0
  3926. dir: dir isU
  3927. |\-551: O: O1102 (predict-no)
  3928. I see 1 and I'm going to do: predict-no
  3929. ENV: Agent did: predict-no for direction U in state State-B
  3930. In State-B moving U
  3931. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3932. predict error 0
  3933. dir: dir isU
  3934. /552: O: O1104 (predict-no)
  3935. I see 1 and I'm going to do: predict-no
  3936. ENV: Agent did: predict-no for direction U in state State-B
  3937. In State-B moving U
  3938. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3939. predict error 0
  3940. dir: dir isL
  3941. |\553: O: O1105 (predict-yes)
  3942. I see 1 and I'm going to do: predict-yes
  3943. ENV: Agent did: predict-yes for direction L in state State-B
  3944. In State-B moving L
  3945. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  3946. predict error 0
  3947. dir: dir isL
  3948. -/|554: O: O1108 (predict-no)
  3949. I see 1 and I'm going to do: predict-no
  3950. ENV: Agent did: predict-no for direction L in state State-A
  3951. In State-A moving L
  3952. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3953. predict error 0
  3954. dir: dir isL
  3955. \-/|555: O: O1110 (predict-no)
  3956. I see 1 and I'm going to do: predict-no
  3957. ENV: Agent did: predict-no for direction L in state State-A
  3958. In State-A moving L
  3959. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3960. predict error 0
  3961. dir: dir isL
  3962. \-/556: O: O1112 (predict-no)
  3963. I see 1 and I'm going to do: predict-no
  3964. ENV: Agent did: predict-no for direction L in state State-A
  3965. In State-A moving L
  3966. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3967. predict error 0
  3968. dir: dir isR
  3969. |\-557: O: O1113 (predict-yes)
  3970. I see 1 and I'm going to do: predict-yes
  3971. ENV: Agent did: predict-yes for direction R in state State-A
  3972. In State-A moving R
  3973. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  3974. predict error 0
  3975. dir: dir isL
  3976. /|\558: O: O1115 (predict-yes)
  3977. I see 1 and I'm going to do: predict-yes
  3978. ENV: Agent did: predict-yes for direction L in state State-B
  3979. In State-B moving L
  3980. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  3981. predict error 0
  3982. dir: dir isR
  3983. -/559: O: O1117 (predict-yes)
  3984. I see 1 and I'm going to do: predict-yes
  3985. ENV: Agent did: predict-yes for direction R in state State-A
  3986. In State-A moving R
  3987. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  3988. predict error 0
  3989. dir: dir isR
  3990. |\-/560: O: O1120 (predict-no)
  3991. I see 1 and I'm going to do: predict-no
  3992. ENV: Agent did: predict-no for direction R in state State-B
  3993. In State-B moving R
  3994. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3995. predict error 0
  3996. dir: dir isR
  3997. |\-561: O: O1122 (predict-no)
  3998. I see 1 and I'm going to do: predict-no
  3999. ENV: Agent did: predict-no for direction R in state State-B
  4000. In State-B moving R
  4001. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4002. predict error 0
  4003. dir: dir isU
  4004. /562: O: O1124 (predict-no)
  4005. I see 1 and I'm going to do: predict-no
  4006. ENV: Agent did: predict-no for direction U in state State-B
  4007. In State-B moving U
  4008. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4009. predict error 0
  4010. dir: dir isU
  4011. |\-563: O: O1126 (predict-no)
  4012. I see 1 and I'm going to do: predict-no
  4013. ENV: Agent did: predict-no for direction U in state State-B
  4014. In State-B moving U
  4015. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4016. predict error 0
  4017. dir: dir isL
  4018. /|\564: O: O1127 (predict-yes)
  4019. I see 1 and I'm going to do: predict-yes
  4020. ENV: Agent did: predict-yes for direction L in state State-B
  4021. In State-B moving L
  4022. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  4023. predict error 0
  4024. dir: dir isR
  4025. -/|565: O: O1129 (predict-yes)
  4026. I see 1 and I'm going to do: predict-yes
  4027. ENV: Agent did: predict-yes for direction R in state State-A
  4028. In State-A moving R
  4029. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  4030. predict error 0
  4031. dir: dir isU
  4032. \-566: O: O1132 (predict-no)
  4033. I see 1 and I'm going to do: predict-no
  4034. ENV: Agent did: predict-no for direction U in state State-B
  4035. In State-B moving U
  4036. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4037. predict error 0
  4038. dir: dir isL
  4039. /|\567: O: O1133 (predict-yes)
  4040. I see 1 and I'm going to do: predict-yes
  4041. ENV: Agent did: predict-yes for direction L in state State-B
  4042. In State-B moving L
  4043. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  4044. predict error 0
  4045. dir: dir isL
  4046. -/568: O: O1136 (predict-no)
  4047. I see 1 and I'm going to do: predict-no
  4048. ENV: Agent did: predict-no for direction L in state State-A
  4049. In State-A moving L
  4050. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4051. predict error 0
  4052. dir: dir isL
  4053. |\569: O: O1138 (predict-no)
  4054. I see 1 and I'm going to do: predict-no
  4055. ENV: Agent did: predict-no for direction L in state State-A
  4056. In State-A moving L
  4057. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4058. predict error 0
  4059. dir: dir isU
  4060. -/|570: O: O1140 (predict-no)
  4061. I see 1 and I'm going to do: predict-no
  4062. ENV: Agent did: predict-no for direction U in state State-A
  4063. In State-A moving U
  4064. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4065. predict error 0
  4066. dir: dir isU
  4067. \-/571: O: O1142 (predict-no)
  4068. I see 1 and I'm going to do: predict-no
  4069. ENV: Agent did: predict-no for direction U in state State-A
  4070. In State-A moving U
  4071. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4072. predict error 0
  4073. dir: dir isU
  4074. |572: O: O1144 (predict-no)
  4075. I see 1 and I'm going to do: predict-no
  4076. ENV: Agent did: predict-no for direction U in state State-A
  4077. In State-A moving U
  4078. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4079. predict error 0
  4080. dir: dir isR
  4081. \-/573: O: O1145 (predict-yes)
  4082. I see 1 and I'm going to do: predict-yes
  4083. ENV: Agent did: predict-yes for direction R in state State-A
  4084. In State-A moving R
  4085. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  4086. predict error 0
  4087. dir: dir isL
  4088. |\-574: O: O1147 (predict-yes)
  4089. I see 1 and I'm going to do: predict-yes
  4090. ENV: Agent did: predict-yes for direction L in state State-B
  4091. In State-B moving L
  4092. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  4093. predict error 0
  4094. dir: dir isL
  4095. /|\575: O: O1150 (predict-no)
  4096. I see 1 and I'm going to do: predict-no
  4097. ENV: Agent did: predict-no for direction L in state State-A
  4098. In State-A moving L
  4099. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4100. predict error 0
  4101. dir: dir isU
  4102. -/|576: O: O1152 (predict-no)
  4103. I see 1 and I'm going to do: predict-no
  4104. ENV: Agent did: predict-no for direction U in state State-A
  4105. In State-A moving U
  4106. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4107. predict error 0
  4108. dir: dir isR
  4109. \-/|577: O: O1153 (predict-yes)
  4110. I see 1 and I'm going to do: predict-yes
  4111. ENV: Agent did: predict-yes for direction R in state State-A
  4112. In State-A moving R
  4113. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  4114. predict error 0
  4115. dir: dir isL
  4116. \-/|578: O: O1155 (predict-yes)
  4117. I see 1 and I'm going to do: predict-yes
  4118. ENV: Agent did: predict-yes for direction L in state State-B
  4119. In State-B moving L
  4120. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  4121. predict error 0
  4122. dir: dir isR
  4123. \-/579: O: O1157 (predict-yes)
  4124. I see 1 and I'm going to do: predict-yes
  4125. ENV: Agent did: predict-yes for direction R in state State-A
  4126. In State-A moving R
  4127. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  4128. predict error 0
  4129. dir: dir isR
  4130. |\580: O: O1160 (predict-no)
  4131. I see 1 and I'm going to do: predict-no
  4132. ENV: Agent did: predict-no for direction R in state State-B
  4133. In State-B moving R
  4134. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4135. predict error 0
  4136. dir: dir isR
  4137. -/581: O: O1162 (predict-no)
  4138. I see 1 and I'm going to do: predict-no
  4139. ENV: Agent did: predict-no for direction R in state State-B
  4140. In State-B moving R
  4141. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4142. predict error 0
  4143. dir: dir isR
  4144. |582: O: O1164 (predict-no)
  4145. I see 1 and I'm going to do: predict-no
  4146. ENV: Agent did: predict-no for direction R in state State-B
  4147. In State-B moving R
  4148. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4149. predict error 0
  4150. dir: dir isL
  4151. \-583: O: O1165 (predict-yes)
  4152. I see 1 and I'm going to do: predict-yes
  4153. ENV: Agent did: predict-yes for direction L in state State-B
  4154. In State-B moving L
  4155. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  4156. predict error 0
  4157. dir: dir isL
  4158. /|\584: O: O1168 (predict-no)
  4159. I see 1 and I'm going to do: predict-no
  4160. ENV: Agent did: predict-no for direction L in state State-A
  4161. In State-A moving L
  4162. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4163. predict error 0
  4164. dir: dir isU
  4165. -/585: O: O1170 (predict-no)
  4166. I see 1 and I'm going to do: predict-no
  4167. ENV: Agent did: predict-no for direction U in state State-A
  4168. In State-A moving U
  4169. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4170. predict error 0
  4171. dir: dir isU
  4172. |\-586: O: O1172 (predict-no)
  4173. I see 1 and I'm going to do: predict-no
  4174. ENV: Agent did: predict-no for direction U in state State-A
  4175. In State-A moving U
  4176. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4177. predict error 0
  4178. dir: dir isR
  4179. /|587: O: O1173 (predict-yes)
  4180. I see 1 and I'm going to do: predict-yes
  4181. ENV: Agent did: predict-yes for direction R in state State-A
  4182. In State-A moving R
  4183. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  4184. predict error 0
  4185. dir: dir isL
  4186. \-/588: O: O1175 (predict-yes)
  4187. I see 1 and I'm going to do: predict-yes
  4188. ENV: Agent did: predict-yes for direction L in state State-B
  4189. In State-B moving L
  4190. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  4191. predict error 0
  4192. dir: dir isL
  4193. |\-589: O: O1178 (predict-no)
  4194. I see 1 and I'm going to do: predict-no
  4195. ENV: Agent did: predict-no for direction L in state State-A
  4196. In State-A moving L
  4197. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4198. predict error 0
  4199. dir: dir isR
  4200. /|\590: O: O1179 (predict-yes)
  4201. I see 1 and I'm going to do: predict-yes
  4202. ENV: Agent did: predict-yes for direction R in state State-A
  4203. In State-A moving R
  4204. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  4205. predict error 0
  4206. dir: dir isU
  4207. -/|591: O: O1182 (predict-no)
  4208. I see 1 and I'm going to do: predict-no
  4209. ENV: Agent did: predict-no for direction U in state State-B
  4210. In State-B moving U
  4211. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4212. predict error 0
  4213. dir: dir isR
  4214. \592: O: O1184 (predict-no)
  4215. I see 1 and I'm going to do: predict-no
  4216. ENV: Agent did: predict-no for direction R in state State-B
  4217. In State-B moving R
  4218. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4219. predict error 0
  4220. dir: dir isU
  4221. -/593: O: O1186 (predict-no)
  4222. I see 1 and I'm going to do: predict-no
  4223. ENV: Agent did: predict-no for direction U in state State-B
  4224. In State-B moving U
  4225. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4226. predict error 0
  4227. dir: dir isR
  4228. |\-594: O: O1188 (predict-no)
  4229. I see 1 and I'm going to do: predict-no
  4230. ENV: Agent did: predict-no for direction R in state State-B
  4231. In State-B moving R
  4232. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4233. predict error 0
  4234. dir: dir isL
  4235. /|\-595: O: O1189 (predict-yes)
  4236. I see 1 and I'm going to do: predict-yes
  4237. ENV: Agent did: predict-yes for direction L in state State-B
  4238. In State-B moving L
  4239. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  4240. predict error 0
  4241. dir: dir isR
  4242. /|\596: O: O1191 (predict-yes)
  4243. I see 1 and I'm going to do: predict-yes
  4244. ENV: Agent did: predict-yes for direction R in state State-A
  4245. In State-A moving R
  4246. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  4247. predict error 0
  4248. dir: dir isR
  4249. -/|597: O: O1194 (predict-no)
  4250. I see 1 and I'm going to do: predict-no
  4251. ENV: Agent did: predict-no for direction R in state State-B
  4252. In State-B moving R
  4253. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4254. predict error 0
  4255. dir: dir isR
  4256. \-598: O: O1196 (predict-no)
  4257. I see 1 and I'm going to do: predict-no
  4258. ENV: Agent did: predict-no for direction R in state State-B
  4259. In State-B moving R
  4260. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4261. predict error 0
  4262. dir: dir isU
  4263. /|\599: O: O1198 (predict-no)
  4264. I see 1 and I'm going to do: predict-no
  4265. ENV: Agent did: predict-no for direction U in state State-B
  4266. In State-B moving U
  4267. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4268. predict error 0
  4269. dir: dir isL
  4270. -/|600: O: O1199 (predict-yes)
  4271. I see 1 and I'm going to do: predict-yes
  4272. ENV: Agent did: predict-yes for direction L in state State-B
  4273. In State-B moving L
  4274. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  4275. predict error 0
  4276. dir: dir isR
  4277. \-/601: O: O1201 (predict-yes)
  4278. I see 1 and I'm going to do: predict-yes
  4279. ENV: Agent did: predict-yes for direction R in state State-A
  4280. In State-A moving R
  4281. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  4282. predict error 0
  4283. dir: dir isU
  4284. |602: O: O1204 (predict-no)
  4285. I see 1 and I'm going to do: predict-no
  4286. ENV: Agent did: predict-no for direction U in state State-B
  4287. In State-B moving U
  4288. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4289. predict error 0
  4290. dir: dir isL
  4291. \-/603: O: O1205 (predict-yes)
  4292. I see 1 and I'm going to do: predict-yes
  4293. ENV: Agent did: predict-yes for direction L in state State-B
  4294. In State-B moving L
  4295. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  4296. predict error 0
  4297. dir: dir isL
  4298. |\604: O: O1208 (predict-no)
  4299. I see 1 and I'm going to do: predict-no
  4300. ENV: Agent did: predict-no for direction L in state State-A
  4301. In State-A moving L
  4302. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4303. predict error 0
  4304. dir: dir isL
  4305. -/|605: O: O1210 (predict-no)
  4306. I see 1 and I'm going to do: predict-no
  4307. ENV: Agent did: predict-no for direction L in state State-A
  4308. In State-A moving L
  4309. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4310. predict error 0
  4311. dir: dir isL
  4312. \-606: O: O1212 (predict-no)
  4313. I see 1 and I'm going to do: predict-no
  4314. ENV: Agent did: predict-no for direction L in state State-A
  4315. In State-A moving L
  4316. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4317. predict error 0
  4318. dir: dir isR
  4319. /|\-607: O: O1213 (predict-yes)
  4320. I see 1 and I'm going to do: predict-yes
  4321. ENV: Agent did: predict-yes for direction R in state State-A
  4322. In State-A moving R
  4323. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  4324. predict error 0
  4325. dir: dir isL
  4326. /|\608: O: O1215 (predict-yes)
  4327. I see 1 and I'm going to do: predict-yes
  4328. ENV: Agent did: predict-yes for direction L in state State-B
  4329. In State-B moving L
  4330. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  4331. predict error 0
  4332. dir: dir isR
  4333. -/609: O: O1217 (predict-yes)
  4334. I see 1 and I'm going to do: predict-yes
  4335. ENV: Agent did: predict-yes for direction R in state State-A
  4336. In State-A moving R
  4337. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  4338. predict error 0
  4339. dir: dir isL
  4340. |\610: O: O1219 (predict-yes)
  4341. I see 1 and I'm going to do: predict-yes
  4342. ENV: Agent did: predict-yes for direction L in state State-B
  4343. In State-B moving L
  4344. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  4345. predict error 0
  4346. dir: dir isR
  4347. -/|\611: O: O1221 (predict-yes)
  4348. I see 1 and I'm going to do: predict-yes
  4349. ENV: Agent did: predict-yes for direction R in state State-A
  4350. In State-A moving R
  4351. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  4352. predict error 0
  4353. dir: dir isU
  4354. -612: O: O1224 (predict-no)
  4355. I see 1 and I'm going to do: predict-no
  4356. ENV: Agent did: predict-no for direction U in state State-B
  4357. In State-B moving U
  4358. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4359. predict error 0
  4360. dir: dir isR
  4361. /|\-613: O: O1226 (predict-no)
  4362. I see 1 and I'm going to do: predict-no
  4363. ENV: Agent did: predict-no for direction R in state State-B
  4364. In State-B moving R
  4365. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4366. predict error 0
  4367. dir: dir isU
  4368. /|\614: O: O1228 (predict-no)
  4369. I see 1 and I'm going to do: predict-no
  4370. ENV: Agent did: predict-no for direction U in state State-B
  4371. In State-B moving U
  4372. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4373. predict error 0
  4374. dir: dir isU
  4375. -/|615: O: O1230 (predict-no)
  4376. I see 1 and I'm going to do: predict-no
  4377. ENV: Agent did: predict-no for direction U in state State-B
  4378. In State-B moving U
  4379. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4380. predict error 0
  4381. dir: dir isL
  4382. \-616: O: O1231 (predict-yes)
  4383. I see 1 and I'm going to do: predict-yes
  4384. ENV: Agent did: predict-yes for direction L in state State-B
  4385. In State-B moving L
  4386. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  4387. predict error 0
  4388. dir: dir isR
  4389. /|\-617: O: O1233 (predict-yes)
  4390. I see 1 and I'm going to do: predict-yes
  4391. ENV: Agent did: predict-yes for direction R in state State-A
  4392. In State-A moving R
  4393. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  4394. predict error 0
  4395. dir: dir isR
  4396. /|\618: O: O1236 (predict-no)
  4397. I see 1 and I'm going to do: predict-no
  4398. ENV: Agent did: predict-no for direction R in state State-B
  4399. In State-B moving R
  4400. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4401. predict error 0
  4402. dir: dir isR
  4403. -/619: O: O1238 (predict-no)
  4404. I see 1 and I'm going to do: predict-no
  4405. ENV: Agent did: predict-no for direction R in state State-B
  4406. In State-B moving R
  4407. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4408. predict error 0
  4409. dir: dir isR
  4410. |\-620: O: O1240 (predict-no)
  4411. I see 1 and I'm going to do: predict-no
  4412. ENV: Agent did: predict-no for direction R in state State-B
  4413. In State-B moving R
  4414. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4415. predict error 0
  4416. dir: dir isU
  4417. /|\621: O: O1242 (predict-no)
  4418. I see 1 and I'm going to do: predict-no
  4419. ENV: Agent did: predict-no for direction U in state State-B
  4420. In State-B moving U
  4421. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4422. predict error 0
  4423. dir: dir isL
  4424. -622: O: O1243 (predict-yes)
  4425. I see 1 and I'm going to do: predict-yes
  4426. ENV: Agent did: predict-yes for direction L in state State-B
  4427. In State-B moving L
  4428. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  4429. predict error 0
  4430. dir: dir isR
  4431. /|623: O: O1245 (predict-yes)
  4432. I see 1 and I'm going to do: predict-yes
  4433. ENV: Agent did: predict-yes for direction R in state State-A
  4434. In State-A moving R
  4435. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  4436. predict error 0
  4437. dir: dir isL
  4438. \-/624: O: O1247 (predict-yes)
  4439. I see 1 and I'm going to do: predict-yes
  4440. ENV: Agent did: predict-yes for direction L in state State-B
  4441. In State-B moving L
  4442. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  4443. predict error 0
  4444. dir: dir isU
  4445. |\-/625: O: O1250 (predict-no)
  4446. I see 1 and I'm going to do: predict-no
  4447. ENV: Agent did: predict-no for direction U in state State-A
  4448. In State-A moving U
  4449. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4450. predict error 0
  4451. dir: dir isR
  4452. |\626: O: O1251 (predict-yes)
  4453. I see 1 and I'm going to do: predict-yes
  4454. ENV: Agent did: predict-yes for direction R in state State-A
  4455. In State-A moving R
  4456. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  4457. predict error 0
  4458. dir: dir isU
  4459. -/|627: O: O1254 (predict-no)
  4460. I see 1 and I'm going to do: predict-no
  4461. ENV: Agent did: predict-no for direction U in state State-B
  4462. In State-B moving U
  4463. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4464. predict error 0
  4465. dir: dir isL
  4466. \-/|628: O: O1255 (predict-yes)
  4467. I see 1 and I'm going to do: predict-yes
  4468. ENV: Agent did: predict-yes for direction L in state State-B
  4469. In State-B moving L
  4470. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  4471. predict error 0
  4472. dir: dir isU
  4473. \-/629: O: O1258 (predict-no)
  4474. I see 1 and I'm going to do: predict-no
  4475. ENV: Agent did: predict-no for direction U in state State-A
  4476. In State-A moving U
  4477. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4478. predict error 0
  4479. dir: dir isR
  4480. |\-630: O: O1259 (predict-yes)
  4481. I see 1 and I'm going to do: predict-yes
  4482. ENV: Agent did: predict-yes for direction R in state State-A
  4483. In State-A moving R
  4484. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  4485. predict error 0
  4486. dir: dir isL
  4487. /|\631: O: O1261 (predict-yes)
  4488. I see 1 and I'm going to do: predict-yes
  4489. ENV: Agent did: predict-yes for direction L in state State-B
  4490. In State-B moving L
  4491. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  4492. predict error 0
  4493. dir: dir isU
  4494. -632: O: O1264 (predict-no)
  4495. I see 1 and I'm going to do: predict-no
  4496. ENV: Agent did: predict-no for direction U in state State-A
  4497. In State-A moving U
  4498. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4499. predict error 0
  4500. dir: dir isU
  4501. /|\633: O: O1266 (predict-no)
  4502. I see 1 and I'm going to do: predict-no
  4503. ENV: Agent did: predict-no for direction U in state State-A
  4504. In State-A moving U
  4505. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4506. predict error 0
  4507. dir: dir isL
  4508. -/|634: O: O1268 (predict-no)
  4509. I see 1 and I'm going to do: predict-no
  4510. ENV: Agent did: predict-no for direction L in state State-A
  4511. In State-A moving L
  4512. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4513. predict error 0
  4514. dir: dir isU
  4515. \-/635: O: O1270 (predict-no)
  4516. I see 1 and I'm going to do: predict-no
  4517. ENV: Agent did: predict-no for direction U in state State-A
  4518. In State-A moving U
  4519. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4520. predict error 0
  4521. dir: dir isU
  4522. |\-636: O: O1272 (predict-no)
  4523. I see 1 and I'm going to do: predict-no
  4524. ENV: Agent did: predict-no for direction U in state State-A
  4525. In State-A moving U
  4526. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4527. predict error 0
  4528. dir: dir isR
  4529. /|637: O: O1273 (predict-yes)
  4530. I see 1 and I'm going to do: predict-yes
  4531. ENV: Agent did: predict-yes for direction R in state State-A
  4532. In State-A moving R
  4533. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  4534. predict error 0
  4535. dir: dir isR
  4536. \-/638: O: O1276 (predict-no)
  4537. I see 1 and I'm going to do: predict-no
  4538. ENV: Agent did: predict-no for direction R in state State-B
  4539. In State-B moving R
  4540. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4541. predict error 0
  4542. dir: dir isL
  4543. |\-/639: O: O1277 (predict-yes)
  4544. I see 1 and I'm going to do: predict-yes
  4545. ENV: Agent did: predict-yes for direction L in state State-B
  4546. In State-B moving L
  4547. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  4548. predict error 0
  4549. dir: dir isL
  4550. |\-640: O: O1280 (predict-no)
  4551. I see 1 and I'm going to do: predict-no
  4552. ENV: Agent did: predict-no for direction L in state State-A
  4553. In State-A moving L
  4554. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4555. predict error 0
  4556. dir: dir isR
  4557. /|641: O: O1281 (predict-yes)
  4558. I see 1 and I'm going to do: predict-yes
  4559. ENV: Agent did: predict-yes for direction R in state State-A
  4560. In State-A moving R
  4561. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  4562. predict error 0
  4563. dir: dir isU
  4564. \642: O: O1284 (predict-no)
  4565. I see 1 and I'm going to do: predict-no
  4566. ENV: Agent did: predict-no for direction U in state State-B
  4567. In State-B moving U
  4568. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4569. predict error 0
  4570. dir: dir isL
  4571. -/|643: O: O1285 (predict-yes)
  4572. I see 1 and I'm going to do: predict-yes
  4573. ENV: Agent did: predict-yes for direction L in state State-B
  4574. In State-B moving L
  4575. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  4576. predict error 0
  4577. dir: dir isR
  4578. \-644: O: O1287 (predict-yes)
  4579. I see 1 and I'm going to do: predict-yes
  4580. ENV: Agent did: predict-yes for direction R in state State-A
  4581. In State-A moving R
  4582. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  4583. predict error 0
  4584. dir: dir isL
  4585. /|\645: O: O1289 (predict-yes)
  4586. I see 1 and I'm going to do: predict-yes
  4587. ENV: Agent did: predict-yes for direction L in state State-B
  4588. In State-B moving L
  4589. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  4590. predict error 0
  4591. dir: dir isU
  4592. -/|\646: O: O1292 (predict-no)
  4593. I see 1 and I'm going to do: predict-no
  4594. ENV: Agent did: predict-no for direction U in state State-A
  4595. In State-A moving U
  4596. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4597. predict error 0
  4598. dir: dir isU
  4599. -/647: O: O1294 (predict-no)
  4600. I see 1 and I'm going to do: predict-no
  4601. ENV: Agent did: predict-no for direction U in state State-A
  4602. In State-A moving U
  4603. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4604. predict error 0
  4605. dir: dir isU
  4606. |\-/648: O: O1296 (predict-no)
  4607. I see 1 and I'm going to do: predict-no
  4608. ENV: Agent did: predict-no for direction U in state State-A
  4609. In State-A moving U
  4610. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4611. predict error 0
  4612. dir: dir isL
  4613. |\649: O: O1298 (predict-no)
  4614. I see 1 and I'm going to do: predict-no
  4615. ENV: Agent did: predict-no for direction L in state State-A
  4616. In State-A moving L
  4617. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4618. predict error 0
  4619. dir: dir isR
  4620. -/|\650: O: O1299 (predict-yes)
  4621. I see 1 and I'm going to do: predict-yes
  4622. ENV: Agent did: predict-yes for direction R in state State-A
  4623. In State-A moving R
  4624. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  4625. predict error 0
  4626. dir: dir isL
  4627. -/651: O: O1301 (predict-yes)
  4628. I see 1 and I'm going to do: predict-yes
  4629. ENV: Agent did: predict-yes for direction L in state State-B
  4630. In State-B moving L
  4631. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  4632. predict error 0
  4633. dir: dir isR
  4634. |652: O: O1303 (predict-yes)
  4635. I see 1 and I'm going to do: predict-yes
  4636. ENV: Agent did: predict-yes for direction R in state State-A
  4637. In State-A moving R
  4638. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  4639. predict error 0
  4640. dir: dir isU
  4641. \-653: O: O1306 (predict-no)
  4642. I see 1 and I'm going to do: predict-no
  4643. ENV: Agent did: predict-no for direction U in state State-B
  4644. In State-B moving U
  4645. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4646. predict error 0
  4647. dir: dir isU
  4648. /|654: O: O1308 (predict-no)
  4649. I see 1 and I'm going to do: predict-no
  4650. ENV: Agent did: predict-no for direction U in state State-B
  4651. In State-B moving U
  4652. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4653. predict error 0
  4654. dir: dir isL
  4655. \-655: O: O1309 (predict-yes)
  4656. I see 1 and I'm going to do: predict-yes
  4657. ENV: Agent did: predict-yes for direction L in state State-B
  4658. In State-B moving L
  4659. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  4660. predict error 0
  4661. dir: dir isR
  4662. /|\656: O: O1311 (predict-yes)
  4663. I see 1 and I'm going to do: predict-yes
  4664. ENV: Agent did: predict-yes for direction R in state State-A
  4665. In State-A moving R
  4666. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  4667. predict error 0
  4668. dir: dir isL
  4669. -/657: O: O1313 (predict-yes)
  4670. I see 1 and I'm going to do: predict-yes
  4671. ENV: Agent did: predict-yes for direction L in state State-B
  4672. In State-B moving L
  4673. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  4674. predict error 0
  4675. dir: dir isR
  4676. |\-658: O: O1315 (predict-yes)
  4677. I see 1 and I'm going to do: predict-yes
  4678. ENV: Agent did: predict-yes for direction R in state State-A
  4679. In State-A moving R
  4680. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  4681. predict error 0
  4682. dir: dir isU
  4683. /|\659: O: O1318 (predict-no)
  4684. I see 1 and I'm going to do: predict-no
  4685. ENV: Agent did: predict-no for direction U in state State-B
  4686. In State-B moving U
  4687. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4688. predict error 0
  4689. dir: dir isL
  4690. -/|660: O: O1319 (predict-yes)
  4691. I see 1 and I'm going to do: predict-yes
  4692. ENV: Agent did: predict-yes for direction L in state State-B
  4693. In State-B moving L
  4694. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  4695. predict error 0
  4696. dir: dir isU
  4697. \-/661: O: O1322 (predict-no)
  4698. I see 1 and I'm going to do: predict-no
  4699. ENV: Agent did: predict-no for direction U in state State-A
  4700. In State-A moving U
  4701. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4702. predict error 0
  4703. dir: dir isU
  4704. |662: O: O1324 (predict-no)
  4705. I see 1 and I'm going to do: predict-no
  4706. ENV: Agent did: predict-no for direction U in state State-A
  4707. In State-A moving U
  4708. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4709. predict error 0
  4710. dir: dir isU
  4711. \-/663: O: O1326 (predict-no)
  4712. I see 1 and I'm going to do: predict-no
  4713. ENV: Agent did: predict-no for direction U in state State-A
  4714. In State-A moving U
  4715. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4716. predict error 0
  4717. dir: dir isL
  4718. |\664: O: O1328 (predict-no)
  4719. I see 1 and I'm going to do: predict-no
  4720. ENV: Agent did: predict-no for direction L in state State-A
  4721. In State-A moving L
  4722. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4723. predict error 0
  4724. dir: dir isU
  4725. -665: O: O1330 (predict-no)
  4726. I see 1 and I'm going to do: predict-no
  4727. ENV: Agent did: predict-no for direction U in state State-A
  4728. In State-A moving U
  4729. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4730. predict error 0
  4731. dir: dir isU
  4732. /|666: O: O1332 (predict-no)
  4733. I see 1 and I'm going to do: predict-no
  4734. ENV: Agent did: predict-no for direction U in state State-A
  4735. In State-A moving U
  4736. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4737. predict error 0
  4738. dir: dir isU
  4739. \-/667: O: O1334 (predict-no)
  4740. I see 1 and I'm going to do: predict-no
  4741. ENV: Agent did: predict-no for direction U in state State-A
  4742. In State-A moving U
  4743. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4744. predict error 0
  4745. dir: dir isL
  4746. |\-668: O: O1336 (predict-no)
  4747. I see 1 and I'm going to do: predict-no
  4748. ENV: Agent did: predict-no for direction L in state State-A
  4749. In State-A moving L
  4750. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4751. predict error 0
  4752. dir: dir isL
  4753. /|669: O: O1338 (predict-no)
  4754. I see 1 and I'm going to do: predict-no
  4755. ENV: Agent did: predict-no for direction L in state State-A
  4756. In State-A moving L
  4757. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4758. predict error 0
  4759. dir: dir isL
  4760. \-/|670: O: O1340 (predict-no)
  4761. I see 1 and I'm going to do: predict-no
  4762. ENV: Agent did: predict-no for direction L in state State-A
  4763. In State-A moving L
  4764. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4765. predict error 0
  4766. dir: dir isR
  4767. \-/671: O: O1341 (predict-yes)
  4768. I see 1 and I'm going to do: predict-yes
  4769. ENV: Agent did: predict-yes for direction R in state State-A
  4770. In State-A moving R
  4771. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  4772. predict error 0
  4773. dir: dir isR
  4774. |672: O: O1344 (predict-no)
  4775. I see 1 and I'm going to do: predict-no
  4776. ENV: Agent did: predict-no for direction R in state State-B
  4777. In State-B moving R
  4778. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4779. predict error 0
  4780. dir: dir isL
  4781. \-673: O: O1345 (predict-yes)
  4782. I see 1 and I'm going to do: predict-yes
  4783. ENV: Agent did: predict-yes for direction L in state State-B
  4784. In State-B moving L
  4785. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  4786. predict error 0
  4787. dir: dir isR
  4788. /|\674: O: O1347 (predict-yes)
  4789. I see 1 and I'm going to do: predict-yes
  4790. ENV: Agent did: predict-yes for direction R in state State-A
  4791. In State-A moving R
  4792. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  4793. predict error 0
  4794. dir: dir isU
  4795. -/|675: O: O1350 (predict-no)
  4796. I see 1 and I'm going to do: predict-no
  4797. ENV: Agent did: predict-no for direction U in state State-B
  4798. In State-B moving U
  4799. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4800. predict error 0
  4801. dir: dir isR
  4802. \-/676: O: O1352 (predict-no)
  4803. I see 1 and I'm going to do: predict-no
  4804. ENV: Agent did: predict-no for direction R in state State-B
  4805. In State-B moving R
  4806. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4807. predict error 0
  4808. dir: dir isR
  4809. |\-677: O: O1354 (predict-no)
  4810. I see 1 and I'm going to do: predict-no
  4811. ENV: Agent did: predict-no for direction R in state State-B
  4812. In State-B moving R
  4813. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4814. predict error 0
  4815. dir: dir isR
  4816. /|\678: O: O1356 (predict-no)
  4817. I see 1 and I'm going to do: predict-no
  4818. ENV: Agent did: predict-no for direction R in state State-B
  4819. In State-B moving R
  4820. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4821. predict error 0
  4822. dir: dir isU
  4823. -/679: O: O1358 (predict-no)
  4824. I see 1 and I'm going to do: predict-no
  4825. ENV: Agent did: predict-no for direction U in state State-B
  4826. In State-B moving U
  4827. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4828. predict error 0
  4829. dir: dir isL
  4830. |\-/680: O: O1359 (predict-yes)
  4831. I see 1 and I'm going to do: predict-yes
  4832. ENV: Agent did: predict-yes for direction L in state State-B
  4833. In State-B moving L
  4834. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  4835. predict error 0
  4836. dir: dir isR
  4837. |\681: O: O1361 (predict-yes)
  4838. I see 1 and I'm going to do: predict-yes
  4839. ENV: Agent did: predict-yes for direction R in state State-A
  4840. In State-A moving R
  4841. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  4842. predict error 0
  4843. dir: dir isL
  4844. -682: O: O1363 (predict-yes)
  4845. I see 1 and I'm going to do: predict-yes
  4846. ENV: Agent did: predict-yes for direction L in state State-B
  4847. In State-B moving L
  4848. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  4849. predict error 0
  4850. dir: dir isL
  4851. /|\-683: O: O1366 (predict-no)
  4852. I see 1 and I'm going to do: predict-no
  4853. ENV: Agent did: predict-no for direction L in state State-A
  4854. In State-A moving L
  4855. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4856. predict error 0
  4857. dir: dir isU
  4858. /|\684: O: O1368 (predict-no)
  4859. I see 1 and I'm going to do: predict-no
  4860. ENV: Agent did: predict-no for direction U in state State-A
  4861. In State-A moving U
  4862. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4863. predict error 0
  4864. dir: dir isL
  4865. -/|685: O: O1370 (predict-no)
  4866. I see 1 and I'm going to do: predict-no
  4867. ENV: Agent did: predict-no for direction L in state State-A
  4868. In State-A moving L
  4869. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4870. predict error 0
  4871. dir: dir isR
  4872. \-/686: O: O1371 (predict-yes)
  4873. I see 1 and I'm going to do: predict-yes
  4874. ENV: Agent did: predict-yes for direction R in state State-A
  4875. In State-A moving R
  4876. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  4877. predict error 0
  4878. dir: dir isL
  4879. |\-687: O: O1373 (predict-yes)
  4880. I see 1 and I'm going to do: predict-yes
  4881. ENV: Agent did: predict-yes for direction L in state State-B
  4882. In State-B moving L
  4883. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  4884. predict error 0
  4885. dir: dir isR
  4886. /|688: O: O1375 (predict-yes)
  4887. I see 1 and I'm going to do: predict-yes
  4888. ENV: Agent did: predict-yes for direction R in state State-A
  4889. In State-A moving R
  4890. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  4891. predict error 0
  4892. dir: dir isL
  4893. \-689: O: O1377 (predict-yes)
  4894. I see 1 and I'm going to do: predict-yes
  4895. ENV: Agent did: predict-yes for direction L in state State-B
  4896. In State-B moving L
  4897. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  4898. predict error 0
  4899. dir: dir isR
  4900. /|\690: O: O1379 (predict-yes)
  4901. I see 1 and I'm going to do: predict-yes
  4902. ENV: Agent did: predict-yes for direction R in state State-A
  4903. In State-A moving R
  4904. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  4905. predict error 0
  4906. dir: dir isL
  4907. -/|691: O: O1381 (predict-yes)
  4908. I see 1 and I'm going to do: predict-yes
  4909. ENV: Agent did: predict-yes for direction L in state State-B
  4910. In State-B moving L
  4911. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  4912. predict error 0
  4913. dir: dir isU
  4914. \692: O: O1384 (predict-no)
  4915. I see 1 and I'm going to do: predict-no
  4916. ENV: Agent did: predict-no for direction U in state State-A
  4917. In State-A moving U
  4918. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4919. predict error 0
  4920. dir: dir isL
  4921. -/693: O: O1386 (predict-no)
  4922. I see 1 and I'm going to do: predict-no
  4923. ENV: Agent did: predict-no for direction L in state State-A
  4924. In State-A moving L
  4925. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4926. predict error 0
  4927. dir: dir isU
  4928. |\-694: O: O1388 (predict-no)
  4929. I see 1 and I'm going to do: predict-no
  4930. ENV: Agent did: predict-no for direction U in state State-A
  4931. In State-A moving U
  4932. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4933. predict error 0
  4934. dir: dir isR
  4935. /|\-695: O: O1389 (predict-yes)
  4936. I see 1 and I'm going to do: predict-yes
  4937. ENV: Agent did: predict-yes for direction R in state State-A
  4938. In State-A moving R
  4939. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  4940. predict error 0
  4941. dir: dir isR
  4942. /|\696: O: O1392 (predict-no)
  4943. I see 1 and I'm going to do: predict-no
  4944. ENV: Agent did: predict-no for direction R in state State-B
  4945. In State-B moving R
  4946. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4947. predict error 0
  4948. dir: dir isL
  4949. -/|697: O: O1393 (predict-yes)
  4950. I see 1 and I'm going to do: predict-yes
  4951. ENV: Agent did: predict-yes for direction L in state State-B
  4952. In State-B moving L
  4953. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  4954. predict error 0
  4955. dir: dir isR
  4956. \-698: O: O1395 (predict-yes)
  4957. I see 1 and I'm going to do: predict-yes
  4958. ENV: Agent did: predict-yes for direction R in state State-A
  4959. In State-A moving R
  4960. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  4961. predict error 0
  4962. dir: dir isU
  4963. /|\699: O: O1398 (predict-no)
  4964. I see 1 and I'm going to do: predict-no
  4965. ENV: Agent did: predict-no for direction U in state State-B
  4966. In State-B moving U
  4967. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4968. predict error 0
  4969. dir: dir isR
  4970. -/|\700: O: O1400 (predict-no)
  4971. I see 1 and I'm going to do: predict-no
  4972. ENV: Agent did: predict-no for direction R in state State-B
  4973. In State-B moving R
  4974. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4975. predict error 0
  4976. dir: dir isR
  4977. -/|701: O: O1402 (predict-no)
  4978. I see 1 and I'm going to do: predict-no
  4979. ENV: Agent did: predict-no for direction R in state State-B
  4980. In State-B moving R
  4981. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4982. predict error 0
  4983. dir: dir isL
  4984. \702: O: O1403 (predict-yes)
  4985. I see 1 and I'm going to do: predict-yes
  4986. ENV: Agent did: predict-yes for direction L in state State-B
  4987. In State-B moving L
  4988. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  4989. predict error 0
  4990. dir: dir isR
  4991. -/703: O: O1405 (predict-yes)
  4992. I see 1 and I'm going to do: predict-yes
  4993. ENV: Agent did: predict-yes for direction R in state State-A
  4994. In State-A moving R
  4995. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  4996. predict error 0
  4997. dir: dir isL
  4998. |\704: O: O1407 (predict-yes)
  4999. I see 1 and I'm going to do: predict-yes
  5000. ENV: Agent did: predict-yes for direction L in state State-B
  5001. In State-B moving L
  5002. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  5003. predict error 0
  5004. dir: dir isR
  5005. -/|705: O: O1409 (predict-yes)
  5006. I see 1 and I'm going to do: predict-yes
  5007. ENV: Agent did: predict-yes for direction R in state State-A
  5008. In State-A moving R
  5009. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  5010. predict error 0
  5011. dir: dir isR
  5012. \-/706: O: O1412 (predict-no)
  5013. I see 1 and I'm going to do: predict-no
  5014. ENV: Agent did: predict-no for direction R in state State-B
  5015. In State-B moving R
  5016. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5017. predict error 0
  5018. dir: dir isR
  5019. |\707: O: O1414 (predict-no)
  5020. I see 1 and I'm going to do: predict-no
  5021. ENV: Agent did: predict-no for direction R in state State-B
  5022. In State-B moving R
  5023. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5024. predict error 0
  5025. dir: dir isR
  5026. -/|708: O: O1416 (predict-no)
  5027. I see 1 and I'm going to do: predict-no
  5028. ENV: Agent did: predict-no for direction R in state State-B
  5029. In State-B moving R
  5030. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5031. predict error 0
  5032. dir: dir isR
  5033. \-/709: O: O1418 (predict-no)
  5034. I see 1 and I'm going to do: predict-no
  5035. ENV: Agent did: predict-no for direction R in state State-B
  5036. In State-B moving R
  5037. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5038. predict error 0
  5039. dir: dir isL
  5040. |\-710: O: O1419 (predict-yes)
  5041. I see 1 and I'm going to do: predict-yes
  5042. ENV: Agent did: predict-yes for direction L in state State-B
  5043. In State-B moving L
  5044. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  5045. predict error 0
  5046. dir: dir isU
  5047. /|\-711: O: O1422 (predict-no)
  5048. I see 1 and I'm going to do: predict-no
  5049. ENV: Agent did: predict-no for direction U in state State-A
  5050. In State-A moving U
  5051. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  5052. predict error 0
  5053. dir: dir isU
  5054. /712: O: O1424 (predict-no)
  5055. I see 1 and I'm going to do: predict-no
  5056. ENV: Agent did: predict-no for direction U in state State-A
  5057. In State-A moving U
  5058. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  5059. predict error 0
  5060. dir: dir isU
  5061. |\-/713: O: O1426 (predict-no)
  5062. I see 1 and I'm going to do: predict-no
  5063. ENV: Agent did: predict-no for direction U in state State-A
  5064. In State-A moving U
  5065. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  5066. predict error 0
  5067. dir: dir isU
  5068. |714: O: O1428 (predict-no)
  5069. I see 1 and I'm going to do: predict-no
  5070. ENV: Agent did: predict-no for direction U in state State-A
  5071. In State-A moving U
  5072. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  5073. predict error 0
  5074. dir: dir isR
  5075. \-/|715: O: O1429 (predict-yes)
  5076. I see 1 and I'm going to do: predict-yes
  5077. ENV: Agent did: predict-yes for direction R in state State-A
  5078. In State-A moving R
  5079. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  5080. predict error 0
  5081. dir: dir isL
  5082. \-/716: O: O1431 (predict-yes)
  5083. I see 1 and I'm going to do: predict-yes
  5084. ENV: Agent did: predict-yes for direction L in state State-B
  5085. In State-B moving L
  5086. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  5087. predict error 0
  5088. dir: dir isL
  5089. |\-717: O: O1434 (predict-no)
  5090. I see 1 and I'm going to do: predict-no
  5091. ENV: Agent did: predict-no for direction L in state State-A
  5092. In State-A moving L
  5093. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  5094. predict error 0
  5095. dir: dir isL
  5096. /|718: O: O1436 (predict-no)
  5097. I see 1 and I'm going to do: predict-no
  5098. ENV: Agent did: predict-no for direction L in state State-A
  5099. In State-A moving L
  5100. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  5101. predict error 0
  5102. dir: dir isL
  5103. \-/719: O: O1438 (predict-no)
  5104. I see 1 and I'm going to do: predict-no
  5105. ENV: Agent did: predict-no for direction L in state State-A
  5106. In State-A moving L
  5107. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  5108. predict error 0
  5109. dir: dir isL
  5110. |720: O: O1440 (predict-no)
  5111. I see 1 and I'm going to do: predict-no
  5112. ENV: Agent did: predict-no for direction L in state State-A
  5113. In State-A moving L
  5114. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  5115. predict error 0
  5116. dir: dir isL
  5117. \-/721: O: O1442 (predict-no)
  5118. I see 1 and I'm going to do: predict-no
  5119. ENV: Agent did: predict-no for direction L in state State-A
  5120. In State-A moving L
  5121. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  5122. predict error 0
  5123. dir: dir isR
  5124. |722: O: O1443 (predict-yes)
  5125. I see 1 and I'm going to do: predict-yes
  5126. ENV: Agent did: predict-yes for direction R in state State-A
  5127. In State-A moving R
  5128. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  5129. predict error 0
  5130. dir: dir isL
  5131. \-723: O: O1445 (predict-yes)
  5132. I see 1 and I'm going to do: predict-yes
  5133. ENV: Agent did: predict-yes for direction L in state State-B
  5134. In State-B moving L
  5135. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  5136. predict error 0
  5137. dir: dir isR
  5138. /|724: O: O1447 (predict-yes)
  5139. I see 1 and I'm going to do: predict-yes
  5140. ENV: Agent did: predict-yes for direction R in state State-A
  5141. In State-A moving R
  5142. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  5143. predict error 0
  5144. dir: dir isR
  5145. \-/725: O: O1450 (predict-no)
  5146. I see 1 and I'm going to do: predict-no
  5147. ENV: Agent did: predict-no for direction R in state State-B
  5148. In State-B moving R
  5149. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5150. predict error 0
  5151. dir: dir isL
  5152. |\726: O: O1451 (predict-yes)
  5153. I see 1 and I'm going to do: predict-yes
  5154. ENV: Agent did: predict-yes for direction L in state State-B
  5155. In State-B moving L
  5156. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  5157. predict error 0
  5158. dir: dir isU
  5159. -/|\727: O: O1454 (predict-no)
  5160. I see 1 and I'm going to do: predict-no
  5161. ENV: Agent did: predict-no for direction U in state State-A
  5162. In State-A moving U
  5163. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  5164. predict error 0
  5165. dir: dir isU
  5166. -/|728: O: O1456 (predict-no)
  5167. I see 1 and I'm going to do: predict-no
  5168. ENV: Agent did: predict-no for direction U in state State-A
  5169. In State-A moving U
  5170. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  5171. predict error 0
  5172. dir: dir isL
  5173. \-729: O: O1458 (predict-no)
  5174. I see 1 and I'm going to do: predict-no
  5175. ENV: Agent did: predict-no for direction L in state State-A
  5176. In State-A moving L
  5177. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  5178. predict error 0
  5179. dir: dir isU
  5180. /|730: O: O1460 (predict-no)
  5181. I see 1 and I'm going to do: predict-no
  5182. ENV: Agent did: predict-no for direction U in state State-A
  5183. In State-A moving U
  5184. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  5185. predict error 0
  5186. dir: dir isL
  5187. \731: O: O1462 (predict-no)
  5188. I see 1 and I'm going to do: predict-no
  5189. ENV: Agent did: predict-no for direction L in state State-A
  5190. In State-A moving L
  5191. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  5192. predict error 0
  5193. dir: dir isL
  5194. -732: O: O1464 (predict-no)
  5195. I see 1 and I'm going to do: predict-no
  5196. ENV: Agent did: predict-no for direction L in state State-A
  5197. In State-A moving L
  5198. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  5199. predict error 0
  5200. dir: dir isU
  5201. /|733: O: O1466 (predict-no)
  5202. I see 1 and I'm going to do: predict-no
  5203. ENV: Agent did: predict-no for direction U in state State-A
  5204. In State-A moving U
  5205. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  5206. predict error 0
  5207. dir: dir isL
  5208. \-/734: O: O1468 (predict-no)
  5209. I see 1 and I'm going to do: predict-no
  5210. ENV: Agent did: predict-no for direction L in state State-A
  5211. In State-A moving L
  5212. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  5213. predict error 0
  5214. dir: dir isL
  5215. |\735: O: O1470 (predict-no)
  5216. I see 1 and I'm going to do: predict-no
  5217. ENV: Agent did: predict-no for direction L in state State-A
  5218. In State-A moving L
  5219. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  5220. predict error 0
  5221. dir: dir isU
  5222. -/|736: O: O1472 (predict-no)
  5223. I see 1 and I'm going to do: predict-no
  5224. ENV: Agent did: predict-no for direction U in state State-A
  5225. In State-A moving U
  5226. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  5227. predict error 0
  5228. dir: dir isL
  5229. \-/737: O: O1474 (predict-no)
  5230. I see 1 and I'm going to do: predict-no
  5231. ENV: Agent did: predict-no for direction L in state State-A
  5232. In State-A moving L
  5233. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  5234. predict error 0
  5235. dir: dir isR
  5236. |\738: O: O1475 (predict-yes)
  5237. I see 1 and I'm going to do: predict-yes
  5238. ENV: Agent did: predict-yes for direction R in state State-A
  5239. In State-A moving R
  5240. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  5241. predict error 0
  5242. dir: dir isR
  5243. -/739: O: O1478 (predict-no)
  5244. I see 1 and I'm going to do: predict-no
  5245. ENV: Agent did: predict-no for direction R in state State-B
  5246. In State-B moving R
  5247. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5248. predict error 0
  5249. dir: dir isL
  5250. |\-/sleeping...
  5251. |740: O: O1479 (predict-yes)
  5252. I see 1 and I'm going to do: predict-yes
  5253. ENV: Agent did: predict-yes for direction L in state State-B
  5254. In State-B moving L
  5255. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  5256. predict error 0
  5257. dir: dir isL
  5258. \-741: O: O1482 (predict-no)
  5259. I see 1 and I'm going to do: predict-no
  5260. ENV: Agent did: predict-no for direction L in state State-A
  5261. In State-A moving L
  5262. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  5263. predict error 0
  5264. dir: dir isU
  5265. /742: O: O1484 (predict-no)
  5266. I see 1 and I'm going to do: predict-no
  5267. ENV: Agent did: predict-no for direction U in state State-A
  5268. In State-A moving U
  5269. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  5270. predict error 0
  5271. dir: dir isR
  5272. |\743: O: O1485 (predict-yes)
  5273. I see 1 and I'm going to do: predict-yes
  5274. ENV: Agent did: predict-yes for direction R in state State-A
  5275. In State-A moving R
  5276. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  5277. predict error 0
  5278. dir: dir isL
  5279. -/|744: O: O1487 (predict-yes)
  5280. I see 1 and I'm going to do: predict-yes
  5281. ENV: Agent did: predict-yes for direction L in state State-B
  5282. In State-B moving L
  5283. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  5284. predict error 0
  5285. dir: dir isR
  5286. \-/|745: O: O1489 (predict-yes)
  5287. I see 1 and I'm going to do: predict-yes
  5288. ENV: Agent did: predict-yes for direction R in state State-A
  5289. In State-A moving R
  5290. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  5291. predict error 0
  5292. dir: dir isU
  5293. \-/746: O: O1492 (predict-no)
  5294. I see 1 and I'm going to do: predict-no
  5295. ENV: Agent did: predict-no for direction U in state State-B
  5296. In State-B moving U
  5297. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5298. predict error 0
  5299. dir: dir isL
  5300. |\747: O: O1493 (predict-yes)
  5301. I see 1 and I'm going to do: predict-yes
  5302. ENV: Agent did: predict-yes for direction L in state State-B
  5303. In State-B moving L
  5304. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  5305. predict error 0
  5306. dir: dir isL
  5307. -/|\748: O: O1496 (predict-no)
  5308. I see 1 and I'm going to do: predict-no
  5309. ENV: Agent did: predict-no for direction L in state State-A
  5310. In State-A moving L
  5311. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  5312. predict error 0
  5313. dir: dir isU
  5314. -/749: O: O1498 (predict-no)
  5315. I see 1 and I'm going to do: predict-no
  5316. ENV: Agent did: predict-no for direction U in state State-A
  5317. In State-A moving U
  5318. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  5319. predict error 0
  5320. dir: dir isL
  5321. |\750: O: O1500 (predict-no)
  5322. I see 1 and I'm going to do: predict-no
  5323. ENV: Agent did: predict-no for direction L in state State-A
  5324. In State-A moving L
  5325. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  5326. predict error 0
  5327. dir: dir isL
  5328. -/|\751: O: O1502 (predict-no)
  5329. I see 1 and I'm going to do: predict-no
  5330. ENV: Agent did: predict-no for direction L in state State-A
  5331. In State-A moving L
  5332. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  5333. predict error 0
  5334. dir: dir isL
  5335. -752: O: O1504 (predict-no)
  5336. I see 1 and I'm going to do: predict-no
  5337. ENV: Agent did: predict-no for direction L in state State-A
  5338. In State-A moving L
  5339. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  5340. predict error 0
  5341. dir: dir isU
  5342. /|\753: O: O1506 (predict-no)
  5343. I see 1 and I'm going to do: predict-no
  5344. ENV: Agent did: predict-no for direction U in state State-A
  5345. In State-A moving U
  5346. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  5347. predict error 0
  5348. dir: dir isR
  5349. -/|754: O: O1507 (predict-yes)
  5350. I see 1 and I'm going to do: predict-yes
  5351. ENV: Agent did: predict-yes for direction R in state State-A
  5352. In State-A moving R
  5353. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  5354. predict error 0
  5355. dir: dir isU
  5356. \-/755: O: O1510 (predict-no)
  5357. I see 1 and I'm going to do: predict-no
  5358. ENV: Agent did: predict-no for direction U in state State-B
  5359. In State-B moving U
  5360. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5361. predict error 0
  5362. dir: dir isR
  5363. |\-/756: O: O1512 (predict-no)
  5364. I see 1 and I'm going to do: predict-no
  5365. ENV: Agent did: predict-no for direction R in state State-B
  5366. In State-B moving R
  5367. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5368. predict error 0
  5369. dir: dir isU
  5370. |\757: O: O1514 (predict-no)
  5371. I see 1 and I'm going to do: predict-no
  5372. ENV: Agent did: predict-no for direction U in state State-B
  5373. In State-B moving U
  5374. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5375. predict error 0
  5376. dir: dir isR
  5377. -/|758: O: O1516 (predict-no)
  5378. I see 1 and I'm going to do: predict-no
  5379. ENV: Agent did: predict-no for direction R in state State-B
  5380. In State-B moving R
  5381. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5382. predict error 0
  5383. dir: dir isR
  5384. \-/759: O: O1518 (predict-no)
  5385. I see 1 and I'm going to do: predict-no
  5386. ENV: Agent did: predict-no for direction R in state State-B
  5387. In State-B moving R
  5388. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5389. predict error 0
  5390. dir: dir isU
  5391. |\760: O: O1520 (predict-no)
  5392. I see 1 and I'm going to do: predict-no
  5393. ENV: Agent did: predict-no for direction U in state State-B
  5394. In State-B moving U
  5395. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5396. predict error 0
  5397. dir: dir isL
  5398. -761: O: O1521 (predict-yes)
  5399. I see 1 and I'm going to do: predict-yes
  5400. ENV: Agent did: predict-yes for direction L in state State-B
  5401. In State-B moving L
  5402. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  5403. predict error 0
  5404. dir: dir isR
  5405. /762: O: O1523 (predict-yes)
  5406. I see 1 and I'm going to do: predict-yes
  5407. ENV: Agent did: predict-yes for direction R in state State-A
  5408. In State-A moving R
  5409. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  5410. predict error 0
  5411. dir: dir isU
  5412. |\-763: O: O1526 (predict-no)
  5413. I see 1 and I'm going to do: predict-no
  5414. ENV: Agent did: predict-no for direction U in state State-B
  5415. In State-B moving U
  5416. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5417. predict error 0
  5418. dir: dir isR
  5419. /|\-764: O: O1528 (predict-no)
  5420. I see 1 and I'm going to do: predict-no
  5421. ENV: Agent did: predict-no for direction R in state State-B
  5422. In State-B moving R
  5423. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5424. predict error 0
  5425. dir: dir isR
  5426. /|\765: O: O1530 (predict-no)
  5427. I see 1 and I'm going to do: predict-no
  5428. ENV: Agent did: predict-no for direction R in state State-B
  5429. In State-B moving R
  5430. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5431. predict error 0
  5432. dir: dir isU
  5433. -/|766: O: O1532 (predict-no)
  5434. I see 1 and I'm going to do: predict-no
  5435. ENV: Agent did: predict-no for direction U in state State-B
  5436. In State-B moving U
  5437. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5438. predict error 0
  5439. dir: dir isR
  5440. \-767: O: O1534 (predict-no)
  5441. I see 1 and I'm going to do: predict-no
  5442. ENV: Agent did: predict-no for direction R in state State-B
  5443. In State-B moving R
  5444. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5445. predict error 0
  5446. dir: dir isU
  5447. /|\768: O: O1536 (predict-no)
  5448. I see 1 and I'm going to do: predict-no
  5449. ENV: Agent did: predict-no for direction U in state State-B
  5450. In State-B moving U
  5451. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5452. predict error 0
  5453. dir: dir isR
  5454. -/769: O: O1538 (predict-no)
  5455. I see 1 and I'm going to do: predict-no
  5456. ENV: Agent did: predict-no for direction R in state State-B
  5457. In State-B moving R
  5458. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5459. predict error 0
  5460. dir: dir isL
  5461. |\770: O: O1539 (predict-yes)
  5462. I see 1 and I'm going to do: predict-yes
  5463. ENV: Agent did: predict-yes for direction L in state State-B
  5464. In State-B moving L
  5465. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  5466. predict error 0
  5467. dir: dir isR
  5468. -/|771: O: O1541 (predict-yes)
  5469. I see 1 and I'm going to do: predict-yes
  5470. ENV: Agent did: predict-yes for direction R in state State-A
  5471. In State-A moving R
  5472. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  5473. predict error 0
  5474. dir: dir isL
  5475. \772: O: O1543 (predict-yes)
  5476. I see 1 and I'm going to do: predict-yes
  5477. ENV: Agent did: predict-yes for direction L in state State-B
  5478. In State-B moving L
  5479. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  5480. predict error 0
  5481. dir: dir isL
  5482. -/773: O: O1546 (predict-no)
  5483. I see 1 and I'm going to do: predict-no
  5484. ENV: Agent did: predict-no for direction L in state State-A
  5485. In State-A moving L
  5486. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  5487. predict error 0
  5488. dir: dir isL
  5489. |\-774: O: O1548 (predict-no)
  5490. I see 1 and I'm going to do: predict-no
  5491. ENV: Agent did: predict-no for direction L in state State-A
  5492. In State-A moving L
  5493. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  5494. predict error 0
  5495. dir: dir isL
  5496. /|775: O: O1550 (predict-no)
  5497. I see 1 and I'm going to do: predict-no
  5498. ENV: Agent did: predict-no for direction L in state State-A
  5499. In State-A moving L
  5500. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  5501. predict error 0
  5502. dir: dir isR
  5503. \-/776: O: O1551 (predict-yes)
  5504. I see 1 and I'm going to do: predict-yes
  5505. ENV: Agent did: predict-yes for direction R in state State-A
  5506. In State-A moving R
  5507. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  5508. predict error 0
  5509. dir: dir isU
  5510. |\777: O: O1554 (predict-no)
  5511. I see 1 and I'm going to do: predict-no
  5512. ENV: Agent did: predict-no for direction U in state State-B
  5513. In State-B moving U
  5514. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5515. predict error 0
  5516. dir: dir isU
  5517. -/|\778: O: O1556 (predict-no)
  5518. I see 1 and I'm going to do: predict-no
  5519. ENV: Agent did: predict-no for direction U in state State-B
  5520. In State-B moving U
  5521. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5522. predict error 0
  5523. dir: dir isU
  5524. -/|779: O: O1558 (predict-no)
  5525. I see 1 and I'm going to do: predict-no
  5526. ENV: Agent did: predict-no for direction U in state State-B
  5527. In State-B moving U
  5528. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5529. predict error 0
  5530. dir: dir isL
  5531. \-/780: O: O1559 (predict-yes)
  5532. I see 1 and I'm going to do: predict-yes
  5533. ENV: Agent did: predict-yes for direction L in state State-B
  5534. In State-B moving L
  5535. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  5536. predict error 0
  5537. dir: dir isU
  5538. |\781: O: O1562 (predict-no)
  5539. I see 1 and I'm going to do: predict-no
  5540. ENV: Agent did: predict-no for direction U in state State-A
  5541. In State-A moving U
  5542. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  5543. predict error 0
  5544. dir: dir isU
  5545. -782: O: O1564 (predict-no)
  5546. I see 1 and I'm going to do: predict-no
  5547. ENV: Agent did: predict-no for direction U in state State-A
  5548. In State-A moving U
  5549. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  5550. predict error 0
  5551. dir: dir isR
  5552. /|\783: O: O1565 (predict-yes)
  5553. I see 1 and I'm going to do: predict-yes
  5554. ENV: Agent did: predict-yes for direction R in state State-A
  5555. In State-A moving R
  5556. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  5557. predict error 0
  5558. dir: dir isU
  5559. -/|784: O: O1568 (predict-no)
  5560. I see 1 and I'm going to do: predict-no
  5561. ENV: Agent did: predict-no for direction U in state State-B
  5562. In State-B moving U
  5563. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5564. predict error 0
  5565. dir: dir isL
  5566. \-/785: O: O1569 (predict-yes)
  5567. I see 1 and I'm going to do: predict-yes
  5568. ENV: Agent did: predict-yes for direction L in state State-B
  5569. In State-B moving L
  5570. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  5571. predict error 0
  5572. dir: dir isU
  5573. |\-786: O: O1572 (predict-no)
  5574. I see 1 and I'm going to do: predict-no
  5575. ENV: Agent did: predict-no for direction U in state State-A
  5576. In State-A moving U
  5577. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  5578. predict error 0
  5579. dir: dir isU
  5580. /|787: O: O1574 (predict-no)
  5581. I see 1 and I'm going to do: predict-no
  5582. ENV: Agent did: predict-no for direction U in state State-A
  5583. In State-A moving U
  5584. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  5585. predict error 0
  5586. dir: dir isU
  5587. \-788: O: O1576 (predict-no)
  5588. I see 1 and I'm going to do: predict-no
  5589. ENV: Agent did: predict-no for direction U in state State-A
  5590. In State-A moving U
  5591. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  5592. predict error 0
  5593. dir: dir isU
  5594. /|789: O: O1578 (predict-no)
  5595. I see 1 and I'm going to do: predict-no
  5596. ENV: Agent did: predict-no for direction U in state State-A
  5597. In State-A moving U
  5598. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  5599. predict error 0
  5600. dir: dir isU
  5601. \-790: O: O1580 (predict-no)
  5602. I see 1 and I'm going to do: predict-no
  5603. ENV: Agent did: predict-no for direction U in state State-A
  5604. In State-A moving U
  5605. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  5606. predict error 0
  5607. dir: dir isR
  5608. /|\-sleeping...
  5609. /791: O: O1581 (predict-yes)
  5610. I see 1 and I'm going to do: predict-yes
  5611. ENV: Agent did: predict-yes for direction R in state State-A
  5612. In State-A moving R
  5613. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  5614. predict error 0
  5615. dir: dir isU
  5616. |792: O: O1584 (predict-no)
  5617. I see 1 and I'm going to do: predict-no
  5618. ENV: Agent did: predict-no for direction U in state State-B
  5619. In State-B moving U
  5620. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5621. predict error 0
  5622. dir: dir isU
  5623. \-/793: O: O1586 (predict-no)
  5624. I see 1 and I'm going to do: predict-no
  5625. ENV: Agent did: predict-no for direction U in state State-B
  5626. In State-B moving U
  5627. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5628. predict error 0
  5629. dir: dir isR
  5630. |\-794: O: O1588 (predict-no)
  5631. I see 1 and I'm going to do: predict-no
  5632. ENV: Agent did: predict-no for direction R in state State-B
  5633. In State-B moving R
  5634. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5635. predict error 0
  5636. dir: dir isR
  5637. /|\-795: O: O1590 (predict-no)
  5638. I see 1 and I'm going to do: predict-no
  5639. ENV: Agent did: predict-no for direction R in state State-B
  5640. In State-B moving R
  5641. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5642. predict error 0
  5643. dir: dir isU
  5644. /|\796: O: O1592 (predict-no)
  5645. I see 1 and I'm going to do: predict-no
  5646. ENV: Agent did: predict-no for direction U in state State-B
  5647. In State-B moving U
  5648. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5649. predict error 0
  5650. dir: dir isL
  5651. -/|797: O: O1593 (predict-yes)
  5652. I see 1 and I'm going to do: predict-yes
  5653. ENV: Agent did: predict-yes for direction L in state State-B
  5654. In State-B moving L
  5655. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  5656. predict error 0
  5657. dir: dir isR
  5658. \-/798: O: O1595 (predict-yes)
  5659. I see 1 and I'm going to do: predict-yes
  5660. ENV: Agent did: predict-yes for direction R in state State-A
  5661. In State-A moving R
  5662. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  5663. predict error 0
  5664. dir: dir isL
  5665. |\-799: O: O1597 (predict-yes)
  5666. I see 1 and I'm going to do: predict-yes
  5667. ENV: Agent did: predict-yes for direction L in state State-B
  5668. In State-B moving L
  5669. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  5670. predict error 0
  5671. dir: dir isU
  5672. /|\800: O: O1600 (predict-no)
  5673. I see 1 and I'm going to do: predict-no
  5674. ENV: Agent did: predict-no for direction U in state State-A
  5675. In State-A moving U
  5676. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  5677. predict error 0
  5678. dir: dir isR
  5679. -/|801: O: O1601 (predict-yes)
  5680. I see 1 and I'm going to do: predict-yes
  5681. ENV: Agent did: predict-yes for direction R in state State-A
  5682. In State-A moving R
  5683. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  5684. predict error 0
  5685. dir: dir isU
  5686. \802: O: O1604 (predict-no)
  5687. I see 1 and I'm going to do: predict-no
  5688. ENV: Agent did: predict-no for direction U in state State-B
  5689. In State-B moving U
  5690. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5691. predict error 0
  5692. dir: dir isL
  5693. -/|803: O: O1605 (predict-yes)
  5694. I see 1 and I'm going to do: predict-yes
  5695. ENV: Agent did: predict-yes for direction L in state State-B
  5696. In State-B moving L
  5697. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  5698. predict error 0
  5699. dir: dir isL
  5700. \-/804: O: O1608 (predict-no)
  5701. I see 1 and I'm going to do: predict-no
  5702. ENV: Agent did: predict-no for direction L in state State-A
  5703. In State-A moving L
  5704. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  5705. predict error 0
  5706. dir: dir isR
  5707. |\805: O: O1609 (predict-yes)
  5708. I see 1 and I'm going to do: predict-yes
  5709. ENV: Agent did: predict-yes for direction R in state State-A
  5710. In State-A moving R
  5711. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  5712. predict error 0
  5713. dir: dir isU
  5714. -/|806: O: O1612 (predict-no)
  5715. I see 1 and I'm going to do: predict-no
  5716. ENV: Agent did: predict-no for direction U in state State-B
  5717. In State-B moving U
  5718. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5719. predict error 0
  5720. dir: dir isR
  5721. \-/807: O: O1614 (predict-no)
  5722. I see 1 and I'm going to do: predict-no
  5723. ENV: Agent did: predict-no for direction R in state State-B
  5724. In State-B moving R
  5725. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5726. predict error 0
  5727. dir: dir isR
  5728. |\808: O: O1616 (predict-no)
  5729. I see 1 and I'm going to do: predict-no
  5730. ENV: Agent did: predict-no for direction R in state State-B
  5731. In State-B moving R
  5732. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5733. predict error 0
  5734. dir: dir isR
  5735. -/|809: O: O1618 (predict-no)
  5736. I see 1 and I'm going to do: predict-no
  5737. ENV: Agent did: predict-no for direction R in state State-B
  5738. In State-B moving R
  5739. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5740. predict error 0
  5741. dir: dir isU
  5742. \-/810: O: O1620 (predict-no)
  5743. I see 1 and I'm going to do: predict-no
  5744. ENV: Agent did: predict-no for direction U in state State-B
  5745. In State-B moving U
  5746. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5747. predict error 0
  5748. dir: dir isL
  5749. |\-811: O: O1621 (predict-yes)
  5750. I see 1 and I'm going to do: predict-yes
  5751. ENV: Agent did: predict-yes for direction L in state State-B
  5752. In State-B moving L
  5753. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  5754. predict error 0
  5755. dir: dir isU
  5756. /812: O: O1624 (predict-no)
  5757. I see 1 and I'm going to do: predict-no
  5758. ENV: Agent did: predict-no for direction U in state State-A
  5759. In State-A moving U
  5760. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  5761. predict error 0
  5762. dir: dir isL
  5763. |\-/813: O: O1626 (predict-no)
  5764. I see 1 and I'm going to do: predict-no
  5765. ENV: Agent did: predict-no for direction L in state State-A
  5766. In State-A moving L
  5767. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  5768. predict error 0
  5769. dir: dir isU
  5770. |\-814: O: O1628 (predict-no)
  5771. I see 1 and I'm going to do: predict-no
  5772. ENV: Agent did: predict-no for direction U in state State-A
  5773. In State-A moving U
  5774. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  5775. predict error 0
  5776. dir: dir isU
  5777. /|\815: O: O1630 (predict-no)
  5778. I see 1 and I'm going to do: predict-no
  5779. ENV: Agent did: predict-no for direction U in state State-A
  5780. In State-A moving U
  5781. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  5782. predict error 0
  5783. dir: dir isR
  5784. -/|816: O: O1631 (predict-yes)
  5785. I see 1 and I'm going to do: predict-yes
  5786. ENV: Agent did: predict-yes for direction R in state State-A
  5787. In State-A moving R
  5788. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  5789. predict error 0
  5790. dir: dir isU
  5791. \-/|817: O: O1634 (predict-no)
  5792. I see 1 and I'm going to do: predict-no
  5793. ENV: Agent did: predict-no for direction U in state State-B
  5794. In State-B moving U
  5795. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5796. predict error 0
  5797. dir: dir isL
  5798. \-/818: O: O1635 (predict-yes)
  5799. I see 1 and I'm going to do: predict-yes
  5800. ENV: Agent did: predict-yes for direction L in state State-B
  5801. In State-B moving L
  5802. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  5803. predict error 0
  5804. dir: dir isL
  5805. |\-819: O: O1638 (predict-no)
  5806. I see 1 and I'm going to do: predict-no
  5807. ENV: Agent did: predict-no for direction L in state State-A
  5808. In State-A moving L
  5809. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  5810. predict error 0
  5811. dir: dir isR
  5812. /|\-820: O: O1639 (predict-yes)
  5813. I see 1 and I'm going to do: predict-yes
  5814. ENV: Agent did: predict-yes for direction R in state State-A
  5815. In State-A moving R
  5816. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  5817. predict error 0
  5818. dir: dir isL
  5819. /|\821: O: O1641 (predict-yes)
  5820. I see 1 and I'm going to do: predict-yes
  5821. ENV: Agent did: predict-yes for direction L in state State-B
  5822. In State-B moving L
  5823. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  5824. predict error 0
  5825. dir: dir isU
  5826. -822: O: O1644 (predict-no)
  5827. I see 1 and I'm going to do: predict-no
  5828. ENV: Agent did: predict-no for direction U in state State-A
  5829. In State-A moving U
  5830. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  5831. predict error 0
  5832. dir: dir isR
  5833. /|823: O: O1645 (predict-yes)
  5834. I see 1 and I'm going to do: predict-yes
  5835. ENV: Agent did: predict-yes for direction R in state State-A
  5836. In State-A moving R
  5837. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  5838. predict error 0
  5839. dir: dir isR
  5840. \-/|824: O: O1648 (predict-no)
  5841. I see 1 and I'm going to do: predict-no
  5842. ENV: Agent did: predict-no for direction R in state State-B
  5843. In State-B moving R
  5844. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5845. predict error 0
  5846. dir: dir isU
  5847. \-/825: O: O1650 (predict-no)
  5848. I see 1 and I'm going to do: predict-no
  5849. ENV: Agent did: predict-no for direction U in state State-B
  5850. In State-B moving U
  5851. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5852. predict error 0
  5853. dir: dir isU
  5854. |\826: O: O1652 (predict-no)
  5855. I see 1 and I'm going to do: predict-no
  5856. ENV: Agent did: predict-no for direction U in state State-B
  5857. In State-B moving U
  5858. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5859. predict error 0
  5860. dir: dir isU
  5861. -/|\827: O: O1654 (predict-no)
  5862. I see 1 and I'm going to do: predict-no
  5863. ENV: Agent did: predict-no for direction U in state State-B
  5864. In State-B moving U
  5865. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5866. predict error 0
  5867. dir: dir isU
  5868. -828: O: O1656 (predict-no)
  5869. I see 1 and I'm going to do: predict-no
  5870. ENV: Agent did: predict-no for direction U in state State-B
  5871. In State-B moving U
  5872. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5873. predict error 0
  5874. dir: dir isU
  5875. /|829: O: O1658 (predict-no)
  5876. I see 1 and I'm going to do: predict-no
  5877. ENV: Agent did: predict-no for direction U in state State-B
  5878. In State-B moving U
  5879. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5880. predict error 0
  5881. dir: dir isU
  5882. \-/|830: O: O1660 (predict-no)
  5883. I see 1 and I'm going to do: predict-no
  5884. ENV: Agent did: predict-no for direction U in state State-B
  5885. In State-B moving U
  5886. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5887. predict error 0
  5888. dir: dir isR
  5889. \-/831: O: O1662 (predict-no)
  5890. I see 1 and I'm going to do: predict-no
  5891. ENV: Agent did: predict-no for direction R in state State-B
  5892. In State-B moving R
  5893. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5894. predict error 0
  5895. dir: dir isR
  5896. |832: O: O1664 (predict-no)
  5897. I see 1 and I'm going to do: predict-no
  5898. ENV: Agent did: predict-no for direction R in state State-B
  5899. In State-B moving R
  5900. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5901. predict error 0
  5902. dir: dir isU
  5903. \-/|833: O: O1666 (predict-no)
  5904. I see 1 and I'm going to do: predict-no
  5905. ENV: Agent did: predict-no for direction U in state State-B
  5906. In State-B moving U
  5907. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5908. predict error 0
  5909. dir: dir isU
  5910. \-/834: O: O1668 (predict-no)
  5911. I see 1 and I'm going to do: predict-no
  5912. ENV: Agent did: predict-no for direction U in state State-B
  5913. In State-B moving U
  5914. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5915. predict error 0
  5916. dir: dir isU
  5917. |\-835: O: O1670 (predict-no)
  5918. I see 1 and I'm going to do: predict-no
  5919. ENV: Agent did: predict-no for direction U in state State-B
  5920. In State-B moving U
  5921. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5922. predict error 0
  5923. dir: dir isU
  5924. /|836: O: O1672 (predict-no)
  5925. I see 1 and I'm going to do: predict-no
  5926. ENV: Agent did: predict-no for direction U in state State-B
  5927. In State-B moving U
  5928. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5929. predict error 0
  5930. dir: dir isU
  5931. \-/837: O: O1674 (predict-no)
  5932. I see 1 and I'm going to do: predict-no
  5933. ENV: Agent did: predict-no for direction U in state State-B
  5934. In State-B moving U
  5935. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5936. predict error 0
  5937. dir: dir isL
  5938. |\-838: O: O1675 (predict-yes)
  5939. I see 1 and I'm going to do: predict-yes
  5940. ENV: Agent did: predict-yes for direction L in state State-B
  5941. In State-B moving L
  5942. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  5943. predict error 0
  5944. dir: dir isR
  5945. /|839: O: O1677 (predict-yes)
  5946. I see 1 and I'm going to do: predict-yes
  5947. ENV: Agent did: predict-yes for direction R in state State-A
  5948. In State-A moving R
  5949. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  5950. predict error 0
  5951. dir: dir isL
  5952. \-840: O: O1679 (predict-yes)
  5953. I see 1 and I'm going to do: predict-yes
  5954. ENV: Agent did: predict-yes for direction L in state State-B
  5955. In State-B moving L
  5956. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  5957. predict error 0
  5958. dir: dir isR
  5959. /|\841: O: O1681 (predict-yes)
  5960. I see 1 and I'm going to do: predict-yes
  5961. ENV: Agent did: predict-yes for direction R in state State-A
  5962. In State-A moving R
  5963. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  5964. predict error 0
  5965. dir: dir isL
  5966. -842: O: O1683 (predict-yes)
  5967. I see 1 and I'm going to do: predict-yes
  5968. ENV: Agent did: predict-yes for direction L in state State-B
  5969. In State-B moving L
  5970. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  5971. predict error 0
  5972. dir: dir isL
  5973. /|\-843: O: O1686 (predict-no)
  5974. I see 1 and I'm going to do: predict-no
  5975. ENV: Agent did: predict-no for direction L in state State-A
  5976. In State-A moving L
  5977. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  5978. predict error 0
  5979. dir: dir isU
  5980. /|844: O: O1688 (predict-no)
  5981. I see 1 and I'm going to do: predict-no
  5982. ENV: Agent did: predict-no for direction U in state State-A
  5983. In State-A moving U
  5984. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  5985. predict error 0
  5986. dir: dir isU
  5987. \-/845: O: O1690 (predict-no)
  5988. I see 1 and I'm going to do: predict-no
  5989. ENV: Agent did: predict-no for direction U in state State-A
  5990. In State-A moving U
  5991. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  5992. predict error 0
  5993. dir: dir isL
  5994. |\846: O: O1692 (predict-no)
  5995. I see 1 and I'm going to do: predict-no
  5996. ENV: Agent did: predict-no for direction L in state State-A
  5997. In State-A moving L
  5998. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  5999. predict error 0
  6000. dir: dir isL
  6001. -/847: O: O1694 (predict-no)
  6002. I see 1 and I'm going to do: predict-no
  6003. ENV: Agent did: predict-no for direction L in state State-A
  6004. In State-A moving L
  6005. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  6006. predict error 0
  6007. dir: dir isU
  6008. |\848: O: O1696 (predict-no)
  6009. I see 1 and I'm going to do: predict-no
  6010. ENV: Agent did: predict-no for direction U in state State-A
  6011. In State-A moving U
  6012. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  6013. predict error 0
  6014. dir: dir isU
  6015. -/|849: O: O1698 (predict-no)
  6016. I see 1 and I'm going to do: predict-no
  6017. ENV: Agent did: predict-no for direction U in state State-A
  6018. In State-A moving U
  6019. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  6020. predict error 0
  6021. dir: dir isL
  6022. \-/850: O: O1700 (predict-no)
  6023. I see 1 and I'm going to do: predict-no
  6024. ENV: Agent did: predict-no for direction L in state State-A
  6025. In State-A moving L
  6026. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  6027. predict error 0
  6028. dir: dir isU
  6029. |851: O: O1702 (predict-no)
  6030. I see 1 and I'm going to do: predict-no
  6031. ENV: Agent did: predict-no for direction U in state State-A
  6032. In State-A moving U
  6033. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  6034. predict error 0
  6035. dir: dir isU
  6036. \852: O: O1704 (predict-no)
  6037. I see 1 and I'm going to do: predict-no
  6038. ENV: Agent did: predict-no for direction U in state State-A
  6039. In State-A moving U
  6040. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  6041. predict error 0
  6042. dir: dir isR
  6043. -/|\853: O: O1705 (predict-yes)
  6044. I see 1 and I'm going to do: predict-yes
  6045. ENV: Agent did: predict-yes for direction R in state State-A
  6046. In State-A moving R
  6047. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  6048. predict error 0
  6049. dir: dir isL
  6050. -/|854: O: O1707 (predict-yes)
  6051. I see 1 and I'm going to do: predict-yes
  6052. ENV: Agent did: predict-yes for direction L in state State-B
  6053. In State-B moving L
  6054. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  6055. predict error 0
  6056. dir: dir isL
  6057. \-/855: O: O1710 (predict-no)
  6058. I see 1 and I'm going to do: predict-no
  6059. ENV: Agent did: predict-no for direction L in state State-A
  6060. In State-A moving L
  6061. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  6062. predict error 0
  6063. dir: dir isL
  6064. |\856: O: O1712 (predict-no)
  6065. I see 1 and I'm going to do: predict-no
  6066. ENV: Agent did: predict-no for direction L in state State-A
  6067. In State-A moving L
  6068. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  6069. predict error 0
  6070. dir: dir isR
  6071. -/857: O: O1713 (predict-yes)
  6072. I see 1 and I'm going to do: predict-yes
  6073. ENV: Agent did: predict-yes for direction R in state State-A
  6074. In State-A moving R
  6075. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  6076. predict error 0
  6077. dir: dir isU
  6078. |\-858: O: O1716 (predict-no)
  6079. I see 1 and I'm going to do: predict-no
  6080. ENV: Agent did: predict-no for direction U in state State-B
  6081. In State-B moving U
  6082. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  6083. predict error 0
  6084. dir: dir isR
  6085. /|859: O: O1718 (predict-no)
  6086. I see 1 and I'm going to do: predict-no
  6087. ENV: Agent did: predict-no for direction R in state State-B
  6088. In State-B moving R
  6089. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  6090. predict error 0
  6091. dir: dir isL
  6092. \-860: O: O1719 (predict-yes)
  6093. I see 1 and I'm going to do: predict-yes
  6094. ENV: Agent did: predict-yes for direction L in state State-B
  6095. In State-B moving L
  6096. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  6097. predict error 0
  6098. dir: dir isU
  6099. /|\861: O: O1722 (predict-no)
  6100. I see 1 and I'm going to do: predict-no
  6101. ENV: Agent did: predict-no for direction U in state State-A
  6102. In State-A moving U
  6103. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  6104. predict error 0
  6105. dir: dir isL
  6106. -862: O: O1724 (predict-no)
  6107. I see 1 and I'm going to do: predict-no
  6108. ENV: Agent did: predict-no for direction L in state State-A
  6109. In State-A moving L
  6110. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  6111. predict error 0
  6112. dir: dir isR
  6113. /|863: O: O1725 (predict-yes)
  6114. I see 1 and I'm going to do: predict-yes
  6115. ENV: Agent did: predict-yes for direction R in state State-A
  6116. In State-A moving R
  6117. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  6118. predict error 0
  6119. dir: dir isL
  6120. \-/|864: O: O1727 (predict-yes)
  6121. I see 1 and I'm going to do: predict-yes
  6122. ENV: Agent did: predict-yes for direction L in state State-B
  6123. In State-B moving L
  6124. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  6125. predict error 0
  6126. dir: dir isL
  6127. \-/865: O: O1730 (predict-no)
  6128. I see 1 and I'm going to do: predict-no
  6129. ENV: Agent did: predict-no for direction L in state State-A
  6130. In State-A moving L
  6131. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  6132. predict error 0
  6133. dir: dir isL
  6134. |\-/866: O: O1732 (predict-no)
  6135. I see 1 and I'm going to do: predict-no
  6136. ENV: Agent did: predict-no for direction L in state State-A
  6137. In State-A moving L
  6138. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  6139. predict error 0
  6140. dir: dir isU
  6141. |\867: O: O1734 (predict-no)
  6142. I see 1 and I'm going to do: predict-no
  6143. ENV: Agent did: predict-no for direction U in state State-A
  6144. In State-A moving U
  6145. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  6146. predict error 0
  6147. dir: dir isL
  6148. -/|868: O: O1736 (predict-no)
  6149. I see 1 and I'm going to do: predict-no
  6150. ENV: Agent did: predict-no for direction L in state State-A
  6151. In State-A moving L
  6152. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  6153. predict error 0
  6154. dir: dir isL
  6155. \-869: O: O1738 (predict-no)
  6156. I see 1 and I'm going to do: predict-no
  6157. ENV: Agent did: predict-no for direction L in state State-A
  6158. In State-A moving L
  6159. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  6160. predict error 0
  6161. dir: dir isR
  6162. /|870: O: O1739 (predict-yes)
  6163. I see 1 and I'm going to do: predict-yes
  6164. ENV: Agent did: predict-yes for direction R in state State-A
  6165. In State-A moving R
  6166. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  6167. predict error 0
  6168. dir: dir isR
  6169. \-/871: O: O1742 (predict-no)
  6170. I see 1 and I'm going to do: predict-no
  6171. ENV: Agent did: predict-no for direction R in state State-B
  6172. In State-B moving R
  6173. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  6174. predict error 0
  6175. dir: dir isR
  6176. |872: O: O1744 (predict-no)
  6177. I see 1 and I'm going to do: predict-no
  6178. ENV: Agent did: predict-no for direction R in state State-B
  6179. In State-B moving R
  6180. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  6181. predict error 0
  6182. dir: dir isR
  6183. \-873: O: O1746 (predict-no)
  6184. I see 1 and I'm going to do: predict-no
  6185. ENV: Agent did: predict-no for direction R in state State-B
  6186. In State-B moving R
  6187. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  6188. predict error 0
  6189. dir: dir isU
  6190. /|874: O: O1748 (predict-no)
  6191. I see 1 and I'm going to do: predict-no
  6192. ENV: Agent did: predict-no for direction U in state State-B
  6193. In State-B moving U
  6194. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  6195. predict error 0
  6196. dir: dir isU
  6197. \-/875: O: O1750 (predict-no)
  6198. I see 1 and I'm going to do: predict-no
  6199. ENV: Agent did: predict-no for direction U in state State-B
  6200. In State-B moving U
  6201. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  6202. predict error 0
  6203. dir: dir isR
  6204. |\-876: O: O1752 (predict-no)
  6205. I see 1 and I'm going to do: predict-no
  6206. ENV: Agent did: predict-no for direction R in state State-B
  6207. In State-B moving R
  6208. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  6209. predict error 0
  6210. dir: dir isR
  6211. /|877: O: O1754 (predict-no)
  6212. I see 1 and I'm going to do: predict-no
  6213. ENV: Agent did: predict-no for direction R in state State-B
  6214. In State-B moving R
  6215. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  6216. predict error 0
  6217. dir: dir isL
  6218. \-878: O: O1755 (predict-yes)
  6219. I see 1 and I'm going to do: predict-yes
  6220. ENV: Agent did: predict-yes for direction L in state State-B
  6221. In State-B moving L
  6222. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  6223. predict error 0
  6224. dir: dir isL
  6225. /|\879: O: O1758 (predict-no)
  6226. I see 1 and I'm going to do: predict-no
  6227. ENV: Agent did: predict-no for direction L in state State-A
  6228. In State-A moving L
  6229. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  6230. predict error 0
  6231. dir: dir isL
  6232. -/|880: O: O1760 (predict-no)
  6233. I see 1 and I'm going to do: predict-no
  6234. ENV: Agent did: predict-no for direction L in state State-A
  6235. In State-A moving L
  6236. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  6237. predict error 0
  6238. dir: dir isU
  6239. \-881: O: O1762 (predict-no)
  6240. I see 1 and I'm going to do: predict-no
  6241. ENV: Agent did: predict-no for direction U in state State-A
  6242. In State-A moving U
  6243. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  6244. predict error 0
  6245. dir: dir isR
  6246. /882: O: O1763 (predict-yes)
  6247. I see 1 and I'm going to do: predict-yes
  6248. ENV: Agent did: predict-yes for direction R in state State-A
  6249. In State-A moving R
  6250. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  6251. predict error 0
  6252. dir: dir isU
  6253. |\-883: O: O1766 (predict-no)
  6254. I see 1 and I'm going to do: predict-no
  6255. ENV: Agent did: predict-no for direction U in state State-B
  6256. In State-B moving U
  6257. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  6258. predict error 0
  6259. dir: dir isU
  6260. /|884: O: O1768 (predict-no)
  6261. I see 1 and I'm going to do: predict-no
  6262. ENV: Agent did: predict-no for direction U in state State-B
  6263. In State-B moving U
  6264. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  6265. predict error 0
  6266. dir: dir isR
  6267. \-/885: O: O1770 (predict-no)
  6268. I see 1 and I'm going to do: predict-no
  6269. ENV: Agent did: predict-no for direction R in state State-B
  6270. In State-B moving R
  6271. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  6272. predict error 0
  6273. dir: dir isL
  6274. |\-/886: O: O1771 (predict-yes)
  6275. I see 1 and I'm going to do: predict-yes
  6276. ENV: Agent did: predict-yes for direction L in state State-B
  6277. In State-B moving L
  6278. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  6279. predict error 0
  6280. dir: dir isL
  6281. |\-887: O: O1774 (predict-no)
  6282. I see 1 and I'm going to do: predict-no
  6283. ENV: Agent did: predict-no for direction L in state State-A
  6284. In State-A moving L
  6285. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  6286. predict error 0
  6287. dir: dir isR
  6288. /|\-888: O: O1775 (predict-yes)
  6289. I see 1 and I'm going to do: predict-yes
  6290. ENV: Agent did: predict-yes for direction R in state State-A
  6291. In State-A moving R
  6292. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  6293. predict error 0
  6294. dir: dir isR
  6295. /|\889: O: O1778 (predict-no)
  6296. I see 1 and I'm going to do: predict-no
  6297. ENV: Agent did: predict-no for direction R in state State-B
  6298. In State-B moving R
  6299. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  6300. predict error 0
  6301. dir: dir isL
  6302. -/|890: O: O1779 (predict-yes)
  6303. I see 1 and I'm going to do: predict-yes
  6304. ENV: Agent did: predict-yes for direction L in state State-B
  6305. In State-B moving L
  6306. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  6307. predict error 0
  6308. dir: dir isU
  6309. \-891: O: O1782 (predict-no)
  6310. I see 1 and I'm going to do: predict-no
  6311. ENV: Agent did: predict-no for direction U in state State-A
  6312. In State-A moving U
  6313. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  6314. predict error 0
  6315. dir: dir isR
  6316. /892: O: O1783 (predict-yes)
  6317. I see 1 and I'm going to do: predict-yes
  6318. ENV: Agent did: predict-yes for direction R in state State-A
  6319. In State-A moving R
  6320. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  6321. predict error 0
  6322. dir: dir isU
  6323. |\893: O: O1786 (predict-no)
  6324. I see 1 and I'm going to do: predict-no
  6325. ENV: Agent did: predict-no for direction U in state State-B
  6326. In State-B moving U
  6327. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  6328. predict error 0
  6329. dir: dir isU
  6330. -/894: O: O1788 (predict-no)
  6331. I see 1 and I'm going to do: predict-no
  6332. ENV: Agent did: predict-no for direction U in state State-B
  6333. In State-B moving U
  6334. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  6335. predict error 0
  6336. dir: dir isU
  6337. |\895: O: O1790 (predict-no)
  6338. I see 1 and I'm going to do: predict-no
  6339. ENV: Agent did: predict-no for direction U in state State-B
  6340. In State-B moving U
  6341. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  6342. predict error 0
  6343. dir: dir isU
  6344. -/896: O: O1792 (predict-no)
  6345. I see 1 and I'm going to do: predict-no
  6346. ENV: Agent did: predict-no for direction U in state State-B
  6347. In State-B moving U
  6348. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  6349. predict error 0
  6350. dir: dir isU
  6351. |\897: O: O1794 (predict-no)
  6352. I see 1 and I'm going to do: predict-no
  6353. ENV: Agent did: predict-no for direction U in state State-B
  6354. In State-B moving U
  6355. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  6356. predict error 0
  6357. dir: dir isR
  6358. -/898: O: O1796 (predict-no)
  6359. I see 1 and I'm going to do: predict-no
  6360. ENV: Agent did: predict-no for direction R in state State-B
  6361. In State-B moving R
  6362. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  6363. predict error 0
  6364. dir: dir isU
  6365. |\899: O: O1798 (predict-no)
  6366. I see 1 and I'm going to do: predict-no
  6367. ENV: Agent did: predict-no for direction U in state State-B
  6368. In State-B moving U
  6369. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  6370. predict error 0
  6371. dir: dir isU
  6372. -/|900: O: O1800 (predict-no)
  6373. I see 1 and I'm going to do: predict-no
  6374. ENV: Agent did: predict-no for direction U in state State-B
  6375. In State-B moving U
  6376. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  6377. predict error 0
  6378. dir: dir isL
  6379. \-901: O: O1801 (predict-yes)
  6380. I see 1 and I'm going to do: predict-yes
  6381. ENV: Agent did: predict-yes for direction L in state State-B
  6382. In State-B moving L
  6383. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  6384. predict error 0
  6385. dir: dir isL
  6386. /902: O: O1804 (predict-no)
  6387. I see 1 and I'm going to do: predict-no
  6388. ENV: Agent did: predict-no for direction L in state State-A
  6389. In State-A moving L
  6390. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  6391. predict error 0
  6392. dir: dir isL
  6393. |\-903: O: O1806 (predict-no)
  6394. I see 1 and I'm going to do: predict-no
  6395. ENV: Agent did: predict-no for direction L in state State-A
  6396. In State-A moving L
  6397. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  6398. predict error 0
  6399. dir: dir isR
  6400. /|\904: O: O1807 (predict-yes)
  6401. I see 1 and I'm going to do: predict-yes
  6402. ENV: Agent did: predict-yes for direction R in state State-A
  6403. In State-A moving R
  6404. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  6405. predict error 0
  6406. dir: dir isU
  6407. -/|905: O: O1810 (predict-no)
  6408. I see 1 and I'm going to do: predict-no
  6409. ENV: Agent did: predict-no for direction U in state State-B
  6410. In State-B moving U
  6411. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  6412. predict error 0
  6413. dir: dir isR
  6414. \-/|906: O: O1812 (predict-no)
  6415. I see 1 and I'm going to do: predict-no
  6416. ENV: Agent did: predict-no for direction R in state State-B
  6417. In State-B moving R
  6418. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  6419. predict error 0
  6420. dir: dir isU
  6421. \-907: O: O1814 (predict-no)
  6422. I see 1 and I'm going to do: predict-no
  6423. ENV: Agent did: predict-no for direction U in state State-B
  6424. In State-B moving U
  6425. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  6426. predict error 0
  6427. dir: dir isR
  6428. /|\908: O: O1816 (predict-no)
  6429. I see 1 and I'm going to do: predict-no
  6430. ENV: Agent did: predict-no for direction R in state State-B
  6431. In State-B moving R
  6432. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  6433. predict error 0
  6434. dir: dir isR
  6435. -/909: O: O1818 (predict-no)
  6436. I see 1 and I'm going to do: predict-no
  6437. ENV: Agent did: predict-no for direction R in state State-B
  6438. In State-B moving R
  6439. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  6440. predict error 0
  6441. dir: dir isL
  6442. |\910: O: O1819 (predict-yes)
  6443. I see 1 and I'm going to do: predict-yes
  6444. ENV: Agent did: predict-yes for direction L in state State-B
  6445. In State-B moving L
  6446. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  6447. predict error 0
  6448. dir: dir isR
  6449. -/|911: O: O1821 (predict-yes)
  6450. I see 1 and I'm going to do: predict-yes
  6451. ENV: Agent did: predict-yes for direction R in state State-A
  6452. In State-A moving R
  6453. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  6454. predict error 0
  6455. dir: dir isL
  6456. \912: O: O1823 (predict-yes)
  6457. I see 1 and I'm going to do: predict-yes
  6458. ENV: Agent did: predict-yes for direction L in state State-B
  6459. In State-B moving L
  6460. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  6461. predict error 0
  6462. dir: dir isL
  6463. -/|\913: O: O1826 (predict-no)
  6464. I see 1 and I'm going to do: predict-no
  6465. ENV: Agent did: predict-no for direction L in state State-A
  6466. In State-A moving L
  6467. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  6468. predict error 0
  6469. dir: dir isR
  6470. -914: O: O1827 (predict-yes)
  6471. I see 1 and I'm going to do: predict-yes
  6472. ENV: Agent did: predict-yes for direction R in state State-A
  6473. In State-A moving R
  6474. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  6475. predict error 0
  6476. dir: dir isR
  6477. /|915: O: O1830 (predict-no)
  6478. I see 1 and I'm going to do: predict-no
  6479. ENV: Agent did: predict-no for direction R in state State-B
  6480. In State-B moving R
  6481. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  6482. predict error 0
  6483. dir: dir isU
  6484. \-/916: O: O1832 (predict-no)
  6485. I see 1 and I'm going to do: predict-no
  6486. ENV: Agent did: predict-no for direction U in state State-B
  6487. In State-B moving U
  6488. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  6489. predict error 0
  6490. dir: dir isL
  6491. |\917: O: O1833 (predict-yes)
  6492. I see 1 and I'm going to do: predict-yes
  6493. ENV: Agent did: predict-yes for direction L in state State-B
  6494. In State-B moving L
  6495. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  6496. predict error 0
  6497. dir: dir isU
  6498. -/918: O: O1836 (predict-no)
  6499. I see 1 and I'm going to do: predict-no
  6500. ENV: Agent did: predict-no for direction U in state State-A
  6501. In State-A moving U
  6502. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  6503. predict error 0
  6504. dir: dir isU
  6505. |\-/919: O: O1838 (predict-no)
  6506. I see 1 and I'm going to do: predict-no
  6507. ENV: Agent did: predict-no for direction U in state State-A
  6508. In State-A moving U
  6509. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  6510. predict error 0
  6511. dir: dir isL
  6512. |\-920: O: O1840 (predict-no)
  6513. I see 1 and I'm going to do: predict-no
  6514. ENV: Agent did: predict-no for direction L in state State-A
  6515. In State-A moving L
  6516. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  6517. predict error 0
  6518. dir: dir isU
  6519. /|\921: O: O1842 (predict-no)
  6520. I see 1 and I'm going to do: predict-no
  6521. ENV: Agent did: predict-no for direction U in state State-A
  6522. In State-A moving U
  6523. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  6524. predict error 0
  6525. dir: dir isU
  6526. -922: O: O1844 (predict-no)
  6527. I see 1 and I'm going to do: predict-no
  6528. ENV: Agent did: predict-no for direction U in state State-A
  6529. In State-A moving U
  6530. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  6531. predict error 0
  6532. dir: dir isU
  6533. /|\923: O: O1846 (predict-no)
  6534. I see 1 and I'm going to do: predict-no
  6535. ENV: Agent did: predict-no for direction U in state State-A
  6536. In State-A moving U
  6537. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  6538. predict error 0
  6539. dir: dir isU
  6540. -/924: O: O1848 (predict-no)
  6541. I see 1 and I'm going to do: predict-no
  6542. ENV: Agent did: predict-no for direction U in state State-A
  6543. In State-A moving U
  6544. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  6545. predict error 0
  6546. dir: dir isR
  6547. |\925: O: O1849 (predict-yes)
  6548. I see 1 and I'm going to do: predict-yes
  6549. ENV: Agent did: predict-yes for direction R in state State-A
  6550. In State-A moving R
  6551. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  6552. predict error 0
  6553. dir: dir isR
  6554. -926: O: O1852 (predict-no)
  6555. I see 1 and I'm going to do: predict-no
  6556. ENV: Agent did: predict-no for direction R in state State-B
  6557. In State-B moving R
  6558. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  6559. predict error 0
  6560. dir: dir isR
  6561. /|\927: O: O1854 (predict-no)
  6562. I see 1 and I'm going to do: predict-no
  6563. ENV: Agent did: predict-no for direction R in state State-B
  6564. In State-B moving R
  6565. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  6566. predict error 0
  6567. dir: dir isR
  6568. -/|928: O: O1856 (predict-no)
  6569. I see 1 and I'm going to do: predict-no
  6570. ENV: Agent did: predict-no for direction R in state State-B
  6571. In State-B moving R
  6572. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  6573. predict error 0
  6574. dir: dir isL
  6575. \-/929: O: O1857 (predict-yes)
  6576. I see 1 and I'm going to do: predict-yes
  6577. ENV: Agent did: predict-yes for direction L in state State-B
  6578. In State-B moving L
  6579. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  6580. predict error 0
  6581. dir: dir isU
  6582. |\930: O: O1860 (predict-no)
  6583. I see 1 and I'm going to do: predict-no
  6584. ENV: Agent did: predict-no for direction U in state State-A
  6585. In State-A moving U
  6586. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  6587. predict error 0
  6588. dir: dir isR
  6589. -/931: O: O1861 (predict-yes)
  6590. I see 1 and I'm going to do: predict-yes
  6591. ENV: Agent did: predict-yes for direction R in state State-A
  6592. In State-A moving R
  6593. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  6594. predict error 0
  6595. dir: dir isL
  6596. |932: O: O1863 (predict-yes)
  6597. I see 1 and I'm going to do: predict-yes
  6598. ENV: Agent did: predict-yes for direction L in state State-B
  6599. In State-B moving L
  6600. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  6601. predict error 0
  6602. dir: dir isL
  6603. \-933: O: O1866 (predict-no)
  6604. I see 1 and I'm going to do: predict-no
  6605. ENV: Agent did: predict-no for direction L in state State-A
  6606. In State-A moving L
  6607. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  6608. predict error 0
  6609. dir: dir isL
  6610. /|\934: O: O1868 (predict-no)
  6611. I see 1 and I'm going to do: predict-no
  6612. ENV: Agent did: predict-no for direction L in state State-A
  6613. In State-A moving L
  6614. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  6615. predict error 0
  6616. dir: dir isR
  6617. -/|935: O: O1869 (predict-yes)
  6618. I see 1 and I'm going to do: predict-yes
  6619. ENV: Agent did: predict-yes for direction R in state State-A
  6620. In State-A moving R
  6621. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  6622. predict error 0
  6623. dir: dir isL
  6624. \-/936: O: O1871 (predict-yes)
  6625. I see 1 and I'm going to do: predict-yes
  6626. ENV: Agent did: predict-yes for direction L in state State-B
  6627. In State-B moving L
  6628. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  6629. predict error 0
  6630. dir: dir isR
  6631. |\937: O: O1873 (predict-yes)
  6632. I see 1 and I'm going to do: predict-yes
  6633. ENV: Agent did: predict-yes for direction R in state State-A
  6634. In State-A moving R
  6635. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  6636. predict error 0
  6637. dir: dir isL
  6638. -/|938: O: O1875 (predict-yes)
  6639. I see 1 and I'm going to do: predict-yes
  6640. ENV: Agent did: predict-yes for direction L in state State-B
  6641. In State-B moving L
  6642. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  6643. predict error 0
  6644. dir: dir isU
  6645. \-/939: O: O1878 (predict-no)
  6646. I see 1 and I'm going to do: predict-no
  6647. ENV: Agent did: predict-no for direction U in state State-A
  6648. In State-A moving U
  6649. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  6650. predict error 0
  6651. dir: dir isU
  6652. |\-940: O: O1880 (predict-no)
  6653. I see 1 and I'm going to do: predict-no
  6654. ENV: Agent did: predict-no for direction U in state State-A
  6655. In State-A moving U
  6656. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  6657. predict error 0
  6658. dir: dir isL
  6659. /|\-sleeping...
  6660. /941: O: O1882 (predict-no)
  6661. I see 1 and I'm going to do: predict-no
  6662. ENV: Agent did: predict-no for direction L in state State-A
  6663. In State-A moving L
  6664. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  6665. predict error 0
  6666. dir: dir isU
  6667. |942: O: O1884 (predict-no)
  6668. I see 1 and I'm going to do: predict-no
  6669. ENV: Agent did: predict-no for direction U in state State-A
  6670. In State-A moving U
  6671. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  6672. predict error 0
  6673. dir: dir isR
  6674. \-/943: O: O1885 (predict-yes)
  6675. I see 1 and I'm going to do: predict-yes
  6676. ENV: Agent did: predict-yes for direction R in state State-A
  6677. In State-A moving R
  6678. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  6679. predict error 0
  6680. dir: dir isL
  6681. |\-944: O: O1887 (predict-yes)
  6682. I see 1 and I'm going to do: predict-yes
  6683. ENV: Agent did: predict-yes for direction L in state State-B
  6684. In State-B moving L
  6685. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  6686. predict error 0
  6687. dir: dir isU
  6688. /|\-945: O: O1890 (predict-no)
  6689. I see 1 and I'm going to do: predict-no
  6690. ENV: Agent did: predict-no for direction U in state State-A
  6691. In State-A moving U
  6692. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  6693. predict error 0
  6694. dir: dir isL
  6695. /|\946: O: O1892 (predict-no)
  6696. I see 1 and I'm going to do: predict-no
  6697. ENV: Agent did: predict-no for direction L in state State-A
  6698. In State-A moving L
  6699. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  6700. predict error 0
  6701. dir: dir isR
  6702. -/|947: O: O1893 (predict-yes)
  6703. I see 1 and I'm going to do: predict-yes
  6704. ENV: Agent did: predict-yes for direction R in state State-A
  6705. In State-A moving R
  6706. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  6707. predict error 0
  6708. dir: dir isR
  6709. \-948: O: O1896 (predict-no)
  6710. I see 1 and I'm going to do: predict-no
  6711. ENV: Agent did: predict-no for direction R in state State-B
  6712. In State-B moving R
  6713. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  6714. predict error 0
  6715. dir: dir isL
  6716. /|949: O: O1897 (predict-yes)
  6717. I see 1 and I'm going to do: predict-yes
  6718. ENV: Agent did: predict-yes for direction L in state State-B
  6719. In State-B moving L
  6720. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  6721. predict error 0
  6722. dir: dir isR
  6723. \-/950: O: O1899 (predict-yes)
  6724. I see 1 and I'm going to do: predict-yes
  6725. ENV: Agent did: predict-yes for direction R in state State-A
  6726. In State-A moving R
  6727. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  6728. predict error 0
  6729. dir: dir isU
  6730. |\-/|\-/|--- Input Phase ---
  6731. =>WM: (13313: I2 ^dir U)
  6732. =>WM: (13312: I2 ^reward 1)
  6733. =>WM: (13311: I2 ^see 1)
  6734. =>WM: (13310: N950 ^status complete)
  6735. <=WM: (13298: I2 ^dir R)
  6736. <=WM: (13297: I2 ^reward 1)
  6737. <=WM: (13296: I2 ^see 1)
  6738. =>WM: (13314: I2 ^level-1 R1-root)
  6739. <=WM: (13299: I2 ^level-1 L1-root)
  6740. --- END Input Phase ---
  6741. --- Proposal Phase ---
  6742. --- Inner Elaboration Phase, active level 1 (S1) ---
  6743. Firing elaborate*copy-see-to-output-link
  6744. -->
  6745. (I3 ^see 1 +)
  6746. Firing elaborate*reward*based*on*reward
  6747. -->
  6748. (R954 ^value 1 +)
  6749. (R1 ^reward R954 +)
  6750. Firing propose*predict-yes
  6751. -->
  6752. (O1901 ^name predict-yes +)
  6753. (S1 ^operator O1901 +)
  6754. Firing propose*predict-no
  6755. -->
  6756. (O1902 ^name predict-no +)
  6757. (S1 ^operator O1902 +)
  6758. Firing rl*prefer*rvt*predict-no*H0*6
  6759. -->
  6760. (S1 ^operator O1900 = 0.9999999999999999)
  6761. Firing rl*prefer*rvt*predict-yes*H0*5
  6762. -->
  6763. (S1 ^operator O1899 = 0.)
  6764. Firing prefer*rvt*predict-yes*H0
  6765. -->
  6766. Firing prefer*rvt*predict-no*H0
  6767. -->
  6768. Firing elaborate*copy-dir-to-output-link
  6769. -->
  6770. (I3 ^dir U +)
  6771. inner elaboration loop at bottom goal.
  6772. Retracting elaborate*copy-see-to-output-link
  6773. -->
  6774. (I3 ^see 1 +)
  6775. Retracting propose*predict-no
  6776. -->
  6777. (O1900 ^name predict-no +)
  6778. (S1 ^operator O1900 +)
  6779. Retracting propose*predict-yes
  6780. -->
  6781. (O1899 ^name predict-yes +)
  6782. (S1 ^operator O1899 +)
  6783. Retracting elaborate*reward*based*on*reward
  6784. -->
  6785. (R953 ^value 1 +)
  6786. (R1 ^reward R953 +)
  6787. Retracting elaborate*copy-dir-to-output-link
  6788. -->
  6789. (I3 ^dir R +)
  6790. Retracting rl*prefer*rvt*predict-no*H0*4*v1*H1*45
  6791. -->
  6792. (S1 ^operator O1900 = -0.02155734064455064)
  6793. Retracting rl*prefer*rvt*predict-no*H0*4
  6794. -->
  6795. (S1 ^operator O1900 = 0.4476192676183378)
  6796. Retracting rl*prefer*rvt*predict-yes*H0*3*v1*H1*46
  6797. -->
  6798. (S1 ^operator O1899 = 0.8155729125006117)
  6799. Retracting rl*prefer*rvt*predict-yes*H0*3
  6800. -->
  6801. (S1 ^operator O1899 = 0.1844075378173239)
  6802. =>WM: (13321: S1 ^operator O1902 +)
  6803. =>WM: (13320: S1 ^operator O1901 +)
  6804. =>WM: (13319: I3 ^dir U)
  6805. =>WM: (13318: O1902 ^name predict-no)
  6806. =>WM: (13317: O1901 ^name predict-yes)
  6807. =>WM: (13316: R954 ^value 1)
  6808. =>WM: (13315: R1 ^reward R954)
  6809. <=WM: (13306: S1 ^operator O1899 +)
  6810. <=WM: (13308: S1 ^operator O1899)
  6811. <=WM: (13307: S1 ^operator O1900 +)
  6812. <=WM: (13305: I3 ^dir R)
  6813. <=WM: (13301: R1 ^reward R953)
  6814. <=WM: (13304: O1900 ^name predict-no)
  6815. <=WM: (13303: O1899 ^name predict-yes)
  6816. <=WM: (13302: R953 ^value 1)
  6817. --- Inner Elaboration Phase, active level 1 (S1) ---
  6818. Firing prefer*rvt*predict-yes*H0
  6819. -->
  6820. Firing rl*prefer*rvt*predict-yes*H0*5
  6821. -->
  6822. (S1 ^operator O1901 = 0.)
  6823. Firing prefer*rvt*predict-no*H0
  6824. -->
  6825. Firing rl*prefer*rvt*predict-no*H0*6
  6826. -->
  6827. (S1 ^operator O1902 = 0.9999999999999999)
  6828. inner elaboration loop at bottom goal.
  6829. Retracting rl*prefer*rvt*predict-no*H0*6
  6830. -->
  6831. (S1 ^operator O1900 = 0.9999999999999999)
  6832. Retracting rl*prefer*rvt*predict-yes*H0*5
  6833. -->
  6834. (S1 ^operator O1899 = 0.)
  6835. --- END Proposal Phase ---
  6836. --- Decision Phase ---
  6837. RL update rl*prefer*rvt*predict-yes*H0*3 0.675409 -0.491002 0.184408 -> 0.675413 -0.491002 0.18441(R,m,v=1,0.89441,0.0950311)
  6838. RL update rl*prefer*rvt*predict-yes*H0*3*v1*H1*46 0.324566 0.491007 0.815573 -> 0.324569 0.491006 0.815576(R,m,v=1,1,0)
  6839. =>WM: (13322: S1 ^operator O1902)
  6840. 951: O: O1902 (predict-no)
  6841. --- END Decision Phase ---
  6842. --- Application Phase ---
  6843. --- Firing Productions (PE) For State At Depth 1 ---
  6844. --- Inner Elaboration Phase, active level 1 (S1) ---
  6845. Firing apply*operator
  6846. -->
  6847. (I3 ^predict-no N951 + :O )
  6848. Firing apply*operator*complete
  6849. -->
  6850. (I3 ^predict-yes N950 - :O )
  6851. inner elaboration loop at bottom goal.
  6852. --- Change Working Memory (PE) ---
  6853. =>WM: (13323: I3 ^predict-no N951)
  6854. <=WM: (13310: N950 ^status complete)
  6855. <=WM: (13309: I3 ^predict-yes N950)
  6856. --- Firing Productions (IE) For State At Depth 1 ---
  6857. --- Inner Elaboration Phase, active level 1 (S1) ---
  6858. Firing monitor*world
  6859. -->
  6860. I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
  6861. --- Change Working Memory (IE) ---
  6862. --- END Application Phase ---
  6863. --- Output Phase ---
  6864. ENV: Agent did: predict-no for direction U in state State-B
  6865. In State-B moving U
  6866. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  6867. predict error 0
  6868. dir: dir isR
  6869. --- END Output Phase ---
  6870. \--- Input Phase ---
  6871. =>WM: (13327: I2 ^dir R)
  6872. =>WM: (13326: I2 ^reward 1)
  6873. =>WM: (13325: I2 ^see 0)
  6874. =>WM: (13324: N951 ^status complete)
  6875. <=WM: (13313: I2 ^dir U)
  6876. <=WM: (13312: I2 ^reward 1)
  6877. <=WM: (13311: I2 ^see 1)
  6878. =>WM: (13328: I2 ^level-1 R1-root)
  6879. <=WM: (13314: I2 ^level-1 R1-root)
  6880. --- END Input Phase ---
  6881. --- Proposal Phase ---
  6882. --- Inner Elaboration Phase, active level 1 (S1) ---
  6883. Firing rl*prefer*rvt*predict-yes*H0*3*v1*H1*40
  6884. -->
  6885. (S1 ^operator O1901 = 0.1398795999120246)
  6886. Firing rl*prefer*rvt*predict-no*H0*4*v1*H1*39
  6887. -->
  6888. (S1 ^operator O1902 = 0.5523833737960075)
  6889. Firing prefer*rvt*predict-no*H0*4*v1*H1
  6890. -->
  6891. Firing prefer*rvt*predict-yes*H0*3*v1*H1
  6892. -->
  6893. Firing elaborate*copy-see-to-output-link
  6894. -->
  6895. (I3 ^see 0 +)
  6896. Firing elaborate*reward*based*on*reward
  6897. -->
  6898. (R955 ^value 1 +)
  6899. (R1 ^reward R955 +)
  6900. Firing propose*predict-yes
  6901. -->
  6902. (O1903 ^name predict-yes +)
  6903. (S1 ^operator O1903 +)
  6904. Firing propose*predict-no
  6905. -->
  6906. (O1904 ^name predict-no +)
  6907. (S1 ^operator O1904 +)
  6908. Firing rl*prefer*rvt*predict-no*H0*4
  6909. -->
  6910. (S1 ^operator O1902 = 0.4476192676183378)
  6911. Firing rl*prefer*rvt*predict-yes*H0*3
  6912. -->
  6913. (S1 ^operator O1901 = 0.1844104702696336)
  6914. Firing prefer*rvt*predict-yes*H0
  6915. -->
  6916. Firing prefer*rvt*predict-no*H0
  6917. -->
  6918. Firing elaborate*copy-dir-to-output-link
  6919. -->
  6920. (I3 ^dir R +)
  6921. inner elaboration loop at bottom goal.
  6922. Retracting elaborate*copy-see-to-output-link
  6923. -->
  6924. (I3 ^see 1 +)
  6925. Retracting propose*predict-no
  6926. -->
  6927. (O1902 ^name predict-no +)
  6928. (S1 ^operator O1902 +)
  6929. Retracting propose*predict-yes
  6930. -->
  6931. (O1901 ^name predict-yes +)
  6932. (S1 ^operator O1901 +)
  6933. Retracting elaborate*reward*based*on*reward
  6934. -->
  6935. (R954 ^value 1 +)
  6936. (R1 ^reward R954 +)
  6937. Retracting elaborate*copy-dir-to-output-link
  6938. -->
  6939. (I3 ^dir U +)
  6940. Retracting rl*prefer*rvt*predict-no*H0*6
  6941. -->
  6942. (S1 ^operator O1902 = 0.9999999999999999)
  6943. Retracting rl*prefer*rvt*predict-yes*H0*5
  6944. -->
  6945. (S1 ^operator O1901 = 0.)
  6946. =>WM: (13336: S1 ^operator O1904 +)
  6947. =>WM: (13335: S1 ^operator O1903 +)
  6948. =>WM: (13334: I3 ^dir R)
  6949. =>WM: (13333: O1904 ^name predict-no)
  6950. =>WM: (13332: O1903 ^name predict-yes)
  6951. =>WM: (13331: R955 ^value 1)
  6952. =>WM: (13330: R1 ^reward R955)
  6953. =>WM: (13329: I3 ^see 0)
  6954. <=WM: (13320: S1 ^operator O1901 +)
  6955. <=WM: (13321: S1 ^operator O1902 +)
  6956. <=WM: (13322: S1 ^operator O1902)
  6957. <=WM: (13319: I3 ^dir U)
  6958. <=WM: (13315: R1 ^reward R954)
  6959. <=WM: (13300: I3 ^see 1)
  6960. <=WM: (13318: O1902 ^name predict-no)
  6961. <=WM: (13317: O1901 ^name predict-yes)
  6962. <=WM: (13316: R954 ^value 1)
  6963. --- Inner Elaboration Phase, active level 1 (S1) ---
  6964. Firing prefer*rvt*predict-yes*H0
  6965. -->
  6966. Firing rl*prefer*rvt*predict-yes*H0*3*v1*H1*40
  6967. -->
  6968. (S1 ^operator O1903 = 0.1398795999120246)
  6969. Firing rl*prefer*rvt*predict-yes*H0*3
  6970. -->
  6971. (S1 ^operator O1903 = 0.1844104702696336)
  6972. Firing prefer*rvt*predict-yes*H0*3*v1*H1
  6973. -->
  6974. Firing prefer*rvt*predict-no*H0
  6975. -->
  6976. Firing rl*prefer*rvt*predict-no*H0*4*v1*H1*39
  6977. -->
  6978. (S1 ^operator O1904 = 0.5523833737960075)
  6979. Firing rl*prefer*rvt*predict-no*H0*4
  6980. -->
  6981. (S1 ^operator O1904 = 0.4476192676183378)
  6982. Firing prefer*rvt*predict-no*H0*4*v1*H1
  6983. -->
  6984. inner elaboration loop at bottom goal.
  6985. Retracting rl*prefer*rvt*predict-no*H0*4
  6986. -->
  6987. (S1 ^operator O1902 = 0.4476192676183378)
  6988. Retracting rl*prefer*rvt*predict-no*H0*4*v1*H1*39
  6989. -->
  6990. (S1 ^operator O1902 = 0.5523833737960075)
  6991. Retracting rl*prefer*rvt*predict-yes*H0*3
  6992. -->
  6993. (S1 ^operator O1901 = 0.1844104702696336)
  6994. Retracting rl*prefer*rvt*predict-yes*H0*3*v1*H1*40
  6995. -->
  6996. (S1 ^operator O1901 = 0.1398795999120246)
  6997. --- END Proposal Phase ---
  6998. --- Decision Phase ---
  6999. RL update rl*prefer*rvt*predict-no*H0*6 1 0 1 -> 1 0 1(R,m,v=1,1,0)
  7000. =>WM: (13337: S1 ^operator O1904)
  7001. 952: O: O1904 (predict-no)
  7002. --- END Decision Phase ---
  7003. --- Application Phase ---
  7004. --- Firing Productions (PE) For State At Depth 1 ---
  7005. --- Inner Elaboration Phase, active level 1 (S1) ---
  7006. Firing apply*operator
  7007. -->
  7008. (I3 ^predict-no N952 + :O )
  7009. Firing apply*operator*complete
  7010. -->
  7011. (I3 ^predict-no N951 - :O )
  7012. inner elaboration loop at bottom goal.
  7013. --- Change Working Memory (PE) ---
  7014. =>WM: (13338: I3 ^predict-no N952)
  7015. <=WM: (13324: N951 ^status complete)
  7016. <=WM: (13323: I3 ^predict-no N951)
  7017. --- Firing Productions (IE) For State At Depth 1 ---
  7018. --- Inner Elaboration Phase, active level 1 (S1) ---
  7019. Firing monitor*world
  7020. -->
  7021. I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
  7022. --- Change Working Memory (IE) ---
  7023. --- END Application Phase ---
  7024. --- Output Phase ---
  7025. ENV: Agent did: predict-no for direction R in state State-B
  7026. In State-B moving R
  7027. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  7028. predict error 0
  7029. dir: dir isU
  7030. --- END Output Phase ---
  7031. -/|--- Input Phase ---
  7032. =>WM: (13342: I2 ^dir U)
  7033. =>WM: (13341: I2 ^reward 1)
  7034. =>WM: (13340: I2 ^see 0)
  7035. =>WM: (13339: N952 ^status complete)
  7036. <=WM: (13327: I2 ^dir R)
  7037. <=WM: (13326: I2 ^reward 1)
  7038. <=WM: (13325: I2 ^see 0)
  7039. =>WM: (13343: I2 ^level-1 R0-root)
  7040. <=WM: (13328: I2 ^level-1 R1-root)
  7041. --- END Input Phase ---
  7042. --- Proposal Phase ---
  7043. --- Inner Elaboration Phase, active level 1 (S1) ---
  7044. Firing elaborate*copy-see-to-output-link
  7045. -->
  7046. (I3 ^see 0 +)
  7047. Firing elaborate*reward*based*on*reward
  7048. -->
  7049. (R956 ^value 1 +)
  7050. (R1 ^reward R956 +)
  7051. Firing propose*predict-yes
  7052. -->
  7053. (O1905 ^name predict-yes +)
  7054. (S1 ^operator O1905 +)
  7055. Firing propose*predict-no
  7056. -->
  7057. (O1906 ^name predict-no +)
  7058. (S1 ^operator O1906 +)
  7059. Firing rl*prefer*rvt*predict-no*H0*6
  7060. -->
  7061. (S1 ^operator O1904 = 0.9999999999999999)
  7062. Firing rl*prefer*rvt*predict-yes*H0*5
  7063. -->
  7064. (S1 ^operator O1903 = 0.)
  7065. Firing prefer*rvt*predict-yes*H0
  7066. -->
  7067. Firing prefer*rvt*predict-no*H0
  7068. -->
  7069. Firing elaborate*copy-dir-to-output-link
  7070. -->
  7071. (I3 ^dir U +)
  7072. inner elaboration loop at bottom goal.
  7073. Retracting elaborate*copy-see-to-output-link
  7074. -->
  7075. (I3 ^see 0 +)
  7076. Retracting propose*predict-no
  7077. -->
  7078. (O1904 ^name predict-no +)
  7079. (S1 ^operator O1904 +)
  7080. Retracting propose*predict-yes
  7081. -->
  7082. (O1903 ^name predict-yes +)
  7083. (S1 ^operator O1903 +)
  7084. Retracting elaborate*reward*based*on*reward
  7085. -->
  7086. (R955 ^value 1 +)
  7087. (R1 ^reward R955 +)
  7088. Retracting elaborate*copy-dir-to-output-link
  7089. -->
  7090. (I3 ^dir R +)
  7091. Retracting rl*prefer*rvt*predict-no*H0*4
  7092. -->
  7093. (S1 ^operator O1904 = 0.4476192676183378)
  7094. Retracting rl*prefer*rvt*predict-no*H0*4*v1*H1*39
  7095. -->
  7096. (S1 ^operator O1904 = 0.5523833737960075)
  7097. Retracting rl*prefer*rvt*predict-yes*H0*3
  7098. -->
  7099. (S1 ^operator O1903 = 0.1844104702696336)
  7100. Retracting rl*prefer*rvt*predict-yes*H0*3*v1*H1*40
  7101. -->
  7102. (S1 ^operator O1903 = 0.1398795999120246)
  7103. =>WM: (13350: S1 ^operator O1906 +)
  7104. =>WM: (13349: S1 ^operator O1905 +)
  7105. =>WM: (13348: I3 ^dir U)
  7106. =>WM: (13347: O1906 ^name predict-no)
  7107. =>WM: (13346: O1905 ^name predict-yes)
  7108. =>WM: (13345: R956 ^value 1)
  7109. =>WM: (13344: R1 ^reward R956)
  7110. <=WM: (13335: S1 ^operator O1903 +)
  7111. <=WM: (13336: S1 ^operator O1904 +)
  7112. <=WM: (13337: S1 ^operator O1904)
  7113. <=WM: (13334: I3 ^dir R)
  7114. <=WM: (13330: R1 ^reward R955)
  7115. <=WM: (13333: O1904 ^name predict-no)
  7116. <=WM: (13332: O1903 ^name predict-yes)
  7117. <=WM: (13331: R955 ^value 1)
  7118. --- Inner Elaboration Phase, active level 1 (S1) ---
  7119. Firing prefer*rvt*predict-yes*H0
  7120. -->
  7121. Firing rl*prefer*rvt*predict-yes*H0*5
  7122. -->
  7123. (S1 ^operator O1905 = 0.)
  7124. Firing prefer*rvt*predict-no*H0
  7125. -->
  7126. Firing rl*prefer*rvt*predict-no*H0*6
  7127. -->
  7128. (S1 ^operator O1906 = 0.9999999999999999)
  7129. inner elaboration loop at bottom goal.
  7130. Retracting rl*prefer*rvt*predict-no*H0*6
  7131. -->
  7132. (S1 ^operator O1904 = 0.9999999999999999)
  7133. Retracting rl*prefer*rvt*predict-yes*H0*5
  7134. -->
  7135. (S1 ^operator O1903 = 0.)
  7136. --- END Proposal Phase ---
  7137. --- Decision Phase ---
  7138. RL update rl*prefer*rvt*predict-no*H0*4 0.622533 -0.174914 0.447619 -> 0.622532 -0.174914 0.447619(R,m,v=1,0.925,0.069958)
  7139. RL update rl*prefer*rvt*predict-no*H0*4*v1*H1*39 0.377469 0.174914 0.552383 -> 0.377469 0.174914 0.552383(R,m,v=1,1,0)
  7140. =>WM: (13351: S1 ^operator O1906)
  7141. 953: O: O1906 (predict-no)
  7142. --- END Decision Phase ---
  7143. --- Application Phase ---
  7144. --- Firing Productions (PE) For State At Depth 1 ---
  7145. --- Inner Elaboration Phase, active level 1 (S1) ---
  7146. Firing apply*operator
  7147. -->
  7148. (I3 ^predict-no N953 + :O )
  7149. Firing apply*operator*complete
  7150. -->
  7151. (I3 ^predict-no N952 - :O )
  7152. inner elaboration loop at bottom goal.
  7153. --- Change Working Memory (PE) ---
  7154. =>WM: (13352: I3 ^predict-no N953)
  7155. <=WM: (13339: N952 ^status complete)
  7156. <=WM: (13338: I3 ^predict-no N952)
  7157. --- Firing Productions (IE) For State At Depth 1 ---
  7158. --- Inner Elaboration Phase, active level 1 (S1) ---
  7159. Firing monitor*world
  7160. -->
  7161. I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
  7162. --- Change Working Memory (IE) ---
  7163. --- END Application Phase ---
  7164. --- Output Phase ---
  7165. ENV: Agent did: predict-no for direction U in state State-B
  7166. In State-B moving U
  7167. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  7168. predict error 0
  7169. dir: dir isL
  7170. --- END Output Phase ---
  7171. \-/--- Input Phase ---
  7172. =>WM: (13356: I2 ^dir L)
  7173. =>WM: (13355: I2 ^reward 1)
  7174. =>WM: (13354: I2 ^see 0)
  7175. =>WM: (13353: N953 ^status complete)
  7176. <=WM: (13342: I2 ^dir U)
  7177. <=WM: (13341: I2 ^reward 1)
  7178. <=WM: (13340: I2 ^see 0)
  7179. =>WM: (13357: I2 ^level-1 R0-root)
  7180. <=WM: (13343: I2 ^level-1 R0-root)
  7181. --- END Input Phase ---
  7182. --- Proposal Phase ---
  7183. --- Inner Elaboration Phase, active level 1 (S1) ---
  7184. Firing rl*prefer*rvt*predict-yes*H0*1*v1*H1*44
  7185. -->
  7186. (S1 ^operator O1905 = 0.6104621686166466)
  7187. Firing rl*prefer*rvt*predict-no*H0*2*v1*H1*43
  7188. -->
  7189. (S1 ^operator O1906 = 0.1063475139796038)
  7190. Firing prefer*rvt*predict-no*H0*2*v1*H1
  7191. -->
  7192. Firing prefer*rvt*predict-yes*H0*1*v1*H1
  7193. -->
  7194. Firing elaborate*copy-see-to-output-link
  7195. -->
  7196. (I3 ^see 0 +)
  7197. Firing elaborate*reward*based*on*reward
  7198. -->
  7199. (R957 ^value 1 +)
  7200. (R1 ^reward R957 +)
  7201. Firing propose*predict-yes
  7202. -->
  7203. (O1907 ^name predict-yes +)
  7204. (S1 ^operator O1907 +)
  7205. Firing propose*predict-no
  7206. -->
  7207. (O1908 ^name predict-no +)
  7208. (S1 ^operator O1908 +)
  7209. Firing rl*prefer*rvt*predict-no*H0*2
  7210. -->
  7211. (S1 ^operator O1906 = 0.3873365065796835)
  7212. Firing rl*prefer*rvt*predict-yes*H0*1
  7213. -->
  7214. (S1 ^operator O1905 = 0.3895397770301633)
  7215. Firing prefer*rvt*predict-yes*H0
  7216. -->
  7217. Firing prefer*rvt*predict-no*H0
  7218. -->
  7219. Firing elaborate*copy-dir-to-output-link
  7220. -->
  7221. (I3 ^dir L +)
  7222. inner elaboration loop at bottom goal.
  7223. Retracting elaborate*copy-see-to-output-link
  7224. -->
  7225. (I3 ^see 0 +)
  7226. Retracting propose*predict-no
  7227. -->
  7228. (O1906 ^name predict-no +)
  7229. (S1 ^operator O1906 +)
  7230. Retracting propose*predict-yes
  7231. -->
  7232. (O1905 ^name predict-yes +)
  7233. (S1 ^operator O1905 +)
  7234. Retracting elaborate*reward*based*on*reward
  7235. -->
  7236. (R956 ^value 1 +)
  7237. (R1 ^reward R956 +)
  7238. Retracting elaborate*copy-dir-to-output-link
  7239. -->
  7240. (I3 ^dir U +)
  7241. Retracting rl*prefer*rvt*predict-no*H0*6
  7242. -->
  7243. (S1 ^operator O1906 = 0.9999999999999999)
  7244. Retracting rl*prefer*rvt*predict-yes*H0*5
  7245. -->
  7246. (S1 ^operator O1905 = 0.)
  7247. =>WM: (13364: S1 ^operator O1908 +)
  7248. =>WM: (13363: S1 ^operator O1907 +)
  7249. =>WM: (13362: I3 ^dir L)
  7250. =>WM: (13361: O1908 ^name predict-no)
  7251. =>WM: (13360: O1907 ^name predict-yes)
  7252. =>WM: (13359: R957 ^value 1)
  7253. =>WM: (13358: R1 ^reward R957)
  7254. <=WM: (13349: S1 ^operator O1905 +)
  7255. <=WM: (13350: S1 ^operator O1906 +)
  7256. <=WM: (13351: S1 ^operator O1906)
  7257. <=WM: (13348: I3 ^dir U)
  7258. <=WM: (13344: R1 ^reward R956)
  7259. <=WM: (13347: O1906 ^name predict-no)
  7260. <=WM: (13346: O1905 ^name predict-yes)
  7261. <=WM: (13345: R956 ^value 1)
  7262. --- Inner Elaboration Phase, active level 1 (S1) ---
  7263. Firing prefer*rvt*predict-yes*H0
  7264. -->
  7265. Firing rl*prefer*rvt*predict-yes*H0*1*v1*H1*44
  7266. -->
  7267. (S1 ^operator O1907 = 0.6104621686166466)
  7268. Firing rl*prefer*rvt*predict-yes*H0*1
  7269. -->
  7270. (S1 ^operator O1907 = 0.3895397770301633)
  7271. Firing prefer*rvt*predict-yes*H0*1*v1*H1
  7272. -->
  7273. Firing prefer*rvt*predict-no*H0
  7274. -->
  7275. Firing rl*prefer*rvt*predict-no*H0*2*v1*H1*43
  7276. -->
  7277. (S1 ^operator O1908 = 0.1063475139796038)
  7278. Firing rl*prefer*rvt*predict-no*H0*2
  7279. -->
  7280. (S1 ^operator O1908 = 0.3873365065796835)
  7281. Firing prefer*rvt*predict-no*H0*2*v1*H1
  7282. -->
  7283. inner elaboration loop at bottom goal.
  7284. Retracting rl*prefer*rvt*predict-no*H0*2
  7285. -->
  7286. (S1 ^operator O1906 = 0.3873365065796835)
  7287. Retracting rl*prefer*rvt*predict-no*H0*2*v1*H1*43
  7288. -->
  7289. (S1 ^operator O1906 = 0.1063475139796038)
  7290. Retracting rl*prefer*rvt*predict-yes*H0*1
  7291. -->
  7292. (S1 ^operator O1905 = 0.3895397770301633)
  7293. Retracting rl*prefer*rvt*predict-yes*H0*1*v1*H1*44
  7294. -->
  7295. (S1 ^operator O1905 = 0.6104621686166466)
  7296. --- END Proposal Phase ---
  7297. --- Decision Phase ---
  7298. RL update rl*prefer*rvt*predict-no*H0*6 1 0 1 -> 1 0 1(R,m,v=1,1,0)
  7299. =>WM: (13365: S1 ^operator O1907)
  7300. 954: O: O1907 (predict-yes)
  7301. --- END Decision Phase ---
  7302. --- Application Phase ---
  7303. --- Firing Productions (PE) For State At Depth 1 ---
  7304. --- Inner Elaboration Phase, active level 1 (S1) ---
  7305. Firing apply*operator
  7306. -->
  7307. (I3 ^predict-yes N954 + :O )
  7308. Firing apply*operator*complete
  7309. -->
  7310. (I3 ^predict-no N953 - :O )
  7311. inner elaboration loop at bottom goal.
  7312. --- Change Working Memory (PE) ---
  7313. =>WM: (13366: I3 ^predict-yes N954)
  7314. <=WM: (13353: N953 ^status complete)
  7315. <=WM: (13352: I3 ^predict-no N953)
  7316. --- Firing Productions (IE) For State At Depth 1 ---
  7317. --- Inner Elaboration Phase, active level 1 (S1) ---
  7318. Firing monitor*world
  7319. -->
  7320. I see 1 and I'm going to do: predict-yes inner elaboration loop at bottom goal.
  7321. --- Change Working Memory (IE) ---
  7322. --- END Application Phase ---
  7323. --- Output Phase ---
  7324. ENV: Agent did: predict-yes for direction L in state State-B
  7325. In State-B moving L
  7326. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  7327. predict error 0
  7328. dir: dir isU
  7329. --- END Output Phase ---
  7330. |\--- Input Phase ---
  7331. =>WM: (13370: I2 ^dir U)
  7332. =>WM: (13369: I2 ^reward 1)
  7333. =>WM: (13368: I2 ^see 1)
  7334. =>WM: (13367: N954 ^status complete)
  7335. <=WM: (13356: I2 ^dir L)
  7336. <=WM: (13355: I2 ^reward 1)
  7337. <=WM: (13354: I2 ^see 0)
  7338. =>WM: (13371: I2 ^level-1 L1-root)
  7339. <=WM: (13357: I2 ^level-1 R0-root)
  7340. --- END Input Phase ---
  7341. --- Proposal Phase ---
  7342. --- Inner Elaboration Phase, active level 1 (S1) ---
  7343. Firing elaborate*copy-see-to-output-link
  7344. -->
  7345. (I3 ^see 1 +)
  7346. Firing elaborate*reward*based*on*reward
  7347. -->
  7348. (R958 ^value 1 +)
  7349. (R1 ^reward R958 +)
  7350. Firing propose*predict-yes
  7351. -->
  7352. (O1909 ^name predict-yes +)
  7353. (S1 ^operator O1909 +)
  7354. Firing propose*predict-no
  7355. -->
  7356. (O1910 ^name predict-no +)
  7357. (S1 ^operator O1910 +)
  7358. Firing rl*prefer*rvt*predict-no*H0*6
  7359. -->
  7360. (S1 ^operator O1908 = 0.9999999999999999)
  7361. Firing rl*prefer*rvt*predict-yes*H0*5
  7362. -->
  7363. (S1 ^operator O1907 = 0.)
  7364. Firing prefer*rvt*predict-yes*H0
  7365. -->
  7366. Firing prefer*rvt*predict-no*H0
  7367. -->
  7368. Firing elaborate*copy-dir-to-output-link
  7369. -->
  7370. (I3 ^dir U +)
  7371. inner elaboration loop at bottom goal.
  7372. Retracting elaborate*copy-see-to-output-link
  7373. -->
  7374. (I3 ^see 0 +)
  7375. Retracting propose*predict-no
  7376. -->
  7377. (O1908 ^name predict-no +)
  7378. (S1 ^operator O1908 +)
  7379. Retracting propose*predict-yes
  7380. -->
  7381. (O1907 ^name predict-yes +)
  7382. (S1 ^operator O1907 +)
  7383. Retracting elaborate*reward*based*on*reward
  7384. -->
  7385. (R957 ^value 1 +)
  7386. (R1 ^reward R957 +)
  7387. Retracting elaborate*copy-dir-to-output-link
  7388. -->
  7389. (I3 ^dir L +)
  7390. Retracting rl*prefer*rvt*predict-no*H0*2
  7391. -->
  7392. (S1 ^operator O1908 = 0.3873365065796835)
  7393. Retracting rl*prefer*rvt*predict-no*H0*2*v1*H1*43
  7394. -->
  7395. (S1 ^operator O1908 = 0.1063475139796038)
  7396. Retracting rl*prefer*rvt*predict-yes*H0*1
  7397. -->
  7398. (S1 ^operator O1907 = 0.3895397770301633)
  7399. Retracting rl*prefer*rvt*predict-yes*H0*1*v1*H1*44
  7400. -->
  7401. (S1 ^operator O1907 = 0.6104621686166466)
  7402. =>WM: (13379: S1 ^operator O1910 +)
  7403. =>WM: (13378: S1 ^operator O1909 +)
  7404. =>WM: (13377: I3 ^dir U)
  7405. =>WM: (13376: O1910 ^name predict-no)
  7406. =>WM: (13375: O1909 ^name predict-yes)
  7407. =>WM: (13374: R958 ^value 1)
  7408. =>WM: (13373: R1 ^reward R958)
  7409. =>WM: (13372: I3 ^see 1)
  7410. <=WM: (13363: S1 ^operator O1907 +)
  7411. <=WM: (13365: S1 ^operator O1907)
  7412. <=WM: (13364: S1 ^operator O1908 +)
  7413. <=WM: (13362: I3 ^dir L)
  7414. <=WM: (13358: R1 ^reward R957)
  7415. <=WM: (13329: I3 ^see 0)
  7416. <=WM: (13361: O1908 ^name predict-no)
  7417. <=WM: (13360: O1907 ^name predict-yes)
  7418. <=WM: (13359: R957 ^value 1)
  7419. --- Inner Elaboration Phase, active level 1 (S1) ---
  7420. Firing prefer*rvt*predict-yes*H0
  7421. -->
  7422. Firing rl*prefer*rvt*predict-yes*H0*5
  7423. -->
  7424. (S1 ^operator O1909 = 0.)
  7425. Firing prefer*rvt*predict-no*H0
  7426. -->
  7427. Firing rl*prefer*rvt*predict-no*H0*6
  7428. -->
  7429. (S1 ^operator O1910 = 0.9999999999999999)
  7430. inner elaboration loop at bottom goal.
  7431. Retracting rl*prefer*rvt*predict-no*H0*6
  7432. -->
  7433. (S1 ^operator O1908 = 0.9999999999999999)
  7434. Retracting rl*prefer*rvt*predict-yes*H0*5
  7435. -->
  7436. (S1 ^operator O1907 = 0.)
  7437. --- END Proposal Phase ---
  7438. --- Decision Phase ---
  7439. RL update rl*prefer*rvt*predict-yes*H0*1 0.711951 -0.322412 0.38954 -> 0.711951 -0.322412 0.389539(R,m,v=1,0.886792,0.101027)
  7440. RL update rl*prefer*rvt*predict-yes*H0*1*v1*H1*44 0.288049 0.322413 0.610462 -> 0.288049 0.322413 0.610462(R,m,v=1,1,0)
  7441. =>WM: (13380: S1 ^operator O1910)
  7442. 955: O: O1910 (predict-no)
  7443. --- END Decision Phase ---
  7444. --- Application Phase ---
  7445. --- Firing Productions (PE) For State At Depth 1 ---
  7446. --- Inner Elaboration Phase, active level 1 (S1) ---
  7447. Firing apply*operator
  7448. -->
  7449. (I3 ^predict-no N955 + :O )
  7450. Firing apply*operator*complete
  7451. -->
  7452. (I3 ^predict-yes N954 - :O )
  7453. inner elaboration loop at bottom goal.
  7454. --- Change Working Memory (PE) ---
  7455. =>WM: (13381: I3 ^predict-no N955)
  7456. <=WM: (13367: N954 ^status complete)
  7457. <=WM: (13366: I3 ^predict-yes N954)
  7458. --- Firing Productions (IE) For State At Depth 1 ---
  7459. --- Inner Elaboration Phase, active level 1 (S1) ---
  7460. Firing monitor*world
  7461. -->
  7462. I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
  7463. --- Change Working Memory (IE) ---
  7464. --- END Application Phase ---
  7465. --- Output Phase ---
  7466. ENV: Agent did: predict-no for direction U in state State-A
  7467. In State-A moving U
  7468. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  7469. predict error 0
  7470. dir: dir isU
  7471. --- END Output Phase ---
  7472. -/--- Input Phase ---
  7473. =>WM: (13385: I2 ^dir U)
  7474. =>WM: (13384: I2 ^reward 1)
  7475. =>WM: (13383: I2 ^see 0)
  7476. =>WM: (13382: N955 ^status complete)
  7477. <=WM: (13370: I2 ^dir U)
  7478. <=WM: (13369: I2 ^reward 1)
  7479. <=WM: (13368: I2 ^see 1)
  7480. =>WM: (13386: I2 ^level-1 L1-root)
  7481. <=WM: (13371: I2 ^level-1 L1-root)
  7482. --- END Input Phase ---
  7483. --- Proposal Phase ---
  7484. --- Inner Elaboration Phase, active level 1 (S1) ---
  7485. Firing elaborate*copy-see-to-output-link
  7486. -->
  7487. (I3 ^see 0 +)
  7488. Firing elaborate*reward*based*on*reward
  7489. -->
  7490. (R959 ^value 1 +)
  7491. (R1 ^reward R959 +)
  7492. Firing propose*predict-yes
  7493. -->
  7494. (O1911 ^name predict-yes +)
  7495. (S1 ^operator O1911 +)
  7496. Firing propose*predict-no
  7497. -->
  7498. (O1912 ^name predict-no +)
  7499. (S1 ^operator O1912 +)
  7500. Firing rl*prefer*rvt*predict-no*H0*6
  7501. -->
  7502. (S1 ^operator O1910 = 0.9999999999999999)
  7503. Firing rl*prefer*rvt*predict-yes*H0*5
  7504. -->
  7505. (S1 ^operator O1909 = 0.)
  7506. Firing prefer*rvt*predict-yes*H0
  7507. -->
  7508. Firing prefer*rvt*predict-no*H0
  7509. -->
  7510. Firing elaborate*copy-dir-to-output-link
  7511. -->
  7512. (I3 ^dir U +)
  7513. inner elaboration loop at bottom goal.
  7514. Retracting elaborate*copy-see-to-output-link
  7515. -->
  7516. (I3 ^see 1 +)
  7517. Retracting propose*predict-no
  7518. -->
  7519. (O1910 ^name predict-no +)
  7520. (S1 ^operator O1910 +)
  7521. Retracting propose*predict-yes
  7522. -->
  7523. (O1909 ^name predict-yes +)
  7524. (S1 ^operator O1909 +)
  7525. Retracting elaborate*reward*based*on*reward
  7526. -->
  7527. (R958 ^value 1 +)
  7528. (R1 ^reward R958 +)
  7529. Retracting elaborate*copy-dir-to-output-link
  7530. -->
  7531. (I3 ^dir U +)
  7532. Retracting rl*prefer*rvt*predict-no*H0*6
  7533. -->
  7534. (S1 ^operator O1910 = 0.9999999999999999)
  7535. Retracting rl*prefer*rvt*predict-yes*H0*5
  7536. -->
  7537. (S1 ^operator O1909 = 0.)
  7538. =>WM: (13393: S1 ^operator O1912 +)
  7539. =>WM: (13392: S1 ^operator O1911 +)
  7540. =>WM: (13391: O1912 ^name predict-no)
  7541. =>WM: (13390: O1911 ^name predict-yes)
  7542. =>WM: (13389: R959 ^value 1)
  7543. =>WM: (13388: R1 ^reward R959)
  7544. =>WM: (13387: I3 ^see 0)
  7545. <=WM: (13378: S1 ^operator O1909 +)
  7546. <=WM: (13379: S1 ^operator O1910 +)
  7547. <=WM: (13380: S1 ^operator O1910)
  7548. <=WM: (13373: R1 ^reward R958)
  7549. <=WM: (13372: I3 ^see 1)
  7550. <=WM: (13376: O1910 ^name predict-no)
  7551. <=WM: (13375: O1909 ^name predict-yes)
  7552. <=WM: (13374: R958 ^value 1)
  7553. --- Inner Elaboration Phase, active level 1 (S1) ---
  7554. Firing prefer*rvt*predict-yes*H0
  7555. -->
  7556. Firing rl*prefer*rvt*predict-yes*H0*5
  7557. -->
  7558. (S1 ^operator O1911 = 0.)
  7559. Firing prefer*rvt*predict-no*H0
  7560. -->
  7561. Firing rl*prefer*rvt*predict-no*H0*6
  7562. -->
  7563. (S1 ^operator O1912 = 0.9999999999999999)
  7564. inner elaboration loop at bottom goal.
  7565. Retracting rl*prefer*rvt*predict-no*H0*6
  7566. -->
  7567. (S1 ^operator O1910 = 0.9999999999999999)
  7568. Retracting rl*prefer*rvt*predict-yes*H0*5
  7569. -->
  7570. (S1 ^operator O1909 = 0.)
  7571. --- END Proposal Phase ---
  7572. --- Decision Phase ---
  7573. RL update rl*prefer*rvt*predict-no*H0*6 1 0 1 -> 1 0 1(R,m,v=1,1,0)
  7574. =>WM: (13394: S1 ^operator O1912)
  7575. 956: O: O1912 (predict-no)
  7576. --- END Decision Phase ---
  7577. --- Application Phase ---
  7578. --- Firing Productions (PE) For State At Depth 1 ---
  7579. --- Inner Elaboration Phase, active level 1 (S1) ---
  7580. Firing apply*operator
  7581. -->
  7582. (I3 ^predict-no N956 + :O )
  7583. Firing apply*operator*complete
  7584. -->
  7585. (I3 ^predict-no N955 - :O )
  7586. inner elaboration loop at bottom goal.
  7587. --- Change Working Memory (PE) ---
  7588. =>WM: (13395: I3 ^predict-no N956)
  7589. <=WM: (13382: N955 ^status complete)
  7590. <=WM: (13381: I3 ^predict-no N955)
  7591. --- Firing Productions (IE) For State At Depth 1 ---
  7592. --- Inner Elaboration Phase, active level 1 (S1) ---
  7593. Firing monitor*world
  7594. -->
  7595. I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
  7596. --- Change Working Memory (IE) ---
  7597. --- END Application Phase ---
  7598. --- Output Phase ---
  7599. ENV: Agent did: predict-no for direction U in state State-A
  7600. In State-A moving U
  7601. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  7602. predict error 0
  7603. dir: dir isL
  7604. --- END Output Phase ---
  7605. |\---- Input Phase ---
  7606. =>WM: (13399: I2 ^dir L)
  7607. =>WM: (13398: I2 ^reward 1)
  7608. =>WM: (13397: I2 ^see 0)
  7609. =>WM: (13396: N956 ^status complete)
  7610. <=WM: (13385: I2 ^dir U)
  7611. <=WM: (13384: I2 ^reward 1)
  7612. <=WM: (13383: I2 ^see 0)
  7613. =>WM: (13400: I2 ^level-1 L1-root)
  7614. <=WM: (13386: I2 ^level-1 L1-root)
  7615. --- END Input Phase ---
  7616. --- Proposal Phase ---
  7617. --- Inner Elaboration Phase, active level 1 (S1) ---
  7618. Firing rl*prefer*rvt*predict-no*H0*2*v1*H1*32
  7619. -->
  7620. (S1 ^operator O1912 = 0.6126622914849755)
  7621. Firing rl*prefer*rvt*predict-yes*H0*1*v1*H1*31
  7622. -->
  7623. (S1 ^operator O1911 = -0.02274740735326741)
  7624. Firing prefer*rvt*predict-no*H0*2*v1*H1
  7625. -->
  7626. Firing prefer*rvt*predict-yes*H0*1*v1*H1
  7627. -->
  7628. Firing elaborate*copy-see-to-output-link
  7629. -->
  7630. (I3 ^see 0 +)
  7631. Firing elaborate*reward*based*on*reward
  7632. -->
  7633. (R960 ^value 1 +)
  7634. (R1 ^reward R960 +)
  7635. Firing propose*predict-yes
  7636. -->
  7637. (O1913 ^name predict-yes +)
  7638. (S1 ^operator O1913 +)
  7639. Firing propose*predict-no
  7640. -->
  7641. (O1914 ^name predict-no +)
  7642. (S1 ^operator O1914 +)
  7643. Firing rl*prefer*rvt*predict-no*H0*2
  7644. -->
  7645. (S1 ^operator O1912 = 0.3873365065796835)
  7646. Firing rl*prefer*rvt*predict-yes*H0*1
  7647. -->
  7648. (S1 ^operator O1911 = 0.3895394851831418)
  7649. Firing prefer*rvt*predict-yes*H0
  7650. -->
  7651. Firing prefer*rvt*predict-no*H0
  7652. -->
  7653. Firing elaborate*copy-dir-to-output-link
  7654. -->
  7655. (I3 ^dir L +)
  7656. inner elaboration loop at bottom goal.
  7657. Retracting elaborate*copy-see-to-output-link
  7658. -->
  7659. (I3 ^see 0 +)
  7660. Retracting propose*predict-no
  7661. -->
  7662. (O1912 ^name predict-no +)
  7663. (S1 ^operator O1912 +)
  7664. Retracting propose*predict-yes
  7665. -->
  7666. (O1911 ^name predict-yes +)
  7667. (S1 ^operator O1911 +)
  7668. Retracting elaborate*reward*based*on*reward
  7669. -->
  7670. (R959 ^value 1 +)
  7671. (R1 ^reward R959 +)
  7672. Retracting elaborate*copy-dir-to-output-link
  7673. -->
  7674. (I3 ^dir U +)
  7675. Retracting rl*prefer*rvt*predict-no*H0*6
  7676. -->
  7677. (S1 ^operator O1912 = 0.9999999999999999)
  7678. Retracting rl*prefer*rvt*predict-yes*H0*5
  7679. -->
  7680. (S1 ^operator O1911 = 0.)
  7681. =>WM: (13407: S1 ^operator O1914 +)
  7682. =>WM: (13406: S1 ^operator O1913 +)
  7683. =>WM: (13405: I3 ^dir L)
  7684. =>WM: (13404: O1914 ^name predict-no)
  7685. =>WM: (13403: O1913 ^name predict-yes)
  7686. =>WM: (13402: R960 ^value 1)
  7687. =>WM: (13401: R1 ^reward R960)
  7688. <=WM: (13392: S1 ^operator O1911 +)
  7689. <=WM: (13393: S1 ^operator O1912 +)
  7690. <=WM: (13394: S1 ^operator O1912)
  7691. <=WM: (13377: I3 ^dir U)
  7692. <=WM: (13388: R1 ^reward R959)
  7693. <=WM: (13391: O1912 ^name predict-no)
  7694. <=WM: (13390: O1911 ^name predict-yes)
  7695. <=WM: (13389: R959 ^value 1)
  7696. --- Inner Elaboration Phase, active level 1 (S1) ---
  7697. Firing prefer*rvt*predict-yes*H0
  7698. -->
  7699. Firing rl*prefer*rvt*predict-yes*H0*1*v1*H1*31
  7700. -->
  7701. (S1 ^operator O1913 = -0.02274740735326741)
  7702. Firing rl*prefer*rvt*predict-yes*H0*1
  7703. -->
  7704. (S1 ^operator O1913 = 0.3895394851831418)
  7705. Firing prefer*rvt*predict-yes*H0*1*v1*H1
  7706. -->
  7707. Firing prefer*rvt*predict-no*H0
  7708. -->
  7709. Firing rl*prefer*rvt*predict-no*H0*2*v1*H1*32
  7710. -->
  7711. (S1 ^operator O1914 = 0.6126622914849755)
  7712. Firing rl*prefer*rvt*predict-no*H0*2
  7713. -->
  7714. (S1 ^operator O1914 = 0.3873365065796835)
  7715. Firing prefer*rvt*predict-no*H0*2*v1*H1
  7716. -->
  7717. inner elaboration loop at bottom goal.
  7718. Retracting rl*prefer*rvt*predict-no*H0*2
  7719. -->
  7720. (S1 ^operator O1912 = 0.3873365065796835)
  7721. Retracting rl*prefer*rvt*predict-no*H0*2*v1*H1*32
  7722. -->
  7723. (S1 ^operator O1912 = 0.6126622914849755)
  7724. Retracting rl*prefer*rvt*predict-yes*H0*1
  7725. -->
  7726. (S1 ^operator O1911 = 0.3895394851831418)
  7727. Retracting rl*prefer*rvt*predict-yes*H0*1*v1*H1*31
  7728. -->
  7729. (S1 ^operator O1911 = -0.02274740735326741)
  7730. --- END Proposal Phase ---
  7731. --- Decision Phase ---
  7732. RL update rl*prefer*rvt*predict-no*H0*6 1 0 1 -> 1 0 1(R,m,v=1,1,0)
  7733. =>WM: (13408: S1 ^operator O1914)
  7734. 957: O: O1914 (predict-no)
  7735. --- END Decision Phase ---
  7736. --- Application Phase ---
  7737. --- Firing Productions (PE) For State At Depth 1 ---
  7738. --- Inner Elaboration Phase, active level 1 (S1) ---
  7739. Firing apply*operator
  7740. -->
  7741. (I3 ^predict-no N957 + :O )
  7742. Firing apply*operator*complete
  7743. -->
  7744. (I3 ^predict-no N956 - :O )
  7745. inner elaboration loop at bottom goal.
  7746. --- Change Working Memory (PE) ---
  7747. =>WM: (13409: I3 ^predict-no N957)
  7748. <=WM: (13396: N956 ^status complete)
  7749. <=WM: (13395: I3 ^predict-no N956)
  7750. --- Firing Productions (IE) For State At Depth 1 ---
  7751. --- Inner Elaboration Phase, active level 1 (S1) ---
  7752. Firing monitor*world
  7753. -->
  7754. I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
  7755. --- Change Working Memory (IE) ---
  7756. --- END Application Phase ---
  7757. --- Output Phase ---
  7758. ENV: Agent did: predict-no for direction L in state State-A
  7759. In State-A moving L
  7760. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  7761. predict error 0
  7762. dir: dir isU
  7763. --- END Output Phase ---
  7764. /|\--- Input Phase ---
  7765. =>WM: (13413: I2 ^dir U)
  7766. =>WM: (13412: I2 ^reward 1)
  7767. =>WM: (13411: I2 ^see 0)
  7768. =>WM: (13410: N957 ^status complete)
  7769. <=WM: (13399: I2 ^dir L)
  7770. <=WM: (13398: I2 ^reward 1)
  7771. <=WM: (13397: I2 ^see 0)
  7772. =>WM: (13414: I2 ^level-1 L0-root)
  7773. <=WM: (13400: I2 ^level-1 L1-root)
  7774. --- END Input Phase ---
  7775. --- Proposal Phase ---
  7776. --- Inner Elaboration Phase, active level 1 (S1) ---
  7777. Firing elaborate*copy-see-to-output-link
  7778. -->
  7779. (I3 ^see 0 +)
  7780. Firing elaborate*reward*based*on*reward
  7781. -->
  7782. (R961 ^value 1 +)
  7783. (R1 ^reward R961 +)
  7784. Firing propose*predict-yes
  7785. -->
  7786. (O1915 ^name predict-yes +)
  7787. (S1 ^operator O1915 +)
  7788. Firing propose*predict-no
  7789. -->
  7790. (O1916 ^name predict-no +)
  7791. (S1 ^operator O1916 +)
  7792. Firing rl*prefer*rvt*predict-no*H0*6
  7793. -->
  7794. (S1 ^operator O1914 = 0.9999999999999999)
  7795. Firing rl*prefer*rvt*predict-yes*H0*5
  7796. -->
  7797. (S1 ^operator O1913 = 0.)
  7798. Firing prefer*rvt*predict-yes*H0
  7799. -->
  7800. Firing prefer*rvt*predict-no*H0
  7801. -->
  7802. Firing elaborate*copy-dir-to-output-link
  7803. -->
  7804. (I3 ^dir U +)
  7805. inner elaboration loop at bottom goal.
  7806. Retracting elaborate*copy-see-to-output-link
  7807. -->
  7808. (I3 ^see 0 +)
  7809. Retracting propose*predict-no
  7810. -->
  7811. (O1914 ^name predict-no +)
  7812. (S1 ^operator O1914 +)
  7813. Retracting propose*predict-yes
  7814. -->
  7815. (O1913 ^name predict-yes +)
  7816. (S1 ^operator O1913 +)
  7817. Retracting elaborate*reward*based*on*reward
  7818. -->
  7819. (R960 ^value 1 +)
  7820. (R1 ^reward R960 +)
  7821. Retracting elaborate*copy-dir-to-output-link
  7822. -->
  7823. (I3 ^dir L +)
  7824. Retracting rl*prefer*rvt*predict-no*H0*2
  7825. -->
  7826. (S1 ^operator O1914 = 0.3873365065796835)
  7827. Retracting rl*prefer*rvt*predict-no*H0*2*v1*H1*32
  7828. -->
  7829. (S1 ^operator O1914 = 0.6126622914849755)
  7830. Retracting rl*prefer*rvt*predict-yes*H0*1
  7831. -->
  7832. (S1 ^operator O1913 = 0.3895394851831418)
  7833. Retracting rl*prefer*rvt*predict-yes*H0*1*v1*H1*31
  7834. -->
  7835. (S1 ^operator O1913 = -0.02274740735326741)
  7836. =>WM: (13421: S1 ^operator O1916 +)
  7837. =>WM: (13420: S1 ^operator O1915 +)
  7838. =>WM: (13419: I3 ^dir U)
  7839. =>WM: (13418: O1916 ^name predict-no)
  7840. =>WM: (13417: O1915 ^name predict-yes)
  7841. =>WM: (13416: R961 ^value 1)
  7842. =>WM: (13415: R1 ^reward R961)
  7843. <=WM: (13406: S1 ^operator O1913 +)
  7844. <=WM: (13407: S1 ^operator O1914 +)
  7845. <=WM: (13408: S1 ^operator O1914)
  7846. <=WM: (13405: I3 ^dir L)
  7847. <=WM: (13401: R1 ^reward R960)
  7848. <=WM: (13404: O1914 ^name predict-no)
  7849. <=WM: (13403: O1913 ^name predict-yes)
  7850. <=WM: (13402: R960 ^value 1)
  7851. --- Inner Elaboration Phase, active level 1 (S1) ---
  7852. Firing prefer*rvt*predict-yes*H0
  7853. -->
  7854. Firing rl*prefer*rvt*predict-yes*H0*5
  7855. -->
  7856. (S1 ^operator O1915 = 0.)
  7857. Firing prefer*rvt*predict-no*H0
  7858. -->
  7859. Firing rl*prefer*rvt*predict-no*H0*6
  7860. -->
  7861. (S1 ^operator O1916 = 0.9999999999999999)
  7862. inner elaboration loop at bottom goal.
  7863. Retracting rl*prefer*rvt*predict-no*H0*6
  7864. -->
  7865. (S1 ^operator O1914 = 0.9999999999999999)
  7866. Retracting rl*prefer*rvt*predict-yes*H0*5
  7867. -->
  7868. (S1 ^operator O1913 = 0.)
  7869. --- END Proposal Phase ---
  7870. --- Decision Phase ---
  7871. RL update rl*prefer*rvt*predict-no*H0*2 0.71908 -0.331744 0.387337 -> 0.719081 -0.331744 0.387337(R,m,v=1,0.930233,0.0652795)
  7872. RL update rl*prefer*rvt*predict-no*H0*2*v1*H1*32 0.280918 0.331744 0.612662 -> 0.280918 0.331744 0.612662(R,m,v=1,1,0)
  7873. =>WM: (13422: S1 ^operator O1916)
  7874. 958: O: O1916 (predict-no)
  7875. --- END Decision Phase ---
  7876. --- Application Phase ---
  7877. --- Firing Productions (PE) For State At Depth 1 ---
  7878. --- Inner Elaboration Phase, active level 1 (S1) ---
  7879. Firing apply*operator
  7880. -->
  7881. (I3 ^predict-no N958 + :O )
  7882. Firing apply*operator*complete
  7883. -->
  7884. (I3 ^predict-no N957 - :O )
  7885. inner elaboration loop at bottom goal.
  7886. --- Change Working Memory (PE) ---
  7887. =>WM: (13423: I3 ^predict-no N958)
  7888. <=WM: (13410: N957 ^status complete)
  7889. <=WM: (13409: I3 ^predict-no N957)
  7890. --- Firing Productions (IE) For State At Depth 1 ---
  7891. --- Inner Elaboration Phase, active level 1 (S1) ---
  7892. Firing monitor*world
  7893. -->
  7894. I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
  7895. --- Change Working Memory (IE) ---
  7896. --- END Application Phase ---
  7897. --- Output Phase ---
  7898. ENV: Agent did: predict-no for direction U in state State-A
  7899. In State-A moving U
  7900. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  7901. predict error 0
  7902. dir: dir isR
  7903. --- END Output Phase ---
  7904. -/--- Input Phase ---
  7905. =>WM: (13427: I2 ^dir R)
  7906. =>WM: (13426: I2 ^reward 1)
  7907. =>WM: (13425: I2 ^see 0)
  7908. =>WM: (13424: N958 ^status complete)
  7909. <=WM: (13413: I2 ^dir U)
  7910. <=WM: (13412: I2 ^reward 1)
  7911. <=WM: (13411: I2 ^see 0)
  7912. =>WM: (13428: I2 ^level-1 L0-root)
  7913. <=WM: (13414: I2 ^level-1 L0-root)
  7914. --- END Input Phase ---
  7915. --- Proposal Phase ---
  7916. --- Inner Elaboration Phase, active level 1 (S1) ---
  7917. Firing rl*prefer*rvt*predict-yes*H0*3*v1*H1*34
  7918. -->
  7919. (S1 ^operator O1915 = 0.8155985324859676)
  7920. Firing rl*prefer*rvt*predict-no*H0*4*v1*H1*33
  7921. -->
  7922. (S1 ^operator O1916 = -0.00558448899823713)
  7923. Firing prefer*rvt*predict-no*H0*4*v1*H1
  7924. -->
  7925. Firing prefer*rvt*predict-yes*H0*3*v1*H1
  7926. -->
  7927. Firing elaborate*copy-see-to-output-link
  7928. -->
  7929. (I3 ^see 0 +)
  7930. Firing elaborate*reward*based*on*reward
  7931. -->
  7932. (R962 ^value 1 +)
  7933. (R1 ^reward R962 +)
  7934. Firing propose*predict-yes
  7935. -->
  7936. (O1917 ^name predict-yes +)
  7937. (S1 ^operator O1917 +)
  7938. Firing propose*predict-no
  7939. -->
  7940. (O1918 ^name predict-no +)
  7941. (S1 ^operator O1918 +)
  7942. Firing rl*prefer*rvt*predict-no*H0*4
  7943. -->
  7944. (S1 ^operator O1916 = 0.4476188714061859)
  7945. Firing rl*prefer*rvt*predict-yes*H0*3
  7946. -->
  7947. (S1 ^operator O1915 = 0.1844104702696336)
  7948. Firing prefer*rvt*predict-yes*H0
  7949. -->
  7950. Firing prefer*rvt*predict-no*H0
  7951. -->
  7952. Firing elaborate*copy-dir-to-output-link
  7953. -->
  7954. (I3 ^dir R +)
  7955. inner elaboration loop at bottom goal.
  7956. Retracting elaborate*copy-see-to-output-link
  7957. -->
  7958. (I3 ^see 0 +)
  7959. Retracting propose*predict-no
  7960. -->
  7961. (O1916 ^name predict-no +)
  7962. (S1 ^operator O1916 +)
  7963. Retracting propose*predict-yes
  7964. -->
  7965. (O1915 ^name predict-yes +)
  7966. (S1 ^operator O1915 +)
  7967. Retracting elaborate*reward*based*on*reward
  7968. -->
  7969. (R961 ^value 1 +)
  7970. (R1 ^reward R961 +)
  7971. Retracting elaborate*copy-dir-to-output-link
  7972. -->
  7973. (I3 ^dir U +)
  7974. Retracting rl*prefer*rvt*predict-no*H0*6
  7975. -->
  7976. (S1 ^operator O1916 = 0.9999999999999999)
  7977. Retracting rl*prefer*rvt*predict-yes*H0*5
  7978. -->
  7979. (S1 ^operator O1915 = 0.)
  7980. =>WM: (13435: S1 ^operator O1918 +)
  7981. =>WM: (13434: S1 ^operator O1917 +)
  7982. =>WM: (13433: I3 ^dir R)
  7983. =>WM: (13432: O1918 ^name predict-no)
  7984. =>WM: (13431: O1917 ^name predict-yes)
  7985. =>WM: (13430: R962 ^value 1)
  7986. =>WM: (13429: R1 ^reward R962)
  7987. <=WM: (13420: S1 ^operator O1915 +)
  7988. <=WM: (13421: S1 ^operator O1916 +)
  7989. <=WM: (13422: S1 ^operator O1916)
  7990. <=WM: (13419: I3 ^dir U)
  7991. <=WM: (13415: R1 ^reward R961)
  7992. <=WM: (13418: O1916 ^name predict-no)
  7993. <=WM: (13417: O1915 ^name predict-yes)
  7994. <=WM: (13416: R961 ^value 1)
  7995. --- Inner Elaboration Phase, active level 1 (S1) ---
  7996. Firing prefer*rvt*predict-yes*H0
  7997. -->
  7998. Firing rl*prefer*rvt*predict-yes*H0*3*v1*H1*34
  7999. -->
  8000. (S1 ^operator O1917 = 0.8155985324859676)
  8001. Firing rl*prefer*rvt*predict-yes*H0*3
  8002. -->
  8003. (S1 ^operator O1917 = 0.1844104702696336)
  8004. Firing prefer*rvt*predict-yes*H0*3*v1*H1
  8005. -->
  8006. Firing prefer*rvt*predict-no*H0
  8007. -->
  8008. Firing rl*prefer*rvt*predict-no*H0*4*v1*H1*33
  8009. -->
  8010. (S1 ^operator O1918 = -0.00558448899823713)
  8011. Firing rl*prefer*rvt*predict-no*H0*4
  8012. -->
  8013. (S1 ^operator O1918 = 0.4476188714061859)
  8014. Firing prefer*rvt*predict-no*H0*4*v1*H1
  8015. -->
  8016. inner elaboration loop at bottom goal.
  8017. Retracting rl*prefer*rvt*predict-no*H0*4
  8018. -->
  8019. (S1 ^operator O1916 = 0.4476188714061859)
  8020. Retracting rl*prefer*rvt*predict-no*H0*4*v1*H1*33
  8021. -->
  8022. (S1 ^operator O1916 = -0.00558448899823713)
  8023. Retracting rl*prefer*rvt*predict-yes*H0*3
  8024. -->
  8025. (S1 ^operator O1915 = 0.1844104702696336)
  8026. Retracting rl*prefer*rvt*predict-yes*H0*3*v1*H1*34
  8027. -->
  8028. (S1 ^operator O1915 = 0.8155985324859676)
  8029. --- END Proposal Phase ---
  8030. --- Decision Phase ---
  8031. RL update rl*prefer*rvt*predict-no*H0*6 1 0 1 -> 1 0 1(R,m,v=1,1,0)
  8032. =>WM: (13436: S1 ^operator O1917)
  8033. 959: O: O1917 (predict-yes)
  8034. --- END Decision Phase ---
  8035. --- Application Phase ---
  8036. --- Firing Productions (PE) For State At Depth 1 ---
  8037. --- Inner Elaboration Phase, active level 1 (S1) ---
  8038. Firing apply*operator
  8039. -->
  8040. (I3 ^predict-yes N959 + :O )
  8041. Firing apply*operator*complete
  8042. -->
  8043. (I3 ^predict-no N958 - :O )
  8044. inner elaboration loop at bottom goal.
  8045. --- Change Working Memory (PE) ---
  8046. =>WM: (13437: I3 ^predict-yes N959)
  8047. <=WM: (13424: N958 ^status complete)
  8048. <=WM: (13423: I3 ^predict-no N958)
  8049. --- Firing Productions (IE) For State At Depth 1 ---
  8050. --- Inner Elaboration Phase, active level 1 (S1) ---
  8051. Firing monitor*world
  8052. -->
  8053. I see 1 and I'm going to do: predict-yes inner elaboration loop at bottom goal.
  8054. --- Change Working Memory (IE) ---
  8055. --- END Application Phase ---
  8056. --- Output Phase ---
  8057. ENV: Agent did: predict-yes for direction R in state State-A
  8058. In State-A moving R
  8059. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  8060. predict error 0
  8061. dir: dir isL
  8062. --- END Output Phase ---
  8063. |\---- Input Phase ---
  8064. =>WM: (13441: I2 ^dir L)
  8065. =>WM: (13440: I2 ^reward 1)
  8066. =>WM: (13439: I2 ^see 1)
  8067. =>WM: (13438: N959 ^status complete)
  8068. <=WM: (13427: I2 ^dir R)
  8069. <=WM: (13426: I2 ^reward 1)
  8070. <=WM: (13425: I2 ^see 0)
  8071. =>WM: (13442: I2 ^level-1 R1-root)
  8072. <=WM: (13428: I2 ^level-1 L0-root)
  8073. --- END Input Phase ---
  8074. --- Proposal Phase ---
  8075. --- Inner Elaboration Phase, active level 1 (S1) ---
  8076. Firing rl*prefer*rvt*predict-yes*H0*1*v1*H1*36
  8077. -->
  8078. (S1 ^operator O1917 = 0.6104587229728515)
  8079. Firing rl*prefer*rvt*predict-no*H0*2*v1*H1*35
  8080. -->
  8081. (S1 ^operator O1918 = 0.2714993082286609)
  8082. Firing prefer*rvt*predict-no*H0*2*v1*H1
  8083. -->
  8084. Firing prefer*rvt*predict-yes*H0*1*v1*H1
  8085. -->
  8086. Firing elaborate*copy-see-to-output-link
  8087. -->
  8088. (I3 ^see 1 +)
  8089. Firing elaborate*reward*based*on*reward
  8090. -->
  8091. (R963 ^value 1 +)
  8092. (R1 ^reward R963 +)
  8093. Firing propose*predict-yes
  8094. -->
  8095. (O1919 ^name predict-yes +)
  8096. (S1 ^operator O1919 +)
  8097. Firing propose*predict-no
  8098. -->
  8099. (O1920 ^name predict-no +)
  8100. (S1 ^operator O1920 +)
  8101. Firing rl*prefer*rvt*predict-no*H0*2
  8102. -->
  8103. (S1 ^operator O1918 = 0.3873366868699847)
  8104. Firing rl*prefer*rvt*predict-yes*H0*1
  8105. -->
  8106. (S1 ^operator O1917 = 0.3895394851831418)
  8107. Firing prefer*rvt*predict-yes*H0
  8108. -->
  8109. Firing prefer*rvt*predict-no*H0
  8110. -->
  8111. Firing elaborate*copy-dir-to-output-link
  8112. -->
  8113. (I3 ^dir L +)
  8114. inner elaboration loop at bottom goal.
  8115. Retracting elaborate*copy-see-to-output-link
  8116. -->
  8117. (I3 ^see 0 +)
  8118. Retracting propose*predict-no
  8119. -->
  8120. (O1918 ^name predict-no +)
  8121. (S1 ^operator O1918 +)
  8122. Retracting propose*predict-yes
  8123. -->
  8124. (O1917 ^name predict-yes +)
  8125. (S1 ^operator O1917 +)
  8126. Retracting elaborate*reward*based*on*reward
  8127. -->
  8128. (R962 ^value 1 +)
  8129. (R1 ^reward R962 +)
  8130. Retracting elaborate*copy-dir-to-output-link
  8131. -->
  8132. (I3 ^dir R +)
  8133. Retracting rl*prefer*rvt*predict-no*H0*4
  8134. -->
  8135. (S1 ^operator O1918 = 0.4476188714061859)
  8136. Retracting rl*prefer*rvt*predict-no*H0*4*v1*H1*33
  8137. -->
  8138. (S1 ^operator O1918 = -0.00558448899823713)
  8139. Retracting rl*prefer*rvt*predict-yes*H0*3
  8140. -->
  8141. (S1 ^operator O1917 = 0.1844104702696336)
  8142. Retracting rl*prefer*rvt*predict-yes*H0*3*v1*H1*34
  8143. -->
  8144. (S1 ^operator O1917 = 0.8155985324859676)
  8145. =>WM: (13450: S1 ^operator O1920 +)
  8146. =>WM: (13449: S1 ^operator O1919 +)
  8147. =>WM: (13448: I3 ^dir L)
  8148. =>WM: (13447: O1920 ^name predict-no)
  8149. =>WM: (13446: O1919 ^name predict-yes)
  8150. =>WM: (13445: R963 ^value 1)
  8151. =>WM: (13444: R1 ^reward R963)
  8152. =>WM: (13443: I3 ^see 1)
  8153. <=WM: (13434: S1 ^operator O1917 +)
  8154. <=WM: (13436: S1 ^operator O1917)
  8155. <=WM: (13435: S1 ^operator O1918 +)
  8156. <=WM: (13433: I3 ^dir R)
  8157. <=WM: (13429: R1 ^reward R962)
  8158. <=WM: (13387: I3 ^see 0)
  8159. <=WM: (13432: O1918 ^name predict-no)
  8160. <=WM: (13431: O1917 ^name predict-yes)
  8161. <=WM: (13430: R962 ^value 1)
  8162. --- Inner Elaboration Phase, active level 1 (S1) ---
  8163. Firing prefer*rvt*predict-yes*H0
  8164. -->
  8165. Firing rl*prefer*rvt*predict-yes*H0*1
  8166. -->
  8167. (S1 ^operator O1919 = 0.3895394851831418)
  8168. Firing prefer*rvt*predict-yes*H0*1*v1*H1
  8169. -->
  8170. Firing rl*prefer*rvt*predict-yes*H0*1*v1*H1*36
  8171. -->
  8172. (S1 ^operator O1919 = 0.6104587229728515)
  8173. Firing prefer*rvt*predict-no*H0
  8174. -->
  8175. Firing rl*prefer*rvt*predict-no*H0*2
  8176. -->
  8177. (S1 ^operator O1920 = 0.3873366868699847)
  8178. Firing prefer*rvt*predict-no*H0*2*v1*H1
  8179. -->
  8180. Firing rl*prefer*rvt*predict-no*H0*2*v1*H1*35
  8181. -->
  8182. (S1 ^operator O1920 = 0.2714993082286609)
  8183. inner elaboration loop at bottom goal.
  8184. Retracting rl*prefer*rvt*predict-no*H0*2
  8185. -->
  8186. (S1 ^operator O1918 = 0.3873366868699847)
  8187. Retracting rl*prefer*rvt*predict-no*H0*2*v1*H1*35
  8188. -->
  8189. (S1 ^operator O1918 = 0.2714993082286609)
  8190. Retracting rl*prefer*rvt*predict-yes*H0*1
  8191. -->
  8192. (S1 ^operator O1917 = 0.3895394851831418)
  8193. Retracting rl*prefer*rvt*predict-yes*H0*1*v1*H1*36
  8194. -->
  8195. (S1 ^operator O1917 = 0.6104587229728515)
  8196. --- END Proposal Phase ---
  8197. --- Decision Phase ---
  8198. RL update rl*prefer*rvt*predict-yes*H0*3 0.675413 -0.491002 0.18441 -> 0.675411 -0.491002 0.184409(R,m,v=1,0.895062,0.0945096)
  8199. RL update rl*prefer*rvt*predict-yes*H0*3*v1*H1*34 0.324599 0.491 0.815599 -> 0.324597 0.491 0.815597(R,m,v=1,1,0)
  8200. =>WM: (13451: S1 ^operator O1919)
  8201. 960: O: O1919 (predict-yes)
  8202. --- END Decision Phase ---
  8203. --- Application Phase ---
  8204. --- Firing Productions (PE) For State At Depth 1 ---
  8205. --- Inner Elaboration Phase, active level 1 (S1) ---
  8206. Firing apply*operator
  8207. -->
  8208. (I3 ^predict-yes N960 + :O )
  8209. Firing apply*operator*complete
  8210. -->
  8211. (I3 ^predict-yes N959 - :O )
  8212. inner elaboration loop at bottom goal.
  8213. --- Change Working Memory (PE) ---
  8214. =>WM: (13452: I3 ^predict-yes N960)
  8215. <=WM: (13438: N959 ^status complete)
  8216. <=WM: (13437: I3 ^predict-yes N959)
  8217. --- Firing Productions (IE) For State At Depth 1 ---
  8218. --- Inner Elaboration Phase, active level 1 (S1) ---
  8219. Firing monitor*world
  8220. -->
  8221. I see 1 and I'm going to do: predict-yes inner elaboration loop at bottom goal.
  8222. --- Change Working Memory (IE) ---
  8223. --- END Application Phase ---
  8224. --- Output Phase ---
  8225. ENV: Agent did: predict-yes for direction L in state State-B
  8226. In State-B moving L
  8227. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  8228. predict error 0
  8229. dir: dir isL
  8230. --- END Output Phase ---
  8231. /|\--- Input Phase ---
  8232. =>WM: (13456: I2 ^dir L)
  8233. =>WM: (13455: I2 ^reward 1)
  8234. =>WM: (13454: I2 ^see 1)
  8235. =>WM: (13453: N960 ^status complete)
  8236. <=WM: (13441: I2 ^dir L)
  8237. <=WM: (13440: I2 ^reward 1)
  8238. <=WM: (13439: I2 ^see 1)
  8239. =>WM: (13457: I2 ^level-1 L1-root)
  8240. <=WM: (13442: I2 ^level-1 R1-root)
  8241. --- END Input Phase ---
  8242. --- Proposal Phase ---
  8243. --- Inner Elaboration Phase, active level 1 (S1) ---
  8244. Firing rl*prefer*rvt*predict-no*H0*2*v1*H1*32
  8245. -->
  8246. (S1 ^operator O1920 = 0.6126624717752767)
  8247. Firing rl*prefer*rvt*predict-yes*H0*1*v1*H1*31
  8248. -->
  8249. (S1 ^operator O1919 = -0.02274740735326741)
  8250. Firing prefer*rvt*predict-no*H0*2*v1*H1
  8251. -->
  8252. Firing prefer*rvt*predict-yes*H0*1*v1*H1
  8253. -->
  8254. Firing elaborate*copy-see-to-output-link
  8255. -->
  8256. (I3 ^see 1 +)
  8257. Firing elaborate*reward*based*on*reward
  8258. -->
  8259. (R964 ^value 1 +)
  8260. (R1 ^reward R964 +)
  8261. Firing propose*predict-yes
  8262. -->
  8263. (O1921 ^name predict-yes +)
  8264. (S1 ^operator O1921 +)
  8265. Firing propose*predict-no
  8266. -->
  8267. (O1922 ^name predict-no +)
  8268. (S1 ^operator O1922 +)
  8269. Firing rl*prefer*rvt*predict-no*H0*2
  8270. -->
  8271. (S1 ^operator O1920 = 0.3873366868699847)
  8272. Firing rl*prefer*rvt*predict-yes*H0*1
  8273. -->
  8274. (S1 ^operator O1919 = 0.3895394851831418)
  8275. Firing prefer*rvt*predict-yes*H0
  8276. -->
  8277. Firing prefer*rvt*predict-no*H0
  8278. -->
  8279. Firing elaborate*copy-dir-to-output-link
  8280. -->
  8281. (I3 ^dir L +)
  8282. inner elaboration loop at bottom goal.
  8283. Retracting elaborate*copy-see-to-output-link
  8284. -->
  8285. (I3 ^see 1 +)
  8286. Retracting propose*predict-no
  8287. -->
  8288. (O1920 ^name predict-no +)
  8289. (S1 ^operator O1920 +)
  8290. Retracting propose*predict-yes
  8291. -->
  8292. (O1919 ^name predict-yes +)
  8293. (S1 ^operator O1919 +)
  8294. Retracting elaborate*reward*based*on*reward
  8295. -->
  8296. (R963 ^value 1 +)
  8297. (R1 ^reward R963 +)
  8298. Retracting elaborate*copy-dir-to-output-link
  8299. -->
  8300. (I3 ^dir L +)
  8301. Retracting rl*prefer*rvt*predict-no*H0*2*v1*H1*35
  8302. -->
  8303. (S1 ^operator O1920 = 0.2714993082286609)
  8304. Retracting rl*prefer*rvt*predict-no*H0*2
  8305. -->
  8306. (S1 ^operator O1920 = 0.3873366868699847)
  8307. Retracting rl*prefer*rvt*predict-yes*H0*1*v1*H1*36
  8308. -->
  8309. (S1 ^operator O1919 = 0.6104587229728515)
  8310. Retracting rl*prefer*rvt*predict-yes*H0*1
  8311. -->
  8312. (S1 ^operator O1919 = 0.3895394851831418)
  8313. =>WM: (13463: S1 ^operator O1922 +)
  8314. =>WM: (13462: S1 ^operator O1921 +)
  8315. =>WM: (13461: O1922 ^name predict-no)
  8316. =>WM: (13460: O1921 ^name predict-yes)
  8317. =>WM: (13459: R964 ^value 1)
  8318. =>WM: (13458: R1 ^reward R964)
  8319. <=WM: (13449: S1 ^operator O1919 +)
  8320. <=WM: (13451: S1 ^operator O1919)
  8321. <=WM: (13450: S1 ^operator O1920 +)
  8322. <=WM: (13444: R1 ^reward R963)
  8323. <=WM: (13447: O1920 ^name predict-no)
  8324. <=WM: (13446: O1919 ^name predict-yes)
  8325. <=WM: (13445: R963 ^value 1)
  8326. --- Inner Elaboration Phase, active level 1 (S1) ---
  8327. Firing prefer*rvt*predict-yes*H0
  8328. -->
  8329. Firing rl*prefer*rvt*predict-yes*H0*1
  8330. -->
  8331. (S1 ^operator O1921 = 0.3895394851831418)
  8332. Firing prefer*rvt*predict-yes*H0*1*v1*H1
  8333. -->
  8334. Firing rl*prefer*rvt*predict-yes*H0*1*v1*H1*31
  8335. -->
  8336. (S1 ^operator O1921 = -0.02274740735326741)
  8337. Firing prefer*rvt*predict-no*H0
  8338. -->
  8339. Firing rl*prefer*rvt*predict-no*H0*2
  8340. -->
  8341. (S1 ^operator O1922 = 0.3873366868699847)
  8342. Firing prefer*rvt*predict-no*H0*2*v1*H1
  8343. -->
  8344. Firing rl*prefer*rvt*predict-no*H0*2*v1*H1*32
  8345. -->
  8346. (S1 ^operator O1922 = 0.6126624717752767)
  8347. inner elaboration loop at bottom goal.
  8348. Retracting rl*prefer*rvt*predict-no*H0*2
  8349. -->
  8350. (S1 ^operator O1920 = 0.3873366868699847)
  8351. Retracting rl*prefer*rvt*predict-no*H0*2*v1*H1*32
  8352. -->
  8353. (S1 ^operator O1920 = 0.6126624717752767)
  8354. Retracting rl*prefer*rvt*predict-yes*H0*1
  8355. -->
  8356. (S1 ^operator O1919 = 0.3895394851831418)
  8357. Retracting rl*prefer*rvt*predict-yes*H0*1*v1*H1*31
  8358. -->
  8359. (S1 ^operator O1919 = -0.02274740735326741)
  8360. --- END Proposal Phase ---
  8361. --- Decision Phase ---
  8362. RL update rl*prefer*rvt*predict-yes*H0*1 0.711951 -0.322412 0.389539 -> 0.711951 -0.322412 0.38954(R,m,v=1,0.8875,0.100472)
  8363. RL update rl*prefer*rvt*predict-yes*H0*1*v1*H1*36 0.288049 0.32241 0.610459 -> 0.288049 0.32241 0.610459(R,m,v=1,1,0)
  8364. =>WM: (13464: S1 ^operator O1922)
  8365. 961: O: O1922 (predict-no)
  8366. --- END Decision Phase ---
  8367. --- Application Phase ---
  8368. --- Firing Productions (PE) For State At Depth 1 ---
  8369. --- Inner Elaboration Phase, active level 1 (S1) ---
  8370. Firing apply*operator
  8371. -->
  8372. (I3 ^predict-no N961 + :O )
  8373. Firing apply*operator*complete
  8374. -->
  8375. (I3 ^predict-yes N960 - :O )
  8376. inner elaboration loop at bottom goal.
  8377. --- Change Working Memory (PE) ---
  8378. =>WM: (13465: I3 ^predict-no N961)
  8379. <=WM: (13453: N960 ^status complete)
  8380. <=WM: (13452: I3 ^predict-yes N960)
  8381. --- Firing Productions (IE) For State At Depth 1 ---
  8382. --- Inner Elaboration Phase, active level 1 (S1) ---
  8383. Firing monitor*world
  8384. -->
  8385. I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
  8386. --- Change Working Memory (IE) ---
  8387. --- END Application Phase ---
  8388. --- Output Phase ---
  8389. ENV: Agent did: predict-no for direction L in state State-A
  8390. In State-A moving L
  8391. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  8392. predict error 0
  8393. dir: dir isU
  8394. --- END Output Phase ---
  8395. ---- Input Phase ---
  8396. =>WM: (13469: I2 ^dir U)
  8397. =>WM: (13468: I2 ^reward 1)
  8398. =>WM: (13467: I2 ^see 0)
  8399. =>WM: (13466: N961 ^status complete)
  8400. <=WM: (13456: I2 ^dir L)
  8401. <=WM: (13455: I2 ^reward 1)
  8402. <=WM: (13454: I2 ^see 1)
  8403. =>WM: (13470: I2 ^level-1 L0-root)
  8404. <=WM: (13457: I2 ^level-1 L1-root)
  8405. --- END Input Phase ---
  8406. --- Proposal Phase ---
  8407. --- Inner Elaboration Phase, active level 1 (S1) ---
  8408. Firing elaborate*copy-see-to-output-link
  8409. -->
  8410. (I3 ^see 0 +)
  8411. Firing elaborate*reward*based*on*reward
  8412. -->
  8413. (R965 ^value 1 +)
  8414. (R1 ^reward R965 +)
  8415. Firing propose*predict-yes
  8416. -->
  8417. (O1923 ^name predict-yes +)
  8418. (S1 ^operator O1923 +)
  8419. Firing propose*predict-no
  8420. -->
  8421. (O1924 ^name predict-no +)
  8422. (S1 ^operator O1924 +)
  8423. Firing rl*prefer*rvt*predict-no*H0*6
  8424. -->
  8425. (S1 ^operator O1922 = 0.9999999999999999)
  8426. Firing rl*prefer*rvt*predict-yes*H0*5
  8427. -->
  8428. (S1 ^operator O1921 = 0.)
  8429. Firing prefer*rvt*predict-yes*H0
  8430. -->
  8431. Firing prefer*rvt*predict-no*H0
  8432. -->
  8433. Firing elaborate*copy-dir-to-output-link
  8434. -->
  8435. (I3 ^dir U +)
  8436. inner elaboration loop at bottom goal.
  8437. Retracting elaborate*copy-see-to-output-link
  8438. -->
  8439. (I3 ^see 1 +)
  8440. Retracting propose*predict-no
  8441. -->
  8442. (O1922 ^name predict-no +)
  8443. (S1 ^operator O1922 +)
  8444. Retracting propose*predict-yes
  8445. -->
  8446. (O1921 ^name predict-yes +)
  8447. (S1 ^operator O1921 +)
  8448. Retracting elaborate*reward*based*on*reward
  8449. -->
  8450. (R964 ^value 1 +)
  8451. (R1 ^reward R964 +)
  8452. Retracting elaborate*copy-dir-to-output-link
  8453. -->
  8454. (I3 ^dir L +)
  8455. Retracting rl*prefer*rvt*predict-no*H0*2*v1*H1*32
  8456. -->
  8457. (S1 ^operator O1922 = 0.6126624717752767)
  8458. Retracting rl*prefer*rvt*predict-no*H0*2
  8459. -->
  8460. (S1 ^operator O1922 = 0.3873366868699847)
  8461. Retracting rl*prefer*rvt*predict-yes*H0*1*v1*H1*31
  8462. -->
  8463. (S1 ^operator O1921 = -0.02274740735326741)
  8464. Retracting rl*prefer*rvt*predict-yes*H0*1
  8465. -->
  8466. (S1 ^operator O1921 = 0.3895397539597428)
  8467. =>WM: (13478: S1 ^operator O1924 +)
  8468. =>WM: (13477: S1 ^operator O1923 +)
  8469. =>WM: (13476: I3 ^dir U)
  8470. =>WM: (13475: O1924 ^name predict-no)
  8471. =>WM: (13474: O1923 ^name predict-yes)
  8472. =>WM: (13473: R965 ^value 1)
  8473. =>WM: (13472: R1 ^reward R965)
  8474. =>WM: (13471: I3 ^see 0)
  8475. <=WM: (13462: S1 ^operator O1921 +)
  8476. <=WM: (13463: S1 ^operator O1922 +)
  8477. <=WM: (13464: S1 ^operator O1922)
  8478. <=WM: (13448: I3 ^dir L)
  8479. <=WM: (13458: R1 ^reward R964)
  8480. <=WM: (13443: I3 ^see 1)
  8481. <=WM: (13461: O1922 ^name predict-no)
  8482. <=WM: (13460: O1921 ^name predict-yes)
  8483. <=WM: (13459: R964 ^value 1)
  8484. --- Inner Elaboration Phase, active level 1 (S1) ---
  8485. Firing prefer*rvt*predict-yes*H0
  8486. -->
  8487. Firing rl*prefer*rvt*predict-yes*H0*5
  8488. -->
  8489. (S1 ^operator O1923 = 0.)
  8490. Firing prefer*rvt*predict-no*H0
  8491. -->
  8492. Firing rl*prefer*rvt*predict-no*H0*6
  8493. -->
  8494. (S1 ^operator O1924 = 0.9999999999999999)
  8495. inner elaboration loop at bottom goal.
  8496. Retracting rl*prefer*rvt*predict-no*H0*6
  8497. -->
  8498. (S1 ^operator O1922 = 0.9999999999999999)
  8499. Retracting rl*prefer*rvt*predict-yes*H0*5
  8500. -->
  8501. (S1 ^operator O1921 = 0.)
  8502. --- END Proposal Phase ---
  8503. --- Decision Phase ---
  8504. RL update rl*prefer*rvt*predict-no*H0*2 0.719081 -0.331744 0.387337 -> 0.719081 -0.331744 0.387337(R,m,v=1,0.930636,0.0649281)
  8505. RL update rl*prefer*rvt*predict-no*H0*2*v1*H1*32 0.280918 0.331744 0.612662 -> 0.280918 0.331744 0.612663(R,m,v=1,1,0)
  8506. =>WM: (13479: S1 ^operator O1924)
  8507. 962: O: O1924 (predict-no)
  8508. --- END Decision Phase ---
  8509. --- Application Phase ---
  8510. --- Firing Productions (PE) For State At Depth 1 ---
  8511. --- Inner Elaboration Phase, active level 1 (S1) ---
  8512. Firing apply*operator
  8513. -->
  8514. (I3 ^predict-no N962 + :O )
  8515. Firing apply*operator*complete
  8516. -->
  8517. (I3 ^predict-no N961 - :O )
  8518. inner elaboration loop at bottom goal.
  8519. --- Change Working Memory (PE) ---
  8520. =>WM: (13480: I3 ^predict-no N962)
  8521. <=WM: (13466: N961 ^status complete)
  8522. <=WM: (13465: I3 ^predict-no N961)
  8523. --- Firing Productions (IE) For State At Depth 1 ---
  8524. --- Inner Elaboration Phase, active level 1 (S1) ---
  8525. Firing monitor*world
  8526. -->
  8527. I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
  8528. --- Change Working Memory (IE) ---
  8529. --- END Application Phase ---
  8530. --- Output Phase ---
  8531. ENV: Agent did: predict-no for direction U in state State-A
  8532. In State-A moving U
  8533. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  8534. predict error 0
  8535. dir: dir isR
  8536. --- END Output Phase ---
  8537. /|\---- Input Phase ---
  8538. =>WM: (13484: I2 ^dir R)
  8539. =>WM: (13483: I2 ^reward 1)
  8540. =>WM: (13482: I2 ^see 0)
  8541. =>WM: (13481: N962 ^status complete)
  8542. <=WM: (13469: I2 ^dir U)
  8543. <=WM: (13468: I2 ^reward 1)
  8544. <=WM: (13467: I2 ^see 0)
  8545. =>WM: (13485: I2 ^level-1 L0-root)
  8546. <=WM: (13470: I2 ^level-1 L0-root)
  8547. --- END Input Phase ---
  8548. --- Proposal Phase ---
  8549. --- Inner Elaboration Phase, active level 1 (S1) ---
  8550. Firing rl*prefer*rvt*predict-yes*H0*3*v1*H1*34
  8551. -->
  8552. (S1 ^operator O1923 = 0.8155971820726273)
  8553. Firing rl*prefer*rvt*predict-no*H0*4*v1*H1*33
  8554. -->
  8555. (S1 ^operator O1924 = -0.00558448899823713)
  8556. Firing prefer*rvt*predict-no*H0*4*v1*H1
  8557. -->
  8558. Firing prefer*rvt*predict-yes*H0*3*v1*H1
  8559. -->
  8560. Firing elaborate*copy-see-to-output-link
  8561. -->
  8562. (I3 ^see 0 +)
  8563. Firing elaborate*reward*based*on*reward
  8564. -->
  8565. (R966 ^value 1 +)
  8566. (R1 ^reward R966 +)
  8567. Firing propose*predict-yes
  8568. -->
  8569. (O1925 ^name predict-yes +)
  8570. (S1 ^operator O1925 +)
  8571. Firing propose*predict-no
  8572. -->
  8573. (O1926 ^name predict-no +)
  8574. (S1 ^operator O1926 +)
  8575. Firing rl*prefer*rvt*predict-no*H0*4
  8576. -->
  8577. (S1 ^operator O1924 = 0.4476188714061859)
  8578. Firing rl*prefer*rvt*predict-yes*H0*3
  8579. -->
  8580. (S1 ^operator O1923 = 0.1844091198562935)
  8581. Firing prefer*rvt*predict-yes*H0
  8582. -->
  8583. Firing prefer*rvt*predict-no*H0
  8584. -->
  8585. Firing elaborate*copy-dir-to-output-link
  8586. -->
  8587. (I3 ^dir R +)
  8588. inner elaboration loop at bottom goal.
  8589. Retracting elaborate*copy-see-to-output-link
  8590. -->
  8591. (I3 ^see 0 +)
  8592. Retracting propose*predict-no
  8593. -->
  8594. (O1924 ^name predict-no +)
  8595. (S1 ^operator O1924 +)
  8596. Retracting propose*predict-yes
  8597. -->
  8598. (O1923 ^name predict-yes +)
  8599. (S1 ^operator O1923 +)
  8600. Retracting elaborate*reward*based*on*reward
  8601. -->
  8602. (R965 ^value 1 +)
  8603. (R1 ^reward R965 +)
  8604. Retracting elaborate*copy-dir-to-output-link
  8605. -->
  8606. (I3 ^dir U +)
  8607. Retracting rl*prefer*rvt*predict-no*H0*6
  8608. -->
  8609. (S1 ^operator O1924 = 0.9999999999999999)
  8610. Retracting rl*prefer*rvt*predict-yes*H0*5
  8611. -->
  8612. (S1 ^operator O1923 = 0.)
  8613. =>WM: (13492: S1 ^operator O1926 +)
  8614. =>WM: (13491: S1 ^operator O1925 +)
  8615. =>WM: (13490: I3 ^dir R)
  8616. =>WM: (13489: O1926 ^name predict-no)
  8617. =>WM: (13488: O1925 ^name predict-yes)
  8618. =>WM: (13487: R966 ^value 1)
  8619. =>WM: (13486: R1 ^reward R966)
  8620. <=WM: (13477: S1 ^operator O1923 +)
  8621. <=WM: (13478: S1 ^operator O1924 +)
  8622. <=WM: (13479: S1 ^operator O1924)
  8623. <=WM: (13476: I3 ^dir U)
  8624. <=WM: (13472: R1 ^reward R965)
  8625. <=WM: (13475: O1924 ^name predict-no)
  8626. <=WM: (13474: O1923 ^name predict-yes)
  8627. <=WM: (13473: R965 ^value 1)
  8628. --- Inner Elaboration Phase, active level 1 (S1) ---
  8629. Firing prefer*rvt*predict-yes*H0
  8630. -->
  8631. Firing rl*prefer*rvt*predict-yes*H0*3*v1*H1*34
  8632. -->
  8633. (S1 ^operator O1925 = 0.8155971820726273)
  8634. Firing rl*prefer*rvt*predict-yes*H0*3
  8635. -->
  8636. (S1 ^operator O1925 = 0.1844091198562935)
  8637. Firing prefer*rvt*predict-yes*H0*3*v1*H1
  8638. -->
  8639. Firing prefer*rvt*predict-no*H0
  8640. -->
  8641. Firing rl*prefer*rvt*predict-no*H0*4*v1*H1*33
  8642. -->
  8643. (S1 ^operator O1926 = -0.00558448899823713)
  8644. Firing rl*prefer*rvt*predict-no*H0*4
  8645. -->
  8646. (S1 ^operator O1926 = 0.4476188714061859)
  8647. Firing prefer*rvt*predict-no*H0*4*v1*H1
  8648. -->
  8649. inner elaboration loop at bottom goal.
  8650. Retracting rl*prefer*rvt*predict-no*H0*4
  8651. -->
  8652. (S1 ^operator O1924 = 0.4476188714061859)
  8653. Retracting rl*prefer*rvt*predict-no*H0*4*v1*H1*33
  8654. -->
  8655. (S1 ^operator O1924 = -0.00558448899823713)
  8656. Retracting rl*prefer*rvt*predict-yes*H0*3
  8657. -->
  8658. (S1 ^operator O1923 = 0.1844091198562935)
  8659. Retracting rl*prefer*rvt*predict-yes*H0*3*v1*H1*34
  8660. -->
  8661. (S1 ^operator O1923 = 0.8155971820726273)
  8662. --- END Proposal Phase ---
  8663. --- Decision Phase ---
  8664. RL update rl*prefer*rvt*predict-no*H0*6 1 0 1 -> 1 0 1(R,m,v=1,1,0)
  8665. =>WM: (13493: S1 ^operator O1925)
  8666. 963: O: O1925 (predict-yes)
  8667. --- END Decision Phase ---
  8668. --- Application Phase ---
  8669. --- Firing Productions (PE) For State At Depth 1 ---
  8670. --- Inner Elaboration Phase, active level 1 (S1) ---
  8671. Firing apply*operator
  8672. -->
  8673. (I3 ^predict-yes N963 + :O )
  8674. Firing apply*operator*complete
  8675. -->
  8676. (I3 ^predict-no N962 - :O )
  8677. inner elaboration loop at bottom goal.
  8678. --- Change Working Memory (PE) ---
  8679. =>WM: (13494: I3 ^predict-yes N963)
  8680. <=WM: (13481: N962 ^status complete)
  8681. <=WM: (13480: I3 ^predict-no N962)
  8682. --- Firing Productions (IE) For State At Depth 1 ---
  8683. --- Inner Elaboration Phase, active level 1 (S1) ---
  8684. Firing monitor*world
  8685. -->
  8686. I see 1 and I'm going to do: predict-yes inner elaboration loop at bottom goal.
  8687. --- Change Working Memory (IE) ---
  8688. --- END Application Phase ---
  8689. --- Output Phase ---
  8690. ENV: Agent did: predict-yes for direction R in state State-A
  8691. In State-A moving R
  8692. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  8693. predict error 0
  8694. dir: dir isR
  8695. --- END Output Phase ---
  8696. /|\--- Input Phase ---
  8697. =>WM: (13498: I2 ^dir R)
  8698. =>WM: (13497: I2 ^reward 1)
  8699. =>WM: (13496: I2 ^see 1)
  8700. =>WM: (13495: N963 ^status complete)
  8701. <=WM: (13484: I2 ^dir R)
  8702. <=WM: (13483: I2 ^reward 1)
  8703. <=WM: (13482: I2 ^see 0)
  8704. =>WM: (13499: I2 ^level-1 R1-root)
  8705. <=WM: (13485: I2 ^level-1 L0-root)
  8706. --- END Input Phase ---
  8707. --- Proposal Phase ---
  8708. --- Inner Elaboration Phase, active level 1 (S1) ---
  8709. Firing rl*prefer*rvt*predict-yes*H0*3*v1*H1*40
  8710. -->
  8711. (S1 ^operator O1925 = 0.1398795999120246)
  8712. Firing rl*prefer*rvt*predict-no*H0*4*v1*H1*39
  8713. -->
  8714. (S1 ^operator O1926 = 0.5523829775838558)
  8715. Firing prefer*rvt*predict-no*H0*4*v1*H1
  8716. -->
  8717. Firing prefer*rvt*predict-yes*H0*3*v1*H1
  8718. -->
  8719. Firing elaborate*copy-see-to-output-link
  8720. -->
  8721. (I3 ^see 1 +)
  8722. Firing elaborate*reward*based*on*reward
  8723. -->
  8724. (R967 ^value 1 +)
  8725. (R1 ^reward R967 +)
  8726. Firing propose*predict-yes
  8727. -->
  8728. (O1927 ^name predict-yes +)
  8729. (S1 ^operator O1927 +)
  8730. Firing propose*predict-no
  8731. -->
  8732. (O1928 ^name predict-no +)
  8733. (S1 ^operator O1928 +)
  8734. Firing rl*prefer*rvt*predict-no*H0*4
  8735. -->
  8736. (S1 ^operator O1926 = 0.4476188714061859)
  8737. Firing rl*prefer*rvt*predict-yes*H0*3
  8738. -->
  8739. (S1 ^operator O1925 = 0.1844091198562935)
  8740. Firing prefer*rvt*predict-yes*H0
  8741. -->
  8742. Firing prefer*rvt*predict-no*H0
  8743. -->
  8744. Firing elaborate*copy-dir-to-output-link
  8745. -->
  8746. (I3 ^dir R +)
  8747. inner elaboration loop at bottom goal.
  8748. Retracting elaborate*copy-see-to-output-link
  8749. -->
  8750. (I3 ^see 0 +)
  8751. Retracting propose*predict-no
  8752. -->
  8753. (O1926 ^name predict-no +)
  8754. (S1 ^operator O1926 +)
  8755. Retracting propose*predict-yes
  8756. -->
  8757. (O1925 ^name predict-yes +)
  8758. (S1 ^operator O1925 +)
  8759. Retracting elaborate*reward*based*on*reward
  8760. -->
  8761. (R966 ^value 1 +)
  8762. (R1 ^reward R966 +)
  8763. Retracting elaborate*copy-dir-to-output-link
  8764. -->
  8765. (I3 ^dir R +)
  8766. Retracting rl*prefer*rvt*predict-no*H0*4
  8767. -->
  8768. (S1 ^operator O1926 = 0.4476188714061859)
  8769. Retracting rl*prefer*rvt*predict-no*H0*4*v1*H1*33
  8770. -->
  8771. (S1 ^operator O1926 = -0.00558448899823713)
  8772. Retracting rl*prefer*rvt*predict-yes*H0*3
  8773. -->
  8774. (S1 ^operator O1925 = 0.1844091198562935)
  8775. Retracting rl*prefer*rvt*predict-yes*H0*3*v1*H1*34
  8776. -->
  8777. (S1 ^operator O1925 = 0.8155971820726273)
  8778. =>WM: (13506: S1 ^operator O1928 +)
  8779. =>WM: (13505: S1 ^operator O1927 +)
  8780. =>WM: (13504: O1928 ^name predict-no)
  8781. =>WM: (13503: O1927 ^name predict-yes)
  8782. =>WM: (13502: R967 ^value 1)
  8783. =>WM: (13501: R1 ^reward R967)
  8784. =>WM: (13500: I3 ^see 1)
  8785. <=WM: (13491: S1 ^operator O1925 +)
  8786. <=WM: (13493: S1 ^operator O1925)
  8787. <=WM: (13492: S1 ^operator O1926 +)
  8788. <=WM: (13486: R1 ^reward R966)
  8789. <=WM: (13471: I3 ^see 0)
  8790. <=WM: (13489: O1926 ^name predict-no)
  8791. <=WM: (13488: O1925 ^name predict-yes)
  8792. <=WM: (13487: R966 ^value 1)
  8793. --- Inner Elaboration Phase, active level 1 (S1) ---
  8794. Firing prefer*rvt*predict-yes*H0
  8795. -->
  8796. Firing rl*prefer*rvt*predict-yes*H0*3
  8797. -->
  8798. (S1 ^operator O1927 = 0.1844091198562935)
  8799. Firing prefer*rvt*predict-yes*H0*3*v1*H1
  8800. -->
  8801. Firing rl*prefer*rvt*predict-yes*H0*3*v1*H1*40
  8802. -->
  8803. (S1 ^operator O1927 = 0.1398795999120246)
  8804. Firing prefer*rvt*predict-no*H0
  8805. -->
  8806. Firing rl*prefer*rvt*predict-no*H0*4
  8807. -->
  8808. (S1 ^operator O1928 = 0.4476188714061859)
  8809. Firing prefer*rvt*predict-no*H0*4*v1*H1
  8810. -->
  8811. Firing rl*prefer*rvt*predict-no*H0*4*v1*H1*39
  8812. -->
  8813. (S1 ^operator O1928 = 0.5523829775838558)
  8814. inner elaboration loop at bottom goal.
  8815. Retracting rl*prefer*rvt*predict-no*H0*4
  8816. -->
  8817. (S1 ^operator O1926 = 0.4476188714061859)
  8818. Retracting rl*prefer*rvt*predict-no*H0*4*v1*H1*39
  8819. -->
  8820. (S1 ^operator O1926 = 0.5523829775838558)
  8821. Retracting rl*prefer*rvt*predict-yes*H0*3
  8822. -->
  8823. (S1 ^operator O1925 = 0.1844091198562935)
  8824. Retracting rl*prefer*rvt*predict-yes*H0*3*v1*H1*40
  8825. -->
  8826. (S1 ^operator O1925 = 0.1398795999120246)
  8827. --- END Proposal Phase ---
  8828. --- Decision Phase ---
  8829. RL update rl*prefer*rvt*predict-yes*H0*3 0.675411 -0.491002 0.184409 -> 0.67541 -0.491002 0.184408(R,m,v=1,0.895706,0.0939938)
  8830. RL update rl*prefer*rvt*predict-yes*H0*3*v1*H1*34 0.324597 0.491 0.815597 -> 0.324596 0.491 0.815596(R,m,v=1,1,0)
  8831. =>WM: (13507: S1 ^operator O1928)
  8832. 964: O: O1928 (predict-no)
  8833. --- END Decision Phase ---
  8834. --- Application Phase ---
  8835. --- Firing Productions (PE) For State At Depth 1 ---
  8836. --- Inner Elaboration Phase, active level 1 (S1) ---
  8837. Firing apply*operator
  8838. -->
  8839. (I3 ^predict-no N964 + :O )
  8840. Firing apply*operator*complete
  8841. -->
  8842. (I3 ^predict-yes N963 - :O )
  8843. inner elaboration loop at bottom goal.
  8844. --- Change Working Memory (PE) ---
  8845. =>WM: (13508: I3 ^predict-no N964)
  8846. <=WM: (13495: N963 ^status complete)
  8847. <=WM: (13494: I3 ^predict-yes N963)
  8848. --- Firing Productions (IE) For State At Depth 1 ---
  8849. --- Inner Elaboration Phase, active level 1 (S1) ---
  8850. Firing monitor*world
  8851. -->
  8852. I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
  8853. --- Change Working Memory (IE) ---
  8854. --- END Application Phase ---
  8855. --- Output Phase ---
  8856. ENV: Agent did: predict-no for direction R in state State-B
  8857. In State-B moving R
  8858. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  8859. predict error 0
  8860. dir: dir isL
  8861. --- END Output Phase ---
  8862. -/|--- Input Phase ---
  8863. =>WM: (13512: I2 ^dir L)
  8864. =>WM: (13511: I2 ^reward 1)
  8865. =>WM: (13510: I2 ^see 0)
  8866. =>WM: (13509: N964 ^status complete)
  8867. <=WM: (13498: I2 ^dir R)
  8868. <=WM: (13497: I2 ^reward 1)
  8869. <=WM: (13496: I2 ^see 1)
  8870. =>WM: (13513: I2 ^level-1 R0-root)
  8871. <=WM: (13499: I2 ^level-1 R1-root)
  8872. --- END Input Phase ---
  8873. --- Proposal Phase ---
  8874. --- Inner Elaboration Phase, active level 1 (S1) ---
  8875. Firing rl*prefer*rvt*predict-yes*H0*1*v1*H1*44
  8876. -->
  8877. (S1 ^operator O1927 = 0.6104618767696252)
  8878. Firing rl*prefer*rvt*predict-no*H0*2*v1*H1*43
  8879. -->
  8880. (S1 ^operator O1928 = 0.1063475139796038)
  8881. Firing prefer*rvt*predict-no*H0*2*v1*H1
  8882. -->
  8883. Firing prefer*rvt*predict-yes*H0*1*v1*H1
  8884. -->
  8885. Firing elaborate*copy-see-to-output-link
  8886. -->
  8887. (I3 ^see 0 +)
  8888. Firing elaborate*reward*based*on*reward
  8889. -->
  8890. (R968 ^value 1 +)
  8891. (R1 ^reward R968 +)
  8892. Firing propose*predict-yes
  8893. -->
  8894. (O1929 ^name predict-yes +)
  8895. (S1 ^operator O1929 +)
  8896. Firing propose*predict-no
  8897. -->
  8898. (O1930 ^name predict-no +)
  8899. (S1 ^operator O1930 +)
  8900. Firing rl*prefer*rvt*predict-no*H0*2
  8901. -->
  8902. (S1 ^operator O1928 = 0.3873368130731955)
  8903. Firing rl*prefer*rvt*predict-yes*H0*1
  8904. -->
  8905. (S1 ^operator O1927 = 0.3895397539597428)
  8906. Firing prefer*rvt*predict-yes*H0
  8907. -->
  8908. Firing prefer*rvt*predict-no*H0
  8909. -->
  8910. Firing elaborate*copy-dir-to-output-link
  8911. -->
  8912. (I3 ^dir L +)
  8913. inner elaboration loop at bottom goal.
  8914. Retracting elaborate*copy-see-to-output-link
  8915. -->
  8916. (I3 ^see 1 +)
  8917. Retracting propose*predict-no
  8918. -->
  8919. (O1928 ^name predict-no +)
  8920. (S1 ^operator O1928 +)
  8921. Retracting propose*predict-yes
  8922. -->
  8923. (O1927 ^name predict-yes +)
  8924. (S1 ^operator O1927 +)
  8925. Retracting elaborate*reward*based*on*reward
  8926. -->
  8927. (R967 ^value 1 +)
  8928. (R1 ^reward R967 +)
  8929. Retracting elaborate*copy-dir-to-output-link
  8930. -->
  8931. (I3 ^dir R +)
  8932. Retracting rl*prefer*rvt*predict-no*H0*4*v1*H1*39
  8933. -->
  8934. (S1 ^operator O1928 = 0.5523829775838558)
  8935. Retracting rl*prefer*rvt*predict-no*H0*4
  8936. -->
  8937. (S1 ^operator O1928 = 0.4476188714061859)
  8938. Retracting rl*prefer*rvt*predict-yes*H0*3*v1*H1*40
  8939. -->
  8940. (S1 ^operator O1927 = 0.1398795999120246)
  8941. Retracting rl*prefer*rvt*predict-yes*H0*3
  8942. -->
  8943. (S1 ^operator O1927 = 0.1844081745669553)
  8944. =>WM: (13521: S1 ^operator O1930 +)
  8945. =>WM: (13520: S1 ^operator O1929 +)
  8946. =>WM: (13519: I3 ^dir L)
  8947. =>WM: (13518: O1930 ^name predict-no)
  8948. =>WM: (13517: O1929 ^name predict-yes)
  8949. =>WM: (13516: R968 ^value 1)
  8950. =>WM: (13515: R1 ^reward R968)
  8951. =>WM: (13514: I3 ^see 0)
  8952. <=WM: (13505: S1 ^operator O1927 +)
  8953. <=WM: (13506: S1 ^operator O1928 +)
  8954. <=WM: (13507: S1 ^operator O1928)
  8955. <=WM: (13490: I3 ^dir R)
  8956. <=WM: (13501: R1 ^reward R967)
  8957. <=WM: (13500: I3 ^see 1)
  8958. <=WM: (13504: O1928 ^name predict-no)
  8959. <=WM: (13503: O1927 ^name predict-yes)
  8960. <=WM: (13502: R967 ^value 1)
  8961. --- Inner Elaboration Phase, active level 1 (S1) ---
  8962. Firing prefer*rvt*predict-yes*H0
  8963. -->
  8964. Firing rl*prefer*rvt*predict-yes*H0*1
  8965. -->
  8966. (S1 ^operator O1929 = 0.3895397539597428)
  8967. Firing prefer*rvt*predict-yes*H0*1*v1*H1
  8968. -->
  8969. Firing rl*prefer*rvt*predict-yes*H0*1*v1*H1*44
  8970. -->
  8971. (S1 ^operator O1929 = 0.6104618767696252)
  8972. Firing prefer*rvt*predict-no*H0
  8973. -->
  8974. Firing rl*prefer*rvt*predict-no*H0*2
  8975. -->
  8976. (S1 ^operator O1930 = 0.3873368130731955)
  8977. Firing prefer*rvt*predict-no*H0*2*v1*H1
  8978. -->
  8979. Firing rl*prefer*rvt*predict-no*H0*2*v1*H1*43
  8980. -->
  8981. (S1 ^operator O1930 = 0.1063475139796038)
  8982. inner elaboration loop at bottom goal.
  8983. Retracting rl*prefer*rvt*predict-no*H0*2
  8984. -->
  8985. (S1 ^operator O1928 = 0.3873368130731955)
  8986. Retracting rl*prefer*rvt*predict-no*H0*2*v1*H1*43
  8987. -->
  8988. (S1 ^operator O1928 = 0.1063475139796038)
  8989. Retracting rl*prefer*rvt*predict-yes*H0*1
  8990. -->
  8991. (S1 ^operator O1927 = 0.3895397539597428)
  8992. Retracting rl*prefer*rvt*predict-yes*H0*1*v1*H1*44
  8993. -->
  8994. (S1 ^operator O1927 = 0.6104618767696252)
  8995. --- END Proposal Phase ---
  8996. --- Decision Phase ---
  8997. RL update rl*prefer*rvt*predict-no*H0*4 0.622532 -0.174914 0.447619 -> 0.622532 -0.174914 0.447619(R,m,v=1,0.92562,0.0694215)
  8998. RL update rl*prefer*rvt*predict-no*H0*4*v1*H1*39 0.377469 0.174914 0.552383 -> 0.377469 0.174914 0.552383(R,m,v=1,1,0)
  8999. =>WM: (13522: S1 ^operator O1929)
  9000. 965: O: O1929 (predict-yes)
  9001. --- END Decision Phase ---
  9002. --- Application Phase ---
  9003. --- Firing Productions (PE) For State At Depth 1 ---
  9004. --- Inner Elaboration Phase, active level 1 (S1) ---
  9005. Firing apply*operator
  9006. -->
  9007. (I3 ^predict-yes N965 + :O )
  9008. Firing apply*operator*complete
  9009. -->
  9010. (I3 ^predict-no N964 - :O )
  9011. inner elaboration loop at bottom goal.
  9012. --- Change Working Memory (PE) ---
  9013. =>WM: (13523: I3 ^predict-yes N965)
  9014. <=WM: (13509: N964 ^status complete)
  9015. <=WM: (13508: I3 ^predict-no N964)
  9016. --- Firing Productions (IE) For State At Depth 1 ---
  9017. --- Inner Elaboration Phase, active level 1 (S1) ---
  9018. Firing monitor*world
  9019. -->
  9020. I see 1 and I'm going to do: predict-yes inner elaboration loop at bottom goal.
  9021. --- Change Working Memory (IE) ---
  9022. --- END Application Phase ---
  9023. --- Output Phase ---
  9024. ENV: Agent did: predict-yes for direction L in state State-B
  9025. In State-B moving L
  9026. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  9027. predict error 0
  9028. dir: dir isL
  9029. --- END Output Phase ---
  9030. \---- Input Phase ---
  9031. =>WM: (13527: I2 ^dir L)
  9032. =>WM: (13526: I2 ^reward 1)
  9033. =>WM: (13525: I2 ^see 1)
  9034. =>WM: (13524: N965 ^status complete)
  9035. <=WM: (13512: I2 ^dir L)
  9036. <=WM: (13511: I2 ^reward 1)
  9037. <=WM: (13510: I2 ^see 0)
  9038. =>WM: (13528: I2 ^level-1 L1-root)
  9039. <=WM: (13513: I2 ^level-1 R0-root)
  9040. --- END Input Phase ---
  9041. --- Proposal Phase ---
  9042. --- Inner Elaboration Phase, active level 1 (S1) ---
  9043. Firing rl*prefer*rvt*predict-no*H0*2*v1*H1*32
  9044. -->
  9045. (S1 ^operator O1930 = 0.6126625979784875)
  9046. Firing rl*prefer*rvt*predict-yes*H0*1*v1*H1*31
  9047. -->
  9048. (S1 ^operator O1929 = -0.02274740735326741)
  9049. Firing prefer*rvt*predict-no*H0*2*v1*H1
  9050. -->
  9051. Firing prefer*rvt*predict-yes*H0*1*v1*H1
  9052. -->
  9053. Firing elaborate*copy-see-to-output-link
  9054. -->
  9055. (I3 ^see 1 +)
  9056. Firing elaborate*reward*based*on*reward
  9057. -->
  9058. (R969 ^value 1 +)
  9059. (R1 ^reward R969 +)
  9060. Firing propose*predict-yes
  9061. -->
  9062. (O1931 ^name predict-yes +)
  9063. (S1 ^operator O1931 +)
  9064. Firing propose*predict-no
  9065. -->
  9066. (O1932 ^name predict-no +)
  9067. (S1 ^operator O1932 +)
  9068. Firing rl*prefer*rvt*predict-no*H0*2
  9069. -->
  9070. (S1 ^operator O1930 = 0.3873368130731955)
  9071. Firing rl*prefer*rvt*predict-yes*H0*1
  9072. -->
  9073. (S1 ^operator O1929 = 0.3895397539597428)
  9074. Firing prefer*rvt*predict-yes*H0
  9075. -->
  9076. Firing prefer*rvt*predict-no*H0
  9077. -->
  9078. Firing elaborate*copy-dir-to-output-link
  9079. -->
  9080. (I3 ^dir L +)
  9081. inner elaboration loop at bottom goal.
  9082. Retracting elaborate*copy-see-to-output-link
  9083. -->
  9084. (I3 ^see 0 +)
  9085. Retracting propose*predict-no
  9086. -->
  9087. (O1930 ^name predict-no +)
  9088. (S1 ^operator O1930 +)
  9089. Retracting propose*predict-yes
  9090. -->
  9091. (O1929 ^name predict-yes +)
  9092. (S1 ^operator O1929 +)
  9093. Retracting elaborate*reward*based*on*reward
  9094. -->
  9095. (R968 ^value 1 +)
  9096. (R1 ^reward R968 +)
  9097. Retracting elaborate*copy-dir-to-output-link
  9098. -->
  9099. (I3 ^dir L +)
  9100. Retracting rl*prefer*rvt*predict-no*H0*2*v1*H1*43
  9101. -->
  9102. (S1 ^operator O1930 = 0.1063475139796038)
  9103. Retracting rl*prefer*rvt*predict-no*H0*2
  9104. -->
  9105. (S1 ^operator O1930 = 0.3873368130731955)
  9106. Retracting rl*prefer*rvt*predict-yes*H0*1*v1*H1*44
  9107. -->
  9108. (S1 ^operator O1929 = 0.6104618767696252)
  9109. Retracting rl*prefer*rvt*predict-yes*H0*1
  9110. -->
  9111. (S1 ^operator O1929 = 0.3895397539597428)
  9112. =>WM: (13535: S1 ^operator O1932 +)
  9113. =>WM: (13534: S1 ^operator O1931 +)
  9114. =>WM: (13533: O1932 ^name predict-no)
  9115. =>WM: (13532: O1931 ^name predict-yes)
  9116. =>WM: (13531: R969 ^value 1)
  9117. =>WM: (13530: R1 ^reward R969)
  9118. =>WM: (13529: I3 ^see 1)
  9119. <=WM: (13520: S1 ^operator O1929 +)
  9120. <=WM: (13522: S1 ^operator O1929)
  9121. <=WM: (13521: S1 ^operator O1930 +)
  9122. <=WM: (13515: R1 ^reward R968)
  9123. <=WM: (13514: I3 ^see 0)
  9124. <=WM: (13518: O1930 ^name predict-no)
  9125. <=WM: (13517: O1929 ^name predict-yes)
  9126. <=WM: (13516: R968 ^value 1)
  9127. --- Inner Elaboration Phase, active level 1 (S1) ---
  9128. Firing prefer*rvt*predict-yes*H0
  9129. -->
  9130. Firing rl*prefer*rvt*predict-yes*H0*1
  9131. -->
  9132. (S1 ^operator O1931 = 0.3895397539597428)
  9133. Firing prefer*rvt*predict-yes*H0*1*v1*H1
  9134. -->
  9135. Firing rl*prefer*rvt*predict-yes*H0*1*v1*H1*31
  9136. -->
  9137. (S1 ^operator O1931 = -0.02274740735326741)
  9138. Firing prefer*rvt*predict-no*H0
  9139. -->
  9140. Firing rl*prefer*rvt*predict-no*H0*2
  9141. -->
  9142. (S1 ^operator O1932 = 0.3873368130731955)
  9143. Firing prefer*rvt*predict-no*H0*2*v1*H1
  9144. -->
  9145. Firing rl*prefer*rvt*predict-no*H0*2*v1*H1*32
  9146. -->
  9147. (S1 ^operator O1932 = 0.6126625979784875)
  9148. inner elaboration loop at bottom goal.
  9149. Retracting rl*prefer*rvt*predict-no*H0*2
  9150. -->
  9151. (S1 ^operator O1930 = 0.3873368130731955)
  9152. Retracting rl*prefer*rvt*predict-no*H0*2*v1*H1*32
  9153. -->
  9154. (S1 ^operator O1930 = 0.6126625979784875)
  9155. Retracting rl*prefer*rvt*predict-yes*H0*1
  9156. -->
  9157. (S1 ^operator O1929 = 0.3895397539597428)
  9158. Retracting rl*prefer*rvt*predict-yes*H0*1*v1*H1*31
  9159. -->
  9160. (S1 ^operator O1929 = -0.02274740735326741)
  9161. --- END Proposal Phase ---
  9162. --- Decision Phase ---
  9163. RL update rl*prefer*rvt*predict-yes*H0*1 0.711951 -0.322412 0.38954 -> 0.711951 -0.322412 0.38954(R,m,v=1,0.888199,0.0999224)
  9164. RL update rl*prefer*rvt*predict-yes*H0*1*v1*H1*44 0.288049 0.322413 0.610462 -> 0.288049 0.322413 0.610462(R,m,v=1,1,0)
  9165. =>WM: (13536: S1 ^operator O1932)
  9166. 966: O: O1932 (predict-no)
  9167. --- END Decision Phase ---
  9168. --- Application Phase ---
  9169. --- Firing Productions (PE) For State At Depth 1 ---
  9170. --- Inner Elaboration Phase, active level 1 (S1) ---
  9171. Firing apply*operator
  9172. -->
  9173. (I3 ^predict-no N966 + :O )
  9174. Firing apply*operator*complete
  9175. -->
  9176. (I3 ^predict-yes N965 - :O )
  9177. inner elaboration loop at bottom goal.
  9178. --- Change Working Memory (PE) ---
  9179. =>WM: (13537: I3 ^predict-no N966)
  9180. <=WM: (13524: N965 ^status complete)
  9181. <=WM: (13523: I3 ^predict-yes N965)
  9182. --- Firing Productions (IE) For State At Depth 1 ---
  9183. --- Inner Elaboration Phase, active level 1 (S1) ---
  9184. Firing monitor*world
  9185. -->
  9186. I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
  9187. --- Change Working Memory (IE) ---
  9188. --- END Application Phase ---
  9189. --- Output Phase ---
  9190. ENV: Agent did: predict-no for direction L in state State-A
  9191. In State-A moving L
  9192. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  9193. predict error 0
  9194. dir: dir isR
  9195. --- END Output Phase ---
  9196. /|\--- Input Phase ---
  9197. =>WM: (13541: I2 ^dir R)
  9198. =>WM: (13540: I2 ^reward 1)
  9199. =>WM: (13539: I2 ^see 0)
  9200. =>WM: (13538: N966 ^status complete)
  9201. <=WM: (13527: I2 ^dir L)
  9202. <=WM: (13526: I2 ^reward 1)
  9203. <=WM: (13525: I2 ^see 1)
  9204. =>WM: (13542: I2 ^level-1 L0-root)
  9205. <=WM: (13528: I2 ^level-1 L1-root)
  9206. --- END Input Phase ---
  9207. --- Proposal Phase ---
  9208. --- Inner Elaboration Phase, active level 1 (S1) ---
  9209. Firing rl*prefer*rvt*predict-yes*H0*3*v1*H1*34
  9210. -->
  9211. (S1 ^operator O1931 = 0.8155962367832892)
  9212. Firing rl*prefer*rvt*predict-no*H0*4*v1*H1*33
  9213. -->
  9214. (S1 ^operator O1932 = -0.00558448899823713)
  9215. Firing prefer*rvt*predict-no*H0*4*v1*H1
  9216. -->
  9217. Firing prefer*rvt*predict-yes*H0*3*v1*H1
  9218. -->
  9219. Firing elaborate*copy-see-to-output-link
  9220. -->
  9221. (I3 ^see 0 +)
  9222. Firing elaborate*reward*based*on*reward
  9223. -->
  9224. (R970 ^value 1 +)
  9225. (R1 ^reward R970 +)
  9226. Firing propose*predict-yes
  9227. -->
  9228. (O1933 ^name predict-yes +)
  9229. (S1 ^operator O1933 +)
  9230. Firing propose*predict-no
  9231. -->
  9232. (O1934 ^name predict-no +)
  9233. (S1 ^operator O1934 +)
  9234. Firing rl*prefer*rvt*predict-no*H0*4
  9235. -->
  9236. (S1 ^operator O1932 = 0.4476185940576797)
  9237. Firing rl*prefer*rvt*predict-yes*H0*3
  9238. -->
  9239. (S1 ^operator O1931 = 0.1844081745669553)
  9240. Firing prefer*rvt*predict-yes*H0
  9241. -->
  9242. Firing prefer*rvt*predict-no*H0
  9243. -->
  9244. Firing elaborate*copy-dir-to-output-link
  9245. -->
  9246. (I3 ^dir R +)
  9247. inner elaboration loop at bottom goal.
  9248. Retracting elaborate*copy-see-to-output-link
  9249. -->
  9250. (I3 ^see 1 +)
  9251. Retracting propose*predict-no
  9252. -->
  9253. (O1932 ^name predict-no +)
  9254. (S1 ^operator O1932 +)
  9255. Retracting propose*predict-yes
  9256. -->
  9257. (O1931 ^name predict-yes +)
  9258. (S1 ^operator O1931 +)
  9259. Retracting elaborate*reward*based*on*reward
  9260. -->
  9261. (R969 ^value 1 +)
  9262. (R1 ^reward R969 +)
  9263. Retracting elaborate*copy-dir-to-output-link
  9264. -->
  9265. (I3 ^dir L +)
  9266. Retracting rl*prefer*rvt*predict-no*H0*2*v1*H1*32
  9267. -->
  9268. (S1 ^operator O1932 = 0.6126625979784875)
  9269. Retracting rl*prefer*rvt*predict-no*H0*2
  9270. -->
  9271. (S1 ^operator O1932 = 0.3873368130731955)
  9272. Retracting rl*prefer*rvt*predict-yes*H0*1*v1*H1*31
  9273. -->
  9274. (S1 ^operator O1931 = -0.02274740735326741)
  9275. Retracting rl*prefer*rvt*predict-yes*H0*1
  9276. -->
  9277. (S1 ^operator O1931 = 0.3895395093503376)
  9278. =>WM: (13550: S1 ^operator O1934 +)
  9279. =>WM: (13549: S1 ^operator O1933 +)
  9280. =>WM: (13548: I3 ^dir R)
  9281. =>WM: (13547: O1934 ^name predict-no)
  9282. =>WM: (13546: O1933 ^name predict-yes)
  9283. =>WM: (13545: R970 ^value 1)
  9284. =>WM: (13544: R1 ^reward R970)
  9285. =>WM: (13543: I3 ^see 0)
  9286. <=WM: (13534: S1 ^operator O1931 +)
  9287. <=WM: (13535: S1 ^operator O1932 +)
  9288. <=WM: (13536: S1 ^operator O1932)
  9289. <=WM: (13519: I3 ^dir L)
  9290. <=WM: (13530: R1 ^reward R969)
  9291. <=WM: (13529: I3 ^see 1)
  9292. <=WM: (13533: O1932 ^name predict-no)
  9293. <=WM: (13532: O1931 ^name predict-yes)
  9294. <=WM: (13531: R969 ^value 1)
  9295. --- Inner Elaboration Phase, active level 1 (S1) ---
  9296. Firing prefer*rvt*predict-yes*H0
  9297. -->
  9298. Firing rl*prefer*rvt*predict-yes*H0*3
  9299. -->
  9300. (S1 ^operator O1933 = 0.1844081745669553)
  9301. Firing prefer*rvt*predict-yes*H0*3*v1*H1
  9302. -->
  9303. Firing rl*prefer*rvt*predict-yes*H0*3*v1*H1*34
  9304. -->
  9305. (S1 ^operator O1933 = 0.8155962367832892)
  9306. Firing prefer*rvt*predict-no*H0
  9307. -->
  9308. Firing rl*prefer*rvt*predict-no*H0*4
  9309. -->
  9310. (S1 ^operator O1934 = 0.4476185940576797)
  9311. Firing prefer*rvt*predict-no*H0*4*v1*H1
  9312. -->
  9313. Firing rl*prefer*rvt*predict-no*H0*4*v1*H1*33
  9314. -->
  9315. (S1 ^operator O1934 = -0.00558448899823713)
  9316. inner elaboration loop at bottom goal.
  9317. Retracting rl*prefer*rvt*predict-no*H0*4
  9318. -->
  9319. (S1 ^operator O1932 = 0.4476185940576797)
  9320. Retracting rl*prefer*rvt*predict-no*H0*4*v1*H1*33
  9321. -->
  9322. (S1 ^operator O1932 = -0.00558448899823713)
  9323. Retracting rl*prefer*rvt*predict-yes*H0*3
  9324. -->
  9325. (S1 ^operator O1931 = 0.1844081745669553)
  9326. Retracting rl*prefer*rvt*predict-yes*H0*3*v1*H1*34
  9327. -->
  9328. (S1 ^operator O1931 = 0.8155962367832892)
  9329. --- END Proposal Phase ---
  9330. --- Decision Phase ---
  9331. RL update rl*prefer*rvt*predict-no*H0*2 0.719081 -0.331744 0.387337 -> 0.719081 -0.331744 0.387337(R,m,v=1,0.931034,0.0645804)
  9332. RL update rl*prefer*rvt*predict-no*H0*2*v1*H1*32 0.280918 0.331744 0.612663 -> 0.280919 0.331744 0.612663(R,m,v=1,1,0)
  9333. =>WM: (13551: S1 ^operator O1933)
  9334. 967: O: O1933 (predict-yes)
  9335. --- END Decision Phase ---
  9336. --- Application Phase ---
  9337. --- Firing Productions (PE) For State At Depth 1 ---
  9338. --- Inner Elaboration Phase, active level 1 (S1) ---
  9339. Firing apply*operator
  9340. -->
  9341. (I3 ^predict-yes N967 + :O )
  9342. Firing apply*operator*complete
  9343. -->
  9344. (I3 ^predict-no N966 - :O )
  9345. inner elaboration loop at bottom goal.
  9346. --- Change Working Memory (PE) ---
  9347. =>WM: (13552: I3 ^predict-yes N967)
  9348. <=WM: (13538: N966 ^status complete)
  9349. <=WM: (13537: I3 ^predict-no N966)
  9350. --- Firing Productions (IE) For State At Depth 1 ---
  9351. --- Inner Elaboration Phase, active level 1 (S1) ---
  9352. Firing monitor*world
  9353. -->
  9354. I see 1 and I'm going to do: predict-yes inner elaboration loop at bottom goal.
  9355. --- Change Working Memory (IE) ---
  9356. --- END Application Phase ---
  9357. --- Output Phase ---
  9358. ENV: Agent did: predict-yes for direction R in state State-A
  9359. In State-A moving R
  9360. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  9361. predict error 0
  9362. dir: dir isR
  9363. --- END Output Phase ---
  9364. -/|--- Input Phase ---
  9365. =>WM: (13556: I2 ^dir R)
  9366. =>WM: (13555: I2 ^reward 1)
  9367. =>WM: (13554: I2 ^see 1)
  9368. =>WM: (13553: N967 ^status complete)
  9369. <=WM: (13541: I2 ^dir R)
  9370. <=WM: (13540: I2 ^reward 1)
  9371. <=WM: (13539: I2 ^see 0)
  9372. =>WM: (13557: I2 ^level-1 R1-root)
  9373. <=WM: (13542: I2 ^level-1 L0-root)
  9374. --- END Input Phase ---
  9375. --- Proposal Phase ---
  9376. --- Inner Elaboration Phase, active level 1 (S1) ---
  9377. Firing rl*prefer*rvt*predict-yes*H0*3*v1*H1*40
  9378. -->
  9379. (S1 ^operator O1933 = 0.1398795999120246)
  9380. Firing rl*prefer*rvt*predict-no*H0*4*v1*H1*39
  9381. -->
  9382. (S1 ^operator O1934 = 0.5523827002353495)
  9383. Firing prefer*rvt*predict-no*H0*4*v1*H1
  9384. -->
  9385. Firing prefer*rvt*predict-yes*H0*3*v1*H1
  9386. -->
  9387. Firing elaborate*copy-see-to-output-link
  9388. -->
  9389. (I3 ^see 1 +)
  9390. Firing elaborate*reward*based*on*reward
  9391. -->
  9392. (R971 ^value 1 +)
  9393. (R1 ^reward R971 +)
  9394. Firing propose*predict-yes
  9395. -->
  9396. (O1935 ^name predict-yes +)
  9397. (S1 ^operator O1935 +)
  9398. Firing propose*predict-no
  9399. -->
  9400. (O1936 ^name predict-no +)
  9401. (S1 ^operator O1936 +)
  9402. Firing rl*prefer*rvt*predict-no*H0*4
  9403. -->
  9404. (S1 ^operator O1934 = 0.4476185940576797)
  9405. Firing rl*prefer*rvt*predict-yes*H0*3
  9406. -->
  9407. (S1 ^operator O1933 = 0.1844081745669553)
  9408. Firing prefer*rvt*predict-yes*H0
  9409. -->
  9410. Firing prefer*rvt*predict-no*H0
  9411. -->
  9412. Firing elaborate*copy-dir-to-output-link
  9413. -->
  9414. (I3 ^dir R +)
  9415. inner elaboration loop at bottom goal.
  9416. Retracting elaborate*copy-see-to-output-link
  9417. -->
  9418. (I3 ^see 0 +)
  9419. Retracting propose*predict-no
  9420. -->
  9421. (O1934 ^name predict-no +)
  9422. (S1 ^operator O1934 +)
  9423. Retracting propose*predict-yes
  9424. -->
  9425. (O1933 ^name predict-yes +)
  9426. (S1 ^operator O1933 +)
  9427. Retracting elaborate*reward*based*on*reward
  9428. -->
  9429. (R970 ^value 1 +)
  9430. (R1 ^reward R970 +)
  9431. Retracting elaborate*copy-dir-to-output-link
  9432. -->
  9433. (I3 ^dir R +)
  9434. Retracting rl*prefer*rvt*predict-no*H0*4*v1*H1*33
  9435. -->
  9436. (S1 ^operator O1934 = -0.00558448899823713)
  9437. Retracting rl*prefer*rvt*predict-no*H0*4
  9438. -->
  9439. (S1 ^operator O1934 = 0.4476185940576797)
  9440. Retracting rl*prefer*rvt*predict-yes*H0*3*v1*H1*34
  9441. -->
  9442. (S1 ^operator O1933 = 0.8155962367832892)
  9443. Retracting rl*prefer*rvt*predict-yes*H0*3
  9444. -->
  9445. (S1 ^operator O1933 = 0.1844081745669553)
  9446. =>WM: (13564: S1 ^operator O1936 +)
  9447. =>WM: (13563: S1 ^operator O1935 +)
  9448. =>WM: (13562: O1936 ^name predict-no)
  9449. =>WM: (13561: O1935 ^name predict-yes)
  9450. =>WM: (13560: R971 ^value 1)
  9451. =>WM: (13559: R1 ^reward R971)
  9452. =>WM: (13558: I3 ^see 1)
  9453. <=WM: (13549: S1 ^operator O1933 +)
  9454. <=WM: (13551: S1 ^operator O1933)
  9455. <=WM: (13550: S1 ^operator O1934 +)
  9456. <=WM: (13544: R1 ^reward R970)
  9457. <=WM: (13543: I3 ^see 0)
  9458. <=WM: (13547: O1934 ^name predict-no)
  9459. <=WM: (13546: O1933 ^name predict-yes)
  9460. <=WM: (13545: R970 ^value 1)
  9461. --- Inner Elaboration Phase, active level 1 (S1) ---
  9462. Firing prefer*rvt*predict-yes*H0
  9463. -->
  9464. Firing rl*prefer*rvt*predict-yes*H0*3
  9465. -->
  9466. (S1 ^operator O1935 = 0.1844081745669553)
  9467. Firing prefer*rvt*predict-yes*H0*3*v1*H1
  9468. -->
  9469. Firing rl*prefer*rvt*predict-yes*H0*3*v1*H1*40
  9470. -->
  9471. (S1 ^operator O1935 = 0.1398795999120246)
  9472. Firing prefer*rvt*predict-no*H0
  9473. -->
  9474. Firing rl*prefer*rvt*predict-no*H0*4
  9475. -->
  9476. (S1 ^operator O1936 = 0.4476185940576797)
  9477. Firing prefer*rvt*predict-no*H0*4*v1*H1
  9478. -->
  9479. Firing rl*prefer*rvt*predict-no*H0*4*v1*H1*39
  9480. -->
  9481. (S1 ^operator O1936 = 0.5523827002353495)
  9482. inner elaboration loop at bottom goal.
  9483. Retracting rl*prefer*rvt*predict-no*H0*4
  9484. -->
  9485. (S1 ^operator O1934 = 0.4476185940576797)
  9486. Retracting rl*prefer*rvt*predict-no*H0*4*v1*H1*39
  9487. -->
  9488. (S1 ^operator O1934 = 0.5523827002353495)
  9489. Retracting rl*prefer*rvt*predict-yes*H0*3
  9490. -->
  9491. (S1 ^operator O1933 = 0.1844081745669553)
  9492. Retracting rl*prefer*rvt*predict-yes*H0*3*v1*H1*40
  9493. -->
  9494. (S1 ^operator O1933 = 0.1398795999120246)
  9495. --- END Proposal Phase ---
  9496. --- Decision Phase ---
  9497. RL update rl*prefer*rvt*predict-yes*H0*3 0.67541 -0.491002 0.184408 -> 0.675409 -0.491002 0.184408(R,m,v=1,0.896341,0.0934835)
  9498. RL update rl*prefer*rvt*predict-yes*H0*3*v1*H1*34 0.324596 0.491 0.815596 -> 0.324595 0.491001 0.815596(R,m,v=1,1,0)
  9499. =>WM: (13565: S1 ^operator O1936)
  9500. 968: O: O1936 (predict-no)
  9501. --- END Decision Phase ---
  9502. --- Application Phase ---
  9503. --- Firing Productions (PE) For State At Depth 1 ---
  9504. --- Inner Elaboration Phase, active level 1 (S1) ---
  9505. Firing apply*operator
  9506. -->
  9507. (I3 ^predict-no N968 + :O )
  9508. Firing apply*operator*complete
  9509. -->
  9510. (I3 ^predict-yes N967 - :O )
  9511. inner elaboration loop at bottom goal.
  9512. --- Change Working Memory (PE) ---
  9513. =>WM: (13566: I3 ^predict-no N968)
  9514. <=WM: (13553: N967 ^status complete)
  9515. <=WM: (13552: I3 ^predict-yes N967)
  9516. --- Firing Productions (IE) For State At Depth 1 ---
  9517. --- Inner Elaboration Phase, active level 1 (S1) ---
  9518. Firing monitor*world
  9519. -->
  9520. I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
  9521. --- Change Working Memory (IE) ---
  9522. --- END Application Phase ---
  9523. --- Output Phase ---
  9524. ENV: Agent did: predict-no for direction R in state State-B
  9525. In State-B moving R
  9526. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  9527. predict error 0
  9528. dir: dir isU
  9529. --- END Output Phase ---
  9530. \-/--- Input Phase ---
  9531. =>WM: (13570: I2 ^dir U)
  9532. =>WM: (13569: I2 ^reward 1)
  9533. =>WM: (13568: I2 ^see 0)
  9534. =>WM: (13567: N968 ^status complete)
  9535. <=WM: (13556: I2 ^dir R)
  9536. <=WM: (13555: I2 ^reward 1)
  9537. <=WM: (13554: I2 ^see 1)
  9538. =>WM: (13571: I2 ^level-1 R0-root)
  9539. <=WM: (13557: I2 ^level-1 R1-root)
  9540. --- END Input Phase ---
  9541. --- Proposal Phase ---
  9542. --- Inner Elaboration Phase, active level 1 (S1) ---
  9543. Firing elaborate*copy-see-to-output-link
  9544. -->
  9545. (I3 ^see 0 +)
  9546. Firing elaborate*reward*based*on*reward
  9547. -->
  9548. (R972 ^value 1 +)
  9549. (R1 ^reward R972 +)
  9550. Firing propose*predict-yes
  9551. -->
  9552. (O1937 ^name predict-yes +)
  9553. (S1 ^operator O1937 +)
  9554. Firing propose*predict-no
  9555. -->
  9556. (O1938 ^name predict-no +)
  9557. (S1 ^operator O1938 +)
  9558. Firing rl*prefer*rvt*predict-no*H0*6
  9559. -->
  9560. (S1 ^operator O1936 = 0.9999999999999999)
  9561. Firing rl*prefer*rvt*predict-yes*H0*5
  9562. -->
  9563. (S1 ^operator O1935 = 0.)
  9564. Firing prefer*rvt*predict-yes*H0
  9565. -->
  9566. Firing prefer*rvt*predict-no*H0
  9567. -->
  9568. Firing elaborate*copy-dir-to-output-link
  9569. -->
  9570. (I3 ^dir U +)
  9571. inner elaboration loop at bottom goal.
  9572. Retracting elaborate*copy-see-to-output-link
  9573. -->
  9574. (I3 ^see 1 +)
  9575. Retracting propose*predict-no
  9576. -->
  9577. (O1936 ^name predict-no +)
  9578. (S1 ^operator O1936 +)
  9579. Retracting propose*predict-yes
  9580. -->
  9581. (O1935 ^name predict-yes +)
  9582. (S1 ^operator O1935 +)
  9583. Retracting elaborate*reward*based*on*reward
  9584. -->
  9585. (R971 ^value 1 +)
  9586. (R1 ^reward R971 +)
  9587. Retracting elaborate*copy-dir-to-output-link
  9588. -->
  9589. (I3 ^dir R +)
  9590. Retracting rl*prefer*rvt*predict-no*H0*4*v1*H1*39
  9591. -->
  9592. (S1 ^operator O1936 = 0.5523827002353495)
  9593. Retracting rl*prefer*rvt*predict-no*H0*4
  9594. -->
  9595. (S1 ^operator O1936 = 0.4476185940576797)
  9596. Retracting rl*prefer*rvt*predict-yes*H0*3*v1*H1*40
  9597. -->
  9598. (S1 ^operator O1935 = 0.1398795999120246)
  9599. Retracting rl*prefer*rvt*predict-yes*H0*3
  9600. -->
  9601. (S1 ^operator O1935 = 0.1844075128644186)
  9602. =>WM: (13579: S1 ^operator O1938 +)
  9603. =>WM: (13578: S1 ^operator O1937 +)
  9604. =>WM: (13577: I3 ^dir U)
  9605. =>WM: (13576: O1938 ^name predict-no)
  9606. =>WM: (13575: O1937 ^name predict-yes)
  9607. =>WM: (13574: R972 ^value 1)
  9608. =>WM: (13573: R1 ^reward R972)
  9609. =>WM: (13572: I3 ^see 0)
  9610. <=WM: (13563: S1 ^operator O1935 +)
  9611. <=WM: (13564: S1 ^operator O1936 +)
  9612. <=WM: (13565: S1 ^operator O1936)
  9613. <=WM: (13548: I3 ^dir R)
  9614. <=WM: (13559: R1 ^reward R971)
  9615. <=WM: (13558: I3 ^see 1)
  9616. <=WM: (13562: O1936 ^name predict-no)
  9617. <=WM: (13561: O1935 ^name predict-yes)
  9618. <=WM: (13560: R971 ^value 1)
  9619. --- Inner Elaboration Phase, active level 1 (S1) ---
  9620. Firing prefer*rvt*predict-yes*H0
  9621. -->
  9622. Firing rl*prefer*rvt*predict-yes*H0*5
  9623. -->
  9624. (S1 ^operator O1937 = 0.)
  9625. Firing prefer*rvt*predict-no*H0
  9626. -->
  9627. Firing rl*prefer*rvt*predict-no*H0*6
  9628. -->
  9629. (S1 ^operator O1938 = 0.9999999999999999)
  9630. inner elaboration loop at bottom goal.
  9631. Retracting rl*prefer*rvt*predict-no*H0*6
  9632. -->
  9633. (S1 ^operator O1936 = 0.9999999999999999)
  9634. Retracting rl*prefer*rvt*predict-yes*H0*5
  9635. -->
  9636. (S1 ^operator O1935 = 0.)
  9637. --- END Proposal Phase ---
  9638. --- Decision Phase ---
  9639. RL update rl*prefer*rvt*predict-no*H0*4 0.622532 -0.174914 0.447619 -> 0.622532 -0.174914 0.447618(R,m,v=1,0.92623,0.0688931)
  9640. RL update rl*prefer*rvt*predict-no*H0*4*v1*H1*39 0.377469 0.174914 0.552383 -> 0.377469 0.174914 0.552383(R,m,v=1,1,0)
  9641. =>WM: (13580: S1 ^operator O1938)
  9642. 969: O: O1938 (predict-no)
  9643. --- END Decision Phase ---
  9644. --- Application Phase ---
  9645. --- Firing Productions (PE) For State At Depth 1 ---
  9646. --- Inner Elaboration Phase, active level 1 (S1) ---
  9647. Firing apply*operator
  9648. -->
  9649. (I3 ^predict-no N969 + :O )
  9650. Firing apply*operator*complete
  9651. -->
  9652. (I3 ^predict-no N968 - :O )
  9653. inner elaboration loop at bottom goal.
  9654. --- Change Working Memory (PE) ---
  9655. =>WM: (13581: I3 ^predict-no N969)
  9656. <=WM: (13567: N968 ^status complete)
  9657. <=WM: (13566: I3 ^predict-no N968)
  9658. --- Firing Productions (IE) For State At Depth 1 ---
  9659. --- Inner Elaboration Phase, active level 1 (S1) ---
  9660. Firing monitor*world
  9661. -->
  9662. I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
  9663. --- Change Working Memory (IE) ---
  9664. --- END Application Phase ---
  9665. --- Output Phase ---
  9666. ENV: Agent did: predict-no for direction U in state State-B
  9667. In State-B moving U
  9668. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  9669. predict error 0
  9670. dir: dir isR
  9671. --- END Output Phase ---
  9672. |\---- Input Phase ---
  9673. =>WM: (13585: I2 ^dir R)
  9674. =>WM: (13584: I2 ^reward 1)
  9675. =>WM: (13583: I2 ^see 0)
  9676. =>WM: (13582: N969 ^status complete)
  9677. <=WM: (13570: I2 ^dir U)
  9678. <=WM: (13569: I2 ^reward 1)
  9679. <=WM: (13568: I2 ^see 0)
  9680. =>WM: (13586: I2 ^level-1 R0-root)
  9681. <=WM: (13571: I2 ^level-1 R0-root)
  9682. --- END Input Phase ---
  9683. --- Proposal Phase ---
  9684. --- Inner Elaboration Phase, active level 1 (S1) ---
  9685. Firing rl*prefer*rvt*predict-yes*H0*3*v1*H1*42
  9686. -->
  9687. (S1 ^operator O1937 = 0.1664311307472832)
  9688. Firing rl*prefer*rvt*predict-no*H0*4*v1*H1*41
  9689. -->
  9690. (S1 ^operator O1938 = 0.5523777234651187)
  9691. Firing prefer*rvt*predict-no*H0*4*v1*H1
  9692. -->
  9693. Firing prefer*rvt*predict-yes*H0*3*v1*H1
  9694. -->
  9695. Firing elaborate*copy-see-to-output-link
  9696. -->
  9697. (I3 ^see 0 +)
  9698. Firing elaborate*reward*based*on*reward
  9699. -->
  9700. (R973 ^value 1 +)
  9701. (R1 ^reward R973 +)
  9702. Firing propose*predict-yes
  9703. -->
  9704. (O1939 ^name predict-yes +)
  9705. (S1 ^operator O1939 +)
  9706. Firing propose*predict-no
  9707. -->
  9708. (O1940 ^name predict-no +)
  9709. (S1 ^operator O1940 +)
  9710. Firing rl*prefer*rvt*predict-no*H0*4
  9711. -->
  9712. (S1 ^operator O1938 = 0.4476183999137253)
  9713. Firing rl*prefer*rvt*predict-yes*H0*3
  9714. -->
  9715. (S1 ^operator O1937 = 0.1844075128644186)
  9716. Firing prefer*rvt*predict-yes*H0
  9717. -->
  9718. Firing prefer*rvt*predict-no*H0
  9719. -->
  9720. Firing elaborate*copy-dir-to-output-link
  9721. -->
  9722. (I3 ^dir R +)
  9723. inner elaboration loop at bottom goal.
  9724. Retracting elaborate*copy-see-to-output-link
  9725. -->
  9726. (I3 ^see 0 +)
  9727. Retracting propose*predict-no
  9728. -->
  9729. (O1938 ^name predict-no +)
  9730. (S1 ^operator O1938 +)
  9731. Retracting propose*predict-yes
  9732. -->
  9733. (O1937 ^name predict-yes +)
  9734. (S1 ^operator O1937 +)
  9735. Retracting elaborate*reward*based*on*reward
  9736. -->
  9737. (R972 ^value 1 +)
  9738. (R1 ^reward R972 +)
  9739. Retracting elaborate*copy-dir-to-output-link
  9740. -->
  9741. (I3 ^dir U +)
  9742. Retracting rl*prefer*rvt*predict-no*H0*6
  9743. -->
  9744. (S1 ^operator O1938 = 0.9999999999999999)
  9745. Retracting rl*prefer*rvt*predict-yes*H0*5
  9746. -->
  9747. (S1 ^operator O1937 = 0.)
  9748. =>WM: (13593: S1 ^operator O1940 +)
  9749. =>WM: (13592: S1 ^operator O1939 +)
  9750. =>WM: (13591: I3 ^dir R)
  9751. =>WM: (13590: O1940 ^name predict-no)
  9752. =>WM: (13589: O1939 ^name predict-yes)
  9753. =>WM: (13588: R973 ^value 1)
  9754. =>WM: (13587: R1 ^reward R973)
  9755. <=WM: (13578: S1 ^operator O1937 +)
  9756. <=WM: (13579: S1 ^operator O1938 +)
  9757. <=WM: (13580: S1 ^operator O1938)
  9758. <=WM: (13577: I3 ^dir U)
  9759. <=WM: (13573: R1 ^reward R972)
  9760. <=WM: (13576: O1938 ^name predict-no)
  9761. <=WM: (13575: O1937 ^name predict-yes)
  9762. <=WM: (13574: R972 ^value 1)
  9763. --- Inner Elaboration Phase, active level 1 (S1) ---
  9764. Firing prefer*rvt*predict-yes*H0
  9765. -->
  9766. Firing rl*prefer*rvt*predict-yes*H0*3*v1*H1*42
  9767. -->
  9768. (S1 ^operator O1939 = 0.1664311307472832)
  9769. Firing rl*prefer*rvt*predict-yes*H0*3
  9770. -->
  9771. (S1 ^operator O1939 = 0.1844075128644186)
  9772. Firing prefer*rvt*predict-yes*H0*3*v1*H1
  9773. -->
  9774. Firing prefer*rvt*predict-no*H0
  9775. -->
  9776. Firing rl*prefer*rvt*predict-no*H0*4*v1*H1*41
  9777. -->
  9778. (S1 ^operator O1940 = 0.5523777234651187)
  9779. Firing rl*prefer*rvt*predict-no*H0*4
  9780. -->
  9781. (S1 ^operator O1940 = 0.4476183999137253)
  9782. Firing prefer*rvt*predict-no*H0*4*v1*H1
  9783. -->
  9784. inner elaboration loop at bottom goal.
  9785. Retracting rl*prefer*rvt*predict-no*H0*4
  9786. -->
  9787. (S1 ^operator O1938 = 0.4476183999137253)
  9788. Retracting rl*prefer*rvt*predict-no*H0*4*v1*H1*41
  9789. -->
  9790. (S1 ^operator O1938 = 0.5523777234651187)
  9791. Retracting rl*prefer*rvt*predict-yes*H0*3
  9792. -->
  9793. (S1 ^operator O1937 = 0.1844075128644186)
  9794. Retracting rl*prefer*rvt*predict-yes*H0*3*v1*H1*42
  9795. -->
  9796. (S1 ^operator O1937 = 0.1664311307472832)
  9797. --- END Proposal Phase ---
  9798. --- Decision Phase ---
  9799. RL update rl*prefer*rvt*predict-no*H0*6 1 0 1 -> 1 0 1(R,m,v=1,1,0)
  9800. =>WM: (13594: S1 ^operator O1940)
  9801. 970: O: O1940 (predict-no)
  9802. --- END Decision Phase ---
  9803. --- Application Phase ---
  9804. --- Firing Productions (PE) For State At Depth 1 ---
  9805. --- Inner Elaboration Phase, active level 1 (S1) ---
  9806. Firing apply*operator
  9807. -->
  9808. (I3 ^predict-no N970 + :O )
  9809. Firing apply*operator*complete
  9810. -->
  9811. (I3 ^predict-no N969 - :O )
  9812. inner elaboration loop at bottom goal.
  9813. --- Change Working Memory (PE) ---
  9814. =>WM: (13595: I3 ^predict-no N970)
  9815. <=WM: (13582: N969 ^status complete)
  9816. <=WM: (13581: I3 ^predict-no N969)
  9817. --- Firing Productions (IE) For State At Depth 1 ---
  9818. --- Inner Elaboration Phase, active level 1 (S1) ---
  9819. Firing monitor*world
  9820. -->
  9821. I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
  9822. --- Change Working Memory (IE) ---
  9823. --- END Application Phase ---
  9824. --- Output Phase ---
  9825. ENV: Agent did: predict-no for direction R in state State-B
  9826. In State-B moving R
  9827. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  9828. predict error 0
  9829. dir: dir isL
  9830. --- END Output Phase ---
  9831. /|\--- Input Phase ---
  9832. =>WM: (13599: I2 ^dir L)
  9833. =>WM: (13598: I2 ^reward 1)
  9834. =>WM: (13597: I2 ^see 0)
  9835. =>WM: (13596: N970 ^status complete)
  9836. <=WM: (13585: I2 ^dir R)
  9837. <=WM: (13584: I2 ^reward 1)
  9838. <=WM: (13583: I2 ^see 0)
  9839. =>WM: (13600: I2 ^level-1 R0-root)
  9840. <=WM: (13586: I2 ^level-1 R0-root)
  9841. --- END Input Phase ---
  9842. --- Proposal Phase ---
  9843. --- Inner Elaboration Phase, active level 1 (S1) ---
  9844. Firing rl*prefer*rvt*predict-yes*H0*1*v1*H1*44
  9845. -->
  9846. (S1 ^operator O1939 = 0.61046163216022)
  9847. Firing rl*prefer*rvt*predict-no*H0*2*v1*H1*43
  9848. -->
  9849. (S1 ^operator O1940 = 0.1063475139796038)
  9850. Firing prefer*rvt*predict-no*H0*2*v1*H1
  9851. -->
  9852. Firing prefer*rvt*predict-yes*H0*1*v1*H1
  9853. -->
  9854. Firing elaborate*copy-see-to-output-link
  9855. -->
  9856. (I3 ^see 0 +)
  9857. Firing elaborate*reward*based*on*reward
  9858. -->
  9859. (R974 ^value 1 +)
  9860. (R1 ^reward R974 +)
  9861. Firing propose*predict-yes
  9862. -->
  9863. (O1941 ^name predict-yes +)
  9864. (S1 ^operator O1941 +)
  9865. Firing propose*predict-no
  9866. -->
  9867. (O1942 ^name predict-no +)
  9868. (S1 ^operator O1942 +)
  9869. Firing rl*prefer*rvt*predict-no*H0*2
  9870. -->
  9871. (S1 ^operator O1940 = 0.387336901415443)
  9872. Firing rl*prefer*rvt*predict-yes*H0*1
  9873. -->
  9874. (S1 ^operator O1939 = 0.3895395093503376)
  9875. Firing prefer*rvt*predict-yes*H0
  9876. -->
  9877. Firing prefer*rvt*predict-no*H0
  9878. -->
  9879. Firing elaborate*copy-dir-to-output-link
  9880. -->
  9881. (I3 ^dir L +)
  9882. inner elaboration loop at bottom goal.
  9883. Retracting elaborate*copy-see-to-output-link
  9884. -->
  9885. (I3 ^see 0 +)
  9886. Retracting propose*predict-no
  9887. -->
  9888. (O1940 ^name predict-no +)
  9889. (S1 ^operator O1940 +)
  9890. Retracting propose*predict-yes
  9891. -->
  9892. (O1939 ^name predict-yes +)
  9893. (S1 ^operator O1939 +)
  9894. Retracting elaborate*reward*based*on*reward
  9895. -->
  9896. (R973 ^value 1 +)
  9897. (R1 ^reward R973 +)
  9898. Retracting elaborate*copy-dir-to-output-link
  9899. -->
  9900. (I3 ^dir R +)
  9901. Retracting rl*prefer*rvt*predict-no*H0*4
  9902. -->
  9903. (S1 ^operator O1940 = 0.4476183999137253)
  9904. Retracting rl*prefer*rvt*predict-no*H0*4*v1*H1*41
  9905. -->
  9906. (S1 ^operator O1940 = 0.5523777234651187)
  9907. Retracting rl*prefer*rvt*predict-yes*H0*3
  9908. -->
  9909. (S1 ^operator O1939 = 0.1844075128644186)
  9910. Retracting rl*prefer*rvt*predict-yes*H0*3*v1*H1*42
  9911. -->
  9912. (S1 ^operator O1939 = 0.1664311307472832)
  9913. =>WM: (13607: S1 ^operator O1942 +)
  9914. =>WM: (13606: S1 ^operator O1941 +)
  9915. =>WM: (13605: I3 ^dir L)
  9916. =>WM: (13604: O1942 ^name predict-no)
  9917. =>WM: (13603: O1941 ^name predict-yes)
  9918. =>WM: (13602: R974 ^value 1)
  9919. =>WM: (13601: R1 ^reward R974)
  9920. <=WM: (13592: S1 ^operator O1939 +)
  9921. <=WM: (13593: S1 ^operator O1940 +)
  9922. <=WM: (13594: S1 ^operator O1940)
  9923. <=WM: (13591: I3 ^dir R)
  9924. <=WM: (13587: R1 ^reward R973)
  9925. <=WM: (13590: O1940 ^name predict-no)
  9926. <=WM: (13589: O1939 ^name predict-yes)
  9927. <=WM: (13588: R973 ^value 1)
  9928. --- Inner Elaboration Phase, active level 1 (S1) ---
  9929. Firing prefer*rvt*predict-yes*H0
  9930. -->
  9931. Firing rl*prefer*rvt*predict-yes*H0*1*v1*H1*44
  9932. -->
  9933. (S1 ^operator O1941 = 0.61046163216022)
  9934. Firing rl*prefer*rvt*predict-yes*H0*1
  9935. -->
  9936. (S1 ^operator O1941 = 0.3895395093503376)
  9937. Firing prefer*rvt*predict-yes*H0*1*v1*H1
  9938. -->
  9939. Firing prefer*rvt*predict-no*H0
  9940. -->
  9941. Firing rl*prefer*rvt*predict-no*H0*2*v1*H1*43
  9942. -->
  9943. (S1 ^operator O1942 = 0.1063475139796038)
  9944. Firing rl*prefer*rvt*predict-no*H0*2
  9945. -->
  9946. (S1 ^operator O1942 = 0.387336901415443)
  9947. Firing prefer*rvt*predict-no*H0*2*v1*H1
  9948. -->
  9949. inner elaboration loop at bottom goal.
  9950. Retracting rl*prefer*rvt*predict-no*H0*2
  9951. -->
  9952. (S1 ^operator O1940 = 0.387336901415443)
  9953. Retracting rl*prefer*rvt*predict-no*H0*2*v1*H1*43
  9954. -->
  9955. (S1 ^operator O1940 = 0.1063475139796038)
  9956. Retracting rl*prefer*rvt*predict-yes*H0*1
  9957. -->
  9958. (S1 ^operator O1939 = 0.3895395093503376)
  9959. Retracting rl*prefer*rvt*predict-yes*H0*1*v1*H1*44
  9960. -->
  9961. (S1 ^operator O1939 = 0.61046163216022)
  9962. --- END Proposal Phase ---
  9963. --- Decision Phase ---
  9964. RL update rl*prefer*rvt*predict-no*H0*4 0.622532 -0.174914 0.447618 -> 0.622533 -0.174914 0.447619(R,m,v=1,0.926829,0.0683727)
  9965. RL update rl*prefer*rvt*predict-no*H0*4*v1*H1*41 0.377465 0.174913 0.552378 -> 0.377465 0.174913 0.552378(R,m,v=1,1,0)
  9966. =>WM: (13608: S1 ^operator O1941)
  9967. 971: O: O1941 (predict-yes)
  9968. --- END Decision Phase ---
  9969. --- Application Phase ---
  9970. --- Firing Productions (PE) For State At Depth 1 ---
  9971. --- Inner Elaboration Phase, active level 1 (S1) ---
  9972. Firing apply*operator
  9973. -->
  9974. (I3 ^predict-yes N971 + :O )
  9975. Firing apply*operator*complete
  9976. -->
  9977. (I3 ^predict-no N970 - :O )
  9978. inner elaboration loop at bottom goal.
  9979. --- Change Working Memory (PE) ---
  9980. =>WM: (13609: I3 ^predict-yes N971)
  9981. <=WM: (13596: N970 ^status complete)
  9982. <=WM: (13595: I3 ^predict-no N970)
  9983. --- Firing Productions (IE) For State At Depth 1 ---
  9984. --- Inner Elaboration Phase, active level 1 (S1) ---
  9985. Firing monitor*world
  9986. -->
  9987. I see 1 and I'm going to do: predict-yes inner elaboration loop at bottom goal.
  9988. --- Change Working Memory (IE) ---
  9989. --- END Application Phase ---
  9990. --- Output Phase ---
  9991. ENV: Agent did: predict-yes for direction L in state State-B
  9992. In State-B moving L
  9993. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  9994. predict error 0
  9995. dir: dir isU
  9996. --- END Output Phase ---
  9997. ---- Input Phase ---
  9998. =>WM: (13613: I2 ^dir U)
  9999. =>WM: (13612: I2 ^reward 1)
  10000. =>WM: (13611: I2 ^see 1)
  10001. =>WM: (13610: N971 ^status complete)
  10002. <=WM: (13599: I2 ^dir L)
  10003. <=WM: (13598: I2 ^reward 1)
  10004. <=WM: (13597: I2 ^see 0)
  10005. =>WM: (13614: I2 ^level-1 L1-root)
  10006. <=WM: (13600: I2 ^level-1 R0-root)
  10007. --- END Input Phase ---
  10008. --- Proposal Phase ---
  10009. --- Inner Elaboration Phase, active level 1 (S1) ---
  10010. Firing elaborate*copy-see-to-output-link
  10011. -->
  10012. (I3 ^see 1 +)
  10013. Firing elaborate*reward*based*on*reward
  10014. -->
  10015. (R975 ^value 1 +)
  10016. (R1 ^reward R975 +)
  10017. Firing propose*predict-yes
  10018. -->
  10019. (O1943 ^name predict-yes +)
  10020. (S1 ^operator O1943 +)
  10021. Firing propose*predict-no
  10022. -->
  10023. (O1944 ^name predict-no +)
  10024. (S1 ^operator O1944 +)
  10025. Firing rl*prefer*rvt*predict-no*H0*6
  10026. -->
  10027. (S1 ^operator O1942 = 0.9999999999999999)
  10028. Firing rl*prefer*rvt*predict-yes*H0*5
  10029. -->
  10030. (S1 ^operator O1941 = 0.)
  10031. Firing prefer*rvt*predict-yes*H0
  10032. -->
  10033. Firing prefer*rvt*predict-no*H0
  10034. -->
  10035. Firing elaborate*copy-dir-to-output-link
  10036. -->
  10037. (I3 ^dir U +)
  10038. inner elaboration loop at bottom goal.
  10039. Retracting elaborate*copy-see-to-output-link
  10040. -->
  10041. (I3 ^see 0 +)
  10042. Retracting propose*predict-no
  10043. -->
  10044. (O1942 ^name predict-no +)
  10045. (S1 ^operator O1942 +)
  10046. Retracting propose*predict-yes
  10047. -->
  10048. (O1941 ^name predict-yes +)
  10049. (S1 ^operator O1941 +)
  10050. Retracting elaborate*reward*based*on*reward
  10051. -->
  10052. (R974 ^value 1 +)
  10053. (R1 ^reward R974 +)
  10054. Retracting elaborate*copy-dir-to-output-link
  10055. -->
  10056. (I3 ^dir L +)
  10057. Retracting rl*prefer*rvt*predict-no*H0*2
  10058. -->
  10059. (S1 ^operator O1942 = 0.387336901415443)
  10060. Retracting rl*prefer*rvt*predict-no*H0*2*v1*H1*43
  10061. -->
  10062. (S1 ^operator O1942 = 0.1063475139796038)
  10063. Retracting rl*prefer*rvt*predict-yes*H0*1
  10064. -->
  10065. (S1 ^operator O1941 = 0.3895395093503376)
  10066. Retracting rl*prefer*rvt*predict-yes*H0*1*v1*H1*44
  10067. -->
  10068. (S1 ^operator O1941 = 0.61046163216022)
  10069. =>WM: (13622: S1 ^operator O1944 +)
  10070. =>WM: (13621: S1 ^operator O1943 +)
  10071. =>WM: (13620: I3 ^dir U)
  10072. =>WM: (13619: O1944 ^name predict-no)
  10073. =>WM: (13618: O1943 ^name predict-yes)
  10074. =>WM: (13617: R975 ^value 1)
  10075. =>WM: (13616: R1 ^reward R975)
  10076. =>WM: (13615: I3 ^see 1)
  10077. <=WM: (13606: S1 ^operator O1941 +)
  10078. <=WM: (13608: S1 ^operator O1941)
  10079. <=WM: (13607: S1 ^operator O1942 +)
  10080. <=WM: (13605: I3 ^dir L)
  10081. <=WM: (13601: R1 ^reward R974)
  10082. <=WM: (13572: I3 ^see 0)
  10083. <=WM: (13604: O1942 ^name predict-no)
  10084. <=WM: (13603: O1941 ^name predict-yes)
  10085. <=WM: (13602: R974 ^value 1)
  10086. --- Inner Elaboration Phase, active level 1 (S1) ---
  10087. Firing prefer*rvt*predict-yes*H0
  10088. -->
  10089. Firing rl*prefer*rvt*predict-yes*H0*5
  10090. -->
  10091. (S1 ^operator O1943 = 0.)
  10092. Firing prefer*rvt*predict-no*H0
  10093. -->
  10094. Firing rl*prefer*rvt*predict-no*H0*6
  10095. -->
  10096. (S1 ^operator O1944 = 0.9999999999999999)
  10097. inner elaboration loop at bottom goal.
  10098. Retracting rl*prefer*rvt*predict-no*H0*6
  10099. -->
  10100. (S1 ^operator O1942 = 0.9999999999999999)
  10101. Retracting rl*prefer*rvt*predict-yes*H0*5
  10102. -->
  10103. (S1 ^operator O1941 = 0.)
  10104. --- END Proposal Phase ---
  10105. --- Decision Phase ---
  10106. RL update rl*prefer*rvt*predict-yes*H0*1 0.711951 -0.322412 0.38954 -> 0.711951 -0.322412 0.389539(R,m,v=1,0.888889,0.0993789)
  10107. RL update rl*prefer*rvt*predict-yes*H0*1*v1*H1*44 0.288049 0.322413 0.610462 -> 0.288049 0.322413 0.610461(R,m,v=1,1,0)
  10108. =>WM: (13623: S1 ^operator O1944)
  10109. 972: O: O1944 (predict-no)
  10110. --- END Decision Phase ---
  10111. --- Application Phase ---
  10112. --- Firing Productions (PE) For State At Depth 1 ---
  10113. --- Inner Elaboration Phase, active level 1 (S1) ---
  10114. Firing apply*operator
  10115. -->
  10116. (I3 ^predict-no N972 + :O )
  10117. Firing apply*operator*complete
  10118. -->
  10119. (I3 ^predict-yes N971 - :O )
  10120. inner elaboration loop at bottom goal.
  10121. --- Change Working Memory (PE) ---
  10122. =>WM: (13624: I3 ^predict-no N972)
  10123. <=WM: (13610: N971 ^status complete)
  10124. <=WM: (13609: I3 ^predict-yes N971)
  10125. --- Firing Productions (IE) For State At Depth 1 ---
  10126. --- Inner Elaboration Phase, active level 1 (S1) ---
  10127. Firing monitor*world
  10128. -->
  10129. I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
  10130. --- Change Working Memory (IE) ---
  10131. --- END Application Phase ---
  10132. --- Output Phase ---
  10133. ENV: Agent did: predict-no for direction U in state State-A
  10134. In State-A moving U
  10135. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  10136. predict error 0
  10137. dir: dir isU
  10138. --- END Output Phase ---
  10139. /|\--- Input Phase ---
  10140. =>WM: (13628: I2 ^dir U)
  10141. =>WM: (13627: I2 ^reward 1)
  10142. =>WM: (13626: I2 ^see 0)
  10143. =>WM: (13625: N972 ^status complete)
  10144. <=WM: (13613: I2 ^dir U)
  10145. <=WM: (13612: I2 ^reward 1)
  10146. <=WM: (13611: I2 ^see 1)
  10147. =>WM: (13629: I2 ^level-1 L1-root)
  10148. <=WM: (13614: I2 ^level-1 L1-root)
  10149. --- END Input Phase ---
  10150. --- Proposal Phase ---
  10151. --- Inner Elaboration Phase, active level 1 (S1) ---
  10152. Firing elaborate*copy-see-to-output-link
  10153. -->
  10154. (I3 ^see 0 +)
  10155. Firing elaborate*reward*based*on*reward
  10156. -->
  10157. (R976 ^value 1 +)
  10158. (R1 ^reward R976 +)
  10159. Firing propose*predict-yes
  10160. -->
  10161. (O1945 ^name predict-yes +)
  10162. (S1 ^operator O1945 +)
  10163. Firing propose*predict-no
  10164. -->
  10165. (O1946 ^name predict-no +)
  10166. (S1 ^operator O1946 +)
  10167. Firing rl*prefer*rvt*predict-no*H0*6
  10168. -->
  10169. (S1 ^operator O1944 = 0.9999999999999999)
  10170. Firing rl*prefer*rvt*predict-yes*H0*5
  10171. -->
  10172. (S1 ^operator O1943 = 0.)
  10173. Firing prefer*rvt*predict-yes*H0
  10174. -->
  10175. Firing prefer*rvt*predict-no*H0
  10176. -->
  10177. Firing elaborate*copy-dir-to-output-link
  10178. -->
  10179. (I3 ^dir U +)
  10180. inner elaboration loop at bottom goal.
  10181. Retracting elaborate*copy-see-to-output-link
  10182. -->
  10183. (I3 ^see 1 +)
  10184. Retracting propose*predict-no
  10185. -->
  10186. (O1944 ^name predict-no +)
  10187. (S1 ^operator O1944 +)
  10188. Retracting propose*predict-yes
  10189. -->
  10190. (O1943 ^name predict-yes +)
  10191. (S1 ^operator O1943 +)
  10192. Retracting elaborate*reward*based*on*reward
  10193. -->
  10194. (R975 ^value 1 +)
  10195. (R1 ^reward R975 +)
  10196. Retracting elaborate*copy-dir-to-output-link
  10197. -->
  10198. (I3 ^dir U +)
  10199. Retracting rl*prefer*rvt*predict-no*H0*6
  10200. -->
  10201. (S1 ^operator O1944 = 0.9999999999999999)
  10202. Retracting rl*prefer*rvt*predict-yes*H0*5
  10203. -->
  10204. (S1 ^operator O1943 = 0.)
  10205. =>WM: (13636: S1 ^operator O1946 +)
  10206. =>WM: (13635: S1 ^operator O1945 +)
  10207. =>WM: (13634: O1946 ^name predict-no)
  10208. =>WM: (13633: O1945 ^name predict-yes)
  10209. =>WM: (13632: R976 ^value 1)
  10210. =>WM: (13631: R1 ^reward R976)
  10211. =>WM: (13630: I3 ^see 0)
  10212. <=WM: (13621: S1 ^operator O1943 +)
  10213. <=WM: (13622: S1 ^operator O1944 +)
  10214. <=WM: (13623: S1 ^operator O1944)
  10215. <=WM: (13616: R1 ^reward R975)
  10216. <=WM: (13615: I3 ^see 1)
  10217. <=WM: (13619: O1944 ^name predict-no)
  10218. <=WM: (13618: O1943 ^name predict-yes)
  10219. <=WM: (13617: R975 ^value 1)
  10220. --- Inner Elaboration Phase, active level 1 (S1) ---
  10221. Firing prefer*rvt*predict-yes*H0
  10222. -->
  10223. Firing rl*prefer*rvt*predict-yes*H0*5
  10224. -->
  10225. (S1 ^operator O1945 = 0.)
  10226. Firing prefer*rvt*predict-no*H0
  10227. -->
  10228. Firing rl*prefer*rvt*predict-no*H0*6
  10229. -->
  10230. (S1 ^operator O1946 = 0.9999999999999999)
  10231. inner elaboration loop at bottom goal.
  10232. Retracting rl*prefer*rvt*predict-no*H0*6
  10233. -->
  10234. (S1 ^operator O1944 = 0.9999999999999999)
  10235. Retracting rl*prefer*rvt*predict-yes*H0*5
  10236. -->
  10237. (S1 ^operator O1943 = 0.)
  10238. --- END Proposal Phase ---
  10239. --- Decision Phase ---
  10240. RL update rl*prefer*rvt*predict-no*H0*6 1 0 1 -> 1 0 1(R,m,v=1,1,0)
  10241. =>WM: (13637: S1 ^operator O1946)
  10242. 973: O: O1946 (predict-no)
  10243. --- END Decision Phase ---
  10244. --- Application Phase ---
  10245. --- Firing Productions (PE) For State At Depth 1 ---
  10246. --- Inner Elaboration Phase, active level 1 (S1) ---
  10247. Firing apply*operator
  10248. -->
  10249. (I3 ^predict-no N973 + :O )
  10250. Firing apply*operator*complete
  10251. -->
  10252. (I3 ^predict-no N972 - :O )
  10253. inner elaboration loop at bottom goal.
  10254. --- Change Working Memory (PE) ---
  10255. =>WM: (13638: I3 ^predict-no N973)
  10256. <=WM: (13625: N972 ^status complete)
  10257. <=WM: (13624: I3 ^predict-no N972)
  10258. --- Firing Productions (IE) For State At Depth 1 ---
  10259. --- Inner Elaboration Phase, active level 1 (S1) ---
  10260. Firing monitor*world
  10261. -->
  10262. I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
  10263. --- Change Working Memory (IE) ---
  10264. --- END Application Phase ---
  10265. --- Output Phase ---
  10266. ENV: Agent did: predict-no for direction U in state State-A
  10267. In State-A moving U
  10268. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  10269. predict error 0
  10270. dir: dir isU
  10271. --- END Output Phase ---
  10272. -/--- Input Phase ---
  10273. =>WM: (13642: I2 ^dir U)
  10274. =>WM: (13641: I2 ^reward 1)
  10275. =>WM: (13640: I2 ^see 0)
  10276. =>WM: (13639: N973 ^status complete)
  10277. <=WM: (13628: I2 ^dir U)
  10278. <=WM: (13627: I2 ^reward 1)
  10279. <=WM: (13626: I2 ^see 0)
  10280. =>WM: (13643: I2 ^level-1 L1-root)
  10281. <=WM: (13629: I2 ^level-1 L1-root)
  10282. --- END Input Phase ---
  10283. --- Proposal Phase ---
  10284. --- Inner Elaboration Phase, active level 1 (S1) ---
  10285. Firing elaborate*copy-see-to-output-link
  10286. -->
  10287. (I3 ^see 0 +)
  10288. Firing elaborate*reward*based*on*reward
  10289. -->
  10290. (R977 ^value 1 +)
  10291. (R1 ^reward R977 +)
  10292. Firing propose*predict-yes
  10293. -->
  10294. (O1947 ^name predict-yes +)
  10295. (S1 ^operator O1947 +)
  10296. Firing propose*predict-no
  10297. -->
  10298. (O1948 ^name predict-no +)
  10299. (S1 ^operator O1948 +)
  10300. Firing rl*prefer*rvt*predict-no*H0*6
  10301. -->
  10302. (S1 ^operator O1946 = 0.9999999999999999)
  10303. Firing rl*prefer*rvt*predict-yes*H0*5
  10304. -->
  10305. (S1 ^operator O1945 = 0.)
  10306. Firing prefer*rvt*predict-yes*H0
  10307. -->
  10308. Firing prefer*rvt*predict-no*H0
  10309. -->
  10310. Firing elaborate*copy-dir-to-output-link
  10311. -->
  10312. (I3 ^dir U +)
  10313. inner elaboration loop at bottom goal.
  10314. Retracting elaborate*copy-see-to-output-link
  10315. -->
  10316. (I3 ^see 0 +)
  10317. Retracting propose*predict-no
  10318. -->
  10319. (O1946 ^name predict-no +)
  10320. (S1 ^operator O1946 +)
  10321. Retracting propose*predict-yes
  10322. -->
  10323. (O1945 ^name predict-yes +)
  10324. (S1 ^operator O1945 +)
  10325. Retracting elaborate*reward*based*on*reward
  10326. -->
  10327. (R976 ^value 1 +)
  10328. (R1 ^reward R976 +)
  10329. Retracting elaborate*copy-dir-to-output-link
  10330. -->
  10331. (I3 ^dir U +)
  10332. Retracting rl*prefer*rvt*predict-no*H0*6
  10333. -->
  10334. (S1 ^operator O1946 = 0.9999999999999999)
  10335. Retracting rl*prefer*rvt*predict-yes*H0*5
  10336. -->
  10337. (S1 ^operator O1945 = 0.)
  10338. =>WM: (13649: S1 ^operator O1948 +)
  10339. =>WM: (13648: S1 ^operator O1947 +)
  10340. =>WM: (13647: O1948 ^name predict-no)
  10341. =>WM: (13646: O1947 ^name predict-yes)
  10342. =>WM: (13645: R977 ^value 1)
  10343. =>WM: (13644: R1 ^reward R977)
  10344. <=WM: (13635: S1 ^operator O1945 +)
  10345. <=WM: (13636: S1 ^operator O1946 +)
  10346. <=WM: (13637: S1 ^operator O1946)
  10347. <=WM: (13631: R1 ^reward R976)
  10348. <=WM: (13634: O1946 ^name predict-no)
  10349. <=WM: (13633: O1945 ^name predict-yes)
  10350. <=WM: (13632: R976 ^value 1)
  10351. --- Inner Elaboration Phase, active level 1 (S1) ---
  10352. Firing prefer*rvt*predict-yes*H0
  10353. -->
  10354. Firing rl*prefer*rvt*predict-yes*H0*5
  10355. -->
  10356. (S1 ^operator O1947 = 0.)
  10357. Firing prefer*rvt*predict-no*H0
  10358. -->
  10359. Firing rl*prefer*rvt*predict-no*H0*6
  10360. -->
  10361. (S1 ^operator O1948 = 0.9999999999999999)
  10362. inner elaboration loop at bottom goal.
  10363. Retracting rl*prefer*rvt*predict-no*H0*6
  10364. -->
  10365. (S1 ^operator O1946 = 0.9999999999999999)
  10366. Retracting rl*prefer*rvt*predict-yes*H0*5
  10367. -->
  10368. (S1 ^operator O1945 = 0.)
  10369. --- END Proposal Phase ---
  10370. --- Decision Phase ---
  10371. RL update rl*prefer*rvt*predict-no*H0*6 1 0 1 -> 1 0 1(R,m,v=1,1,0)
  10372. =>WM: (13650: S1 ^operator O1948)
  10373. 974: O: O1948 (predict-no)
  10374. --- END Decision Phase ---
  10375. --- Application Phase ---
  10376. --- Firing Productions (PE) For State At Depth 1 ---
  10377. --- Inner Elaboration Phase, active level 1 (S1) ---
  10378. Firing apply*operator
  10379. -->
  10380. (I3 ^predict-no N974 + :O )
  10381. Firing apply*operator*complete
  10382. -->
  10383. (I3 ^predict-no N973 - :O )
  10384. inner elaboration loop at bottom goal.
  10385. --- Change Working Memory (PE) ---
  10386. =>WM: (13651: I3 ^predict-no N974)
  10387. <=WM: (13639: N973 ^status complete)
  10388. <=WM: (13638: I3 ^predict-no N973)
  10389. --- Firing Productions (IE) For State At Depth 1 ---
  10390. --- Inner Elaboration Phase, active level 1 (S1) ---
  10391. Firing monitor*world
  10392. -->
  10393. I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
  10394. --- Change Working Memory (IE) ---
  10395. --- END Application Phase ---
  10396. --- Output Phase ---
  10397. ENV: Agent did: predict-no for direction U in state State-A
  10398. In State-A moving U
  10399. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  10400. predict error 0
  10401. dir: dir isU
  10402. --- END Output Phase ---
  10403. |\---- Input Phase ---
  10404. =>WM: (13655: I2 ^dir U)
  10405. =>WM: (13654: I2 ^reward 1)
  10406. =>WM: (13653: I2 ^see 0)
  10407. =>WM: (13652: N974 ^status complete)
  10408. <=WM: (13642: I2 ^dir U)
  10409. <=WM: (13641: I2 ^reward 1)
  10410. <=WM: (13640: I2 ^see 0)
  10411. =>WM: (13656: I2 ^level-1 L1-root)
  10412. <=WM: (13643: I2 ^level-1 L1-root)
  10413. --- END Input Phase ---
  10414. --- Proposal Phase ---
  10415. --- Inner Elaboration Phase, active level 1 (S1) ---
  10416. Firing elaborate*copy-see-to-output-link
  10417. -->
  10418. (I3 ^see 0 +)
  10419. Firing elaborate*reward*based*on*reward
  10420. -->
  10421. (R978 ^value 1 +)
  10422. (R1 ^reward R978 +)
  10423. Firing propose*predict-yes
  10424. -->
  10425. (O1949 ^name predict-yes +)
  10426. (S1 ^operator O1949 +)
  10427. Firing propose*predict-no
  10428. -->
  10429. (O1950 ^name predict-no +)
  10430. (S1 ^operator O1950 +)
  10431. Firing rl*prefer*rvt*predict-no*H0*6
  10432. -->
  10433. (S1 ^operator O1948 = 0.9999999999999999)
  10434. Firing rl*prefer*rvt*predict-yes*H0*5
  10435. -->
  10436. (S1 ^operator O1947 = 0.)
  10437. Firing prefer*rvt*predict-yes*H0
  10438. -->
  10439. Firing prefer*rvt*predict-no*H0
  10440. -->
  10441. Firing elaborate*copy-dir-to-output-link
  10442. -->
  10443. (I3 ^dir U +)
  10444. inner elaboration loop at bottom goal.
  10445. Retracting elaborate*copy-see-to-output-link
  10446. -->
  10447. (I3 ^see 0 +)
  10448. Retracting propose*predict-no
  10449. -->
  10450. (O1948 ^name predict-no +)
  10451. (S1 ^operator O1948 +)
  10452. Retracting propose*predict-yes
  10453. -->
  10454. (O1947 ^name predict-yes +)
  10455. (S1 ^operator O1947 +)
  10456. Retracting elaborate*reward*based*on*reward
  10457. -->
  10458. (R977 ^value 1 +)
  10459. (R1 ^reward R977 +)
  10460. Retracting elaborate*copy-dir-to-output-link
  10461. -->
  10462. (I3 ^dir U +)
  10463. Retracting rl*prefer*rvt*predict-no*H0*6
  10464. -->
  10465. (S1 ^operator O1948 = 0.9999999999999999)
  10466. Retracting rl*prefer*rvt*predict-yes*H0*5
  10467. -->
  10468. (S1 ^operator O1947 = 0.)
  10469. =>WM: (13662: S1 ^operator O1950 +)
  10470. =>WM: (13661: S1 ^operator O1949 +)
  10471. =>WM: (13660: O1950 ^name predict-no)
  10472. =>WM: (13659: O1949 ^name predict-yes)
  10473. =>WM: (13658: R978 ^value 1)
  10474. =>WM: (13657: R1 ^reward R978)
  10475. <=WM: (13648: S1 ^operator O1947 +)
  10476. <=WM: (13649: S1 ^operator O1948 +)
  10477. <=WM: (13650: S1 ^operator O1948)
  10478. <=WM: (13644: R1 ^reward R977)
  10479. <=WM: (13647: O1948 ^name predict-no)
  10480. <=WM: (13646: O1947 ^name predict-yes)
  10481. <=WM: (13645: R977 ^value 1)
  10482. --- Inner Elaboration Phase, active level 1 (S1) ---
  10483. Firing prefer*rvt*predict-yes*H0
  10484. -->
  10485. Firing rl*prefer*rvt*predict-yes*H0*5
  10486. -->
  10487. (S1 ^operator O1949 = 0.)
  10488. Firing prefer*rvt*predict-no*H0
  10489. -->
  10490. Firing rl*prefer*rvt*predict-no*H0*6
  10491. -->
  10492. (S1 ^operator O1950 = 0.9999999999999999)
  10493. inner elaboration loop at bottom goal.
  10494. Retracting rl*prefer*rvt*predict-no*H0*6
  10495. -->
  10496. (S1 ^operator O1948 = 0.9999999999999999)
  10497. Retracting rl*prefer*rvt*predict-yes*H0*5
  10498. -->
  10499. (S1 ^operator O1947 = 0.)
  10500. --- END Proposal Phase ---
  10501. --- Decision Phase ---
  10502. RL update rl*prefer*rvt*predict-no*H0*6 1 0 1 -> 1 0 1(R,m,v=1,1,0)
  10503. =>WM: (13663: S1 ^operator O1950)
  10504. 975: O: O1950 (predict-no)
  10505. --- END Decision Phase ---
  10506. --- Application Phase ---
  10507. --- Firing Productions (PE) For State At Depth 1 ---
  10508. --- Inner Elaboration Phase, active level 1 (S1) ---
  10509. Firing apply*operator
  10510. -->
  10511. (I3 ^predict-no N975 + :O )
  10512. Firing apply*operator*complete
  10513. -->
  10514. (I3 ^predict-no N974 - :O )
  10515. inner elaboration loop at bottom goal.
  10516. --- Change Working Memory (PE) ---
  10517. =>WM: (13664: I3 ^predict-no N975)
  10518. <=WM: (13652: N974 ^status complete)
  10519. <=WM: (13651: I3 ^predict-no N974)
  10520. --- Firing Productions (IE) For State At Depth 1 ---
  10521. --- Inner Elaboration Phase, active level 1 (S1) ---
  10522. Firing monitor*world
  10523. -->
  10524. I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
  10525. --- Change Working Memory (IE) ---
  10526. --- END Application Phase ---
  10527. --- Output Phase ---
  10528. ENV: Agent did: predict-no for direction U in state State-A
  10529. In State-A moving U
  10530. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  10531. predict error 0
  10532. dir: dir isR
  10533. --- END Output Phase ---
  10534. /|\--- Input Phase ---
  10535. =>WM: (13668: I2 ^dir R)
  10536. =>WM: (13667: I2 ^reward 1)
  10537. =>WM: (13666: I2 ^see 0)
  10538. =>WM: (13665: N975 ^status complete)
  10539. <=WM: (13655: I2 ^dir U)
  10540. <=WM: (13654: I2 ^reward 1)
  10541. <=WM: (13653: I2 ^see 0)
  10542. =>WM: (13669: I2 ^level-1 L1-root)
  10543. <=WM: (13656: I2 ^level-1 L1-root)
  10544. --- END Input Phase ---
  10545. --- Proposal Phase ---
  10546. --- Inner Elaboration Phase, active level 1 (S1) ---
  10547. Firing rl*prefer*rvt*predict-no*H0*4*v1*H1*45
  10548. -->
  10549. (S1 ^operator O1950 = -0.02155734064455064)
  10550. Firing rl*prefer*rvt*predict-yes*H0*3*v1*H1*46
  10551. -->
  10552. (S1 ^operator O1949 = 0.8155758449529213)
  10553. Firing prefer*rvt*predict-no*H0*4*v1*H1
  10554. -->
  10555. Firing prefer*rvt*predict-yes*H0*3*v1*H1
  10556. -->
  10557. Firing elaborate*copy-see-to-output-link
  10558. -->
  10559. (I3 ^see 0 +)
  10560. Firing elaborate*reward*based*on*reward
  10561. -->
  10562. (R979 ^value 1 +)
  10563. (R1 ^reward R979 +)
  10564. Firing propose*predict-yes
  10565. -->
  10566. (O1951 ^name predict-yes +)
  10567. (S1 ^operator O1951 +)
  10568. Firing propose*predict-no
  10569. -->
  10570. (O1952 ^name predict-no +)
  10571. (S1 ^operator O1952 +)
  10572. Firing rl*prefer*rvt*predict-no*H0*4
  10573. -->
  10574. (S1 ^operator O1950 = 0.4476189814068987)
  10575. Firing rl*prefer*rvt*predict-yes*H0*3
  10576. -->
  10577. (S1 ^operator O1949 = 0.1844075128644186)
  10578. Firing prefer*rvt*predict-yes*H0
  10579. -->
  10580. Firing prefer*rvt*predict-no*H0
  10581. -->
  10582. Firing elaborate*copy-dir-to-output-link
  10583. -->
  10584. (I3 ^dir R +)
  10585. inner elaboration loop at bottom goal.
  10586. Retracting elaborate*copy-see-to-output-link
  10587. -->
  10588. (I3 ^see 0 +)
  10589. Retracting propose*predict-no
  10590. -->
  10591. (O1950 ^name predict-no +)
  10592. (S1 ^operator O1950 +)
  10593. Retracting propose*predict-yes
  10594. -->
  10595. (O1949 ^name predict-yes +)
  10596. (S1 ^operator O1949 +)
  10597. Retracting elaborate*reward*based*on*reward
  10598. -->
  10599. (R978 ^value 1 +)
  10600. (R1 ^reward R978 +)
  10601. Retracting elaborate*copy-dir-to-output-link
  10602. -->
  10603. (I3 ^dir U +)
  10604. Retracting rl*prefer*rvt*predict-no*H0*6
  10605. -->
  10606. (S1 ^operator O1950 = 0.9999999999999999)
  10607. Retracting rl*prefer*rvt*predict-yes*H0*5
  10608. -->
  10609. (S1 ^operator O1949 = 0.)
  10610. =>WM: (13676: S1 ^operator O1952 +)
  10611. =>WM: (13675: S1 ^operator O1951 +)
  10612. =>WM: (13674: I3 ^dir R)
  10613. =>WM: (13673: O1952 ^name predict-no)
  10614. =>WM: (13672: O1951 ^name predict-yes)
  10615. =>WM: (13671: R979 ^value 1)
  10616. =>WM: (13670: R1 ^reward R979)
  10617. <=WM: (13661: S1 ^operator O1949 +)
  10618. <=WM: (13662: S1 ^operator O1950 +)
  10619. <=WM: (13663: S1 ^operator O1950)
  10620. <=WM: (13620: I3 ^dir U)
  10621. <=WM: (13657: R1 ^reward R978)
  10622. <=WM: (13660: O1950 ^name predict-no)
  10623. <=WM: (13659: O1949 ^name predict-yes)
  10624. <=WM: (13658: R978 ^value 1)
  10625. --- Inner Elaboration Phase, active level 1 (S1) ---
  10626. Firing prefer*rvt*predict-yes*H0
  10627. -->
  10628. Firing rl*prefer*rvt*predict-yes*H0*3*v1*H1*46
  10629. -->
  10630. (S1 ^operator O1951 = 0.8155758449529213)
  10631. Firing rl*prefer*rvt*predict-yes*H0*3
  10632. -->
  10633. (S1 ^operator O1951 = 0.1844075128644186)
  10634. Firing prefer*rvt*predict-yes*H0*3*v1*H1
  10635. -->
  10636. Firing prefer*rvt*predict-no*H0
  10637. -->
  10638. Firing rl*prefer*rvt*predict-no*H0*4*v1*H1*45
  10639. -->
  10640. (S1 ^operator O1952 = -0.02155734064455064)
  10641. Firing rl*prefer*rvt*predict-no*H0*4
  10642. -->
  10643. (S1 ^operator O1952 = 0.4476189814068987)
  10644. Firing prefer*rvt*predict-no*H0*4*v1*H1
  10645. -->
  10646. inner elaboration loop at bottom goal.
  10647. Retracting rl*prefer*rvt*predict-no*H0*4
  10648. -->
  10649. (S1 ^operator O1950 = 0.4476189814068987)
  10650. Retracting rl*prefer*rvt*predict-no*H0*4*v1*H1*45
  10651. -->
  10652. (S1 ^operator O1950 = -0.02155734064455064)
  10653. Retracting rl*prefer*rvt*predict-yes*H0*3
  10654. -->
  10655. (S1 ^operator O1949 = 0.1844075128644186)
  10656. Retracting rl*prefer*rvt*predict-yes*H0*3*v1*H1*46
  10657. -->
  10658. (S1 ^operator O1949 = 0.8155758449529213)
  10659. --- END Proposal Phase ---
  10660. --- Decision Phase ---
  10661. RL update rl*prefer*rvt*predict-no*H0*6 1 0 1 -> 1 0 1(R,m,v=1,1,0)
  10662. =>WM: (13677: S1 ^operator O1951)
  10663. 976: O: O1951 (predict-yes)
  10664. --- END Decision Phase ---
  10665. --- Application Phase ---
  10666. --- Firing Productions (PE) For State At Depth 1 ---
  10667. --- Inner Elaboration Phase, active level 1 (S1) ---
  10668. Firing apply*operator
  10669. -->
  10670. (I3 ^predict-yes N976 + :O )
  10671. Firing apply*operator*complete
  10672. -->
  10673. (I3 ^predict-no N975 - :O )
  10674. inner elaboration loop at bottom goal.
  10675. --- Change Working Memory (PE) ---
  10676. =>WM: (13678: I3 ^predict-yes N976)
  10677. <=WM: (13665: N975 ^status complete)
  10678. <=WM: (13664: I3 ^predict-no N975)
  10679. --- Firing Productions (IE) For State At Depth 1 ---
  10680. --- Inner Elaboration Phase, active level 1 (S1) ---
  10681. Firing monitor*world
  10682. -->
  10683. I see 1 and I'm going to do: predict-yes inner elaboration loop at bottom goal.
  10684. --- Change Working Memory (IE) ---
  10685. --- END Application Phase ---
  10686. --- Output Phase ---
  10687. ENV: Agent did: predict-yes for direction R in state State-A
  10688. In State-A moving R
  10689. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  10690. predict error 0
  10691. dir: dir isL
  10692. --- END Output Phase ---
  10693. -/|--- Input Phase ---
  10694. =>WM: (13682: I2 ^dir L)
  10695. =>WM: (13681: I2 ^reward 1)
  10696. =>WM: (13680: I2 ^see 1)
  10697. =>WM: (13679: N976 ^status complete)
  10698. <=WM: (13668: I2 ^dir R)
  10699. <=WM: (13667: I2 ^reward 1)
  10700. <=WM: (13666: I2 ^see 0)
  10701. =>WM: (13683: I2 ^level-1 R1-root)
  10702. <=WM: (13669: I2 ^level-1 L1-root)
  10703. --- END Input Phase ---
  10704. --- Proposal Phase ---
  10705. --- Inner Elaboration Phase, active level 1 (S1) ---
  10706. Firing rl*prefer*rvt*predict-yes*H0*1*v1*H1*36
  10707. -->
  10708. (S1 ^operator O1951 = 0.6104589917494525)
  10709. Firing rl*prefer*rvt*predict-no*H0*2*v1*H1*35
  10710. -->
  10711. (S1 ^operator O1952 = 0.2714993082286609)
  10712. Firing prefer*rvt*predict-no*H0*2*v1*H1
  10713. -->
  10714. Firing prefer*rvt*predict-yes*H0*1*v1*H1
  10715. -->
  10716. Firing elaborate*copy-see-to-output-link
  10717. -->
  10718. (I3 ^see 1 +)
  10719. Firing elaborate*reward*based*on*reward
  10720. -->
  10721. (R980 ^value 1 +)
  10722. (R1 ^reward R980 +)
  10723. Firing propose*predict-yes
  10724. -->
  10725. (O1953 ^name predict-yes +)
  10726. (S1 ^operator O1953 +)
  10727. Firing propose*predict-no
  10728. -->
  10729. (O1954 ^name predict-no +)
  10730. (S1 ^operator O1954 +)
  10731. Firing rl*prefer*rvt*predict-no*H0*2
  10732. -->
  10733. (S1 ^operator O1952 = 0.387336901415443)
  10734. Firing rl*prefer*rvt*predict-yes*H0*1
  10735. -->
  10736. (S1 ^operator O1951 = 0.389539338123754)
  10737. Firing prefer*rvt*predict-yes*H0
  10738. -->
  10739. Firing prefer*rvt*predict-no*H0
  10740. -->
  10741. Firing elaborate*copy-dir-to-output-link
  10742. -->
  10743. (I3 ^dir L +)
  10744. inner elaboration loop at bottom goal.
  10745. Retracting elaborate*copy-see-to-output-link
  10746. -->
  10747. (I3 ^see 0 +)
  10748. Retracting propose*predict-no
  10749. -->
  10750. (O1952 ^name predict-no +)
  10751. (S1 ^operator O1952 +)
  10752. Retracting propose*predict-yes
  10753. -->
  10754. (O1951 ^name predict-yes +)
  10755. (S1 ^operator O1951 +)
  10756. Retracting elaborate*reward*based*on*reward
  10757. -->
  10758. (R979 ^value 1 +)
  10759. (R1 ^reward R979 +)
  10760. Retracting elaborate*copy-dir-to-output-link
  10761. -->
  10762. (I3 ^dir R +)
  10763. Retracting rl*prefer*rvt*predict-no*H0*4
  10764. -->
  10765. (S1 ^operator O1952 = 0.4476189814068987)
  10766. Retracting rl*prefer*rvt*predict-no*H0*4*v1*H1*45
  10767. -->
  10768. (S1 ^operator O1952 = -0.02155734064455064)
  10769. Retracting rl*prefer*rvt*predict-yes*H0*3
  10770. -->
  10771. (S1 ^operator O1951 = 0.1844075128644186)
  10772. Retracting rl*prefer*rvt*predict-yes*H0*3*v1*H1*46
  10773. -->
  10774. (S1 ^operator O1951 = 0.8155758449529213)
  10775. =>WM: (13691: S1 ^operator O1954 +)
  10776. =>WM: (13690: S1 ^operator O1953 +)
  10777. =>WM: (13689: I3 ^dir L)
  10778. =>WM: (13688: O1954 ^name predict-no)
  10779. =>WM: (13687: O1953 ^name predict-yes)
  10780. =>WM: (13686: R980 ^value 1)
  10781. =>WM: (13685: R1 ^reward R980)
  10782. =>WM: (13684: I3 ^see 1)
  10783. <=WM: (13675: S1 ^operator O1951 +)
  10784. <=WM: (13677: S1 ^operator O1951)
  10785. <=WM: (13676: S1 ^operator O1952 +)
  10786. <=WM: (13674: I3 ^dir R)
  10787. <=WM: (13670: R1 ^reward R979)
  10788. <=WM: (13630: I3 ^see 0)
  10789. <=WM: (13673: O1952 ^name predict-no)
  10790. <=WM: (13672: O1951 ^name predict-yes)
  10791. <=WM: (13671: R979 ^value 1)
  10792. --- Inner Elaboration Phase, active level 1 (S1) ---
  10793. Firing prefer*rvt*predict-yes*H0
  10794. -->
  10795. Firing rl*prefer*rvt*predict-yes*H0*1
  10796. -->
  10797. (S1 ^operator O1953 = 0.389539338123754)
  10798. Firing prefer*rvt*predict-yes*H0*1*v1*H1
  10799. -->
  10800. Firing rl*prefer*rvt*predict-yes*H0*1*v1*H1*36
  10801. -->
  10802. (S1 ^operator O1953 = 0.6104589917494525)
  10803. Firing prefer*rvt*predict-no*H0
  10804. -->
  10805. Firing rl*prefer*rvt*predict-no*H0*2
  10806. -->
  10807. (S1 ^operator O1954 = 0.387336901415443)
  10808. Firing prefer*rvt*predict-no*H0*2*v1*H1
  10809. -->
  10810. Firing rl*prefer*rvt*predict-no*H0*2*v1*H1*35
  10811. -->
  10812. (S1 ^operator O1954 = 0.2714993082286609)
  10813. inner elaboration loop at bottom goal.
  10814. Retracting rl*prefer*rvt*predict-no*H0*2
  10815. -->
  10816. (S1 ^operator O1952 = 0.387336901415443)
  10817. Retracting rl*prefer*rvt*predict-no*H0*2*v1*H1*35
  10818. -->
  10819. (S1 ^operator O1952 = 0.2714993082286609)
  10820. Retracting rl*prefer*rvt*predict-yes*H0*1
  10821. -->
  10822. (S1 ^operator O1951 = 0.389539338123754)
  10823. Retracting rl*prefer*rvt*predict-yes*H0*1*v1*H1*36
  10824. -->
  10825. (S1 ^operator O1951 = 0.6104589917494525)
  10826. --- END Proposal Phase ---
  10827. --- Decision Phase ---
  10828. RL update rl*prefer*rvt*predict-yes*H0*3 0.675409 -0.491002 0.184408 -> 0.675412 -0.491002 0.18441(R,m,v=1,0.89697,0.0929786)
  10829. RL update rl*prefer*rvt*predict-yes*H0*3*v1*H1*46 0.324569 0.491006 0.815576 -> 0.324573 0.491006 0.815578(R,m,v=1,1,0)
  10830. =>WM: (13692: S1 ^operator O1953)
  10831. 977: O: O1953 (predict-yes)
  10832. --- END Decision Phase ---
  10833. --- Application Phase ---
  10834. --- Firing Productions (PE) For State At Depth 1 ---
  10835. --- Inner Elaboration Phase, active level 1 (S1) ---
  10836. Firing apply*operator
  10837. -->
  10838. (I3 ^predict-yes N977 + :O )
  10839. Firing apply*operator*complete
  10840. -->
  10841. (I3 ^predict-yes N976 - :O )
  10842. inner elaboration loop at bottom goal.
  10843. --- Change Working Memory (PE) ---
  10844. =>WM: (13693: I3 ^predict-yes N977)
  10845. <=WM: (13679: N976 ^status complete)
  10846. <=WM: (13678: I3 ^predict-yes N976)
  10847. --- Firing Productions (IE) For State At Depth 1 ---
  10848. --- Inner Elaboration Phase, active level 1 (S1) ---
  10849. Firing monitor*world
  10850. -->
  10851. I see 1 and I'm going to do: predict-yes inner elaboration loop at bottom goal.
  10852. --- Change Working Memory (IE) ---
  10853. --- END Application Phase ---
  10854. --- Output Phase ---
  10855. ENV: Agent did: predict-yes for direction L in state State-B
  10856. In State-B moving L
  10857. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  10858. predict error 0
  10859. dir: dir isL
  10860. --- END Output Phase ---
  10861. \-/--- Input Phase ---
  10862. =>WM: (13697: I2 ^dir L)
  10863. =>WM: (13696: I2 ^reward 1)
  10864. =>WM: (13695: I2 ^see 1)
  10865. =>WM: (13694: N977 ^status complete)
  10866. <=WM: (13682: I2 ^dir L)
  10867. <=WM: (13681: I2 ^reward 1)
  10868. <=WM: (13680: I2 ^see 1)
  10869. =>WM: (13698: I2 ^level-1 L1-root)
  10870. <=WM: (13683: I2 ^level-1 R1-root)
  10871. --- END Input Phase ---
  10872. --- Proposal Phase ---
  10873. --- Inner Elaboration Phase, active level 1 (S1) ---
  10874. Firing rl*prefer*rvt*predict-no*H0*2*v1*H1*32
  10875. -->
  10876. (S1 ^operator O1954 = 0.6126626863207351)
  10877. Firing rl*prefer*rvt*predict-yes*H0*1*v1*H1*31
  10878. -->
  10879. (S1 ^operator O1953 = -0.02274740735326741)
  10880. Firing prefer*rvt*predict-no*H0*2*v1*H1
  10881. -->
  10882. Firing prefer*rvt*predict-yes*H0*1*v1*H1
  10883. -->
  10884. Firing elaborate*copy-see-to-output-link
  10885. -->
  10886. (I3 ^see 1 +)
  10887. Firing elaborate*reward*based*on*reward
  10888. -->
  10889. (R981 ^value 1 +)
  10890. (R1 ^reward R981 +)
  10891. Firing propose*predict-yes
  10892. -->
  10893. (O1955 ^name predict-yes +)
  10894. (S1 ^operator O1955 +)
  10895. Firing propose*predict-no
  10896. -->
  10897. (O1956 ^name predict-no +)
  10898. (S1 ^operator O1956 +)
  10899. Firing rl*prefer*rvt*predict-no*H0*2
  10900. -->
  10901. (S1 ^operator O1954 = 0.387336901415443)
  10902. Firing rl*prefer*rvt*predict-yes*H0*1
  10903. -->
  10904. (S1 ^operator O1953 = 0.389539338123754)
  10905. Firing prefer*rvt*predict-yes*H0
  10906. -->
  10907. Firing prefer*rvt*predict-no*H0
  10908. -->
  10909. Firing elaborate*copy-dir-to-output-link
  10910. -->
  10911. (I3 ^dir L +)
  10912. inner elaboration loop at bottom goal.
  10913. Retracting elaborate*copy-see-to-output-link
  10914. -->
  10915. (I3 ^see 1 +)
  10916. Retracting propose*predict-no
  10917. -->
  10918. (O1954 ^name predict-no +)
  10919. (S1 ^operator O1954 +)
  10920. Retracting propose*predict-yes
  10921. -->
  10922. (O1953 ^name predict-yes +)
  10923. (S1 ^operator O1953 +)
  10924. Retracting elaborate*reward*based*on*reward
  10925. -->
  10926. (R980 ^value 1 +)
  10927. (R1 ^reward R980 +)
  10928. Retracting elaborate*copy-dir-to-output-link
  10929. -->
  10930. (I3 ^dir L +)
  10931. Retracting rl*prefer*rvt*predict-no*H0*2*v1*H1*35
  10932. -->
  10933. (S1 ^operator O1954 = 0.2714993082286609)
  10934. Retracting rl*prefer*rvt*predict-no*H0*2
  10935. -->
  10936. (S1 ^operator O1954 = 0.387336901415443)
  10937. Retracting rl*prefer*rvt*predict-yes*H0*1*v1*H1*36
  10938. -->
  10939. (S1 ^operator O1953 = 0.6104589917494525)
  10940. Retracting rl*prefer*rvt*predict-yes*H0*1
  10941. -->
  10942. (S1 ^operator O1953 = 0.389539338123754)
  10943. =>WM: (13704: S1 ^operator O1956 +)
  10944. =>WM: (13703: S1 ^operator O1955 +)
  10945. =>WM: (13702: O1956 ^name predict-no)
  10946. =>WM: (13701: O1955 ^name predict-yes)
  10947. =>WM: (13700: R981 ^value 1)
  10948. =>WM: (13699: R1 ^reward R981)
  10949. <=WM: (13690: S1 ^operator O1953 +)
  10950. <=WM: (13692: S1 ^operator O1953)
  10951. <=WM: (13691: S1 ^operator O1954 +)
  10952. <=WM: (13685: R1 ^reward R980)
  10953. <=WM: (13688: O1954 ^name predict-no)
  10954. <=WM: (13687: O1953 ^name predict-yes)
  10955. <=WM: (13686: R980 ^value 1)
  10956. --- Inner Elaboration Phase, active level 1 (S1) ---
  10957. Firing prefer*rvt*predict-yes*H0
  10958. -->
  10959. Firing rl*prefer*rvt*predict-yes*H0*1
  10960. -->
  10961. (S1 ^operator O1955 = 0.389539338123754)
  10962. Firing prefer*rvt*predict-yes*H0*1*v1*H1
  10963. -->
  10964. Firing rl*prefer*rvt*predict-yes*H0*1*v1*H1*31
  10965. -->
  10966. (S1 ^operator O1955 = -0.02274740735326741)
  10967. Firing prefer*rvt*predict-no*H0
  10968. -->
  10969. Firing rl*prefer*rvt*predict-no*H0*2
  10970. -->
  10971. (S1 ^operator O1956 = 0.387336901415443)
  10972. Firing prefer*rvt*predict-no*H0*2*v1*H1
  10973. -->
  10974. Firing rl*prefer*rvt*predict-no*H0*2*v1*H1*32
  10975. -->
  10976. (S1 ^operator O1956 = 0.6126626863207351)
  10977. inner elaboration loop at bottom goal.
  10978. Retracting rl*prefer*rvt*predict-no*H0*2
  10979. -->
  10980. (S1 ^operator O1954 = 0.387336901415443)
  10981. Retracting rl*prefer*rvt*predict-no*H0*2*v1*H1*32
  10982. -->
  10983. (S1 ^operator O1954 = 0.6126626863207351)
  10984. Retracting rl*prefer*rvt*predict-yes*H0*1
  10985. -->
  10986. (S1 ^operator O1953 = 0.389539338123754)
  10987. Retracting rl*prefer*rvt*predict-yes*H0*1*v1*H1*31
  10988. -->
  10989. (S1 ^operator O1953 = -0.02274740735326741)
  10990. --- END Proposal Phase ---
  10991. --- Decision Phase ---
  10992. RL update rl*prefer*rvt*predict-yes*H0*1 0.711951 -0.322412 0.389539 -> 0.711951 -0.322412 0.38954(R,m,v=1,0.889571,0.0988412)
  10993. RL update rl*prefer*rvt*predict-yes*H0*1*v1*H1*36 0.288049 0.32241 0.610459 -> 0.288049 0.322411 0.610459(R,m,v=1,1,0)
  10994. =>WM: (13705: S1 ^operator O1956)
  10995. 978: O: O1956 (predict-no)
  10996. --- END Decision Phase ---
  10997. --- Application Phase ---
  10998. --- Firing Productions (PE) For State At Depth 1 ---
  10999. --- Inner Elaboration Phase, active level 1 (S1) ---
  11000. Firing apply*operator
  11001. -->
  11002. (I3 ^predict-no N978 + :O )
  11003. Firing apply*operator*complete
  11004. -->
  11005. (I3 ^predict-yes N977 - :O )
  11006. inner elaboration loop at bottom goal.
  11007. --- Change Working Memory (PE) ---
  11008. =>WM: (13706: I3 ^predict-no N978)
  11009. <=WM: (13694: N977 ^status complete)
  11010. <=WM: (13693: I3 ^predict-yes N977)
  11011. --- Firing Productions (IE) For State At Depth 1 ---
  11012. --- Inner Elaboration Phase, active level 1 (S1) ---
  11013. Firing monitor*world
  11014. -->
  11015. I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
  11016. --- Change Working Memory (IE) ---
  11017. --- END Application Phase ---
  11018. --- Output Phase ---
  11019. ENV: Agent did: predict-no for direction L in state State-A
  11020. In State-A moving L
  11021. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  11022. predict error 0
  11023. dir: dir isR
  11024. --- END Output Phase ---
  11025. |\---- Input Phase ---
  11026. =>WM: (13710: I2 ^dir R)
  11027. =>WM: (13709: I2 ^reward 1)
  11028. =>WM: (13708: I2 ^see 0)
  11029. =>WM: (13707: N978 ^status complete)
  11030. <=WM: (13697: I2 ^dir L)
  11031. <=WM: (13696: I2 ^reward 1)
  11032. <=WM: (13695: I2 ^see 1)
  11033. =>WM: (13711: I2 ^level-1 L0-root)
  11034. <=WM: (13698: I2 ^level-1 L1-root)
  11035. --- END Input Phase ---
  11036. --- Proposal Phase ---
  11037. --- Inner Elaboration Phase, active level 1 (S1) ---
  11038. Firing rl*prefer*rvt*predict-yes*H0*3*v1*H1*34
  11039. -->
  11040. (S1 ^operator O1955 = 0.8155955750807526)
  11041. Firing rl*prefer*rvt*predict-no*H0*4*v1*H1*33
  11042. -->
  11043. (S1 ^operator O1956 = -0.00558448899823713)
  11044. Firing prefer*rvt*predict-no*H0*4*v1*H1
  11045. -->
  11046. Firing prefer*rvt*predict-yes*H0*3*v1*H1
  11047. -->
  11048. Firing elaborate*copy-see-to-output-link
  11049. -->
  11050. (I3 ^see 0 +)
  11051. Firing elaborate*reward*based*on*reward
  11052. -->
  11053. (R982 ^value 1 +)
  11054. (R1 ^reward R982 +)
  11055. Firing propose*predict-yes
  11056. -->
  11057. (O1957 ^name predict-yes +)
  11058. (S1 ^operator O1957 +)
  11059. Firing propose*predict-no
  11060. -->
  11061. (O1958 ^name predict-no +)
  11062. (S1 ^operator O1958 +)
  11063. Firing rl*prefer*rvt*predict-no*H0*4
  11064. -->
  11065. (S1 ^operator O1956 = 0.4476189814068987)
  11066. Firing rl*prefer*rvt*predict-yes*H0*3
  11067. -->
  11068. (S1 ^operator O1955 = 0.1844100091918176)
  11069. Firing prefer*rvt*predict-yes*H0
  11070. -->
  11071. Firing prefer*rvt*predict-no*H0
  11072. -->
  11073. Firing elaborate*copy-dir-to-output-link
  11074. -->
  11075. (I3 ^dir R +)
  11076. inner elaboration loop at bottom goal.
  11077. Retracting elaborate*copy-see-to-output-link
  11078. -->
  11079. (I3 ^see 1 +)
  11080. Retracting propose*predict-no
  11081. -->
  11082. (O1956 ^name predict-no +)
  11083. (S1 ^operator O1956 +)
  11084. Retracting propose*predict-yes
  11085. -->
  11086. (O1955 ^name predict-yes +)
  11087. (S1 ^operator O1955 +)
  11088. Retracting elaborate*reward*based*on*reward
  11089. -->
  11090. (R981 ^value 1 +)
  11091. (R1 ^reward R981 +)
  11092. Retracting elaborate*copy-dir-to-output-link
  11093. -->
  11094. (I3 ^dir L +)
  11095. Retracting rl*prefer*rvt*predict-no*H0*2*v1*H1*32
  11096. -->
  11097. (S1 ^operator O1956 = 0.6126626863207351)
  11098. Retracting rl*prefer*rvt*predict-no*H0*2
  11099. -->
  11100. (S1 ^operator O1956 = 0.387336901415443)
  11101. Retracting rl*prefer*rvt*predict-yes*H0*1*v1*H1*31
  11102. -->
  11103. (S1 ^operator O1955 = -0.02274740735326741)
  11104. Retracting rl*prefer*rvt*predict-yes*H0*1
  11105. -->
  11106. (S1 ^operator O1955 = 0.389539588642773)
  11107. =>WM: (13719: S1 ^operator O1958 +)
  11108. =>WM: (13718: S1 ^operator O1957 +)
  11109. =>WM: (13717: I3 ^dir R)
  11110. =>WM: (13716: O1958 ^name predict-no)
  11111. =>WM: (13715: O1957 ^name predict-yes)
  11112. =>WM: (13714: R982 ^value 1)
  11113. =>WM: (13713: R1 ^reward R982)
  11114. =>WM: (13712: I3 ^see 0)
  11115. <=WM: (13703: S1 ^operator O1955 +)
  11116. <=WM: (13704: S1 ^operator O1956 +)
  11117. <=WM: (13705: S1 ^operator O1956)
  11118. <=WM: (13689: I3 ^dir L)
  11119. <=WM: (13699: R1 ^reward R981)
  11120. <=WM: (13684: I3 ^see 1)
  11121. <=WM: (13702: O1956 ^name predict-no)
  11122. <=WM: (13701: O1955 ^name predict-yes)
  11123. <=WM: (13700: R981 ^value 1)
  11124. --- Inner Elaboration Phase, active level 1 (S1) ---
  11125. Firing prefer*rvt*predict-yes*H0
  11126. -->
  11127. Firing rl*prefer*rvt*predict-yes*H0*3
  11128. -->
  11129. (S1 ^operator O1957 = 0.1844100091918176)
  11130. Firing prefer*rvt*predict-yes*H0*3*v1*H1
  11131. -->
  11132. Firing rl*prefer*rvt*predict-yes*H0*3*v1*H1*34
  11133. -->
  11134. (S1 ^operator O1957 = 0.8155955750807526)
  11135. Firing prefer*rvt*predict-no*H0
  11136. -->
  11137. Firing rl*prefer*rvt*predict-no*H0*4
  11138. -->
  11139. (S1 ^operator O1958 = 0.4476189814068987)
  11140. Firing prefer*rvt*predict-no*H0*4*v1*H1
  11141. -->
  11142. Firing rl*prefer*rvt*predict-no*H0*4*v1*H1*33
  11143. -->
  11144. (S1 ^operator O1958 = -0.00558448899823713)
  11145. inner elaboration loop at bottom goal.
  11146. Retracting rl*prefer*rvt*predict-no*H0*4
  11147. -->
  11148. (S1 ^operator O1956 = 0.4476189814068987)
  11149. Retracting rl*prefer*rvt*predict-no*H0*4*v1*H1*33
  11150. -->
  11151. (S1 ^operator O1956 = -0.00558448899823713)
  11152. Retracting rl*prefer*rvt*predict-yes*H0*3
  11153. -->
  11154. (S1 ^operator O1955 = 0.1844100091918176)
  11155. Retracting rl*prefer*rvt*predict-yes*H0*3*v1*H1*34
  11156. -->
  11157. (S1 ^operator O1955 = 0.8155955750807526)
  11158. --- END Proposal Phase ---
  11159. --- Decision Phase ---
  11160. RL update rl*prefer*rvt*predict-no*H0*2 0.719081 -0.331744 0.387337 -> 0.719081 -0.331744 0.387337(R,m,v=1,0.931429,0.0642365)
  11161. RL update rl*prefer*rvt*predict-no*H0*2*v1*H1*32 0.280919 0.331744 0.612663 -> 0.280919 0.331744 0.612663(R,m,v=1,1,0)
  11162. =>WM: (13720: S1 ^operator O1957)
  11163. 979: O: O1957 (predict-yes)
  11164. --- END Decision Phase ---
  11165. --- Application Phase ---
  11166. --- Firing Productions (PE) For State At Depth 1 ---
  11167. --- Inner Elaboration Phase, active level 1 (S1) ---
  11168. Firing apply*operator
  11169. -->
  11170. (I3 ^predict-yes N979 + :O )
  11171. Firing apply*operator*complete
  11172. -->
  11173. (I3 ^predict-no N978 - :O )
  11174. inner elaboration loop at bottom goal.
  11175. --- Change Working Memory (PE) ---
  11176. =>WM: (13721: I3 ^predict-yes N979)
  11177. <=WM: (13707: N978 ^status complete)
  11178. <=WM: (13706: I3 ^predict-no N978)
  11179. --- Firing Productions (IE) For State At Depth 1 ---
  11180. --- Inner Elaboration Phase, active level 1 (S1) ---
  11181. Firing monitor*world
  11182. -->
  11183. I see 1 and I'm going to do: predict-yes inner elaboration loop at bottom goal.
  11184. --- Change Working Memory (IE) ---
  11185. --- END Application Phase ---
  11186. --- Output Phase ---
  11187. ENV: Agent did: predict-yes for direction R in state State-A
  11188. In State-A moving R
  11189. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  11190. predict error 0
  11191. dir: dir isU
  11192. --- END Output Phase ---
  11193. /|\--- Input Phase ---
  11194. =>WM: (13725: I2 ^dir U)
  11195. =>WM: (13724: I2 ^reward 1)
  11196. =>WM: (13723: I2 ^see 1)
  11197. =>WM: (13722: N979 ^status complete)
  11198. <=WM: (13710: I2 ^dir R)
  11199. <=WM: (13709: I2 ^reward 1)
  11200. <=WM: (13708: I2 ^see 0)
  11201. =>WM: (13726: I2 ^level-1 R1-root)
  11202. <=WM: (13711: I2 ^level-1 L0-root)
  11203. --- END Input Phase ---
  11204. --- Proposal Phase ---
  11205. --- Inner Elaboration Phase, active level 1 (S1) ---
  11206. Firing elaborate*copy-see-to-output-link
  11207. -->
  11208. (I3 ^see 1 +)
  11209. Firing elaborate*reward*based*on*reward
  11210. -->
  11211. (R983 ^value 1 +)
  11212. (R1 ^reward R983 +)
  11213. Firing propose*predict-yes
  11214. -->
  11215. (O1959 ^name predict-yes +)
  11216. (S1 ^operator O1959 +)
  11217. Firing propose*predict-no
  11218. -->
  11219. (O1960 ^name predict-no +)
  11220. (S1 ^operator O1960 +)
  11221. Firing rl*prefer*rvt*predict-no*H0*6
  11222. -->
  11223. (S1 ^operator O1958 = 0.9999999999999999)
  11224. Firing rl*prefer*rvt*predict-yes*H0*5
  11225. -->
  11226. (S1 ^operator O1957 = 0.)
  11227. Firing prefer*rvt*predict-yes*H0
  11228. -->
  11229. Firing prefer*rvt*predict-no*H0
  11230. -->
  11231. Firing elaborate*copy-dir-to-output-link
  11232. -->
  11233. (I3 ^dir U +)
  11234. inner elaboration loop at bottom goal.
  11235. Retracting elaborate*copy-see-to-output-link
  11236. -->
  11237. (I3 ^see 0 +)
  11238. Retracting propose*predict-no
  11239. -->
  11240. (O1958 ^name predict-no +)
  11241. (S1 ^operator O1958 +)
  11242. Retracting propose*predict-yes
  11243. -->
  11244. (O1957 ^name predict-yes +)
  11245. (S1 ^operator O1957 +)
  11246. Retracting elaborate*reward*based*on*reward
  11247. -->
  11248. (R982 ^value 1 +)
  11249. (R1 ^reward R982 +)
  11250. Retracting elaborate*copy-dir-to-output-link
  11251. -->
  11252. (I3 ^dir R +)
  11253. Retracting rl*prefer*rvt*predict-no*H0*4*v1*H1*33
  11254. -->
  11255. (S1 ^operator O1958 = -0.00558448899823713)
  11256. Retracting rl*prefer*rvt*predict-no*H0*4
  11257. -->
  11258. (S1 ^operator O1958 = 0.4476189814068987)
  11259. Retracting rl*prefer*rvt*predict-yes*H0*3*v1*H1*34
  11260. -->
  11261. (S1 ^operator O1957 = 0.8155955750807526)
  11262. Retracting rl*prefer*rvt*predict-yes*H0*3
  11263. -->
  11264. (S1 ^operator O1957 = 0.1844100091918176)
  11265. =>WM: (13734: S1 ^operator O1960 +)
  11266. =>WM: (13733: S1 ^operator O1959 +)
  11267. =>WM: (13732: I3 ^dir U)
  11268. =>WM: (13731: O1960 ^name predict-no)
  11269. =>WM: (13730: O1959 ^name predict-yes)
  11270. =>WM: (13729: R983 ^value 1)
  11271. =>WM: (13728: R1 ^reward R983)
  11272. =>WM: (13727: I3 ^see 1)
  11273. <=WM: (13718: S1 ^operator O1957 +)
  11274. <=WM: (13720: S1 ^operator O1957)
  11275. <=WM: (13719: S1 ^operator O1958 +)
  11276. <=WM: (13717: I3 ^dir R)
  11277. <=WM: (13713: R1 ^reward R982)
  11278. <=WM: (13712: I3 ^see 0)
  11279. <=WM: (13716: O1958 ^name predict-no)
  11280. <=WM: (13715: O1957 ^name predict-yes)
  11281. <=WM: (13714: R982 ^value 1)
  11282. --- Inner Elaboration Phase, active level 1 (S1) ---
  11283. Firing prefer*rvt*predict-yes*H0
  11284. -->
  11285. Firing rl*prefer*rvt*predict-yes*H0*5
  11286. -->
  11287. (S1 ^operator O1959 = 0.)
  11288. Firing prefer*rvt*predict-no*H0
  11289. -->
  11290. Firing rl*prefer*rvt*predict-no*H0*6
  11291. -->
  11292. (S1 ^operator O1960 = 0.9999999999999999)
  11293. inner elaboration loop at bottom goal.
  11294. Retracting rl*prefer*rvt*predict-no*H0*6
  11295. -->
  11296. (S1 ^operator O1958 = 0.9999999999999999)
  11297. Retracting rl*prefer*rvt*predict-yes*H0*5
  11298. -->
  11299. (S1 ^operator O1957 = 0.)
  11300. --- END Proposal Phase ---
  11301. --- Decision Phase ---
  11302. RL update rl*prefer*rvt*predict-yes*H0*3 0.675412 -0.491002 0.18441 -> 0.675411 -0.491002 0.184409(R,m,v=1,0.89759,0.092479)
  11303. RL update rl*prefer*rvt*predict-yes*H0*3*v1*H1*34 0.324595 0.491001 0.815596 -> 0.324594 0.491001 0.815595(R,m,v=1,1,0)
  11304. =>WM: (13735: S1 ^operator O1960)
  11305. 980: O: O1960 (predict-no)
  11306. --- END Decision Phase ---
  11307. --- Application Phase ---
  11308. --- Firing Productions (PE) For State At Depth 1 ---
  11309. --- Inner Elaboration Phase, active level 1 (S1) ---
  11310. Firing apply*operator
  11311. -->
  11312. (I3 ^predict-no N980 + :O )
  11313. Firing apply*operator*complete
  11314. -->
  11315. (I3 ^predict-yes N979 - :O )
  11316. inner elaboration loop at bottom goal.
  11317. --- Change Working Memory (PE) ---
  11318. =>WM: (13736: I3 ^predict-no N980)
  11319. <=WM: (13722: N979 ^status complete)
  11320. <=WM: (13721: I3 ^predict-yes N979)
  11321. --- Firing Productions (IE) For State At Depth 1 ---
  11322. --- Inner Elaboration Phase, active level 1 (S1) ---
  11323. Firing monitor*world
  11324. -->
  11325. I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
  11326. --- Change Working Memory (IE) ---
  11327. --- END Application Phase ---
  11328. --- Output Phase ---
  11329. ENV: Agent did: predict-no for direction U in state State-B
  11330. In State-B moving U
  11331. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  11332. predict error 0
  11333. dir: dir isU
  11334. --- END Output Phase ---
  11335. -/|--- Input Phase ---
  11336. =>WM: (13740: I2 ^dir U)
  11337. =>WM: (13739: I2 ^reward 1)
  11338. =>WM: (13738: I2 ^see 0)
  11339. =>WM: (13737: N980 ^status complete)
  11340. <=WM: (13725: I2 ^dir U)
  11341. <=WM: (13724: I2 ^reward 1)
  11342. <=WM: (13723: I2 ^see 1)
  11343. =>WM: (13741: I2 ^level-1 R1-root)
  11344. <=WM: (13726: I2 ^level-1 R1-root)
  11345. --- END Input Phase ---
  11346. --- Proposal Phase ---
  11347. --- Inner Elaboration Phase, active level 1 (S1) ---
  11348. Firing elaborate*copy-see-to-output-link
  11349. -->
  11350. (I3 ^see 0 +)
  11351. Firing elaborate*reward*based*on*reward
  11352. -->
  11353. (R984 ^value 1 +)
  11354. (R1 ^reward R984 +)
  11355. Firing propose*predict-yes
  11356. -->
  11357. (O1961 ^name predict-yes +)
  11358. (S1 ^operator O1961 +)
  11359. Firing propose*predict-no
  11360. -->
  11361. (O1962 ^name predict-no +)
  11362. (S1 ^operator O1962 +)
  11363. Firing rl*prefer*rvt*predict-no*H0*6
  11364. -->
  11365. (S1 ^operator O1960 = 0.9999999999999999)
  11366. Firing rl*prefer*rvt*predict-yes*H0*5
  11367. -->
  11368. (S1 ^operator O1959 = 0.)
  11369. Firing prefer*rvt*predict-yes*H0
  11370. -->
  11371. Firing prefer*rvt*predict-no*H0
  11372. -->
  11373. Firing elaborate*copy-dir-to-output-link
  11374. -->
  11375. (I3 ^dir U +)
  11376. inner elaboration loop at bottom goal.
  11377. Retracting elaborate*copy-see-to-output-link
  11378. -->
  11379. (I3 ^see 1 +)
  11380. Retracting propose*predict-no
  11381. -->
  11382. (O1960 ^name predict-no +)
  11383. (S1 ^operator O1960 +)
  11384. Retracting propose*predict-yes
  11385. -->
  11386. (O1959 ^name predict-yes +)
  11387. (S1 ^operator O1959 +)
  11388. Retracting elaborate*reward*based*on*reward
  11389. -->
  11390. (R983 ^value 1 +)
  11391. (R1 ^reward R983 +)
  11392. Retracting elaborate*copy-dir-to-output-link
  11393. -->
  11394. (I3 ^dir U +)
  11395. Retracting rl*prefer*rvt*predict-no*H0*6
  11396. -->
  11397. (S1 ^operator O1960 = 0.9999999999999999)
  11398. Retracting rl*prefer*rvt*predict-yes*H0*5
  11399. -->
  11400. (S1 ^operator O1959 = 0.)
  11401. =>WM: (13748: S1 ^operator O1962 +)
  11402. =>WM: (13747: S1 ^operator O1961 +)
  11403. =>WM: (13746: O1962 ^name predict-no)
  11404. =>WM: (13745: O1961 ^name predict-yes)
  11405. =>WM: (13744: R984 ^value 1)
  11406. =>WM: (13743: R1 ^reward R984)
  11407. =>WM: (13742: I3 ^see 0)
  11408. <=WM: (13733: S1 ^operator O1959 +)
  11409. <=WM: (13734: S1 ^operator O1960 +)
  11410. <=WM: (13735: S1 ^operator O1960)
  11411. <=WM: (13728: R1 ^reward R983)
  11412. <=WM: (13727: I3 ^see 1)
  11413. <=WM: (13731: O1960 ^name predict-no)
  11414. <=WM: (13730: O1959 ^name predict-yes)
  11415. <=WM: (13729: R983 ^value 1)
  11416. --- Inner Elaboration Phase, active level 1 (S1) ---
  11417. Firing prefer*rvt*predict-yes*H0
  11418. -->
  11419. Firing rl*prefer*rvt*predict-yes*H0*5
  11420. -->
  11421. (S1 ^operator O1961 = 0.)
  11422. Firing prefer*rvt*predict-no*H0
  11423. -->
  11424. Firing rl*prefer*rvt*predict-no*H0*6
  11425. -->
  11426. (S1 ^operator O1962 = 0.9999999999999999)
  11427. inner elaboration loop at bottom goal.
  11428. Retracting rl*prefer*rvt*predict-no*H0*6
  11429. -->
  11430. (S1 ^operator O1960 = 0.9999999999999999)
  11431. Retracting rl*prefer*rvt*predict-yes*H0*5
  11432. -->
  11433. (S1 ^operator O1959 = 0.)
  11434. --- END Proposal Phase ---
  11435. --- Decision Phase ---
  11436. RL update rl*prefer*rvt*predict-no*H0*6 1 0 1 -> 1 0 1(R,m,v=1,1,0)
  11437. =>WM: (13749: S1 ^operator O1962)
  11438. 981: O: O1962 (predict-no)
  11439. --- END Decision Phase ---
  11440. --- Application Phase ---
  11441. --- Firing Productions (PE) For State At Depth 1 ---
  11442. --- Inner Elaboration Phase, active level 1 (S1) ---
  11443. Firing apply*operator
  11444. -->
  11445. (I3 ^predict-no N981 + :O )
  11446. Firing apply*operator*complete
  11447. -->
  11448. (I3 ^predict-no N980 - :O )
  11449. inner elaboration loop at bottom goal.
  11450. --- Change Working Memory (PE) ---
  11451. =>WM: (13750: I3 ^predict-no N981)
  11452. <=WM: (13737: N980 ^status complete)
  11453. <=WM: (13736: I3 ^predict-no N980)
  11454. --- Firing Productions (IE) For State At Depth 1 ---
  11455. --- Inner Elaboration Phase, active level 1 (S1) ---
  11456. Firing monitor*world
  11457. -->
  11458. I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
  11459. --- Change Working Memory (IE) ---
  11460. --- END Application Phase ---
  11461. --- Output Phase ---
  11462. ENV: Agent did: predict-no for direction U in state State-B
  11463. In State-B moving U
  11464. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  11465. predict error 0
  11466. dir: dir isU
  11467. --- END Output Phase ---
  11468. \--- Input Phase ---
  11469. =>WM: (13754: I2 ^dir U)
  11470. =>WM: (13753: I2 ^reward 1)
  11471. =>WM: (13752: I2 ^see 0)
  11472. =>WM: (13751: N981 ^status complete)
  11473. <=WM: (13740: I2 ^dir U)
  11474. <=WM: (13739: I2 ^reward 1)
  11475. <=WM: (13738: I2 ^see 0)
  11476. =>WM: (13755: I2 ^level-1 R1-root)
  11477. <=WM: (13741: I2 ^level-1 R1-root)
  11478. --- END Input Phase ---
  11479. --- Proposal Phase ---
  11480. --- Inner Elaboration Phase, active level 1 (S1) ---
  11481. Firing elaborate*copy-see-to-output-link
  11482. -->
  11483. (I3 ^see 0 +)
  11484. Firing elaborate*reward*based*on*reward
  11485. -->
  11486. (R985 ^value 1 +)
  11487. (R1 ^reward R985 +)
  11488. Firing propose*predict-yes
  11489. -->
  11490. (O1963 ^name predict-yes +)
  11491. (S1 ^operator O1963 +)
  11492. Firing propose*predict-no
  11493. -->
  11494. (O1964 ^name predict-no +)
  11495. (S1 ^operator O1964 +)
  11496. Firing rl*prefer*rvt*predict-no*H0*6
  11497. -->
  11498. (S1 ^operator O1962 = 0.9999999999999999)
  11499. Firing rl*prefer*rvt*predict-yes*H0*5
  11500. -->
  11501. (S1 ^operator O1961 = 0.)
  11502. Firing prefer*rvt*predict-yes*H0
  11503. -->
  11504. Firing prefer*rvt*predict-no*H0
  11505. -->
  11506. Firing elaborate*copy-dir-to-output-link
  11507. -->
  11508. (I3 ^dir U +)
  11509. inner elaboration loop at bottom goal.
  11510. Retracting elaborate*copy-see-to-output-link
  11511. -->
  11512. (I3 ^see 0 +)
  11513. Retracting propose*predict-no
  11514. -->
  11515. (O1962 ^name predict-no +)
  11516. (S1 ^operator O1962 +)
  11517. Retracting propose*predict-yes
  11518. -->
  11519. (O1961 ^name predict-yes +)
  11520. (S1 ^operator O1961 +)
  11521. Retracting elaborate*reward*based*on*reward
  11522. -->
  11523. (R984 ^value 1 +)
  11524. (R1 ^reward R984 +)
  11525. Retracting elaborate*copy-dir-to-output-link
  11526. -->
  11527. (I3 ^dir U +)
  11528. Retracting rl*prefer*rvt*predict-no*H0*6
  11529. -->
  11530. (S1 ^operator O1962 = 0.9999999999999999)
  11531. Retracting rl*prefer*rvt*predict-yes*H0*5
  11532. -->
  11533. (S1 ^operator O1961 = 0.)
  11534. =>WM: (13761: S1 ^operator O1964 +)
  11535. =>WM: (13760: S1 ^operator O1963 +)
  11536. =>WM: (13759: O1964 ^name predict-no)
  11537. =>WM: (13758: O1963 ^name predict-yes)
  11538. =>WM: (13757: R985 ^value 1)
  11539. =>WM: (13756: R1 ^reward R985)
  11540. <=WM: (13747: S1 ^operator O1961 +)
  11541. <=WM: (13748: S1 ^operator O1962 +)
  11542. <=WM: (13749: S1 ^operator O1962)
  11543. <=WM: (13743: R1 ^reward R984)
  11544. <=WM: (13746: O1962 ^name predict-no)
  11545. <=WM: (13745: O1961 ^name predict-yes)
  11546. <=WM: (13744: R984 ^value 1)
  11547. --- Inner Elaboration Phase, active level 1 (S1) ---
  11548. Firing prefer*rvt*predict-yes*H0
  11549. -->
  11550. Firing rl*prefer*rvt*predict-yes*H0*5
  11551. -->
  11552. (S1 ^operator O1963 = 0.)
  11553. Firing prefer*rvt*predict-no*H0
  11554. -->
  11555. Firing rl*prefer*rvt*predict-no*H0*6
  11556. -->
  11557. (S1 ^operator O1964 = 0.9999999999999999)
  11558. inner elaboration loop at bottom goal.
  11559. Retracting rl*prefer*rvt*predict-no*H0*6
  11560. -->
  11561. (S1 ^operator O1962 = 0.9999999999999999)
  11562. Retracting rl*prefer*rvt*predict-yes*H0*5
  11563. -->
  11564. (S1 ^operator O1961 = 0.)
  11565. --- END Proposal Phase ---
  11566. --- Decision Phase ---
  11567. RL update rl*prefer*rvt*predict-no*H0*6 1 0 1 -> 1 0 1(R,m,v=1,1,0)
  11568. =>WM: (13762: S1 ^operator O1964)
  11569. 982: O: O1964 (predict-no)
  11570. --- END Decision Phase ---
  11571. --- Application Phase ---
  11572. --- Firing Productions (PE) For State At Depth 1 ---
  11573. --- Inner Elaboration Phase, active level 1 (S1) ---
  11574. Firing apply*operator
  11575. -->
  11576. (I3 ^predict-no N982 + :O )
  11577. Firing apply*operator*complete
  11578. -->
  11579. (I3 ^predict-no N981 - :O )
  11580. inner elaboration loop at bottom goal.
  11581. --- Change Working Memory (PE) ---
  11582. =>WM: (13763: I3 ^predict-no N982)
  11583. <=WM: (13751: N981 ^status complete)
  11584. <=WM: (13750: I3 ^predict-no N981)
  11585. --- Firing Productions (IE) For State At Depth 1 ---
  11586. --- Inner Elaboration Phase, active level 1 (S1) ---
  11587. Firing monitor*world
  11588. -->
  11589. I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
  11590. --- Change Working Memory (IE) ---
  11591. --- END Application Phase ---
  11592. --- Output Phase ---
  11593. ENV: Agent did: predict-no for direction U in state State-B
  11594. In State-B moving U
  11595. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  11596. predict error 0
  11597. dir: dir isR
  11598. --- END Output Phase ---
  11599. -/|--- Input Phase ---
  11600. =>WM: (13767: I2 ^dir R)
  11601. =>WM: (13766: I2 ^reward 1)
  11602. =>WM: (13765: I2 ^see 0)
  11603. =>WM: (13764: N982 ^status complete)
  11604. <=WM: (13754: I2 ^dir U)
  11605. <=WM: (13753: I2 ^reward 1)
  11606. <=WM: (13752: I2 ^see 0)
  11607. =>WM: (13768: I2 ^level-1 R1-root)
  11608. <=WM: (13755: I2 ^level-1 R1-root)
  11609. --- END Input Phase ---
  11610. --- Proposal Phase ---
  11611. --- Inner Elaboration Phase, active level 1 (S1) ---
  11612. Firing rl*prefer*rvt*predict-yes*H0*3*v1*H1*40
  11613. -->
  11614. (S1 ^operator O1963 = 0.1398795999120246)
  11615. Firing rl*prefer*rvt*predict-no*H0*4*v1*H1*39
  11616. -->
  11617. (S1 ^operator O1964 = 0.5523825060913952)
  11618. Firing prefer*rvt*predict-no*H0*4*v1*H1
  11619. -->
  11620. Firing prefer*rvt*predict-yes*H0*3*v1*H1
  11621. -->
  11622. Firing elaborate*copy-see-to-output-link
  11623. -->
  11624. (I3 ^see 0 +)
  11625. Firing elaborate*reward*based*on*reward
  11626. -->
  11627. (R986 ^value 1 +)
  11628. (R1 ^reward R986 +)
  11629. Firing propose*predict-yes
  11630. -->
  11631. (O1965 ^name predict-yes +)
  11632. (S1 ^operator O1965 +)
  11633. Firing propose*predict-no
  11634. -->
  11635. (O1966 ^name predict-no +)
  11636. (S1 ^operator O1966 +)
  11637. Firing rl*prefer*rvt*predict-no*H0*4
  11638. -->
  11639. (S1 ^operator O1964 = 0.4476189814068987)
  11640. Firing rl*prefer*rvt*predict-yes*H0*3
  11641. -->
  11642. (S1 ^operator O1963 = 0.1844091715509321)
  11643. Firing prefer*rvt*predict-yes*H0
  11644. -->
  11645. Firing prefer*rvt*predict-no*H0
  11646. -->
  11647. Firing elaborate*copy-dir-to-output-link
  11648. -->
  11649. (I3 ^dir R +)
  11650. inner elaboration loop at bottom goal.
  11651. Retracting elaborate*copy-see-to-output-link
  11652. -->
  11653. (I3 ^see 0 +)
  11654. Retracting propose*predict-no
  11655. -->
  11656. (O1964 ^name predict-no +)
  11657. (S1 ^operator O1964 +)
  11658. Retracting propose*predict-yes
  11659. -->
  11660. (O1963 ^name predict-yes +)
  11661. (S1 ^operator O1963 +)
  11662. Retracting elaborate*reward*based*on*reward
  11663. -->
  11664. (R985 ^value 1 +)
  11665. (R1 ^reward R985 +)
  11666. Retracting elaborate*copy-dir-to-output-link
  11667. -->
  11668. (I3 ^dir U +)
  11669. Retracting rl*prefer*rvt*predict-no*H0*6
  11670. -->
  11671. (S1 ^operator O1964 = 0.9999999999999999)
  11672. Retracting rl*prefer*rvt*predict-yes*H0*5
  11673. -->
  11674. (S1 ^operator O1963 = 0.)
  11675. =>WM: (13775: S1 ^operator O1966 +)
  11676. =>WM: (13774: S1 ^operator O1965 +)
  11677. =>WM: (13773: I3 ^dir R)
  11678. =>WM: (13772: O1966 ^name predict-no)
  11679. =>WM: (13771: O1965 ^name predict-yes)
  11680. =>WM: (13770: R986 ^value 1)
  11681. =>WM: (13769: R1 ^reward R986)
  11682. <=WM: (13760: S1 ^operator O1963 +)
  11683. <=WM: (13761: S1 ^operator O1964 +)
  11684. <=WM: (13762: S1 ^operator O1964)
  11685. <=WM: (13732: I3 ^dir U)
  11686. <=WM: (13756: R1 ^reward R985)
  11687. <=WM: (13759: O1964 ^name predict-no)
  11688. <=WM: (13758: O1963 ^name predict-yes)
  11689. <=WM: (13757: R985 ^value 1)
  11690. --- Inner Elaboration Phase, active level 1 (S1) ---
  11691. Firing prefer*rvt*predict-yes*H0
  11692. -->
  11693. Firing rl*prefer*rvt*predict-yes*H0*3*v1*H1*40
  11694. -->
  11695. (S1 ^operator O1965 = 0.1398795999120246)
  11696. Firing rl*prefer*rvt*predict-yes*H0*3
  11697. -->
  11698. (S1 ^operator O1965 = 0.1844091715509321)
  11699. Firing prefer*rvt*predict-yes*H0*3*v1*H1
  11700. -->
  11701. Firing prefer*rvt*predict-no*H0
  11702. -->
  11703. Firing rl*prefer*rvt*predict-no*H0*4*v1*H1*39
  11704. -->
  11705. (S1 ^operator O1966 = 0.5523825060913952)
  11706. Firing rl*prefer*rvt*predict-no*H0*4
  11707. -->
  11708. (S1 ^operator O1966 = 0.4476189814068987)
  11709. Firing prefer*rvt*predict-no*H0*4*v1*H1
  11710. -->
  11711. inner elaboration loop at bottom goal.
  11712. Retracting rl*prefer*rvt*predict-no*H0*4
  11713. -->
  11714. (S1 ^operator O1964 = 0.4476189814068987)
  11715. Retracting rl*prefer*rvt*predict-no*H0*4*v1*H1*39
  11716. -->
  11717. (S1 ^operator O1964 = 0.5523825060913952)
  11718. Retracting rl*prefer*rvt*predict-yes*H0*3
  11719. -->
  11720. (S1 ^operator O1963 = 0.1844091715509321)
  11721. Retracting rl*prefer*rvt*predict-yes*H0*3*v1*H1*40
  11722. -->
  11723. (S1 ^operator O1963 = 0.1398795999120246)
  11724. --- END Proposal Phase ---
  11725. --- Decision Phase ---
  11726. RL update rl*prefer*rvt*predict-no*H0*6 1 0 1 -> 1 0 1(R,m,v=1,1,0)
  11727. =>WM: (13776: S1 ^operator O1966)
  11728. 983: O: O1966 (predict-no)
  11729. --- END Decision Phase ---
  11730. --- Application Phase ---
  11731. --- Firing Productions (PE) For State At Depth 1 ---
  11732. --- Inner Elaboration Phase, active level 1 (S1) ---
  11733. Firing apply*operator
  11734. -->
  11735. (I3 ^predict-no N983 + :O )
  11736. Firing apply*operator*complete
  11737. -->
  11738. (I3 ^predict-no N982 - :O )
  11739. inner elaboration loop at bottom goal.
  11740. --- Change Working Memory (PE) ---
  11741. =>WM: (13777: I3 ^predict-no N983)
  11742. <=WM: (13764: N982 ^status complete)
  11743. <=WM: (13763: I3 ^predict-no N982)
  11744. --- Firing Productions (IE) For State At Depth 1 ---
  11745. --- Inner Elaboration Phase, active level 1 (S1) ---
  11746. Firing monitor*world
  11747. -->
  11748. I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
  11749. --- Change Working Memory (IE) ---
  11750. --- END Application Phase ---
  11751. --- Output Phase ---
  11752. ENV: Agent did: predict-no for direction R in state State-B
  11753. In State-B moving R
  11754. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  11755. predict error 0
  11756. dir: dir isR
  11757. --- END Output Phase ---
  11758. \-/|--- Input Phase ---
  11759. =>WM: (13781: I2 ^dir R)
  11760. =>WM: (13780: I2 ^reward 1)
  11761. =>WM: (13779: I2 ^see 0)
  11762. =>WM: (13778: N983 ^status complete)
  11763. <=WM: (13767: I2 ^dir R)
  11764. <=WM: (13766: I2 ^reward 1)
  11765. <=WM: (13765: I2 ^see 0)
  11766. =>WM: (13782: I2 ^level-1 R0-root)
  11767. <=WM: (13768: I2 ^level-1 R1-root)
  11768. --- END Input Phase ---
  11769. --- Proposal Phase ---
  11770. --- Inner Elaboration Phase, active level 1 (S1) ---
  11771. Firing rl*prefer*rvt*predict-yes*H0*3*v1*H1*42
  11772. -->
  11773. (S1 ^operator O1965 = 0.1664311307472832)
  11774. Firing rl*prefer*rvt*predict-no*H0*4*v1*H1*41
  11775. -->
  11776. (S1 ^operator O1966 = 0.5523783049582921)
  11777. Firing prefer*rvt*predict-no*H0*4*v1*H1
  11778. -->
  11779. Firing prefer*rvt*predict-yes*H0*3*v1*H1
  11780. -->
  11781. Firing elaborate*copy-see-to-output-link
  11782. -->
  11783. (I3 ^see 0 +)
  11784. Firing elaborate*reward*based*on*reward
  11785. -->
  11786. (R987 ^value 1 +)
  11787. (R1 ^reward R987 +)
  11788. Firing propose*predict-yes
  11789. -->
  11790. (O1967 ^name predict-yes +)
  11791. (S1 ^operator O1967 +)
  11792. Firing propose*predict-no
  11793. -->
  11794. (O1968 ^name predict-no +)
  11795. (S1 ^operator O1968 +)
  11796. Firing rl*prefer*rvt*predict-no*H0*4
  11797. -->
  11798. (S1 ^operator O1966 = 0.4476189814068987)
  11799. Firing rl*prefer*rvt*predict-yes*H0*3
  11800. -->
  11801. (S1 ^operator O1965 = 0.1844091715509321)
  11802. Firing prefer*rvt*predict-yes*H0
  11803. -->
  11804. Firing prefer*rvt*predict-no*H0
  11805. -->
  11806. Firing elaborate*copy-dir-to-output-link
  11807. -->
  11808. (I3 ^dir R +)
  11809. inner elaboration loop at bottom goal.
  11810. Retracting elaborate*copy-see-to-output-link
  11811. -->
  11812. (I3 ^see 0 +)
  11813. Retracting propose*predict-no
  11814. -->
  11815. (O1966 ^name predict-no +)
  11816. (S1 ^operator O1966 +)
  11817. Retracting propose*predict-yes
  11818. -->
  11819. (O1965 ^name predict-yes +)
  11820. (S1 ^operator O1965 +)
  11821. Retracting elaborate*reward*based*on*reward
  11822. -->
  11823. (R986 ^value 1 +)
  11824. (R1 ^reward R986 +)
  11825. Retracting elaborate*copy-dir-to-output-link
  11826. -->
  11827. (I3 ^dir R +)
  11828. Retracting rl*prefer*rvt*predict-no*H0*4
  11829. -->
  11830. (S1 ^operator O1966 = 0.4476189814068987)
  11831. Retracting rl*prefer*rvt*predict-no*H0*4*v1*H1*39
  11832. -->
  11833. (S1 ^operator O1966 = 0.5523825060913952)
  11834. Retracting rl*prefer*rvt*predict-yes*H0*3
  11835. -->
  11836. (S1 ^operator O1965 = 0.1844091715509321)
  11837. Retracting rl*prefer*rvt*predict-yes*H0*3*v1*H1*40
  11838. -->
  11839. (S1 ^operator O1965 = 0.1398795999120246)
  11840. =>WM: (13788: S1 ^operator O1968 +)
  11841. =>WM: (13787: S1 ^operator O1967 +)
  11842. =>WM: (13786: O1968 ^name predict-no)
  11843. =>WM: (13785: O1967 ^name predict-yes)
  11844. =>WM: (13784: R987 ^value 1)
  11845. =>WM: (13783: R1 ^reward R987)
  11846. <=WM: (13774: S1 ^operator O1965 +)
  11847. <=WM: (13775: S1 ^operator O1966 +)
  11848. <=WM: (13776: S1 ^operator O1966)
  11849. <=WM: (13769: R1 ^reward R986)
  11850. <=WM: (13772: O1966 ^name predict-no)
  11851. <=WM: (13771: O1965 ^name predict-yes)
  11852. <=WM: (13770: R986 ^value 1)
  11853. --- Inner Elaboration Phase, active level 1 (S1) ---
  11854. Firing prefer*rvt*predict-yes*H0
  11855. -->
  11856. Firing rl*prefer*rvt*predict-yes*H0*3
  11857. -->
  11858. (S1 ^operator O1967 = 0.1844091715509321)
  11859. Firing prefer*rvt*predict-yes*H0*3*v1*H1
  11860. -->
  11861. Firing rl*prefer*rvt*predict-yes*H0*3*v1*H1*42
  11862. -->
  11863. (S1 ^operator O1967 = 0.1664311307472832)
  11864. Firing prefer*rvt*predict-no*H0
  11865. -->
  11866. Firing rl*prefer*rvt*predict-no*H0*4
  11867. -->
  11868. (S1 ^operator O1968 = 0.4476189814068987)
  11869. Firing prefer*rvt*predict-no*H0*4*v1*H1
  11870. -->
  11871. Firing rl*prefer*rvt*predict-no*H0*4*v1*H1*41
  11872. -->
  11873. (S1 ^operator O1968 = 0.5523783049582921)
  11874. inner elaboration loop at bottom goal.
  11875. Retracting rl*prefer*rvt*predict-no*H0*4
  11876. -->
  11877. (S1 ^operator O1966 = 0.4476189814068987)
  11878. Retracting rl*prefer*rvt*predict-no*H0*4*v1*H1*41
  11879. -->
  11880. (S1 ^operator O1966 = 0.5523783049582921)
  11881. Retracting rl*prefer*rvt*predict-yes*H0*3
  11882. -->
  11883. (S1 ^operator O1965 = 0.1844091715509321)
  11884. Retracting rl*prefer*rvt*predict-yes*H0*3*v1*H1*42
  11885. -->
  11886. (S1 ^operator O1965 = 0.1664311307472832)
  11887. --- END Proposal Phase ---
  11888. --- Decision Phase ---
  11889. RL update rl*prefer*rvt*predict-no*H0*4 0.622533 -0.174914 0.447619 -> 0.622532 -0.174914 0.447619(R,m,v=1,0.927419,0.06786)
  11890. RL update rl*prefer*rvt*predict-no*H0*4*v1*H1*39 0.377469 0.174914 0.552383 -> 0.377468 0.174914 0.552382(R,m,v=1,1,0)
  11891. =>WM: (13789: S1 ^operator O1968)
  11892. 984: O: O1968 (predict-no)
  11893. --- END Decision Phase ---
  11894. --- Application Phase ---
  11895. --- Firing Productions (PE) For State At Depth 1 ---
  11896. --- Inner Elaboration Phase, active level 1 (S1) ---
  11897. Firing apply*operator
  11898. -->
  11899. (I3 ^predict-no N984 + :O )
  11900. Firing apply*operator*complete
  11901. -->
  11902. (I3 ^predict-no N983 - :O )
  11903. inner elaboration loop at bottom goal.
  11904. --- Change Working Memory (PE) ---
  11905. =>WM: (13790: I3 ^predict-no N984)
  11906. <=WM: (13778: N983 ^status complete)
  11907. <=WM: (13777: I3 ^predict-no N983)
  11908. --- Firing Productions (IE) For State At Depth 1 ---
  11909. --- Inner Elaboration Phase, active level 1 (S1) ---
  11910. Firing monitor*world
  11911. -->
  11912. I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
  11913. --- Change Working Memory (IE) ---
  11914. --- END Application Phase ---
  11915. --- Output Phase ---
  11916. ENV: Agent did: predict-no for direction R in state State-B
  11917. In State-B moving R
  11918. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  11919. predict error 0
  11920. dir: dir isU
  11921. --- END Output Phase ---
  11922. \-/--- Input Phase ---
  11923. =>WM: (13794: I2 ^dir U)
  11924. =>WM: (13793: I2 ^reward 1)
  11925. =>WM: (13792: I2 ^see 0)
  11926. =>WM: (13791: N984 ^status complete)
  11927. <=WM: (13781: I2 ^dir R)
  11928. <=WM: (13780: I2 ^reward 1)
  11929. <=WM: (13779: I2 ^see 0)
  11930. =>WM: (13795: I2 ^level-1 R0-root)
  11931. <=WM: (13782: I2 ^level-1 R0-root)
  11932. --- END Input Phase ---
  11933. --- Proposal Phase ---
  11934. --- Inner Elaboration Phase, active level 1 (S1) ---
  11935. Firing elaborate*copy-see-to-output-link
  11936. -->
  11937. (I3 ^see 0 +)
  11938. Firing elaborate*reward*based*on*reward
  11939. -->
  11940. (R988 ^value 1 +)
  11941. (R1 ^reward R988 +)
  11942. Firing propose*predict-yes
  11943. -->
  11944. (O1969 ^name predict-yes +)
  11945. (S1 ^operator O1969 +)
  11946. Firing propose*predict-no
  11947. -->
  11948. (O1970 ^name predict-no +)
  11949. (S1 ^operator O1970 +)
  11950. Firing rl*prefer*rvt*predict-no*H0*6
  11951. -->
  11952. (S1 ^operator O1968 = 0.9999999999999999)
  11953. Firing rl*prefer*rvt*predict-yes*H0*5
  11954. -->
  11955. (S1 ^operator O1967 = 0.)
  11956. Firing prefer*rvt*predict-yes*H0
  11957. -->
  11958. Firing prefer*rvt*predict-no*H0
  11959. -->
  11960. Firing elaborate*copy-dir-to-output-link
  11961. -->
  11962. (I3 ^dir U +)
  11963. inner elaboration loop at bottom goal.
  11964. Retracting elaborate*copy-see-to-output-link
  11965. -->
  11966. (I3 ^see 0 +)
  11967. Retracting propose*predict-no
  11968. -->
  11969. (O1968 ^name predict-no +)
  11970. (S1 ^operator O1968 +)
  11971. Retracting propose*predict-yes
  11972. -->
  11973. (O1967 ^name predict-yes +)
  11974. (S1 ^operator O1967 +)
  11975. Retracting elaborate*reward*based*on*reward
  11976. -->
  11977. (R987 ^value 1 +)
  11978. (R1 ^reward R987 +)
  11979. Retracting elaborate*copy-dir-to-output-link
  11980. -->
  11981. (I3 ^dir R +)
  11982. Retracting rl*prefer*rvt*predict-no*H0*4*v1*H1*41
  11983. -->
  11984. (S1 ^operator O1968 = 0.5523783049582921)
  11985. Retracting rl*prefer*rvt*predict-no*H0*4
  11986. -->
  11987. (S1 ^operator O1968 = 0.4476187582821546)
  11988. Retracting rl*prefer*rvt*predict-yes*H0*3*v1*H1*42
  11989. -->
  11990. (S1 ^operator O1967 = 0.1664311307472832)
  11991. Retracting rl*prefer*rvt*predict-yes*H0*3
  11992. -->
  11993. (S1 ^operator O1967 = 0.1844091715509321)
  11994. =>WM: (13802: S1 ^operator O1970 +)
  11995. =>WM: (13801: S1 ^operator O1969 +)
  11996. =>WM: (13800: I3 ^dir U)
  11997. =>WM: (13799: O1970 ^name predict-no)
  11998. =>WM: (13798: O1969 ^name predict-yes)
  11999. =>WM: (13797: R988 ^value 1)
  12000. =>WM: (13796: R1 ^reward R988)
  12001. <=WM: (13787: S1 ^operator O1967 +)
  12002. <=WM: (13788: S1 ^operator O1968 +)
  12003. <=WM: (13789: S1 ^operator O1968)
  12004. <=WM: (13773: I3 ^dir R)
  12005. <=WM: (13783: R1 ^reward R987)
  12006. <=WM: (13786: O1968 ^name predict-no)
  12007. <=WM: (13785: O1967 ^name predict-yes)
  12008. <=WM: (13784: R987 ^value 1)
  12009. --- Inner Elaboration Phase, active level 1 (S1) ---
  12010. Firing prefer*rvt*predict-yes*H0
  12011. -->
  12012. Firing rl*prefer*rvt*predict-yes*H0*5
  12013. -->
  12014. (S1 ^operator O1969 = 0.)
  12015. Firing prefer*rvt*predict-no*H0
  12016. -->
  12017. Firing rl*prefer*rvt*predict-no*H0*6
  12018. -->
  12019. (S1 ^operator O1970 = 0.9999999999999999)
  12020. inner elaboration loop at bottom goal.
  12021. Retracting rl*prefer*rvt*predict-no*H0*6
  12022. -->
  12023. (S1 ^operator O1968 = 0.9999999999999999)
  12024. Retracting rl*prefer*rvt*predict-yes*H0*5
  12025. -->
  12026. (S1 ^operator O1967 = 0.)
  12027. --- END Proposal Phase ---
  12028. --- Decision Phase ---
  12029. RL update rl*prefer*rvt*predict-no*H0*4 0.622532 -0.174914 0.447619 -> 0.622533 -0.174914 0.447619(R,m,v=1,0.928,0.0673548)
  12030. RL update rl*prefer*rvt*predict-no*H0*4*v1*H1*41 0.377465 0.174913 0.552378 -> 0.377466 0.174913 0.552379(R,m,v=1,1,0)
  12031. =>WM: (13803: S1 ^operator O1970)
  12032. 985: O: O1970 (predict-no)
  12033. --- END Decision Phase ---
  12034. --- Application Phase ---
  12035. --- Firing Productions (PE) For State At Depth 1 ---
  12036. --- Inner Elaboration Phase, active level 1 (S1) ---
  12037. Firing apply*operator
  12038. -->
  12039. (I3 ^predict-no N985 + :O )
  12040. Firing apply*operator*complete
  12041. -->
  12042. (I3 ^predict-no N984 - :O )
  12043. inner elaboration loop at bottom goal.
  12044. --- Change Working Memory (PE) ---
  12045. =>WM: (13804: I3 ^predict-no N985)
  12046. <=WM: (13791: N984 ^status complete)
  12047. <=WM: (13790: I3 ^predict-no N984)
  12048. --- Firing Productions (IE) For State At Depth 1 ---
  12049. --- Inner Elaboration Phase, active level 1 (S1) ---
  12050. Firing monitor*world
  12051. -->
  12052. I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
  12053. --- Change Working Memory (IE) ---
  12054. --- END Application Phase ---
  12055. --- Output Phase ---
  12056. ENV: Agent did: predict-no for direction U in state State-B
  12057. In State-B moving U
  12058. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  12059. predict error 0
  12060. dir: dir isL
  12061. --- END Output Phase ---
  12062. |\-/--- Input Phase ---
  12063. =>WM: (13808: I2 ^dir L)
  12064. =>WM: (13807: I2 ^reward 1)
  12065. =>WM: (13806: I2 ^see 0)
  12066. =>WM: (13805: N985 ^status complete)
  12067. <=WM: (13794: I2 ^dir U)
  12068. <=WM: (13793: I2 ^reward 1)
  12069. <=WM: (13792: I2 ^see 0)
  12070. =>WM: (13809: I2 ^level-1 R0-root)
  12071. <=WM: (13795: I2 ^level-1 R0-root)
  12072. --- END Input Phase ---
  12073. --- Proposal Phase ---
  12074. --- Inner Elaboration Phase, active level 1 (S1) ---
  12075. Firing rl*prefer*rvt*predict-yes*H0*1*v1*H1*44
  12076. -->
  12077. (S1 ^operator O1969 = 0.6104614609336363)
  12078. Firing rl*prefer*rvt*predict-no*H0*2*v1*H1*43
  12079. -->
  12080. (S1 ^operator O1970 = 0.1063475139796038)
  12081. Firing prefer*rvt*predict-no*H0*2*v1*H1
  12082. -->
  12083. Firing prefer*rvt*predict-yes*H0*1*v1*H1
  12084. -->
  12085. Firing elaborate*copy-see-to-output-link
  12086. -->
  12087. (I3 ^see 0 +)
  12088. Firing elaborate*reward*based*on*reward
  12089. -->
  12090. (R989 ^value 1 +)
  12091. (R1 ^reward R989 +)
  12092. Firing propose*predict-yes
  12093. -->
  12094. (O1971 ^name predict-yes +)
  12095. (S1 ^operator O1971 +)
  12096. Firing propose*predict-no
  12097. -->
  12098. (O1972 ^name predict-no +)
  12099. (S1 ^operator O1972 +)
  12100. Firing rl*prefer*rvt*predict-no*H0*2
  12101. -->
  12102. (S1 ^operator O1970 = 0.3873369632550164)
  12103. Firing rl*prefer*rvt*predict-yes*H0*1
  12104. -->
  12105. (S1 ^operator O1969 = 0.389539588642773)
  12106. Firing prefer*rvt*predict-yes*H0
  12107. -->
  12108. Firing prefer*rvt*predict-no*H0
  12109. -->
  12110. Firing elaborate*copy-dir-to-output-link
  12111. -->
  12112. (I3 ^dir L +)
  12113. inner elaboration loop at bottom goal.
  12114. Retracting elaborate*copy-see-to-output-link
  12115. -->
  12116. (I3 ^see 0 +)
  12117. Retracting propose*predict-no
  12118. -->
  12119. (O1970 ^name predict-no +)
  12120. (S1 ^operator O1970 +)
  12121. Retracting propose*predict-yes
  12122. -->
  12123. (O1969 ^name predict-yes +)
  12124. (S1 ^operator O1969 +)
  12125. Retracting elaborate*reward*based*on*reward
  12126. -->
  12127. (R988 ^value 1 +)
  12128. (R1 ^reward R988 +)
  12129. Retracting elaborate*copy-dir-to-output-link
  12130. -->
  12131. (I3 ^dir U +)
  12132. Retracting rl*prefer*rvt*predict-no*H0*6
  12133. -->
  12134. (S1 ^operator O1970 = 0.9999999999999999)
  12135. Retracting rl*prefer*rvt*predict-yes*H0*5
  12136. -->
  12137. (S1 ^operator O1969 = 0.)
  12138. =>WM: (13816: S1 ^operator O1972 +)
  12139. =>WM: (13815: S1 ^operator O1971 +)
  12140. =>WM: (13814: I3 ^dir L)
  12141. =>WM: (13813: O1972 ^name predict-no)
  12142. =>WM: (13812: O1971 ^name predict-yes)
  12143. =>WM: (13811: R989 ^value 1)
  12144. =>WM: (13810: R1 ^reward R989)
  12145. <=WM: (13801: S1 ^operator O1969 +)
  12146. <=WM: (13802: S1 ^operator O1970 +)
  12147. <=WM: (13803: S1 ^operator O1970)
  12148. <=WM: (13800: I3 ^dir U)
  12149. <=WM: (13796: R1 ^reward R988)
  12150. <=WM: (13799: O1970 ^name predict-no)
  12151. <=WM: (13798: O1969 ^name predict-yes)
  12152. <=WM: (13797: R988 ^value 1)
  12153. --- Inner Elaboration Phase, active level 1 (S1) ---
  12154. Firing prefer*rvt*predict-yes*H0
  12155. -->
  12156. Firing rl*prefer*rvt*predict-yes*H0*1*v1*H1*44
  12157. -->
  12158. (S1 ^operator O1971 = 0.6104614609336363)
  12159. Firing rl*prefer*rvt*predict-yes*H0*1
  12160. -->
  12161. (S1 ^operator O1971 = 0.389539588642773)
  12162. Firing prefer*rvt*predict-yes*H0*1*v1*H1
  12163. -->
  12164. Firing prefer*rvt*predict-no*H0
  12165. -->
  12166. Firing rl*prefer*rvt*predict-no*H0*2*v1*H1*43
  12167. -->
  12168. (S1 ^operator O1972 = 0.1063475139796038)
  12169. Firing rl*prefer*rvt*predict-no*H0*2
  12170. -->
  12171. (S1 ^operator O1972 = 0.3873369632550164)
  12172. Firing prefer*rvt*predict-no*H0*2*v1*H1
  12173. -->
  12174. inner elaboration loop at bottom goal.
  12175. Retracting rl*prefer*rvt*predict-no*H0*2
  12176. -->
  12177. (S1 ^operator O1970 = 0.3873369632550164)
  12178. Retracting rl*prefer*rvt*predict-no*H0*2*v1*H1*43
  12179. -->
  12180. (S1 ^operator O1970 = 0.1063475139796038)
  12181. Retracting rl*prefer*rvt*predict-yes*H0*1
  12182. -->
  12183. (S1 ^operator O1969 = 0.389539588642773)
  12184. Retracting rl*prefer*rvt*predict-yes*H0*1*v1*H1*44
  12185. -->
  12186. (S1 ^operator O1969 = 0.6104614609336363)
  12187. --- END Proposal Phase ---
  12188. --- Decision Phase ---
  12189. RL update rl*prefer*rvt*predict-no*H0*6 1 0 1 -> 1 0 1(R,m,v=1,1,0)
  12190. =>WM: (13817: S1 ^operator O1971)
  12191. 986: O: O1971 (predict-yes)
  12192. --- END Decision Phase ---
  12193. --- Application Phase ---
  12194. --- Firing Productions (PE) For State At Depth 1 ---
  12195. --- Inner Elaboration Phase, active level 1 (S1) ---
  12196. Firing apply*operator
  12197. -->
  12198. (I3 ^predict-yes N986 + :O )
  12199. Firing apply*operator*complete
  12200. -->
  12201. (I3 ^predict-no N985 - :O )
  12202. inner elaboration loop at bottom goal.
  12203. --- Change Working Memory (PE) ---
  12204. =>WM: (13818: I3 ^predict-yes N986)
  12205. <=WM: (13805: N985 ^status complete)
  12206. <=WM: (13804: I3 ^predict-no N985)
  12207. --- Firing Productions (IE) For State At Depth 1 ---
  12208. --- Inner Elaboration Phase, active level 1 (S1) ---
  12209. Firing monitor*world
  12210. -->
  12211. I see 1 and I'm going to do: predict-yes inner elaboration loop at bottom goal.
  12212. --- Change Working Memory (IE) ---
  12213. --- END Application Phase ---
  12214. --- Output Phase ---
  12215. ENV: Agent did: predict-yes for direction L in state State-B
  12216. In State-B moving L
  12217. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  12218. predict error 0
  12219. dir: dir isR
  12220. --- END Output Phase ---
  12221. |\---- Input Phase ---
  12222. =>WM: (13822: I2 ^dir R)
  12223. =>WM: (13821: I2 ^reward 1)
  12224. =>WM: (13820: I2 ^see 1)
  12225. =>WM: (13819: N986 ^status complete)
  12226. <=WM: (13808: I2 ^dir L)
  12227. <=WM: (13807: I2 ^reward 1)
  12228. <=WM: (13806: I2 ^see 0)
  12229. =>WM: (13823: I2 ^level-1 L1-root)
  12230. <=WM: (13809: I2 ^level-1 R0-root)
  12231. --- END Input Phase ---
  12232. --- Proposal Phase ---
  12233. --- Inner Elaboration Phase, active level 1 (S1) ---
  12234. Firing rl*prefer*rvt*predict-no*H0*4*v1*H1*45
  12235. -->
  12236. (S1 ^operator O1972 = -0.02155734064455064)
  12237. Firing rl*prefer*rvt*predict-yes*H0*3*v1*H1*46
  12238. -->
  12239. (S1 ^operator O1971 = 0.8155783412803204)
  12240. Firing prefer*rvt*predict-no*H0*4*v1*H1
  12241. -->
  12242. Firing prefer*rvt*predict-yes*H0*3*v1*H1
  12243. -->
  12244. Firing elaborate*copy-see-to-output-link
  12245. -->
  12246. (I3 ^see 1 +)
  12247. Firing elaborate*reward*based*on*reward
  12248. -->
  12249. (R990 ^value 1 +)
  12250. (R1 ^reward R990 +)
  12251. Firing propose*predict-yes
  12252. -->
  12253. (O1973 ^name predict-yes +)
  12254. (S1 ^operator O1973 +)
  12255. Firing propose*predict-no
  12256. -->
  12257. (O1974 ^name predict-no +)
  12258. (S1 ^operator O1974 +)
  12259. Firing rl*prefer*rvt*predict-no*H0*4
  12260. -->
  12261. (S1 ^operator O1972 = 0.4476191987960876)
  12262. Firing rl*prefer*rvt*predict-yes*H0*3
  12263. -->
  12264. (S1 ^operator O1971 = 0.1844091715509321)
  12265. Firing prefer*rvt*predict-yes*H0
  12266. -->
  12267. Firing prefer*rvt*predict-no*H0
  12268. -->
  12269. Firing elaborate*copy-dir-to-output-link
  12270. -->
  12271. (I3 ^dir R +)
  12272. inner elaboration loop at bottom goal.
  12273. Retracting elaborate*copy-see-to-output-link
  12274. -->
  12275. (I3 ^see 0 +)
  12276. Retracting propose*predict-no
  12277. -->
  12278. (O1972 ^name predict-no +)
  12279. (S1 ^operator O1972 +)
  12280. Retracting propose*predict-yes
  12281. -->
  12282. (O1971 ^name predict-yes +)
  12283. (S1 ^operator O1971 +)
  12284. Retracting elaborate*reward*based*on*reward
  12285. -->
  12286. (R989 ^value 1 +)
  12287. (R1 ^reward R989 +)
  12288. Retracting elaborate*copy-dir-to-output-link
  12289. -->
  12290. (I3 ^dir L +)
  12291. Retracting rl*prefer*rvt*predict-no*H0*2
  12292. -->
  12293. (S1 ^operator O1972 = 0.3873369632550164)
  12294. Retracting rl*prefer*rvt*predict-no*H0*2*v1*H1*43
  12295. -->
  12296. (S1 ^operator O1972 = 0.1063475139796038)
  12297. Retracting rl*prefer*rvt*predict-yes*H0*1
  12298. -->
  12299. (S1 ^operator O1971 = 0.389539588642773)
  12300. Retracting rl*prefer*rvt*predict-yes*H0*1*v1*H1*44
  12301. -->
  12302. (S1 ^operator O1971 = 0.6104614609336363)
  12303. =>WM: (13831: S1 ^operator O1974 +)
  12304. =>WM: (13830: S1 ^operator O1973 +)
  12305. =>WM: (13829: I3 ^dir R)
  12306. =>WM: (13828: O1974 ^name predict-no)
  12307. =>WM: (13827: O1973 ^name predict-yes)
  12308. =>WM: (13826: R990 ^value 1)
  12309. =>WM: (13825: R1 ^reward R990)
  12310. =>WM: (13824: I3 ^see 1)
  12311. <=WM: (13815: S1 ^operator O1971 +)
  12312. <=WM: (13817: S1 ^operator O1971)
  12313. <=WM: (13816: S1 ^operator O1972 +)
  12314. <=WM: (13814: I3 ^dir L)
  12315. <=WM: (13810: R1 ^reward R989)
  12316. <=WM: (13742: I3 ^see 0)
  12317. <=WM: (13813: O1972 ^name predict-no)
  12318. <=WM: (13812: O1971 ^name predict-yes)
  12319. <=WM: (13811: R989 ^value 1)
  12320. --- Inner Elaboration Phase, active level 1 (S1) ---
  12321. Firing prefer*rvt*predict-yes*H0
  12322. -->
  12323. Firing rl*prefer*rvt*predict-yes*H0*3
  12324. -->
  12325. (S1 ^operator O1973 = 0.1844091715509321)
  12326. Firing prefer*rvt*predict-yes*H0*3*v1*H1
  12327. -->
  12328. Firing rl*prefer*rvt*predict-yes*H0*3*v1*H1*46
  12329. -->
  12330. (S1 ^operator O1973 = 0.8155783412803204)
  12331. Firing prefer*rvt*predict-no*H0
  12332. -->
  12333. Firing rl*prefer*rvt*predict-no*H0*4
  12334. -->
  12335. (S1 ^operator O1974 = 0.4476191987960876)
  12336. Firing prefer*rvt*predict-no*H0*4*v1*H1
  12337. -->
  12338. Firing rl*prefer*rvt*predict-no*H0*4*v1*H1*45
  12339. -->
  12340. (S1 ^operator O1974 = -0.02155734064455064)
  12341. inner elaboration loop at bottom goal.
  12342. Retracting rl*prefer*rvt*predict-no*H0*4
  12343. -->
  12344. (S1 ^operator O1972 = 0.4476191987960876)
  12345. Retracting rl*prefer*rvt*predict-no*H0*4*v1*H1*45
  12346. -->
  12347. (S1 ^operator O1972 = -0.02155734064455064)
  12348. Retracting rl*prefer*rvt*predict-yes*H0*3
  12349. -->
  12350. (S1 ^operator O1971 = 0.1844091715509321)
  12351. Retracting rl*prefer*rvt*predict-yes*H0*3*v1*H1*46
  12352. -->
  12353. (S1 ^operator O1971 = 0.8155783412803204)
  12354. --- END Proposal Phase ---
  12355. --- Decision Phase ---
  12356. RL update rl*prefer*rvt*predict-yes*H0*1 0.711951 -0.322412 0.38954 -> 0.711951 -0.322412 0.389539(R,m,v=1,0.890244,0.0983091)
  12357. RL update rl*prefer*rvt*predict-yes*H0*1*v1*H1*44 0.288049 0.322413 0.610461 -> 0.288049 0.322412 0.610461(R,m,v=1,1,0)
  12358. =>WM: (13832: S1 ^operator O1973)
  12359. 987: O: O1973 (predict-yes)
  12360. --- END Decision Phase ---
  12361. --- Application Phase ---
  12362. --- Firing Productions (PE) For State At Depth 1 ---
  12363. --- Inner Elaboration Phase, active level 1 (S1) ---
  12364. Firing apply*operator
  12365. -->
  12366. (I3 ^predict-yes N987 + :O )
  12367. Firing apply*operator*complete
  12368. -->
  12369. (I3 ^predict-yes N986 - :O )
  12370. inner elaboration loop at bottom goal.
  12371. --- Change Working Memory (PE) ---
  12372. =>WM: (13833: I3 ^predict-yes N987)
  12373. <=WM: (13819: N986 ^status complete)
  12374. <=WM: (13818: I3 ^predict-yes N986)
  12375. --- Firing Productions (IE) For State At Depth 1 ---
  12376. --- Inner Elaboration Phase, active level 1 (S1) ---
  12377. Firing monitor*world
  12378. -->
  12379. I see 1 and I'm going to do: predict-yes inner elaboration loop at bottom goal.
  12380. --- Change Working Memory (IE) ---
  12381. --- END Application Phase ---
  12382. --- Output Phase ---
  12383. ENV: Agent did: predict-yes for direction R in state State-A
  12384. In State-A moving R
  12385. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  12386. predict error 0
  12387. dir: dir isR
  12388. --- END Output Phase ---
  12389. /|--- Input Phase ---
  12390. =>WM: (13837: I2 ^dir R)
  12391. =>WM: (13836: I2 ^reward 1)
  12392. =>WM: (13835: I2 ^see 1)
  12393. =>WM: (13834: N987 ^status complete)
  12394. <=WM: (13822: I2 ^dir R)
  12395. <=WM: (13821: I2 ^reward 1)
  12396. <=WM: (13820: I2 ^see 1)
  12397. =>WM: (13838: I2 ^level-1 R1-root)
  12398. <=WM: (13823: I2 ^level-1 L1-root)
  12399. --- END Input Phase ---
  12400. --- Proposal Phase ---
  12401. --- Inner Elaboration Phase, active level 1 (S1) ---
  12402. Firing rl*prefer*rvt*predict-yes*H0*3*v1*H1*40
  12403. -->
  12404. (S1 ^operator O1973 = 0.1398795999120246)
  12405. Firing rl*prefer*rvt*predict-no*H0*4*v1*H1*39
  12406. -->
  12407. (S1 ^operator O1974 = 0.552382282966651)
  12408. Firing prefer*rvt*predict-no*H0*4*v1*H1
  12409. -->
  12410. Firing prefer*rvt*predict-yes*H0*3*v1*H1
  12411. -->
  12412. Firing elaborate*copy-see-to-output-link
  12413. -->
  12414. (I3 ^see 1 +)
  12415. Firing elaborate*reward*based*on*reward
  12416. -->
  12417. (R991 ^value 1 +)
  12418. (R1 ^reward R991 +)
  12419. Firing propose*predict-yes
  12420. -->
  12421. (O1975 ^name predict-yes +)
  12422. (S1 ^operator O1975 +)
  12423. Firing propose*predict-no
  12424. -->
  12425. (O1976 ^name predict-no +)
  12426. (S1 ^operator O1976 +)
  12427. Firing rl*prefer*rvt*predict-no*H0*4
  12428. -->
  12429. (S1 ^operator O1974 = 0.4476191987960876)
  12430. Firing rl*prefer*rvt*predict-yes*H0*3
  12431. -->
  12432. (S1 ^operator O1973 = 0.1844091715509321)
  12433. Firing prefer*rvt*predict-yes*H0
  12434. -->
  12435. Firing prefer*rvt*predict-no*H0
  12436. -->
  12437. Firing elaborate*copy-dir-to-output-link
  12438. -->
  12439. (I3 ^dir R +)
  12440. inner elaboration loop at bottom goal.
  12441. Retracting elaborate*copy-see-to-output-link
  12442. -->
  12443. (I3 ^see 1 +)
  12444. Retracting propose*predict-no
  12445. -->
  12446. (O1974 ^name predict-no +)
  12447. (S1 ^operator O1974 +)
  12448. Retracting propose*predict-yes
  12449. -->
  12450. (O1973 ^name predict-yes +)
  12451. (S1 ^operator O1973 +)
  12452. Retracting elaborate*reward*based*on*reward
  12453. -->
  12454. (R990 ^value 1 +)
  12455. (R1 ^reward R990 +)
  12456. Retracting elaborate*copy-dir-to-output-link
  12457. -->
  12458. (I3 ^dir R +)
  12459. Retracting rl*prefer*rvt*predict-no*H0*4*v1*H1*45
  12460. -->
  12461. (S1 ^operator O1974 = -0.02155734064455064)
  12462. Retracting rl*prefer*rvt*predict-no*H0*4
  12463. -->
  12464. (S1 ^operator O1974 = 0.4476191987960876)
  12465. Retracting rl*prefer*rvt*predict-yes*H0*3*v1*H1*46
  12466. -->
  12467. (S1 ^operator O1973 = 0.8155783412803204)
  12468. Retracting rl*prefer*rvt*predict-yes*H0*3
  12469. -->
  12470. (S1 ^operator O1973 = 0.1844091715509321)
  12471. =>WM: (13844: S1 ^operator O1976 +)
  12472. =>WM: (13843: S1 ^operator O1975 +)
  12473. =>WM: (13842: O1976 ^name predict-no)
  12474. =>WM: (13841: O1975 ^name predict-yes)
  12475. =>WM: (13840: R991 ^value 1)
  12476. =>WM: (13839: R1 ^reward R991)
  12477. <=WM: (13830: S1 ^operator O1973 +)
  12478. <=WM: (13832: S1 ^operator O1973)
  12479. <=WM: (13831: S1 ^operator O1974 +)
  12480. <=WM: (13825: R1 ^reward R990)
  12481. <=WM: (13828: O1974 ^name predict-no)
  12482. <=WM: (13827: O1973 ^name predict-yes)
  12483. <=WM: (13826: R990 ^value 1)
  12484. --- Inner Elaboration Phase, active level 1 (S1) ---
  12485. Firing prefer*rvt*predict-yes*H0
  12486. -->
  12487. Firing rl*prefer*rvt*predict-yes*H0*3
  12488. -->
  12489. (S1 ^operator O1975 = 0.1844091715509321)
  12490. Firing prefer*rvt*predict-yes*H0*3*v1*H1
  12491. -->
  12492. Firing rl*prefer*rvt*predict-yes*H0*3*v1*H1*40
  12493. -->
  12494. (S1 ^operator O1975 = 0.1398795999120246)
  12495. Firing prefer*rvt*predict-no*H0
  12496. -->
  12497. Firing rl*prefer*rvt*predict-no*H0*4
  12498. -->
  12499. (S1 ^operator O1976 = 0.4476191987960876)
  12500. Firing prefer*rvt*predict-no*H0*4*v1*H1
  12501. -->
  12502. Firing rl*prefer*rvt*predict-no*H0*4*v1*H1*39
  12503. -->
  12504. (S1 ^operator O1976 = 0.552382282966651)
  12505. inner elaboration loop at bottom goal.
  12506. Retracting rl*prefer*rvt*predict-no*H0*4
  12507. -->
  12508. (S1 ^operator O1974 = 0.4476191987960876)
  12509. Retracting rl*prefer*rvt*predict-no*H0*4*v1*H1*39
  12510. -->
  12511. (S1 ^operator O1974 = 0.552382282966651)
  12512. Retracting rl*prefer*rvt*predict-yes*H0*3
  12513. -->
  12514. (S1 ^operator O1973 = 0.1844091715509321)
  12515. Retracting rl*prefer*rvt*predict-yes*H0*3*v1*H1*40
  12516. -->
  12517. (S1 ^operator O1973 = 0.1398795999120246)
  12518. --- END Proposal Phase ---
  12519. --- Decision Phase ---
  12520. RL update rl*prefer*rvt*predict-yes*H0*3 0.675411 -0.491002 0.184409 -> 0.675414 -0.491003 0.184411(R,m,v=1,0.898204,0.0919847)
  12521. RL update rl*prefer*rvt*predict-yes*H0*3*v1*H1*46 0.324573 0.491006 0.815578 -> 0.324575 0.491005 0.81558(R,m,v=1,1,0)
  12522. =>WM: (13845: S1 ^operator O1976)
  12523. 988: O: O1976 (predict-no)
  12524. --- END Decision Phase ---
  12525. --- Application Phase ---
  12526. --- Firing Productions (PE) For State At Depth 1 ---
  12527. --- Inner Elaboration Phase, active level 1 (S1) ---
  12528. Firing apply*operator
  12529. -->
  12530. (I3 ^predict-no N988 + :O )
  12531. Firing apply*operator*complete
  12532. -->
  12533. (I3 ^predict-yes N987 - :O )
  12534. inner elaboration loop at bottom goal.
  12535. --- Change Working Memory (PE) ---
  12536. =>WM: (13846: I3 ^predict-no N988)
  12537. <=WM: (13834: N987 ^status complete)
  12538. <=WM: (13833: I3 ^predict-yes N987)
  12539. --- Firing Productions (IE) For State At Depth 1 ---
  12540. --- Inner Elaboration Phase, active level 1 (S1) ---
  12541. Firing monitor*world
  12542. -->
  12543. I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
  12544. --- Change Working Memory (IE) ---
  12545. --- END Application Phase ---
  12546. --- Output Phase ---
  12547. ENV: Agent did: predict-no for direction R in state State-B
  12548. In State-B moving R
  12549. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  12550. predict error 0
  12551. dir: dir isR
  12552. --- END Output Phase ---
  12553. \---- Input Phase ---
  12554. =>WM: (13850: I2 ^dir R)
  12555. =>WM: (13849: I2 ^reward 1)
  12556. =>WM: (13848: I2 ^see 0)
  12557. =>WM: (13847: N988 ^status complete)
  12558. <=WM: (13837: I2 ^dir R)
  12559. <=WM: (13836: I2 ^reward 1)
  12560. <=WM: (13835: I2 ^see 1)
  12561. =>WM: (13851: I2 ^level-1 R0-root)
  12562. <=WM: (13838: I2 ^level-1 R1-root)
  12563. --- END Input Phase ---
  12564. --- Proposal Phase ---
  12565. --- Inner Elaboration Phase, active level 1 (S1) ---
  12566. Firing rl*prefer*rvt*predict-yes*H0*3*v1*H1*42
  12567. -->
  12568. (S1 ^operator O1975 = 0.1664311307472832)
  12569. Firing rl*prefer*rvt*predict-no*H0*4*v1*H1*41
  12570. -->
  12571. (S1 ^operator O1976 = 0.5523787454722251)
  12572. Firing prefer*rvt*predict-no*H0*4*v1*H1
  12573. -->
  12574. Firing prefer*rvt*predict-yes*H0*3*v1*H1
  12575. -->
  12576. Firing elaborate*copy-see-to-output-link
  12577. -->
  12578. (I3 ^see 0 +)
  12579. Firing elaborate*reward*based*on*reward
  12580. -->
  12581. (R992 ^value 1 +)
  12582. (R1 ^reward R992 +)
  12583. Firing propose*predict-yes
  12584. -->
  12585. (O1977 ^name predict-yes +)
  12586. (S1 ^operator O1977 +)
  12587. Firing propose*predict-no
  12588. -->
  12589. (O1978 ^name predict-no +)
  12590. (S1 ^operator O1978 +)
  12591. Firing rl*prefer*rvt*predict-no*H0*4
  12592. -->
  12593. (S1 ^operator O1976 = 0.4476191987960876)
  12594. Firing rl*prefer*rvt*predict-yes*H0*3
  12595. -->
  12596. (S1 ^operator O1975 = 0.1844110446262441)
  12597. Firing prefer*rvt*predict-yes*H0
  12598. -->
  12599. Firing prefer*rvt*predict-no*H0
  12600. -->
  12601. Firing elaborate*copy-dir-to-output-link
  12602. -->
  12603. (I3 ^dir R +)
  12604. inner elaboration loop at bottom goal.
  12605. Retracting elaborate*copy-see-to-output-link
  12606. -->
  12607. (I3 ^see 1 +)
  12608. Retracting propose*predict-no
  12609. -->
  12610. (O1976 ^name predict-no +)
  12611. (S1 ^operator O1976 +)
  12612. Retracting propose*predict-yes
  12613. -->
  12614. (O1975 ^name predict-yes +)
  12615. (S1 ^operator O1975 +)
  12616. Retracting elaborate*reward*based*on*reward
  12617. -->
  12618. (R991 ^value 1 +)
  12619. (R1 ^reward R991 +)
  12620. Retracting elaborate*copy-dir-to-output-link
  12621. -->
  12622. (I3 ^dir R +)
  12623. Retracting rl*prefer*rvt*predict-no*H0*4*v1*H1*39
  12624. -->
  12625. (S1 ^operator O1976 = 0.552382282966651)
  12626. Retracting rl*prefer*rvt*predict-no*H0*4
  12627. -->
  12628. (S1 ^operator O1976 = 0.4476191987960876)
  12629. Retracting rl*prefer*rvt*predict-yes*H0*3*v1*H1*40
  12630. -->
  12631. (S1 ^operator O1975 = 0.1398795999120246)
  12632. Retracting rl*prefer*rvt*predict-yes*H0*3
  12633. -->
  12634. (S1 ^operator O1975 = 0.1844110446262441)
  12635. =>WM: (13858: S1 ^operator O1978 +)
  12636. =>WM: (13857: S1 ^operator O1977 +)
  12637. =>WM: (13856: O1978 ^name predict-no)
  12638. =>WM: (13855: O1977 ^name predict-yes)
  12639. =>WM: (13854: R992 ^value 1)
  12640. =>WM: (13853: R1 ^reward R992)
  12641. =>WM: (13852: I3 ^see 0)
  12642. <=WM: (13843: S1 ^operator O1975 +)
  12643. <=WM: (13844: S1 ^operator O1976 +)
  12644. <=WM: (13845: S1 ^operator O1976)
  12645. <=WM: (13839: R1 ^reward R991)
  12646. <=WM: (13824: I3 ^see 1)
  12647. <=WM: (13842: O1976 ^name predict-no)
  12648. <=WM: (13841: O1975 ^name predict-yes)
  12649. <=WM: (13840: R991 ^value 1)
  12650. --- Inner Elaboration Phase, active level 1 (S1) ---
  12651. Firing prefer*rvt*predict-yes*H0
  12652. -->
  12653. Firing rl*prefer*rvt*predict-yes*H0*3
  12654. -->
  12655. (S1 ^operator O1977 = 0.1844110446262441)
  12656. Firing prefer*rvt*predict-yes*H0*3*v1*H1
  12657. -->
  12658. Firing rl*prefer*rvt*predict-yes*H0*3*v1*H1*42
  12659. -->
  12660. (S1 ^operator O1977 = 0.1664311307472832)
  12661. Firing prefer*rvt*predict-no*H0
  12662. -->
  12663. Firing rl*prefer*rvt*predict-no*H0*4
  12664. -->
  12665. (S1 ^operator O1978 = 0.4476191987960876)
  12666. Firing prefer*rvt*predict-no*H0*4*v1*H1
  12667. -->
  12668. Firing rl*prefer*rvt*predict-no*H0*4*v1*H1*41
  12669. -->
  12670. (S1 ^operator O1978 = 0.5523787454722251)
  12671. inner elaboration loop at bottom goal.
  12672. Retracting rl*prefer*rvt*predict-no*H0*4
  12673. -->
  12674. (S1 ^operator O1976 = 0.4476191987960876)
  12675. Retracting rl*prefer*rvt*predict-no*H0*4*v1*H1*41
  12676. -->
  12677. (S1 ^operator O1976 = 0.5523787454722251)
  12678. Retracting rl*prefer*rvt*predict-yes*H0*3
  12679. -->
  12680. (S1 ^operator O1975 = 0.1844110446262441)
  12681. Retracting rl*prefer*rvt*predict-yes*H0*3*v1*H1*42
  12682. -->
  12683. (S1 ^operator O1975 = 0.1664311307472832)
  12684. --- END Proposal Phase ---
  12685. --- Decision Phase ---
  12686. RL update rl*prefer*rvt*predict-no*H0*4 0.622533 -0.174914 0.447619 -> 0.622533 -0.174914 0.447619(R,m,v=1,0.928571,0.0668571)
  12687. RL update rl*prefer*rvt*predict-no*H0*4*v1*H1*39 0.377468 0.174914 0.552382 -> 0.377468 0.174914 0.552382(R,m,v=1,1,0)
  12688. =>WM: (13859: S1 ^operator O1978)
  12689. 989: O: O1978 (predict-no)
  12690. --- END Decision Phase ---
  12691. --- Application Phase ---
  12692. --- Firing Productions (PE) For State At Depth 1 ---
  12693. --- Inner Elaboration Phase, active level 1 (S1) ---
  12694. Firing apply*operator
  12695. -->
  12696. (I3 ^predict-no N989 + :O )
  12697. Firing apply*operator*complete
  12698. -->
  12699. (I3 ^predict-no N988 - :O )
  12700. inner elaboration loop at bottom goal.
  12701. --- Change Working Memory (PE) ---
  12702. =>WM: (13860: I3 ^predict-no N989)
  12703. <=WM: (13847: N988 ^status complete)
  12704. <=WM: (13846: I3 ^predict-no N988)
  12705. --- Firing Productions (IE) For State At Depth 1 ---
  12706. --- Inner Elaboration Phase, active level 1 (S1) ---
  12707. Firing monitor*world
  12708. -->
  12709. I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
  12710. --- Change Working Memory (IE) ---
  12711. --- END Application Phase ---
  12712. --- Output Phase ---
  12713. ENV: Agent did: predict-no for direction R in state State-B
  12714. In State-B moving R
  12715. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  12716. predict error 0
  12717. dir: dir isR
  12718. --- END Output Phase ---
  12719. /|\--- Input Phase ---
  12720. =>WM: (13864: I2 ^dir R)
  12721. =>WM: (13863: I2 ^reward 1)
  12722. =>WM: (13862: I2 ^see 0)
  12723. =>WM: (13861: N989 ^status complete)
  12724. <=WM: (13850: I2 ^dir R)
  12725. <=WM: (13849: I2 ^reward 1)
  12726. <=WM: (13848: I2 ^see 0)
  12727. =>WM: (13865: I2 ^level-1 R0-root)
  12728. <=WM: (13851: I2 ^level-1 R0-root)
  12729. --- END Input Phase ---
  12730. --- Proposal Phase ---
  12731. --- Inner Elaboration Phase, active level 1 (S1) ---
  12732. Firing rl*prefer*rvt*predict-yes*H0*3*v1*H1*42
  12733. -->
  12734. (S1 ^operator O1977 = 0.1664311307472832)
  12735. Firing rl*prefer*rvt*predict-no*H0*4*v1*H1*41
  12736. -->
  12737. (S1 ^operator O1978 = 0.5523787454722251)
  12738. Firing prefer*rvt*predict-no*H0*4*v1*H1
  12739. -->
  12740. Firing prefer*rvt*predict-yes*H0*3*v1*H1
  12741. -->
  12742. Firing elaborate*copy-see-to-output-link
  12743. -->
  12744. (I3 ^see 0 +)
  12745. Firing elaborate*reward*based*on*reward
  12746. -->
  12747. (R993 ^value 1 +)
  12748. (R1 ^reward R993 +)
  12749. Firing propose*predict-yes
  12750. -->
  12751. (O1979 ^name predict-yes +)
  12752. (S1 ^operator O1979 +)
  12753. Firing propose*predict-no
  12754. -->
  12755. (O1980 ^name predict-no +)
  12756. (S1 ^operator O1980 +)
  12757. Firing rl*prefer*rvt*predict-no*H0*4
  12758. -->
  12759. (S1 ^operator O1978 = 0.4476189765316768)
  12760. Firing rl*prefer*rvt*predict-yes*H0*3
  12761. -->
  12762. (S1 ^operator O1977 = 0.1844110446262441)
  12763. Firing prefer*rvt*predict-yes*H0
  12764. -->
  12765. Firing prefer*rvt*predict-no*H0
  12766. -->
  12767. Firing elaborate*copy-dir-to-output-link
  12768. -->
  12769. (I3 ^dir R +)
  12770. inner elaboration loop at bottom goal.
  12771. Retracting elaborate*copy-see-to-output-link
  12772. -->
  12773. (I3 ^see 0 +)
  12774. Retracting propose*predict-no
  12775. -->
  12776. (O1978 ^name predict-no +)
  12777. (S1 ^operator O1978 +)
  12778. Retracting propose*predict-yes
  12779. -->
  12780. (O1977 ^name predict-yes +)
  12781. (S1 ^operator O1977 +)
  12782. Retracting elaborate*reward*based*on*reward
  12783. -->
  12784. (R992 ^value 1 +)
  12785. (R1 ^reward R992 +)
  12786. Retracting elaborate*copy-dir-to-output-link
  12787. -->
  12788. (I3 ^dir R +)
  12789. Retracting rl*prefer*rvt*predict-no*H0*4*v1*H1*41
  12790. -->
  12791. (S1 ^operator O1978 = 0.5523787454722251)
  12792. Retracting rl*prefer*rvt*predict-no*H0*4
  12793. -->
  12794. (S1 ^operator O1978 = 0.4476189765316768)
  12795. Retracting rl*prefer*rvt*predict-yes*H0*3*v1*H1*42
  12796. -->
  12797. (S1 ^operator O1977 = 0.1664311307472832)
  12798. Retracting rl*prefer*rvt*predict-yes*H0*3
  12799. -->
  12800. (S1 ^operator O1977 = 0.1844110446262441)
  12801. =>WM: (13871: S1 ^operator O1980 +)
  12802. =>WM: (13870: S1 ^operator O1979 +)
  12803. =>WM: (13869: O1980 ^name predict-no)
  12804. =>WM: (13868: O1979 ^name predict-yes)
  12805. =>WM: (13867: R993 ^value 1)
  12806. =>WM: (13866: R1 ^reward R993)
  12807. <=WM: (13857: S1 ^operator O1977 +)
  12808. <=WM: (13858: S1 ^operator O1978 +)
  12809. <=WM: (13859: S1 ^operator O1978)
  12810. <=WM: (13853: R1 ^reward R992)
  12811. <=WM: (13856: O1978 ^name predict-no)
  12812. <=WM: (13855: O1977 ^name predict-yes)
  12813. <=WM: (13854: R992 ^value 1)
  12814. --- Inner Elaboration Phase, active level 1 (S1) ---
  12815. Firing prefer*rvt*predict-yes*H0
  12816. -->
  12817. Firing rl*prefer*rvt*predict-yes*H0*3
  12818. -->
  12819. (S1 ^operator O1979 = 0.1844110446262441)
  12820. Firing prefer*rvt*predict-yes*H0*3*v1*H1
  12821. -->
  12822. Firing rl*prefer*rvt*predict-yes*H0*3*v1*H1*42
  12823. -->
  12824. (S1 ^operator O1979 = 0.1664311307472832)
  12825. Firing prefer*rvt*predict-no*H0
  12826. -->
  12827. Firing rl*prefer*rvt*predict-no*H0*4
  12828. -->
  12829. (S1 ^operator O1980 = 0.4476189765316768)
  12830. Firing prefer*rvt*predict-no*H0*4*v1*H1
  12831. -->
  12832. Firing rl*prefer*rvt*predict-no*H0*4*v1*H1*41
  12833. -->
  12834. (S1 ^operator O1980 = 0.5523787454722251)
  12835. inner elaboration loop at bottom goal.
  12836. Retracting rl*prefer*rvt*predict-no*H0*4
  12837. -->
  12838. (S1 ^operator O1978 = 0.4476189765316768)
  12839. Retracting rl*prefer*rvt*predict-no*H0*4*v1*H1*41
  12840. -->
  12841. (S1 ^operator O1978 = 0.5523787454722251)
  12842. Retracting rl*prefer*rvt*predict-yes*H0*3
  12843. -->
  12844. (S1 ^operator O1977 = 0.1844110446262441)
  12845. Retracting rl*prefer*rvt*predict-yes*H0*3*v1*H1*42
  12846. -->
  12847. (S1 ^operator O1977 = 0.1664311307472832)
  12848. --- END Proposal Phase ---
  12849. --- Decision Phase ---
  12850. RL update rl*prefer*rvt*predict-no*H0*4 0.622533 -0.174914 0.447619 -> 0.622533 -0.174914 0.447619(R,m,v=1,0.929134,0.0663667)
  12851. RL update rl*prefer*rvt*predict-no*H0*4*v1*H1*41 0.377466 0.174913 0.552379 -> 0.377466 0.174913 0.552379(R,m,v=1,1,0)
  12852. =>WM: (13872: S1 ^operator O1980)
  12853. 990: O: O1980 (predict-no)
  12854. --- END Decision Phase ---
  12855. --- Application Phase ---
  12856. --- Firing Productions (PE) For State At Depth 1 ---
  12857. --- Inner Elaboration Phase, active level 1 (S1) ---
  12858. Firing apply*operator
  12859. -->
  12860. (I3 ^predict-no N990 + :O )
  12861. Firing apply*operator*complete
  12862. -->
  12863. (I3 ^predict-no N989 - :O )
  12864. inner elaboration loop at bottom goal.
  12865. --- Change Working Memory (PE) ---
  12866. =>WM: (13873: I3 ^predict-no N990)
  12867. <=WM: (13861: N989 ^status complete)
  12868. <=WM: (13860: I3 ^predict-no N989)
  12869. --- Firing Productions (IE) For State At Depth 1 ---
  12870. --- Inner Elaboration Phase, active level 1 (S1) ---
  12871. Firing monitor*world
  12872. -->
  12873. I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
  12874. --- Change Working Memory (IE) ---
  12875. --- END Application Phase ---
  12876. --- Output Phase ---
  12877. ENV: Agent did: predict-no for direction R in state State-B
  12878. In State-B moving R
  12879. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  12880. predict error 0
  12881. dir: dir isL
  12882. --- END Output Phase ---
  12883. -/|\--- Input Phase ---
  12884. =>WM: (13877: I2 ^dir L)
  12885. =>WM: (13876: I2 ^reward 1)
  12886. =>WM: (13875: I2 ^see 0)
  12887. =>WM: (13874: N990 ^status complete)
  12888. <=WM: (13864: I2 ^dir R)
  12889. <=WM: (13863: I2 ^reward 1)
  12890. <=WM: (13862: I2 ^see 0)
  12891. =>WM: (13878: I2 ^level-1 R0-root)
  12892. <=WM: (13865: I2 ^level-1 R0-root)
  12893. --- END Input Phase ---
  12894. --- Proposal Phase ---
  12895. --- Inner Elaboration Phase, active level 1 (S1) ---
  12896. Firing rl*prefer*rvt*predict-yes*H0*1*v1*H1*44
  12897. -->
  12898. (S1 ^operator O1979 = 0.6104613034971749)
  12899. Firing rl*prefer*rvt*predict-no*H0*2*v1*H1*43
  12900. -->
  12901. (S1 ^operator O1980 = 0.1063475139796038)
  12902. Firing prefer*rvt*predict-no*H0*2*v1*H1
  12903. -->
  12904. Firing prefer*rvt*predict-yes*H0*1*v1*H1
  12905. -->
  12906. Firing elaborate*copy-see-to-output-link
  12907. -->
  12908. (I3 ^see 0 +)
  12909. Firing elaborate*reward*based*on*reward
  12910. -->
  12911. (R994 ^value 1 +)
  12912. (R1 ^reward R994 +)
  12913. Firing propose*predict-yes
  12914. -->
  12915. (O1981 ^name predict-yes +)
  12916. (S1 ^operator O1981 +)
  12917. Firing propose*predict-no
  12918. -->
  12919. (O1982 ^name predict-no +)
  12920. (S1 ^operator O1982 +)
  12921. Firing rl*prefer*rvt*predict-no*H0*2
  12922. -->
  12923. (S1 ^operator O1980 = 0.3873369632550164)
  12924. Firing rl*prefer*rvt*predict-yes*H0*1
  12925. -->
  12926. (S1 ^operator O1979 = 0.3895394312063116)
  12927. Firing prefer*rvt*predict-yes*H0
  12928. -->
  12929. Firing prefer*rvt*predict-no*H0
  12930. -->
  12931. Firing elaborate*copy-dir-to-output-link
  12932. -->
  12933. (I3 ^dir L +)
  12934. inner elaboration loop at bottom goal.
  12935. Retracting elaborate*copy-see-to-output-link
  12936. -->
  12937. (I3 ^see 0 +)
  12938. Retracting propose*predict-no
  12939. -->
  12940. (O1980 ^name predict-no +)
  12941. (S1 ^operator O1980 +)
  12942. Retracting propose*predict-yes
  12943. -->
  12944. (O1979 ^name predict-yes +)
  12945. (S1 ^operator O1979 +)
  12946. Retracting elaborate*reward*based*on*reward
  12947. -->
  12948. (R993 ^value 1 +)
  12949. (R1 ^reward R993 +)
  12950. Retracting elaborate*copy-dir-to-output-link
  12951. -->
  12952. (I3 ^dir R +)
  12953. Retracting rl*prefer*rvt*predict-no*H0*4*v1*H1*41
  12954. -->
  12955. (S1 ^operator O1980 = 0.5523790871716397)
  12956. Retracting rl*prefer*rvt*predict-no*H0*4
  12957. -->
  12958. (S1 ^operator O1980 = 0.4476193182310915)
  12959. Retracting rl*prefer*rvt*predict-yes*H0*3*v1*H1*42
  12960. -->
  12961. (S1 ^operator O1979 = 0.1664311307472832)
  12962. Retracting rl*prefer*rvt*predict-yes*H0*3
  12963. -->
  12964. (S1 ^operator O1979 = 0.1844110446262441)
  12965. =>WM: (13885: S1 ^operator O1982 +)
  12966. =>WM: (13884: S1 ^operator O1981 +)
  12967. =>WM: (13883: I3 ^dir L)
  12968. =>WM: (13882: O1982 ^name predict-no)
  12969. =>WM: (13881: O1981 ^name predict-yes)
  12970. =>WM: (13880: R994 ^value 1)
  12971. =>WM: (13879: R1 ^reward R994)
  12972. <=WM: (13870: S1 ^operator O1979 +)
  12973. <=WM: (13871: S1 ^operator O1980 +)
  12974. <=WM: (13872: S1 ^operator O1980)
  12975. <=WM: (13829: I3 ^dir R)
  12976. <=WM: (13866: R1 ^reward R993)
  12977. <=WM: (13869: O1980 ^name predict-no)
  12978. <=WM: (13868: O1979 ^name predict-yes)
  12979. <=WM: (13867: R993 ^value 1)
  12980. --- Inner Elaboration Phase, active level 1 (S1) ---
  12981. Firing prefer*rvt*predict-yes*H0
  12982. -->
  12983. Firing rl*prefer*rvt*predict-yes*H0*1*v1*H1*44
  12984. -->
  12985. (S1 ^operator O1981 = 0.6104613034971749)
  12986. Firing rl*prefer*rvt*predict-yes*H0*1
  12987. -->
  12988. (S1 ^operator O1981 = 0.3895394312063116)
  12989. Firing prefer*rvt*predict-yes*H0*1*v1*H1
  12990. -->
  12991. Firing prefer*rvt*predict-no*H0
  12992. -->
  12993. Firing rl*prefer*rvt*predict-no*H0*2*v1*H1*43
  12994. -->
  12995. (S1 ^operator O1982 = 0.1063475139796038)
  12996. Firing rl*prefer*rvt*predict-no*H0*2
  12997. -->
  12998. (S1 ^operator O1982 = 0.3873369632550164)
  12999. Firing prefer*rvt*predict-no*H0*2*v1*H1
  13000. -->
  13001. inner elaboration loop at bottom goal.
  13002. Retracting rl*prefer*rvt*predict-no*H0*2
  13003. -->
  13004. (S1 ^operator O1980 = 0.3873369632550164)
  13005. Retracting rl*prefer*rvt*predict-no*H0*2*v1*H1*43
  13006. -->
  13007. (S1 ^operator O1980 = 0.1063475139796038)
  13008. Retracting rl*prefer*rvt*predict-yes*H0*1
  13009. -->
  13010. (S1 ^operator O1979 = 0.3895394312063116)
  13011. Retracting rl*prefer*rvt*predict-yes*H0*1*v1*H1*44
  13012. -->
  13013. (S1 ^operator O1979 = 0.6104613034971749)
  13014. --- END Proposal Phase ---
  13015. --- Decision Phase ---
  13016. RL update rl*prefer*rvt*predict-no*H0*4 0.622533 -0.174914 0.447619 -> 0.622533 -0.174913 0.44762(R,m,v=1,0.929687,0.0658834)
  13017. RL update rl*prefer*rvt*predict-no*H0*4*v1*H1*41 0.377466 0.174913 0.552379 -> 0.377466 0.174913 0.552379(R,m,v=1,1,0)
  13018. =>WM: (13886: S1 ^operator O1981)
  13019. 991: O: O1981 (predict-yes)
  13020. --- END Decision Phase ---
  13021. --- Application Phase ---
  13022. --- Firing Productions (PE) For State At Depth 1 ---
  13023. --- Inner Elaboration Phase, active level 1 (S1) ---
  13024. Firing apply*operator
  13025. -->
  13026. (I3 ^predict-yes N991 + :O )
  13027. Firing apply*operator*complete
  13028. -->
  13029. (I3 ^predict-no N990 - :O )
  13030. inner elaboration loop at bottom goal.
  13031. --- Change Working Memory (PE) ---
  13032. =>WM: (13887: I3 ^predict-yes N991)
  13033. <=WM: (13874: N990 ^status complete)
  13034. <=WM: (13873: I3 ^predict-no N990)
  13035. --- Firing Productions (IE) For State At Depth 1 ---
  13036. --- Inner Elaboration Phase, active level 1 (S1) ---
  13037. Firing monitor*world
  13038. -->
  13039. I see 1 and I'm going to do: predict-yes inner elaboration loop at bottom goal.
  13040. --- Change Working Memory (IE) ---
  13041. --- END Application Phase ---
  13042. --- Output Phase ---
  13043. ENV: Agent did: predict-yes for direction L in state State-B
  13044. In State-B moving L
  13045. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  13046. predict error 0
  13047. dir: dir isR
  13048. --- END Output Phase ---
  13049. ---- Input Phase ---
  13050. =>WM: (13891: I2 ^dir R)
  13051. =>WM: (13890: I2 ^reward 1)
  13052. =>WM: (13889: I2 ^see 1)
  13053. =>WM: (13888: N991 ^status complete)
  13054. <=WM: (13877: I2 ^dir L)
  13055. <=WM: (13876: I2 ^reward 1)
  13056. <=WM: (13875: I2 ^see 0)
  13057. =>WM: (13892: I2 ^level-1 L1-root)
  13058. <=WM: (13878: I2 ^level-1 R0-root)
  13059. --- END Input Phase ---
  13060. --- Proposal Phase ---
  13061. --- Inner Elaboration Phase, active level 1 (S1) ---
  13062. Firing rl*prefer*rvt*predict-no*H0*4*v1*H1*45
  13063. -->
  13064. (S1 ^operator O1982 = -0.02155734064455064)
  13065. Firing rl*prefer*rvt*predict-yes*H0*3*v1*H1*46
  13066. -->
  13067. (S1 ^operator O1981 = 0.8155802143556325)
  13068. Firing prefer*rvt*predict-no*H0*4*v1*H1
  13069. -->
  13070. Firing prefer*rvt*predict-yes*H0*3*v1*H1
  13071. -->
  13072. Firing elaborate*copy-see-to-output-link
  13073. -->
  13074. (I3 ^see 1 +)
  13075. Firing elaborate*reward*based*on*reward
  13076. -->
  13077. (R995 ^value 1 +)
  13078. (R1 ^reward R995 +)
  13079. Firing propose*predict-yes
  13080. -->
  13081. (O1983 ^name predict-yes +)
  13082. (S1 ^operator O1983 +)
  13083. Firing propose*predict-no
  13084. -->
  13085. (O1984 ^name predict-no +)
  13086. (S1 ^operator O1984 +)
  13087. Firing rl*prefer*rvt*predict-no*H0*4
  13088. -->
  13089. (S1 ^operator O1982 = 0.4476195574206818)
  13090. Firing rl*prefer*rvt*predict-yes*H0*3
  13091. -->
  13092. (S1 ^operator O1981 = 0.1844110446262441)
  13093. Firing prefer*rvt*predict-yes*H0
  13094. -->
  13095. Firing prefer*rvt*predict-no*H0
  13096. -->
  13097. Firing elaborate*copy-dir-to-output-link
  13098. -->
  13099. (I3 ^dir R +)
  13100. inner elaboration loop at bottom goal.
  13101. Retracting elaborate*copy-see-to-output-link
  13102. -->
  13103. (I3 ^see 0 +)
  13104. Retracting propose*predict-no
  13105. -->
  13106. (O1982 ^name predict-no +)
  13107. (S1 ^operator O1982 +)
  13108. Retracting propose*predict-yes
  13109. -->
  13110. (O1981 ^name predict-yes +)
  13111. (S1 ^operator O1981 +)
  13112. Retracting elaborate*reward*based*on*reward
  13113. -->
  13114. (R994 ^value 1 +)
  13115. (R1 ^reward R994 +)
  13116. Retracting elaborate*copy-dir-to-output-link
  13117. -->
  13118. (I3 ^dir L +)
  13119. Retracting rl*prefer*rvt*predict-no*H0*2
  13120. -->
  13121. (S1 ^operator O1982 = 0.3873369632550164)
  13122. Retracting rl*prefer*rvt*predict-no*H0*2*v1*H1*43
  13123. -->
  13124. (S1 ^operator O1982 = 0.1063475139796038)
  13125. Retracting rl*prefer*rvt*predict-yes*H0*1
  13126. -->
  13127. (S1 ^operator O1981 = 0.3895394312063116)
  13128. Retracting rl*prefer*rvt*predict-yes*H0*1*v1*H1*44
  13129. -->
  13130. (S1 ^operator O1981 = 0.6104613034971749)
  13131. =>WM: (13900: S1 ^operator O1984 +)
  13132. =>WM: (13899: S1 ^operator O1983 +)
  13133. =>WM: (13898: I3 ^dir R)
  13134. =>WM: (13897: O1984 ^name predict-no)
  13135. =>WM: (13896: O1983 ^name predict-yes)
  13136. =>WM: (13895: R995 ^value 1)
  13137. =>WM: (13894: R1 ^reward R995)
  13138. =>WM: (13893: I3 ^see 1)
  13139. <=WM: (13884: S1 ^operator O1981 +)
  13140. <=WM: (13886: S1 ^operator O1981)
  13141. <=WM: (13885: S1 ^operator O1982 +)
  13142. <=WM: (13883: I3 ^dir L)
  13143. <=WM: (13879: R1 ^reward R994)
  13144. <=WM: (13852: I3 ^see 0)
  13145. <=WM: (13882: O1982 ^name predict-no)
  13146. <=WM: (13881: O1981 ^name predict-yes)
  13147. <=WM: (13880: R994 ^value 1)
  13148. --- Inner Elaboration Phase, active level 1 (S1) ---
  13149. Firing prefer*rvt*predict-yes*H0
  13150. -->
  13151. Firing rl*prefer*rvt*predict-yes*H0*3
  13152. -->
  13153. (S1 ^operator O1983 = 0.1844110446262441)
  13154. Firing prefer*rvt*predict-yes*H0*3*v1*H1
  13155. -->
  13156. Firing rl*prefer*rvt*predict-yes*H0*3*v1*H1*46
  13157. -->
  13158. (S1 ^operator O1983 = 0.8155802143556325)
  13159. Firing prefer*rvt*predict-no*H0
  13160. -->
  13161. Firing rl*prefer*rvt*predict-no*H0*4
  13162. -->
  13163. (S1 ^operator O1984 = 0.4476195574206818)
  13164. Firing prefer*rvt*predict-no*H0*4*v1*H1
  13165. -->
  13166. Firing rl*prefer*rvt*predict-no*H0*4*v1*H1*45
  13167. -->
  13168. (S1 ^operator O1984 = -0.02155734064455064)
  13169. inner elaboration loop at bottom goal.
  13170. Retracting rl*prefer*rvt*predict-no*H0*4
  13171. -->
  13172. (S1 ^operator O1982 = 0.4476195574206818)
  13173. Retracting rl*prefer*rvt*predict-no*H0*4*v1*H1*45
  13174. -->
  13175. (S1 ^operator O1982 = -0.02155734064455064)
  13176. Retracting rl*prefer*rvt*predict-yes*H0*3
  13177. -->
  13178. (S1 ^operator O1981 = 0.1844110446262441)
  13179. Retracting rl*prefer*rvt*predict-yes*H0*3*v1*H1*46
  13180. -->
  13181. (S1 ^operator O1981 = 0.8155802143556325)
  13182. --- END Proposal Phase ---
  13183. --- Decision Phase ---
  13184. RL update rl*prefer*rvt*predict-yes*H0*1 0.711951 -0.322412 0.389539 -> 0.711951 -0.322412 0.389539(R,m,v=1,0.890909,0.0977827)
  13185. RL update rl*prefer*rvt*predict-yes*H0*1*v1*H1*44 0.288049 0.322412 0.610461 -> 0.288049 0.322412 0.610461(R,m,v=1,1,0)
  13186. =>WM: (13901: S1 ^operator O1983)
  13187. 992: O: O1983 (predict-yes)
  13188. --- END Decision Phase ---
  13189. --- Application Phase ---
  13190. --- Firing Productions (PE) For State At Depth 1 ---
  13191. --- Inner Elaboration Phase, active level 1 (S1) ---
  13192. Firing apply*operator
  13193. -->
  13194. (I3 ^predict-yes N992 + :O )
  13195. Firing apply*operator*complete
  13196. -->
  13197. (I3 ^predict-yes N991 - :O )
  13198. inner elaboration loop at bottom goal.
  13199. --- Change Working Memory (PE) ---
  13200. =>WM: (13902: I3 ^predict-yes N992)
  13201. <=WM: (13888: N991 ^status complete)
  13202. <=WM: (13887: I3 ^predict-yes N991)
  13203. --- Firing Productions (IE) For State At Depth 1 ---
  13204. --- Inner Elaboration Phase, active level 1 (S1) ---
  13205. Firing monitor*world
  13206. -->
  13207. I see 1 and I'm going to do: predict-yes inner elaboration loop at bottom goal.
  13208. --- Change Working Memory (IE) ---
  13209. --- END Application Phase ---
  13210. --- Output Phase ---
  13211. ENV: Agent did: predict-yes for direction R in state State-A
  13212. In State-A moving R
  13213. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  13214. predict error 0
  13215. dir: dir isL
  13216. --- END Output Phase ---
  13217. /|--- Input Phase ---
  13218. =>WM: (13906: I2 ^dir L)
  13219. =>WM: (13905: I2 ^reward 1)
  13220. =>WM: (13904: I2 ^see 1)
  13221. =>WM: (13903: N992 ^status complete)
  13222. <=WM: (13891: I2 ^dir R)
  13223. <=WM: (13890: I2 ^reward 1)
  13224. <=WM: (13889: I2 ^see 1)
  13225. =>WM: (13907: I2 ^level-1 R1-root)
  13226. <=WM: (13892: I2 ^level-1 L1-root)
  13227. --- END Input Phase ---
  13228. --- Proposal Phase ---
  13229. --- Inner Elaboration Phase, active level 1 (S1) ---
  13230. Firing rl*prefer*rvt*predict-yes*H0*1*v1*H1*36
  13231. -->
  13232. (S1 ^operator O1983 = 0.6104592422684716)
  13233. Firing rl*prefer*rvt*predict-no*H0*2*v1*H1*35
  13234. -->
  13235. (S1 ^operator O1984 = 0.2714993082286609)
  13236. Firing prefer*rvt*predict-no*H0*2*v1*H1
  13237. -->
  13238. Firing prefer*rvt*predict-yes*H0*1*v1*H1
  13239. -->
  13240. Firing elaborate*copy-see-to-output-link
  13241. -->
  13242. (I3 ^see 1 +)
  13243. Firing elaborate*reward*based*on*reward
  13244. -->
  13245. (R996 ^value 1 +)
  13246. (R1 ^reward R996 +)
  13247. Firing propose*predict-yes
  13248. -->
  13249. (O1985 ^name predict-yes +)
  13250. (S1 ^operator O1985 +)
  13251. Firing propose*predict-no
  13252. -->
  13253. (O1986 ^name predict-no +)
  13254. (S1 ^operator O1986 +)
  13255. Firing rl*prefer*rvt*predict-no*H0*2
  13256. -->
  13257. (S1 ^operator O1984 = 0.3873369632550164)
  13258. Firing rl*prefer*rvt*predict-yes*H0*1
  13259. -->
  13260. (S1 ^operator O1983 = 0.3895393210007886)
  13261. Firing prefer*rvt*predict-yes*H0
  13262. -->
  13263. Firing prefer*rvt*predict-no*H0
  13264. -->
  13265. Firing elaborate*copy-dir-to-output-link
  13266. -->
  13267. (I3 ^dir L +)
  13268. inner elaboration loop at bottom goal.
  13269. Retracting elaborate*copy-see-to-output-link
  13270. -->
  13271. (I3 ^see 1 +)
  13272. Retracting propose*predict-no
  13273. -->
  13274. (O1984 ^name predict-no +)
  13275. (S1 ^operator O1984 +)
  13276. Retracting propose*predict-yes
  13277. -->
  13278. (O1983 ^name predict-yes +)
  13279. (S1 ^operator O1983 +)
  13280. Retracting elaborate*reward*based*on*reward
  13281. -->
  13282. (R995 ^value 1 +)
  13283. (R1 ^reward R995 +)
  13284. Retracting elaborate*copy-dir-to-output-link
  13285. -->
  13286. (I3 ^dir R +)
  13287. Retracting rl*prefer*rvt*predict-no*H0*4*v1*H1*45
  13288. -->
  13289. (S1 ^operator O1984 = -0.02155734064455064)
  13290. Retracting rl*prefer*rvt*predict-no*H0*4
  13291. -->
  13292. (S1 ^operator O1984 = 0.4476195574206818)
  13293. Retracting rl*prefer*rvt*predict-yes*H0*3*v1*H1*46
  13294. -->
  13295. (S1 ^operator O1983 = 0.8155802143556325)
  13296. Retracting rl*prefer*rvt*predict-yes*H0*3
  13297. -->
  13298. (S1 ^operator O1983 = 0.1844110446262441)
  13299. =>WM: (13914: S1 ^operator O1986 +)
  13300. =>WM: (13913: S1 ^operator O1985 +)
  13301. =>WM: (13912: I3 ^dir L)
  13302. =>WM: (13911: O1986 ^name predict-no)
  13303. =>WM: (13910: O1985 ^name predict-yes)
  13304. =>WM: (13909: R996 ^value 1)
  13305. =>WM: (13908: R1 ^reward R996)
  13306. <=WM: (13899: S1 ^operator O1983 +)
  13307. <=WM: (13901: S1 ^operator O1983)
  13308. <=WM: (13900: S1 ^operator O1984 +)
  13309. <=WM: (13898: I3 ^dir R)
  13310. <=WM: (13894: R1 ^reward R995)
  13311. <=WM: (13897: O1984 ^name predict-no)
  13312. <=WM: (13896: O1983 ^name predict-yes)
  13313. <=WM: (13895: R995 ^value 1)
  13314. --- Inner Elaboration Phase, active level 1 (S1) ---
  13315. Firing prefer*rvt*predict-yes*H0
  13316. -->
  13317. Firing rl*prefer*rvt*predict-yes*H0*1
  13318. -->
  13319. (S1 ^operator O1985 = 0.3895393210007886)
  13320. Firing prefer*rvt*predict-yes*H0*1*v1*H1
  13321. -->
  13322. Firing rl*prefer*rvt*predict-yes*H0*1*v1*H1*36
  13323. -->
  13324. (S1 ^operator O1985 = 0.6104592422684716)
  13325. Firing prefer*rvt*predict-no*H0
  13326. -->
  13327. Firing rl*prefer*rvt*predict-no*H0*2
  13328. -->
  13329. (S1 ^operator O1986 = 0.3873369632550164)
  13330. Firing prefer*rvt*predict-no*H0*2*v1*H1
  13331. -->
  13332. Firing rl*prefer*rvt*predict-no*H0*2*v1*H1*35
  13333. -->
  13334. (S1 ^operator O1986 = 0.2714993082286609)
  13335. inner elaboration loop at bottom goal.
  13336. Retracting rl*prefer*rvt*predict-no*H0*2
  13337. -->
  13338. (S1 ^operator O1984 = 0.3873369632550164)
  13339. Retracting rl*prefer*rvt*predict-no*H0*2*v1*H1*35
  13340. -->
  13341. (S1 ^operator O1984 = 0.2714993082286609)
  13342. Retracting rl*prefer*rvt*predict-yes*H0*1
  13343. -->
  13344. (S1 ^operator O1983 = 0.3895393210007886)
  13345. Retracting rl*prefer*rvt*predict-yes*H0*1*v1*H1*36
  13346. -->
  13347. (S1 ^operator O1983 = 0.6104592422684716)
  13348. --- END Proposal Phase ---
  13349. --- Decision Phase ---
  13350. RL update rl*prefer*rvt*predict-yes*H0*3 0.675414 -0.491003 0.184411 -> 0.675415 -0.491003 0.184412(R,m,v=1,0.89881,0.0914956)
  13351. RL update rl*prefer*rvt*predict-yes*H0*3*v1*H1*46 0.324575 0.491005 0.81558 -> 0.324577 0.491005 0.815582(R,m,v=1,1,0)
  13352. =>WM: (13915: S1 ^operator O1985)
  13353. 993: O: O1985 (predict-yes)
  13354. --- END Decision Phase ---
  13355. --- Application Phase ---
  13356. --- Firing Productions (PE) For State At Depth 1 ---
  13357. --- Inner Elaboration Phase, active level 1 (S1) ---
  13358. Firing apply*operator
  13359. -->
  13360. (I3 ^predict-yes N993 + :O )
  13361. Firing apply*operator*complete
  13362. -->
  13363. (I3 ^predict-yes N992 - :O )
  13364. inner elaboration loop at bottom goal.
  13365. --- Change Working Memory (PE) ---
  13366. =>WM: (13916: I3 ^predict-yes N993)
  13367. <=WM: (13903: N992 ^status complete)
  13368. <=WM: (13902: I3 ^predict-yes N992)
  13369. --- Firing Productions (IE) For State At Depth 1 ---
  13370. --- Inner Elaboration Phase, active level 1 (S1) ---
  13371. Firing monitor*world
  13372. -->
  13373. I see 1 and I'm going to do: predict-yes inner elaboration loop at bottom goal.
  13374. --- Change Working Memory (IE) ---
  13375. --- END Application Phase ---
  13376. --- Output Phase ---
  13377. ENV: Agent did: predict-yes for direction L in state State-B
  13378. In State-B moving L
  13379. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  13380. predict error 0
  13381. dir: dir isR
  13382. --- END Output Phase ---
  13383. \--- Input Phase ---
  13384. =>WM: (13920: I2 ^dir R)
  13385. =>WM: (13919: I2 ^reward 1)
  13386. =>WM: (13918: I2 ^see 1)
  13387. =>WM: (13917: N993 ^status complete)
  13388. <=WM: (13906: I2 ^dir L)
  13389. <=WM: (13905: I2 ^reward 1)
  13390. <=WM: (13904: I2 ^see 1)
  13391. =>WM: (13921: I2 ^level-1 L1-root)
  13392. <=WM: (13907: I2 ^level-1 R1-root)
  13393. --- END Input Phase ---
  13394. --- Proposal Phase ---
  13395. --- Inner Elaboration Phase, active level 1 (S1) ---
  13396. Firing rl*prefer*rvt*predict-no*H0*4*v1*H1*45
  13397. -->
  13398. (S1 ^operator O1986 = -0.02155734064455064)
  13399. Firing rl*prefer*rvt*predict-yes*H0*3*v1*H1*46
  13400. -->
  13401. (S1 ^operator O1985 = 0.8155815255083509)
  13402. Firing prefer*rvt*predict-no*H0*4*v1*H1
  13403. -->
  13404. Firing prefer*rvt*predict-yes*H0*3*v1*H1
  13405. -->
  13406. Firing elaborate*copy-see-to-output-link
  13407. -->
  13408. (I3 ^see 1 +)
  13409. Firing elaborate*reward*based*on*reward
  13410. -->
  13411. (R997 ^value 1 +)
  13412. (R1 ^reward R997 +)
  13413. Firing propose*predict-yes
  13414. -->
  13415. (O1987 ^name predict-yes +)
  13416. (S1 ^operator O1987 +)
  13417. Firing propose*predict-no
  13418. -->
  13419. (O1988 ^name predict-no +)
  13420. (S1 ^operator O1988 +)
  13421. Firing rl*prefer*rvt*predict-no*H0*4
  13422. -->
  13423. (S1 ^operator O1986 = 0.4476195574206818)
  13424. Firing rl*prefer*rvt*predict-yes*H0*3
  13425. -->
  13426. (S1 ^operator O1985 = 0.1844123557789626)
  13427. Firing prefer*rvt*predict-yes*H0
  13428. -->
  13429. Firing prefer*rvt*predict-no*H0
  13430. -->
  13431. Firing elaborate*copy-dir-to-output-link
  13432. -->
  13433. (I3 ^dir R +)
  13434. inner elaboration loop at bottom goal.
  13435. Retracting elaborate*copy-see-to-output-link
  13436. -->
  13437. (I3 ^see 1 +)
  13438. Retracting propose*predict-no
  13439. -->
  13440. (O1986 ^name predict-no +)
  13441. (S1 ^operator O1986 +)
  13442. Retracting propose*predict-yes
  13443. -->
  13444. (O1985 ^name predict-yes +)
  13445. (S1 ^operator O1985 +)
  13446. Retracting elaborate*reward*based*on*reward
  13447. -->
  13448. (R996 ^value 1 +)
  13449. (R1 ^reward R996 +)
  13450. Retracting elaborate*copy-dir-to-output-link
  13451. -->
  13452. (I3 ^dir L +)
  13453. Retracting rl*prefer*rvt*predict-no*H0*2*v1*H1*35
  13454. -->
  13455. (S1 ^operator O1986 = 0.2714993082286609)
  13456. Retracting rl*prefer*rvt*predict-no*H0*2
  13457. -->
  13458. (S1 ^operator O1986 = 0.3873369632550164)
  13459. Retracting rl*prefer*rvt*predict-yes*H0*1*v1*H1*36
  13460. -->
  13461. (S1 ^operator O1985 = 0.6104592422684716)
  13462. Retracting rl*prefer*rvt*predict-yes*H0*1
  13463. -->
  13464. (S1 ^operator O1985 = 0.3895393210007886)
  13465. =>WM: (13928: S1 ^operator O1988 +)
  13466. =>WM: (13927: S1 ^operator O1987 +)
  13467. =>WM: (13926: I3 ^dir R)
  13468. =>WM: (13925: O1988 ^name predict-no)
  13469. =>WM: (13924: O1987 ^name predict-yes)
  13470. =>WM: (13923: R997 ^value 1)
  13471. =>WM: (13922: R1 ^reward R997)
  13472. <=WM: (13913: S1 ^operator O1985 +)
  13473. <=WM: (13915: S1 ^operator O1985)
  13474. <=WM: (13914: S1 ^operator O1986 +)
  13475. <=WM: (13912: I3 ^dir L)
  13476. <=WM: (13908: R1 ^reward R996)
  13477. <=WM: (13911: O1986 ^name predict-no)
  13478. <=WM: (13910: O1985 ^name predict-yes)
  13479. <=WM: (13909: R996 ^value 1)
  13480. --- Inner Elaboration Phase, active level 1 (S1) ---
  13481. Firing prefer*rvt*predict-yes*H0
  13482. -->
  13483. Firing rl*prefer*rvt*predict-yes*H0*3
  13484. -->
  13485. (S1 ^operator O1987 = 0.1844123557789626)
  13486. Firing prefer*rvt*predict-yes*H0*3*v1*H1
  13487. -->
  13488. Firing rl*prefer*rvt*predict-yes*H0*3*v1*H1*46
  13489. -->
  13490. (S1 ^operator O1987 = 0.8155815255083509)
  13491. Firing prefer*rvt*predict-no*H0
  13492. -->
  13493. Firing rl*prefer*rvt*predict-no*H0*4
  13494. -->
  13495. (S1 ^operator O1988 = 0.4476195574206818)
  13496. Firing prefer*rvt*predict-no*H0*4*v1*H1
  13497. -->
  13498. Firing rl*prefer*rvt*predict-no*H0*4*v1*H1*45
  13499. -->
  13500. (S1 ^operator O1988 = -0.02155734064455064)
  13501. inner elaboration loop at bottom goal.
  13502. Retracting rl*prefer*rvt*predict-no*H0*4
  13503. -->
  13504. (S1 ^operator O1986 = 0.4476195574206818)
  13505. Retracting rl*prefer*rvt*predict-no*H0*4*v1*H1*45
  13506. -->
  13507. (S1 ^operator O1986 = -0.02155734064455064)
  13508. Retracting rl*prefer*rvt*predict-yes*H0*3
  13509. -->
  13510. (S1 ^operator O1985 = 0.1844123557789626)
  13511. Retracting rl*prefer*rvt*predict-yes*H0*3*v1*H1*46
  13512. -->
  13513. (S1 ^operator O1985 = 0.8155815255083509)
  13514. --- END Proposal Phase ---
  13515. --- Decision Phase ---
  13516. RL update rl*prefer*rvt*predict-yes*H0*1 0.711951 -0.322412 0.389539 -> 0.711951 -0.322412 0.38954(R,m,v=1,0.891566,0.0972618)
  13517. RL update rl*prefer*rvt*predict-yes*H0*1*v1*H1*36 0.288049 0.322411 0.610459 -> 0.288049 0.322411 0.610459(R,m,v=1,1,0)
  13518. =>WM: (13929: S1 ^operator O1987)
  13519. 994: O: O1987 (predict-yes)
  13520. --- END Decision Phase ---
  13521. --- Application Phase ---
  13522. --- Firing Productions (PE) For State At Depth 1 ---
  13523. --- Inner Elaboration Phase, active level 1 (S1) ---
  13524. Firing apply*operator
  13525. -->
  13526. (I3 ^predict-yes N994 + :O )
  13527. Firing apply*operator*complete
  13528. -->
  13529. (I3 ^predict-yes N993 - :O )
  13530. inner elaboration loop at bottom goal.
  13531. --- Change Working Memory (PE) ---
  13532. =>WM: (13930: I3 ^predict-yes N994)
  13533. <=WM: (13917: N993 ^status complete)
  13534. <=WM: (13916: I3 ^predict-yes N993)
  13535. --- Firing Productions (IE) For State At Depth 1 ---
  13536. --- Inner Elaboration Phase, active level 1 (S1) ---
  13537. Firing monitor*world
  13538. -->
  13539. I see 1 and I'm going to do: predict-yes inner elaboration loop at bottom goal.
  13540. --- Change Working Memory (IE) ---
  13541. --- END Application Phase ---
  13542. --- Output Phase ---
  13543. ENV: Agent did: predict-yes for direction R in state State-A
  13544. In State-A moving R
  13545. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  13546. predict error 0
  13547. dir: dir isL
  13548. --- END Output Phase ---
  13549. -/|--- Input Phase ---
  13550. =>WM: (13934: I2 ^dir L)
  13551. =>WM: (13933: I2 ^reward 1)
  13552. =>WM: (13932: I2 ^see 1)
  13553. =>WM: (13931: N994 ^status complete)
  13554. <=WM: (13920: I2 ^dir R)
  13555. <=WM: (13919: I2 ^reward 1)
  13556. <=WM: (13918: I2 ^see 1)
  13557. =>WM: (13935: I2 ^level-1 R1-root)
  13558. <=WM: (13921: I2 ^level-1 L1-root)
  13559. --- END Input Phase ---
  13560. --- Proposal Phase ---
  13561. --- Inner Elaboration Phase, active level 1 (S1) ---
  13562. Firing rl*prefer*rvt*predict-yes*H0*1*v1*H1*36
  13563. -->
  13564. (S1 ^operator O1987 = 0.6104594577780825)
  13565. Firing rl*prefer*rvt*predict-no*H0*2*v1*H1*35
  13566. -->
  13567. (S1 ^operator O1988 = 0.2714993082286609)
  13568. Firing prefer*rvt*predict-no*H0*2*v1*H1
  13569. -->
  13570. Firing prefer*rvt*predict-yes*H0*1*v1*H1
  13571. -->
  13572. Firing elaborate*copy-see-to-output-link
  13573. -->
  13574. (I3 ^see 1 +)
  13575. Firing elaborate*reward*based*on*reward
  13576. -->
  13577. (R998 ^value 1 +)
  13578. (R1 ^reward R998 +)
  13579. Firing propose*predict-yes
  13580. -->
  13581. (O1989 ^name predict-yes +)
  13582. (S1 ^operator O1989 +)
  13583. Firing propose*predict-no
  13584. -->
  13585. (O1990 ^name predict-no +)
  13586. (S1 ^operator O1990 +)
  13587. Firing rl*prefer*rvt*predict-no*H0*2
  13588. -->
  13589. (S1 ^operator O1988 = 0.3873369632550164)
  13590. Firing rl*prefer*rvt*predict-yes*H0*1
  13591. -->
  13592. (S1 ^operator O1987 = 0.3895395365103996)
  13593. Firing prefer*rvt*predict-yes*H0
  13594. -->
  13595. Firing prefer*rvt*predict-no*H0
  13596. -->
  13597. Firing elaborate*copy-dir-to-output-link
  13598. -->
  13599. (I3 ^dir L +)
  13600. inner elaboration loop at bottom goal.
  13601. Retracting elaborate*copy-see-to-output-link
  13602. -->
  13603. (I3 ^see 1 +)
  13604. Retracting propose*predict-no
  13605. -->
  13606. (O1988 ^name predict-no +)
  13607. (S1 ^operator O1988 +)
  13608. Retracting propose*predict-yes
  13609. -->
  13610. (O1987 ^name predict-yes +)
  13611. (S1 ^operator O1987 +)
  13612. Retracting elaborate*reward*based*on*reward
  13613. -->
  13614. (R997 ^value 1 +)
  13615. (R1 ^reward R997 +)
  13616. Retracting elaborate*copy-dir-to-output-link
  13617. -->
  13618. (I3 ^dir R +)
  13619. Retracting rl*prefer*rvt*predict-no*H0*4*v1*H1*45
  13620. -->
  13621. (S1 ^operator O1988 = -0.02155734064455064)
  13622. Retracting rl*prefer*rvt*predict-no*H0*4
  13623. -->
  13624. (S1 ^operator O1988 = 0.4476195574206818)
  13625. Retracting rl*prefer*rvt*predict-yes*H0*3*v1*H1*46
  13626. -->
  13627. (S1 ^operator O1987 = 0.8155815255083509)
  13628. Retracting rl*prefer*rvt*predict-yes*H0*3
  13629. -->
  13630. (S1 ^operator O1987 = 0.1844123557789626)
  13631. =>WM: (13942: S1 ^operator O1990 +)
  13632. =>WM: (13941: S1 ^operator O1989 +)
  13633. =>WM: (13940: I3 ^dir L)
  13634. =>WM: (13939: O1990 ^name predict-no)
  13635. =>WM: (13938: O1989 ^name predict-yes)
  13636. =>WM: (13937: R998 ^value 1)
  13637. =>WM: (13936: R1 ^reward R998)
  13638. <=WM: (13927: S1 ^operator O1987 +)
  13639. <=WM: (13929: S1 ^operator O1987)
  13640. <=WM: (13928: S1 ^operator O1988 +)
  13641. <=WM: (13926: I3 ^dir R)
  13642. <=WM: (13922: R1 ^reward R997)
  13643. <=WM: (13925: O1988 ^name predict-no)
  13644. <=WM: (13924: O1987 ^name predict-yes)
  13645. <=WM: (13923: R997 ^value 1)
  13646. --- Inner Elaboration Phase, active level 1 (S1) ---
  13647. Firing prefer*rvt*predict-yes*H0
  13648. -->
  13649. Firing rl*prefer*rvt*predict-yes*H0*1
  13650. -->
  13651. (S1 ^operator O1989 = 0.3895395365103996)
  13652. Firing prefer*rvt*predict-yes*H0*1*v1*H1
  13653. -->
  13654. Firing rl*prefer*rvt*predict-yes*H0*1*v1*H1*36
  13655. -->
  13656. (S1 ^operator O1989 = 0.6104594577780825)
  13657. Firing prefer*rvt*predict-no*H0
  13658. -->
  13659. Firing rl*prefer*rvt*predict-no*H0*2
  13660. -->
  13661. (S1 ^operator O1990 = 0.3873369632550164)
  13662. Firing prefer*rvt*predict-no*H0*2*v1*H1
  13663. -->
  13664. Firing rl*prefer*rvt*predict-no*H0*2*v1*H1*35
  13665. -->
  13666. (S1 ^operator O1990 = 0.2714993082286609)
  13667. inner elaboration loop at bottom goal.
  13668. Retracting rl*prefer*rvt*predict-no*H0*2
  13669. -->
  13670. (S1 ^operator O1988 = 0.3873369632550164)
  13671. Retracting rl*prefer*rvt*predict-no*H0*2*v1*H1*35
  13672. -->
  13673. (S1 ^operator O1988 = 0.2714993082286609)
  13674. Retracting rl*prefer*rvt*predict-yes*H0*1
  13675. -->
  13676. (S1 ^operator O1987 = 0.3895395365103996)
  13677. Retracting rl*prefer*rvt*predict-yes*H0*1*v1*H1*36
  13678. -->
  13679. (S1 ^operator O1987 = 0.6104594577780825)
  13680. --- END Proposal Phase ---
  13681. --- Decision Phase ---
  13682. RL update rl*prefer*rvt*predict-yes*H0*3 0.675415 -0.491003 0.184412 -> 0.675417 -0.491003 0.184413(R,m,v=1,0.899408,0.0910116)
  13683. RL update rl*prefer*rvt*predict-yes*H0*3*v1*H1*46 0.324577 0.491005 0.815582 -> 0.324578 0.491005 0.815582(R,m,v=1,1,0)
  13684. =>WM: (13943: S1 ^operator O1989)
  13685. 995: O: O1989 (predict-yes)
  13686. --- END Decision Phase ---
  13687. --- Application Phase ---
  13688. --- Firing Productions (PE) For State At Depth 1 ---
  13689. --- Inner Elaboration Phase, active level 1 (S1) ---
  13690. Firing apply*operator
  13691. -->
  13692. (I3 ^predict-yes N995 + :O )
  13693. Firing apply*operator*complete
  13694. -->
  13695. (I3 ^predict-yes N994 - :O )
  13696. inner elaboration loop at bottom goal.
  13697. --- Change Working Memory (PE) ---
  13698. =>WM: (13944: I3 ^predict-yes N995)
  13699. <=WM: (13931: N994 ^status complete)
  13700. <=WM: (13930: I3 ^predict-yes N994)
  13701. --- Firing Productions (IE) For State At Depth 1 ---
  13702. --- Inner Elaboration Phase, active level 1 (S1) ---
  13703. Firing monitor*world
  13704. -->
  13705. I see 1 and I'm going to do: predict-yes inner elaboration loop at bottom goal.
  13706. --- Change Working Memory (IE) ---
  13707. --- END Application Phase ---
  13708. --- Output Phase ---
  13709. ENV: Agent did: predict-yes for direction L in state State-B
  13710. In State-B moving L
  13711. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  13712. predict error 0
  13713. dir: dir isL
  13714. --- END Output Phase ---
  13715. \---- Input Phase ---
  13716. =>WM: (13948: I2 ^dir L)
  13717. =>WM: (13947: I2 ^reward 1)
  13718. =>WM: (13946: I2 ^see 1)
  13719. =>WM: (13945: N995 ^status complete)
  13720. <=WM: (13934: I2 ^dir L)
  13721. <=WM: (13933: I2 ^reward 1)
  13722. <=WM: (13932: I2 ^see 1)
  13723. =>WM: (13949: I2 ^level-1 L1-root)
  13724. <=WM: (13935: I2 ^level-1 R1-root)
  13725. --- END Input Phase ---
  13726. --- Proposal Phase ---
  13727. --- Inner Elaboration Phase, active level 1 (S1) ---
  13728. Firing rl*prefer*rvt*predict-no*H0*2*v1*H1*32
  13729. -->
  13730. (S1 ^operator O1990 = 0.6126627481603084)
  13731. Firing rl*prefer*rvt*predict-yes*H0*1*v1*H1*31
  13732. -->
  13733. (S1 ^operator O1989 = -0.02274740735326741)
  13734. Firing prefer*rvt*predict-no*H0*2*v1*H1
  13735. -->
  13736. Firing prefer*rvt*predict-yes*H0*1*v1*H1
  13737. -->
  13738. Firing elaborate*copy-see-to-output-link
  13739. -->
  13740. (I3 ^see 1 +)
  13741. Firing elaborate*reward*based*on*reward
  13742. -->
  13743. (R999 ^value 1 +)
  13744. (R1 ^reward R999 +)
  13745. Firing propose*predict-yes
  13746. -->
  13747. (O1991 ^name predict-yes +)
  13748. (S1 ^operator O1991 +)
  13749. Firing propose*predict-no
  13750. -->
  13751. (O1992 ^name predict-no +)
  13752. (S1 ^operator O1992 +)
  13753. Firing rl*prefer*rvt*predict-no*H0*2
  13754. -->
  13755. (S1 ^operator O1990 = 0.3873369632550164)
  13756. Firing rl*prefer*rvt*predict-yes*H0*1
  13757. -->
  13758. (S1 ^operator O1989 = 0.3895395365103996)
  13759. Firing prefer*rvt*predict-yes*H0
  13760. -->
  13761. Firing prefer*rvt*predict-no*H0
  13762. -->
  13763. Firing elaborate*copy-dir-to-output-link
  13764. -->
  13765. (I3 ^dir L +)
  13766. inner elaboration loop at bottom goal.
  13767. Retracting elaborate*copy-see-to-output-link
  13768. -->
  13769. (I3 ^see 1 +)
  13770. Retracting propose*predict-no
  13771. -->
  13772. (O1990 ^name predict-no +)
  13773. (S1 ^operator O1990 +)
  13774. Retracting propose*predict-yes
  13775. -->
  13776. (O1989 ^name predict-yes +)
  13777. (S1 ^operator O1989 +)
  13778. Retracting elaborate*reward*based*on*reward
  13779. -->
  13780. (R998 ^value 1 +)
  13781. (R1 ^reward R998 +)
  13782. Retracting elaborate*copy-dir-to-output-link
  13783. -->
  13784. (I3 ^dir L +)
  13785. Retracting rl*prefer*rvt*predict-no*H0*2*v1*H1*35
  13786. -->
  13787. (S1 ^operator O1990 = 0.2714993082286609)
  13788. Retracting rl*prefer*rvt*predict-no*H0*2
  13789. -->
  13790. (S1 ^operator O1990 = 0.3873369632550164)
  13791. Retracting rl*prefer*rvt*predict-yes*H0*1*v1*H1*36
  13792. -->
  13793. (S1 ^operator O1989 = 0.6104594577780825)
  13794. Retracting rl*prefer*rvt*predict-yes*H0*1
  13795. -->
  13796. (S1 ^operator O1989 = 0.3895395365103996)
  13797. =>WM: (13955: S1 ^operator O1992 +)
  13798. =>WM: (13954: S1 ^operator O1991 +)
  13799. =>WM: (13953: O1992 ^name predict-no)
  13800. =>WM: (13952: O1991 ^name predict-yes)
  13801. =>WM: (13951: R999 ^value 1)
  13802. =>WM: (13950: R1 ^reward R999)
  13803. <=WM: (13941: S1 ^operator O1989 +)
  13804. <=WM: (13943: S1 ^operator O1989)
  13805. <=WM: (13942: S1 ^operator O1990 +)
  13806. <=WM: (13936: R1 ^reward R998)
  13807. <=WM: (13939: O1990 ^name predict-no)
  13808. <=WM: (13938: O1989 ^name predict-yes)
  13809. <=WM: (13937: R998 ^value 1)
  13810. --- Inner Elaboration Phase, active level 1 (S1) ---
  13811. Firing prefer*rvt*predict-yes*H0
  13812. -->
  13813. Firing rl*prefer*rvt*predict-yes*H0*1
  13814. -->
  13815. (S1 ^operator O1991 = 0.3895395365103996)
  13816. Firing prefer*rvt*predict-yes*H0*1*v1*H1
  13817. -->
  13818. Firing rl*prefer*rvt*predict-yes*H0*1*v1*H1*31
  13819. -->
  13820. (S1 ^operator O1991 = -0.02274740735326741)
  13821. Firing prefer*rvt*predict-no*H0
  13822. -->
  13823. Firing rl*prefer*rvt*predict-no*H0*2
  13824. -->
  13825. (S1 ^operator O1992 = 0.3873369632550164)
  13826. Firing prefer*rvt*predict-no*H0*2*v1*H1
  13827. -->
  13828. Firing rl*prefer*rvt*predict-no*H0*2*v1*H1*32
  13829. -->
  13830. (S1 ^operator O1992 = 0.6126627481603084)
  13831. inner elaboration loop at bottom goal.
  13832. Retracting rl*prefer*rvt*predict-no*H0*2
  13833. -->
  13834. (S1 ^operator O1990 = 0.3873369632550164)
  13835. Retracting rl*prefer*rvt*predict-no*H0*2*v1*H1*32
  13836. -->
  13837. (S1 ^operator O1990 = 0.6126627481603084)
  13838. Retracting rl*prefer*rvt*predict-yes*H0*1
  13839. -->
  13840. (S1 ^operator O1989 = 0.3895395365103996)
  13841. Retracting rl*prefer*rvt*predict-yes*H0*1*v1*H1*31
  13842. -->
  13843. (S1 ^operator O1989 = -0.02274740735326741)
  13844. --- END Proposal Phase ---
  13845. --- Decision Phase ---
  13846. RL update rl*prefer*rvt*predict-yes*H0*1 0.711951 -0.322412 0.38954 -> 0.711951 -0.322412 0.38954(R,m,v=1,0.892216,0.0967463)
  13847. RL update rl*prefer*rvt*predict-yes*H0*1*v1*H1*36 0.288049 0.322411 0.610459 -> 0.288049 0.322411 0.61046(R,m,v=1,1,0)
  13848. =>WM: (13956: S1 ^operator O1992)
  13849. 996: O: O1992 (predict-no)
  13850. --- END Decision Phase ---
  13851. --- Application Phase ---
  13852. --- Firing Productions (PE) For State At Depth 1 ---
  13853. --- Inner Elaboration Phase, active level 1 (S1) ---
  13854. Firing apply*operator
  13855. -->
  13856. (I3 ^predict-no N996 + :O )
  13857. Firing apply*operator*complete
  13858. -->
  13859. (I3 ^predict-yes N995 - :O )
  13860. inner elaboration loop at bottom goal.
  13861. --- Change Working Memory (PE) ---
  13862. =>WM: (13957: I3 ^predict-no N996)
  13863. <=WM: (13945: N995 ^status complete)
  13864. <=WM: (13944: I3 ^predict-yes N995)
  13865. --- Firing Productions (IE) For State At Depth 1 ---
  13866. --- Inner Elaboration Phase, active level 1 (S1) ---
  13867. Firing monitor*world
  13868. -->
  13869. I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
  13870. --- Change Working Memory (IE) ---
  13871. --- END Application Phase ---
  13872. --- Output Phase ---
  13873. ENV: Agent did: predict-no for direction L in state State-A
  13874. In State-A moving L
  13875. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  13876. predict error 0
  13877. dir: dir isR
  13878. --- END Output Phase ---
  13879. /|\---- Input Phase ---
  13880. =>WM: (13961: I2 ^dir R)
  13881. =>WM: (13960: I2 ^reward 1)
  13882. =>WM: (13959: I2 ^see 0)
  13883. =>WM: (13958: N996 ^status complete)
  13884. <=WM: (13948: I2 ^dir L)
  13885. <=WM: (13947: I2 ^reward 1)
  13886. <=WM: (13946: I2 ^see 1)
  13887. =>WM: (13962: I2 ^level-1 L0-root)
  13888. <=WM: (13949: I2 ^level-1 L1-root)
  13889. --- END Input Phase ---
  13890. --- Proposal Phase ---
  13891. --- Inner Elaboration Phase, active level 1 (S1) ---
  13892. Firing rl*prefer*rvt*predict-yes*H0*3*v1*H1*34
  13893. -->
  13894. (S1 ^operator O1991 = 0.8155947374398671)
  13895. Firing rl*prefer*rvt*predict-no*H0*4*v1*H1*33
  13896. -->
  13897. (S1 ^operator O1992 = -0.00558448899823713)
  13898. Firing prefer*rvt*predict-no*H0*4*v1*H1
  13899. -->
  13900. Firing prefer*rvt*predict-yes*H0*3*v1*H1
  13901. -->
  13902. Firing elaborate*copy-see-to-output-link
  13903. -->
  13904. (I3 ^see 0 +)
  13905. Firing elaborate*reward*based*on*reward
  13906. -->
  13907. (R1000 ^value 1 +)
  13908. (R1 ^reward R1000 +)
  13909. Firing propose*predict-yes
  13910. -->
  13911. (O1993 ^name predict-yes +)
  13912. (S1 ^operator O1993 +)
  13913. Firing propose*predict-no
  13914. -->
  13915. (O1994 ^name predict-no +)
  13916. (S1 ^operator O1994 +)
  13917. Firing rl*prefer*rvt*predict-no*H0*4
  13918. -->
  13919. (S1 ^operator O1992 = 0.4476195574206818)
  13920. Firing rl*prefer*rvt*predict-yes*H0*3
  13921. -->
  13922. (S1 ^operator O1991 = 0.1844132735858656)
  13923. Firing prefer*rvt*predict-yes*H0
  13924. -->
  13925. Firing prefer*rvt*predict-no*H0
  13926. -->
  13927. Firing elaborate*copy-dir-to-output-link
  13928. -->
  13929. (I3 ^dir R +)
  13930. inner elaboration loop at bottom goal.
  13931. Retracting elaborate*copy-see-to-output-link
  13932. -->
  13933. (I3 ^see 1 +)
  13934. Retracting propose*predict-no
  13935. -->
  13936. (O1992 ^name predict-no +)
  13937. (S1 ^operator O1992 +)
  13938. Retracting propose*predict-yes
  13939. -->
  13940. (O1991 ^name predict-yes +)
  13941. (S1 ^operator O1991 +)
  13942. Retracting elaborate*reward*based*on*reward
  13943. -->
  13944. (R999 ^value 1 +)
  13945. (R1 ^reward R999 +)
  13946. Retracting elaborate*copy-dir-to-output-link
  13947. -->
  13948. (I3 ^dir L +)
  13949. Retracting rl*prefer*rvt*predict-no*H0*2*v1*H1*32
  13950. -->
  13951. (S1 ^operator O1992 = 0.6126627481603084)
  13952. Retracting rl*prefer*rvt*predict-no*H0*2
  13953. -->
  13954. (S1 ^operator O1992 = 0.3873369632550164)
  13955. Retracting rl*prefer*rvt*predict-yes*H0*1*v1*H1*31
  13956. -->
  13957. (S1 ^operator O1991 = -0.02274740735326741)
  13958. Retracting rl*prefer*rvt*predict-yes*H0*1
  13959. -->
  13960. (S1 ^operator O1991 = 0.3895396873671274)
  13961. =>WM: (13970: S1 ^operator O1994 +)
  13962. =>WM: (13969: S1 ^operator O1993 +)
  13963. =>WM: (13968: I3 ^dir R)
  13964. =>WM: (13967: O1994 ^name predict-no)
  13965. =>WM: (13966: O1993 ^name predict-yes)
  13966. =>WM: (13965: R1000 ^value 1)
  13967. =>WM: (13964: R1 ^reward R1000)
  13968. =>WM: (13963: I3 ^see 0)
  13969. <=WM: (13954: S1 ^operator O1991 +)
  13970. <=WM: (13955: S1 ^operator O1992 +)
  13971. <=WM: (13956: S1 ^operator O1992)
  13972. <=WM: (13940: I3 ^dir L)
  13973. <=WM: (13950: R1 ^reward R999)
  13974. <=WM: (13893: I3 ^see 1)
  13975. <=WM: (13953: O1992 ^name predict-no)
  13976. <=WM: (13952: O1991 ^name predict-yes)
  13977. <=WM: (13951: R999 ^value 1)
  13978. --- Inner Elaboration Phase, active level 1 (S1) ---
  13979. Firing prefer*rvt*predict-yes*H0
  13980. -->
  13981. Firing rl*prefer*rvt*predict-yes*H0*3
  13982. -->
  13983. (S1 ^operator O1993 = 0.1844132735858656)
  13984. Firing prefer*rvt*predict-yes*H0*3*v1*H1
  13985. -->
  13986. Firing rl*prefer*rvt*predict-yes*H0*3*v1*H1*34
  13987. -->
  13988. (S1 ^operator O1993 = 0.8155947374398671)
  13989. Firing prefer*rvt*predict-no*H0
  13990. -->
  13991. Firing rl*prefer*rvt*predict-no*H0*4
  13992. -->
  13993. (S1 ^operator O1994 = 0.4476195574206818)
  13994. Firing prefer*rvt*predict-no*H0*4*v1*H1
  13995. -->
  13996. Firing rl*prefer*rvt*predict-no*H0*4*v1*H1*33
  13997. -->
  13998. (S1 ^operator O1994 = -0.00558448899823713)
  13999. inner elaboration loop at bottom goal.
  14000. Retracting rl*prefer*rvt*predict-no*H0*4
  14001. -->
  14002. (S1 ^operator O1992 = 0.4476195574206818)
  14003. Retracting rl*prefer*rvt*predict-no*H0*4*v1*H1*33
  14004. -->
  14005. (S1 ^operator O1992 = -0.00558448899823713)
  14006. Retracting rl*prefer*rvt*predict-yes*H0*3
  14007. -->
  14008. (S1 ^operator O1991 = 0.1844132735858656)
  14009. Retracting rl*prefer*rvt*predict-yes*H0*3*v1*H1*34
  14010. -->
  14011. (S1 ^operator O1991 = 0.8155947374398671)
  14012. --- END Proposal Phase ---
  14013. --- Decision Phase ---
  14014. RL update rl*prefer*rvt*predict-no*H0*2 0.719081 -0.331744 0.387337 -> 0.719081 -0.331744 0.387337(R,m,v=1,0.931818,0.0638961)
  14015. RL update rl*prefer*rvt*predict-no*H0*2*v1*H1*32 0.280919 0.331744 0.612663 -> 0.280919 0.331744 0.612663(R,m,v=1,1,0)
  14016. =>WM: (13971: S1 ^operator O1993)
  14017. 997: O: O1993 (predict-yes)
  14018. --- END Decision Phase ---
  14019. --- Application Phase ---
  14020. --- Firing Productions (PE) For State At Depth 1 ---
  14021. --- Inner Elaboration Phase, active level 1 (S1) ---
  14022. Firing apply*operator
  14023. -->
  14024. (I3 ^predict-yes N997 + :O )
  14025. Firing apply*operator*complete
  14026. -->
  14027. (I3 ^predict-no N996 - :O )
  14028. inner elaboration loop at bottom goal.
  14029. --- Change Working Memory (PE) ---
  14030. =>WM: (13972: I3 ^predict-yes N997)
  14031. <=WM: (13958: N996 ^status complete)
  14032. <=WM: (13957: I3 ^predict-no N996)
  14033. --- Firing Productions (IE) For State At Depth 1 ---
  14034. --- Inner Elaboration Phase, active level 1 (S1) ---
  14035. Firing monitor*world
  14036. -->
  14037. I see 1 and I'm going to do: predict-yes inner elaboration loop at bottom goal.
  14038. --- Change Working Memory (IE) ---
  14039. --- END Application Phase ---
  14040. --- Output Phase ---
  14041. ENV: Agent did: predict-yes for direction R in state State-A
  14042. In State-A moving R
  14043. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  14044. predict error 0
  14045. dir: dir isR
  14046. --- END Output Phase ---
  14047. /|\--- Input Phase ---
  14048. =>WM: (13976: I2 ^dir R)
  14049. =>WM: (13975: I2 ^reward 1)
  14050. =>WM: (13974: I2 ^see 1)
  14051. =>WM: (13973: N997 ^status complete)
  14052. <=WM: (13961: I2 ^dir R)
  14053. <=WM: (13960: I2 ^reward 1)
  14054. <=WM: (13959: I2 ^see 0)
  14055. =>WM: (13977: I2 ^level-1 R1-root)
  14056. <=WM: (13962: I2 ^level-1 L0-root)
  14057. --- END Input Phase ---
  14058. --- Proposal Phase ---
  14059. --- Inner Elaboration Phase, active level 1 (S1) ---
  14060. Firing rl*prefer*rvt*predict-yes*H0*3*v1*H1*40
  14061. -->
  14062. (S1 ^operator O1993 = 0.1398795999120246)
  14063. Firing rl*prefer*rvt*predict-no*H0*4*v1*H1*39
  14064. -->
  14065. (S1 ^operator O1994 = 0.5523820607022403)
  14066. Firing prefer*rvt*predict-no*H0*4*v1*H1
  14067. -->
  14068. Firing prefer*rvt*predict-yes*H0*3*v1*H1
  14069. -->
  14070. Firing elaborate*copy-see-to-output-link
  14071. -->
  14072. (I3 ^see 1 +)
  14073. Firing elaborate*reward*based*on*reward
  14074. -->
  14075. (R1001 ^value 1 +)
  14076. (R1 ^reward R1001 +)
  14077. Firing propose*predict-yes
  14078. -->
  14079. (O1995 ^name predict-yes +)
  14080. (S1 ^operator O1995 +)
  14081. Firing propose*predict-no
  14082. -->
  14083. (O1996 ^name predict-no +)
  14084. (S1 ^operator O1996 +)
  14085. Firing rl*prefer*rvt*predict-no*H0*4
  14086. -->
  14087. (S1 ^operator O1994 = 0.4476195574206818)
  14088. Firing rl*prefer*rvt*predict-yes*H0*3
  14089. -->
  14090. (S1 ^operator O1993 = 0.1844132735858656)
  14091. Firing prefer*rvt*predict-yes*H0
  14092. -->
  14093. Firing prefer*rvt*predict-no*H0
  14094. -->
  14095. Firing elaborate*copy-dir-to-output-link
  14096. -->
  14097. (I3 ^dir R +)
  14098. inner elaboration loop at bottom goal.
  14099. Retracting elaborate*copy-see-to-output-link
  14100. -->
  14101. (I3 ^see 0 +)
  14102. Retracting propose*predict-no
  14103. -->
  14104. (O1994 ^name predict-no +)
  14105. (S1 ^operator O1994 +)
  14106. Retracting propose*predict-yes
  14107. -->
  14108. (O1993 ^name predict-yes +)
  14109. (S1 ^operator O1993 +)
  14110. Retracting elaborate*reward*based*on*reward
  14111. -->
  14112. (R1000 ^value 1 +)
  14113. (R1 ^reward R1000 +)
  14114. Retracting elaborate*copy-dir-to-output-link
  14115. -->
  14116. (I3 ^dir R +)
  14117. Retracting rl*prefer*rvt*predict-no*H0*4*v1*H1*33
  14118. -->
  14119. (S1 ^operator O1994 = -0.00558448899823713)
  14120. Retracting rl*prefer*rvt*predict-no*H0*4
  14121. -->
  14122. (S1 ^operator O1994 = 0.4476195574206818)
  14123. Retracting rl*prefer*rvt*predict-yes*H0*3*v1*H1*34
  14124. -->
  14125. (S1 ^operator O1993 = 0.8155947374398671)
  14126. Retracting rl*prefer*rvt*predict-yes*H0*3
  14127. -->
  14128. (S1 ^operator O1993 = 0.1844132735858656)
  14129. =>WM: (13984: S1 ^operator O1996 +)
  14130. =>WM: (13983: S1 ^operator O1995 +)
  14131. =>WM: (13982: O1996 ^name predict-no)
  14132. =>WM: (13981: O1995 ^name predict-yes)
  14133. =>WM: (13980: R1001 ^value 1)
  14134. =>WM: (13979: R1 ^reward R1001)
  14135. =>WM: (13978: I3 ^see 1)
  14136. <=WM: (13969: S1 ^operator O1993 +)
  14137. <=WM: (13971: S1 ^operator O1993)
  14138. <=WM: (13970: S1 ^operator O1994 +)
  14139. <=WM: (13964: R1 ^reward R1000)
  14140. <=WM: (13963: I3 ^see 0)
  14141. <=WM: (13967: O1994 ^name predict-no)
  14142. <=WM: (13966: O1993 ^name predict-yes)
  14143. <=WM: (13965: R1000 ^value 1)
  14144. --- Inner Elaboration Phase, active level 1 (S1) ---
  14145. Firing prefer*rvt*predict-yes*H0
  14146. -->
  14147. Firing rl*prefer*rvt*predict-yes*H0*3
  14148. -->
  14149. (S1 ^operator O1995 = 0.1844132735858656)
  14150. Firing prefer*rvt*predict-yes*H0*3*v1*H1
  14151. -->
  14152. Firing rl*prefer*rvt*predict-yes*H0*3*v1*H1*40
  14153. -->
  14154. (S1 ^operator O1995 = 0.1398795999120246)
  14155. Firing prefer*rvt*predict-no*H0
  14156. -->
  14157. Firing rl*prefer*rvt*predict-no*H0*4
  14158. -->
  14159. (S1 ^operator O1996 = 0.4476195574206818)
  14160. Firing prefer*rvt*predict-no*H0*4*v1*H1
  14161. -->
  14162. Firing rl*prefer*rvt*predict-no*H0*4*v1*H1*39
  14163. -->
  14164. (S1 ^operator O1996 = 0.5523820607022403)
  14165. inner elaboration loop at bottom goal.
  14166. Retracting rl*prefer*rvt*predict-no*H0*4
  14167. -->
  14168. (S1 ^operator O1994 = 0.4476195574206818)
  14169. Retracting rl*prefer*rvt*predict-no*H0*4*v1*H1*39
  14170. -->
  14171. (S1 ^operator O1994 = 0.5523820607022403)
  14172. Retracting rl*prefer*rvt*predict-yes*H0*3
  14173. -->
  14174. (S1 ^operator O1993 = 0.1844132735858656)
  14175. Retracting rl*prefer*rvt*predict-yes*H0*3*v1*H1*40
  14176. -->
  14177. (S1 ^operator O1993 = 0.1398795999120246)
  14178. --- END Proposal Phase ---
  14179. --- Decision Phase ---
  14180. RL update rl*prefer*rvt*predict-yes*H0*3 0.675417 -0.491003 0.184413 -> 0.675415 -0.491003 0.184412(R,m,v=1,0.9,0.0905325)
  14181. RL update rl*prefer*rvt*predict-yes*H0*3*v1*H1*34 0.324594 0.491001 0.815595 -> 0.324592 0.491001 0.815594(R,m,v=1,1,0)
  14182. =>WM: (13985: S1 ^operator O1996)
  14183. 998: O: O1996 (predict-no)
  14184. --- END Decision Phase ---
  14185. --- Application Phase ---
  14186. --- Firing Productions (PE) For State At Depth 1 ---
  14187. --- Inner Elaboration Phase, active level 1 (S1) ---
  14188. Firing apply*operator
  14189. -->
  14190. (I3 ^predict-no N998 + :O )
  14191. Firing apply*operator*complete
  14192. -->
  14193. (I3 ^predict-yes N997 - :O )
  14194. inner elaboration loop at bottom goal.
  14195. --- Change Working Memory (PE) ---
  14196. =>WM: (13986: I3 ^predict-no N998)
  14197. <=WM: (13973: N997 ^status complete)
  14198. <=WM: (13972: I3 ^predict-yes N997)
  14199. --- Firing Productions (IE) For State At Depth 1 ---
  14200. --- Inner Elaboration Phase, active level 1 (S1) ---
  14201. Firing monitor*world
  14202. -->
  14203. I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
  14204. --- Change Working Memory (IE) ---
  14205. --- END Application Phase ---
  14206. --- Output Phase ---
  14207. ENV: Agent did: predict-no for direction R in state State-B
  14208. In State-B moving R
  14209. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  14210. predict error 0
  14211. dir: dir isL
  14212. --- END Output Phase ---
  14213. -/|--- Input Phase ---
  14214. =>WM: (13990: I2 ^dir L)
  14215. =>WM: (13989: I2 ^reward 1)
  14216. =>WM: (13988: I2 ^see 0)
  14217. =>WM: (13987: N998 ^status complete)
  14218. <=WM: (13976: I2 ^dir R)
  14219. <=WM: (13975: I2 ^reward 1)
  14220. <=WM: (13974: I2 ^see 1)
  14221. =>WM: (13991: I2 ^level-1 R0-root)
  14222. <=WM: (13977: I2 ^level-1 R1-root)
  14223. --- END Input Phase ---
  14224. --- Proposal Phase ---
  14225. --- Inner Elaboration Phase, active level 1 (S1) ---
  14226. Firing rl*prefer*rvt*predict-yes*H0*1*v1*H1*44
  14227. -->
  14228. (S1 ^operator O1995 = 0.6104611932916519)
  14229. Firing rl*prefer*rvt*predict-no*H0*2*v1*H1*43
  14230. -->
  14231. (S1 ^operator O1996 = 0.1063475139796038)
  14232. Firing prefer*rvt*predict-no*H0*2*v1*H1
  14233. -->
  14234. Firing prefer*rvt*predict-yes*H0*1*v1*H1
  14235. -->
  14236. Firing elaborate*copy-see-to-output-link
  14237. -->
  14238. (I3 ^see 0 +)
  14239. Firing elaborate*reward*based*on*reward
  14240. -->
  14241. (R1002 ^value 1 +)
  14242. (R1 ^reward R1002 +)
  14243. Firing propose*predict-yes
  14244. -->
  14245. (O1997 ^name predict-yes +)
  14246. (S1 ^operator O1997 +)
  14247. Firing propose*predict-no
  14248. -->
  14249. (O1998 ^name predict-no +)
  14250. (S1 ^operator O1998 +)
  14251. Firing rl*prefer*rvt*predict-no*H0*2
  14252. -->
  14253. (S1 ^operator O1996 = 0.3873370065427176)
  14254. Firing rl*prefer*rvt*predict-yes*H0*1
  14255. -->
  14256. (S1 ^operator O1995 = 0.3895396873671274)
  14257. Firing prefer*rvt*predict-yes*H0
  14258. -->
  14259. Firing prefer*rvt*predict-no*H0
  14260. -->
  14261. Firing elaborate*copy-dir-to-output-link
  14262. -->
  14263. (I3 ^dir L +)
  14264. inner elaboration loop at bottom goal.
  14265. Retracting elaborate*copy-see-to-output-link
  14266. -->
  14267. (I3 ^see 1 +)
  14268. Retracting propose*predict-no
  14269. -->
  14270. (O1996 ^name predict-no +)
  14271. (S1 ^operator O1996 +)
  14272. Retracting propose*predict-yes
  14273. -->
  14274. (O1995 ^name predict-yes +)
  14275. (S1 ^operator O1995 +)
  14276. Retracting elaborate*reward*based*on*reward
  14277. -->
  14278. (R1001 ^value 1 +)
  14279. (R1 ^reward R1001 +)
  14280. Retracting elaborate*copy-dir-to-output-link
  14281. -->
  14282. (I3 ^dir R +)
  14283. Retracting rl*prefer*rvt*predict-no*H0*4*v1*H1*39
  14284. -->
  14285. (S1 ^operator O1996 = 0.5523820607022403)
  14286. Retracting rl*prefer*rvt*predict-no*H0*4
  14287. -->
  14288. (S1 ^operator O1996 = 0.4476195574206818)
  14289. Retracting rl*prefer*rvt*predict-yes*H0*3*v1*H1*40
  14290. -->
  14291. (S1 ^operator O1995 = 0.1398795999120246)
  14292. Retracting rl*prefer*rvt*predict-yes*H0*3
  14293. -->
  14294. (S1 ^operator O1995 = 0.1844120719320057)
  14295. =>WM: (13999: S1 ^operator O1998 +)
  14296. =>WM: (13998: S1 ^operator O1997 +)
  14297. =>WM: (13997: I3 ^dir L)
  14298. =>WM: (13996: O1998 ^name predict-no)
  14299. =>WM: (13995: O1997 ^name predict-yes)
  14300. =>WM: (13994: R1002 ^value 1)
  14301. =>WM: (13993: R1 ^reward R1002)
  14302. =>WM: (13992: I3 ^see 0)
  14303. <=WM: (13983: S1 ^operator O1995 +)
  14304. <=WM: (13984: S1 ^operator O1996 +)
  14305. <=WM: (13985: S1 ^operator O1996)
  14306. <=WM: (13968: I3 ^dir R)
  14307. <=WM: (13979: R1 ^reward R1001)
  14308. <=WM: (13978: I3 ^see 1)
  14309. <=WM: (13982: O1996 ^name predict-no)
  14310. <=WM: (13981: O1995 ^name predict-yes)
  14311. <=WM: (13980: R1001 ^value 1)
  14312. --- Inner Elaboration Phase, active level 1 (S1) ---
  14313. Firing prefer*rvt*predict-yes*H0
  14314. -->
  14315. Firing rl*prefer*rvt*predict-yes*H0*1
  14316. -->
  14317. (S1 ^operator O1997 = 0.3895396873671274)
  14318. Firing prefer*rvt*predict-yes*H0*1*v1*H1
  14319. -->
  14320. Firing rl*prefer*rvt*predict-yes*H0*1*v1*H1*44
  14321. -->
  14322. (S1 ^operator O1997 = 0.6104611932916519)
  14323. Firing prefer*rvt*predict-no*H0
  14324. -->
  14325. Firing rl*prefer*rvt*predict-no*H0*2
  14326. -->
  14327. (S1 ^operator O1998 = 0.3873370065427176)
  14328. Firing prefer*rvt*predict-no*H0*2*v1*H1
  14329. -->
  14330. Firing rl*prefer*rvt*predict-no*H0*2*v1*H1*43
  14331. -->
  14332. (S1 ^operator O1998 = 0.1063475139796038)
  14333. inner elaboration loop at bottom goal.
  14334. Retracting rl*prefer*rvt*predict-no*H0*2
  14335. -->
  14336. (S1 ^operator O1996 = 0.3873370065427176)
  14337. Retracting rl*prefer*rvt*predict-no*H0*2*v1*H1*43
  14338. -->
  14339. (S1 ^operator O1996 = 0.1063475139796038)
  14340. Retracting rl*prefer*rvt*predict-yes*H0*1
  14341. -->
  14342. (S1 ^operator O1995 = 0.3895396873671274)
  14343. Retracting rl*prefer*rvt*predict-yes*H0*1*v1*H1*44
  14344. -->
  14345. (S1 ^operator O1995 = 0.6104611932916519)
  14346. --- END Proposal Phase ---
  14347. --- Decision Phase ---
  14348. RL update rl*prefer*rvt*predict-no*H0*4 0.622533 -0.174913 0.44762 -> 0.622533 -0.174914 0.447619(R,m,v=1,0.930233,0.065407)
  14349. RL update rl*prefer*rvt*predict-no*H0*4*v1*H1*39 0.377468 0.174914 0.552382 -> 0.377468 0.174914 0.552382(R,m,v=1,1,0)
  14350. =>WM: (14000: S1 ^operator O1997)
  14351. 999: O: O1997 (predict-yes)
  14352. --- END Decision Phase ---
  14353. --- Application Phase ---
  14354. --- Firing Productions (PE) For State At Depth 1 ---
  14355. --- Inner Elaboration Phase, active level 1 (S1) ---
  14356. Firing apply*operator
  14357. -->
  14358. (I3 ^predict-yes N999 + :O )
  14359. Firing apply*operator*complete
  14360. -->
  14361. (I3 ^predict-no N998 - :O )
  14362. inner elaboration loop at bottom goal.
  14363. --- Change Working Memory (PE) ---
  14364. =>WM: (14001: I3 ^predict-yes N999)
  14365. <=WM: (13987: N998 ^status complete)
  14366. <=WM: (13986: I3 ^predict-no N998)
  14367. --- Firing Productions (IE) For State At Depth 1 ---
  14368. --- Inner Elaboration Phase, active level 1 (S1) ---
  14369. Firing monitor*world
  14370. -->
  14371. I see 1 and I'm going to do: predict-yes inner elaboration loop at bottom goal.
  14372. --- Change Working Memory (IE) ---
  14373. --- END Application Phase ---
  14374. --- Output Phase ---
  14375. ENV: Agent did: predict-yes for direction L in state State-B
  14376. In State-B moving L
  14377. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  14378. predict error 0
  14379. dir: dir isR
  14380. --- END Output Phase ---
  14381. \-/--- Input Phase ---
  14382. =>WM: (14005: I2 ^dir R)
  14383. =>WM: (14004: I2 ^reward 1)
  14384. =>WM: (14003: I2 ^see 1)
  14385. =>WM: (14002: N999 ^status complete)
  14386. <=WM: (13990: I2 ^dir L)
  14387. <=WM: (13989: I2 ^reward 1)
  14388. <=WM: (13988: I2 ^see 0)
  14389. =>WM: (14006: I2 ^level-1 L1-root)
  14390. <=WM: (13991: I2 ^level-1 R0-root)
  14391. --- END Input Phase ---
  14392. --- Proposal Phase ---
  14393. --- Inner Elaboration Phase, active level 1 (S1) ---
  14394. Firing rl*prefer*rvt*predict-no*H0*4*v1*H1*45
  14395. -->
  14396. (S1 ^operator O1998 = -0.02155734064455064)
  14397. Firing rl*prefer*rvt*predict-yes*H0*3*v1*H1*46
  14398. -->
  14399. (S1 ^operator O1997 = 0.815582443315254)
  14400. Firing prefer*rvt*predict-no*H0*4*v1*H1
  14401. -->
  14402. Firing prefer*rvt*predict-yes*H0*3*v1*H1
  14403. -->
  14404. Firing elaborate*copy-see-to-output-link
  14405. -->
  14406. (I3 ^see 1 +)
  14407. Firing elaborate*reward*based*on*reward
  14408. -->
  14409. (R1003 ^value 1 +)
  14410. (R1 ^reward R1003 +)
  14411. Firing propose*predict-yes
  14412. -->
  14413. (O1999 ^name predict-yes +)
  14414. (S1 ^operator O1999 +)
  14415. Firing propose*predict-no
  14416. -->
  14417. (O2000 ^name predict-no +)
  14418. (S1 ^operator O2000 +)
  14419. Firing rl*prefer*rvt*predict-no*H0*4
  14420. -->
  14421. (S1 ^operator O1998 = 0.4476193147022436)
  14422. Firing rl*prefer*rvt*predict-yes*H0*3
  14423. -->
  14424. (S1 ^operator O1997 = 0.1844120719320057)
  14425. Firing prefer*rvt*predict-yes*H0
  14426. -->
  14427. Firing prefer*rvt*predict-no*H0
  14428. -->
  14429. Firing elaborate*copy-dir-to-output-link
  14430. -->
  14431. (I3 ^dir R +)
  14432. inner elaboration loop at bottom goal.
  14433. Retracting elaborate*copy-see-to-output-link
  14434. -->
  14435. (I3 ^see 0 +)
  14436. Retracting propose*predict-no
  14437. -->
  14438. (O1998 ^name predict-no +)
  14439. (S1 ^operator O1998 +)
  14440. Retracting propose*predict-yes
  14441. -->
  14442. (O1997 ^name predict-yes +)
  14443. (S1 ^operator O1997 +)
  14444. Retracting elaborate*reward*based*on*reward
  14445. -->
  14446. (R1002 ^value 1 +)
  14447. (R1 ^reward R1002 +)
  14448. Retracting elaborate*copy-dir-to-output-link
  14449. -->
  14450. (I3 ^dir L +)
  14451. Retracting rl*prefer*rvt*predict-no*H0*2*v1*H1*43
  14452. -->
  14453. (S1 ^operator O1998 = 0.1063475139796038)
  14454. Retracting rl*prefer*rvt*predict-no*H0*2
  14455. -->
  14456. (S1 ^operator O1998 = 0.3873370065427176)
  14457. Retracting rl*prefer*rvt*predict-yes*H0*1*v1*H1*44
  14458. -->
  14459. (S1 ^operator O1997 = 0.6104611932916519)
  14460. Retracting rl*prefer*rvt*predict-yes*H0*1
  14461. -->
  14462. (S1 ^operator O1997 = 0.3895396873671274)
  14463. =>WM: (14014: S1 ^operator O2000 +)
  14464. =>WM: (14013: S1 ^operator O1999 +)
  14465. =>WM: (14012: I3 ^dir R)
  14466. =>WM: (14011: O2000 ^name predict-no)
  14467. =>WM: (14010: O1999 ^name predict-yes)
  14468. =>WM: (14009: R1003 ^value 1)
  14469. =>WM: (14008: R1 ^reward R1003)
  14470. =>WM: (14007: I3 ^see 1)
  14471. <=WM: (13998: S1 ^operator O1997 +)
  14472. <=WM: (14000: S1 ^operator O1997)
  14473. <=WM: (13999: S1 ^operator O1998 +)
  14474. <=WM: (13997: I3 ^dir L)
  14475. <=WM: (13993: R1 ^reward R1002)
  14476. <=WM: (13992: I3 ^see 0)
  14477. <=WM: (13996: O1998 ^name predict-no)
  14478. <=WM: (13995: O1997 ^name predict-yes)
  14479. <=WM: (13994: R1002 ^value 1)
  14480. --- Inner Elaboration Phase, active level 1 (S1) ---
  14481. Firing prefer*rvt*predict-yes*H0
  14482. -->
  14483. Firing rl*prefer*rvt*predict-yes*H0*3
  14484. -->
  14485. (S1 ^operator O1999 = 0.1844120719320057)
  14486. Firing prefer*rvt*predict-yes*H0*3*v1*H1
  14487. -->
  14488. Firing rl*prefer*rvt*predict-yes*H0*3*v1*H1*46
  14489. -->
  14490. (S1 ^operator O1999 = 0.815582443315254)
  14491. Firing prefer*rvt*predict-no*H0
  14492. -->
  14493. Firing rl*prefer*rvt*predict-no*H0*4
  14494. -->
  14495. (S1 ^operator O2000 = 0.4476193147022436)
  14496. Firing prefer*rvt*predict-no*H0*4*v1*H1
  14497. -->
  14498. Firing rl*prefer*rvt*predict-no*H0*4*v1*H1*45
  14499. -->
  14500. (S1 ^operator O2000 = -0.02155734064455064)
  14501. inner elaboration loop at bottom goal.
  14502. Retracting rl*prefer*rvt*predict-no*H0*4
  14503. -->
  14504. (S1 ^operator O1998 = 0.4476193147022436)
  14505. Retracting rl*prefer*rvt*predict-no*H0*4*v1*H1*45
  14506. -->
  14507. (S1 ^operator O1998 = -0.02155734064455064)
  14508. Retracting rl*prefer*rvt*predict-yes*H0*3
  14509. -->
  14510. (S1 ^operator O1997 = 0.1844120719320057)
  14511. Retracting rl*prefer*rvt*predict-yes*H0*3*v1*H1*46
  14512. -->
  14513. (S1 ^operator O1997 = 0.815582443315254)
  14514. --- END Proposal Phase ---
  14515. --- Decision Phase ---
  14516. RL update rl*prefer*rvt*predict-yes*H0*1 0.711951 -0.322412 0.38954 -> 0.711951 -0.322412 0.38954(R,m,v=1,0.892857,0.0962361)
  14517. RL update rl*prefer*rvt*predict-yes*H0*1*v1*H1*44 0.288049 0.322412 0.610461 -> 0.288049 0.322412 0.610461(R,m,v=1,1,0)
  14518. =>WM: (14015: S1 ^operator O1999)
  14519. 1000: O: O1999 (predict-yes)
  14520. --- END Decision Phase ---
  14521. --- Application Phase ---
  14522. --- Firing Productions (PE) For State At Depth 1 ---
  14523. --- Inner Elaboration Phase, active level 1 (S1) ---
  14524. Firing apply*operator
  14525. -->
  14526. (I3 ^predict-yes N1000 + :O )
  14527. Firing apply*operator*complete
  14528. -->
  14529. (I3 ^predict-yes N999 - :O )
  14530. inner elaboration loop at bottom goal.
  14531. --- Change Working Memory (PE) ---
  14532. =>WM: (14016: I3 ^predict-yes N1000)
  14533. <=WM: (14002: N999 ^status complete)
  14534. <=WM: (14001: I3 ^predict-yes N999)
  14535. --- Firing Productions (IE) For State At Depth 1 ---
  14536. --- Inner Elaboration Phase, active level 1 (S1) ---
  14537. Firing monitor*world
  14538. -->
  14539. I see 1 and I'm going to do: predict-yes inner elaboration loop at bottom goal.
  14540. --- Change Working Memory (IE) ---
  14541. --- END Application Phase ---
  14542. --- Output Phase ---
  14543. ENV: Agent did: predict-yes for direction R in state State-A
  14544. In State-A moving R
  14545. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  14546. predict error 0
  14547. dir: dir isU
  14548. --- END Output Phase ---
  14549. |\-/|\-/|\---- Input Phase ---
  14550. =>WM: (14020: I2 ^dir U)
  14551. =>WM: (14019: I2 ^reward 1)
  14552. =>WM: (14018: I2 ^see 1)
  14553. =>WM: (14017: N1000 ^status complete)
  14554. <=WM: (14005: I2 ^dir R)
  14555. <=WM: (14004: I2 ^reward 1)
  14556. <=WM: (14003: I2 ^see 1)
  14557. =>WM: (14021: I2 ^level-1 R1-root)
  14558. <=WM: (14006: I2 ^level-1 L1-root)
  14559. --- END Input Phase ---
  14560. --- Proposal Phase ---
  14561. --- Inner Elaboration Phase, active level 1 (S1) ---
  14562. Firing elaborate*copy-see-to-output-link
  14563. -->
  14564. (I3 ^see 1 +)
  14565. Firing elaborate*reward*based*on*reward
  14566. -->
  14567. (R1004 ^value 1 +)
  14568. (R1 ^reward R1004 +)
  14569. Firing propose*predict-yes
  14570. -->
  14571. (O2001 ^name predict-yes +)
  14572. (S1 ^operator O2001 +)
  14573. Firing propose*predict-no
  14574. -->
  14575. (O2002 ^name predict-no +)
  14576. (S1 ^operator O2002 +)
  14577. Firing rl*prefer*rvt*predict-no*H0*6
  14578. -->
  14579. (S1 ^operator O2000 = 0.9999999999999999)
  14580. Firing rl*prefer*rvt*predict-yes*H0*5
  14581. -->
  14582. (S1 ^operator O1999 = 0.)
  14583. Firing prefer*rvt*predict-yes*H0
  14584. -->
  14585. Firing prefer*rvt*predict-no*H0
  14586. -->
  14587. Firing elaborate*copy-dir-to-output-link
  14588. -->
  14589. (I3 ^dir U +)
  14590. inner elaboration loop at bottom goal.
  14591. Retracting elaborate*copy-see-to-output-link
  14592. -->
  14593. (I3 ^see 1 +)
  14594. Retracting propose*predict-no
  14595. -->
  14596. (O2000 ^name predict-no +)
  14597. (S1 ^operator O2000 +)
  14598. Retracting propose*predict-yes
  14599. -->
  14600. (O1999 ^name predict-yes +)
  14601. (S1 ^operator O1999 +)
  14602. Retracting elaborate*reward*based*on*reward
  14603. -->
  14604. (R1003 ^value 1 +)
  14605. (R1 ^reward R1003 +)
  14606. Retracting elaborate*copy-dir-to-output-link
  14607. -->
  14608. (I3 ^dir R +)
  14609. Retracting rl*prefer*rvt*predict-no*H0*4*v1*H1*45
  14610. -->
  14611. (S1 ^operator O2000 = -0.02155734064455064)
  14612. Retracting rl*prefer*rvt*predict-no*H0*4
  14613. -->
  14614. (S1 ^operator O2000 = 0.4476193147022436)
  14615. Retracting rl*prefer*rvt*predict-yes*H0*3*v1*H1*46
  14616. -->
  14617. (S1 ^operator O1999 = 0.815582443315254)
  14618. Retracting rl*prefer*rvt*predict-yes*H0*3
  14619. -->
  14620. (S1 ^operator O1999 = 0.1844120719320057)
  14621. =>WM: (14028: S1 ^operator O2002 +)
  14622. =>WM: (14027: S1 ^operator O2001 +)
  14623. =>WM: (14026: I3 ^dir U)
  14624. =>WM: (14025: O2002 ^name predict-no)
  14625. =>WM: (14024: O2001 ^name predict-yes)
  14626. =>WM: (14023: R1004 ^value 1)
  14627. =>WM: (14022: R1 ^reward R1004)
  14628. <=WM: (14013: S1 ^operator O1999 +)
  14629. <=WM: (14015: S1 ^operator O1999)
  14630. <=WM: (14014: S1 ^operator O2000 +)
  14631. <=WM: (14012: I3 ^dir R)
  14632. <=WM: (14008: R1 ^reward R1003)
  14633. <=WM: (14011: O2000 ^name predict-no)
  14634. <=WM: (14010: O1999 ^name predict-yes)
  14635. <=WM: (14009: R1003 ^value 1)
  14636. --- Inner Elaboration Phase, active level 1 (S1) ---
  14637. Firing prefer*rvt*predict-yes*H0
  14638. -->
  14639. Firing rl*prefer*rvt*predict-yes*H0*5
  14640. -->
  14641. (S1 ^operator O2001 = 0.)
  14642. Firing prefer*rvt*predict-no*H0
  14643. -->
  14644. Firing rl*prefer*rvt*predict-no*H0*6
  14645. -->
  14646. (S1 ^operator O2002 = 0.9999999999999999)
  14647. inner elaboration loop at bottom goal.
  14648. Retracting rl*prefer*rvt*predict-no*H0*6
  14649. -->
  14650. (S1 ^operator O2000 = 0.9999999999999999)
  14651. Retracting rl*prefer*rvt*predict-yes*H0*5
  14652. -->
  14653. (S1 ^operator O1999 = 0.)
  14654. --- END Proposal Phase ---
  14655. --- Decision Phase ---
  14656. RL update rl*prefer*rvt*predict-yes*H0*3 0.675415 -0.491003 0.184412 -> 0.675416 -0.491003 0.184413(R,m,v=1,0.900585,0.0900585)
  14657. RL update rl*prefer*rvt*predict-yes*H0*3*v1*H1*46 0.324578 0.491005 0.815582 -> 0.324579 0.491004 0.815583(R,m,v=1,1,0)
  14658. =>WM: (14029: S1 ^operator O2002)
  14659. 1001: O: O2002 (predict-no)
  14660. --- END Decision Phase ---
  14661. --- Application Phase ---
  14662. --- Firing Productions (PE) For State At Depth 1 ---
  14663. --- Inner Elaboration Phase, active level 1 (S1) ---
  14664. Firing apply*operator
  14665. -->
  14666. (I3 ^predict-no N1001 + :O )
  14667. Firing apply*operator*complete
  14668. -->
  14669. (I3 ^predict-yes N1000 - :O )
  14670. inner elaboration loop at bottom goal.
  14671. --- Change Working Memory (PE) ---
  14672. =>WM: (14030: I3 ^predict-no N1001)
  14673. <=WM: (14017: N1000 ^status complete)
  14674. <=WM: (14016: I3 ^predict-yes N1000)
  14675. --- Firing Productions (IE) For State At Depth 1 ---
  14676. --- Inner Elaboration Phase, active level 1 (S1) ---
  14677. Firing monitor*world
  14678. -->
  14679. I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
  14680. --- Change Working Memory (IE) ---
  14681. --- END Application Phase ---
  14682. --- Output Phase ---
  14683. ENV: Agent did: predict-no for direction U in state State-B
  14684. In State-B moving U
  14685. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  14686. predict error 0
  14687. dir: dir isL
  14688. --- END Output Phase ---
  14689. /--- Input Phase ---
  14690. =>WM: (14034: I2 ^dir L)
  14691. =>WM: (14033: I2 ^reward 1)
  14692. =>WM: (14032: I2 ^see 0)
  14693. =>WM: (14031: N1001 ^status complete)
  14694. <=WM: (14020: I2 ^dir U)
  14695. <=WM: (14019: I2 ^reward 1)
  14696. <=WM: (14018: I2 ^see 1)
  14697. =>WM: (14035: I2 ^level-1 R1-root)
  14698. <=WM: (14021: I2 ^level-1 R1-root)
  14699. --- END Input Phase ---
  14700. --- Proposal Phase ---
  14701. --- Inner Elaboration Phase, active level 1 (S1) ---
  14702. Firing rl*prefer*rvt*predict-yes*H0*1*v1*H1*36
  14703. -->
  14704. (S1 ^operator O2001 = 0.6104596086348102)
  14705. Firing rl*prefer*rvt*predict-no*H0*2*v1*H1*35
  14706. -->
  14707. (S1 ^operator O2002 = 0.2714993082286609)
  14708. Firing prefer*rvt*predict-no*H0*2*v1*H1
  14709. -->
  14710. Firing prefer*rvt*predict-yes*H0*1*v1*H1
  14711. -->
  14712. Firing elaborate*copy-see-to-output-link
  14713. -->
  14714. (I3 ^see 0 +)
  14715. Firing elaborate*reward*based*on*reward
  14716. -->
  14717. (R1005 ^value 1 +)
  14718. (R1 ^reward R1005 +)
  14719. Firing propose*predict-yes
  14720. -->
  14721. (O2003 ^name predict-yes +)
  14722. (S1 ^operator O2003 +)
  14723. Firing propose*predict-no
  14724. -->
  14725. (O2004 ^name predict-no +)
  14726. (S1 ^operator O2004 +)
  14727. Firing rl*prefer*rvt*predict-no*H0*2
  14728. -->
  14729. (S1 ^operator O2002 = 0.3873370065427176)
  14730. Firing rl*prefer*rvt*predict-yes*H0*1
  14731. -->
  14732. (S1 ^operator O2001 = 0.3895395552683104)
  14733. Firing prefer*rvt*predict-yes*H0
  14734. -->
  14735. Firing prefer*rvt*predict-no*H0
  14736. -->
  14737. Firing elaborate*copy-dir-to-output-link
  14738. -->
  14739. (I3 ^dir L +)
  14740. inner elaboration loop at bottom goal.
  14741. Retracting elaborate*copy-see-to-output-link
  14742. -->
  14743. (I3 ^see 1 +)
  14744. Retracting propose*predict-no
  14745. -->
  14746. (O2002 ^name predict-no +)
  14747. (S1 ^operator O2002 +)
  14748. Retracting propose*predict-yes
  14749. -->
  14750. (O2001 ^name predict-yes +)
  14751. (S1 ^operator O2001 +)
  14752. Retracting elaborate*reward*based*on*reward
  14753. -->
  14754. (R1004 ^value 1 +)
  14755. (R1 ^reward R1004 +)
  14756. Retracting elaborate*copy-dir-to-output-link
  14757. -->
  14758. (I3 ^dir U +)
  14759. Retracting rl*prefer*rvt*predict-no*H0*6
  14760. -->
  14761. (S1 ^operator O2002 = 0.9999999999999999)
  14762. Retracting rl*prefer*rvt*predict-yes*H0*5
  14763. -->
  14764. (S1 ^operator O2001 = 0.)
  14765. =>WM: (14043: S1 ^operator O2004 +)
  14766. =>WM: (14042: S1 ^operator O2003 +)
  14767. =>WM: (14041: I3 ^dir L)
  14768. =>WM: (14040: O2004 ^name predict-no)
  14769. =>WM: (14039: O2003 ^name predict-yes)
  14770. =>WM: (14038: R1005 ^value 1)
  14771. =>WM: (14037: R1 ^reward R1005)
  14772. =>WM: (14036: I3 ^see 0)
  14773. <=WM: (14027: S1 ^operator O2001 +)
  14774. <=WM: (14028: S1 ^operator O2002 +)
  14775. <=WM: (14029: S1 ^operator O2002)
  14776. <=WM: (14026: I3 ^dir U)
  14777. <=WM: (14022: R1 ^reward R1004)
  14778. <=WM: (14007: I3 ^see 1)
  14779. <=WM: (14025: O2002 ^name predict-no)
  14780. <=WM: (14024: O2001 ^name predict-yes)
  14781. <=WM: (14023: R1004 ^value 1)
  14782. --- Inner Elaboration Phase, active level 1 (S1) ---
  14783. Firing prefer*rvt*predict-yes*H0
  14784. -->
  14785. Firing rl*prefer*rvt*predict-yes*H0*1*v1*H1*36
  14786. -->
  14787. (S1 ^operator O2003 = 0.6104596086348102)
  14788. Firing rl*prefer*rvt*predict-yes*H0*1
  14789. -->
  14790. (S1 ^operator O2003 = 0.3895395552683104)
  14791. Firing prefer*rvt*predict-yes*H0*1*v1*H1
  14792. -->
  14793. Firing prefer*rvt*predict-no*H0
  14794. -->
  14795. Firing rl*prefer*rvt*predict-no*H0*2*v1*H1*35
  14796. -->
  14797. (S1 ^operator O2004 = 0.2714993082286609)
  14798. Firing rl*prefer*rvt*predict-no*H0*2
  14799. -->
  14800. (S1 ^operator O2004 = 0.3873370065427176)
  14801. Firing prefer*rvt*predict-no*H0*2*v1*H1
  14802. -->
  14803. inner elaboration loop at bottom goal.
  14804. Retracting rl*prefer*rvt*predict-no*H0*2
  14805. -->
  14806. (S1 ^operator O2002 = 0.3873370065427176)
  14807. Retracting rl*prefer*rvt*predict-no*H0*2*v1*H1*35
  14808. -->
  14809. (S1 ^operator O2002 = 0.2714993082286609)
  14810. Retracting rl*prefer*rvt*predict-yes*H0*1
  14811. -->
  14812. (S1 ^operator O2001 = 0.3895395552683104)
  14813. Retracting rl*prefer*rvt*predict-yes*H0*1*v1*H1*36
  14814. -->
  14815. (S1 ^operator O2001 = 0.6104596086348102)
  14816. --- END Proposal Phase ---
  14817. --- Decision Phase ---
  14818. RL update rl*prefer*rvt*predict-no*H0*6 1 0 1 -> 1 0 1(R,m,v=1,1,0)
  14819. =>WM: (14044: S1 ^operator O2003)
  14820. 1002: O: O2003 (predict-yes)
  14821. --- END Decision Phase ---
  14822. --- Application Phase ---
  14823. --- Firing Productions (PE) For State At Depth 1 ---
  14824. --- Inner Elaboration Phase, active level 1 (S1) ---
  14825. Firing apply*operator
  14826. -->
  14827. (I3 ^predict-yes N1002 + :O )
  14828. Firing apply*operator*complete
  14829. -->
  14830. (I3 ^predict-no N1001 - :O )
  14831. inner elaboration loop at bottom goal.
  14832. --- Change Working Memory (PE) ---
  14833. =>WM: (14045: I3 ^predict-yes N1002)
  14834. <=WM: (14031: N1001 ^status complete)
  14835. <=WM: (14030: I3 ^predict-no N1001)
  14836. --- Firing Productions (IE) For State At Depth 1 ---
  14837. --- Inner Elaboration Phase, active level 1 (S1) ---
  14838. Firing monitor*world
  14839. -->
  14840. I see 1 and I'm going to do: predict-yes inner elaboration loop at bottom goal.
  14841. --- Change Working Memory (IE) ---
  14842. --- END Application Phase ---
  14843. --- Output Phase ---
  14844. ENV: Agent did: predict-yes for direction L in state State-B
  14845. In State-B moving L
  14846. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  14847. predict error 0
  14848. dir: dir isL
  14849. --- END Output Phase ---
  14850. |\-/--- Input Phase ---
  14851. =>WM: (14049: I2 ^dir L)
  14852. =>WM: (14048: I2 ^reward 1)
  14853. =>WM: (14047: I2 ^see 1)
  14854. =>WM: (14046: N1002 ^status complete)
  14855. <=WM: (14034: I2 ^dir L)
  14856. <=WM: (14033: I2 ^reward 1)
  14857. <=WM: (14032: I2 ^see 0)
  14858. =>WM: (14050: I2 ^level-1 L1-root)
  14859. <=WM: (14035: I2 ^level-1 R1-root)
  14860. --- END Input Phase ---
  14861. --- Proposal Phase ---
  14862. --- Inner Elaboration Phase, active level 1 (S1) ---
  14863. Firing rl*prefer*rvt*predict-no*H0*2*v1*H1*32
  14864. -->
  14865. (S1 ^operator O2004 = 0.6126627914480096)
  14866. Firing rl*prefer*rvt*predict-yes*H0*1*v1*H1*31
  14867. -->
  14868. (S1 ^operator O2003 = -0.02274740735326741)
  14869. Firing prefer*rvt*predict-no*H0*2*v1*H1
  14870. -->
  14871. Firing prefer*rvt*predict-yes*H0*1*v1*H1
  14872. -->
  14873. Firing elaborate*copy-see-to-output-link
  14874. -->
  14875. (I3 ^see 1 +)
  14876. Firing elaborate*reward*based*on*reward
  14877. -->
  14878. (R1006 ^value 1 +)
  14879. (R1 ^reward R1006 +)
  14880. Firing propose*predict-yes
  14881. -->
  14882. (O2005 ^name predict-yes +)
  14883. (S1 ^operator O2005 +)
  14884. Firing propose*predict-no
  14885. -->
  14886. (O2006 ^name predict-no +)
  14887. (S1 ^operator O2006 +)
  14888. Firing rl*prefer*rvt*predict-no*H0*2
  14889. -->
  14890. (S1 ^operator O2004 = 0.3873370065427176)
  14891. Firing rl*prefer*rvt*predict-yes*H0*1
  14892. -->
  14893. (S1 ^operator O2003 = 0.3895395552683104)
  14894. Firing prefer*rvt*predict-yes*H0
  14895. -->
  14896. Firing prefer*rvt*predict-no*H0
  14897. -->
  14898. Firing elaborate*copy-dir-to-output-link
  14899. -->
  14900. (I3 ^dir L +)
  14901. inner elaboration loop at bottom goal.
  14902. Retracting elaborate*copy-see-to-output-link
  14903. -->
  14904. (I3 ^see 0 +)
  14905. Retracting propose*predict-no
  14906. -->
  14907. (O2004 ^name predict-no +)
  14908. (S1 ^operator O2004 +)
  14909. Retracting propose*predict-yes
  14910. -->
  14911. (O2003 ^name predict-yes +)
  14912. (S1 ^operator O2003 +)
  14913. Retracting elaborate*reward*based*on*reward
  14914. -->
  14915. (R1005 ^value 1 +)
  14916. (R1 ^reward R1005 +)
  14917. Retracting elaborate*copy-dir-to-output-link
  14918. -->
  14919. (I3 ^dir L +)
  14920. Retracting rl*prefer*rvt*predict-no*H0*2
  14921. -->
  14922. (S1 ^operator O2004 = 0.3873370065427176)
  14923. Retracting rl*prefer*rvt*predict-no*H0*2*v1*H1*35
  14924. -->
  14925. (S1 ^operator O2004 = 0.2714993082286609)
  14926. Retracting rl*prefer*rvt*predict-yes*H0*1
  14927. -->
  14928. (S1 ^operator O2003 = 0.3895395552683104)
  14929. Retracting rl*prefer*rvt*predict-yes*H0*1*v1*H1*36
  14930. -->
  14931. (S1 ^operator O2003 = 0.6104596086348102)
  14932. =>WM: (14057: S1 ^operator O2006 +)
  14933. =>WM: (14056: S1 ^operator O2005 +)
  14934. =>WM: (14055: O2006 ^name predict-no)
  14935. =>WM: (14054: O2005 ^name predict-yes)
  14936. =>WM: (14053: R1006 ^value 1)
  14937. =>WM: (14052: R1 ^reward R1006)
  14938. =>WM: (14051: I3 ^see 1)
  14939. <=WM: (14042: S1 ^operator O2003 +)
  14940. <=WM: (14044: S1 ^operator O2003)
  14941. <=WM: (14043: S1 ^operator O2004 +)
  14942. <=WM: (14037: R1 ^reward R1005)
  14943. <=WM: (14036: I3 ^see 0)
  14944. <=WM: (14040: O2004 ^name predict-no)
  14945. <=WM: (14039: O2003 ^name predict-yes)
  14946. <=WM: (14038: R1005 ^value 1)
  14947. --- Inner Elaboration Phase, active level 1 (S1) ---
  14948. Firing prefer*rvt*predict-yes*H0
  14949. -->
  14950. Firing rl*prefer*rvt*predict-yes*H0*1
  14951. -->
  14952. (S1 ^operator O2005 = 0.3895395552683104)
  14953. Firing prefer*rvt*predict-yes*H0*1*v1*H1
  14954. -->
  14955. Firing rl*prefer*rvt*predict-yes*H0*1*v1*H1*31
  14956. -->
  14957. (S1 ^operator O2005 = -0.02274740735326741)
  14958. Firing prefer*rvt*predict-no*H0
  14959. -->
  14960. Firing rl*prefer*rvt*predict-no*H0*2
  14961. -->
  14962. (S1 ^operator O2006 = 0.3873370065427176)
  14963. Firing prefer*rvt*predict-no*H0*2*v1*H1
  14964. -->
  14965. Firing rl*prefer*rvt*predict-no*H0*2*v1*H1*32
  14966. -->
  14967. (S1 ^operator O2006 = 0.6126627914480096)
  14968. inner elaboration loop at bottom goal.
  14969. Retracting rl*prefer*rvt*predict-no*H0*2
  14970. -->
  14971. (S1 ^operator O2004 = 0.3873370065427176)
  14972. Retracting rl*prefer*rvt*predict-no*H0*2*v1*H1*32
  14973. -->
  14974. (S1 ^operator O2004 = 0.6126627914480096)
  14975. Retracting rl*prefer*rvt*predict-yes*H0*1
  14976. -->
  14977. (S1 ^operator O2003 = 0.3895395552683104)
  14978. Retracting rl*prefer*rvt*predict-yes*H0*1*v1*H1*31
  14979. -->
  14980. (S1 ^operator O2003 = -0.02274740735326741)
  14981. --- END Proposal Phase ---
  14982. --- Decision Phase ---
  14983. RL update rl*prefer*rvt*predict-yes*H0*1 0.711951 -0.322412 0.38954 -> 0.711951 -0.322412 0.38954(R,m,v=1,0.893491,0.0957312)
  14984. RL update rl*prefer*rvt*predict-yes*H0*1*v1*H1*36 0.288049 0.322411 0.61046 -> 0.288049 0.322411 0.61046(R,m,v=1,1,0)
  14985. =>WM: (14058: S1 ^operator O2006)
  14986. 1003: O: O2006 (predict-no)
  14987. --- END Decision Phase ---
  14988. --- Application Phase ---
  14989. --- Firing Productions (PE) For State At Depth 1 ---
  14990. --- Inner Elaboration Phase, active level 1 (S1) ---
  14991. Firing apply*operator
  14992. -->
  14993. (I3 ^predict-no N1003 + :O )
  14994. Firing apply*operator*complete
  14995. -->
  14996. (I3 ^predict-yes N1002 - :O )
  14997. inner elaboration loop at bottom goal.
  14998. --- Change Working Memory (PE) ---
  14999. =>WM: (14059: I3 ^predict-no N1003)
  15000. <=WM: (14046: N1002 ^status complete)
  15001. <=WM: (14045: I3 ^predict-yes N1002)
  15002. --- Firing Productions (IE) For State At Depth 1 ---
  15003. --- Inner Elaboration Phase, active level 1 (S1) ---
  15004. Firing monitor*world
  15005. -->
  15006. I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
  15007. --- Change Working Memory (IE) ---
  15008. --- END Application Phase ---
  15009. --- Output Phase ---
  15010. ENV: Agent did: predict-no for direction L in state State-A
  15011. In State-A moving L
  15012. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  15013. predict error 0
  15014. dir: dir isR
  15015. --- END Output Phase ---
  15016. |\---- Input Phase ---
  15017. =>WM: (14063: I2 ^dir R)
  15018. =>WM: (14062: I2 ^reward 1)
  15019. =>WM: (14061: I2 ^see 0)
  15020. =>WM: (14060: N1003 ^status complete)
  15021. <=WM: (14049: I2 ^dir L)
  15022. <=WM: (14048: I2 ^reward 1)
  15023. <=WM: (14047: I2 ^see 1)
  15024. =>WM: (14064: I2 ^level-1 L0-root)
  15025. <=WM: (14050: I2 ^level-1 L1-root)
  15026. --- END Input Phase ---
  15027. --- Proposal Phase ---
  15028. --- Inner Elaboration Phase, active level 1 (S1) ---
  15029. Firing rl*prefer*rvt*predict-yes*H0*3*v1*H1*34
  15030. -->
  15031. (S1 ^operator O2005 = 0.8155935357860071)
  15032. Firing rl*prefer*rvt*predict-no*H0*4*v1*H1*33
  15033. -->
  15034. (S1 ^operator O2006 = -0.00558448899823713)
  15035. Firing prefer*rvt*predict-no*H0*4*v1*H1
  15036. -->
  15037. Firing prefer*rvt*predict-yes*H0*3*v1*H1
  15038. -->
  15039. Firing elaborate*copy-see-to-output-link
  15040. -->
  15041. (I3 ^see 0 +)
  15042. Firing elaborate*reward*based*on*reward
  15043. -->
  15044. (R1007 ^value 1 +)
  15045. (R1 ^reward R1007 +)
  15046. Firing propose*predict-yes
  15047. -->
  15048. (O2007 ^name predict-yes +)
  15049. (S1 ^operator O2007 +)
  15050. Firing propose*predict-no
  15051. -->
  15052. (O2008 ^name predict-no +)
  15053. (S1 ^operator O2008 +)
  15054. Firing rl*prefer*rvt*predict-no*H0*4
  15055. -->
  15056. (S1 ^operator O2006 = 0.4476193147022436)
  15057. Firing rl*prefer*rvt*predict-yes*H0*3
  15058. -->
  15059. (S1 ^operator O2005 = 0.1844128946449167)
  15060. Firing prefer*rvt*predict-yes*H0
  15061. -->
  15062. Firing prefer*rvt*predict-no*H0
  15063. -->
  15064. Firing elaborate*copy-dir-to-output-link
  15065. -->
  15066. (I3 ^dir R +)
  15067. inner elaboration loop at bottom goal.
  15068. Retracting elaborate*copy-see-to-output-link
  15069. -->
  15070. (I3 ^see 1 +)
  15071. Retracting propose*predict-no
  15072. -->
  15073. (O2006 ^name predict-no +)
  15074. (S1 ^operator O2006 +)
  15075. Retracting propose*predict-yes
  15076. -->
  15077. (O2005 ^name predict-yes +)
  15078. (S1 ^operator O2005 +)
  15079. Retracting elaborate*reward*based*on*reward
  15080. -->
  15081. (R1006 ^value 1 +)
  15082. (R1 ^reward R1006 +)
  15083. Retracting elaborate*copy-dir-to-output-link
  15084. -->
  15085. (I3 ^dir L +)
  15086. Retracting rl*prefer*rvt*predict-no*H0*2*v1*H1*32
  15087. -->
  15088. (S1 ^operator O2006 = 0.6126627914480096)
  15089. Retracting rl*prefer*rvt*predict-no*H0*2
  15090. -->
  15091. (S1 ^operator O2006 = 0.3873370065427176)
  15092. Retracting rl*prefer*rvt*predict-yes*H0*1*v1*H1*31
  15093. -->
  15094. (S1 ^operator O2005 = -0.02274740735326741)
  15095. Retracting rl*prefer*rvt*predict-yes*H0*1
  15096. -->
  15097. (S1 ^operator O2005 = 0.3895396806828423)
  15098. =>WM: (14072: S1 ^operator O2008 +)
  15099. =>WM: (14071: S1 ^operator O2007 +)
  15100. =>WM: (14070: I3 ^dir R)
  15101. =>WM: (14069: O2008 ^name predict-no)
  15102. =>WM: (14068: O2007 ^name predict-yes)
  15103. =>WM: (14067: R1007 ^value 1)
  15104. =>WM: (14066: R1 ^reward R1007)
  15105. =>WM: (14065: I3 ^see 0)
  15106. <=WM: (14056: S1 ^operator O2005 +)
  15107. <=WM: (14057: S1 ^operator O2006 +)
  15108. <=WM: (14058: S1 ^operator O2006)
  15109. <=WM: (14041: I3 ^dir L)
  15110. <=WM: (14052: R1 ^reward R1006)
  15111. <=WM: (14051: I3 ^see 1)
  15112. <=WM: (14055: O2006 ^name predict-no)
  15113. <=WM: (14054: O2005 ^name predict-yes)
  15114. <=WM: (14053: R1006 ^value 1)
  15115. --- Inner Elaboration Phase, active level 1 (S1) ---
  15116. Firing prefer*rvt*predict-yes*H0
  15117. -->
  15118. Firing rl*prefer*rvt*predict-yes*H0*3
  15119. -->
  15120. (S1 ^operator O2007 = 0.1844128946449167)
  15121. Firing prefer*rvt*predict-yes*H0*3*v1*H1
  15122. -->
  15123. Firing rl*prefer*rvt*predict-yes*H0*3*v1*H1*34
  15124. -->
  15125. (S1 ^operator O2007 = 0.8155935357860071)
  15126. Firing prefer*rvt*predict-no*H0
  15127. -->
  15128. Firing rl*prefer*rvt*predict-no*H0*4
  15129. -->
  15130. (S1 ^operator O2008 = 0.4476193147022436)
  15131. Firing prefer*rvt*predict-no*H0*4*v1*H1
  15132. -->
  15133. Firing rl*prefer*rvt*predict-no*H0*4*v1*H1*33
  15134. -->
  15135. (S1 ^operator O2008 = -0.00558448899823713)
  15136. inner elaboration loop at bottom goal.
  15137. Retracting rl*prefer*rvt*predict-no*H0*4
  15138. -->
  15139. (S1 ^operator O2006 = 0.4476193147022436)
  15140. Retracting rl*prefer*rvt*predict-no*H0*4*v1*H1*33
  15141. -->
  15142. (S1 ^operator O2006 = -0.00558448899823713)
  15143. Retracting rl*prefer*rvt*predict-yes*H0*3
  15144. -->
  15145. (S1 ^operator O2005 = 0.1844128946449167)
  15146. Retracting rl*prefer*rvt*predict-yes*H0*3*v1*H1*34
  15147. -->
  15148. (S1 ^operator O2005 = 0.8155935357860071)
  15149. --- END Proposal Phase ---
  15150. --- Decision Phase ---
  15151. RL update rl*prefer*rvt*predict-no*H0*2 0.719081 -0.331744 0.387337 -> 0.719081 -0.331744 0.387337(R,m,v=1,0.932203,0.0635593)
  15152. RL update rl*prefer*rvt*predict-no*H0*2*v1*H1*32 0.280919 0.331744 0.612663 -> 0.280919 0.331744 0.612663(R,m,v=1,1,0)
  15153. =>WM: (14073: S1 ^operator O2007)
  15154. 1004: O: O2007 (predict-yes)
  15155. --- END Decision Phase ---
  15156. --- Application Phase ---
  15157. --- Firing Productions (PE) For State At Depth 1 ---
  15158. --- Inner Elaboration Phase, active level 1 (S1) ---
  15159. Firing apply*operator
  15160. -->
  15161. (I3 ^predict-yes N1004 + :O )
  15162. Firing apply*operator*complete
  15163. -->
  15164. (I3 ^predict-no N1003 - :O )
  15165. inner elaboration loop at bottom goal.
  15166. --- Change Working Memory (PE) ---
  15167. =>WM: (14074: I3 ^predict-yes N1004)
  15168. <=WM: (14060: N1003 ^status complete)
  15169. <=WM: (14059: I3 ^predict-no N1003)
  15170. --- Firing Productions (IE) For State At Depth 1 ---
  15171. --- Inner Elaboration Phase, active level 1 (S1) ---
  15172. Firing monitor*world
  15173. -->
  15174. I see 1 and I'm going to do: predict-yes inner elaboration loop at bottom goal.
  15175. --- Change Working Memory (IE) ---
  15176. --- END Application Phase ---
  15177. --- Output Phase ---
  15178. ENV: Agent did: predict-yes for direction R in state State-A
  15179. In State-A moving R
  15180. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  15181. predict error 0
  15182. dir: dir isU
  15183. --- END Output Phase ---
  15184. /|--- Input Phase ---
  15185. =>WM: (14078: I2 ^dir U)
  15186. =>WM: (14077: I2 ^reward 1)
  15187. =>WM: (14076: I2 ^see 1)
  15188. =>WM: (14075: N1004 ^status complete)
  15189. <=WM: (14063: I2 ^dir R)
  15190. <=WM: (14062: I2 ^reward 1)
  15191. <=WM: (14061: I2 ^see 0)
  15192. =>WM: (14079: I2 ^level-1 R1-root)
  15193. <=WM: (14064: I2 ^level-1 L0-root)
  15194. --- END Input Phase ---
  15195. --- Proposal Phase ---
  15196. --- Inner Elaboration Phase, active level 1 (S1) ---
  15197. Firing elaborate*copy-see-to-output-link
  15198. -->
  15199. (I3 ^see 1 +)
  15200. Firing elaborate*reward*based*on*reward
  15201. -->
  15202. (R1008 ^value 1 +)
  15203. (R1 ^reward R1008 +)
  15204. Firing propose*predict-yes
  15205. -->
  15206. (O2009 ^name predict-yes +)
  15207. (S1 ^operator O2009 +)
  15208. Firing propose*predict-no
  15209. -->
  15210. (O2010 ^name predict-no +)
  15211. (S1 ^operator O2010 +)
  15212. Firing rl*prefer*rvt*predict-no*H0*6
  15213. -->
  15214. (S1 ^operator O2008 = 0.9999999999999999)
  15215. Firing rl*prefer*rvt*predict-yes*H0*5
  15216. -->
  15217. (S1 ^operator O2007 = 0.)
  15218. Firing prefer*rvt*predict-yes*H0
  15219. -->
  15220. Firing prefer*rvt*predict-no*H0
  15221. -->
  15222. Firing elaborate*copy-dir-to-output-link
  15223. -->
  15224. (I3 ^dir U +)
  15225. inner elaboration loop at bottom goal.
  15226. Retracting elaborate*copy-see-to-output-link
  15227. -->
  15228. (I3 ^see 0 +)
  15229. Retracting propose*predict-no
  15230. -->
  15231. (O2008 ^name predict-no +)
  15232. (S1 ^operator O2008 +)
  15233. Retracting propose*predict-yes
  15234. -->
  15235. (O2007 ^name predict-yes +)
  15236. (S1 ^operator O2007 +)
  15237. Retracting elaborate*reward*based*on*reward
  15238. -->
  15239. (R1007 ^value 1 +)
  15240. (R1 ^reward R1007 +)
  15241. Retracting elaborate*copy-dir-to-output-link
  15242. -->
  15243. (I3 ^dir R +)
  15244. Retracting rl*prefer*rvt*predict-no*H0*4*v1*H1*33
  15245. -->
  15246. (S1 ^operator O2008 = -0.00558448899823713)
  15247. Retracting rl*prefer*rvt*predict-no*H0*4
  15248. -->
  15249. (S1 ^operator O2008 = 0.4476193147022436)
  15250. Retracting rl*prefer*rvt*predict-yes*H0*3*v1*H1*34
  15251. -->
  15252. (S1 ^operator O2007 = 0.8155935357860071)
  15253. Retracting rl*prefer*rvt*predict-yes*H0*3
  15254. -->
  15255. (S1 ^operator O2007 = 0.1844128946449167)
  15256. =>WM: (14087: S1 ^operator O2010 +)
  15257. =>WM: (14086: S1 ^operator O2009 +)
  15258. =>WM: (14085: I3 ^dir U)
  15259. =>WM: (14084: O2010 ^name predict-no)
  15260. =>WM: (14083: O2009 ^name predict-yes)
  15261. =>WM: (14082: R1008 ^value 1)
  15262. =>WM: (14081: R1 ^reward R1008)
  15263. =>WM: (14080: I3 ^see 1)
  15264. <=WM: (14071: S1 ^operator O2007 +)
  15265. <=WM: (14073: S1 ^operator O2007)
  15266. <=WM: (14072: S1 ^operator O2008 +)
  15267. <=WM: (14070: I3 ^dir R)
  15268. <=WM: (14066: R1 ^reward R1007)
  15269. <=WM: (14065: I3 ^see 0)
  15270. <=WM: (14069: O2008 ^name predict-no)
  15271. <=WM: (14068: O2007 ^name predict-yes)
  15272. <=WM: (14067: R1007 ^value 1)
  15273. --- Inner Elaboration Phase, active level 1 (S1) ---
  15274. Firing prefer*rvt*predict-yes*H0
  15275. -->
  15276. Firing rl*prefer*rvt*predict-yes*H0*5
  15277. -->
  15278. (S1 ^operator O2009 = 0.)
  15279. Firing prefer*rvt*predict-no*H0
  15280. -->
  15281. Firing rl*prefer*rvt*predict-no*H0*6
  15282. -->
  15283. (S1 ^operator O2010 = 0.9999999999999999)
  15284. inner elaboration loop at bottom goal.
  15285. Retracting rl*prefer*rvt*predict-no*H0*6
  15286. -->
  15287. (S1 ^operator O2008 = 0.9999999999999999)
  15288. Retracting rl*prefer*rvt*predict-yes*H0*5
  15289. -->
  15290. (S1 ^operator O2007 = 0.)
  15291. --- END Proposal Phase ---
  15292. --- Decision Phase ---
  15293. RL update rl*prefer*rvt*predict-yes*H0*3 0.675416 -0.491003 0.184413 -> 0.675415 -0.491003 0.184412(R,m,v=1,0.901163,0.0895893)
  15294. RL update rl*prefer*rvt*predict-yes*H0*3*v1*H1*34 0.324592 0.491001 0.815594 -> 0.324591 0.491001 0.815593(R,m,v=1,1,0)
  15295. =>WM: (14088: S1 ^operator O2010)
  15296. 1005: O: O2010 (predict-no)
  15297. --- END Decision Phase ---
  15298. --- Application Phase ---
  15299. --- Firing Productions (PE) For State At Depth 1 ---
  15300. --- Inner Elaboration Phase, active level 1 (S1) ---
  15301. Firing apply*operator
  15302. -->
  15303. (I3 ^predict-no N1005 + :O )
  15304. Firing apply*operator*complete
  15305. -->
  15306. (I3 ^predict-yes N1004 - :O )
  15307. inner elaboration loop at bottom goal.
  15308. --- Change Working Memory (PE) ---
  15309. =>WM: (14089: I3 ^predict-no N1005)
  15310. <=WM: (14075: N1004 ^status complete)
  15311. <=WM: (14074: I3 ^predict-yes N1004)
  15312. --- Firing Productions (IE) For State At Depth 1 ---
  15313. --- Inner Elaboration Phase, active level 1 (S1) ---
  15314. Firing monitor*world
  15315. -->
  15316. I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
  15317. --- Change Working Memory (IE) ---
  15318. --- END Application Phase ---
  15319. --- Output Phase ---
  15320. ENV: Agent did: predict-no for direction U in state State-B
  15321. In State-B moving U
  15322. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  15323. predict error 0
  15324. dir: dir isL
  15325. --- END Output Phase ---
  15326. \-/|--- Input Phase ---
  15327. =>WM: (14093: I2 ^dir L)
  15328. =>WM: (14092: I2 ^reward 1)
  15329. =>WM: (14091: I2 ^see 0)
  15330. =>WM: (14090: N1005 ^status complete)
  15331. <=WM: (14078: I2 ^dir U)
  15332. <=WM: (14077: I2 ^reward 1)
  15333. <=WM: (14076: I2 ^see 1)
  15334. =>WM: (14094: I2 ^level-1 R1-root)
  15335. <=WM: (14079: I2 ^level-1 R1-root)
  15336. --- END Input Phase ---
  15337. --- Proposal Phase ---
  15338. --- Inner Elaboration Phase, active level 1 (S1) ---
  15339. Firing rl*prefer*rvt*predict-yes*H0*1*v1*H1*36
  15340. -->
  15341. (S1 ^operator O2009 = 0.6104597340493421)
  15342. Firing rl*prefer*rvt*predict-no*H0*2*v1*H1*35
  15343. -->
  15344. (S1 ^operator O2010 = 0.2714993082286609)
  15345. Firing prefer*rvt*predict-no*H0*2*v1*H1
  15346. -->
  15347. Firing prefer*rvt*predict-yes*H0*1*v1*H1
  15348. -->
  15349. Firing elaborate*copy-see-to-output-link
  15350. -->
  15351. (I3 ^see 0 +)
  15352. Firing elaborate*reward*based*on*reward
  15353. -->
  15354. (R1009 ^value 1 +)
  15355. (R1 ^reward R1009 +)
  15356. Firing propose*predict-yes
  15357. -->
  15358. (O2011 ^name predict-yes +)
  15359. (S1 ^operator O2011 +)
  15360. Firing propose*predict-no
  15361. -->
  15362. (O2012 ^name predict-no +)
  15363. (S1 ^operator O2012 +)
  15364. Firing rl*prefer*rvt*predict-no*H0*2
  15365. -->
  15366. (S1 ^operator O2010 = 0.3873370368441085)
  15367. Firing rl*prefer*rvt*predict-yes*H0*1
  15368. -->
  15369. (S1 ^operator O2009 = 0.3895396806828423)
  15370. Firing prefer*rvt*predict-yes*H0
  15371. -->
  15372. Firing prefer*rvt*predict-no*H0
  15373. -->
  15374. Firing elaborate*copy-dir-to-output-link
  15375. -->
  15376. (I3 ^dir L +)
  15377. inner elaboration loop at bottom goal.
  15378. Retracting elaborate*copy-see-to-output-link
  15379. -->
  15380. (I3 ^see 1 +)
  15381. Retracting propose*predict-no
  15382. -->
  15383. (O2010 ^name predict-no +)
  15384. (S1 ^operator O2010 +)
  15385. Retracting propose*predict-yes
  15386. -->
  15387. (O2009 ^name predict-yes +)
  15388. (S1 ^operator O2009 +)
  15389. Retracting elaborate*reward*based*on*reward
  15390. -->
  15391. (R1008 ^value 1 +)
  15392. (R1 ^reward R1008 +)
  15393. Retracting elaborate*copy-dir-to-output-link
  15394. -->
  15395. (I3 ^dir U +)
  15396. Retracting rl*prefer*rvt*predict-no*H0*6
  15397. -->
  15398. (S1 ^operator O2010 = 0.9999999999999999)
  15399. Retracting rl*prefer*rvt*predict-yes*H0*5
  15400. -->
  15401. (S1 ^operator O2009 = 0.)
  15402. =>WM: (14102: S1 ^operator O2012 +)
  15403. =>WM: (14101: S1 ^operator O2011 +)
  15404. =>WM: (14100: I3 ^dir L)
  15405. =>WM: (14099: O2012 ^name predict-no)
  15406. =>WM: (14098: O2011 ^name predict-yes)
  15407. =>WM: (14097: R1009 ^value 1)
  15408. =>WM: (14096: R1 ^reward R1009)
  15409. =>WM: (14095: I3 ^see 0)
  15410. <=WM: (14086: S1 ^operator O2009 +)
  15411. <=WM: (14087: S1 ^operator O2010 +)
  15412. <=WM: (14088: S1 ^operator O2010)
  15413. <=WM: (14085: I3 ^dir U)
  15414. <=WM: (14081: R1 ^reward R1008)
  15415. <=WM: (14080: I3 ^see 1)
  15416. <=WM: (14084: O2010 ^name predict-no)
  15417. <=WM: (14083: O2009 ^name predict-yes)
  15418. <=WM: (14082: R1008 ^value 1)
  15419. --- Inner Elaboration Phase, active level 1 (S1) ---
  15420. Firing prefer*rvt*predict-yes*H0
  15421. -->
  15422. Firing rl*prefer*rvt*predict-yes*H0*1*v1*H1*36
  15423. -->
  15424. (S1 ^operator O2011 = 0.6104597340493421)
  15425. Firing rl*prefer*rvt*predict-yes*H0*1
  15426. -->
  15427. (S1 ^operator O2011 = 0.3895396806828423)
  15428. Firing prefer*rvt*predict-yes*H0*1*v1*H1
  15429. -->
  15430. Firing prefer*rvt*predict-no*H0
  15431. -->
  15432. Firing rl*prefer*rvt*predict-no*H0*2*v1*H1*35
  15433. -->
  15434. (S1 ^operator O2012 = 0.2714993082286609)
  15435. Firing rl*prefer*rvt*predict-no*H0*2
  15436. -->
  15437. (S1 ^operator O2012 = 0.3873370368441085)
  15438. Firing prefer*rvt*predict-no*H0*2*v1*H1
  15439. -->
  15440. inner elaboration loop at bottom goal.
  15441. Retracting rl*prefer*rvt*predict-no*H0*2
  15442. -->
  15443. (S1 ^operator O2010 = 0.3873370368441085)
  15444. Retracting rl*prefer*rvt*predict-no*H0*2*v1*H1*35
  15445. -->
  15446. (S1 ^operator O2010 = 0.2714993082286609)
  15447. Retracting rl*prefer*rvt*predict-yes*H0*1
  15448. -->
  15449. (S1 ^operator O2009 = 0.3895396806828423)
  15450. Retracting rl*prefer*rvt*predict-yes*H0*1*v1*H1*36
  15451. -->
  15452. (S1 ^operator O2009 = 0.6104597340493421)
  15453. --- END Proposal Phase ---
  15454. --- Decision Phase ---
  15455. RL update rl*prefer*rvt*predict-no*H0*6 1 0 1 -> 1 0 1(R,m,v=1,1,0)
  15456. =>WM: (14103: S1 ^operator O2011)
  15457. 1006: O: O2011 (predict-yes)
  15458. --- END Decision Phase ---
  15459. --- Application Phase ---
  15460. --- Firing Productions (PE) For State At Depth 1 ---
  15461. --- Inner Elaboration Phase, active level 1 (S1) ---
  15462. Firing apply*operator
  15463. -->
  15464. (I3 ^predict-yes N1006 + :O )
  15465. Firing apply*operator*complete
  15466. -->
  15467. (I3 ^predict-no N1005 - :O )
  15468. inner elaboration loop at bottom goal.
  15469. --- Change Working Memory (PE) ---
  15470. =>WM: (14104: I3 ^predict-yes N1006)
  15471. <=WM: (14090: N1005 ^status complete)
  15472. <=WM: (14089: I3 ^predict-no N1005)
  15473. --- Firing Productions (IE) For State At Depth 1 ---
  15474. --- Inner Elaboration Phase, active level 1 (S1) ---
  15475. Firing monitor*world
  15476. -->
  15477. I see 1 and I'm going to do: predict-yes inner elaboration loop at bottom goal.
  15478. --- Change Working Memory (IE) ---
  15479. --- END Application Phase ---
  15480. --- Output Phase ---
  15481. ENV: Agent did: predict-yes for direction L in state State-B
  15482. In State-B moving L
  15483. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  15484. predict error 0
  15485. dir: dir isU
  15486. --- END Output Phase ---
  15487. \-/--- Input Phase ---
  15488. =>WM: (14108: I2 ^dir U)
  15489. =>WM: (14107: I2 ^reward 1)
  15490. =>WM: (14106: I2 ^see 1)
  15491. =>WM: (14105: N1006 ^status complete)
  15492. <=WM: (14093: I2 ^dir L)
  15493. <=WM: (14092: I2 ^reward 1)
  15494. <=WM: (14091: I2 ^see 0)
  15495. =>WM: (14109: I2 ^level-1 L1-root)
  15496. <=WM: (14094: I2 ^level-1 R1-root)
  15497. --- END Input Phase ---
  15498. --- Proposal Phase ---
  15499. --- Inner Elaboration Phase, active level 1 (S1) ---
  15500. Firing elaborate*copy-see-to-output-link
  15501. -->
  15502. (I3 ^see 1 +)
  15503. Firing elaborate*reward*based*on*reward
  15504. -->
  15505. (R1010 ^value 1 +)
  15506. (R1 ^reward R1010 +)
  15507. Firing propose*predict-yes
  15508. -->
  15509. (O2013 ^name predict-yes +)
  15510. (S1 ^operator O2013 +)
  15511. Firing propose*predict-no
  15512. -->
  15513. (O2014 ^name predict-no +)
  15514. (S1 ^operator O2014 +)
  15515. Firing rl*prefer*rvt*predict-no*H0*6
  15516. -->
  15517. (S1 ^operator O2012 = 0.9999999999999999)
  15518. Firing rl*prefer*rvt*predict-yes*H0*5
  15519. -->
  15520. (S1 ^operator O2011 = 0.)
  15521. Firing prefer*rvt*predict-yes*H0
  15522. -->
  15523. Firing prefer*rvt*predict-no*H0
  15524. -->
  15525. Firing elaborate*copy-dir-to-output-link
  15526. -->
  15527. (I3 ^dir U +)
  15528. inner elaboration loop at bottom goal.
  15529. Retracting elaborate*copy-see-to-output-link
  15530. -->
  15531. (I3 ^see 0 +)
  15532. Retracting propose*predict-no
  15533. -->
  15534. (O2012 ^name predict-no +)
  15535. (S1 ^operator O2012 +)
  15536. Retracting propose*predict-yes
  15537. -->
  15538. (O2011 ^name predict-yes +)
  15539. (S1 ^operator O2011 +)
  15540. Retracting elaborate*reward*based*on*reward
  15541. -->
  15542. (R1009 ^value 1 +)
  15543. (R1 ^reward R1009 +)
  15544. Retracting elaborate*copy-dir-to-output-link
  15545. -->
  15546. (I3 ^dir L +)
  15547. Retracting rl*prefer*rvt*predict-no*H0*2
  15548. -->
  15549. (S1 ^operator O2012 = 0.3873370368441085)
  15550. Retracting rl*prefer*rvt*predict-no*H0*2*v1*H1*35
  15551. -->
  15552. (S1 ^operator O2012 = 0.2714993082286609)
  15553. Retracting rl*prefer*rvt*predict-yes*H0*1
  15554. -->
  15555. (S1 ^operator O2011 = 0.3895396806828423)
  15556. Retracting rl*prefer*rvt*predict-yes*H0*1*v1*H1*36
  15557. -->
  15558. (S1 ^operator O2011 = 0.6104597340493421)
  15559. =>WM: (14117: S1 ^operator O2014 +)
  15560. =>WM: (14116: S1 ^operator O2013 +)
  15561. =>WM: (14115: I3 ^dir U)
  15562. =>WM: (14114: O2014 ^name predict-no)
  15563. =>WM: (14113: O2013 ^name predict-yes)
  15564. =>WM: (14112: R1010 ^value 1)
  15565. =>WM: (14111: R1 ^reward R1010)
  15566. =>WM: (14110: I3 ^see 1)
  15567. <=WM: (14101: S1 ^operator O2011 +)
  15568. <=WM: (14103: S1 ^operator O2011)
  15569. <=WM: (14102: S1 ^operator O2012 +)
  15570. <=WM: (14100: I3 ^dir L)
  15571. <=WM: (14096: R1 ^reward R1009)
  15572. <=WM: (14095: I3 ^see 0)
  15573. <=WM: (14099: O2012 ^name predict-no)
  15574. <=WM: (14098: O2011 ^name predict-yes)
  15575. <=WM: (14097: R1009 ^value 1)
  15576. --- Inner Elaboration Phase, active level 1 (S1) ---
  15577. Firing prefer*rvt*predict-yes*H0
  15578. -->
  15579. Firing rl*prefer*rvt*predict-yes*H0*5
  15580. -->
  15581. (S1 ^operator O2013 = 0.)
  15582. Firing prefer*rvt*predict-no*H0
  15583. -->
  15584. Firing rl*prefer*rvt*predict-no*H0*6
  15585. -->
  15586. (S1 ^operator O2014 = 0.9999999999999999)
  15587. inner elaboration loop at bottom goal.
  15588. Retracting rl*prefer*rvt*predict-no*H0*6
  15589. -->
  15590. (S1 ^operator O2012 = 0.9999999999999999)
  15591. Retracting rl*prefer*rvt*predict-yes*H0*5
  15592. -->
  15593. (S1 ^operator O2011 = 0.)
  15594. --- END Proposal Phase ---
  15595. --- Decision Phase ---
  15596. RL update rl*prefer*rvt*predict-yes*H0*1 0.711951 -0.322412 0.38954