PageRenderTime 143ms CodeModel.GetById 27ms RepoModel.GetById 0ms app.codeStats 1ms

/flipv2/20121113-091142-2.5K-ReLST-asneeded_epochs_50_5runs_noalphadecay/stdout-flip-2.5K_0.txt

https://bitbucket.org/evan13579b/soar-ziggurat
Plain Text | 16417 lines | 15665 code | 752 blank | 0 comment | 0 complexity | 5d7ebd7b63172960c957e153706b02e3 MD5 | raw file
Possible License(s): BSD-3-Clause
  1. Seeding... 0
  2. dir: dir isU
  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 0 ...
  10. soar> Entering slave mode:
  11. - log file 'rl-slave-2.5K_0.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: O1 (predict-yes)
  22. I see 0 and I'm going to do: predict-yes
  23. ENV: Agent did: predict-yes for direction U in state State-A
  24. In State-A moving U
  25. ENV: (next state, see, prediction correct?) = (State-A, 0, False)
  26. predict error 1
  27. dir: dir isU
  28. rule alias: '*'
  29. rule alias: '*'
  30. \-/|\-/2: O: O4 (predict-no)
  31. I see 0 and I'm going to do: predict-no
  32. ENV: Agent did: predict-no for direction U in state State-A
  33. In State-A moving U
  34. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  35. predict error 0
  36. dir: dir isR
  37. |\-3: O: O5 (predict-yes)
  38. I see 1 and I'm going to do: predict-yes
  39. ENV: Agent did: predict-yes for direction R in state State-A
  40. In State-A moving R
  41. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  42. predict error 0
  43. dir: dir isL
  44. /|\4: O: O7 (predict-yes)
  45. I see 1 and I'm going to do: predict-yes
  46. ENV: Agent did: predict-yes for direction L in state State-B
  47. In State-B moving L
  48. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  49. predict error 0
  50. dir: dir isR
  51. -/|5: O: O9 (predict-yes)
  52. I see 1 and I'm going to do: predict-yes
  53. ENV: Agent did: predict-yes for direction R in state State-A
  54. In State-A moving R
  55. ENV: (next state, see, prediction correct?) = (State-B, 1, 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-B
  61. In State-B moving R
  62. ENV: (next state, see, prediction correct?) = (State-B, 0, False)
  63. predict error 1
  64. dir: dir isU
  65. |\7: O: O14 (predict-no)
  66. I see 0 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 isL
  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 L in state State-B
  75. In State-B moving L
  76. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  77. predict error 0
  78. dir: dir isR
  79. \-9: O: O17 (predict-yes)
  80. I see 1 and I'm going to do: predict-yes
  81. ENV: Agent did: predict-yes for direction R in state State-A
  82. In State-A moving R
  83. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  84. predict error 0
  85. dir: dir isR
  86. /|\10: O: O19 (predict-yes)
  87. I see 1 and I'm going to do: predict-yes
  88. ENV: Agent did: predict-yes for direction R in state State-B
  89. In State-B moving R
  90. ENV: (next state, see, prediction correct?) = (State-B, 0, False)
  91. predict error 1
  92. dir: dir isU
  93. -/|11: O: O22 (predict-no)
  94. I see 0 and I'm going to do: predict-no
  95. ENV: Agent did: predict-no for direction U in state State-B
  96. In State-B moving U
  97. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  98. predict error 0
  99. dir: dir isR
  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 R in state State-B
  107. In State-B moving R
  108. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  109. predict error 0
  110. dir: dir isL
  111. -/|13: O: O26 (predict-no)
  112. I see 1 and I'm going to do: predict-no
  113. ENV: Agent did: predict-no for direction L in state State-B
  114. In State-B moving L
  115. ENV: (next state, see, prediction correct?) = (State-A, 1, False)
  116. predict error 1
  117. dir: dir isU
  118. \-14: O: O28 (predict-no)
  119. I see 0 and I'm going to do: predict-no
  120. ENV: Agent did: predict-no for direction U in state State-A
  121. In State-A moving U
  122. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  123. predict error 0
  124. dir: dir isR
  125. /|15: O: O29 (predict-yes)
  126. I see 1 and I'm going to do: predict-yes
  127. ENV: Agent did: predict-yes for direction R in state State-A
  128. In State-A moving R
  129. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  130. predict error 0
  131. dir: dir isL
  132. \-/16: O: O31 (predict-yes)
  133. I see 1 and I'm going to do: predict-yes
  134. ENV: Agent did: predict-yes for direction L in state State-B
  135. In State-B moving L
  136. ENV: (next state, see, prediction correct?) = (State-A, 1, 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 isU
  160. \-/20: O: O40 (predict-no)
  161. I see 1 and I'm going to do: predict-no
  162. ENV: Agent did: predict-no for direction U in state State-A
  163. In State-A moving U
  164. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  165. predict error 0
  166. dir: dir isL
  167. |\-21: O: O41 (predict-yes)
  168. I see 1 and I'm going to do: predict-yes
  169. ENV: Agent did: predict-yes for direction L in state State-A
  170. In State-A moving L
  171. ENV: (next state, see, prediction correct?) = (State-A, 0, False)
  172. predict error 1
  173. dir: dir isU
  174. /22: O: O44 (predict-no)
  175. I see 0 and I'm going to do: predict-no
  176. ENV: Agent did: predict-no for direction U in state State-A
  177. In State-A moving U
  178. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  179. predict error 0
  180. dir: dir isU
  181. |\-23: O: O46 (predict-no)
  182. I see 1 and I'm going to do: predict-no
  183. ENV: Agent did: predict-no for direction U in state State-A
  184. In State-A moving U
  185. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  186. predict error 0
  187. dir: dir isU
  188. /|\24: O: O48 (predict-no)
  189. I see 1 and I'm going to do: predict-no
  190. ENV: Agent did: predict-no for direction U in state State-A
  191. In State-A moving U
  192. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  193. predict error 0
  194. dir: dir isR
  195. -/|25: O: O50 (predict-no)
  196. I see 1 and I'm going to do: predict-no
  197. ENV: Agent did: predict-no for direction R in state State-A
  198. In State-A moving R
  199. ENV: (next state, see, prediction correct?) = (State-B, 1, False)
  200. predict error 1
  201. dir: dir isL
  202. \-/26: O: O51 (predict-yes)
  203. I see 0 and I'm going to do: predict-yes
  204. ENV: Agent did: predict-yes for direction L in state State-B
  205. In State-B moving L
  206. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  207. predict error 0
  208. dir: dir isR
  209. |\27: O: O53 (predict-yes)
  210. I see 1 and I'm going to do: predict-yes
  211. ENV: Agent did: predict-yes for direction R in state State-A
  212. In State-A moving R
  213. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  214. predict error 0
  215. dir: dir isR
  216. -/|28: O: O55 (predict-yes)
  217. I see 1 and I'm going to do: predict-yes
  218. ENV: Agent did: predict-yes for direction R in state State-B
  219. In State-B moving R
  220. ENV: (next state, see, prediction correct?) = (State-B, 0, False)
  221. predict error 1
  222. dir: dir isU
  223. \-/29: O: O57 (predict-yes)
  224. I see 0 and I'm going to do: predict-yes
  225. ENV: Agent did: predict-yes for direction U in state State-B
  226. In State-B moving U
  227. ENV: (next state, see, prediction correct?) = (State-B, 0, False)
  228. predict error 1
  229. dir: dir isU
  230. |\-/30: O: O60 (predict-no)
  231. I see 0 and I'm going to do: predict-no
  232. ENV: Agent did: predict-no for direction U in state State-B
  233. In State-B moving U
  234. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  235. predict error 0
  236. dir: dir isR
  237. |\-31: O: O61 (predict-yes)
  238. I see 1 and I'm going to do: predict-yes
  239. ENV: Agent did: predict-yes for direction R in state State-B
  240. In State-B moving R
  241. ENV: (next state, see, prediction correct?) = (State-B, 0, False)
  242. predict error 1
  243. dir: dir isU
  244. /32: O: O64 (predict-no)
  245. I see 0 and I'm going to do: predict-no
  246. ENV: Agent did: predict-no for direction U in state State-B
  247. In State-B moving U
  248. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  249. predict error 0
  250. dir: dir isL
  251. |\-33: O: O65 (predict-yes)
  252. I see 1 and I'm going to do: predict-yes
  253. ENV: Agent did: predict-yes for direction L in state State-B
  254. In State-B moving L
  255. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  256. predict error 0
  257. dir: dir isU
  258. /|\34: O: O68 (predict-no)
  259. I see 1 and I'm going to do: predict-no
  260. ENV: Agent did: predict-no for direction U in state State-A
  261. In State-A moving U
  262. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  263. predict error 0
  264. dir: dir isR
  265. -/|35: O: O69 (predict-yes)
  266. I see 1 and I'm going to do: predict-yes
  267. ENV: Agent did: predict-yes for direction R in state State-A
  268. In State-A moving R
  269. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  270. predict error 0
  271. dir: dir isL
  272. \-/36: O: O71 (predict-yes)
  273. I see 1 and I'm going to do: predict-yes
  274. ENV: Agent did: predict-yes for direction L in state State-B
  275. In State-B moving L
  276. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  277. predict error 0
  278. dir: dir isU
  279. |\37: O: O74 (predict-no)
  280. I see 1 and I'm going to do: predict-no
  281. ENV: Agent did: predict-no for direction U in state State-A
  282. In State-A moving U
  283. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  284. predict error 0
  285. dir: dir isR
  286. -/|38: O: O75 (predict-yes)
  287. I see 1 and I'm going to do: predict-yes
  288. ENV: Agent did: predict-yes for direction R in state State-A
  289. In State-A moving R
  290. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  291. predict error 0
  292. dir: dir isU
  293. \-39: O: O77 (predict-yes)
  294. I see 1 and I'm going to do: predict-yes
  295. ENV: Agent did: predict-yes for direction U in state State-B
  296. In State-B moving U
  297. ENV: (next state, see, prediction correct?) = (State-B, 0, False)
  298. predict error 1
  299. dir: dir isU
  300. /|40: O: O80 (predict-no)
  301. I see 0 and I'm going to do: predict-no
  302. ENV: Agent did: predict-no for direction U in state State-B
  303. In State-B moving U
  304. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  305. predict error 0
  306. dir: dir isL
  307. \-/41: O: O81 (predict-yes)
  308. I see 1 and I'm going to do: predict-yes
  309. ENV: Agent did: predict-yes for direction L in state State-B
  310. In State-B moving L
  311. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  312. predict error 0
  313. dir: dir isR
  314. |42: O: O83 (predict-yes)
  315. I see 1 and I'm going to do: predict-yes
  316. ENV: Agent did: predict-yes for direction R in state State-A
  317. In State-A moving R
  318. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  319. predict error 0
  320. dir: dir isU
  321. \-/43: O: O86 (predict-no)
  322. I see 1 and I'm going to do: predict-no
  323. ENV: Agent did: predict-no for direction U in state State-B
  324. In State-B moving U
  325. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  326. predict error 0
  327. dir: dir isL
  328. |\-44: O: O87 (predict-yes)
  329. I see 1 and I'm going to do: predict-yes
  330. ENV: Agent did: predict-yes for direction L in state State-B
  331. In State-B moving L
  332. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  333. predict error 0
  334. dir: dir isL
  335. /|\45: O: O89 (predict-yes)
  336. I see 1 and I'm going to do: predict-yes
  337. ENV: Agent did: predict-yes for direction L in state State-A
  338. In State-A moving L
  339. ENV: (next state, see, prediction correct?) = (State-A, 0, False)
  340. predict error 1
  341. dir: dir isU
  342. -/|46: O: O92 (predict-no)
  343. I see 0 and I'm going to do: predict-no
  344. ENV: Agent did: predict-no for direction U in state State-A
  345. In State-A moving U
  346. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  347. predict error 0
  348. dir: dir isL
  349. \-/47: O: O93 (predict-yes)
  350. I see 1 and I'm going to do: predict-yes
  351. ENV: Agent did: predict-yes for direction L in state State-A
  352. In State-A moving L
  353. ENV: (next state, see, prediction correct?) = (State-A, 0, False)
  354. predict error 1
  355. dir: dir isR
  356. |\-48: O: O96 (predict-no)
  357. I see 0 and I'm going to do: predict-no
  358. ENV: Agent did: predict-no for direction R in state State-A
  359. In State-A moving R
  360. ENV: (next state, see, prediction correct?) = (State-B, 1, False)
  361. predict error 1
  362. dir: dir isL
  363. /|49: O: O97 (predict-yes)
  364. I see 0 and I'm going to do: predict-yes
  365. ENV: Agent did: predict-yes for direction L in state State-B
  366. In State-B moving L
  367. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  368. predict error 0
  369. dir: dir isU
  370. \-/50: O: O100 (predict-no)
  371. I see 1 and I'm going to do: predict-no
  372. ENV: Agent did: predict-no for direction U in state State-A
  373. In State-A moving U
  374. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  375. predict error 0
  376. dir: dir isU
  377. |\-/|\-sleeping...
  378. /sleeping...
  379. |51: O: O102 (predict-no)
  380. I see 1 and I'm going to do: predict-no
  381. ENV: Agent did: predict-no for direction U in state State-A
  382. In State-A moving U
  383. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  384. predict error 0
  385. dir: dir isR
  386. \52: O: O104 (predict-no)
  387. I see 1 and I'm going to do: predict-no
  388. ENV: Agent did: predict-no for direction R in state State-A
  389. In State-A moving R
  390. ENV: (next state, see, prediction correct?) = (State-B, 1, False)
  391. predict error 1
  392. dir: dir isL
  393. -/|53: O: O106 (predict-no)
  394. I see 0 and I'm going to do: predict-no
  395. ENV: Agent did: predict-no for direction L in state State-B
  396. In State-B moving L
  397. ENV: (next state, see, prediction correct?) = (State-A, 1, False)
  398. predict error 1
  399. dir: dir isL
  400. \-/54: O: O107 (predict-yes)
  401. I see 0 and I'm going to do: predict-yes
  402. ENV: Agent did: predict-yes for direction L in state State-A
  403. In State-A moving L
  404. ENV: (next state, see, prediction correct?) = (State-A, 0, False)
  405. predict error 1
  406. dir: dir isR
  407. |\-55: O: O109 (predict-yes)
  408. I see 0 and I'm going to do: predict-yes
  409. ENV: Agent did: predict-yes for direction R in state State-A
  410. In State-A moving R
  411. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  412. predict error 0
  413. dir: dir isU
  414. /|\56: O: O112 (predict-no)
  415. I see 1 and I'm going to do: predict-no
  416. ENV: Agent did: predict-no for direction U in state State-B
  417. In State-B moving U
  418. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  419. predict error 0
  420. dir: dir isL
  421. -/|57: O: O114 (predict-no)
  422. I see 1 and I'm going to do: predict-no
  423. ENV: Agent did: predict-no for direction L in state State-B
  424. In State-B moving L
  425. ENV: (next state, see, prediction correct?) = (State-A, 1, False)
  426. predict error 1
  427. dir: dir isR
  428. \-/58: O: O115 (predict-yes)
  429. I see 0 and I'm going to do: predict-yes
  430. ENV: Agent did: predict-yes for direction R in state State-A
  431. In State-A moving R
  432. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  433. predict error 0
  434. dir: dir isU
  435. |\-59: O: O118 (predict-no)
  436. I see 1 and I'm going to do: predict-no
  437. ENV: Agent did: predict-no for direction U in state State-B
  438. In State-B moving U
  439. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  440. predict error 0
  441. dir: dir isR
  442. /|\60: O: O119 (predict-yes)
  443. I see 1 and I'm going to do: predict-yes
  444. ENV: Agent did: predict-yes for direction R in state State-B
  445. In State-B moving R
  446. ENV: (next state, see, prediction correct?) = (State-B, 0, False)
  447. predict error 1
  448. dir: dir isU
  449. -/|61: O: O122 (predict-no)
  450. I see 0 and I'm going to do: predict-no
  451. ENV: Agent did: predict-no for direction U in state State-B
  452. In State-B moving U
  453. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  454. predict error 0
  455. dir: dir isR
  456. rule alias: '*'
  457. rule alias: '*'
  458. rule alias: '*'
  459. rule alias: '*'
  460. rule alias: '*'
  461. rule alias: '*'
  462. rule alias: '*'
  463. rule alias: '*'
  464. rule alias: '*'
  465. rule alias: '*'
  466. rule alias: '*'
  467. \62: O: O123 (predict-yes)
  468. I see 1 and I'm going to do: predict-yes
  469. ENV: Agent did: predict-yes for direction R in state State-B
  470. In State-B moving R
  471. ENV: (next state, see, prediction correct?) = (State-B, 0, False)
  472. predict error 1
  473. dir: dir isU
  474. -/63: O: O126 (predict-no)
  475. I see 0 and I'm going to do: predict-no
  476. ENV: Agent did: predict-no for direction U in state State-B
  477. In State-B moving U
  478. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  479. predict error 0
  480. dir: dir isR
  481. |\64: O: O127 (predict-yes)
  482. I see 1 and I'm going to do: predict-yes
  483. ENV: Agent did: predict-yes for direction R in state State-B
  484. In State-B moving R
  485. ENV: (next state, see, prediction correct?) = (State-B, 0, False)
  486. predict error 1
  487. dir: dir isR
  488. -65: O: O129 (predict-yes)
  489. I see 0 and I'm going to do: predict-yes
  490. ENV: Agent did: predict-yes for direction R in state State-B
  491. In State-B moving R
  492. ENV: (next state, see, prediction correct?) = (State-B, 0, False)
  493. predict error 1
  494. dir: dir isR
  495. /|\66: O: O131 (predict-yes)
  496. I see 0 and I'm going to do: predict-yes
  497. ENV: Agent did: predict-yes for direction R in state State-B
  498. In State-B moving R
  499. ENV: (next state, see, prediction correct?) = (State-B, 0, False)
  500. predict error 1
  501. dir: dir isR
  502. -/67: O: O133 (predict-yes)
  503. I see 0 and I'm going to do: predict-yes
  504. ENV: Agent did: predict-yes for direction R in state State-B
  505. In State-B moving R
  506. ENV: (next state, see, prediction correct?) = (State-B, 0, False)
  507. predict error 1
  508. dir: dir isR
  509. |68: O: O135 (predict-yes)
  510. I see 0 and I'm going to do: predict-yes
  511. ENV: Agent did: predict-yes for direction R in state State-B
  512. In State-B moving R
  513. ENV: (next state, see, prediction correct?) = (State-B, 0, False)
  514. predict error 1
  515. dir: dir isR
  516. \-69: O: O137 (predict-yes)
  517. I see 0 and I'm going to do: predict-yes
  518. ENV: Agent did: predict-yes for direction R in state State-B
  519. In State-B moving R
  520. ENV: (next state, see, prediction correct?) = (State-B, 0, False)
  521. predict error 1
  522. dir: dir isL
  523. /|70: O: O139 (predict-yes)
  524. I see 0 and I'm going to do: predict-yes
  525. ENV: Agent did: predict-yes for direction L in state State-B
  526. In State-B moving L
  527. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  528. predict error 0
  529. dir: dir isL
  530. \-/71: O: O141 (predict-yes)
  531. I see 1 and I'm going to do: predict-yes
  532. ENV: Agent did: predict-yes for direction L in state State-A
  533. In State-A moving L
  534. ENV: (next state, see, prediction correct?) = (State-A, 0, False)
  535. predict error 1
  536. dir: dir isL
  537. rule alias: '*'
  538. rule alias: '*'
  539. rule alias: '*'
  540. rule alias: '*'
  541. rule alias: '*'
  542. |72: O: O143 (predict-yes)
  543. I see 0 and I'm going to do: predict-yes
  544. ENV: Agent did: predict-yes for direction L in state State-A
  545. In State-A moving L
  546. ENV: (next state, see, prediction correct?) = (State-A, 0, False)
  547. predict error 1
  548. dir: dir isR
  549. \-/73: O: O146 (predict-no)
  550. I see 0 and I'm going to do: predict-no
  551. ENV: Agent did: predict-no for direction R in state State-A
  552. In State-A moving R
  553. ENV: (next state, see, prediction correct?) = (State-B, 1, False)
  554. predict error 1
  555. dir: dir isR
  556. |\-74: O: O147 (predict-yes)
  557. I see 0 and I'm going to do: predict-yes
  558. ENV: Agent did: predict-yes for direction R in state State-B
  559. In State-B moving R
  560. ENV: (next state, see, prediction correct?) = (State-B, 0, False)
  561. predict error 1
  562. dir: dir isR
  563. /|\75: O: O150 (predict-no)
  564. I see 0 and I'm going to do: predict-no
  565. ENV: Agent did: predict-no for direction R in state State-B
  566. In State-B moving R
  567. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  568. predict error 0
  569. dir: dir isL
  570. -/76: O: O151 (predict-yes)
  571. I see 1 and I'm going to do: predict-yes
  572. ENV: Agent did: predict-yes for direction L in state State-B
  573. In State-B moving L
  574. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  575. predict error 0
  576. dir: dir isU
  577. |\77: O: O154 (predict-no)
  578. I see 1 and I'm going to do: predict-no
  579. ENV: Agent did: predict-no for direction U in state State-A
  580. In State-A moving U
  581. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  582. predict error 0
  583. dir: dir isU
  584. -/|78: O: O156 (predict-no)
  585. I see 1 and I'm going to do: predict-no
  586. ENV: Agent did: predict-no for direction U in state State-A
  587. In State-A moving U
  588. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  589. predict error 0
  590. dir: dir isU
  591. \-/79: O: O158 (predict-no)
  592. I see 1 and I'm going to do: predict-no
  593. ENV: Agent did: predict-no for direction U in state State-A
  594. In State-A moving U
  595. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  596. predict error 0
  597. dir: dir isU
  598. |\-80: O: O160 (predict-no)
  599. I see 1 and I'm going to do: predict-no
  600. ENV: Agent did: predict-no for direction U in state State-A
  601. In State-A moving U
  602. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  603. predict error 0
  604. dir: dir isU
  605. /|81: O: O162 (predict-no)
  606. I see 1 and I'm going to do: predict-no
  607. ENV: Agent did: predict-no for direction U in state State-A
  608. In State-A moving U
  609. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  610. predict error 0
  611. dir: dir isU
  612. rule alias: '*'
  613. rule alias: '*'
  614. rule alias: '*'
  615. \82: O: O164 (predict-no)
  616. I see 1 and I'm going to do: predict-no
  617. ENV: Agent did: predict-no for direction U in state State-A
  618. In State-A moving U
  619. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  620. predict error 0
  621. dir: dir isR
  622. -/|83: O: O165 (predict-yes)
  623. I see 1 and I'm going to do: predict-yes
  624. ENV: Agent did: predict-yes for direction R in state State-A
  625. In State-A moving R
  626. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  627. predict error 0
  628. dir: dir isR
  629. \-/84: O: O167 (predict-yes)
  630. I see 1 and I'm going to do: predict-yes
  631. ENV: Agent did: predict-yes for direction R in state State-B
  632. In State-B moving R
  633. ENV: (next state, see, prediction correct?) = (State-B, 0, False)
  634. predict error 1
  635. dir: dir isU
  636. |\-85: O: O169 (predict-yes)
  637. I see 0 and I'm going to do: predict-yes
  638. ENV: Agent did: predict-yes for direction U in state State-B
  639. In State-B moving U
  640. ENV: (next state, see, prediction correct?) = (State-B, 0, False)
  641. predict error 1
  642. dir: dir isL
  643. /|\86: O: O172 (predict-no)
  644. I see 0 and I'm going to do: predict-no
  645. ENV: Agent did: predict-no for direction L in state State-B
  646. In State-B moving L
  647. ENV: (next state, see, prediction correct?) = (State-A, 1, False)
  648. predict error 1
  649. dir: dir isU
  650. -/|87: O: O174 (predict-no)
  651. I see 0 and I'm going to do: predict-no
  652. ENV: Agent did: predict-no for direction U in state State-A
  653. In State-A moving U
  654. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  655. predict error 0
  656. dir: dir isU
  657. \-/88: O: O176 (predict-no)
  658. I see 1 and I'm going to do: predict-no
  659. ENV: Agent did: predict-no for direction U in state State-A
  660. In State-A moving U
  661. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  662. predict error 0
  663. dir: dir isU
  664. |\-89: O: O178 (predict-no)
  665. I see 1 and I'm going to do: predict-no
  666. ENV: Agent did: predict-no for direction U in state State-A
  667. In State-A moving U
  668. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  669. predict error 0
  670. dir: dir isR
  671. /|\90: O: O179 (predict-yes)
  672. I see 1 and I'm going to do: predict-yes
  673. ENV: Agent did: predict-yes for direction R in state State-A
  674. In State-A moving R
  675. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  676. predict error 0
  677. dir: dir isU
  678. -/|91: O: O182 (predict-no)
  679. I see 1 and I'm going to do: predict-no
  680. ENV: Agent did: predict-no for direction U in state State-B
  681. In State-B moving U
  682. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  683. predict error 0
  684. dir: dir isR
  685. rule alias: '*'
  686. rule alias: '*'
  687. rule alias: '*'
  688. \92: O: O184 (predict-no)
  689. I see 1 and I'm going to do: predict-no
  690. ENV: Agent did: predict-no for direction R in state State-B
  691. In State-B moving R
  692. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  693. predict error 0
  694. dir: dir isR
  695. -/|93: O: O186 (predict-no)
  696. I see 1 and I'm going to do: predict-no
  697. ENV: Agent did: predict-no for direction R in state State-B
  698. In State-B moving R
  699. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  700. predict error 0
  701. dir: dir isR
  702. \-/94: O: O188 (predict-no)
  703. I see 1 and I'm going to do: predict-no
  704. ENV: Agent did: predict-no for direction R in state State-B
  705. In State-B moving R
  706. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  707. predict error 0
  708. dir: dir isU
  709. |\-95: O: O189 (predict-yes)
  710. I see 1 and I'm going to do: predict-yes
  711. ENV: Agent did: predict-yes for direction U in state State-B
  712. In State-B moving U
  713. ENV: (next state, see, prediction correct?) = (State-B, 0, False)
  714. predict error 1
  715. dir: dir isU
  716. /96: O: O191 (predict-yes)
  717. I see 0 and I'm going to do: predict-yes
  718. ENV: Agent did: predict-yes for direction U in state State-B
  719. In State-B moving U
  720. ENV: (next state, see, prediction correct?) = (State-B, 0, False)
  721. predict error 1
  722. dir: dir isU
  723. |\97: O: O194 (predict-no)
  724. I see 0 and I'm going to do: predict-no
  725. ENV: Agent did: predict-no for direction U in state State-B
  726. In State-B moving U
  727. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  728. predict error 0
  729. dir: dir isL
  730. -/|98: O: O195 (predict-yes)
  731. I see 1 and I'm going to do: predict-yes
  732. ENV: Agent did: predict-yes for direction L in state State-B
  733. In State-B moving L
  734. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  735. predict error 0
  736. dir: dir isR
  737. \-/99: O: O197 (predict-yes)
  738. I see 1 and I'm going to do: predict-yes
  739. ENV: Agent did: predict-yes for direction R in state State-A
  740. In State-A moving R
  741. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  742. predict error 0
  743. dir: dir isR
  744. |\100: O: O199 (predict-yes)
  745. I see 1 and I'm going to do: predict-yes
  746. ENV: Agent did: predict-yes for direction R in state State-B
  747. In State-B moving R
  748. ENV: (next state, see, prediction correct?) = (State-B, 0, False)
  749. predict error 1
  750. dir: dir isR
  751. -/|101: O: O202 (predict-no)
  752. I see 0 and I'm going to do: predict-no
  753. ENV: Agent did: predict-no for direction R in state State-B
  754. In State-B moving R
  755. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  756. predict error 0
  757. dir: dir isU
  758. rule alias: '*'
  759. \-/|\-/|\-/|\-/|\-/|\-/|\-/|\-/|\sleeping...
  760. -102: O: O204 (predict-no)
  761. I see 1 and I'm going to do: predict-no
  762. ENV: Agent did: predict-no for direction U in state State-B
  763. In State-B moving U
  764. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  765. predict error 0
  766. dir: dir isL
  767. /|\103: O: O205 (predict-yes)
  768. I see 1 and I'm going to do: predict-yes
  769. ENV: Agent did: predict-yes for direction L in state State-B
  770. In State-B moving L
  771. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  772. predict error 0
  773. dir: dir isU
  774. -/104: O: O208 (predict-no)
  775. I see 1 and I'm going to do: predict-no
  776. ENV: Agent did: predict-no for direction U in state State-A
  777. In State-A moving U
  778. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  779. predict error 0
  780. dir: dir isL
  781. |\-105: O: O209 (predict-yes)
  782. I see 1 and I'm going to do: predict-yes
  783. ENV: Agent did: predict-yes for direction L in state State-A
  784. In State-A moving L
  785. ENV: (next state, see, prediction correct?) = (State-A, 0, False)
  786. predict error 1
  787. dir: dir isL
  788. /|\106: O: O211 (predict-yes)
  789. I see 0 and I'm going to do: predict-yes
  790. ENV: Agent did: predict-yes for direction L in state State-A
  791. In State-A moving L
  792. ENV: (next state, see, prediction correct?) = (State-A, 0, False)
  793. predict error 1
  794. dir: dir isU
  795. -/|107: O: O214 (predict-no)
  796. I see 0 and I'm going to do: predict-no
  797. ENV: Agent did: predict-no for direction U in state State-A
  798. In State-A moving U
  799. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  800. predict error 0
  801. dir: dir isL
  802. \-/108: O: O216 (predict-no)
  803. I see 1 and I'm going to do: predict-no
  804. ENV: Agent did: predict-no for direction L in state State-A
  805. In State-A moving L
  806. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  807. predict error 0
  808. dir: dir isU
  809. |\-109: O: O218 (predict-no)
  810. I see 1 and I'm going to do: predict-no
  811. ENV: Agent did: predict-no for direction U in state State-A
  812. In State-A moving U
  813. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  814. predict error 0
  815. dir: dir isL
  816. /|\110: O: O220 (predict-no)
  817. I see 1 and I'm going to do: predict-no
  818. ENV: Agent did: predict-no for direction L in state State-A
  819. In State-A moving L
  820. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  821. predict error 0
  822. dir: dir isL
  823. -/|111: O: O222 (predict-no)
  824. I see 1 and I'm going to do: predict-no
  825. ENV: Agent did: predict-no for direction L in state State-A
  826. In State-A moving L
  827. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  828. predict error 0
  829. dir: dir isU
  830. rule alias: '*'
  831. rule alias: '*'
  832. rule alias: '*'
  833. rule alias: '*'
  834. \112: O: O224 (predict-no)
  835. I see 1 and I'm going to do: predict-no
  836. ENV: Agent did: predict-no for direction U in state State-A
  837. In State-A moving U
  838. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  839. predict error 0
  840. dir: dir isL
  841. -/|113: O: O226 (predict-no)
  842. I see 1 and I'm going to do: predict-no
  843. ENV: Agent did: predict-no for direction L in state State-A
  844. In State-A moving L
  845. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  846. predict error 0
  847. dir: dir isR
  848. \-/114: O: O227 (predict-yes)
  849. I see 1 and I'm going to do: predict-yes
  850. ENV: Agent did: predict-yes for direction R in state State-A
  851. In State-A moving R
  852. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  853. predict error 0
  854. dir: dir isU
  855. |\115: O: O230 (predict-no)
  856. I see 1 and I'm going to do: predict-no
  857. ENV: Agent did: predict-no for direction U in state State-B
  858. In State-B moving U
  859. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  860. predict error 0
  861. dir: dir isR
  862. -/|116: O: O232 (predict-no)
  863. I see 1 and I'm going to do: predict-no
  864. ENV: Agent did: predict-no for direction R in state State-B
  865. In State-B moving R
  866. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  867. predict error 0
  868. dir: dir isU
  869. \-/117: O: O234 (predict-no)
  870. I see 1 and I'm going to do: predict-no
  871. ENV: Agent did: predict-no for direction U in state State-B
  872. In State-B moving U
  873. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  874. predict error 0
  875. dir: dir isL
  876. |\-118: O: O236 (predict-no)
  877. I see 1 and I'm going to do: predict-no
  878. ENV: Agent did: predict-no for direction L in state State-B
  879. In State-B moving L
  880. ENV: (next state, see, prediction correct?) = (State-A, 1, False)
  881. predict error 1
  882. dir: dir isR
  883. /|\119: O: O238 (predict-no)
  884. I see 0 and I'm going to do: predict-no
  885. ENV: Agent did: predict-no for direction R in state State-A
  886. In State-A moving R
  887. ENV: (next state, see, prediction correct?) = (State-B, 1, False)
  888. predict error 1
  889. dir: dir isR
  890. -/|120: O: O240 (predict-no)
  891. I see 0 and I'm going to do: predict-no
  892. ENV: Agent did: predict-no for direction R in state State-B
  893. In State-B moving R
  894. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  895. predict error 0
  896. dir: dir isR
  897. \-/121: O: O241 (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 isR
  904. rule alias: '*'
  905. rule alias: '*'
  906. rule alias: '*'
  907. rule alias: '*'
  908. rule alias: '*'
  909. rule alias: '*'
  910. rule alias: '*'
  911. rule alias: '*'
  912. rule alias: '*'
  913. |122: O: O244 (predict-no)
  914. I see 0 and I'm going to do: predict-no
  915. ENV: Agent did: predict-no for direction R in state State-B
  916. In State-B moving R
  917. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  918. predict error 0
  919. dir: dir isR
  920. \-/123: O: O246 (predict-no)
  921. I see 1 and I'm going to do: predict-no
  922. ENV: Agent did: predict-no for direction R in state State-B
  923. In State-B moving R
  924. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  925. predict error 0
  926. dir: dir isU
  927. |\124: O: O247 (predict-yes)
  928. I see 1 and I'm going to do: predict-yes
  929. ENV: Agent did: predict-yes for direction U in state State-B
  930. In State-B moving U
  931. ENV: (next state, see, prediction correct?) = (State-B, 0, False)
  932. predict error 1
  933. dir: dir isL
  934. -/125: O: O250 (predict-no)
  935. I see 0 and I'm going to do: predict-no
  936. ENV: Agent did: predict-no for direction L in state State-B
  937. In State-B moving L
  938. ENV: (next state, see, prediction correct?) = (State-A, 1, False)
  939. predict error 1
  940. dir: dir isL
  941. |\-126: O: O252 (predict-no)
  942. I see 0 and I'm going to do: predict-no
  943. ENV: Agent did: predict-no for direction L in state State-A
  944. In State-A moving L
  945. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  946. predict error 0
  947. dir: dir isU
  948. /|\127: O: O254 (predict-no)
  949. I see 1 and I'm going to do: predict-no
  950. ENV: Agent did: predict-no for direction U in state State-A
  951. In State-A moving U
  952. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  953. predict error 0
  954. dir: dir isL
  955. -/|128: O: O256 (predict-no)
  956. I see 1 and I'm going to do: predict-no
  957. ENV: Agent did: predict-no for direction L in state State-A
  958. In State-A moving L
  959. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  960. predict error 0
  961. dir: dir isL
  962. \-/129: O: O257 (predict-yes)
  963. I see 1 and I'm going to do: predict-yes
  964. ENV: Agent did: predict-yes for direction L in state State-A
  965. In State-A moving L
  966. ENV: (next state, see, prediction correct?) = (State-A, 0, False)
  967. predict error 1
  968. dir: dir isL
  969. |\-130: O: O260 (predict-no)
  970. I see 0 and I'm going to do: predict-no
  971. ENV: Agent did: predict-no for direction L in state State-A
  972. In State-A moving L
  973. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  974. predict error 0
  975. dir: dir isU
  976. /|\131: O: O262 (predict-no)
  977. I see 1 and I'm going to do: predict-no
  978. ENV: Agent did: predict-no for direction U in state State-A
  979. In State-A moving U
  980. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  981. predict error 0
  982. dir: dir isU
  983. rule alias: '*'
  984. -132: O: O264 (predict-no)
  985. I see 1 and I'm going to do: predict-no
  986. ENV: Agent did: predict-no for direction U in state State-A
  987. In State-A moving U
  988. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  989. predict error 0
  990. dir: dir isL
  991. /|\133: O: O266 (predict-no)
  992. I see 1 and I'm going to do: predict-no
  993. ENV: Agent did: predict-no for direction L in state State-A
  994. In State-A moving L
  995. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  996. predict error 0
  997. dir: dir isR
  998. -/134: O: O268 (predict-no)
  999. I see 1 and I'm going to do: predict-no
  1000. ENV: Agent did: predict-no for direction R in state State-A
  1001. In State-A moving R
  1002. ENV: (next state, see, prediction correct?) = (State-B, 1, False)
  1003. predict error 1
  1004. dir: dir isL
  1005. |\-135: O: O270 (predict-no)
  1006. I see 0 and I'm going to do: predict-no
  1007. ENV: Agent did: predict-no for direction L in state State-B
  1008. In State-B moving L
  1009. ENV: (next state, see, prediction correct?) = (State-A, 1, False)
  1010. predict error 1
  1011. dir: dir isL
  1012. /|136: O: O272 (predict-no)
  1013. I see 0 and I'm going to do: predict-no
  1014. ENV: Agent did: predict-no for direction L in state State-A
  1015. In State-A moving L
  1016. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  1017. predict error 0
  1018. dir: dir isL
  1019. \-/137: O: O274 (predict-no)
  1020. I see 1 and I'm going to do: predict-no
  1021. ENV: Agent did: predict-no for direction L in state State-A
  1022. In State-A moving L
  1023. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  1024. predict error 0
  1025. dir: dir isR
  1026. |\138: O: O276 (predict-no)
  1027. I see 1 and I'm going to do: predict-no
  1028. ENV: Agent did: predict-no for direction R in state State-A
  1029. In State-A moving R
  1030. ENV: (next state, see, prediction correct?) = (State-B, 1, False)
  1031. predict error 1
  1032. dir: dir isR
  1033. -/|139: O: O278 (predict-no)
  1034. I see 0 and I'm going to do: predict-no
  1035. ENV: Agent did: predict-no for direction R in state State-B
  1036. In State-B moving R
  1037. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  1038. predict error 0
  1039. dir: dir isL
  1040. \-/140: O: O280 (predict-no)
  1041. I see 1 and I'm going to do: predict-no
  1042. ENV: Agent did: predict-no for direction L in state State-B
  1043. In State-B moving L
  1044. ENV: (next state, see, prediction correct?) = (State-A, 1, False)
  1045. predict error 1
  1046. dir: dir isR
  1047. |\-141: O: O282 (predict-no)
  1048. I see 0 and I'm going to do: predict-no
  1049. ENV: Agent did: predict-no for direction R in state State-A
  1050. In State-A moving R
  1051. ENV: (next state, see, prediction correct?) = (State-B, 1, False)
  1052. predict error 1
  1053. dir: dir isL
  1054. rule alias: '*'
  1055. rule alias: '*'
  1056. /142: O: O284 (predict-no)
  1057. I see 0 and I'm going to do: predict-no
  1058. ENV: Agent did: predict-no for direction L in state State-B
  1059. In State-B moving L
  1060. ENV: (next state, see, prediction correct?) = (State-A, 1, False)
  1061. predict error 1
  1062. dir: dir isL
  1063. |\143: O: O285 (predict-yes)
  1064. I see 0 and I'm going to do: predict-yes
  1065. ENV: Agent did: predict-yes for direction L in state State-A
  1066. In State-A moving L
  1067. ENV: (next state, see, prediction correct?) = (State-A, 0, False)
  1068. predict error 1
  1069. dir: dir isU
  1070. -/|144: O: O288 (predict-no)
  1071. I see 0 and I'm going to do: predict-no
  1072. ENV: Agent did: predict-no for direction U in state State-A
  1073. In State-A moving U
  1074. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  1075. predict error 0
  1076. dir: dir isL
  1077. \-145: O: O290 (predict-no)
  1078. I see 1 and I'm going to do: predict-no
  1079. ENV: Agent did: predict-no for direction L in state State-A
  1080. In State-A moving L
  1081. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  1082. predict error 0
  1083. dir: dir isR
  1084. /|\146: O: O292 (predict-no)
  1085. I see 1 and I'm going to do: predict-no
  1086. ENV: Agent did: predict-no for direction R in state State-A
  1087. In State-A moving R
  1088. ENV: (next state, see, prediction correct?) = (State-B, 1, False)
  1089. predict error 1
  1090. dir: dir isU
  1091. -/|147: O: O294 (predict-no)
  1092. I see 0 and I'm going to do: predict-no
  1093. ENV: Agent did: predict-no for direction U in state State-B
  1094. In State-B moving U
  1095. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  1096. predict error 0
  1097. dir: dir isU
  1098. \-/148: O: O296 (predict-no)
  1099. I see 1 and I'm going to do: predict-no
  1100. ENV: Agent did: predict-no for direction U in state State-B
  1101. In State-B moving U
  1102. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  1103. predict error 0
  1104. dir: dir isU
  1105. |\-149: O: O298 (predict-no)
  1106. I see 1 and I'm going to do: predict-no
  1107. ENV: Agent did: predict-no for direction U in state State-B
  1108. In State-B moving U
  1109. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  1110. predict error 0
  1111. dir: dir isL
  1112. /|\150: O: O300 (predict-no)
  1113. I see 1 and I'm going to do: predict-no
  1114. ENV: Agent did: predict-no for direction L in state State-B
  1115. In State-B moving L
  1116. ENV: (next state, see, prediction correct?) = (State-A, 1, False)
  1117. predict error 1
  1118. dir: dir isU
  1119. -/|151: O: O302 (predict-no)
  1120. I see 0 and I'm going to do: predict-no
  1121. ENV: Agent did: predict-no for direction U in state State-A
  1122. In State-A moving U
  1123. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  1124. predict error 0
  1125. dir: dir isU
  1126. \152: O: O304 (predict-no)
  1127. I see 1 and I'm going to do: predict-no
  1128. ENV: Agent did: predict-no for direction U in state State-A
  1129. In State-A moving U
  1130. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  1131. predict error 0
  1132. dir: dir isL
  1133. -/|153: O: O306 (predict-no)
  1134. I see 1 and I'm going to do: predict-no
  1135. ENV: Agent did: predict-no for direction L in state State-A
  1136. In State-A moving L
  1137. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  1138. predict error 0
  1139. dir: dir isU
  1140. \-154: O: O308 (predict-no)
  1141. I see 1 and I'm going to do: predict-no
  1142. ENV: Agent did: predict-no for direction U in state State-A
  1143. In State-A moving U
  1144. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  1145. predict error 0
  1146. dir: dir isU
  1147. /|\155: O: O310 (predict-no)
  1148. I see 1 and I'm going to do: predict-no
  1149. ENV: Agent did: predict-no for direction U in state State-A
  1150. In State-A moving U
  1151. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  1152. predict error 0
  1153. dir: dir isR
  1154. -/156: O: O312 (predict-no)
  1155. I see 1 and I'm going to do: predict-no
  1156. ENV: Agent did: predict-no for direction R in state State-A
  1157. In State-A moving R
  1158. ENV: (next state, see, prediction correct?) = (State-B, 1, False)
  1159. predict error 1
  1160. dir: dir isL
  1161. |\-157: O: O314 (predict-no)
  1162. I see 0 and I'm going to do: predict-no
  1163. ENV: Agent did: predict-no for direction L in state State-B
  1164. In State-B moving L
  1165. ENV: (next state, see, prediction correct?) = (State-A, 1, False)
  1166. predict error 1
  1167. dir: dir isR
  1168. /|158: O: O316 (predict-no)
  1169. I see 0 and I'm going to do: predict-no
  1170. ENV: Agent did: predict-no for direction R in state State-A
  1171. In State-A moving R
  1172. ENV: (next state, see, prediction correct?) = (State-B, 1, False)
  1173. predict error 1
  1174. dir: dir isR
  1175. \-/159: O: O318 (predict-no)
  1176. I see 0 and I'm going to do: predict-no
  1177. ENV: Agent did: predict-no for direction R in state State-B
  1178. In State-B moving R
  1179. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  1180. predict error 0
  1181. dir: dir isL
  1182. |\160: O: O319 (predict-yes)
  1183. I see 1 and I'm going to do: predict-yes
  1184. ENV: Agent did: predict-yes for direction L in state State-B
  1185. In State-B moving L
  1186. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  1187. predict error 0
  1188. dir: dir isR
  1189. -/|161: O: O322 (predict-no)
  1190. I see 1 and I'm going to do: predict-no
  1191. ENV: Agent did: predict-no for direction R in state State-A
  1192. In State-A moving R
  1193. ENV: (next state, see, prediction correct?) = (State-B, 1, False)
  1194. predict error 1
  1195. dir: dir isR
  1196. \162: O: O324 (predict-no)
  1197. I see 0 and I'm going to do: predict-no
  1198. ENV: Agent did: predict-no for direction R in state State-B
  1199. In State-B moving R
  1200. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  1201. predict error 0
  1202. dir: dir isR
  1203. -/|163: O: O326 (predict-no)
  1204. I see 1 and I'm going to do: predict-no
  1205. ENV: Agent did: predict-no for direction R in state State-B
  1206. In State-B moving R
  1207. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  1208. predict error 0
  1209. dir: dir isR
  1210. \-/164: O: O328 (predict-no)
  1211. I see 1 and I'm going to do: predict-no
  1212. ENV: Agent did: predict-no for direction R in state State-B
  1213. In State-B moving R
  1214. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  1215. predict error 0
  1216. dir: dir isL
  1217. |\165: O: O329 (predict-yes)
  1218. I see 1 and I'm going to do: predict-yes
  1219. ENV: Agent did: predict-yes for direction L in state State-B
  1220. In State-B moving L
  1221. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  1222. predict error 0
  1223. dir: dir isR
  1224. -/|166: O: O332 (predict-no)
  1225. I see 1 and I'm going to do: predict-no
  1226. ENV: Agent did: predict-no for direction R in state State-A
  1227. In State-A moving R
  1228. ENV: (next state, see, prediction correct?) = (State-B, 1, False)
  1229. predict error 1
  1230. dir: dir isU
  1231. \-167: O: O334 (predict-no)
  1232. I see 0 and I'm going to do: predict-no
  1233. ENV: Agent did: predict-no for direction U in state State-B
  1234. In State-B moving U
  1235. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  1236. predict error 0
  1237. dir: dir isL
  1238. /|\168: O: O335 (predict-yes)
  1239. I see 1 and I'm going to do: predict-yes
  1240. ENV: Agent did: predict-yes for direction L in state State-B
  1241. In State-B moving L
  1242. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  1243. predict error 0
  1244. dir: dir isR
  1245. -/|169: O: O338 (predict-no)
  1246. I see 1 and I'm going to do: predict-no
  1247. ENV: Agent did: predict-no for direction R in state State-A
  1248. In State-A moving R
  1249. ENV: (next state, see, prediction correct?) = (State-B, 1, False)
  1250. predict error 1
  1251. dir: dir isL
  1252. \-/170: O: O339 (predict-yes)
  1253. I see 0 and I'm going to do: predict-yes
  1254. ENV: Agent did: predict-yes for direction L in state State-B
  1255. In State-B moving L
  1256. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  1257. predict error 0
  1258. dir: dir isU
  1259. |\-171: O: O342 (predict-no)
  1260. I see 1 and I'm going to do: predict-no
  1261. ENV: Agent did: predict-no for direction U in state State-A
  1262. In State-A moving U
  1263. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  1264. predict error 0
  1265. dir: dir isR
  1266. /172: O: O344 (predict-no)
  1267. I see 1 and I'm going to do: predict-no
  1268. ENV: Agent did: predict-no for direction R in state State-A
  1269. In State-A moving R
  1270. ENV: (next state, see, prediction correct?) = (State-B, 1, False)
  1271. predict error 1
  1272. dir: dir isL
  1273. |\-173: O: O345 (predict-yes)
  1274. I see 0 and I'm going to do: predict-yes
  1275. ENV: Agent did: predict-yes for direction L in state State-B
  1276. In State-B moving L
  1277. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  1278. predict error 0
  1279. dir: dir isL
  1280. /|\174: O: O348 (predict-no)
  1281. I see 1 and I'm going to do: predict-no
  1282. ENV: Agent did: predict-no for direction L in state State-A
  1283. In State-A moving L
  1284. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  1285. predict error 0
  1286. dir: dir isL
  1287. -/|175: O: O350 (predict-no)
  1288. I see 1 and I'm going to do: predict-no
  1289. ENV: Agent did: predict-no for direction L in state State-A
  1290. In State-A moving L
  1291. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  1292. predict error 0
  1293. dir: dir isU
  1294. \-/176: O: O352 (predict-no)
  1295. I see 1 and I'm going to do: predict-no
  1296. ENV: Agent did: predict-no for direction U in state State-A
  1297. In State-A moving U
  1298. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  1299. predict error 0
  1300. dir: dir isR
  1301. |\-177: O: O354 (predict-no)
  1302. I see 1 and I'm going to do: predict-no
  1303. ENV: Agent did: predict-no for direction R in state State-A
  1304. In State-A moving R
  1305. ENV: (next state, see, prediction correct?) = (State-B, 1, False)
  1306. predict error 1
  1307. dir: dir isL
  1308. /|178: O: O355 (predict-yes)
  1309. I see 0 and I'm going to do: predict-yes
  1310. ENV: Agent did: predict-yes for direction L in state State-B
  1311. In State-B moving L
  1312. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  1313. predict error 0
  1314. dir: dir isR
  1315. \-179: O: O358 (predict-no)
  1316. I see 1 and I'm going to do: predict-no
  1317. ENV: Agent did: predict-no for direction R in state State-A
  1318. In State-A moving R
  1319. ENV: (next state, see, prediction correct?) = (State-B, 1, False)
  1320. predict error 1
  1321. dir: dir isU
  1322. /|\180: O: O360 (predict-no)
  1323. I see 0 and I'm going to do: predict-no
  1324. ENV: Agent did: predict-no for direction U in state State-B
  1325. In State-B moving U
  1326. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  1327. predict error 0
  1328. dir: dir isR
  1329. -/181: O: O362 (predict-no)
  1330. I see 1 and I'm going to do: predict-no
  1331. ENV: Agent did: predict-no for direction R in state State-B
  1332. In State-B moving R
  1333. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  1334. predict error 0
  1335. dir: dir isR
  1336. |182: O: O364 (predict-no)
  1337. I see 1 and I'm going to do: predict-no
  1338. ENV: Agent did: predict-no for direction R in state State-B
  1339. In State-B moving R
  1340. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  1341. predict error 0
  1342. dir: dir isU
  1343. \-/183: O: O366 (predict-no)
  1344. I see 1 and I'm going to do: predict-no
  1345. ENV: Agent did: predict-no for direction U in state State-B
  1346. In State-B moving U
  1347. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  1348. predict error 0
  1349. dir: dir isR
  1350. |\184: O: O368 (predict-no)
  1351. I see 1 and I'm going to do: predict-no
  1352. ENV: Agent did: predict-no for direction R in state State-B
  1353. In State-B moving R
  1354. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  1355. predict error 0
  1356. dir: dir isR
  1357. -/185: O: O370 (predict-no)
  1358. I see 1 and I'm going to do: predict-no
  1359. ENV: Agent did: predict-no for direction R in state State-B
  1360. In State-B moving R
  1361. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  1362. predict error 0
  1363. dir: dir isR
  1364. |\-186: O: O372 (predict-no)
  1365. I see 1 and I'm going to do: predict-no
  1366. ENV: Agent did: predict-no for direction R in state State-B
  1367. In State-B moving R
  1368. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  1369. predict error 0
  1370. dir: dir isL
  1371. /|\187: O: O373 (predict-yes)
  1372. I see 1 and I'm going to do: predict-yes
  1373. ENV: Agent did: predict-yes for direction L in state State-B
  1374. In State-B moving L
  1375. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  1376. predict error 0
  1377. dir: dir isL
  1378. -/|188: O: O376 (predict-no)
  1379. I see 1 and I'm going to do: predict-no
  1380. ENV: Agent did: predict-no for direction L in state State-A
  1381. In State-A moving L
  1382. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  1383. predict error 0
  1384. dir: dir isR
  1385. \-/189: O: O378 (predict-no)
  1386. I see 1 and I'm going to do: predict-no
  1387. ENV: Agent did: predict-no for direction R in state State-A
  1388. In State-A moving R
  1389. ENV: (next state, see, prediction correct?) = (State-B, 1, False)
  1390. predict error 1
  1391. dir: dir isL
  1392. |\-190: O: O379 (predict-yes)
  1393. I see 0 and I'm going to do: predict-yes
  1394. ENV: Agent did: predict-yes for direction L in state State-B
  1395. In State-B moving L
  1396. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  1397. predict error 0
  1398. dir: dir isR
  1399. /|191: O: O382 (predict-no)
  1400. I see 1 and I'm going to do: predict-no
  1401. ENV: Agent did: predict-no for direction R in state State-A
  1402. In State-A moving R
  1403. ENV: (next state, see, prediction correct?) = (State-B, 1, False)
  1404. predict error 1
  1405. dir: dir isR
  1406. \192: O: O384 (predict-no)
  1407. I see 0 and I'm going to do: predict-no
  1408. ENV: Agent did: predict-no for direction R in state State-B
  1409. In State-B moving R
  1410. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  1411. predict error 0
  1412. dir: dir isU
  1413. -/193: O: O386 (predict-no)
  1414. I see 1 and I'm going to do: predict-no
  1415. ENV: Agent did: predict-no for direction U in state State-B
  1416. In State-B moving U
  1417. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  1418. predict error 0
  1419. dir: dir isR
  1420. |194: O: O388 (predict-no)
  1421. I see 1 and I'm going to do: predict-no
  1422. ENV: Agent did: predict-no for direction R in state State-B
  1423. In State-B moving R
  1424. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  1425. predict error 0
  1426. dir: dir isR
  1427. \-/195: O: O390 (predict-no)
  1428. I see 1 and I'm going to do: predict-no
  1429. ENV: Agent did: predict-no for direction R in state State-B
  1430. In State-B moving R
  1431. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  1432. predict error 0
  1433. dir: dir isR
  1434. |\-196: O: O392 (predict-no)
  1435. I see 1 and I'm going to do: predict-no
  1436. ENV: Agent did: predict-no for direction R in state State-B
  1437. In State-B moving R
  1438. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  1439. predict error 0
  1440. dir: dir isU
  1441. /|\197: O: O394 (predict-no)
  1442. I see 1 and I'm going to do: predict-no
  1443. ENV: Agent did: predict-no for direction U in state State-B
  1444. In State-B moving U
  1445. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  1446. predict error 0
  1447. dir: dir isR
  1448. -/|198: O: O396 (predict-no)
  1449. I see 1 and I'm going to do: predict-no
  1450. ENV: Agent did: predict-no for direction R in state State-B
  1451. In State-B moving R
  1452. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  1453. predict error 0
  1454. dir: dir isR
  1455. \-/199: O: O398 (predict-no)
  1456. I see 1 and I'm going to do: predict-no
  1457. ENV: Agent did: predict-no for direction R in state State-B
  1458. In State-B moving R
  1459. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  1460. predict error 0
  1461. dir: dir isL
  1462. |\-200: O: O399 (predict-yes)
  1463. I see 1 and I'm going to do: predict-yes
  1464. ENV: Agent did: predict-yes for direction L in state State-B
  1465. In State-B moving L
  1466. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  1467. predict error 0
  1468. dir: dir isR
  1469. /|\201: O: O402 (predict-no)
  1470. I see 1 and I'm going to do: predict-no
  1471. ENV: Agent did: predict-no for direction R in state State-A
  1472. In State-A moving R
  1473. ENV: (next state, see, prediction correct?) = (State-B, 1, False)
  1474. predict error 1
  1475. dir: dir isL
  1476. -/202: O: O403 (predict-yes)
  1477. I see 0 and I'm going to do: predict-yes
  1478. ENV: Agent did: predict-yes for direction L in state State-B
  1479. In State-B moving L
  1480. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  1481. predict error 0
  1482. dir: dir isL
  1483. |\-203: O: O406 (predict-no)
  1484. I see 1 and I'm going to do: predict-no
  1485. ENV: Agent did: predict-no for direction L in state State-A
  1486. In State-A moving L
  1487. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  1488. predict error 0
  1489. dir: dir isR
  1490. /|\204: O: O408 (predict-no)
  1491. I see 1 and I'm going to do: predict-no
  1492. ENV: Agent did: predict-no for direction R in state State-A
  1493. In State-A moving R
  1494. ENV: (next state, see, prediction correct?) = (State-B, 1, False)
  1495. predict error 1
  1496. dir: dir isR
  1497. -/205: O: O410 (predict-no)
  1498. I see 0 and I'm going to do: predict-no
  1499. ENV: Agent did: predict-no for direction R in state State-B
  1500. In State-B moving R
  1501. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  1502. predict error 0
  1503. dir: dir isR
  1504. |\206: O: O412 (predict-no)
  1505. I see 1 and I'm going to do: predict-no
  1506. ENV: Agent did: predict-no for direction R in state State-B
  1507. In State-B moving R
  1508. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  1509. predict error 0
  1510. dir: dir isU
  1511. -/|207: O: O414 (predict-no)
  1512. I see 1 and I'm going to do: predict-no
  1513. ENV: Agent did: predict-no for direction U in state State-B
  1514. In State-B moving U
  1515. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  1516. predict error 0
  1517. dir: dir isU
  1518. \-/208: O: O416 (predict-no)
  1519. I see 1 and I'm going to do: predict-no
  1520. ENV: Agent did: predict-no for direction U in state State-B
  1521. In State-B moving U
  1522. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  1523. predict error 0
  1524. dir: dir isR
  1525. |\209: O: O418 (predict-no)
  1526. I see 1 and I'm going to do: predict-no
  1527. ENV: Agent did: predict-no for direction R in state State-B
  1528. In State-B moving R
  1529. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  1530. predict error 0
  1531. dir: dir isL
  1532. -/|210: O: O419 (predict-yes)
  1533. I see 1 and I'm going to do: predict-yes
  1534. ENV: Agent did: predict-yes for direction L in state State-B
  1535. In State-B moving L
  1536. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  1537. predict error 0
  1538. dir: dir isR
  1539. \-211: O: O422 (predict-no)
  1540. I see 1 and I'm going to do: predict-no
  1541. ENV: Agent did: predict-no for direction R in state State-A
  1542. In State-A moving R
  1543. ENV: (next state, see, prediction correct?) = (State-B, 1, False)
  1544. predict error 1
  1545. dir: dir isU
  1546. /212: O: O424 (predict-no)
  1547. I see 0 and I'm going to do: predict-no
  1548. ENV: Agent did: predict-no for direction U in state State-B
  1549. In State-B moving U
  1550. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  1551. predict error 0
  1552. dir: dir isU
  1553. |\-213: O: O426 (predict-no)
  1554. I see 1 and I'm going to do: predict-no
  1555. ENV: Agent did: predict-no for direction U in state State-B
  1556. In State-B moving U
  1557. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  1558. predict error 0
  1559. dir: dir isU
  1560. /|\214: O: O428 (predict-no)
  1561. I see 1 and I'm going to do: predict-no
  1562. ENV: Agent did: predict-no for direction U in state State-B
  1563. In State-B moving U
  1564. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  1565. predict error 0
  1566. dir: dir isL
  1567. -/|215: O: O429 (predict-yes)
  1568. I see 1 and I'm going to do: predict-yes
  1569. ENV: Agent did: predict-yes for direction L in state State-B
  1570. In State-B moving L
  1571. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  1572. predict error 0
  1573. dir: dir isU
  1574. \-/216: O: O432 (predict-no)
  1575. I see 1 and I'm going to do: predict-no
  1576. ENV: Agent did: predict-no for direction U in state State-A
  1577. In State-A moving U
  1578. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  1579. predict error 0
  1580. dir: dir isR
  1581. |\-217: O: O434 (predict-no)
  1582. I see 1 and I'm going to do: predict-no
  1583. ENV: Agent did: predict-no for direction R in state State-A
  1584. In State-A moving R
  1585. ENV: (next state, see, prediction correct?) = (State-B, 1, False)
  1586. predict error 1
  1587. dir: dir isL
  1588. /|218: O: O435 (predict-yes)
  1589. I see 0 and I'm going to do: predict-yes
  1590. ENV: Agent did: predict-yes for direction L in state State-B
  1591. In State-B moving L
  1592. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  1593. predict error 0
  1594. dir: dir isU
  1595. \-219: O: O437 (predict-yes)
  1596. I see 1 and I'm going to do: predict-yes
  1597. ENV: Agent did: predict-yes for direction U in state State-A
  1598. In State-A moving U
  1599. ENV: (next state, see, prediction correct?) = (State-A, 0, False)
  1600. predict error 1
  1601. dir: dir isU
  1602. /|\220: O: O440 (predict-no)
  1603. I see 0 and I'm going to do: predict-no
  1604. ENV: Agent did: predict-no for direction U in state State-A
  1605. In State-A moving U
  1606. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  1607. predict error 0
  1608. dir: dir isR
  1609. -/|221: O: O441 (predict-yes)
  1610. I see 1 and I'm going to do: predict-yes
  1611. ENV: Agent did: predict-yes for direction R in state State-A
  1612. In State-A moving R
  1613. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  1614. predict error 0
  1615. dir: dir isU
  1616. \222: O: O444 (predict-no)
  1617. I see 1 and I'm going to do: predict-no
  1618. ENV: Agent did: predict-no for direction U in state State-B
  1619. In State-B moving U
  1620. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  1621. predict error 0
  1622. dir: dir isL
  1623. -/|223: O: O445 (predict-yes)
  1624. I see 1 and I'm going to do: predict-yes
  1625. ENV: Agent did: predict-yes for direction L in state State-B
  1626. In State-B moving L
  1627. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  1628. predict error 0
  1629. dir: dir isL
  1630. \-/224: O: O448 (predict-no)
  1631. I see 1 and I'm going to do: predict-no
  1632. ENV: Agent did: predict-no for direction L in state State-A
  1633. In State-A moving L
  1634. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  1635. predict error 0
  1636. dir: dir isU
  1637. |\-225: O: O450 (predict-no)
  1638. I see 1 and I'm going to do: predict-no
  1639. ENV: Agent did: predict-no for direction U in state State-A
  1640. In State-A moving U
  1641. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  1642. predict error 0
  1643. dir: dir isL
  1644. /|226: O: O452 (predict-no)
  1645. I see 1 and I'm going to do: predict-no
  1646. ENV: Agent did: predict-no for direction L in state State-A
  1647. In State-A moving L
  1648. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  1649. predict error 0
  1650. dir: dir isU
  1651. \-/227: O: O454 (predict-no)
  1652. I see 1 and I'm going to do: predict-no
  1653. ENV: Agent did: predict-no for direction U in state State-A
  1654. In State-A moving U
  1655. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  1656. predict error 0
  1657. dir: dir isR
  1658. |\-228: O: O455 (predict-yes)
  1659. I see 1 and I'm going to do: predict-yes
  1660. ENV: Agent did: predict-yes for direction R in state State-A
  1661. In State-A moving R
  1662. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  1663. predict error 0
  1664. dir: dir isL
  1665. /|229: O: O457 (predict-yes)
  1666. I see 1 and I'm going to do: predict-yes
  1667. ENV: Agent did: predict-yes for direction L in state State-B
  1668. In State-B moving L
  1669. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  1670. predict error 0
  1671. dir: dir isL
  1672. \-230: O: O460 (predict-no)
  1673. I see 1 and I'm going to do: predict-no
  1674. ENV: Agent did: predict-no for direction L in state State-A
  1675. In State-A moving L
  1676. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  1677. predict error 0
  1678. dir: dir isR
  1679. /|\231: O: O461 (predict-yes)
  1680. I see 1 and I'm going to do: predict-yes
  1681. ENV: Agent did: predict-yes for direction R in state State-A
  1682. In State-A moving R
  1683. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  1684. predict error 0
  1685. dir: dir isU
  1686. -232: O: O464 (predict-no)
  1687. I see 1 and I'm going to do: predict-no
  1688. ENV: Agent did: predict-no for direction U in state State-B
  1689. In State-B moving U
  1690. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  1691. predict error 0
  1692. dir: dir isL
  1693. /|233: O: O466 (predict-no)
  1694. I see 1 and I'm going to do: predict-no
  1695. ENV: Agent did: predict-no for direction L in state State-B
  1696. In State-B moving L
  1697. ENV: (next state, see, prediction correct?) = (State-A, 1, False)
  1698. predict error 1
  1699. dir: dir isU
  1700. \-/234: O: O468 (predict-no)
  1701. I see 0 and I'm going to do: predict-no
  1702. ENV: Agent did: predict-no for direction U in state State-A
  1703. In State-A moving U
  1704. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  1705. predict error 0
  1706. dir: dir isL
  1707. |\-235: O: O470 (predict-no)
  1708. I see 1 and I'm going to do: predict-no
  1709. ENV: Agent did: predict-no for direction L in state State-A
  1710. In State-A moving L
  1711. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  1712. predict error 0
  1713. dir: dir isU
  1714. /|\236: O: O472 (predict-no)
  1715. I see 1 and I'm going to do: predict-no
  1716. ENV: Agent did: predict-no for direction U in state State-A
  1717. In State-A moving U
  1718. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  1719. predict error 0
  1720. dir: dir isR
  1721. -/|237: O: O473 (predict-yes)
  1722. I see 1 and I'm going to do: predict-yes
  1723. ENV: Agent did: predict-yes for direction R in state State-A
  1724. In State-A moving R
  1725. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  1726. predict error 0
  1727. dir: dir isL
  1728. \-/238: O: O475 (predict-yes)
  1729. I see 1 and I'm going to do: predict-yes
  1730. ENV: Agent did: predict-yes for direction L in state State-B
  1731. In State-B moving L
  1732. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  1733. predict error 0
  1734. dir: dir isL
  1735. |\-239: O: O478 (predict-no)
  1736. I see 1 and I'm going to do: predict-no
  1737. ENV: Agent did: predict-no for direction L in state State-A
  1738. In State-A moving L
  1739. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  1740. predict error 0
  1741. dir: dir isR
  1742. /|\240: O: O479 (predict-yes)
  1743. I see 1 and I'm going to do: predict-yes
  1744. ENV: Agent did: predict-yes for direction R in state State-A
  1745. In State-A moving R
  1746. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  1747. predict error 0
  1748. dir: dir isU
  1749. -/|241: O: O482 (predict-no)
  1750. I see 1 and I'm going to do: predict-no
  1751. ENV: Agent did: predict-no for direction U in state State-B
  1752. In State-B moving U
  1753. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  1754. predict error 0
  1755. dir: dir isU
  1756. \242: O: O483 (predict-yes)
  1757. I see 1 and I'm going to do: predict-yes
  1758. ENV: Agent did: predict-yes for direction U in state State-B
  1759. In State-B moving U
  1760. ENV: (next state, see, prediction correct?) = (State-B, 0, False)
  1761. predict error 1
  1762. dir: dir isL
  1763. -/|243: O: O485 (predict-yes)
  1764. I see 0 and I'm going to do: predict-yes
  1765. ENV: Agent did: predict-yes for direction L in state State-B
  1766. In State-B moving L
  1767. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  1768. predict error 0
  1769. dir: dir isR
  1770. \-/244: O: O487 (predict-yes)
  1771. I see 1 and I'm going to do: predict-yes
  1772. ENV: Agent did: predict-yes for direction R in state State-A
  1773. In State-A moving R
  1774. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  1775. predict error 0
  1776. dir: dir isR
  1777. |\-245: O: O490 (predict-no)
  1778. I see 1 and I'm going to do: predict-no
  1779. ENV: Agent did: predict-no for direction R in state State-B
  1780. In State-B moving R
  1781. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  1782. predict error 0
  1783. dir: dir isR
  1784. /|\246: O: O492 (predict-no)
  1785. I see 1 and I'm going to do: predict-no
  1786. ENV: Agent did: predict-no for direction R in state State-B
  1787. In State-B moving R
  1788. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  1789. predict error 0
  1790. dir: dir isU
  1791. -/|247: O: O494 (predict-no)
  1792. I see 1 and I'm going to do: predict-no
  1793. ENV: Agent did: predict-no for direction U in state State-B
  1794. In State-B moving U
  1795. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  1796. predict error 0
  1797. dir: dir isL
  1798. \-/248: O: O495 (predict-yes)
  1799. I see 1 and I'm going to do: predict-yes
  1800. ENV: Agent did: predict-yes for direction L in state State-B
  1801. In State-B moving L
  1802. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  1803. predict error 0
  1804. dir: dir isL
  1805. |\249: O: O498 (predict-no)
  1806. I see 1 and I'm going to do: predict-no
  1807. ENV: Agent did: predict-no for direction L in state State-A
  1808. In State-A moving L
  1809. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  1810. predict error 0
  1811. dir: dir isL
  1812. -/|250: O: O500 (predict-no)
  1813. I see 1 and I'm going to do: predict-no
  1814. ENV: Agent did: predict-no for direction L in state State-A
  1815. In State-A moving L
  1816. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  1817. predict error 0
  1818. dir: dir isU
  1819. \-251: O: O502 (predict-no)
  1820. I see 1 and I'm going to do: predict-no
  1821. ENV: Agent did: predict-no for direction U in state State-A
  1822. In State-A moving U
  1823. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  1824. predict error 0
  1825. dir: dir isR
  1826. /252: O: O503 (predict-yes)
  1827. I see 1 and I'm going to do: predict-yes
  1828. ENV: Agent did: predict-yes for direction R in state State-A
  1829. In State-A moving R
  1830. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  1831. predict error 0
  1832. dir: dir isU
  1833. |\253: O: O506 (predict-no)
  1834. I see 1 and I'm going to do: predict-no
  1835. ENV: Agent did: predict-no for direction U in state State-B
  1836. In State-B moving U
  1837. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  1838. predict error 0
  1839. dir: dir isU
  1840. -/|254: O: O508 (predict-no)
  1841. I see 1 and I'm going to do: predict-no
  1842. ENV: Agent did: predict-no for direction U in state State-B
  1843. In State-B moving U
  1844. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  1845. predict error 0
  1846. dir: dir isU
  1847. \-/255: O: O509 (predict-yes)
  1848. I see 1 and I'm going to do: predict-yes
  1849. ENV: Agent did: predict-yes for direction U in state State-B
  1850. In State-B moving U
  1851. ENV: (next state, see, prediction correct?) = (State-B, 0, False)
  1852. predict error 1
  1853. dir: dir isL
  1854. |\256: O: O511 (predict-yes)
  1855. I see 0 and I'm going to do: predict-yes
  1856. ENV: Agent did: predict-yes for direction L in state State-B
  1857. In State-B moving L
  1858. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  1859. predict error 0
  1860. dir: dir isU
  1861. -/|257: O: O514 (predict-no)
  1862. I see 1 and I'm going to do: predict-no
  1863. ENV: Agent did: predict-no for direction U in state State-A
  1864. In State-A moving U
  1865. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  1866. predict error 0
  1867. dir: dir isU
  1868. \-/258: O: O516 (predict-no)
  1869. I see 1 and I'm going to do: predict-no
  1870. ENV: Agent did: predict-no for direction U in state State-A
  1871. In State-A moving U
  1872. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  1873. predict error 0
  1874. dir: dir isR
  1875. |\-259: O: O517 (predict-yes)
  1876. I see 1 and I'm going to do: predict-yes
  1877. ENV: Agent did: predict-yes for direction R in state State-A
  1878. In State-A moving R
  1879. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  1880. predict error 0
  1881. dir: dir isU
  1882. /|\260: O: O520 (predict-no)
  1883. I see 1 and I'm going to do: predict-no
  1884. ENV: Agent did: predict-no for direction U in state State-B
  1885. In State-B moving U
  1886. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  1887. predict error 0
  1888. dir: dir isU
  1889. -/261: O: O521 (predict-yes)
  1890. I see 1 and I'm going to do: predict-yes
  1891. ENV: Agent did: predict-yes for direction U in state State-B
  1892. In State-B moving U
  1893. ENV: (next state, see, prediction correct?) = (State-B, 0, False)
  1894. predict error 1
  1895. dir: dir isR
  1896. |262: O: O523 (predict-yes)
  1897. I see 0 and I'm going to do: predict-yes
  1898. ENV: Agent did: predict-yes for direction R in state State-B
  1899. In State-B moving R
  1900. ENV: (next state, see, prediction correct?) = (State-B, 0, False)
  1901. predict error 1
  1902. dir: dir isR
  1903. \-263: O: O526 (predict-no)
  1904. I see 0 and I'm going to do: predict-no
  1905. ENV: Agent did: predict-no for direction R in state State-B
  1906. In State-B moving R
  1907. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  1908. predict error 0
  1909. dir: dir isR
  1910. /|264: O: O528 (predict-no)
  1911. I see 1 and I'm going to do: predict-no
  1912. ENV: Agent did: predict-no for direction R in state State-B
  1913. In State-B moving R
  1914. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  1915. predict error 0
  1916. dir: dir isL
  1917. \-/265: O: O529 (predict-yes)
  1918. I see 1 and I'm going to do: predict-yes
  1919. ENV: Agent did: predict-yes for direction L in state State-B
  1920. In State-B moving L
  1921. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  1922. predict error 0
  1923. dir: dir isR
  1924. |\-266: O: O531 (predict-yes)
  1925. I see 1 and I'm going to do: predict-yes
  1926. ENV: Agent did: predict-yes for direction R in state State-A
  1927. In State-A moving R
  1928. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  1929. predict error 0
  1930. dir: dir isL
  1931. /|267: O: O533 (predict-yes)
  1932. I see 1 and I'm going to do: predict-yes
  1933. ENV: Agent did: predict-yes for direction L in state State-B
  1934. In State-B moving L
  1935. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  1936. predict error 0
  1937. dir: dir isL
  1938. \-268: O: O536 (predict-no)
  1939. I see 1 and I'm going to do: predict-no
  1940. ENV: Agent did: predict-no for direction L in state State-A
  1941. In State-A moving L
  1942. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  1943. predict error 0
  1944. dir: dir isR
  1945. /|269: O: O538 (predict-no)
  1946. I see 1 and I'm going to do: predict-no
  1947. ENV: Agent did: predict-no for direction R in state State-A
  1948. In State-A moving R
  1949. ENV: (next state, see, prediction correct?) = (State-B, 1, False)
  1950. predict error 1
  1951. dir: dir isU
  1952. \-/270: O: O540 (predict-no)
  1953. I see 0 and I'm going to do: predict-no
  1954. ENV: Agent did: predict-no for direction U in state State-B
  1955. In State-B moving U
  1956. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  1957. predict error 0
  1958. dir: dir isU
  1959. |\-271: O: O542 (predict-no)
  1960. I see 1 and I'm going to do: predict-no
  1961. ENV: Agent did: predict-no for direction U in state State-B
  1962. In State-B moving U
  1963. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  1964. predict error 0
  1965. dir: dir isR
  1966. /272: O: O544 (predict-no)
  1967. I see 1 and I'm going to do: predict-no
  1968. ENV: Agent did: predict-no for direction R in state State-B
  1969. In State-B moving R
  1970. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  1971. predict error 0
  1972. dir: dir isR
  1973. |\-273: O: O546 (predict-no)
  1974. I see 1 and I'm going to do: predict-no
  1975. ENV: Agent did: predict-no for direction R in state State-B
  1976. In State-B moving R
  1977. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  1978. predict error 0
  1979. dir: dir isL
  1980. /|274: O: O547 (predict-yes)
  1981. I see 1 and I'm going to do: predict-yes
  1982. ENV: Agent did: predict-yes for direction L in state State-B
  1983. In State-B moving L
  1984. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  1985. predict error 0
  1986. dir: dir isL
  1987. \-/275: O: O550 (predict-no)
  1988. I see 1 and I'm going to do: predict-no
  1989. ENV: Agent did: predict-no for direction L in state State-A
  1990. In State-A moving L
  1991. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  1992. predict error 0
  1993. dir: dir isU
  1994. |\-276: O: O552 (predict-no)
  1995. I see 1 and I'm going to do: predict-no
  1996. ENV: Agent did: predict-no for direction U in state State-A
  1997. In State-A moving U
  1998. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  1999. predict error 0
  2000. dir: dir isL
  2001. /|\277: O: O554 (predict-no)
  2002. I see 1 and I'm going to do: predict-no
  2003. ENV: Agent did: predict-no for direction L in state State-A
  2004. In State-A moving L
  2005. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  2006. predict error 0
  2007. dir: dir isR
  2008. -/278: O: O555 (predict-yes)
  2009. I see 1 and I'm going to do: predict-yes
  2010. ENV: Agent did: predict-yes for direction R in state State-A
  2011. In State-A moving R
  2012. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  2013. predict error 0
  2014. dir: dir isR
  2015. |\-279: O: O558 (predict-no)
  2016. I see 1 and I'm going to do: predict-no
  2017. ENV: Agent did: predict-no for direction R in state State-B
  2018. In State-B moving R
  2019. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2020. predict error 0
  2021. dir: dir isL
  2022. /|280: O: O559 (predict-yes)
  2023. I see 1 and I'm going to do: predict-yes
  2024. ENV: Agent did: predict-yes for direction L in state State-B
  2025. In State-B moving L
  2026. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  2027. predict error 0
  2028. dir: dir isR
  2029. \-/281: O: O561 (predict-yes)
  2030. I see 1 and I'm going to do: predict-yes
  2031. ENV: Agent did: predict-yes for direction R in state State-A
  2032. In State-A moving R
  2033. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  2034. predict error 0
  2035. dir: dir isL
  2036. |282: O: O563 (predict-yes)
  2037. I see 1 and I'm going to do: predict-yes
  2038. ENV: Agent did: predict-yes for direction L in state State-B
  2039. In State-B moving L
  2040. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  2041. predict error 0
  2042. dir: dir isL
  2043. \-/283: O: O565 (predict-yes)
  2044. I see 1 and I'm going to do: predict-yes
  2045. ENV: Agent did: predict-yes for direction L in state State-A
  2046. In State-A moving L
  2047. ENV: (next state, see, prediction correct?) = (State-A, 0, False)
  2048. predict error 1
  2049. dir: dir isL
  2050. |\-284: O: O568 (predict-no)
  2051. I see 0 and I'm going to do: predict-no
  2052. ENV: Agent did: predict-no for direction L in state State-A
  2053. In State-A moving L
  2054. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  2055. predict error 0
  2056. dir: dir isR
  2057. /|\-sleeping...
  2058. /285: O: O569 (predict-yes)
  2059. I see 1 and I'm going to do: predict-yes
  2060. ENV: Agent did: predict-yes for direction R in state State-A
  2061. In State-A moving R
  2062. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  2063. predict error 0
  2064. dir: dir isL
  2065. |\-286: O: O572 (predict-no)
  2066. I see 1 and I'm going to do: predict-no
  2067. ENV: Agent did: predict-no for direction L in state State-B
  2068. In State-B moving L
  2069. ENV: (next state, see, prediction correct?) = (State-A, 1, False)
  2070. predict error 1
  2071. dir: dir isR
  2072. /|\287: O: O573 (predict-yes)
  2073. I see 0 and I'm going to do: predict-yes
  2074. ENV: Agent did: predict-yes for direction R in state State-A
  2075. In State-A moving R
  2076. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  2077. predict error 0
  2078. dir: dir isL
  2079. -/288: O: O575 (predict-yes)
  2080. I see 1 and I'm going to do: predict-yes
  2081. ENV: Agent did: predict-yes for direction L in state State-B
  2082. In State-B moving L
  2083. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  2084. predict error 0
  2085. dir: dir isR
  2086. |\289: O: O577 (predict-yes)
  2087. I see 1 and I'm going to do: predict-yes
  2088. ENV: Agent did: predict-yes for direction R in state State-A
  2089. In State-A moving R
  2090. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  2091. predict error 0
  2092. dir: dir isL
  2093. -/290: O: O579 (predict-yes)
  2094. I see 1 and I'm going to do: predict-yes
  2095. ENV: Agent did: predict-yes for direction L in state State-B
  2096. In State-B moving L
  2097. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  2098. predict error 0
  2099. dir: dir isU
  2100. |291: O: O582 (predict-no)
  2101. I see 1 and I'm going to do: predict-no
  2102. ENV: Agent did: predict-no for direction U in state State-A
  2103. In State-A moving U
  2104. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  2105. predict error 0
  2106. dir: dir isR
  2107. \292: O: O583 (predict-yes)
  2108. I see 1 and I'm going to do: predict-yes
  2109. ENV: Agent did: predict-yes for direction R in state State-A
  2110. In State-A moving R
  2111. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  2112. predict error 0
  2113. dir: dir isU
  2114. -/293: O: O586 (predict-no)
  2115. I see 1 and I'm going to do: predict-no
  2116. ENV: Agent did: predict-no for direction U in state State-B
  2117. In State-B moving U
  2118. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2119. predict error 0
  2120. dir: dir isU
  2121. |\-294: O: O588 (predict-no)
  2122. I see 1 and I'm going to do: predict-no
  2123. ENV: Agent did: predict-no for direction U in state State-B
  2124. In State-B moving U
  2125. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2126. predict error 0
  2127. dir: dir isR
  2128. /|\295: O: O590 (predict-no)
  2129. I see 1 and I'm going to do: predict-no
  2130. ENV: Agent did: predict-no for direction R in state State-B
  2131. In State-B moving R
  2132. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2133. predict error 0
  2134. dir: dir isR
  2135. -/296: O: O592 (predict-no)
  2136. I see 1 and I'm going to do: predict-no
  2137. ENV: Agent did: predict-no for direction R in state State-B
  2138. In State-B moving R
  2139. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2140. predict error 0
  2141. dir: dir isU
  2142. |\-297: O: O593 (predict-yes)
  2143. I see 1 and I'm going to do: predict-yes
  2144. ENV: Agent did: predict-yes for direction U in state State-B
  2145. In State-B moving U
  2146. ENV: (next state, see, prediction correct?) = (State-B, 0, False)
  2147. predict error 1
  2148. dir: dir isR
  2149. /|298: O: O596 (predict-no)
  2150. I see 0 and I'm going to do: predict-no
  2151. ENV: Agent did: predict-no for direction R in state State-B
  2152. In State-B moving R
  2153. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2154. predict error 0
  2155. dir: dir isL
  2156. \-299: O: O597 (predict-yes)
  2157. I see 1 and I'm going to do: predict-yes
  2158. ENV: Agent did: predict-yes for direction L in state State-B
  2159. In State-B moving L
  2160. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  2161. predict error 0
  2162. dir: dir isU
  2163. /|300: O: O600 (predict-no)
  2164. I see 1 and I'm going to do: predict-no
  2165. ENV: Agent did: predict-no for direction U in state State-A
  2166. In State-A moving U
  2167. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  2168. predict error 0
  2169. dir: dir isU
  2170. \-/|\-301: O: O602 (predict-no)
  2171. I see 1 and I'm going to do: predict-no
  2172. ENV: Agent did: predict-no for direction U in state State-A
  2173. In State-A moving U
  2174. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  2175. predict error 0
  2176. dir: dir isU
  2177. /302: O: O604 (predict-no)
  2178. I see 1 and I'm going to do: predict-no
  2179. ENV: Agent did: predict-no for direction U in state State-A
  2180. In State-A moving U
  2181. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  2182. predict error 0
  2183. dir: dir isR
  2184. |\-303: O: O605 (predict-yes)
  2185. I see 1 and I'm going to do: predict-yes
  2186. ENV: Agent did: predict-yes for direction R in state State-A
  2187. In State-A moving R
  2188. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  2189. predict error 0
  2190. dir: dir isR
  2191. /|\-304: O: O608 (predict-no)
  2192. I see 1 and I'm going to do: predict-no
  2193. ENV: Agent did: predict-no for direction R in state State-B
  2194. In State-B moving R
  2195. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2196. predict error 0
  2197. dir: dir isU
  2198. /|305: O: O610 (predict-no)
  2199. I see 1 and I'm going to do: predict-no
  2200. ENV: Agent did: predict-no for direction U in state State-B
  2201. In State-B moving U
  2202. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2203. predict error 0
  2204. dir: dir isR
  2205. \-/306: O: O612 (predict-no)
  2206. I see 1 and I'm going to do: predict-no
  2207. ENV: Agent did: predict-no for direction R in state State-B
  2208. In State-B moving R
  2209. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2210. predict error 0
  2211. dir: dir isL
  2212. |307: O: O613 (predict-yes)
  2213. I see 1 and I'm going to do: predict-yes
  2214. ENV: Agent did: predict-yes for direction L in state State-B
  2215. In State-B moving L
  2216. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  2217. predict error 0
  2218. dir: dir isL
  2219. \-/308: O: O616 (predict-no)
  2220. I see 1 and I'm going to do: predict-no
  2221. ENV: Agent did: predict-no for direction L in state State-A
  2222. In State-A moving L
  2223. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  2224. predict error 0
  2225. dir: dir isU
  2226. |\-309: O: O618 (predict-no)
  2227. I see 1 and I'm going to do: predict-no
  2228. ENV: Agent did: predict-no for direction U in state State-A
  2229. In State-A moving U
  2230. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  2231. predict error 0
  2232. dir: dir isL
  2233. /|\310: O: O620 (predict-no)
  2234. I see 1 and I'm going to do: predict-no
  2235. ENV: Agent did: predict-no for direction L in state State-A
  2236. In State-A moving L
  2237. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  2238. predict error 0
  2239. dir: dir isL
  2240. -/|311: O: O622 (predict-no)
  2241. I see 1 and I'm going to do: predict-no
  2242. ENV: Agent did: predict-no for direction L in state State-A
  2243. In State-A moving L
  2244. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  2245. predict error 0
  2246. dir: dir isR
  2247. \312: O: O623 (predict-yes)
  2248. I see 1 and I'm going to do: predict-yes
  2249. ENV: Agent did: predict-yes for direction R in state State-A
  2250. In State-A moving R
  2251. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  2252. predict error 0
  2253. dir: dir isR
  2254. -/|313: O: O626 (predict-no)
  2255. I see 1 and I'm going to do: predict-no
  2256. ENV: Agent did: predict-no for direction R in state State-B
  2257. In State-B moving R
  2258. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2259. predict error 0
  2260. dir: dir isR
  2261. \-/314: O: O628 (predict-no)
  2262. I see 1 and I'm going to do: predict-no
  2263. ENV: Agent did: predict-no for direction R in state State-B
  2264. In State-B moving R
  2265. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2266. predict error 0
  2267. dir: dir isR
  2268. |\-315: O: O630 (predict-no)
  2269. I see 1 and I'm going to do: predict-no
  2270. ENV: Agent did: predict-no for direction R in state State-B
  2271. In State-B moving R
  2272. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2273. predict error 0
  2274. dir: dir isR
  2275. /|\316: O: O632 (predict-no)
  2276. I see 1 and I'm going to do: predict-no
  2277. ENV: Agent did: predict-no for direction R in state State-B
  2278. In State-B moving R
  2279. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2280. predict error 0
  2281. dir: dir isU
  2282. -/317: O: O634 (predict-no)
  2283. I see 1 and I'm going to do: predict-no
  2284. ENV: Agent did: predict-no for direction U in state State-B
  2285. In State-B moving U
  2286. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2287. predict error 0
  2288. dir: dir isR
  2289. |\-318: O: O636 (predict-no)
  2290. I see 1 and I'm going to do: predict-no
  2291. ENV: Agent did: predict-no for direction R in state State-B
  2292. In State-B moving R
  2293. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2294. predict error 0
  2295. dir: dir isR
  2296. /|\319: O: O638 (predict-no)
  2297. I see 1 and I'm going to do: predict-no
  2298. ENV: Agent did: predict-no for direction R in state State-B
  2299. In State-B moving R
  2300. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2301. predict error 0
  2302. dir: dir isU
  2303. -/320: O: O640 (predict-no)
  2304. I see 1 and I'm going to do: predict-no
  2305. ENV: Agent did: predict-no for direction U in state State-B
  2306. In State-B moving U
  2307. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2308. predict error 0
  2309. dir: dir isL
  2310. |\-321: O: O641 (predict-yes)
  2311. I see 1 and I'm going to do: predict-yes
  2312. ENV: Agent did: predict-yes for direction L in state State-B
  2313. In State-B moving L
  2314. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  2315. predict error 0
  2316. dir: dir isU
  2317. /322: O: O644 (predict-no)
  2318. I see 1 and I'm going to do: predict-no
  2319. ENV: Agent did: predict-no for direction U in state State-A
  2320. In State-A moving U
  2321. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  2322. predict error 0
  2323. dir: dir isR
  2324. |\-323: O: O645 (predict-yes)
  2325. I see 1 and I'm going to do: predict-yes
  2326. ENV: Agent did: predict-yes for direction R in state State-A
  2327. In State-A moving R
  2328. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  2329. predict error 0
  2330. dir: dir isR
  2331. /|324: O: O648 (predict-no)
  2332. I see 1 and I'm going to do: predict-no
  2333. ENV: Agent did: predict-no for direction R in state State-B
  2334. In State-B moving R
  2335. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2336. predict error 0
  2337. dir: dir isL
  2338. \-/325: O: O649 (predict-yes)
  2339. I see 1 and I'm going to do: predict-yes
  2340. ENV: Agent did: predict-yes for direction L in state State-B
  2341. In State-B moving L
  2342. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  2343. predict error 0
  2344. dir: dir isU
  2345. |\-326: O: O652 (predict-no)
  2346. I see 1 and I'm going to do: predict-no
  2347. ENV: Agent did: predict-no for direction U in state State-A
  2348. In State-A moving U
  2349. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  2350. predict error 0
  2351. dir: dir isU
  2352. /|\327: O: O654 (predict-no)
  2353. I see 1 and I'm going to do: predict-no
  2354. ENV: Agent did: predict-no for direction U in state State-A
  2355. In State-A moving U
  2356. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  2357. predict error 0
  2358. dir: dir isU
  2359. -/|328: O: O656 (predict-no)
  2360. I see 1 and I'm going to do: predict-no
  2361. ENV: Agent did: predict-no for direction U in state State-A
  2362. In State-A moving U
  2363. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  2364. predict error 0
  2365. dir: dir isR
  2366. \-/329: O: O657 (predict-yes)
  2367. I see 1 and I'm going to do: predict-yes
  2368. ENV: Agent did: predict-yes for direction R in state State-A
  2369. In State-A moving R
  2370. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  2371. predict error 0
  2372. dir: dir isU
  2373. |\-330: O: O660 (predict-no)
  2374. I see 1 and I'm going to do: predict-no
  2375. ENV: Agent did: predict-no for direction U in state State-B
  2376. In State-B moving U
  2377. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2378. predict error 0
  2379. dir: dir isL
  2380. /|\331: O: O661 (predict-yes)
  2381. I see 1 and I'm going to do: predict-yes
  2382. ENV: Agent did: predict-yes for direction L in state State-B
  2383. In State-B moving L
  2384. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  2385. predict error 0
  2386. dir: dir isR
  2387. -332: O: O663 (predict-yes)
  2388. I see 1 and I'm going to do: predict-yes
  2389. ENV: Agent did: predict-yes for direction R in state State-A
  2390. In State-A moving R
  2391. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  2392. predict error 0
  2393. dir: dir isL
  2394. /|\333: O: O666 (predict-no)
  2395. I see 1 and I'm going to do: predict-no
  2396. ENV: Agent did: predict-no for direction L in state State-B
  2397. In State-B moving L
  2398. ENV: (next state, see, prediction correct?) = (State-A, 1, False)
  2399. predict error 1
  2400. dir: dir isL
  2401. -/|334: O: O668 (predict-no)
  2402. I see 0 and I'm going to do: predict-no
  2403. ENV: Agent did: predict-no for direction L in state State-A
  2404. In State-A moving L
  2405. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  2406. predict error 0
  2407. dir: dir isU
  2408. \-/|335: O: O670 (predict-no)
  2409. I see 1 and I'm going to do: predict-no
  2410. ENV: Agent did: predict-no for direction U in state State-A
  2411. In State-A moving U
  2412. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  2413. predict error 0
  2414. dir: dir isL
  2415. \-336: O: O672 (predict-no)
  2416. I see 1 and I'm going to do: predict-no
  2417. ENV: Agent did: predict-no for direction L in state State-A
  2418. In State-A moving L
  2419. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  2420. predict error 0
  2421. dir: dir isL
  2422. /|\337: O: O674 (predict-no)
  2423. I see 1 and I'm going to do: predict-no
  2424. ENV: Agent did: predict-no for direction L in state State-A
  2425. In State-A moving L
  2426. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  2427. predict error 0
  2428. dir: dir isL
  2429. -/|338: O: O676 (predict-no)
  2430. I see 1 and I'm going to do: predict-no
  2431. ENV: Agent did: predict-no for direction L in state State-A
  2432. In State-A moving L
  2433. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  2434. predict error 0
  2435. dir: dir isR
  2436. \-/339: O: O677 (predict-yes)
  2437. I see 1 and I'm going to do: predict-yes
  2438. ENV: Agent did: predict-yes for direction R in state State-A
  2439. In State-A moving R
  2440. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  2441. predict error 0
  2442. dir: dir isR
  2443. |\340: O: O680 (predict-no)
  2444. I see 1 and I'm going to do: predict-no
  2445. ENV: Agent did: predict-no for direction R in state State-B
  2446. In State-B moving R
  2447. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2448. predict error 0
  2449. dir: dir isL
  2450. -/|341: O: O681 (predict-yes)
  2451. I see 1 and I'm going to do: predict-yes
  2452. ENV: Agent did: predict-yes for direction L in state State-B
  2453. In State-B moving L
  2454. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  2455. predict error 0
  2456. dir: dir isU
  2457. \342: O: O684 (predict-no)
  2458. I see 1 and I'm going to do: predict-no
  2459. ENV: Agent did: predict-no for direction U in state State-A
  2460. In State-A moving U
  2461. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  2462. predict error 0
  2463. dir: dir isU
  2464. -/|343: O: O686 (predict-no)
  2465. I see 1 and I'm going to do: predict-no
  2466. ENV: Agent did: predict-no for direction U in state State-A
  2467. In State-A moving U
  2468. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  2469. predict error 0
  2470. dir: dir isL
  2471. \-/344: O: O687 (predict-yes)
  2472. I see 1 and I'm going to do: predict-yes
  2473. ENV: Agent did: predict-yes for direction L in state State-A
  2474. In State-A moving L
  2475. ENV: (next state, see, prediction correct?) = (State-A, 0, False)
  2476. predict error 1
  2477. dir: dir isR
  2478. |\-345: O: O689 (predict-yes)
  2479. I see 0 and I'm going to do: predict-yes
  2480. ENV: Agent did: predict-yes for direction R in state State-A
  2481. In State-A moving R
  2482. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  2483. predict error 0
  2484. dir: dir isU
  2485. /|346: O: O692 (predict-no)
  2486. I see 1 and I'm going to do: predict-no
  2487. ENV: Agent did: predict-no for direction U in state State-B
  2488. In State-B moving U
  2489. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2490. predict error 0
  2491. dir: dir isU
  2492. \347: O: O694 (predict-no)
  2493. I see 1 and I'm going to do: predict-no
  2494. ENV: Agent did: predict-no for direction U in state State-B
  2495. In State-B moving U
  2496. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2497. predict error 0
  2498. dir: dir isR
  2499. -/|348: O: O696 (predict-no)
  2500. I see 1 and I'm going to do: predict-no
  2501. ENV: Agent did: predict-no for direction R in state State-B
  2502. In State-B moving R
  2503. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2504. predict error 0
  2505. dir: dir isU
  2506. \-/349: O: O698 (predict-no)
  2507. I see 1 and I'm going to do: predict-no
  2508. ENV: Agent did: predict-no for direction U in state State-B
  2509. In State-B moving U
  2510. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2511. predict error 0
  2512. dir: dir isL
  2513. |\350: O: O699 (predict-yes)
  2514. I see 1 and I'm going to do: predict-yes
  2515. ENV: Agent did: predict-yes for direction L in state State-B
  2516. In State-B moving L
  2517. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  2518. predict error 0
  2519. dir: dir isR
  2520. -/|351: O: O701 (predict-yes)
  2521. I see 1 and I'm going to do: predict-yes
  2522. ENV: Agent did: predict-yes for direction R in state State-A
  2523. In State-A moving R
  2524. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  2525. predict error 0
  2526. dir: dir isR
  2527. \352: O: O704 (predict-no)
  2528. I see 1 and I'm going to do: predict-no
  2529. ENV: Agent did: predict-no for direction R in state State-B
  2530. In State-B moving R
  2531. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2532. predict error 0
  2533. dir: dir isU
  2534. -/353: O: O706 (predict-no)
  2535. I see 1 and I'm going to do: predict-no
  2536. ENV: Agent did: predict-no for direction U in state State-B
  2537. In State-B moving U
  2538. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2539. predict error 0
  2540. dir: dir isL
  2541. |\354: O: O707 (predict-yes)
  2542. I see 1 and I'm going to do: predict-yes
  2543. ENV: Agent did: predict-yes for direction L in state State-B
  2544. In State-B moving L
  2545. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  2546. predict error 0
  2547. dir: dir isR
  2548. -/|355: O: O709 (predict-yes)
  2549. I see 1 and I'm going to do: predict-yes
  2550. ENV: Agent did: predict-yes for direction R in state State-A
  2551. In State-A moving R
  2552. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  2553. predict error 0
  2554. dir: dir isL
  2555. \-/356: O: O711 (predict-yes)
  2556. I see 1 and I'm going to do: predict-yes
  2557. ENV: Agent did: predict-yes for direction L in state State-B
  2558. In State-B moving L
  2559. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  2560. predict error 0
  2561. dir: dir isR
  2562. |\-357: O: O713 (predict-yes)
  2563. I see 1 and I'm going to do: predict-yes
  2564. ENV: Agent did: predict-yes for direction R in state State-A
  2565. In State-A moving R
  2566. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  2567. predict error 0
  2568. dir: dir isU
  2569. /|\358: O: O716 (predict-no)
  2570. I see 1 and I'm going to do: predict-no
  2571. ENV: Agent did: predict-no for direction U in state State-B
  2572. In State-B moving U
  2573. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2574. predict error 0
  2575. dir: dir isU
  2576. -359: O: O718 (predict-no)
  2577. I see 1 and I'm going to do: predict-no
  2578. ENV: Agent did: predict-no for direction U in state State-B
  2579. In State-B moving U
  2580. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2581. predict error 0
  2582. dir: dir isU
  2583. /|\360: O: O720 (predict-no)
  2584. I see 1 and I'm going to do: predict-no
  2585. ENV: Agent did: predict-no for direction U in state State-B
  2586. In State-B moving U
  2587. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2588. predict error 0
  2589. dir: dir isL
  2590. -/361: O: O722 (predict-no)
  2591. I see 1 and I'm going to do: predict-no
  2592. ENV: Agent did: predict-no for direction L in state State-B
  2593. In State-B moving L
  2594. ENV: (next state, see, prediction correct?) = (State-A, 1, False)
  2595. predict error 1
  2596. dir: dir isL
  2597. |362: O: O724 (predict-no)
  2598. I see 0 and I'm going to do: predict-no
  2599. ENV: Agent did: predict-no for direction L in state State-A
  2600. In State-A moving L
  2601. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  2602. predict error 0
  2603. dir: dir isL
  2604. \-/363: O: O726 (predict-no)
  2605. I see 1 and I'm going to do: predict-no
  2606. ENV: Agent did: predict-no for direction L in state State-A
  2607. In State-A moving L
  2608. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  2609. predict error 0
  2610. dir: dir isU
  2611. |\-/364: O: O728 (predict-no)
  2612. I see 1 and I'm going to do: predict-no
  2613. ENV: Agent did: predict-no for direction U in state State-A
  2614. In State-A moving U
  2615. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  2616. predict error 0
  2617. dir: dir isU
  2618. |\-365: O: O730 (predict-no)
  2619. I see 1 and I'm going to do: predict-no
  2620. ENV: Agent did: predict-no for direction U in state State-A
  2621. In State-A moving U
  2622. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  2623. predict error 0
  2624. dir: dir isR
  2625. /|\366: O: O731 (predict-yes)
  2626. I see 1 and I'm going to do: predict-yes
  2627. ENV: Agent did: predict-yes for direction R in state State-A
  2628. In State-A moving R
  2629. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  2630. predict error 0
  2631. dir: dir isU
  2632. -/|367: O: O734 (predict-no)
  2633. I see 1 and I'm going to do: predict-no
  2634. ENV: Agent did: predict-no for direction U in state State-B
  2635. In State-B moving U
  2636. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2637. predict error 0
  2638. dir: dir isU
  2639. \-/368: O: O736 (predict-no)
  2640. I see 1 and I'm going to do: predict-no
  2641. ENV: Agent did: predict-no for direction U in state State-B
  2642. In State-B moving U
  2643. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2644. predict error 0
  2645. dir: dir isL
  2646. |\-369: O: O737 (predict-yes)
  2647. I see 1 and I'm going to do: predict-yes
  2648. ENV: Agent did: predict-yes for direction L in state State-B
  2649. In State-B moving L
  2650. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  2651. predict error 0
  2652. dir: dir isL
  2653. /|\370: O: O740 (predict-no)
  2654. I see 1 and I'm going to do: predict-no
  2655. ENV: Agent did: predict-no for direction L in state State-A
  2656. In State-A moving L
  2657. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  2658. predict error 0
  2659. dir: dir isU
  2660. -/|\371: O: O742 (predict-no)
  2661. I see 1 and I'm going to do: predict-no
  2662. ENV: Agent did: predict-no for direction U in state State-A
  2663. In State-A moving U
  2664. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  2665. predict error 0
  2666. dir: dir isL
  2667. -372: O: O744 (predict-no)
  2668. I see 1 and I'm going to do: predict-no
  2669. ENV: Agent did: predict-no for direction L in state State-A
  2670. In State-A moving L
  2671. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  2672. predict error 0
  2673. dir: dir isL
  2674. /|\373: O: O745 (predict-yes)
  2675. I see 1 and I'm going to do: predict-yes
  2676. ENV: Agent did: predict-yes for direction L in state State-A
  2677. In State-A moving L
  2678. ENV: (next state, see, prediction correct?) = (State-A, 0, False)
  2679. predict error 1
  2680. dir: dir isL
  2681. -/|374: O: O748 (predict-no)
  2682. I see 0 and I'm going to do: predict-no
  2683. ENV: Agent did: predict-no for direction L in state State-A
  2684. In State-A moving L
  2685. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  2686. predict error 0
  2687. dir: dir isL
  2688. \-/375: O: O750 (predict-no)
  2689. I see 1 and I'm going to do: predict-no
  2690. ENV: Agent did: predict-no for direction L in state State-A
  2691. In State-A moving L
  2692. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  2693. predict error 0
  2694. dir: dir isU
  2695. |\376: O: O752 (predict-no)
  2696. I see 1 and I'm going to do: predict-no
  2697. ENV: Agent did: predict-no for direction U in state State-A
  2698. In State-A moving U
  2699. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  2700. predict error 0
  2701. dir: dir isL
  2702. -/|377: O: O754 (predict-no)
  2703. I see 1 and I'm going to do: predict-no
  2704. ENV: Agent did: predict-no for direction L in state State-A
  2705. In State-A moving L
  2706. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  2707. predict error 0
  2708. dir: dir isL
  2709. \-378: O: O756 (predict-no)
  2710. I see 1 and I'm going to do: predict-no
  2711. ENV: Agent did: predict-no for direction L in state State-A
  2712. In State-A moving L
  2713. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  2714. predict error 0
  2715. dir: dir isL
  2716. /|\379: O: O758 (predict-no)
  2717. I see 1 and I'm going to do: predict-no
  2718. ENV: Agent did: predict-no for direction L in state State-A
  2719. In State-A moving L
  2720. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  2721. predict error 0
  2722. dir: dir isR
  2723. -/|380: O: O759 (predict-yes)
  2724. I see 1 and I'm going to do: predict-yes
  2725. ENV: Agent did: predict-yes for direction R in state State-A
  2726. In State-A moving R
  2727. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  2728. predict error 0
  2729. dir: dir isU
  2730. \-/381: O: O762 (predict-no)
  2731. I see 1 and I'm going to do: predict-no
  2732. ENV: Agent did: predict-no for direction U in state State-B
  2733. In State-B moving U
  2734. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2735. predict error 0
  2736. dir: dir isR
  2737. |382: O: O764 (predict-no)
  2738. I see 1 and I'm going to do: predict-no
  2739. ENV: Agent did: predict-no for direction R in state State-B
  2740. In State-B moving R
  2741. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2742. predict error 0
  2743. dir: dir isU
  2744. \-/383: O: O766 (predict-no)
  2745. I see 1 and I'm going to do: predict-no
  2746. ENV: Agent did: predict-no for direction U in state State-B
  2747. In State-B moving U
  2748. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2749. predict error 0
  2750. dir: dir isR
  2751. |\-384: O: O768 (predict-no)
  2752. I see 1 and I'm going to do: predict-no
  2753. ENV: Agent did: predict-no for direction R in state State-B
  2754. In State-B moving R
  2755. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2756. predict error 0
  2757. dir: dir isR
  2758. /|\385: O: O770 (predict-no)
  2759. I see 1 and I'm going to do: predict-no
  2760. ENV: Agent did: predict-no for direction R in state State-B
  2761. In State-B moving R
  2762. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2763. predict error 0
  2764. dir: dir isU
  2765. -/386: O: O772 (predict-no)
  2766. I see 1 and I'm going to do: predict-no
  2767. ENV: Agent did: predict-no for direction U in state State-B
  2768. In State-B moving U
  2769. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2770. predict error 0
  2771. dir: dir isU
  2772. |\-387: O: O774 (predict-no)
  2773. I see 1 and I'm going to do: predict-no
  2774. ENV: Agent did: predict-no for direction U in state State-B
  2775. In State-B moving U
  2776. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2777. predict error 0
  2778. dir: dir isU
  2779. /|\388: O: O776 (predict-no)
  2780. I see 1 and I'm going to do: predict-no
  2781. ENV: Agent did: predict-no for direction U in state State-B
  2782. In State-B moving U
  2783. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2784. predict error 0
  2785. dir: dir isU
  2786. -/389: O: O778 (predict-no)
  2787. I see 1 and I'm going to do: predict-no
  2788. ENV: Agent did: predict-no for direction U in state State-B
  2789. In State-B moving U
  2790. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2791. predict error 0
  2792. dir: dir isU
  2793. |\-/390: O: O780 (predict-no)
  2794. I see 1 and I'm going to do: predict-no
  2795. ENV: Agent did: predict-no for direction U in state State-B
  2796. In State-B moving U
  2797. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2798. predict error 0
  2799. dir: dir isU
  2800. |\-391: O: O782 (predict-no)
  2801. I see 1 and I'm going to do: predict-no
  2802. ENV: Agent did: predict-no for direction U in state State-B
  2803. In State-B moving U
  2804. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2805. predict error 0
  2806. dir: dir isL
  2807. /392: O: O783 (predict-yes)
  2808. I see 1 and I'm going to do: predict-yes
  2809. ENV: Agent did: predict-yes for direction L in state State-B
  2810. In State-B moving L
  2811. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  2812. predict error 0
  2813. dir: dir isR
  2814. |\-393: O: O785 (predict-yes)
  2815. I see 1 and I'm going to do: predict-yes
  2816. ENV: Agent did: predict-yes for direction R in state State-A
  2817. In State-A moving R
  2818. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  2819. predict error 0
  2820. dir: dir isR
  2821. /|\394: O: O788 (predict-no)
  2822. I see 1 and I'm going to do: predict-no
  2823. ENV: Agent did: predict-no for direction R in state State-B
  2824. In State-B moving R
  2825. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2826. predict error 0
  2827. dir: dir isU
  2828. -/|395: O: O790 (predict-no)
  2829. I see 1 and I'm going to do: predict-no
  2830. ENV: Agent did: predict-no for direction U in state State-B
  2831. In State-B moving U
  2832. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2833. predict error 0
  2834. dir: dir isR
  2835. \-/396: O: O792 (predict-no)
  2836. I see 1 and I'm going to do: predict-no
  2837. ENV: Agent did: predict-no for direction R in state State-B
  2838. In State-B moving R
  2839. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2840. predict error 0
  2841. dir: dir isU
  2842. |\-397: O: O794 (predict-no)
  2843. I see 1 and I'm going to do: predict-no
  2844. ENV: Agent did: predict-no for direction U in state State-B
  2845. In State-B moving U
  2846. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2847. predict error 0
  2848. dir: dir isR
  2849. /|398: O: O796 (predict-no)
  2850. I see 1 and I'm going to do: predict-no
  2851. ENV: Agent did: predict-no for direction R in state State-B
  2852. In State-B moving R
  2853. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2854. predict error 0
  2855. dir: dir isR
  2856. \-399: O: O798 (predict-no)
  2857. I see 1 and I'm going to do: predict-no
  2858. ENV: Agent did: predict-no for direction R in state State-B
  2859. In State-B moving R
  2860. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2861. predict error 0
  2862. dir: dir isU
  2863. /|400: O: O800 (predict-no)
  2864. I see 1 and I'm going to do: predict-no
  2865. ENV: Agent did: predict-no for direction U in state State-B
  2866. In State-B moving U
  2867. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2868. predict error 0
  2869. dir: dir isU
  2870. \-/401: O: O802 (predict-no)
  2871. I see 1 and I'm going to do: predict-no
  2872. ENV: Agent did: predict-no for direction U in state State-B
  2873. In State-B moving U
  2874. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2875. predict error 0
  2876. dir: dir isR
  2877. |402: O: O804 (predict-no)
  2878. I see 1 and I'm going to do: predict-no
  2879. ENV: Agent did: predict-no for direction R in state State-B
  2880. In State-B moving R
  2881. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2882. predict error 0
  2883. dir: dir isL
  2884. \-/403: O: O805 (predict-yes)
  2885. I see 1 and I'm going to do: predict-yes
  2886. ENV: Agent did: predict-yes for direction L in state State-B
  2887. In State-B moving L
  2888. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  2889. predict error 0
  2890. dir: dir isL
  2891. |\-404: O: O808 (predict-no)
  2892. I see 1 and I'm going to do: predict-no
  2893. ENV: Agent did: predict-no for direction L in state State-A
  2894. In State-A moving L
  2895. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  2896. predict error 0
  2897. dir: dir isR
  2898. /|405: O: O809 (predict-yes)
  2899. I see 1 and I'm going to do: predict-yes
  2900. ENV: Agent did: predict-yes for direction R in state State-A
  2901. In State-A moving R
  2902. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  2903. predict error 0
  2904. dir: dir isL
  2905. \-/406: O: O811 (predict-yes)
  2906. I see 1 and I'm going to do: predict-yes
  2907. ENV: Agent did: predict-yes for direction L in state State-B
  2908. In State-B moving L
  2909. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  2910. predict error 0
  2911. dir: dir isL
  2912. |\-407: O: O814 (predict-no)
  2913. I see 1 and I'm going to do: predict-no
  2914. ENV: Agent did: predict-no for direction L in state State-A
  2915. In State-A moving L
  2916. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  2917. predict error 0
  2918. dir: dir isU
  2919. /|\408: O: O816 (predict-no)
  2920. I see 1 and I'm going to do: predict-no
  2921. ENV: Agent did: predict-no for direction U in state State-A
  2922. In State-A moving U
  2923. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  2924. predict error 0
  2925. dir: dir isU
  2926. -/|409: O: O818 (predict-no)
  2927. I see 1 and I'm going to do: predict-no
  2928. ENV: Agent did: predict-no for direction U in state State-A
  2929. In State-A moving U
  2930. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  2931. predict error 0
  2932. dir: dir isL
  2933. \-/410: O: O820 (predict-no)
  2934. I see 1 and I'm going to do: predict-no
  2935. ENV: Agent did: predict-no for direction L in state State-A
  2936. In State-A moving L
  2937. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  2938. predict error 0
  2939. dir: dir isR
  2940. |\-411: O: O821 (predict-yes)
  2941. I see 1 and I'm going to do: predict-yes
  2942. ENV: Agent did: predict-yes for direction R in state State-A
  2943. In State-A moving R
  2944. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  2945. predict error 0
  2946. dir: dir isU
  2947. /412: O: O824 (predict-no)
  2948. I see 1 and I'm going to do: predict-no
  2949. ENV: Agent did: predict-no for direction U in state State-B
  2950. In State-B moving U
  2951. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2952. predict error 0
  2953. dir: dir isL
  2954. |\-413: O: O825 (predict-yes)
  2955. I see 1 and I'm going to do: predict-yes
  2956. ENV: Agent did: predict-yes for direction L in state State-B
  2957. In State-B moving L
  2958. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  2959. predict error 0
  2960. dir: dir isR
  2961. /|\414: O: O827 (predict-yes)
  2962. I see 1 and I'm going to do: predict-yes
  2963. ENV: Agent did: predict-yes for direction R in state State-A
  2964. In State-A moving R
  2965. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  2966. predict error 0
  2967. dir: dir isL
  2968. -/|415: O: O829 (predict-yes)
  2969. I see 1 and I'm going to do: predict-yes
  2970. ENV: Agent did: predict-yes for direction L in state State-B
  2971. In State-B moving L
  2972. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  2973. predict error 0
  2974. dir: dir isL
  2975. \-416: O: O832 (predict-no)
  2976. I see 1 and I'm going to do: predict-no
  2977. ENV: Agent did: predict-no for direction L in state State-A
  2978. In State-A moving L
  2979. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  2980. predict error 0
  2981. dir: dir isU
  2982. /|417: O: O834 (predict-no)
  2983. I see 1 and I'm going to do: predict-no
  2984. ENV: Agent did: predict-no for direction U in state State-A
  2985. In State-A moving U
  2986. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  2987. predict error 0
  2988. dir: dir isL
  2989. \-418: O: O836 (predict-no)
  2990. I see 1 and I'm going to do: predict-no
  2991. ENV: Agent did: predict-no for direction L in state State-A
  2992. In State-A moving L
  2993. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  2994. predict error 0
  2995. dir: dir isL
  2996. /|\419: O: O838 (predict-no)
  2997. I see 1 and I'm going to do: predict-no
  2998. ENV: Agent did: predict-no for direction L in state State-A
  2999. In State-A moving L
  3000. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3001. predict error 0
  3002. dir: dir isR
  3003. -/|420: O: O839 (predict-yes)
  3004. I see 1 and I'm going to do: predict-yes
  3005. ENV: Agent did: predict-yes for direction R in state State-A
  3006. In State-A moving R
  3007. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  3008. predict error 0
  3009. dir: dir isR
  3010. \-/421: O: O842 (predict-no)
  3011. I see 1 and I'm going to do: predict-no
  3012. ENV: Agent did: predict-no for direction R in state State-B
  3013. In State-B moving R
  3014. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3015. predict error 0
  3016. dir: dir isU
  3017. |422: O: O844 (predict-no)
  3018. I see 1 and I'm going to do: predict-no
  3019. ENV: Agent did: predict-no for direction U in state State-B
  3020. In State-B moving U
  3021. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3022. predict error 0
  3023. dir: dir isU
  3024. \-/423: O: O846 (predict-no)
  3025. I see 1 and I'm going to do: predict-no
  3026. ENV: Agent did: predict-no for direction U in state State-B
  3027. In State-B moving U
  3028. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3029. predict error 0
  3030. dir: dir isU
  3031. |\-424: O: O848 (predict-no)
  3032. I see 1 and I'm going to do: predict-no
  3033. ENV: Agent did: predict-no for direction U in state State-B
  3034. In State-B moving U
  3035. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3036. predict error 0
  3037. dir: dir isL
  3038. /|\425: O: O849 (predict-yes)
  3039. I see 1 and I'm going to do: predict-yes
  3040. ENV: Agent did: predict-yes for direction L in state State-B
  3041. In State-B moving L
  3042. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  3043. predict error 0
  3044. dir: dir isU
  3045. -/|426: O: O852 (predict-no)
  3046. I see 1 and I'm going to do: predict-no
  3047. ENV: Agent did: predict-no for direction U in state State-A
  3048. In State-A moving U
  3049. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3050. predict error 0
  3051. dir: dir isR
  3052. \-427: O: O853 (predict-yes)
  3053. I see 1 and I'm going to do: predict-yes
  3054. ENV: Agent did: predict-yes for direction R in state State-A
  3055. In State-A moving R
  3056. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  3057. predict error 0
  3058. dir: dir isR
  3059. /|\428: O: O856 (predict-no)
  3060. I see 1 and I'm going to do: predict-no
  3061. ENV: Agent did: predict-no for direction R in state State-B
  3062. In State-B moving R
  3063. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3064. predict error 0
  3065. dir: dir isR
  3066. -/|429: O: O858 (predict-no)
  3067. I see 1 and I'm going to do: predict-no
  3068. ENV: Agent did: predict-no for direction R in state State-B
  3069. In State-B moving R
  3070. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3071. predict error 0
  3072. dir: dir isL
  3073. \-430: O: O859 (predict-yes)
  3074. I see 1 and I'm going to do: predict-yes
  3075. ENV: Agent did: predict-yes for direction L in state State-B
  3076. In State-B moving L
  3077. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  3078. predict error 0
  3079. dir: dir isR
  3080. /|431: O: O861 (predict-yes)
  3081. I see 1 and I'm going to do: predict-yes
  3082. ENV: Agent did: predict-yes for direction R in state State-A
  3083. In State-A moving R
  3084. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  3085. predict error 0
  3086. dir: dir isL
  3087. \432: O: O863 (predict-yes)
  3088. I see 1 and I'm going to do: predict-yes
  3089. ENV: Agent did: predict-yes for direction L in state State-B
  3090. In State-B moving L
  3091. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  3092. predict error 0
  3093. dir: dir isL
  3094. -/|433: O: O866 (predict-no)
  3095. I see 1 and I'm going to do: predict-no
  3096. ENV: Agent did: predict-no for direction L in state State-A
  3097. In State-A moving L
  3098. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3099. predict error 0
  3100. dir: dir isR
  3101. \-/434: O: O867 (predict-yes)
  3102. I see 1 and I'm going to do: predict-yes
  3103. ENV: Agent did: predict-yes for direction R in state State-A
  3104. In State-A moving R
  3105. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  3106. predict error 0
  3107. dir: dir isR
  3108. |\-435: O: O870 (predict-no)
  3109. I see 1 and I'm going to do: predict-no
  3110. ENV: Agent did: predict-no for direction R in state State-B
  3111. In State-B moving R
  3112. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3113. predict error 0
  3114. dir: dir isL
  3115. /|\436: O: O871 (predict-yes)
  3116. I see 1 and I'm going to do: predict-yes
  3117. ENV: Agent did: predict-yes for direction L in state State-B
  3118. In State-B moving L
  3119. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  3120. predict error 0
  3121. dir: dir isR
  3122. -/|437: O: O873 (predict-yes)
  3123. I see 1 and I'm going to do: predict-yes
  3124. ENV: Agent did: predict-yes for direction R in state State-A
  3125. In State-A moving R
  3126. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  3127. predict error 0
  3128. dir: dir isR
  3129. \-438: O: O876 (predict-no)
  3130. I see 1 and I'm going to do: predict-no
  3131. ENV: Agent did: predict-no for direction R in state State-B
  3132. In State-B moving R
  3133. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3134. predict error 0
  3135. dir: dir isR
  3136. /|\439: O: O878 (predict-no)
  3137. I see 1 and I'm going to do: predict-no
  3138. ENV: Agent did: predict-no for direction R in state State-B
  3139. In State-B moving R
  3140. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3141. predict error 0
  3142. dir: dir isU
  3143. -/|440: O: O880 (predict-no)
  3144. I see 1 and I'm going to do: predict-no
  3145. ENV: Agent did: predict-no for direction U in state State-B
  3146. In State-B moving U
  3147. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3148. predict error 0
  3149. dir: dir isR
  3150. \-/441: O: O882 (predict-no)
  3151. I see 1 and I'm going to do: predict-no
  3152. ENV: Agent did: predict-no for direction R in state State-B
  3153. In State-B moving R
  3154. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3155. predict error 0
  3156. dir: dir isU
  3157. |442: O: O884 (predict-no)
  3158. I see 1 and I'm going to do: predict-no
  3159. ENV: Agent did: predict-no for direction U in state State-B
  3160. In State-B moving U
  3161. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3162. predict error 0
  3163. dir: dir isR
  3164. \-/443: O: O886 (predict-no)
  3165. I see 1 and I'm going to do: predict-no
  3166. ENV: Agent did: predict-no for direction R in state State-B
  3167. In State-B moving R
  3168. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3169. predict error 0
  3170. dir: dir isR
  3171. |444: O: O888 (predict-no)
  3172. I see 1 and I'm going to do: predict-no
  3173. ENV: Agent did: predict-no for direction R in state State-B
  3174. In State-B moving R
  3175. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3176. predict error 0
  3177. dir: dir isR
  3178. \-/445: O: O890 (predict-no)
  3179. I see 1 and I'm going to do: predict-no
  3180. ENV: Agent did: predict-no for direction R in state State-B
  3181. In State-B moving R
  3182. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3183. predict error 0
  3184. dir: dir isR
  3185. |\-446: O: O892 (predict-no)
  3186. I see 1 and I'm going to do: predict-no
  3187. ENV: Agent did: predict-no for direction R in state State-B
  3188. In State-B moving R
  3189. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3190. predict error 0
  3191. dir: dir isL
  3192. /|447: O: O893 (predict-yes)
  3193. I see 1 and I'm going to do: predict-yes
  3194. ENV: Agent did: predict-yes for direction L in state State-B
  3195. In State-B moving L
  3196. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  3197. predict error 0
  3198. dir: dir isU
  3199. \-/448: O: O896 (predict-no)
  3200. I see 1 and I'm going to do: predict-no
  3201. ENV: Agent did: predict-no for direction U in state State-A
  3202. In State-A moving U
  3203. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3204. predict error 0
  3205. dir: dir isR
  3206. |\-449: O: O897 (predict-yes)
  3207. I see 1 and I'm going to do: predict-yes
  3208. ENV: Agent did: predict-yes for direction R in state State-A
  3209. In State-A moving R
  3210. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  3211. predict error 0
  3212. dir: dir isU
  3213. /|\450: O: O900 (predict-no)
  3214. I see 1 and I'm going to do: predict-no
  3215. ENV: Agent did: predict-no for direction U in state State-B
  3216. In State-B moving U
  3217. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3218. predict error 0
  3219. dir: dir isL
  3220. -/|451: O: O901 (predict-yes)
  3221. I see 1 and I'm going to do: predict-yes
  3222. ENV: Agent did: predict-yes for direction L in state State-B
  3223. In State-B moving L
  3224. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  3225. predict error 0
  3226. dir: dir isU
  3227. \452: O: O904 (predict-no)
  3228. I see 1 and I'm going to do: predict-no
  3229. ENV: Agent did: predict-no for direction U in state State-A
  3230. In State-A moving U
  3231. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3232. predict error 0
  3233. dir: dir isU
  3234. -/|453: O: O906 (predict-no)
  3235. I see 1 and I'm going to do: predict-no
  3236. ENV: Agent did: predict-no for direction U in state State-A
  3237. In State-A moving U
  3238. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3239. predict error 0
  3240. dir: dir isU
  3241. \-/|454: O: O908 (predict-no)
  3242. I see 1 and I'm going to do: predict-no
  3243. ENV: Agent did: predict-no for direction U in state State-A
  3244. In State-A moving U
  3245. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3246. predict error 0
  3247. dir: dir isU
  3248. \-455: O: O910 (predict-no)
  3249. I see 1 and I'm going to do: predict-no
  3250. ENV: Agent did: predict-no for direction U in state State-A
  3251. In State-A moving U
  3252. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3253. predict error 0
  3254. dir: dir isU
  3255. /|\456: O: O912 (predict-no)
  3256. I see 1 and I'm going to do: predict-no
  3257. ENV: Agent did: predict-no for direction U in state State-A
  3258. In State-A moving U
  3259. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3260. predict error 0
  3261. dir: dir isU
  3262. -/|457: O: O914 (predict-no)
  3263. I see 1 and I'm going to do: predict-no
  3264. ENV: Agent did: predict-no for direction U in state State-A
  3265. In State-A moving U
  3266. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3267. predict error 0
  3268. dir: dir isR
  3269. \-458: O: O915 (predict-yes)
  3270. I see 1 and I'm going to do: predict-yes
  3271. ENV: Agent did: predict-yes for direction R in state State-A
  3272. In State-A moving R
  3273. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  3274. predict error 0
  3275. dir: dir isU
  3276. /|\459: O: O918 (predict-no)
  3277. I see 1 and I'm going to do: predict-no
  3278. ENV: Agent did: predict-no for direction U in state State-B
  3279. In State-B moving U
  3280. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3281. predict error 0
  3282. dir: dir isL
  3283. -/|460: O: O919 (predict-yes)
  3284. I see 1 and I'm going to do: predict-yes
  3285. ENV: Agent did: predict-yes for direction L in state State-B
  3286. In State-B moving L
  3287. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  3288. predict error 0
  3289. dir: dir isU
  3290. \-/461: O: O922 (predict-no)
  3291. I see 1 and I'm going to do: predict-no
  3292. ENV: Agent did: predict-no for direction U in state State-A
  3293. In State-A moving U
  3294. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3295. predict error 0
  3296. dir: dir isR
  3297. |462: O: O923 (predict-yes)
  3298. I see 1 and I'm going to do: predict-yes
  3299. ENV: Agent did: predict-yes for direction R in state State-A
  3300. In State-A moving R
  3301. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  3302. predict error 0
  3303. dir: dir isU
  3304. \-/463: O: O926 (predict-no)
  3305. I see 1 and I'm going to do: predict-no
  3306. ENV: Agent did: predict-no for direction U in state State-B
  3307. In State-B moving U
  3308. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3309. predict error 0
  3310. dir: dir isR
  3311. |\464: O: O928 (predict-no)
  3312. I see 1 and I'm going to do: predict-no
  3313. ENV: Agent did: predict-no for direction R in state State-B
  3314. In State-B moving R
  3315. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3316. predict error 0
  3317. dir: dir isU
  3318. -/|465: O: O930 (predict-no)
  3319. I see 1 and I'm going to do: predict-no
  3320. ENV: Agent did: predict-no for direction U in state State-B
  3321. In State-B moving U
  3322. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3323. predict error 0
  3324. dir: dir isL
  3325. \-/466: O: O931 (predict-yes)
  3326. I see 1 and I'm going to do: predict-yes
  3327. ENV: Agent did: predict-yes for direction L in state State-B
  3328. In State-B moving L
  3329. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  3330. predict error 0
  3331. dir: dir isL
  3332. |\467: O: O934 (predict-no)
  3333. I see 1 and I'm going to do: predict-no
  3334. ENV: Agent did: predict-no for direction L in state State-A
  3335. In State-A moving L
  3336. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3337. predict error 0
  3338. dir: dir isU
  3339. -/|468: O: O936 (predict-no)
  3340. I see 1 and I'm going to do: predict-no
  3341. ENV: Agent did: predict-no for direction U in state State-A
  3342. In State-A moving U
  3343. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3344. predict error 0
  3345. dir: dir isR
  3346. \-/469: O: O937 (predict-yes)
  3347. I see 1 and I'm going to do: predict-yes
  3348. ENV: Agent did: predict-yes for direction R in state State-A
  3349. In State-A moving R
  3350. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  3351. predict error 0
  3352. dir: dir isU
  3353. |\-470: O: O940 (predict-no)
  3354. I see 1 and I'm going to do: predict-no
  3355. ENV: Agent did: predict-no for direction U in state State-B
  3356. In State-B moving U
  3357. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3358. predict error 0
  3359. dir: dir isU
  3360. /|\471: O: O942 (predict-no)
  3361. I see 1 and I'm going to do: predict-no
  3362. ENV: Agent did: predict-no for direction U in state State-B
  3363. In State-B moving U
  3364. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3365. predict error 0
  3366. dir: dir isR
  3367. -472: O: O944 (predict-no)
  3368. I see 1 and I'm going to do: predict-no
  3369. ENV: Agent did: predict-no for direction R in state State-B
  3370. In State-B moving R
  3371. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3372. predict error 0
  3373. dir: dir isR
  3374. /|\473: O: O946 (predict-no)
  3375. I see 1 and I'm going to do: predict-no
  3376. ENV: Agent did: predict-no for direction R in state State-B
  3377. In State-B moving R
  3378. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3379. predict error 0
  3380. dir: dir isL
  3381. -/|\474: O: O947 (predict-yes)
  3382. I see 1 and I'm going to do: predict-yes
  3383. ENV: Agent did: predict-yes for direction L in state State-B
  3384. In State-B moving L
  3385. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  3386. predict error 0
  3387. dir: dir isL
  3388. -/|475: O: O950 (predict-no)
  3389. I see 1 and I'm going to do: predict-no
  3390. ENV: Agent did: predict-no for direction L in state State-A
  3391. In State-A moving L
  3392. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3393. predict error 0
  3394. dir: dir isU
  3395. \-476: O: O952 (predict-no)
  3396. I see 1 and I'm going to do: predict-no
  3397. ENV: Agent did: predict-no for direction U in state State-A
  3398. In State-A moving U
  3399. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3400. predict error 0
  3401. dir: dir isU
  3402. /|\477: O: O954 (predict-no)
  3403. I see 1 and I'm going to do: predict-no
  3404. ENV: Agent did: predict-no for direction U in state State-A
  3405. In State-A moving U
  3406. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3407. predict error 0
  3408. dir: dir isU
  3409. -/|478: O: O956 (predict-no)
  3410. I see 1 and I'm going to do: predict-no
  3411. ENV: Agent did: predict-no for direction U in state State-A
  3412. In State-A moving U
  3413. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3414. predict error 0
  3415. dir: dir isU
  3416. \-479: O: O958 (predict-no)
  3417. I see 1 and I'm going to do: predict-no
  3418. ENV: Agent did: predict-no for direction U in state State-A
  3419. In State-A moving U
  3420. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3421. predict error 0
  3422. dir: dir isR
  3423. /|\480: O: O959 (predict-yes)
  3424. I see 1 and I'm going to do: predict-yes
  3425. ENV: Agent did: predict-yes for direction R in state State-A
  3426. In State-A moving R
  3427. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  3428. predict error 0
  3429. dir: dir isL
  3430. -/|481: O: O961 (predict-yes)
  3431. I see 1 and I'm going to do: predict-yes
  3432. ENV: Agent did: predict-yes for direction L in state State-B
  3433. In State-B moving L
  3434. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  3435. predict error 0
  3436. dir: dir isL
  3437. \482: O: O964 (predict-no)
  3438. I see 1 and I'm going to do: predict-no
  3439. ENV: Agent did: predict-no for direction L in state State-A
  3440. In State-A moving L
  3441. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3442. predict error 0
  3443. dir: dir isR
  3444. -/|\483: O: O965 (predict-yes)
  3445. I see 1 and I'm going to do: predict-yes
  3446. ENV: Agent did: predict-yes for direction R in state State-A
  3447. In State-A moving R
  3448. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  3449. predict error 0
  3450. dir: dir isR
  3451. -484: O: O968 (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. /|\485: O: O970 (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 isU
  3465. -/|486: O: O972 (predict-no)
  3466. I see 1 and I'm going to do: predict-no
  3467. ENV: Agent did: predict-no for direction U in state State-B
  3468. In State-B moving U
  3469. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3470. predict error 0
  3471. dir: dir isR
  3472. \-487: O: O974 (predict-no)
  3473. I see 1 and I'm going to do: predict-no
  3474. ENV: Agent did: predict-no for direction R in state State-B
  3475. In State-B moving R
  3476. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3477. predict error 0
  3478. dir: dir isL
  3479. /|\488: O: O975 (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 isU
  3486. -/489: O: O978 (predict-no)
  3487. I see 1 and I'm going to do: predict-no
  3488. ENV: Agent did: predict-no for direction U in state State-A
  3489. In State-A moving U
  3490. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3491. predict error 0
  3492. dir: dir isU
  3493. |\-/490: O: O980 (predict-no)
  3494. I see 1 and I'm going to do: predict-no
  3495. ENV: Agent did: predict-no for direction U in state State-A
  3496. In State-A moving U
  3497. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3498. predict error 0
  3499. dir: dir isL
  3500. |\-491: O: O982 (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 isR
  3507. /492: O: O983 (predict-yes)
  3508. I see 1 and I'm going to do: predict-yes
  3509. ENV: Agent did: predict-yes for direction R in state State-A
  3510. In State-A moving R
  3511. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  3512. predict error 0
  3513. dir: dir isU
  3514. |\-493: O: O986 (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-B
  3517. In State-B moving U
  3518. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3519. predict error 0
  3520. dir: dir isL
  3521. /|\494: O: O987 (predict-yes)
  3522. I see 1 and I'm going to do: predict-yes
  3523. ENV: Agent did: predict-yes for direction L in state State-B
  3524. In State-B moving L
  3525. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  3526. predict error 0
  3527. dir: dir isU
  3528. -/|495: O: O990 (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 isU
  3535. \-/496: O: O992 (predict-no)
  3536. I see 1 and I'm going to do: predict-no
  3537. ENV: Agent did: predict-no for direction U in state State-A
  3538. In State-A moving U
  3539. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3540. predict error 0
  3541. dir: dir isU
  3542. |\497: O: O994 (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. -/|498: O: O996 (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. \-/499: O: O998 (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 isR
  3563. |\-500: O: O999 (predict-yes)
  3564. I see 1 and I'm going to do: predict-yes
  3565. ENV: Agent did: predict-yes for direction R in state State-A
  3566. In State-A moving R
  3567. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  3568. predict error 0
  3569. dir: dir isL
  3570. /|\-/|501: O: O1001 (predict-yes)
  3571. I see 1 and I'm going to do: predict-yes
  3572. ENV: Agent did: predict-yes for direction L in state State-B
  3573. In State-B moving L
  3574. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  3575. predict error 0
  3576. dir: dir isR
  3577. \502: O: O1003 (predict-yes)
  3578. I see 1 and I'm going to do: predict-yes
  3579. ENV: Agent did: predict-yes for direction R in state State-A
  3580. In State-A moving R
  3581. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  3582. predict error 0
  3583. dir: dir isL
  3584. -/|503: O: O1005 (predict-yes)
  3585. I see 1 and I'm going to do: predict-yes
  3586. ENV: Agent did: predict-yes for direction L in state State-B
  3587. In State-B moving L
  3588. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  3589. predict error 0
  3590. dir: dir isU
  3591. \-/|504: O: O1008 (predict-no)
  3592. I see 1 and I'm going to do: predict-no
  3593. ENV: Agent did: predict-no for direction U in state State-A
  3594. In State-A moving U
  3595. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3596. predict error 0
  3597. dir: dir isU
  3598. \-/505: O: O1010 (predict-no)
  3599. I see 1 and I'm going to do: predict-no
  3600. ENV: Agent did: predict-no for direction U in state State-A
  3601. In State-A moving U
  3602. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3603. predict error 0
  3604. dir: dir isL
  3605. |\-506: O: O1012 (predict-no)
  3606. I see 1 and I'm going to do: predict-no
  3607. ENV: Agent did: predict-no for direction L in state State-A
  3608. In State-A moving L
  3609. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3610. predict error 0
  3611. dir: dir isU
  3612. /|507: O: O1014 (predict-no)
  3613. I see 1 and I'm going to do: predict-no
  3614. ENV: Agent did: predict-no for direction U in state State-A
  3615. In State-A moving U
  3616. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3617. predict error 0
  3618. dir: dir isL
  3619. \-/|508: O: O1016 (predict-no)
  3620. I see 1 and I'm going to do: predict-no
  3621. ENV: Agent did: predict-no for direction L in state State-A
  3622. In State-A moving L
  3623. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3624. predict error 0
  3625. dir: dir isL
  3626. \-/509: O: O1018 (predict-no)
  3627. I see 1 and I'm going to do: predict-no
  3628. ENV: Agent did: predict-no for direction L in state State-A
  3629. In State-A moving L
  3630. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3631. predict error 0
  3632. dir: dir isU
  3633. |\-510: O: O1020 (predict-no)
  3634. I see 1 and I'm going to do: predict-no
  3635. ENV: Agent did: predict-no for direction U in state State-A
  3636. In State-A moving U
  3637. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3638. predict error 0
  3639. dir: dir isU
  3640. /|\511: O: O1022 (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. -512: O: O1024 (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 isL
  3654. /|\513: O: O1026 (predict-no)
  3655. I see 1 and I'm going to do: predict-no
  3656. ENV: Agent did: predict-no for direction L in state State-A
  3657. In State-A moving L
  3658. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3659. predict error 0
  3660. dir: dir isR
  3661. -/|514: O: O1027 (predict-yes)
  3662. I see 1 and I'm going to do: predict-yes
  3663. ENV: Agent did: predict-yes for direction R in state State-A
  3664. In State-A moving R
  3665. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  3666. predict error 0
  3667. dir: dir isL
  3668. \-/515: O: O1029 (predict-yes)
  3669. I see 1 and I'm going to do: predict-yes
  3670. ENV: Agent did: predict-yes for direction L in state State-B
  3671. In State-B moving L
  3672. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  3673. predict error 0
  3674. dir: dir isR
  3675. |\-516: O: O1031 (predict-yes)
  3676. I see 1 and I'm going to do: predict-yes
  3677. ENV: Agent did: predict-yes for direction R in state State-A
  3678. In State-A moving R
  3679. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  3680. predict error 0
  3681. dir: dir isU
  3682. /|517: O: O1034 (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. \-/518: O: O1035 (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 isL
  3696. |\-519: O: O1038 (predict-no)
  3697. I see 1 and I'm going to do: predict-no
  3698. ENV: Agent did: predict-no for direction L in state State-A
  3699. In State-A moving L
  3700. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3701. predict error 0
  3702. dir: dir isR
  3703. /|520: O: O1039 (predict-yes)
  3704. I see 1 and I'm going to do: predict-yes
  3705. ENV: Agent did: predict-yes for direction R in state State-A
  3706. In State-A moving R
  3707. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  3708. predict error 0
  3709. dir: dir isU
  3710. \-/521: O: O1042 (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-B
  3713. In State-B moving U
  3714. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3715. predict error 0
  3716. dir: dir isL
  3717. |522: O: O1043 (predict-yes)
  3718. I see 1 and I'm going to do: predict-yes
  3719. ENV: Agent did: predict-yes for direction L in state State-B
  3720. In State-B moving L
  3721. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  3722. predict error 0
  3723. dir: dir isU
  3724. \-/523: O: O1046 (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 isR
  3731. |\-524: O: O1047 (predict-yes)
  3732. I see 1 and I'm going to do: predict-yes
  3733. ENV: Agent did: predict-yes for direction R in state State-A
  3734. In State-A moving R
  3735. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  3736. predict error 0
  3737. dir: dir isR
  3738. /|\525: O: O1050 (predict-no)
  3739. I see 1 and I'm going to do: predict-no
  3740. ENV: Agent did: predict-no for direction R in state State-B
  3741. In State-B moving R
  3742. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3743. predict error 0
  3744. dir: dir isL
  3745. -/526: O: O1051 (predict-yes)
  3746. I see 1 and I'm going to do: predict-yes
  3747. ENV: Agent did: predict-yes for direction L in state State-B
  3748. In State-B moving L
  3749. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  3750. predict error 0
  3751. dir: dir isU
  3752. |\-527: O: O1054 (predict-no)
  3753. I see 1 and I'm going to do: predict-no
  3754. ENV: Agent did: predict-no for direction U in state State-A
  3755. In State-A moving U
  3756. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3757. predict error 0
  3758. dir: dir isU
  3759. /|\528: O: O1056 (predict-no)
  3760. I see 1 and I'm going to do: predict-no
  3761. ENV: Agent did: predict-no for direction U in state State-A
  3762. In State-A moving U
  3763. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3764. predict error 0
  3765. dir: dir isR
  3766. -/|\529: O: O1057 (predict-yes)
  3767. I see 1 and I'm going to do: predict-yes
  3768. ENV: Agent did: predict-yes for direction R in state State-A
  3769. In State-A moving R
  3770. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  3771. predict error 0
  3772. dir: dir isL
  3773. -/|530: O: O1059 (predict-yes)
  3774. I see 1 and I'm going to do: predict-yes
  3775. ENV: Agent did: predict-yes for direction L in state State-B
  3776. In State-B moving L
  3777. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  3778. predict error 0
  3779. dir: dir isU
  3780. \-531: O: O1062 (predict-no)
  3781. I see 1 and I'm going to do: predict-no
  3782. ENV: Agent did: predict-no for direction U in state State-A
  3783. In State-A moving U
  3784. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3785. predict error 0
  3786. dir: dir isL
  3787. /532: O: O1064 (predict-no)
  3788. I see 1 and I'm going to do: predict-no
  3789. ENV: Agent did: predict-no for direction L in state State-A
  3790. In State-A moving L
  3791. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3792. predict error 0
  3793. dir: dir isR
  3794. |\533: O: O1065 (predict-yes)
  3795. I see 1 and I'm going to do: predict-yes
  3796. ENV: Agent did: predict-yes for direction R in state State-A
  3797. In State-A moving R
  3798. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  3799. predict error 0
  3800. dir: dir isL
  3801. -/|534: O: O1067 (predict-yes)
  3802. I see 1 and I'm going to do: predict-yes
  3803. ENV: Agent did: predict-yes for direction L in state State-B
  3804. In State-B moving L
  3805. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  3806. predict error 0
  3807. dir: dir isU
  3808. \535: O: O1070 (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. -/536: O: O1072 (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. |\-537: O: O1074 (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 isL
  3829. /538: O: O1076 (predict-no)
  3830. I see 1 and I'm going to do: predict-no
  3831. ENV: Agent did: predict-no for direction L in state State-A
  3832. In State-A moving L
  3833. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3834. predict error 0
  3835. dir: dir isL
  3836. |\-539: O: O1078 (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. /|\540: O: O1080 (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 isL
  3850. -/|541: O: O1082 (predict-no)
  3851. I see 1 and I'm going to do: predict-no
  3852. ENV: Agent did: predict-no for direction L in state State-A
  3853. In State-A moving L
  3854. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3855. predict error 0
  3856. dir: dir isR
  3857. \542: O: O1083 (predict-yes)
  3858. I see 1 and I'm going to do: predict-yes
  3859. ENV: Agent did: predict-yes for direction R in state State-A
  3860. In State-A moving R
  3861. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  3862. predict error 0
  3863. dir: dir isL
  3864. -543: O: O1085 (predict-yes)
  3865. I see 1 and I'm going to do: predict-yes
  3866. ENV: Agent did: predict-yes for direction L in state State-B
  3867. In State-B moving L
  3868. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  3869. predict error 0
  3870. dir: dir isL
  3871. /|\544: O: O1088 (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. -/545: O: O1090 (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. |\546: O: O1092 (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 isL
  3892. -/|547: O: O1094 (predict-no)
  3893. I see 1 and I'm going to do: predict-no
  3894. ENV: Agent did: predict-no for direction L in state State-A
  3895. In State-A moving L
  3896. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3897. predict error 0
  3898. dir: dir isR
  3899. \-548: O: O1095 (predict-yes)
  3900. I see 1 and I'm going to do: predict-yes
  3901. ENV: Agent did: predict-yes for direction R in state State-A
  3902. In State-A moving R
  3903. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  3904. predict error 0
  3905. dir: dir isR
  3906. /|\549: O: O1098 (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 isU
  3913. -/|\sleeping...
  3914. -550: O: O1100 (predict-no)
  3915. I see 1 and I'm going to do: predict-no
  3916. ENV: Agent did: predict-no for direction U in state State-B
  3917. In State-B moving U
  3918. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3919. predict error 0
  3920. dir: dir isL
  3921. /|\551: O: O1101 (predict-yes)
  3922. I see 1 and I'm going to do: predict-yes
  3923. ENV: Agent did: predict-yes for direction L in state State-B
  3924. In State-B moving L
  3925. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  3926. predict error 0
  3927. dir: dir isR
  3928. -552: O: O1103 (predict-yes)
  3929. I see 1 and I'm going to do: predict-yes
  3930. ENV: Agent did: predict-yes for direction R in state State-A
  3931. In State-A moving R
  3932. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  3933. predict error 0
  3934. dir: dir isR
  3935. /|\553: O: O1106 (predict-no)
  3936. I see 1 and I'm going to do: predict-no
  3937. ENV: Agent did: predict-no for direction R in state State-B
  3938. In State-B moving R
  3939. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3940. predict error 0
  3941. dir: dir isL
  3942. -/|554: O: O1107 (predict-yes)
  3943. I see 1 and I'm going to do: predict-yes
  3944. ENV: Agent did: predict-yes for direction L in state State-B
  3945. In State-B moving L
  3946. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  3947. predict error 0
  3948. dir: dir isR
  3949. \-/555: O: O1109 (predict-yes)
  3950. I see 1 and I'm going to do: predict-yes
  3951. ENV: Agent did: predict-yes for direction R in state State-A
  3952. In State-A moving R
  3953. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  3954. predict error 0
  3955. dir: dir isR
  3956. |\556: O: O1112 (predict-no)
  3957. I see 1 and I'm going to do: predict-no
  3958. ENV: Agent did: predict-no for direction R in state State-B
  3959. In State-B moving R
  3960. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3961. predict error 0
  3962. dir: dir isU
  3963. -/|557: O: O1114 (predict-no)
  3964. I see 1 and I'm going to do: predict-no
  3965. ENV: Agent did: predict-no for direction U in state State-B
  3966. In State-B moving U
  3967. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3968. predict error 0
  3969. dir: dir isL
  3970. \-/558: O: O1115 (predict-yes)
  3971. I see 1 and I'm going to do: predict-yes
  3972. ENV: Agent did: predict-yes for direction L in state State-B
  3973. In State-B moving L
  3974. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  3975. predict error 0
  3976. dir: dir isR
  3977. |\-559: O: O1117 (predict-yes)
  3978. I see 1 and I'm going to do: predict-yes
  3979. ENV: Agent did: predict-yes for direction R in state State-A
  3980. In State-A moving R
  3981. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  3982. predict error 0
  3983. dir: dir isR
  3984. /|\560: O: O1120 (predict-no)
  3985. I see 1 and I'm going to do: predict-no
  3986. ENV: Agent did: predict-no for direction R in state State-B
  3987. In State-B moving R
  3988. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3989. predict error 0
  3990. dir: dir isU
  3991. -/|561: O: O1122 (predict-no)
  3992. I see 1 and I'm going to do: predict-no
  3993. ENV: Agent did: predict-no for direction U in state State-B
  3994. In State-B moving U
  3995. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3996. predict error 0
  3997. dir: dir isL
  3998. \562: O: O1123 (predict-yes)
  3999. I see 1 and I'm going to do: predict-yes
  4000. ENV: Agent did: predict-yes for direction L in state State-B
  4001. In State-B moving L
  4002. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  4003. predict error 0
  4004. dir: dir isL
  4005. -/|563: O: O1126 (predict-no)
  4006. I see 1 and I'm going to do: predict-no
  4007. ENV: Agent did: predict-no for direction L in state State-A
  4008. In State-A moving L
  4009. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4010. predict error 0
  4011. dir: dir isL
  4012. \-564: O: O1128 (predict-no)
  4013. I see 1 and I'm going to do: predict-no
  4014. ENV: Agent did: predict-no for direction L in state State-A
  4015. In State-A moving L
  4016. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4017. predict error 0
  4018. dir: dir isR
  4019. /|\565: O: O1129 (predict-yes)
  4020. I see 1 and I'm going to do: predict-yes
  4021. ENV: Agent did: predict-yes for direction R in state State-A
  4022. In State-A moving R
  4023. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  4024. predict error 0
  4025. dir: dir isU
  4026. -/|566: O: O1132 (predict-no)
  4027. I see 1 and I'm going to do: predict-no
  4028. ENV: Agent did: predict-no for direction U in state State-B
  4029. In State-B moving U
  4030. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4031. predict error 0
  4032. dir: dir isU
  4033. \-/567: O: O1134 (predict-no)
  4034. I see 1 and I'm going to do: predict-no
  4035. ENV: Agent did: predict-no for direction U in state State-B
  4036. In State-B moving U
  4037. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4038. predict error 0
  4039. dir: dir isL
  4040. |\568: O: O1135 (predict-yes)
  4041. I see 1 and I'm going to do: predict-yes
  4042. ENV: Agent did: predict-yes for direction L in state State-B
  4043. In State-B moving L
  4044. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  4045. predict error 0
  4046. dir: dir isR
  4047. -/|569: O: O1137 (predict-yes)
  4048. I see 1 and I'm going to do: predict-yes
  4049. ENV: Agent did: predict-yes for direction R in state State-A
  4050. In State-A moving R
  4051. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  4052. predict error 0
  4053. dir: dir isU
  4054. \-/570: O: O1140 (predict-no)
  4055. I see 1 and I'm going to do: predict-no
  4056. ENV: Agent did: predict-no for direction U in state State-B
  4057. In State-B moving U
  4058. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4059. predict error 0
  4060. dir: dir isU
  4061. |\-571: O: O1142 (predict-no)
  4062. I see 1 and I'm going to do: predict-no
  4063. ENV: Agent did: predict-no for direction U in state State-B
  4064. In State-B moving U
  4065. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4066. predict error 0
  4067. dir: dir isR
  4068. /572: O: O1144 (predict-no)
  4069. I see 1 and I'm going to do: predict-no
  4070. ENV: Agent did: predict-no for direction R in state State-B
  4071. In State-B moving R
  4072. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4073. predict error 0
  4074. dir: dir isR
  4075. |\-573: O: O1146 (predict-no)
  4076. I see 1 and I'm going to do: predict-no
  4077. ENV: Agent did: predict-no for direction R in state State-B
  4078. In State-B moving R
  4079. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4080. predict error 0
  4081. dir: dir isU
  4082. /|\574: O: O1148 (predict-no)
  4083. I see 1 and I'm going to do: predict-no
  4084. ENV: Agent did: predict-no for direction U in state State-B
  4085. In State-B moving U
  4086. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4087. predict error 0
  4088. dir: dir isR
  4089. -/|575: O: O1150 (predict-no)
  4090. I see 1 and I'm going to do: predict-no
  4091. ENV: Agent did: predict-no for direction R in state State-B
  4092. In State-B moving R
  4093. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4094. predict error 0
  4095. dir: dir isL
  4096. \-/576: O: O1151 (predict-yes)
  4097. I see 1 and I'm going to do: predict-yes
  4098. ENV: Agent did: predict-yes for direction L in state State-B
  4099. In State-B moving L
  4100. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  4101. predict error 0
  4102. dir: dir isR
  4103. |\577: O: O1153 (predict-yes)
  4104. I see 1 and I'm going to do: predict-yes
  4105. ENV: Agent did: predict-yes for direction R in state State-A
  4106. In State-A moving R
  4107. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  4108. predict error 0
  4109. dir: dir isU
  4110. -/|578: O: O1156 (predict-no)
  4111. I see 1 and I'm going to do: predict-no
  4112. ENV: Agent did: predict-no for direction U in state State-B
  4113. In State-B moving U
  4114. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4115. predict error 0
  4116. dir: dir isL
  4117. \-579: O: O1157 (predict-yes)
  4118. I see 1 and I'm going to do: predict-yes
  4119. ENV: Agent did: predict-yes for direction L in state State-B
  4120. In State-B moving L
  4121. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  4122. predict error 0
  4123. dir: dir isR
  4124. /|\580: O: O1159 (predict-yes)
  4125. I see 1 and I'm going to do: predict-yes
  4126. ENV: Agent did: predict-yes for direction R in state State-A
  4127. In State-A moving R
  4128. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  4129. predict error 0
  4130. dir: dir isR
  4131. -/581: O: O1162 (predict-no)
  4132. I see 1 and I'm going to do: predict-no
  4133. ENV: Agent did: predict-no for direction R in state State-B
  4134. In State-B moving R
  4135. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4136. predict error 0
  4137. dir: dir isR
  4138. |582: O: O1164 (predict-no)
  4139. I see 1 and I'm going to do: predict-no
  4140. ENV: Agent did: predict-no for direction R in state State-B
  4141. In State-B moving R
  4142. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4143. predict error 0
  4144. dir: dir isL
  4145. \-/583: O: O1165 (predict-yes)
  4146. I see 1 and I'm going to do: predict-yes
  4147. ENV: Agent did: predict-yes for direction L in state State-B
  4148. In State-B moving L
  4149. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  4150. predict error 0
  4151. dir: dir isL
  4152. |\-584: O: O1168 (predict-no)
  4153. I see 1 and I'm going to do: predict-no
  4154. ENV: Agent did: predict-no for direction L in state State-A
  4155. In State-A moving L
  4156. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4157. predict error 0
  4158. dir: dir isU
  4159. /|\585: O: O1170 (predict-no)
  4160. I see 1 and I'm going to do: predict-no
  4161. ENV: Agent did: predict-no for direction U in state State-A
  4162. In State-A moving U
  4163. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4164. predict error 0
  4165. dir: dir isR
  4166. -/|586: O: O1171 (predict-yes)
  4167. I see 1 and I'm going to do: predict-yes
  4168. ENV: Agent did: predict-yes for direction R in state State-A
  4169. In State-A moving R
  4170. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  4171. predict error 0
  4172. dir: dir isL
  4173. \-/587: O: O1173 (predict-yes)
  4174. I see 1 and I'm going to do: predict-yes
  4175. ENV: Agent did: predict-yes for direction L in state State-B
  4176. In State-B moving L
  4177. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  4178. predict error 0
  4179. dir: dir isL
  4180. |\-588: O: O1176 (predict-no)
  4181. I see 1 and I'm going to do: predict-no
  4182. ENV: Agent did: predict-no for direction L in state State-A
  4183. In State-A moving L
  4184. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4185. predict error 0
  4186. dir: dir isU
  4187. /|\589: O: O1178 (predict-no)
  4188. I see 1 and I'm going to do: predict-no
  4189. ENV: Agent did: predict-no for direction U in state State-A
  4190. In State-A moving U
  4191. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4192. predict error 0
  4193. dir: dir isR
  4194. -/|590: O: O1179 (predict-yes)
  4195. I see 1 and I'm going to do: predict-yes
  4196. ENV: Agent did: predict-yes for direction R in state State-A
  4197. In State-A moving R
  4198. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  4199. predict error 0
  4200. dir: dir isR
  4201. \-/591: O: O1182 (predict-no)
  4202. I see 1 and I'm going to do: predict-no
  4203. ENV: Agent did: predict-no for direction R in state State-B
  4204. In State-B moving R
  4205. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4206. predict error 0
  4207. dir: dir isL
  4208. |592: O: O1183 (predict-yes)
  4209. I see 1 and I'm going to do: predict-yes
  4210. ENV: Agent did: predict-yes for direction L in state State-B
  4211. In State-B moving L
  4212. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  4213. predict error 0
  4214. dir: dir isU
  4215. \-/593: O: O1186 (predict-no)
  4216. I see 1 and I'm going to do: predict-no
  4217. ENV: Agent did: predict-no for direction U in state State-A
  4218. In State-A moving U
  4219. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4220. predict error 0
  4221. dir: dir isR
  4222. |\-594: O: O1187 (predict-yes)
  4223. I see 1 and I'm going to do: predict-yes
  4224. ENV: Agent did: predict-yes for direction R in state State-A
  4225. In State-A moving R
  4226. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  4227. predict error 0
  4228. dir: dir isU
  4229. /|\595: O: O1190 (predict-no)
  4230. I see 1 and I'm going to do: predict-no
  4231. ENV: Agent did: predict-no for direction U in state State-B
  4232. In State-B moving U
  4233. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4234. predict error 0
  4235. dir: dir isU
  4236. -/|596: O: O1192 (predict-no)
  4237. I see 1 and I'm going to do: predict-no
  4238. ENV: Agent did: predict-no for direction U in state State-B
  4239. In State-B moving U
  4240. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4241. predict error 0
  4242. dir: dir isL
  4243. \-/597: O: O1193 (predict-yes)
  4244. I see 1 and I'm going to do: predict-yes
  4245. ENV: Agent did: predict-yes for direction L in state State-B
  4246. In State-B moving L
  4247. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  4248. predict error 0
  4249. dir: dir isU
  4250. |\-598: O: O1196 (predict-no)
  4251. I see 1 and I'm going to do: predict-no
  4252. ENV: Agent did: predict-no for direction U in state State-A
  4253. In State-A moving U
  4254. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4255. predict error 0
  4256. dir: dir isL
  4257. /|\599: O: O1198 (predict-no)
  4258. I see 1 and I'm going to do: predict-no
  4259. ENV: Agent did: predict-no for direction L in state State-A
  4260. In State-A moving L
  4261. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4262. predict error 0
  4263. dir: dir isU
  4264. -/|600: O: O1200 (predict-no)
  4265. I see 1 and I'm going to do: predict-no
  4266. ENV: Agent did: predict-no for direction U in state State-A
  4267. In State-A moving U
  4268. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4269. predict error 0
  4270. dir: dir isL
  4271. \-/601: O: O1202 (predict-no)
  4272. I see 1 and I'm going to do: predict-no
  4273. ENV: Agent did: predict-no for direction L in state State-A
  4274. In State-A moving L
  4275. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4276. predict error 0
  4277. dir: dir isU
  4278. |602: O: O1204 (predict-no)
  4279. I see 1 and I'm going to do: predict-no
  4280. ENV: Agent did: predict-no for direction U in state State-A
  4281. In State-A moving U
  4282. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4283. predict error 0
  4284. dir: dir isL
  4285. \-/603: O: O1206 (predict-no)
  4286. I see 1 and I'm going to do: predict-no
  4287. ENV: Agent did: predict-no for direction L in state State-A
  4288. In State-A moving L
  4289. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4290. predict error 0
  4291. dir: dir isL
  4292. |\604: O: O1208 (predict-no)
  4293. I see 1 and I'm going to do: predict-no
  4294. ENV: Agent did: predict-no for direction L in state State-A
  4295. In State-A moving L
  4296. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4297. predict error 0
  4298. dir: dir isR
  4299. -/|605: O: O1209 (predict-yes)
  4300. I see 1 and I'm going to do: predict-yes
  4301. ENV: Agent did: predict-yes for direction R in state State-A
  4302. In State-A moving R
  4303. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  4304. predict error 0
  4305. dir: dir isR
  4306. \-606: O: O1212 (predict-no)
  4307. I see 1 and I'm going to do: predict-no
  4308. ENV: Agent did: predict-no for direction R in state State-B
  4309. In State-B moving R
  4310. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4311. predict error 0
  4312. dir: dir isR
  4313. /|\607: O: O1214 (predict-no)
  4314. I see 1 and I'm going to do: predict-no
  4315. ENV: Agent did: predict-no for direction R in state State-B
  4316. In State-B moving R
  4317. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4318. predict error 0
  4319. dir: dir isL
  4320. -/608: O: O1215 (predict-yes)
  4321. I see 1 and I'm going to do: predict-yes
  4322. ENV: Agent did: predict-yes for direction L in state State-B
  4323. In State-B moving L
  4324. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  4325. predict error 0
  4326. dir: dir isL
  4327. |\-609: O: O1218 (predict-no)
  4328. I see 1 and I'm going to do: predict-no
  4329. ENV: Agent did: predict-no for direction L in state State-A
  4330. In State-A moving L
  4331. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4332. predict error 0
  4333. dir: dir isL
  4334. /|\610: O: O1220 (predict-no)
  4335. I see 1 and I'm going to do: predict-no
  4336. ENV: Agent did: predict-no for direction L in state State-A
  4337. In State-A moving L
  4338. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4339. predict error 0
  4340. dir: dir isU
  4341. -/|611: O: O1222 (predict-no)
  4342. I see 1 and I'm going to do: predict-no
  4343. ENV: Agent did: predict-no for direction U in state State-A
  4344. In State-A moving U
  4345. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4346. predict error 0
  4347. dir: dir isU
  4348. \612: O: O1224 (predict-no)
  4349. I see 1 and I'm going to do: predict-no
  4350. ENV: Agent did: predict-no for direction U in state State-A
  4351. In State-A moving U
  4352. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4353. predict error 0
  4354. dir: dir isR
  4355. -/|613: O: O1225 (predict-yes)
  4356. I see 1 and I'm going to do: predict-yes
  4357. ENV: Agent did: predict-yes for direction R in state State-A
  4358. In State-A moving R
  4359. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  4360. predict error 0
  4361. dir: dir isL
  4362. \-614: O: O1227 (predict-yes)
  4363. I see 1 and I'm going to do: predict-yes
  4364. ENV: Agent did: predict-yes for direction L in state State-B
  4365. In State-B moving L
  4366. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  4367. predict error 0
  4368. dir: dir isU
  4369. /|615: O: O1230 (predict-no)
  4370. I see 1 and I'm going to do: predict-no
  4371. ENV: Agent did: predict-no for direction U in state State-A
  4372. In State-A moving U
  4373. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4374. predict error 0
  4375. dir: dir isL
  4376. \-/616: O: O1232 (predict-no)
  4377. I see 1 and I'm going to do: predict-no
  4378. ENV: Agent did: predict-no for direction L in state State-A
  4379. In State-A moving L
  4380. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4381. predict error 0
  4382. dir: dir isR
  4383. |\617: O: O1233 (predict-yes)
  4384. I see 1 and I'm going to do: predict-yes
  4385. ENV: Agent did: predict-yes for direction R in state State-A
  4386. In State-A moving R
  4387. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  4388. predict error 0
  4389. dir: dir isR
  4390. -/618: O: O1236 (predict-no)
  4391. I see 1 and I'm going to do: predict-no
  4392. ENV: Agent did: predict-no for direction R in state State-B
  4393. In State-B moving R
  4394. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4395. predict error 0
  4396. dir: dir isL
  4397. |\-619: O: O1237 (predict-yes)
  4398. I see 1 and I'm going to do: predict-yes
  4399. ENV: Agent did: predict-yes for direction L in state State-B
  4400. In State-B moving L
  4401. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  4402. predict error 0
  4403. dir: dir isU
  4404. /|\620: O: O1240 (predict-no)
  4405. I see 1 and I'm going to do: predict-no
  4406. ENV: Agent did: predict-no for direction U in state State-A
  4407. In State-A moving U
  4408. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4409. predict error 0
  4410. dir: dir isL
  4411. -/|621: O: O1242 (predict-no)
  4412. I see 1 and I'm going to do: predict-no
  4413. ENV: Agent did: predict-no for direction L in state State-A
  4414. In State-A moving L
  4415. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4416. predict error 0
  4417. dir: dir isR
  4418. \622: O: O1243 (predict-yes)
  4419. I see 1 and I'm going to do: predict-yes
  4420. ENV: Agent did: predict-yes for direction R in state State-A
  4421. In State-A moving R
  4422. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  4423. predict error 0
  4424. dir: dir isL
  4425. -/|623: O: O1245 (predict-yes)
  4426. I see 1 and I'm going to do: predict-yes
  4427. ENV: Agent did: predict-yes for direction L in state State-B
  4428. In State-B moving L
  4429. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  4430. predict error 0
  4431. dir: dir isR
  4432. \-/624: O: O1247 (predict-yes)
  4433. I see 1 and I'm going to do: predict-yes
  4434. ENV: Agent did: predict-yes for direction R in state State-A
  4435. In State-A moving R
  4436. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  4437. predict error 0
  4438. dir: dir isR
  4439. |\-625: O: O1250 (predict-no)
  4440. I see 1 and I'm going to do: predict-no
  4441. ENV: Agent did: predict-no for direction R in state State-B
  4442. In State-B moving R
  4443. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4444. predict error 0
  4445. dir: dir isR
  4446. /|\626: O: O1252 (predict-no)
  4447. I see 1 and I'm going to do: predict-no
  4448. ENV: Agent did: predict-no for direction R in state State-B
  4449. In State-B moving R
  4450. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4451. predict error 0
  4452. dir: dir isR
  4453. -/|627: O: O1254 (predict-no)
  4454. I see 1 and I'm going to do: predict-no
  4455. ENV: Agent did: predict-no for direction R in state State-B
  4456. In State-B moving R
  4457. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4458. predict error 0
  4459. dir: dir isR
  4460. \-/628: O: O1256 (predict-no)
  4461. I see 1 and I'm going to do: predict-no
  4462. ENV: Agent did: predict-no for direction R in state State-B
  4463. In State-B moving R
  4464. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4465. predict error 0
  4466. dir: dir isR
  4467. |\-629: O: O1258 (predict-no)
  4468. I see 1 and I'm going to do: predict-no
  4469. ENV: Agent did: predict-no for direction R in state State-B
  4470. In State-B moving R
  4471. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4472. predict error 0
  4473. dir: dir isR
  4474. /|630: O: O1260 (predict-no)
  4475. I see 1 and I'm going to do: predict-no
  4476. ENV: Agent did: predict-no for direction R in state State-B
  4477. In State-B moving R
  4478. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4479. predict error 0
  4480. dir: dir isU
  4481. \-/631: O: O1262 (predict-no)
  4482. I see 1 and I'm going to do: predict-no
  4483. ENV: Agent did: predict-no for direction U in state State-B
  4484. In State-B moving U
  4485. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4486. predict error 0
  4487. dir: dir isU
  4488. |632: O: O1264 (predict-no)
  4489. I see 1 and I'm going to do: predict-no
  4490. ENV: Agent did: predict-no for direction U in state State-B
  4491. In State-B moving U
  4492. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4493. predict error 0
  4494. dir: dir isL
  4495. \-/633: O: O1265 (predict-yes)
  4496. I see 1 and I'm going to do: predict-yes
  4497. ENV: Agent did: predict-yes for direction L in state State-B
  4498. In State-B moving L
  4499. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  4500. predict error 0
  4501. dir: dir isR
  4502. |\634: O: O1267 (predict-yes)
  4503. I see 1 and I'm going to do: predict-yes
  4504. ENV: Agent did: predict-yes for direction R in state State-A
  4505. In State-A moving R
  4506. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  4507. predict error 0
  4508. dir: dir isR
  4509. -/|635: O: O1270 (predict-no)
  4510. I see 1 and I'm going to do: predict-no
  4511. ENV: Agent did: predict-no for direction R in state State-B
  4512. In State-B moving R
  4513. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4514. predict error 0
  4515. dir: dir isL
  4516. \-/636: O: O1271 (predict-yes)
  4517. I see 1 and I'm going to do: predict-yes
  4518. ENV: Agent did: predict-yes for direction L in state State-B
  4519. In State-B moving L
  4520. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  4521. predict error 0
  4522. dir: dir isU
  4523. |\637: O: O1274 (predict-no)
  4524. I see 1 and I'm going to do: predict-no
  4525. ENV: Agent did: predict-no for direction U in state State-A
  4526. In State-A moving U
  4527. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4528. predict error 0
  4529. dir: dir isR
  4530. -/|638: O: O1275 (predict-yes)
  4531. I see 1 and I'm going to do: predict-yes
  4532. ENV: Agent did: predict-yes for direction R in state State-A
  4533. In State-A moving R
  4534. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  4535. predict error 0
  4536. dir: dir isR
  4537. \-/639: O: O1278 (predict-no)
  4538. I see 1 and I'm going to do: predict-no
  4539. ENV: Agent did: predict-no for direction R in state State-B
  4540. In State-B moving R
  4541. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4542. predict error 0
  4543. dir: dir isL
  4544. |\640: O: O1279 (predict-yes)
  4545. I see 1 and I'm going to do: predict-yes
  4546. ENV: Agent did: predict-yes for direction L in state State-B
  4547. In State-B moving L
  4548. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  4549. predict error 0
  4550. dir: dir isU
  4551. -/|641: O: O1282 (predict-no)
  4552. I see 1 and I'm going to do: predict-no
  4553. ENV: Agent did: predict-no for direction U in state State-A
  4554. In State-A moving U
  4555. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4556. predict error 0
  4557. dir: dir isR
  4558. \642: O: O1283 (predict-yes)
  4559. I see 1 and I'm going to do: predict-yes
  4560. ENV: Agent did: predict-yes for direction R in state State-A
  4561. In State-A moving R
  4562. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  4563. predict error 0
  4564. dir: dir isR
  4565. -/|643: O: O1286 (predict-no)
  4566. I see 1 and I'm going to do: predict-no
  4567. ENV: Agent did: predict-no for direction R in state State-B
  4568. In State-B moving R
  4569. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4570. predict error 0
  4571. dir: dir isR
  4572. \-/644: O: O1288 (predict-no)
  4573. I see 1 and I'm going to do: predict-no
  4574. ENV: Agent did: predict-no for direction R in state State-B
  4575. In State-B moving R
  4576. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4577. predict error 0
  4578. dir: dir isR
  4579. |\645: O: O1290 (predict-no)
  4580. I see 1 and I'm going to do: predict-no
  4581. ENV: Agent did: predict-no for direction R in state State-B
  4582. In State-B moving R
  4583. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4584. predict error 0
  4585. dir: dir isU
  4586. -/|646: O: O1292 (predict-no)
  4587. I see 1 and I'm going to do: predict-no
  4588. ENV: Agent did: predict-no for direction U in state State-B
  4589. In State-B moving U
  4590. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4591. predict error 0
  4592. dir: dir isL
  4593. \-/647: O: O1293 (predict-yes)
  4594. I see 1 and I'm going to do: predict-yes
  4595. ENV: Agent did: predict-yes for direction L in state State-B
  4596. In State-B moving L
  4597. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  4598. predict error 0
  4599. dir: dir isR
  4600. |\648: O: O1295 (predict-yes)
  4601. I see 1 and I'm going to do: predict-yes
  4602. ENV: Agent did: predict-yes for direction R in state State-A
  4603. In State-A moving R
  4604. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  4605. predict error 0
  4606. dir: dir isL
  4607. -/|649: O: O1297 (predict-yes)
  4608. I see 1 and I'm going to do: predict-yes
  4609. ENV: Agent did: predict-yes for direction L in state State-B
  4610. In State-B moving L
  4611. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  4612. predict error 0
  4613. dir: dir isL
  4614. \-650: O: O1300 (predict-no)
  4615. I see 1 and I'm going to do: predict-no
  4616. ENV: Agent did: predict-no for direction L in state State-A
  4617. In State-A moving L
  4618. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4619. predict error 0
  4620. dir: dir isU
  4621. /|651: O: O1302 (predict-no)
  4622. I see 1 and I'm going to do: predict-no
  4623. ENV: Agent did: predict-no for direction U in state State-A
  4624. In State-A moving U
  4625. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4626. predict error 0
  4627. dir: dir isL
  4628. \652: O: O1304 (predict-no)
  4629. I see 1 and I'm going to do: predict-no
  4630. ENV: Agent did: predict-no for direction L in state State-A
  4631. In State-A moving L
  4632. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4633. predict error 0
  4634. dir: dir isR
  4635. -/|653: O: O1305 (predict-yes)
  4636. I see 1 and I'm going to do: predict-yes
  4637. ENV: Agent did: predict-yes for direction R in state State-A
  4638. In State-A moving R
  4639. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  4640. predict error 0
  4641. dir: dir isL
  4642. \-/654: O: O1307 (predict-yes)
  4643. I see 1 and I'm going to do: predict-yes
  4644. ENV: Agent did: predict-yes for direction L in state State-B
  4645. In State-B moving L
  4646. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  4647. predict error 0
  4648. dir: dir isR
  4649. |\655: O: O1309 (predict-yes)
  4650. I see 1 and I'm going to do: predict-yes
  4651. ENV: Agent did: predict-yes for direction R in state State-A
  4652. In State-A moving R
  4653. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  4654. predict error 0
  4655. dir: dir isU
  4656. -/656: O: O1312 (predict-no)
  4657. I see 1 and I'm going to do: predict-no
  4658. ENV: Agent did: predict-no for direction U in state State-B
  4659. In State-B moving U
  4660. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4661. predict error 0
  4662. dir: dir isL
  4663. |\657: O: O1313 (predict-yes)
  4664. I see 1 and I'm going to do: predict-yes
  4665. ENV: Agent did: predict-yes for direction L in state State-B
  4666. In State-B moving L
  4667. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  4668. predict error 0
  4669. dir: dir isR
  4670. -/658: O: O1315 (predict-yes)
  4671. I see 1 and I'm going to do: predict-yes
  4672. ENV: Agent did: predict-yes for direction R in state State-A
  4673. In State-A moving R
  4674. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  4675. predict error 0
  4676. dir: dir isL
  4677. |\-659: O: O1317 (predict-yes)
  4678. I see 1 and I'm going to do: predict-yes
  4679. ENV: Agent did: predict-yes for direction L in state State-B
  4680. In State-B moving L
  4681. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  4682. predict error 0
  4683. dir: dir isU
  4684. /|\660: O: O1320 (predict-no)
  4685. I see 1 and I'm going to do: predict-no
  4686. ENV: Agent did: predict-no for direction U in state State-A
  4687. In State-A moving U
  4688. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4689. predict error 0
  4690. dir: dir isU
  4691. -/|661: O: O1322 (predict-no)
  4692. I see 1 and I'm going to do: predict-no
  4693. ENV: Agent did: predict-no for direction U in state State-A
  4694. In State-A moving U
  4695. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4696. predict error 0
  4697. dir: dir isU
  4698. \662: O: O1324 (predict-no)
  4699. I see 1 and I'm going to do: predict-no
  4700. ENV: Agent did: predict-no for direction U in state State-A
  4701. In State-A moving U
  4702. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4703. predict error 0
  4704. dir: dir isU
  4705. -/|663: O: O1326 (predict-no)
  4706. I see 1 and I'm going to do: predict-no
  4707. ENV: Agent did: predict-no for direction U in state State-A
  4708. In State-A moving U
  4709. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4710. predict error 0
  4711. dir: dir isL
  4712. \-664: O: O1328 (predict-no)
  4713. I see 1 and I'm going to do: predict-no
  4714. ENV: Agent did: predict-no for direction L in state State-A
  4715. In State-A moving L
  4716. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4717. predict error 0
  4718. dir: dir isL
  4719. /665: O: O1330 (predict-no)
  4720. I see 1 and I'm going to do: predict-no
  4721. ENV: Agent did: predict-no for direction L in state State-A
  4722. In State-A moving L
  4723. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4724. predict error 0
  4725. dir: dir isR
  4726. |\-666: O: O1331 (predict-yes)
  4727. I see 1 and I'm going to do: predict-yes
  4728. ENV: Agent did: predict-yes for direction R in state State-A
  4729. In State-A moving R
  4730. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  4731. predict error 0
  4732. dir: dir isU
  4733. /|\667: O: O1334 (predict-no)
  4734. I see 1 and I'm going to do: predict-no
  4735. ENV: Agent did: predict-no for direction U in state State-B
  4736. In State-B moving U
  4737. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4738. predict error 0
  4739. dir: dir isU
  4740. -668: O: O1336 (predict-no)
  4741. I see 1 and I'm going to do: predict-no
  4742. ENV: Agent did: predict-no for direction U in state State-B
  4743. In State-B moving U
  4744. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4745. predict error 0
  4746. dir: dir isU
  4747. /|\669: O: O1338 (predict-no)
  4748. I see 1 and I'm going to do: predict-no
  4749. ENV: Agent did: predict-no for direction U in state State-B
  4750. In State-B moving U
  4751. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4752. predict error 0
  4753. dir: dir isU
  4754. -/|670: O: O1340 (predict-no)
  4755. I see 1 and I'm going to do: predict-no
  4756. ENV: Agent did: predict-no for direction U in state State-B
  4757. In State-B moving U
  4758. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4759. predict error 0
  4760. dir: dir isL
  4761. \-/|671: O: O1341 (predict-yes)
  4762. I see 1 and I'm going to do: predict-yes
  4763. ENV: Agent did: predict-yes for direction L in state State-B
  4764. In State-B moving L
  4765. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  4766. predict error 0
  4767. dir: dir isU
  4768. \672: O: O1344 (predict-no)
  4769. I see 1 and I'm going to do: predict-no
  4770. ENV: Agent did: predict-no for direction U in state State-A
  4771. In State-A moving U
  4772. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4773. predict error 0
  4774. dir: dir isL
  4775. -/|673: O: O1346 (predict-no)
  4776. I see 1 and I'm going to do: predict-no
  4777. ENV: Agent did: predict-no for direction L in state State-A
  4778. In State-A moving L
  4779. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4780. predict error 0
  4781. dir: dir isL
  4782. \-/674: O: O1348 (predict-no)
  4783. I see 1 and I'm going to do: predict-no
  4784. ENV: Agent did: predict-no for direction L in state State-A
  4785. In State-A moving L
  4786. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4787. predict error 0
  4788. dir: dir isR
  4789. |\-675: O: O1349 (predict-yes)
  4790. I see 1 and I'm going to do: predict-yes
  4791. ENV: Agent did: predict-yes for direction R in state State-A
  4792. In State-A moving R
  4793. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  4794. predict error 0
  4795. dir: dir isL
  4796. /|\676: O: O1351 (predict-yes)
  4797. I see 1 and I'm going to do: predict-yes
  4798. ENV: Agent did: predict-yes for direction L in state State-B
  4799. In State-B moving L
  4800. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  4801. predict error 0
  4802. dir: dir isL
  4803. -677: O: O1354 (predict-no)
  4804. I see 1 and I'm going to do: predict-no
  4805. ENV: Agent did: predict-no for direction L in state State-A
  4806. In State-A moving L
  4807. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4808. predict error 0
  4809. dir: dir isR
  4810. /|678: O: O1355 (predict-yes)
  4811. I see 1 and I'm going to do: predict-yes
  4812. ENV: Agent did: predict-yes for direction R in state State-A
  4813. In State-A moving R
  4814. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  4815. predict error 0
  4816. dir: dir isU
  4817. \-/679: O: O1358 (predict-no)
  4818. I see 1 and I'm going to do: predict-no
  4819. ENV: Agent did: predict-no for direction U in state State-B
  4820. In State-B moving U
  4821. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4822. predict error 0
  4823. dir: dir isR
  4824. |\680: O: O1360 (predict-no)
  4825. I see 1 and I'm going to do: predict-no
  4826. ENV: Agent did: predict-no for direction R in state State-B
  4827. In State-B moving R
  4828. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4829. predict error 0
  4830. dir: dir isR
  4831. -/681: O: O1362 (predict-no)
  4832. I see 1 and I'm going to do: predict-no
  4833. ENV: Agent did: predict-no for direction R in state State-B
  4834. In State-B moving R
  4835. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4836. predict error 0
  4837. dir: dir isU
  4838. |682: O: O1364 (predict-no)
  4839. I see 1 and I'm going to do: predict-no
  4840. ENV: Agent did: predict-no for direction U in state State-B
  4841. In State-B moving U
  4842. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4843. predict error 0
  4844. dir: dir isR
  4845. \683: O: O1366 (predict-no)
  4846. I see 1 and I'm going to do: predict-no
  4847. ENV: Agent did: predict-no for direction R in state State-B
  4848. In State-B moving R
  4849. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4850. predict error 0
  4851. dir: dir isL
  4852. -/|684: O: O1367 (predict-yes)
  4853. I see 1 and I'm going to do: predict-yes
  4854. ENV: Agent did: predict-yes for direction L in state State-B
  4855. In State-B moving L
  4856. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  4857. predict error 0
  4858. dir: dir isU
  4859. \-/685: O: O1370 (predict-no)
  4860. I see 1 and I'm going to do: predict-no
  4861. ENV: Agent did: predict-no for direction U in state State-A
  4862. In State-A moving U
  4863. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4864. predict error 0
  4865. dir: dir isR
  4866. |\-686: O: O1371 (predict-yes)
  4867. I see 1 and I'm going to do: predict-yes
  4868. ENV: Agent did: predict-yes for direction R in state State-A
  4869. In State-A moving R
  4870. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  4871. predict error 0
  4872. dir: dir isU
  4873. /|687: O: O1374 (predict-no)
  4874. I see 1 and I'm going to do: predict-no
  4875. ENV: Agent did: predict-no for direction U in state State-B
  4876. In State-B moving U
  4877. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4878. predict error 0
  4879. dir: dir isR
  4880. \-/688: O: O1376 (predict-no)
  4881. I see 1 and I'm going to do: predict-no
  4882. ENV: Agent did: predict-no for direction R in state State-B
  4883. In State-B moving R
  4884. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4885. predict error 0
  4886. dir: dir isU
  4887. |\-689: O: O1378 (predict-no)
  4888. I see 1 and I'm going to do: predict-no
  4889. ENV: Agent did: predict-no for direction U in state State-B
  4890. In State-B moving U
  4891. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4892. predict error 0
  4893. dir: dir isR
  4894. /|\690: O: O1380 (predict-no)
  4895. I see 1 and I'm going to do: predict-no
  4896. ENV: Agent did: predict-no for direction R in state State-B
  4897. In State-B moving R
  4898. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4899. predict error 0
  4900. dir: dir isL
  4901. -/691: O: O1381 (predict-yes)
  4902. I see 1 and I'm going to do: predict-yes
  4903. ENV: Agent did: predict-yes for direction L in state State-B
  4904. In State-B moving L
  4905. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  4906. predict error 0
  4907. dir: dir isL
  4908. |692: O: O1384 (predict-no)
  4909. I see 1 and I'm going to do: predict-no
  4910. ENV: Agent did: predict-no for direction L in state State-A
  4911. In State-A moving L
  4912. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4913. predict error 0
  4914. dir: dir isU
  4915. \-693: O: O1386 (predict-no)
  4916. I see 1 and I'm going to do: predict-no
  4917. ENV: Agent did: predict-no for direction U in state State-A
  4918. In State-A moving U
  4919. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4920. predict error 0
  4921. dir: dir isR
  4922. /|\694: O: O1387 (predict-yes)
  4923. I see 1 and I'm going to do: predict-yes
  4924. ENV: Agent did: predict-yes for direction R in state State-A
  4925. In State-A moving R
  4926. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  4927. predict error 0
  4928. dir: dir isL
  4929. -/|695: O: O1389 (predict-yes)
  4930. I see 1 and I'm going to do: predict-yes
  4931. ENV: Agent did: predict-yes for direction L in state State-B
  4932. In State-B moving L
  4933. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  4934. predict error 0
  4935. dir: dir isR
  4936. \-/696: O: O1391 (predict-yes)
  4937. I see 1 and I'm going to do: predict-yes
  4938. ENV: Agent did: predict-yes for direction R in state State-A
  4939. In State-A moving R
  4940. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  4941. predict error 0
  4942. dir: dir isL
  4943. |\-697: O: O1393 (predict-yes)
  4944. I see 1 and I'm going to do: predict-yes
  4945. ENV: Agent did: predict-yes for direction L in state State-B
  4946. In State-B moving L
  4947. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  4948. predict error 0
  4949. dir: dir isL
  4950. /|\698: O: O1396 (predict-no)
  4951. I see 1 and I'm going to do: predict-no
  4952. ENV: Agent did: predict-no for direction L in state State-A
  4953. In State-A moving L
  4954. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4955. predict error 0
  4956. dir: dir isL
  4957. -/|699: O: O1398 (predict-no)
  4958. I see 1 and I'm going to do: predict-no
  4959. ENV: Agent did: predict-no for direction L in state State-A
  4960. In State-A moving L
  4961. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4962. predict error 0
  4963. dir: dir isL
  4964. \-/700: O: O1400 (predict-no)
  4965. I see 1 and I'm going to do: predict-no
  4966. ENV: Agent did: predict-no for direction L in state State-A
  4967. In State-A moving L
  4968. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4969. predict error 0
  4970. dir: dir isR
  4971. |\701: O: O1401 (predict-yes)
  4972. I see 1 and I'm going to do: predict-yes
  4973. ENV: Agent did: predict-yes for direction R in state State-A
  4974. In State-A moving R
  4975. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  4976. predict error 0
  4977. dir: dir isL
  4978. -702: O: O1403 (predict-yes)
  4979. I see 1 and I'm going to do: predict-yes
  4980. ENV: Agent did: predict-yes for direction L in state State-B
  4981. In State-B moving L
  4982. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  4983. predict error 0
  4984. dir: dir isR
  4985. /|703: O: O1405 (predict-yes)
  4986. I see 1 and I'm going to do: predict-yes
  4987. ENV: Agent did: predict-yes for direction R in state State-A
  4988. In State-A moving R
  4989. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  4990. predict error 0
  4991. dir: dir isR
  4992. \-/704: O: O1408 (predict-no)
  4993. I see 1 and I'm going to do: predict-no
  4994. ENV: Agent did: predict-no for direction R in state State-B
  4995. In State-B moving R
  4996. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4997. predict error 0
  4998. dir: dir isU
  4999. |\705: O: O1410 (predict-no)
  5000. I see 1 and I'm going to do: predict-no
  5001. ENV: Agent did: predict-no for direction U in state State-B
  5002. In State-B moving U
  5003. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5004. predict error 0
  5005. dir: dir isR
  5006. -/|706: O: O1412 (predict-no)
  5007. I see 1 and I'm going to do: predict-no
  5008. ENV: Agent did: predict-no for direction R in state State-B
  5009. In State-B moving R
  5010. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5011. predict error 0
  5012. dir: dir isL
  5013. \-/707: O: O1413 (predict-yes)
  5014. I see 1 and I'm going to do: predict-yes
  5015. ENV: Agent did: predict-yes for direction L in state State-B
  5016. In State-B moving L
  5017. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  5018. predict error 0
  5019. dir: dir isU
  5020. |\-708: O: O1416 (predict-no)
  5021. I see 1 and I'm going to do: predict-no
  5022. ENV: Agent did: predict-no for direction U in state State-A
  5023. In State-A moving U
  5024. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  5025. predict error 0
  5026. dir: dir isR
  5027. /|\709: O: O1417 (predict-yes)
  5028. I see 1 and I'm going to do: predict-yes
  5029. ENV: Agent did: predict-yes for direction R in state State-A
  5030. In State-A moving R
  5031. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  5032. predict error 0
  5033. dir: dir isR
  5034. -/|710: O: O1420 (predict-no)
  5035. I see 1 and I'm going to do: predict-no
  5036. ENV: Agent did: predict-no for direction R in state State-B
  5037. In State-B moving R
  5038. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5039. predict error 0
  5040. dir: dir isR
  5041. \-/|711: O: O1422 (predict-no)
  5042. I see 1 and I'm going to do: predict-no
  5043. ENV: Agent did: predict-no for direction R in state State-B
  5044. In State-B moving R
  5045. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5046. predict error 0
  5047. dir: dir isR
  5048. \712: O: O1424 (predict-no)
  5049. I see 1 and I'm going to do: predict-no
  5050. ENV: Agent did: predict-no for direction R in state State-B
  5051. In State-B moving R
  5052. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5053. predict error 0
  5054. dir: dir isU
  5055. -/|713: O: O1426 (predict-no)
  5056. I see 1 and I'm going to do: predict-no
  5057. ENV: Agent did: predict-no for direction U in state State-B
  5058. In State-B moving U
  5059. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5060. predict error 0
  5061. dir: dir isU
  5062. \-/714: O: O1428 (predict-no)
  5063. I see 1 and I'm going to do: predict-no
  5064. ENV: Agent did: predict-no for direction U in state State-B
  5065. In State-B moving U
  5066. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5067. predict error 0
  5068. dir: dir isU
  5069. |\715: O: O1430 (predict-no)
  5070. I see 1 and I'm going to do: predict-no
  5071. ENV: Agent did: predict-no for direction U in state State-B
  5072. In State-B moving U
  5073. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5074. predict error 0
  5075. dir: dir isU
  5076. -/|716: O: O1432 (predict-no)
  5077. I see 1 and I'm going to do: predict-no
  5078. ENV: Agent did: predict-no for direction U in state State-B
  5079. In State-B moving U
  5080. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5081. predict error 0
  5082. dir: dir isR
  5083. \-/717: O: O1434 (predict-no)
  5084. I see 1 and I'm going to do: predict-no
  5085. ENV: Agent did: predict-no for direction R in state State-B
  5086. In State-B moving R
  5087. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5088. predict error 0
  5089. dir: dir isR
  5090. |\-718: O: O1436 (predict-no)
  5091. I see 1 and I'm going to do: predict-no
  5092. ENV: Agent did: predict-no for direction R in state State-B
  5093. In State-B moving R
  5094. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5095. predict error 0
  5096. dir: dir isU
  5097. /|\719: O: O1438 (predict-no)
  5098. I see 1 and I'm going to do: predict-no
  5099. ENV: Agent did: predict-no for direction U in state State-B
  5100. In State-B moving U
  5101. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5102. predict error 0
  5103. dir: dir isL
  5104. -/|720: O: O1439 (predict-yes)
  5105. I see 1 and I'm going to do: predict-yes
  5106. ENV: Agent did: predict-yes for direction L in state State-B
  5107. In State-B moving L
  5108. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  5109. predict error 0
  5110. dir: dir isL
  5111. \-/721: O: O1442 (predict-no)
  5112. I see 1 and I'm going to do: predict-no
  5113. ENV: Agent did: predict-no for direction L in state State-A
  5114. In State-A moving L
  5115. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  5116. predict error 0
  5117. dir: dir isL
  5118. |722: O: O1444 (predict-no)
  5119. I see 1 and I'm going to do: predict-no
  5120. ENV: Agent did: predict-no for direction L in state State-A
  5121. In State-A moving L
  5122. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  5123. predict error 0
  5124. dir: dir isL
  5125. \-/723: O: O1446 (predict-no)
  5126. I see 1 and I'm going to do: predict-no
  5127. ENV: Agent did: predict-no for direction L in state State-A
  5128. In State-A moving L
  5129. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  5130. predict error 0
  5131. dir: dir isL
  5132. |\-724: O: O1448 (predict-no)
  5133. I see 1 and I'm going to do: predict-no
  5134. ENV: Agent did: predict-no for direction L in state State-A
  5135. In State-A moving L
  5136. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  5137. predict error 0
  5138. dir: dir isR
  5139. /|\725: O: O1449 (predict-yes)
  5140. I see 1 and I'm going to do: predict-yes
  5141. ENV: Agent did: predict-yes for direction R in state State-A
  5142. In State-A moving R
  5143. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  5144. predict error 0
  5145. dir: dir isL
  5146. -/|726: O: O1451 (predict-yes)
  5147. I see 1 and I'm going to do: predict-yes
  5148. ENV: Agent did: predict-yes for direction L in state State-B
  5149. In State-B moving L
  5150. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  5151. predict error 0
  5152. dir: dir isU
  5153. \-/727: O: O1454 (predict-no)
  5154. I see 1 and I'm going to do: predict-no
  5155. ENV: Agent did: predict-no for direction U in state State-A
  5156. In State-A moving U
  5157. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  5158. predict error 0
  5159. dir: dir isU
  5160. |\-728: O: O1456 (predict-no)
  5161. I see 1 and I'm going to do: predict-no
  5162. ENV: Agent did: predict-no for direction U in state State-A
  5163. In State-A moving U
  5164. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  5165. predict error 0
  5166. dir: dir isU
  5167. /|\729: O: O1458 (predict-no)
  5168. I see 1 and I'm going to do: predict-no
  5169. ENV: Agent did: predict-no for direction U in state State-A
  5170. In State-A moving U
  5171. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  5172. predict error 0
  5173. dir: dir isR
  5174. -/|730: O: O1459 (predict-yes)
  5175. I see 1 and I'm going to do: predict-yes
  5176. ENV: Agent did: predict-yes for direction R in state State-A
  5177. In State-A moving R
  5178. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  5179. predict error 0
  5180. dir: dir isU
  5181. \-/731: O: O1462 (predict-no)
  5182. I see 1 and I'm going to do: predict-no
  5183. ENV: Agent did: predict-no for direction U in state State-B
  5184. In State-B moving U
  5185. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5186. predict error 0
  5187. dir: dir isR
  5188. |732: O: O1464 (predict-no)
  5189. I see 1 and I'm going to do: predict-no
  5190. ENV: Agent did: predict-no for direction R in state State-B
  5191. In State-B moving R
  5192. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5193. predict error 0
  5194. dir: dir isR
  5195. \-/|733: O: O1466 (predict-no)
  5196. I see 1 and I'm going to do: predict-no
  5197. ENV: Agent did: predict-no for direction R in state State-B
  5198. In State-B moving R
  5199. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5200. predict error 0
  5201. dir: dir isL
  5202. \-/734: O: O1467 (predict-yes)
  5203. I see 1 and I'm going to do: predict-yes
  5204. ENV: Agent did: predict-yes for direction L in state State-B
  5205. In State-B moving L
  5206. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  5207. predict error 0
  5208. dir: dir isU
  5209. |\735: O: O1470 (predict-no)
  5210. I see 1 and I'm going to do: predict-no
  5211. ENV: Agent did: predict-no for direction U in state State-A
  5212. In State-A moving U
  5213. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  5214. predict error 0
  5215. dir: dir isU
  5216. -/|736: O: O1472 (predict-no)
  5217. I see 1 and I'm going to do: predict-no
  5218. ENV: Agent did: predict-no for direction U in state State-A
  5219. In State-A moving U
  5220. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  5221. predict error 0
  5222. dir: dir isL
  5223. \-/737: O: O1474 (predict-no)
  5224. I see 1 and I'm going to do: predict-no
  5225. ENV: Agent did: predict-no for direction L in state State-A
  5226. In State-A moving L
  5227. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  5228. predict error 0
  5229. dir: dir isR
  5230. |\-738: O: O1475 (predict-yes)
  5231. I see 1 and I'm going to do: predict-yes
  5232. ENV: Agent did: predict-yes for direction R in state State-A
  5233. In State-A moving R
  5234. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  5235. predict error 0
  5236. dir: dir isL
  5237. /|\739: O: O1477 (predict-yes)
  5238. I see 1 and I'm going to do: predict-yes
  5239. ENV: Agent did: predict-yes for direction L in state State-B
  5240. In State-B moving L
  5241. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  5242. predict error 0
  5243. dir: dir isL
  5244. -/740: O: O1480 (predict-no)
  5245. I see 1 and I'm going to do: predict-no
  5246. ENV: Agent did: predict-no for direction L in state State-A
  5247. In State-A moving L
  5248. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  5249. predict error 0
  5250. dir: dir isL
  5251. |\-741: O: O1482 (predict-no)
  5252. I see 1 and I'm going to do: predict-no
  5253. ENV: Agent did: predict-no for direction L in state State-A
  5254. In State-A moving L
  5255. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  5256. predict error 0
  5257. dir: dir isR
  5258. /742: O: O1483 (predict-yes)
  5259. I see 1 and I'm going to do: predict-yes
  5260. ENV: Agent did: predict-yes for direction R in state State-A
  5261. In State-A moving R
  5262. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  5263. predict error 0
  5264. dir: dir isL
  5265. |\-743: O: O1485 (predict-yes)
  5266. I see 1 and I'm going to do: predict-yes
  5267. ENV: Agent did: predict-yes for direction L in state State-B
  5268. In State-B moving L
  5269. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  5270. predict error 0
  5271. dir: dir isR
  5272. /|\744: O: O1487 (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. -/|745: O: O1489 (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 isL
  5286. \-/746: O: O1492 (predict-no)
  5287. I see 1 and I'm going to do: predict-no
  5288. ENV: Agent did: predict-no for direction L in state State-A
  5289. In State-A moving L
  5290. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  5291. predict error 0
  5292. dir: dir isU
  5293. |\-747: O: O1494 (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-A
  5296. In State-A moving U
  5297. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  5298. predict error 0
  5299. dir: dir isU
  5300. /|\748: O: O1496 (predict-no)
  5301. I see 1 and I'm going to do: predict-no
  5302. ENV: Agent did: predict-no for direction U in state State-A
  5303. In State-A moving U
  5304. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  5305. predict error 0
  5306. dir: dir isL
  5307. -/|749: O: O1498 (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. \-750: O: O1500 (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. /|\751: O: O1502 (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 isR
  5328. -752: O: O1503 (predict-yes)
  5329. I see 1 and I'm going to do: predict-yes
  5330. ENV: Agent did: predict-yes for direction R in state State-A
  5331. In State-A moving R
  5332. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  5333. predict error 0
  5334. dir: dir isU
  5335. /|753: O: O1506 (predict-no)
  5336. I see 1 and I'm going to do: predict-no
  5337. ENV: Agent did: predict-no for direction U in state State-B
  5338. In State-B moving U
  5339. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5340. predict error 0
  5341. dir: dir isL
  5342. \754: O: O1507 (predict-yes)
  5343. I see 1 and I'm going to do: predict-yes
  5344. ENV: Agent did: predict-yes for direction L in state State-B
  5345. In State-B moving L
  5346. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  5347. predict error 0
  5348. dir: dir isU
  5349. -/|755: O: O1510 (predict-no)
  5350. I see 1 and I'm going to do: predict-no
  5351. ENV: Agent did: predict-no for direction U in state State-A
  5352. In State-A moving U
  5353. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  5354. predict error 0
  5355. dir: dir isL
  5356. \-/756: O: O1512 (predict-no)
  5357. I see 1 and I'm going to do: predict-no
  5358. ENV: Agent did: predict-no for direction L in state State-A
  5359. In State-A moving L
  5360. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  5361. predict error 0
  5362. dir: dir isR
  5363. |\-757: O: O1513 (predict-yes)
  5364. I see 1 and I'm going to do: predict-yes
  5365. ENV: Agent did: predict-yes for direction R in state State-A
  5366. In State-A moving R
  5367. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  5368. predict error 0
  5369. dir: dir isU
  5370. /|758: O: O1516 (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 isL
  5377. \-/759: O: O1517 (predict-yes)
  5378. I see 1 and I'm going to do: predict-yes
  5379. ENV: Agent did: predict-yes for direction L in state State-B
  5380. In State-B moving L
  5381. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  5382. predict error 0
  5383. dir: dir isU
  5384. |\-760: O: O1520 (predict-no)
  5385. I see 1 and I'm going to do: predict-no
  5386. ENV: Agent did: predict-no for direction U in state State-A
  5387. In State-A moving U
  5388. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  5389. predict error 0
  5390. dir: dir isU
  5391. /|\761: O: O1522 (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-A
  5394. In State-A moving U
  5395. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  5396. predict error 0
  5397. dir: dir isR
  5398. -762: O: O1523 (predict-yes)
  5399. I see 1 and I'm going to do: predict-yes
  5400. ENV: Agent did: predict-yes for direction R in state State-A
  5401. In State-A moving R
  5402. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  5403. predict error 0
  5404. dir: dir isL
  5405. /|\-763: O: O1525 (predict-yes)
  5406. I see 1 and I'm going to do: predict-yes
  5407. ENV: Agent did: predict-yes for direction L in state State-B
  5408. In State-B moving L
  5409. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  5410. predict error 0
  5411. dir: dir isL
  5412. /764: O: O1528 (predict-no)
  5413. I see 1 and I'm going to do: predict-no
  5414. ENV: Agent did: predict-no for direction L in state State-A
  5415. In State-A moving L
  5416. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  5417. predict error 0
  5418. dir: dir isL
  5419. |\-765: O: O1530 (predict-no)
  5420. I see 1 and I'm going to do: predict-no
  5421. ENV: Agent did: predict-no for direction L in state State-A
  5422. In State-A moving L
  5423. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  5424. predict error 0
  5425. dir: dir isU
  5426. /|766: O: O1532 (predict-no)
  5427. I see 1 and I'm going to do: predict-no
  5428. ENV: Agent did: predict-no for direction U in state State-A
  5429. In State-A moving U
  5430. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  5431. predict error 0
  5432. dir: dir isR
  5433. \-/767: O: O1533 (predict-yes)
  5434. I see 1 and I'm going to do: predict-yes
  5435. ENV: Agent did: predict-yes for direction R in state State-A
  5436. In State-A moving R
  5437. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  5438. predict error 0
  5439. dir: dir isU
  5440. |\-768: O: O1536 (predict-no)
  5441. I see 1 and I'm going to do: predict-no
  5442. ENV: Agent did: predict-no for direction U in state State-B
  5443. In State-B moving U
  5444. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5445. predict error 0
  5446. dir: dir isR
  5447. /|\769: O: O1538 (predict-no)
  5448. I see 1 and I'm going to do: predict-no
  5449. ENV: Agent did: predict-no for direction R in state State-B
  5450. In State-B moving R
  5451. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5452. predict error 0
  5453. dir: dir isL
  5454. -/|770: O: O1539 (predict-yes)
  5455. I see 1 and I'm going to do: predict-yes
  5456. ENV: Agent did: predict-yes for direction L in state State-B
  5457. In State-B moving L
  5458. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  5459. predict error 0
  5460. dir: dir isR
  5461. \-/|771: O: O1541 (predict-yes)
  5462. I see 1 and I'm going to do: predict-yes
  5463. ENV: Agent did: predict-yes for direction R in state State-A
  5464. In State-A moving R
  5465. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  5466. predict error 0
  5467. dir: dir isU
  5468. \772: O: O1544 (predict-no)
  5469. I see 1 and I'm going to do: predict-no
  5470. ENV: Agent did: predict-no for direction U in state State-B
  5471. In State-B moving U
  5472. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5473. predict error 0
  5474. dir: dir isU
  5475. -/|773: O: O1546 (predict-no)
  5476. I see 1 and I'm going to do: predict-no
  5477. ENV: Agent did: predict-no for direction U in state State-B
  5478. In State-B moving U
  5479. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5480. predict error 0
  5481. dir: dir isL
  5482. \-/774: O: O1547 (predict-yes)
  5483. I see 1 and I'm going to do: predict-yes
  5484. ENV: Agent did: predict-yes for direction L in state State-B
  5485. In State-B moving L
  5486. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  5487. predict error 0
  5488. dir: dir isL
  5489. |\-775: O: O1550 (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 isR
  5496. /|776: O: O1551 (predict-yes)
  5497. I see 1 and I'm going to do: predict-yes
  5498. ENV: Agent did: predict-yes for direction R in state State-A
  5499. In State-A moving R
  5500. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  5501. predict error 0
  5502. dir: dir isL
  5503. \-/777: O: O1553 (predict-yes)
  5504. I see 1 and I'm going to do: predict-yes
  5505. ENV: Agent did: predict-yes for direction L in state State-B
  5506. In State-B moving L
  5507. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  5508. predict error 0
  5509. dir: dir isU
  5510. |\778: O: O1556 (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-A
  5513. In State-A moving U
  5514. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  5515. predict error 0
  5516. dir: dir isU
  5517. -/|779: O: O1558 (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-A
  5520. In State-A moving U
  5521. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  5522. predict error 0
  5523. dir: dir isL
  5524. \-/780: O: O1560 (predict-no)
  5525. I see 1 and I'm going to do: predict-no
  5526. ENV: Agent did: predict-no for direction L in state State-A
  5527. In State-A moving L
  5528. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  5529. predict error 0
  5530. dir: dir isR
  5531. |\-/781: O: O1561 (predict-yes)
  5532. I see 1 and I'm going to do: predict-yes
  5533. ENV: Agent did: predict-yes for direction R in state State-A
  5534. In State-A moving R
  5535. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  5536. predict error 0
  5537. dir: dir isR
  5538. |782: O: O1564 (predict-no)
  5539. I see 1 and I'm going to do: predict-no
  5540. ENV: Agent did: predict-no for direction R in state State-B
  5541. In State-B moving R
  5542. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5543. predict error 0
  5544. dir: dir isL
  5545. \-/783: O: O1565 (predict-yes)
  5546. I see 1 and I'm going to do: predict-yes
  5547. ENV: Agent did: predict-yes for direction L in state State-B
  5548. In State-B moving L
  5549. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  5550. predict error 0
  5551. dir: dir isR
  5552. |\784: O: O1567 (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 isL
  5559. -/|\785: O: O1569 (predict-yes)
  5560. I see 1 and I'm going to do: predict-yes
  5561. ENV: Agent did: predict-yes for direction L in state State-B
  5562. In State-B moving L
  5563. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  5564. predict error 0
  5565. dir: dir isL
  5566. -/|786: O: O1572 (predict-no)
  5567. I see 1 and I'm going to do: predict-no
  5568. ENV: Agent did: predict-no for direction L in state State-A
  5569. In State-A moving L
  5570. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  5571. predict error 0
  5572. dir: dir isR
  5573. \-/|sleeping...
  5574. \787: O: O1573 (predict-yes)
  5575. I see 1 and I'm going to do: predict-yes
  5576. ENV: Agent did: predict-yes for direction R in state State-A
  5577. In State-A moving R
  5578. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  5579. predict error 0
  5580. dir: dir isR
  5581. -/|788: O: O1576 (predict-no)
  5582. I see 1 and I'm going to do: predict-no
  5583. ENV: Agent did: predict-no for direction R in state State-B
  5584. In State-B moving R
  5585. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5586. predict error 0
  5587. dir: dir isR
  5588. \789: O: O1578 (predict-no)
  5589. I see 1 and I'm going to do: predict-no
  5590. ENV: Agent did: predict-no for direction R in state State-B
  5591. In State-B moving R
  5592. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5593. predict error 0
  5594. dir: dir isL
  5595. -/790: O: O1579 (predict-yes)
  5596. I see 1 and I'm going to do: predict-yes
  5597. ENV: Agent did: predict-yes for direction L in state State-B
  5598. In State-B moving L
  5599. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  5600. predict error 0
  5601. dir: dir isL
  5602. |\-791: O: O1582 (predict-no)
  5603. I see 1 and I'm going to do: predict-no
  5604. ENV: Agent did: predict-no for direction L in state State-A
  5605. In State-A moving L
  5606. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  5607. predict error 0
  5608. dir: dir isL
  5609. /792: O: O1584 (predict-no)
  5610. I see 1 and I'm going to do: predict-no
  5611. ENV: Agent did: predict-no for direction L in state State-A
  5612. In State-A moving L
  5613. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  5614. predict error 0
  5615. dir: dir isU
  5616. |\793: O: O1586 (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-A
  5619. In State-A moving U
  5620. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  5621. predict error 0
  5622. dir: dir isL
  5623. -/|794: O: O1588 (predict-no)
  5624. I see 1 and I'm going to do: predict-no
  5625. ENV: Agent did: predict-no for direction L in state State-A
  5626. In State-A moving L
  5627. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  5628. predict error 0
  5629. dir: dir isU
  5630. \-795: O: O1590 (predict-no)
  5631. I see 1 and I'm going to do: predict-no
  5632. ENV: Agent did: predict-no for direction U in state State-A
  5633. In State-A moving U
  5634. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  5635. predict error 0
  5636. dir: dir isL
  5637. /|\796: O: O1592 (predict-no)
  5638. I see 1 and I'm going to do: predict-no
  5639. ENV: Agent did: predict-no for direction L in state State-A
  5640. In State-A moving L
  5641. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  5642. predict error 0
  5643. dir: dir isL
  5644. -/797: O: O1594 (predict-no)
  5645. I see 1 and I'm going to do: predict-no
  5646. ENV: Agent did: predict-no for direction L in state State-A
  5647. In State-A moving L
  5648. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  5649. predict error 0
  5650. dir: dir isU
  5651. |\798: O: O1596 (predict-no)
  5652. I see 1 and I'm going to do: predict-no
  5653. ENV: Agent did: predict-no for direction U in state State-A
  5654. In State-A moving U
  5655. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  5656. predict error 0
  5657. dir: dir isR
  5658. -799: O: O1597 (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 isU
  5665. /|800: O: O1600 (predict-no)
  5666. I see 1 and I'm going to do: predict-no
  5667. ENV: Agent did: predict-no for direction U in state State-B
  5668. In State-B moving U
  5669. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5670. predict error 0
  5671. dir: dir isR
  5672. \-/801: O: O1602 (predict-no)
  5673. I see 1 and I'm going to do: predict-no
  5674. ENV: Agent did: predict-no for direction R in state State-B
  5675. In State-B moving R
  5676. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5677. predict error 0
  5678. dir: dir isU
  5679. |802: O: O1604 (predict-no)
  5680. I see 1 and I'm going to do: predict-no
  5681. ENV: Agent did: predict-no for direction U in state State-B
  5682. In State-B moving U
  5683. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5684. predict error 0
  5685. dir: dir isL
  5686. \-/803: O: O1605 (predict-yes)
  5687. I see 1 and I'm going to do: predict-yes
  5688. ENV: Agent did: predict-yes for direction L in state State-B
  5689. In State-B moving L
  5690. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  5691. predict error 0
  5692. dir: dir isR
  5693. |\-804: O: O1607 (predict-yes)
  5694. I see 1 and I'm going to do: predict-yes
  5695. ENV: Agent did: predict-yes for direction R in state State-A
  5696. In State-A moving R
  5697. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  5698. predict error 0
  5699. dir: dir isL
  5700. /|805: O: O1609 (predict-yes)
  5701. I see 1 and I'm going to do: predict-yes
  5702. ENV: Agent did: predict-yes for direction L in state State-B
  5703. In State-B moving L
  5704. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  5705. predict error 0
  5706. dir: dir isU
  5707. \-/806: O: O1612 (predict-no)
  5708. I see 1 and I'm going to do: predict-no
  5709. ENV: Agent did: predict-no for direction U in state State-A
  5710. In State-A moving U
  5711. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  5712. predict error 0
  5713. dir: dir isR
  5714. |\807: O: O1613 (predict-yes)
  5715. I see 1 and I'm going to do: predict-yes
  5716. ENV: Agent did: predict-yes for direction R in state State-A
  5717. In State-A moving R
  5718. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  5719. predict error 0
  5720. dir: dir isU
  5721. -/|808: O: O1616 (predict-no)
  5722. I see 1 and I'm going to do: predict-no
  5723. ENV: Agent did: predict-no for direction U in state State-B
  5724. In State-B moving U
  5725. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5726. predict error 0
  5727. dir: dir isU
  5728. \-/809: O: O1618 (predict-no)
  5729. I see 1 and I'm going to do: predict-no
  5730. ENV: Agent did: predict-no for direction U in state State-B
  5731. In State-B moving U
  5732. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5733. predict error 0
  5734. dir: dir isR
  5735. |\810: O: O1620 (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 isL
  5742. -/|811: O: O1621 (predict-yes)
  5743. I see 1 and I'm going to do: predict-yes
  5744. ENV: Agent did: predict-yes for direction L in state State-B
  5745. In State-B moving L
  5746. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  5747. predict error 0
  5748. dir: dir isU
  5749. \812: O: O1624 (predict-no)
  5750. I see 1 and I'm going to do: predict-no
  5751. ENV: Agent did: predict-no for direction U in state State-A
  5752. In State-A moving U
  5753. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  5754. predict error 0
  5755. dir: dir isL
  5756. -813: O: O1626 (predict-no)
  5757. I see 1 and I'm going to do: predict-no
  5758. ENV: Agent did: predict-no for direction L in state State-A
  5759. In State-A moving L
  5760. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  5761. predict error 0
  5762. dir: dir isR
  5763. /|\-sleeping...
  5764. /814: O: O1627 (predict-yes)
  5765. I see 1 and I'm going to do: predict-yes
  5766. ENV: Agent did: predict-yes for direction R in state State-A
  5767. In State-A moving R
  5768. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  5769. predict error 0
  5770. dir: dir isU
  5771. |\815: O: O1630 (predict-no)
  5772. I see 1 and I'm going to do: predict-no
  5773. ENV: Agent did: predict-no for direction U in state State-B
  5774. In State-B moving U
  5775. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5776. predict error 0
  5777. dir: dir isL
  5778. -/|816: O: O1631 (predict-yes)
  5779. I see 1 and I'm going to do: predict-yes
  5780. ENV: Agent did: predict-yes for direction L in state State-B
  5781. In State-B moving L
  5782. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  5783. predict error 0
  5784. dir: dir isR
  5785. \-817: O: O1633 (predict-yes)
  5786. I see 1 and I'm going to do: predict-yes
  5787. ENV: Agent did: predict-yes for direction R in state State-A
  5788. In State-A moving R
  5789. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  5790. predict error 0
  5791. dir: dir isL
  5792. /|\818: O: O1635 (predict-yes)
  5793. I see 1 and I'm going to do: predict-yes
  5794. ENV: Agent did: predict-yes for direction L in state State-B
  5795. In State-B moving L
  5796. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  5797. predict error 0
  5798. dir: dir isL
  5799. -/|819: O: O1638 (predict-no)
  5800. I see 1 and I'm going to do: predict-no
  5801. ENV: Agent did: predict-no for direction L in state State-A
  5802. In State-A moving L
  5803. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  5804. predict error 0
  5805. dir: dir isU
  5806. \-/|820: O: O1640 (predict-no)
  5807. I see 1 and I'm going to do: predict-no
  5808. ENV: Agent did: predict-no for direction U in state State-A
  5809. In State-A moving U
  5810. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  5811. predict error 0
  5812. dir: dir isR
  5813. \-821: O: O1641 (predict-yes)
  5814. I see 1 and I'm going to do: predict-yes
  5815. ENV: Agent did: predict-yes for direction R in state State-A
  5816. In State-A moving R
  5817. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  5818. predict error 0
  5819. dir: dir isL
  5820. /822: O: O1643 (predict-yes)
  5821. I see 1 and I'm going to do: predict-yes
  5822. ENV: Agent did: predict-yes for direction L in state State-B
  5823. In State-B moving L
  5824. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  5825. predict error 0
  5826. dir: dir isR
  5827. |\-823: O: O1645 (predict-yes)
  5828. I see 1 and I'm going to do: predict-yes
  5829. ENV: Agent did: predict-yes for direction R in state State-A
  5830. In State-A moving R
  5831. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  5832. predict error 0
  5833. dir: dir isL
  5834. /|\824: O: O1647 (predict-yes)
  5835. I see 1 and I'm going to do: predict-yes
  5836. ENV: Agent did: predict-yes for direction L in state State-B
  5837. In State-B moving L
  5838. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  5839. predict error 0
  5840. dir: dir isL
  5841. -825: O: O1650 (predict-no)
  5842. I see 1 and I'm going to do: predict-no
  5843. ENV: Agent did: predict-no for direction L in state State-A
  5844. In State-A moving L
  5845. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  5846. predict error 0
  5847. dir: dir isR
  5848. /|826: O: O1651 (predict-yes)
  5849. I see 1 and I'm going to do: predict-yes
  5850. ENV: Agent did: predict-yes for direction R in state State-A
  5851. In State-A moving R
  5852. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  5853. predict error 0
  5854. dir: dir isU
  5855. \-/827: O: O1654 (predict-no)
  5856. I see 1 and I'm going to do: predict-no
  5857. ENV: Agent did: predict-no for direction U in state State-B
  5858. In State-B moving U
  5859. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5860. predict error 0
  5861. dir: dir isR
  5862. |\828: O: O1656 (predict-no)
  5863. I see 1 and I'm going to do: predict-no
  5864. ENV: Agent did: predict-no for direction R in state State-B
  5865. In State-B moving R
  5866. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5867. predict error 0
  5868. dir: dir isL
  5869. -/829: O: O1657 (predict-yes)
  5870. I see 1 and I'm going to do: predict-yes
  5871. ENV: Agent did: predict-yes for direction L in state State-B
  5872. In State-B moving L
  5873. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  5874. predict error 0
  5875. dir: dir isU
  5876. |\830: O: O1660 (predict-no)
  5877. I see 1 and I'm going to do: predict-no
  5878. ENV: Agent did: predict-no for direction U in state State-A
  5879. In State-A moving U
  5880. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  5881. predict error 0
  5882. dir: dir isU
  5883. -/831: O: O1662 (predict-no)
  5884. I see 1 and I'm going to do: predict-no
  5885. ENV: Agent did: predict-no for direction U in state State-A
  5886. In State-A moving U
  5887. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  5888. predict error 0
  5889. dir: dir isU
  5890. |832: O: O1664 (predict-no)
  5891. I see 1 and I'm going to do: predict-no
  5892. ENV: Agent did: predict-no for direction U in state State-A
  5893. In State-A moving U
  5894. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  5895. predict error 0
  5896. dir: dir isR
  5897. \-833: O: O1665 (predict-yes)
  5898. I see 1 and I'm going to do: predict-yes
  5899. ENV: Agent did: predict-yes for direction R in state State-A
  5900. In State-A moving R
  5901. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  5902. predict error 0
  5903. dir: dir isU
  5904. /834: O: O1668 (predict-no)
  5905. I see 1 and I'm going to do: predict-no
  5906. ENV: Agent did: predict-no for direction U in state State-B
  5907. In State-B moving U
  5908. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5909. predict error 0
  5910. dir: dir isL
  5911. |\835: O: O1669 (predict-yes)
  5912. I see 1 and I'm going to do: predict-yes
  5913. ENV: Agent did: predict-yes for direction L in state State-B
  5914. In State-B moving L
  5915. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  5916. predict error 0
  5917. dir: dir isU
  5918. -/|836: O: O1672 (predict-no)
  5919. I see 1 and I'm going to do: predict-no
  5920. ENV: Agent did: predict-no for direction U in state State-A
  5921. In State-A moving U
  5922. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  5923. predict error 0
  5924. dir: dir isU
  5925. \-837: O: O1674 (predict-no)
  5926. I see 1 and I'm going to do: predict-no
  5927. ENV: Agent did: predict-no for direction U in state State-A
  5928. In State-A moving U
  5929. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  5930. predict error 0
  5931. dir: dir isU
  5932. /|\838: O: O1676 (predict-no)
  5933. I see 1 and I'm going to do: predict-no
  5934. ENV: Agent did: predict-no for direction U in state State-A
  5935. In State-A moving U
  5936. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  5937. predict error 0
  5938. dir: dir isR
  5939. -/839: O: O1677 (predict-yes)
  5940. I see 1 and I'm going to do: predict-yes
  5941. ENV: Agent did: predict-yes for direction R in state State-A
  5942. In State-A moving R
  5943. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  5944. predict error 0
  5945. dir: dir isR
  5946. |\-840: O: O1680 (predict-no)
  5947. I see 1 and I'm going to do: predict-no
  5948. ENV: Agent did: predict-no for direction R in state State-B
  5949. In State-B moving R
  5950. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5951. predict error 0
  5952. dir: dir isR
  5953. /|841: O: O1682 (predict-no)
  5954. I see 1 and I'm going to do: predict-no
  5955. ENV: Agent did: predict-no for direction R in state State-B
  5956. In State-B moving R
  5957. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5958. predict error 0
  5959. dir: dir isU
  5960. \842: O: O1684 (predict-no)
  5961. I see 1 and I'm going to do: predict-no
  5962. ENV: Agent did: predict-no for direction U in state State-B
  5963. In State-B moving U
  5964. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5965. predict error 0
  5966. dir: dir isL
  5967. -/843: O: O1685 (predict-yes)
  5968. I see 1 and I'm going to do: predict-yes
  5969. ENV: Agent did: predict-yes for direction L in state State-B
  5970. In State-B moving L
  5971. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  5972. predict error 0
  5973. dir: dir isU
  5974. |\844: O: O1688 (predict-no)
  5975. I see 1 and I'm going to do: predict-no
  5976. ENV: Agent did: predict-no for direction U in state State-A
  5977. In State-A moving U
  5978. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  5979. predict error 0
  5980. dir: dir isR
  5981. -/|845: O: O1689 (predict-yes)
  5982. I see 1 and I'm going to do: predict-yes
  5983. ENV: Agent did: predict-yes for direction R in state State-A
  5984. In State-A moving R
  5985. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  5986. predict error 0
  5987. dir: dir isR
  5988. \-846: O: O1692 (predict-no)
  5989. I see 1 and I'm going to do: predict-no
  5990. ENV: Agent did: predict-no for direction R in state State-B
  5991. In State-B moving R
  5992. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5993. predict error 0
  5994. dir: dir isR
  5995. /|\847: O: O1694 (predict-no)
  5996. I see 1 and I'm going to do: predict-no
  5997. ENV: Agent did: predict-no for direction R in state State-B
  5998. In State-B moving R
  5999. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  6000. predict error 0
  6001. dir: dir isL
  6002. -/848: O: O1695 (predict-yes)
  6003. I see 1 and I'm going to do: predict-yes
  6004. ENV: Agent did: predict-yes for direction L in state State-B
  6005. In State-B moving L
  6006. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  6007. predict error 0
  6008. dir: dir isL
  6009. |\-849: O: O1698 (predict-no)
  6010. I see 1 and I'm going to do: predict-no
  6011. ENV: Agent did: predict-no for direction L in state State-A
  6012. In State-A moving L
  6013. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  6014. predict error 0
  6015. dir: dir isR
  6016. /|850: O: O1699 (predict-yes)
  6017. I see 1 and I'm going to do: predict-yes
  6018. ENV: Agent did: predict-yes for direction R in state State-A
  6019. In State-A moving R
  6020. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  6021. predict error 0
  6022. dir: dir isR
  6023. \-/851: O: O1702 (predict-no)
  6024. I see 1 and I'm going to do: predict-no
  6025. ENV: Agent did: predict-no for direction R in state State-B
  6026. In State-B moving R
  6027. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  6028. predict error 0
  6029. dir: dir isR
  6030. |852: O: O1704 (predict-no)
  6031. I see 1 and I'm going to do: predict-no
  6032. ENV: Agent did: predict-no for direction R in state State-B
  6033. In State-B moving R
  6034. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  6035. predict error 0
  6036. dir: dir isU
  6037. \-/853: O: O1706 (predict-no)
  6038. I see 1 and I'm going to do: predict-no
  6039. ENV: Agent did: predict-no for direction U in state State-B
  6040. In State-B moving U
  6041. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  6042. predict error 0
  6043. dir: dir isR
  6044. |\-854: O: O1708 (predict-no)
  6045. I see 1 and I'm going to do: predict-no
  6046. ENV: Agent did: predict-no for direction R in state State-B
  6047. In State-B moving R
  6048. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  6049. predict error 0
  6050. dir: dir isL
  6051. /|\-855: O: O1709 (predict-yes)
  6052. I see 1 and I'm going to do: predict-yes
  6053. ENV: Agent did: predict-yes for direction L in state State-B
  6054. In State-B moving L
  6055. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  6056. predict error 0
  6057. dir: dir isU
  6058. /856: O: O1712 (predict-no)
  6059. I see 1 and I'm going to do: predict-no
  6060. ENV: Agent did: predict-no for direction U in state State-A
  6061. In State-A moving U
  6062. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  6063. predict error 0
  6064. dir: dir isL
  6065. |\-857: O: O1714 (predict-no)
  6066. I see 1 and I'm going to do: predict-no
  6067. ENV: Agent did: predict-no for direction L in state State-A
  6068. In State-A moving L
  6069. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  6070. predict error 0
  6071. dir: dir isR
  6072. /|\858: O: O1715 (predict-yes)
  6073. I see 1 and I'm going to do: predict-yes
  6074. ENV: Agent did: predict-yes for direction R in state State-A
  6075. In State-A moving R
  6076. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  6077. predict error 0
  6078. dir: dir isU
  6079. -/859: O: O1718 (predict-no)
  6080. I see 1 and I'm going to do: predict-no
  6081. ENV: Agent did: predict-no for direction U in state State-B
  6082. In State-B moving U
  6083. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  6084. predict error 0
  6085. dir: dir isU
  6086. |\-860: O: O1720 (predict-no)
  6087. I see 1 and I'm going to do: predict-no
  6088. ENV: Agent did: predict-no for direction U in state State-B
  6089. In State-B moving U
  6090. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  6091. predict error 0
  6092. dir: dir isU
  6093. /|\861: O: O1722 (predict-no)
  6094. I see 1 and I'm going to do: predict-no
  6095. ENV: Agent did: predict-no for direction U in state State-B
  6096. In State-B moving U
  6097. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  6098. predict error 0
  6099. dir: dir isR
  6100. -862: O: O1724 (predict-no)
  6101. I see 1 and I'm going to do: predict-no
  6102. ENV: Agent did: predict-no for direction R in state State-B
  6103. In State-B moving R
  6104. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  6105. predict error 0
  6106. dir: dir isL
  6107. /|\863: O: O1725 (predict-yes)
  6108. I see 1 and I'm going to do: predict-yes
  6109. ENV: Agent did: predict-yes for direction L in state State-B
  6110. In State-B moving L
  6111. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  6112. predict error 0
  6113. dir: dir isL
  6114. -/|864: O: O1728 (predict-no)
  6115. I see 1 and I'm going to do: predict-no
  6116. ENV: Agent did: predict-no for direction L in state State-A
  6117. In State-A moving L
  6118. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  6119. predict error 0
  6120. dir: dir isU
  6121. \-/865: O: O1730 (predict-no)
  6122. I see 1 and I'm going to do: predict-no
  6123. ENV: Agent did: predict-no for direction U in state State-A
  6124. In State-A moving U
  6125. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  6126. predict error 0
  6127. dir: dir isU
  6128. |\-866: O: O1732 (predict-no)
  6129. I see 1 and I'm going to do: predict-no
  6130. ENV: Agent did: predict-no for direction U in state State-A
  6131. In State-A moving U
  6132. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  6133. predict error 0
  6134. dir: dir isR
  6135. /|867: O: O1733 (predict-yes)
  6136. I see 1 and I'm going to do: predict-yes
  6137. ENV: Agent did: predict-yes for direction R in state State-A
  6138. In State-A moving R
  6139. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  6140. predict error 0
  6141. dir: dir isR
  6142. \-/|868: O: O1736 (predict-no)
  6143. I see 1 and I'm going to do: predict-no
  6144. ENV: Agent did: predict-no for direction R in state State-B
  6145. In State-B moving R
  6146. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  6147. predict error 0
  6148. dir: dir isU
  6149. \-/869: O: O1738 (predict-no)
  6150. I see 1 and I'm going to do: predict-no
  6151. ENV: Agent did: predict-no for direction U in state State-B
  6152. In State-B moving U
  6153. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  6154. predict error 0
  6155. dir: dir isR
  6156. |\870: O: O1740 (predict-no)
  6157. I see 1 and I'm going to do: predict-no
  6158. ENV: Agent did: predict-no for direction R in state State-B
  6159. In State-B moving R
  6160. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  6161. predict error 0
  6162. dir: dir isL
  6163. -/871: O: O1741 (predict-yes)
  6164. I see 1 and I'm going to do: predict-yes
  6165. ENV: Agent did: predict-yes for direction L in state State-B
  6166. In State-B moving L
  6167. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  6168. predict error 0
  6169. dir: dir isU
  6170. |872: O: O1744 (predict-no)
  6171. I see 1 and I'm going to do: predict-no
  6172. ENV: Agent did: predict-no for direction U in state State-A
  6173. In State-A moving U
  6174. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  6175. predict error 0
  6176. dir: dir isL
  6177. \-/873: O: O1746 (predict-no)
  6178. I see 1 and I'm going to do: predict-no
  6179. ENV: Agent did: predict-no for direction L in state State-A
  6180. In State-A moving L
  6181. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  6182. predict error 0
  6183. dir: dir isR
  6184. |874: O: O1747 (predict-yes)
  6185. I see 1 and I'm going to do: predict-yes
  6186. ENV: Agent did: predict-yes for direction R in state State-A
  6187. In State-A moving R
  6188. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  6189. predict error 0
  6190. dir: dir isR
  6191. \875: O: O1750 (predict-no)
  6192. I see 1 and I'm going to do: predict-no
  6193. ENV: Agent did: predict-no for direction R in state State-B
  6194. In State-B moving R
  6195. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  6196. predict error 0
  6197. dir: dir isU
  6198. -876: O: O1752 (predict-no)
  6199. I see 1 and I'm going to do: predict-no
  6200. ENV: Agent did: predict-no for direction U in state State-B
  6201. In State-B moving U
  6202. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  6203. predict error 0
  6204. dir: dir isL
  6205. /|\877: O: O1753 (predict-yes)
  6206. I see 1 and I'm going to do: predict-yes
  6207. ENV: Agent did: predict-yes for direction L in state State-B
  6208. In State-B moving L
  6209. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  6210. predict error 0
  6211. dir: dir isL
  6212. -878: O: O1756 (predict-no)
  6213. I see 1 and I'm going to do: predict-no
  6214. ENV: Agent did: predict-no for direction L in state State-A
  6215. In State-A moving L
  6216. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  6217. predict error 0
  6218. dir: dir isR
  6219. /|\879: O: O1757 (predict-yes)
  6220. I see 1 and I'm going to do: predict-yes
  6221. ENV: Agent did: predict-yes for direction R in state State-A
  6222. In State-A moving R
  6223. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  6224. predict error 0
  6225. dir: dir isL
  6226. -/|880: O: O1759 (predict-yes)
  6227. I see 1 and I'm going to do: predict-yes
  6228. ENV: Agent did: predict-yes for direction L in state State-B
  6229. In State-B moving L
  6230. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  6231. predict error 0
  6232. dir: dir isL
  6233. \-/881: O: O1762 (predict-no)
  6234. I see 1 and I'm going to do: predict-no
  6235. ENV: Agent did: predict-no for direction L in state State-A
  6236. In State-A moving L
  6237. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  6238. predict error 0
  6239. dir: dir isL
  6240. |882: O: O1764 (predict-no)
  6241. I see 1 and I'm going to do: predict-no
  6242. ENV: Agent did: predict-no for direction L in state State-A
  6243. In State-A moving L
  6244. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  6245. predict error 0
  6246. dir: dir isR
  6247. \-/883: O: O1765 (predict-yes)
  6248. I see 1 and I'm going to do: predict-yes
  6249. ENV: Agent did: predict-yes for direction R in state State-A
  6250. In State-A moving R
  6251. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  6252. predict error 0
  6253. dir: dir isL
  6254. |\884: O: O1767 (predict-yes)
  6255. I see 1 and I'm going to do: predict-yes
  6256. ENV: Agent did: predict-yes for direction L in state State-B
  6257. In State-B moving L
  6258. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  6259. predict error 0
  6260. dir: dir isL
  6261. -/|885: O: O1770 (predict-no)
  6262. I see 1 and I'm going to do: predict-no
  6263. ENV: Agent did: predict-no for direction L in state State-A
  6264. In State-A moving L
  6265. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  6266. predict error 0
  6267. dir: dir isU
  6268. \-886: O: O1772 (predict-no)
  6269. I see 1 and I'm going to do: predict-no
  6270. ENV: Agent did: predict-no for direction U in state State-A
  6271. In State-A moving U
  6272. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  6273. predict error 0
  6274. dir: dir isR
  6275. /|887: O: O1773 (predict-yes)
  6276. I see 1 and I'm going to do: predict-yes
  6277. ENV: Agent did: predict-yes for direction R in state State-A
  6278. In State-A moving R
  6279. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  6280. predict error 0
  6281. dir: dir isU
  6282. \-888: O: O1776 (predict-no)
  6283. I see 1 and I'm going to do: predict-no
  6284. ENV: Agent did: predict-no for direction U in state State-B
  6285. In State-B moving U
  6286. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  6287. predict error 0
  6288. dir: dir isL
  6289. /|889: O: O1777 (predict-yes)
  6290. I see 1 and I'm going to do: predict-yes
  6291. ENV: Agent did: predict-yes for direction L in state State-B
  6292. In State-B moving L
  6293. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  6294. predict error 0
  6295. dir: dir isR
  6296. \-/|890: O: O1779 (predict-yes)
  6297. I see 1 and I'm going to do: predict-yes
  6298. ENV: Agent did: predict-yes for direction R in state State-A
  6299. In State-A moving R
  6300. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  6301. predict error 0
  6302. dir: dir isR
  6303. \-/891: O: O1782 (predict-no)
  6304. I see 1 and I'm going to do: predict-no
  6305. ENV: Agent did: predict-no for direction R in state State-B
  6306. In State-B moving R
  6307. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  6308. predict error 0
  6309. dir: dir isL
  6310. |892: O: O1783 (predict-yes)
  6311. I see 1 and I'm going to do: predict-yes
  6312. ENV: Agent did: predict-yes for direction L in state State-B
  6313. In State-B moving L
  6314. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  6315. predict error 0
  6316. dir: dir isL
  6317. \-893: O: O1786 (predict-no)
  6318. I see 1 and I'm going to do: predict-no
  6319. ENV: Agent did: predict-no for direction L in state State-A
  6320. In State-A moving L
  6321. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  6322. predict error 0
  6323. dir: dir isU
  6324. /|\894: O: O1788 (predict-no)
  6325. I see 1 and I'm going to do: predict-no
  6326. ENV: Agent did: predict-no for direction U in state State-A
  6327. In State-A moving U
  6328. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  6329. predict error 0
  6330. dir: dir isU
  6331. -895: O: O1790 (predict-no)
  6332. I see 1 and I'm going to do: predict-no
  6333. ENV: Agent did: predict-no for direction U in state State-A
  6334. In State-A moving U
  6335. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  6336. predict error 0
  6337. dir: dir isR
  6338. /|\896: O: O1791 (predict-yes)
  6339. I see 1 and I'm going to do: predict-yes
  6340. ENV: Agent did: predict-yes for direction R in state State-A
  6341. In State-A moving R
  6342. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  6343. predict error 0
  6344. dir: dir isR
  6345. -/|897: O: O1794 (predict-no)
  6346. I see 1 and I'm going to do: predict-no
  6347. ENV: Agent did: predict-no for direction R in state State-B
  6348. In State-B moving R
  6349. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  6350. predict error 0
  6351. dir: dir isL
  6352. \-/898: O: O1795 (predict-yes)
  6353. I see 1 and I'm going to do: predict-yes
  6354. ENV: Agent did: predict-yes for direction L in state State-B
  6355. In State-B moving L
  6356. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  6357. predict error 0
  6358. dir: dir isR
  6359. |\-899: O: O1797 (predict-yes)
  6360. I see 1 and I'm going to do: predict-yes
  6361. ENV: Agent did: predict-yes for direction R in state State-A
  6362. In State-A moving R
  6363. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  6364. predict error 0
  6365. dir: dir isU
  6366. /|\900: O: O1800 (predict-no)
  6367. I see 1 and I'm going to do: predict-no
  6368. ENV: Agent did: predict-no for direction U in state State-B
  6369. In State-B moving U
  6370. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  6371. predict error 0
  6372. dir: dir isU
  6373. -/|901: O: O1802 (predict-no)
  6374. I see 1 and I'm going to do: predict-no
  6375. ENV: Agent did: predict-no for direction U in state State-B
  6376. In State-B moving U
  6377. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  6378. predict error 0
  6379. dir: dir isR
  6380. \902: O: O1804 (predict-no)
  6381. I see 1 and I'm going to do: predict-no
  6382. ENV: Agent did: predict-no for direction R in state State-B
  6383. In State-B moving R
  6384. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  6385. predict error 0
  6386. dir: dir isL
  6387. -/|903: O: O1805 (predict-yes)
  6388. I see 1 and I'm going to do: predict-yes
  6389. ENV: Agent did: predict-yes for direction L in state State-B
  6390. In State-B moving L
  6391. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  6392. predict error 0
  6393. dir: dir isU
  6394. \-/904: O: O1808 (predict-no)
  6395. I see 1 and I'm going to do: predict-no
  6396. ENV: Agent did: predict-no for direction U in state State-A
  6397. In State-A moving U
  6398. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  6399. predict error 0
  6400. dir: dir isR
  6401. |\-905: O: O1809 (predict-yes)
  6402. I see 1 and I'm going to do: predict-yes
  6403. ENV: Agent did: predict-yes for direction R in state State-A
  6404. In State-A moving R
  6405. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  6406. predict error 0
  6407. dir: dir isR
  6408. /|906: O: O1812 (predict-no)
  6409. I see 1 and I'm going to do: predict-no
  6410. ENV: Agent did: predict-no for direction R in state State-B
  6411. In State-B moving R
  6412. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  6413. predict error 0
  6414. dir: dir isL
  6415. \-/907: O: O1813 (predict-yes)
  6416. I see 1 and I'm going to do: predict-yes
  6417. ENV: Agent did: predict-yes for direction L in state State-B
  6418. In State-B moving L
  6419. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  6420. predict error 0
  6421. dir: dir isL
  6422. |908: O: O1816 (predict-no)
  6423. I see 1 and I'm going to do: predict-no
  6424. ENV: Agent did: predict-no for direction L in state State-A
  6425. In State-A moving L
  6426. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  6427. predict error 0
  6428. dir: dir isU
  6429. \-/909: O: O1818 (predict-no)
  6430. I see 1 and I'm going to do: predict-no
  6431. ENV: Agent did: predict-no for direction U in state State-A
  6432. In State-A moving U
  6433. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  6434. predict error 0
  6435. dir: dir isR
  6436. |\-910: O: O1819 (predict-yes)
  6437. I see 1 and I'm going to do: predict-yes
  6438. ENV: Agent did: predict-yes for direction R in state State-A
  6439. In State-A moving R
  6440. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  6441. predict error 0
  6442. dir: dir isU
  6443. /911: O: O1822 (predict-no)
  6444. I see 1 and I'm going to do: predict-no
  6445. ENV: Agent did: predict-no for direction U in state State-B
  6446. In State-B moving U
  6447. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  6448. predict error 0
  6449. dir: dir isL
  6450. |912: O: O1823 (predict-yes)
  6451. I see 1 and I'm going to do: predict-yes
  6452. ENV: Agent did: predict-yes for direction L in state State-B
  6453. In State-B moving L
  6454. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  6455. predict error 0
  6456. dir: dir isL
  6457. \-/913: O: O1826 (predict-no)
  6458. I see 1 and I'm going to do: predict-no
  6459. ENV: Agent did: predict-no for direction L in state State-A
  6460. In State-A moving L
  6461. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  6462. predict error 0
  6463. dir: dir isU
  6464. |\-914: O: O1828 (predict-no)
  6465. I see 1 and I'm going to do: predict-no
  6466. ENV: Agent did: predict-no for direction U in state State-A
  6467. In State-A moving U
  6468. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  6469. predict error 0
  6470. dir: dir isU
  6471. /|\-915: O: O1830 (predict-no)
  6472. I see 1 and I'm going to do: predict-no
  6473. ENV: Agent did: predict-no for direction U in state State-A
  6474. In State-A moving U
  6475. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  6476. predict error 0
  6477. dir: dir isL
  6478. /|\916: O: O1832 (predict-no)
  6479. I see 1 and I'm going to do: predict-no
  6480. ENV: Agent did: predict-no for direction L in state State-A
  6481. In State-A moving L
  6482. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  6483. predict error 0
  6484. dir: dir isL
  6485. -/|917: O: O1834 (predict-no)
  6486. I see 1 and I'm going to do: predict-no
  6487. ENV: Agent did: predict-no for direction L in state State-A
  6488. In State-A moving L
  6489. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  6490. predict error 0
  6491. dir: dir isU
  6492. \-918: O: O1836 (predict-no)
  6493. I see 1 and I'm going to do: predict-no
  6494. ENV: Agent did: predict-no for direction U in state State-A
  6495. In State-A moving U
  6496. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  6497. predict error 0
  6498. dir: dir isL
  6499. /|\919: O: O1838 (predict-no)
  6500. I see 1 and I'm going to do: predict-no
  6501. ENV: Agent did: predict-no for direction L in state State-A
  6502. In State-A moving L
  6503. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  6504. predict error 0
  6505. dir: dir isU
  6506. -920: O: O1840 (predict-no)
  6507. I see 1 and I'm going to do: predict-no
  6508. ENV: Agent did: predict-no for direction U in state State-A
  6509. In State-A moving U
  6510. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  6511. predict error 0
  6512. dir: dir isU
  6513. /|\921: O: O1842 (predict-no)
  6514. I see 1 and I'm going to do: predict-no
  6515. ENV: Agent did: predict-no for direction U in state State-A
  6516. In State-A moving U
  6517. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  6518. predict error 0
  6519. dir: dir isL
  6520. -922: O: O1844 (predict-no)
  6521. I see 1 and I'm going to do: predict-no
  6522. ENV: Agent did: predict-no for direction L in state State-A
  6523. In State-A moving L
  6524. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  6525. predict error 0
  6526. dir: dir isL
  6527. /|923: O: O1846 (predict-no)
  6528. I see 1 and I'm going to do: predict-no
  6529. ENV: Agent did: predict-no for direction L in state State-A
  6530. In State-A moving L
  6531. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  6532. predict error 0
  6533. dir: dir isU
  6534. \-924: O: O1848 (predict-no)
  6535. I see 1 and I'm going to do: predict-no
  6536. ENV: Agent did: predict-no for direction U in state State-A
  6537. In State-A moving U
  6538. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  6539. predict error 0
  6540. dir: dir isR
  6541. /|925: O: O1849 (predict-yes)
  6542. I see 1 and I'm going to do: predict-yes
  6543. ENV: Agent did: predict-yes for direction R in state State-A
  6544. In State-A moving R
  6545. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  6546. predict error 0
  6547. dir: dir isR
  6548. \-/926: O: O1852 (predict-no)
  6549. I see 1 and I'm going to do: predict-no
  6550. ENV: Agent did: predict-no for direction R in state State-B
  6551. In State-B moving R
  6552. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  6553. predict error 0
  6554. dir: dir isR
  6555. |\-927: O: O1854 (predict-no)
  6556. I see 1 and I'm going to do: predict-no
  6557. ENV: Agent did: predict-no for direction R in state State-B
  6558. In State-B moving R
  6559. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  6560. predict error 0
  6561. dir: dir isL
  6562. /|\928: O: O1855 (predict-yes)
  6563. I see 1 and I'm going to do: predict-yes
  6564. ENV: Agent did: predict-yes for direction L in state State-B
  6565. In State-B moving L
  6566. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  6567. predict error 0
  6568. dir: dir isR
  6569. -/929: O: O1857 (predict-yes)
  6570. I see 1 and I'm going to do: predict-yes
  6571. ENV: Agent did: predict-yes for direction R in state State-A
  6572. In State-A moving R
  6573. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  6574. predict error 0
  6575. dir: dir isL
  6576. |\930: O: O1859 (predict-yes)
  6577. I see 1 and I'm going to do: predict-yes
  6578. ENV: Agent did: predict-yes for direction L in state State-B
  6579. In State-B moving L
  6580. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  6581. predict error 0
  6582. dir: dir isU
  6583. -/931: O: O1862 (predict-no)
  6584. I see 1 and I'm going to do: predict-no
  6585. ENV: Agent did: predict-no for direction U in state State-A
  6586. In State-A moving U
  6587. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  6588. predict error 0
  6589. dir: dir isU
  6590. |932: O: O1864 (predict-no)
  6591. I see 1 and I'm going to do: predict-no
  6592. ENV: Agent did: predict-no for direction U in state State-A
  6593. In State-A moving U
  6594. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  6595. predict error 0
  6596. dir: dir isL
  6597. \-/933: O: O1866 (predict-no)
  6598. I see 1 and I'm going to do: predict-no
  6599. ENV: Agent did: predict-no for direction L in state State-A
  6600. In State-A moving L
  6601. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  6602. predict error 0
  6603. dir: dir isU
  6604. |\-934: O: O1868 (predict-no)
  6605. I see 1 and I'm going to do: predict-no
  6606. ENV: Agent did: predict-no for direction U in state State-A
  6607. In State-A moving U
  6608. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  6609. predict error 0
  6610. dir: dir isL
  6611. /|935: O: O1870 (predict-no)
  6612. I see 1 and I'm going to do: predict-no
  6613. ENV: Agent did: predict-no for direction L in state State-A
  6614. In State-A moving L
  6615. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  6616. predict error 0
  6617. dir: dir isL
  6618. \-936: O: O1872 (predict-no)
  6619. I see 1 and I'm going to do: predict-no
  6620. ENV: Agent did: predict-no for direction L in state State-A
  6621. In State-A moving L
  6622. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  6623. predict error 0
  6624. dir: dir isL
  6625. /|937: O: O1874 (predict-no)
  6626. I see 1 and I'm going to do: predict-no
  6627. ENV: Agent did: predict-no for direction L in state State-A
  6628. In State-A moving L
  6629. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  6630. predict error 0
  6631. dir: dir isL
  6632. \-938: O: O1876 (predict-no)
  6633. I see 1 and I'm going to do: predict-no
  6634. ENV: Agent did: predict-no for direction L in state State-A
  6635. In State-A moving L
  6636. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  6637. predict error 0
  6638. dir: dir isL
  6639. /|\939: O: O1878 (predict-no)
  6640. I see 1 and I'm going to do: predict-no
  6641. ENV: Agent did: predict-no for direction L in state State-A
  6642. In State-A moving L
  6643. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  6644. predict error 0
  6645. dir: dir isR
  6646. -/940: O: O1879 (predict-yes)
  6647. I see 1 and I'm going to do: predict-yes
  6648. ENV: Agent did: predict-yes for direction R in state State-A
  6649. In State-A moving R
  6650. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  6651. predict error 0
  6652. dir: dir isU
  6653. |\-/941: O: O1882 (predict-no)
  6654. I see 1 and I'm going to do: predict-no
  6655. ENV: Agent did: predict-no for direction U in state State-B
  6656. In State-B moving U
  6657. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  6658. predict error 0
  6659. dir: dir isR
  6660. |942: O: O1884 (predict-no)
  6661. I see 1 and I'm going to do: predict-no
  6662. ENV: Agent did: predict-no for direction R in state State-B
  6663. In State-B moving R
  6664. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  6665. predict error 0
  6666. dir: dir isL
  6667. \-943: O: O1885 (predict-yes)
  6668. I see 1 and I'm going to do: predict-yes
  6669. ENV: Agent did: predict-yes for direction L in state State-B
  6670. In State-B moving L
  6671. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  6672. predict error 0
  6673. dir: dir isR
  6674. /|944: O: O1887 (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 isR
  6681. \-945: O: O1890 (predict-no)
  6682. I see 1 and I'm going to do: predict-no
  6683. ENV: Agent did: predict-no for direction R in state State-B
  6684. In State-B moving R
  6685. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  6686. predict error 0
  6687. dir: dir isL
  6688. /|946: O: O1891 (predict-yes)
  6689. I see 1 and I'm going to do: predict-yes
  6690. ENV: Agent did: predict-yes for direction L in state State-B
  6691. In State-B moving L
  6692. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  6693. predict error 0
  6694. dir: dir isU
  6695. \-/947: O: O1894 (predict-no)
  6696. I see 1 and I'm going to do: predict-no
  6697. ENV: Agent did: predict-no for direction U in state State-A
  6698. In State-A moving U
  6699. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  6700. predict error 0
  6701. dir: dir isR
  6702. |\-948: O: O1895 (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 isU
  6709. /|\949: O: O1898 (predict-no)
  6710. I see 1 and I'm going to do: predict-no
  6711. ENV: Agent did: predict-no for direction U in state State-B
  6712. In State-B moving U
  6713. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  6714. predict error 0
  6715. dir: dir isU
  6716. -/950: O: O1900 (predict-no)
  6717. I see 1 and I'm going to do: predict-no
  6718. ENV: Agent did: predict-no for direction U in state State-B
  6719. In State-B moving U
  6720. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  6721. predict error 0
  6722. dir: dir isR
  6723. |\-/|\-/|\-/|--- Input Phase ---
  6724. =>WM: (13382: I2 ^dir R)
  6725. =>WM: (13381: I2 ^reward 1)
  6726. =>WM: (13380: I2 ^see 0)
  6727. =>WM: (13379: N950 ^status complete)
  6728. <=WM: (13368: I2 ^dir U)
  6729. <=WM: (13367: I2 ^reward 1)
  6730. <=WM: (13366: I2 ^see 0)
  6731. =>WM: (13383: I2 ^level-1 R1-root)
  6732. <=WM: (13369: I2 ^level-1 R1-root)
  6733. --- END Input Phase ---
  6734. --- Proposal Phase ---
  6735. --- Inner Elaboration Phase, active level 1 (S1) ---
  6736. Firing rl*prefer*rvt*predict-yes*H0*3*v1*H1*37
  6737. -->
  6738. (S1 ^operator O1899 = -0.3011268063455669)
  6739. Firing rl*prefer*rvt*predict-no*H0*4*v1*H1*36
  6740. -->
  6741. (S1 ^operator O1900 = 0.7427516277634807)
  6742. Firing prefer*rvt*predict-no*H0*4*v1*H1
  6743. -->
  6744. Firing prefer*rvt*predict-yes*H0*3*v1*H1
  6745. -->
  6746. Firing elaborate*copy-see-to-output-link
  6747. -->
  6748. (I3 ^see 0 +)
  6749. Firing elaborate*reward*based*on*reward
  6750. -->
  6751. (R954 ^value 1 +)
  6752. (R1 ^reward R954 +)
  6753. Firing propose*predict-yes
  6754. -->
  6755. (O1901 ^name predict-yes +)
  6756. (S1 ^operator O1901 +)
  6757. Firing propose*predict-no
  6758. -->
  6759. (O1902 ^name predict-no +)
  6760. (S1 ^operator O1902 +)
  6761. Firing rl*prefer*rvt*predict-no*H0*4
  6762. -->
  6763. (S1 ^operator O1900 = 0.2572472160770417)
  6764. Firing rl*prefer*rvt*predict-yes*H0*3
  6765. -->
  6766. (S1 ^operator O1899 = 0.736829027581098)
  6767. Firing prefer*rvt*predict-yes*H0
  6768. -->
  6769. Firing prefer*rvt*predict-no*H0
  6770. -->
  6771. Firing elaborate*copy-dir-to-output-link
  6772. -->
  6773. (I3 ^dir R +)
  6774. inner elaboration loop at bottom goal.
  6775. Retracting elaborate*copy-see-to-output-link
  6776. -->
  6777. (I3 ^see 0 +)
  6778. Retracting propose*predict-no
  6779. -->
  6780. (O1900 ^name predict-no +)
  6781. (S1 ^operator O1900 +)
  6782. Retracting propose*predict-yes
  6783. -->
  6784. (O1899 ^name predict-yes +)
  6785. (S1 ^operator O1899 +)
  6786. Retracting elaborate*reward*based*on*reward
  6787. -->
  6788. (R953 ^value 1 +)
  6789. (R1 ^reward R953 +)
  6790. Retracting elaborate*copy-dir-to-output-link
  6791. -->
  6792. (I3 ^dir U +)
  6793. Retracting rl*prefer*rvt*predict-no*H0*2
  6794. -->
  6795. (S1 ^operator O1900 = 0.9999999999999999)
  6796. Retracting rl*prefer*rvt*predict-yes*H0*1
  6797. -->
  6798. (S1 ^operator O1899 = 0.)
  6799. =>WM: (13390: S1 ^operator O1902 +)
  6800. =>WM: (13389: S1 ^operator O1901 +)
  6801. =>WM: (13388: I3 ^dir R)
  6802. =>WM: (13387: O1902 ^name predict-no)
  6803. =>WM: (13386: O1901 ^name predict-yes)
  6804. =>WM: (13385: R954 ^value 1)
  6805. =>WM: (13384: R1 ^reward R954)
  6806. <=WM: (13375: S1 ^operator O1899 +)
  6807. <=WM: (13376: S1 ^operator O1900 +)
  6808. <=WM: (13377: S1 ^operator O1900)
  6809. <=WM: (13360: I3 ^dir U)
  6810. <=WM: (13371: R1 ^reward R953)
  6811. <=WM: (13374: O1900 ^name predict-no)
  6812. <=WM: (13373: O1899 ^name predict-yes)
  6813. <=WM: (13372: R953 ^value 1)
  6814. --- Inner Elaboration Phase, active level 1 (S1) ---
  6815. Firing prefer*rvt*predict-yes*H0
  6816. -->
  6817. Firing rl*prefer*rvt*predict-yes*H0*3*v1*H1*37
  6818. -->
  6819. (S1 ^operator O1901 = -0.3011268063455669)
  6820. Firing rl*prefer*rvt*predict-yes*H0*3
  6821. -->
  6822. (S1 ^operator O1901 = 0.736829027581098)
  6823. Firing prefer*rvt*predict-yes*H0*3*v1*H1
  6824. -->
  6825. Firing prefer*rvt*predict-no*H0
  6826. -->
  6827. Firing rl*prefer*rvt*predict-no*H0*4*v1*H1*36
  6828. -->
  6829. (S1 ^operator O1902 = 0.7427516277634807)
  6830. Firing rl*prefer*rvt*predict-no*H0*4
  6831. -->
  6832. (S1 ^operator O1902 = 0.2572472160770417)
  6833. Firing prefer*rvt*predict-no*H0*4*v1*H1
  6834. -->
  6835. inner elaboration loop at bottom goal.
  6836. Retracting rl*prefer*rvt*predict-no*H0*4
  6837. -->
  6838. (S1 ^operator O1900 = 0.2572472160770417)
  6839. Retracting rl*prefer*rvt*predict-no*H0*4*v1*H1*36
  6840. -->
  6841. (S1 ^operator O1900 = 0.7427516277634807)
  6842. Retracting rl*prefer*rvt*predict-yes*H0*3
  6843. -->
  6844. (S1 ^operator O1899 = 0.736829027581098)
  6845. Retracting rl*prefer*rvt*predict-yes*H0*3*v1*H1*37
  6846. -->
  6847. (S1 ^operator O1899 = -0.3011268063455669)
  6848. --- END Proposal Phase ---
  6849. --- Decision Phase ---
  6850. RL update rl*prefer*rvt*predict-no*H0*2 1 0 1 -> 1 0 1(R,m,v=1,1,0)
  6851. =>WM: (13391: S1 ^operator O1902)
  6852. 951: O: O1902 (predict-no)
  6853. --- END Decision Phase ---
  6854. --- Application Phase ---
  6855. --- Firing Productions (PE) For State At Depth 1 ---
  6856. --- Inner Elaboration Phase, active level 1 (S1) ---
  6857. Firing apply*operator
  6858. -->
  6859. (I3 ^predict-no N951 + :O )
  6860. Firing apply*operator*complete
  6861. -->
  6862. (I3 ^predict-no N950 - :O )
  6863. inner elaboration loop at bottom goal.
  6864. --- Change Working Memory (PE) ---
  6865. =>WM: (13392: I3 ^predict-no N951)
  6866. <=WM: (13379: N950 ^status complete)
  6867. <=WM: (13378: I3 ^predict-no N950)
  6868. --- Firing Productions (IE) For State At Depth 1 ---
  6869. --- Inner Elaboration Phase, active level 1 (S1) ---
  6870. Firing monitor*world
  6871. -->
  6872. I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
  6873. --- Change Working Memory (IE) ---
  6874. --- END Application Phase ---
  6875. --- Output Phase ---
  6876. ENV: Agent did: predict-no for direction R in state State-B
  6877. In State-B moving R
  6878. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  6879. predict error 0
  6880. dir: dir isL
  6881. --- END Output Phase ---
  6882. \--- Input Phase ---
  6883. =>WM: (13396: I2 ^dir L)
  6884. =>WM: (13395: I2 ^reward 1)
  6885. =>WM: (13394: I2 ^see 0)
  6886. =>WM: (13393: N951 ^status complete)
  6887. <=WM: (13382: I2 ^dir R)
  6888. <=WM: (13381: I2 ^reward 1)
  6889. <=WM: (13380: I2 ^see 0)
  6890. =>WM: (13397: I2 ^level-1 R0-root)
  6891. <=WM: (13383: I2 ^level-1 R1-root)
  6892. --- END Input Phase ---
  6893. --- Proposal Phase ---
  6894. --- Inner Elaboration Phase, active level 1 (S1) ---
  6895. Firing rl*prefer*rvt*predict-no*H0*6*v1*H1*38
  6896. -->
  6897. (S1 ^operator O1902 = 0.04178081990804111)
  6898. Firing rl*prefer*rvt*predict-yes*H0*5*v1*H1*30
  6899. -->
  6900. (S1 ^operator O1901 = 0.5681127864180794)
  6901. Firing prefer*rvt*predict-no*H0*6*v1*H1
  6902. -->
  6903. Firing prefer*rvt*predict-yes*H0*5*v1*H1
  6904. -->
  6905. Firing elaborate*copy-see-to-output-link
  6906. -->
  6907. (I3 ^see 0 +)
  6908. Firing elaborate*reward*based*on*reward
  6909. -->
  6910. (R955 ^value 1 +)
  6911. (R1 ^reward R955 +)
  6912. Firing propose*predict-yes
  6913. -->
  6914. (O1903 ^name predict-yes +)
  6915. (S1 ^operator O1903 +)
  6916. Firing propose*predict-no
  6917. -->
  6918. (O1904 ^name predict-no +)
  6919. (S1 ^operator O1904 +)
  6920. Firing rl*prefer*rvt*predict-no*H0*6
  6921. -->
  6922. (S1 ^operator O1902 = 0.3289450941277776)
  6923. Firing rl*prefer*rvt*predict-yes*H0*5
  6924. -->
  6925. (S1 ^operator O1901 = 0.43188926143453)
  6926. Firing prefer*rvt*predict-yes*H0
  6927. -->
  6928. Firing prefer*rvt*predict-no*H0
  6929. -->
  6930. Firing elaborate*copy-dir-to-output-link
  6931. -->
  6932. (I3 ^dir L +)
  6933. inner elaboration loop at bottom goal.
  6934. Retracting elaborate*copy-see-to-output-link
  6935. -->
  6936. (I3 ^see 0 +)
  6937. Retracting propose*predict-no
  6938. -->
  6939. (O1902 ^name predict-no +)
  6940. (S1 ^operator O1902 +)
  6941. Retracting propose*predict-yes
  6942. -->
  6943. (O1901 ^name predict-yes +)
  6944. (S1 ^operator O1901 +)
  6945. Retracting elaborate*reward*based*on*reward
  6946. -->
  6947. (R954 ^value 1 +)
  6948. (R1 ^reward R954 +)
  6949. Retracting elaborate*copy-dir-to-output-link
  6950. -->
  6951. (I3 ^dir R +)
  6952. Retracting rl*prefer*rvt*predict-no*H0*4
  6953. -->
  6954. (S1 ^operator O1902 = 0.2572472160770417)
  6955. Retracting rl*prefer*rvt*predict-no*H0*4*v1*H1*36
  6956. -->
  6957. (S1 ^operator O1902 = 0.7427516277634807)
  6958. Retracting rl*prefer*rvt*predict-yes*H0*3
  6959. -->
  6960. (S1 ^operator O1901 = 0.736829027581098)
  6961. Retracting rl*prefer*rvt*predict-yes*H0*3*v1*H1*37
  6962. -->
  6963. (S1 ^operator O1901 = -0.3011268063455669)
  6964. =>WM: (13404: S1 ^operator O1904 +)
  6965. =>WM: (13403: S1 ^operator O1903 +)
  6966. =>WM: (13402: I3 ^dir L)
  6967. =>WM: (13401: O1904 ^name predict-no)
  6968. =>WM: (13400: O1903 ^name predict-yes)
  6969. =>WM: (13399: R955 ^value 1)
  6970. =>WM: (13398: R1 ^reward R955)
  6971. <=WM: (13389: S1 ^operator O1901 +)
  6972. <=WM: (13390: S1 ^operator O1902 +)
  6973. <=WM: (13391: S1 ^operator O1902)
  6974. <=WM: (13388: I3 ^dir R)
  6975. <=WM: (13384: R1 ^reward R954)
  6976. <=WM: (13387: O1902 ^name predict-no)
  6977. <=WM: (13386: O1901 ^name predict-yes)
  6978. <=WM: (13385: R954 ^value 1)
  6979. --- Inner Elaboration Phase, active level 1 (S1) ---
  6980. Firing prefer*rvt*predict-yes*H0
  6981. -->
  6982. Firing rl*prefer*rvt*predict-yes*H0*5
  6983. -->
  6984. (S1 ^operator O1903 = 0.43188926143453)
  6985. Firing prefer*rvt*predict-yes*H0*5*v1*H1
  6986. -->
  6987. Firing rl*prefer*rvt*predict-yes*H0*5*v1*H1*30
  6988. -->
  6989. (S1 ^operator O1903 = 0.5681127864180794)
  6990. Firing prefer*rvt*predict-no*H0
  6991. -->
  6992. Firing rl*prefer*rvt*predict-no*H0*6
  6993. -->
  6994. (S1 ^operator O1904 = 0.3289450941277776)
  6995. Firing prefer*rvt*predict-no*H0*6*v1*H1
  6996. -->
  6997. Firing rl*prefer*rvt*predict-no*H0*6*v1*H1*38
  6998. -->
  6999. (S1 ^operator O1904 = 0.04178081990804111)
  7000. inner elaboration loop at bottom goal.
  7001. Retracting rl*prefer*rvt*predict-no*H0*6
  7002. -->
  7003. (S1 ^operator O1902 = 0.3289450941277776)
  7004. Retracting rl*prefer*rvt*predict-no*H0*6*v1*H1*38
  7005. -->
  7006. (S1 ^operator O1902 = 0.04178081990804111)
  7007. Retracting rl*prefer*rvt*predict-yes*H0*5
  7008. -->
  7009. (S1 ^operator O1901 = 0.43188926143453)
  7010. Retracting rl*prefer*rvt*predict-yes*H0*5*v1*H1*30
  7011. -->
  7012. (S1 ^operator O1901 = 0.5681127864180794)
  7013. --- END Proposal Phase ---
  7014. --- Decision Phase ---
  7015. RL update rl*prefer*rvt*predict-no*H0*4 0.586137 -0.32889 0.257247 -> 0.586137 -0.32889 0.257247(R,m,v=1,0.854545,0.125055)
  7016. RL update rl*prefer*rvt*predict-no*H0*4*v1*H1*36 0.413862 0.32889 0.742752 -> 0.413862 0.32889 0.742752(R,m,v=1,1,0)
  7017. =>WM: (13405: S1 ^operator O1903)
  7018. 952: O: O1903 (predict-yes)
  7019. --- END Decision Phase ---
  7020. --- Application Phase ---
  7021. --- Firing Productions (PE) For State At Depth 1 ---
  7022. --- Inner Elaboration Phase, active level 1 (S1) ---
  7023. Firing apply*operator
  7024. -->
  7025. (I3 ^predict-yes N952 + :O )
  7026. Firing apply*operator*complete
  7027. -->
  7028. (I3 ^predict-no N951 - :O )
  7029. inner elaboration loop at bottom goal.
  7030. --- Change Working Memory (PE) ---
  7031. =>WM: (13406: I3 ^predict-yes N952)
  7032. <=WM: (13393: N951 ^status complete)
  7033. <=WM: (13392: I3 ^predict-no N951)
  7034. --- Firing Productions (IE) For State At Depth 1 ---
  7035. --- Inner Elaboration Phase, active level 1 (S1) ---
  7036. Firing monitor*world
  7037. -->
  7038. I see 1 and I'm going to do: predict-yes inner elaboration loop at bottom goal.
  7039. --- Change Working Memory (IE) ---
  7040. --- END Application Phase ---
  7041. --- Output Phase ---
  7042. ENV: Agent did: predict-yes for direction L in state State-B
  7043. In State-B moving L
  7044. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  7045. predict error 0
  7046. dir: dir isU
  7047. --- END Output Phase ---
  7048. -/|--- Input Phase ---
  7049. =>WM: (13410: I2 ^dir U)
  7050. =>WM: (13409: I2 ^reward 1)
  7051. =>WM: (13408: I2 ^see 1)
  7052. =>WM: (13407: N952 ^status complete)
  7053. <=WM: (13396: I2 ^dir L)
  7054. <=WM: (13395: I2 ^reward 1)
  7055. <=WM: (13394: I2 ^see 0)
  7056. =>WM: (13411: I2 ^level-1 L1-root)
  7057. <=WM: (13397: I2 ^level-1 R0-root)
  7058. --- END Input Phase ---
  7059. --- Proposal Phase ---
  7060. --- Inner Elaboration Phase, active level 1 (S1) ---
  7061. Firing elaborate*copy-see-to-output-link
  7062. -->
  7063. (I3 ^see 1 +)
  7064. Firing elaborate*reward*based*on*reward
  7065. -->
  7066. (R956 ^value 1 +)
  7067. (R1 ^reward R956 +)
  7068. Firing propose*predict-yes
  7069. -->
  7070. (O1905 ^name predict-yes +)
  7071. (S1 ^operator O1905 +)
  7072. Firing propose*predict-no
  7073. -->
  7074. (O1906 ^name predict-no +)
  7075. (S1 ^operator O1906 +)
  7076. Firing rl*prefer*rvt*predict-no*H0*2
  7077. -->
  7078. (S1 ^operator O1904 = 0.9999999999999999)
  7079. Firing rl*prefer*rvt*predict-yes*H0*1
  7080. -->
  7081. (S1 ^operator O1903 = 0.)
  7082. Firing prefer*rvt*predict-yes*H0
  7083. -->
  7084. Firing prefer*rvt*predict-no*H0
  7085. -->
  7086. Firing elaborate*copy-dir-to-output-link
  7087. -->
  7088. (I3 ^dir U +)
  7089. inner elaboration loop at bottom goal.
  7090. Retracting elaborate*copy-see-to-output-link
  7091. -->
  7092. (I3 ^see 0 +)
  7093. Retracting propose*predict-no
  7094. -->
  7095. (O1904 ^name predict-no +)
  7096. (S1 ^operator O1904 +)
  7097. Retracting propose*predict-yes
  7098. -->
  7099. (O1903 ^name predict-yes +)
  7100. (S1 ^operator O1903 +)
  7101. Retracting elaborate*reward*based*on*reward
  7102. -->
  7103. (R955 ^value 1 +)
  7104. (R1 ^reward R955 +)
  7105. Retracting elaborate*copy-dir-to-output-link
  7106. -->
  7107. (I3 ^dir L +)
  7108. Retracting rl*prefer*rvt*predict-no*H0*6*v1*H1*38
  7109. -->
  7110. (S1 ^operator O1904 = 0.04178081990804111)
  7111. Retracting rl*prefer*rvt*predict-no*H0*6
  7112. -->
  7113. (S1 ^operator O1904 = 0.3289450941277776)
  7114. Retracting rl*prefer*rvt*predict-yes*H0*5*v1*H1*30
  7115. -->
  7116. (S1 ^operator O1903 = 0.5681127864180794)
  7117. Retracting rl*prefer*rvt*predict-yes*H0*5
  7118. -->
  7119. (S1 ^operator O1903 = 0.43188926143453)
  7120. =>WM: (13419: S1 ^operator O1906 +)
  7121. =>WM: (13418: S1 ^operator O1905 +)
  7122. =>WM: (13417: I3 ^dir U)
  7123. =>WM: (13416: O1906 ^name predict-no)
  7124. =>WM: (13415: O1905 ^name predict-yes)
  7125. =>WM: (13414: R956 ^value 1)
  7126. =>WM: (13413: R1 ^reward R956)
  7127. =>WM: (13412: I3 ^see 1)
  7128. <=WM: (13403: S1 ^operator O1903 +)
  7129. <=WM: (13405: S1 ^operator O1903)
  7130. <=WM: (13404: S1 ^operator O1904 +)
  7131. <=WM: (13402: I3 ^dir L)
  7132. <=WM: (13398: R1 ^reward R955)
  7133. <=WM: (13370: I3 ^see 0)
  7134. <=WM: (13401: O1904 ^name predict-no)
  7135. <=WM: (13400: O1903 ^name predict-yes)
  7136. <=WM: (13399: R955 ^value 1)
  7137. --- Inner Elaboration Phase, active level 1 (S1) ---
  7138. Firing prefer*rvt*predict-yes*H0
  7139. -->
  7140. Firing rl*prefer*rvt*predict-yes*H0*1
  7141. -->
  7142. (S1 ^operator O1905 = 0.)
  7143. Firing prefer*rvt*predict-no*H0
  7144. -->
  7145. Firing rl*prefer*rvt*predict-no*H0*2
  7146. -->
  7147. (S1 ^operator O1906 = 0.9999999999999999)
  7148. inner elaboration loop at bottom goal.
  7149. Retracting rl*prefer*rvt*predict-no*H0*2
  7150. -->
  7151. (S1 ^operator O1904 = 0.9999999999999999)
  7152. Retracting rl*prefer*rvt*predict-yes*H0*1
  7153. -->
  7154. (S1 ^operator O1903 = 0.)
  7155. --- END Proposal Phase ---
  7156. --- Decision Phase ---
  7157. RL update rl*prefer*rvt*predict-yes*H0*5 0.683775 -0.251886 0.431889 -> 0.683775 -0.251886 0.431889(R,m,v=1,0.919753,0.0742658)
  7158. RL update rl*prefer*rvt*predict-yes*H0*5*v1*H1*30 0.316226 0.251886 0.568113 -> 0.316226 0.251886 0.568112(R,m,v=1,1,0)
  7159. =>WM: (13420: S1 ^operator O1906)
  7160. 953: O: O1906 (predict-no)
  7161. --- END Decision Phase ---
  7162. --- Application Phase ---
  7163. --- Firing Productions (PE) For State At Depth 1 ---
  7164. --- Inner Elaboration Phase, active level 1 (S1) ---
  7165. Firing apply*operator
  7166. -->
  7167. (I3 ^predict-no N953 + :O )
  7168. Firing apply*operator*complete
  7169. -->
  7170. (I3 ^predict-yes N952 - :O )
  7171. inner elaboration loop at bottom goal.
  7172. --- Change Working Memory (PE) ---
  7173. =>WM: (13421: I3 ^predict-no N953)
  7174. <=WM: (13407: N952 ^status complete)
  7175. <=WM: (13406: I3 ^predict-yes N952)
  7176. --- Firing Productions (IE) For State At Depth 1 ---
  7177. --- Inner Elaboration Phase, active level 1 (S1) ---
  7178. Firing monitor*world
  7179. -->
  7180. I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
  7181. --- Change Working Memory (IE) ---
  7182. --- END Application Phase ---
  7183. --- Output Phase ---
  7184. ENV: Agent did: predict-no for direction U in state State-A
  7185. In State-A moving U
  7186. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  7187. predict error 0
  7188. dir: dir isR
  7189. --- END Output Phase ---
  7190. \---- Input Phase ---
  7191. =>WM: (13425: I2 ^dir R)
  7192. =>WM: (13424: I2 ^reward 1)
  7193. =>WM: (13423: I2 ^see 0)
  7194. =>WM: (13422: N953 ^status complete)
  7195. <=WM: (13410: I2 ^dir U)
  7196. <=WM: (13409: I2 ^reward 1)
  7197. <=WM: (13408: I2 ^see 1)
  7198. =>WM: (13426: I2 ^level-1 L1-root)
  7199. <=WM: (13411: I2 ^level-1 L1-root)
  7200. --- END Input Phase ---
  7201. --- Proposal Phase ---
  7202. --- Inner Elaboration Phase, active level 1 (S1) ---
  7203. Firing rl*prefer*rvt*predict-no*H0*4*v1*H1*39
  7204. -->
  7205. (S1 ^operator O1906 = -0.1377248055371832)
  7206. Firing rl*prefer*rvt*predict-yes*H0*3*v1*H1*40
  7207. -->
  7208. (S1 ^operator O1905 = 0.2631666904115852)
  7209. Firing prefer*rvt*predict-no*H0*4*v1*H1
  7210. -->
  7211. Firing prefer*rvt*predict-yes*H0*3*v1*H1
  7212. -->
  7213. Firing elaborate*copy-see-to-output-link
  7214. -->
  7215. (I3 ^see 0 +)
  7216. Firing elaborate*reward*based*on*reward
  7217. -->
  7218. (R957 ^value 1 +)
  7219. (R1 ^reward R957 +)
  7220. Firing propose*predict-yes
  7221. -->
  7222. (O1907 ^name predict-yes +)
  7223. (S1 ^operator O1907 +)
  7224. Firing propose*predict-no
  7225. -->
  7226. (O1908 ^name predict-no +)
  7227. (S1 ^operator O1908 +)
  7228. Firing rl*prefer*rvt*predict-no*H0*4
  7229. -->
  7230. (S1 ^operator O1906 = 0.2572473895009633)
  7231. Firing rl*prefer*rvt*predict-yes*H0*3
  7232. -->
  7233. (S1 ^operator O1905 = 0.736829027581098)
  7234. Firing prefer*rvt*predict-yes*H0
  7235. -->
  7236. Firing prefer*rvt*predict-no*H0
  7237. -->
  7238. Firing elaborate*copy-dir-to-output-link
  7239. -->
  7240. (I3 ^dir R +)
  7241. inner elaboration loop at bottom goal.
  7242. Retracting elaborate*copy-see-to-output-link
  7243. -->
  7244. (I3 ^see 1 +)
  7245. Retracting propose*predict-no
  7246. -->
  7247. (O1906 ^name predict-no +)
  7248. (S1 ^operator O1906 +)
  7249. Retracting propose*predict-yes
  7250. -->
  7251. (O1905 ^name predict-yes +)
  7252. (S1 ^operator O1905 +)
  7253. Retracting elaborate*reward*based*on*reward
  7254. -->
  7255. (R956 ^value 1 +)
  7256. (R1 ^reward R956 +)
  7257. Retracting elaborate*copy-dir-to-output-link
  7258. -->
  7259. (I3 ^dir U +)
  7260. Retracting rl*prefer*rvt*predict-no*H0*2
  7261. -->
  7262. (S1 ^operator O1906 = 0.9999999999999999)
  7263. Retracting rl*prefer*rvt*predict-yes*H0*1
  7264. -->
  7265. (S1 ^operator O1905 = 0.)
  7266. =>WM: (13434: S1 ^operator O1908 +)
  7267. =>WM: (13433: S1 ^operator O1907 +)
  7268. =>WM: (13432: I3 ^dir R)
  7269. =>WM: (13431: O1908 ^name predict-no)
  7270. =>WM: (13430: O1907 ^name predict-yes)
  7271. =>WM: (13429: R957 ^value 1)
  7272. =>WM: (13428: R1 ^reward R957)
  7273. =>WM: (13427: I3 ^see 0)
  7274. <=WM: (13418: S1 ^operator O1905 +)
  7275. <=WM: (13419: S1 ^operator O1906 +)
  7276. <=WM: (13420: S1 ^operator O1906)
  7277. <=WM: (13417: I3 ^dir U)
  7278. <=WM: (13413: R1 ^reward R956)
  7279. <=WM: (13412: I3 ^see 1)
  7280. <=WM: (13416: O1906 ^name predict-no)
  7281. <=WM: (13415: O1905 ^name predict-yes)
  7282. <=WM: (13414: R956 ^value 1)
  7283. --- Inner Elaboration Phase, active level 1 (S1) ---
  7284. Firing prefer*rvt*predict-yes*H0
  7285. -->
  7286. Firing rl*prefer*rvt*predict-yes*H0*3*v1*H1*40
  7287. -->
  7288. (S1 ^operator O1907 = 0.2631666904115852)
  7289. Firing rl*prefer*rvt*predict-yes*H0*3
  7290. -->
  7291. (S1 ^operator O1907 = 0.736829027581098)
  7292. Firing prefer*rvt*predict-yes*H0*3*v1*H1
  7293. -->
  7294. Firing prefer*rvt*predict-no*H0
  7295. -->
  7296. Firing rl*prefer*rvt*predict-no*H0*4*v1*H1*39
  7297. -->
  7298. (S1 ^operator O1908 = -0.1377248055371832)
  7299. Firing rl*prefer*rvt*predict-no*H0*4
  7300. -->
  7301. (S1 ^operator O1908 = 0.2572473895009633)
  7302. Firing prefer*rvt*predict-no*H0*4*v1*H1
  7303. -->
  7304. inner elaboration loop at bottom goal.
  7305. Retracting rl*prefer*rvt*predict-no*H0*4
  7306. -->
  7307. (S1 ^operator O1906 = 0.2572473895009633)
  7308. Retracting rl*prefer*rvt*predict-no*H0*4*v1*H1*39
  7309. -->
  7310. (S1 ^operator O1906 = -0.1377248055371832)
  7311. Retracting rl*prefer*rvt*predict-yes*H0*3
  7312. -->
  7313. (S1 ^operator O1905 = 0.736829027581098)
  7314. Retracting rl*prefer*rvt*predict-yes*H0*3*v1*H1*40
  7315. -->
  7316. (S1 ^operator O1905 = 0.2631666904115852)
  7317. --- END Proposal Phase ---
  7318. --- Decision Phase ---
  7319. RL update rl*prefer*rvt*predict-no*H0*2 1 0 1 -> 1 0 1(R,m,v=1,1,0)
  7320. =>WM: (13435: S1 ^operator O1907)
  7321. 954: O: O1907 (predict-yes)
  7322. --- END Decision Phase ---
  7323. --- Application Phase ---
  7324. --- Firing Productions (PE) For State At Depth 1 ---
  7325. --- Inner Elaboration Phase, active level 1 (S1) ---
  7326. Firing apply*operator
  7327. -->
  7328. (I3 ^predict-yes N954 + :O )
  7329. Firing apply*operator*complete
  7330. -->
  7331. (I3 ^predict-no N953 - :O )
  7332. inner elaboration loop at bottom goal.
  7333. --- Change Working Memory (PE) ---
  7334. =>WM: (13436: I3 ^predict-yes N954)
  7335. <=WM: (13422: N953 ^status complete)
  7336. <=WM: (13421: I3 ^predict-no N953)
  7337. --- Firing Productions (IE) For State At Depth 1 ---
  7338. --- Inner Elaboration Phase, active level 1 (S1) ---
  7339. Firing monitor*world
  7340. -->
  7341. I see 1 and I'm going to do: predict-yes inner elaboration loop at bottom goal.
  7342. --- Change Working Memory (IE) ---
  7343. --- END Application Phase ---
  7344. --- Output Phase ---
  7345. ENV: Agent did: predict-yes for direction R in state State-A
  7346. In State-A moving R
  7347. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  7348. predict error 0
  7349. dir: dir isU
  7350. --- END Output Phase ---
  7351. /|\---- Input Phase ---
  7352. =>WM: (13440: I2 ^dir U)
  7353. =>WM: (13439: I2 ^reward 1)
  7354. =>WM: (13438: I2 ^see 1)
  7355. =>WM: (13437: N954 ^status complete)
  7356. <=WM: (13425: I2 ^dir R)
  7357. <=WM: (13424: I2 ^reward 1)
  7358. <=WM: (13423: I2 ^see 0)
  7359. =>WM: (13441: I2 ^level-1 R1-root)
  7360. <=WM: (13426: I2 ^level-1 L1-root)
  7361. --- END Input Phase ---
  7362. --- Proposal Phase ---
  7363. --- Inner Elaboration Phase, active level 1 (S1) ---
  7364. Firing elaborate*copy-see-to-output-link
  7365. -->
  7366. (I3 ^see 1 +)
  7367. Firing elaborate*reward*based*on*reward
  7368. -->
  7369. (R958 ^value 1 +)
  7370. (R1 ^reward R958 +)
  7371. Firing propose*predict-yes
  7372. -->
  7373. (O1909 ^name predict-yes +)
  7374. (S1 ^operator O1909 +)
  7375. Firing propose*predict-no
  7376. -->
  7377. (O1910 ^name predict-no +)
  7378. (S1 ^operator O1910 +)
  7379. Firing rl*prefer*rvt*predict-no*H0*2
  7380. -->
  7381. (S1 ^operator O1908 = 0.9999999999999999)
  7382. Firing rl*prefer*rvt*predict-yes*H0*1
  7383. -->
  7384. (S1 ^operator O1907 = 0.)
  7385. Firing prefer*rvt*predict-yes*H0
  7386. -->
  7387. Firing prefer*rvt*predict-no*H0
  7388. -->
  7389. Firing elaborate*copy-dir-to-output-link
  7390. -->
  7391. (I3 ^dir U +)
  7392. inner elaboration loop at bottom goal.
  7393. Retracting elaborate*copy-see-to-output-link
  7394. -->
  7395. (I3 ^see 0 +)
  7396. Retracting propose*predict-no
  7397. -->
  7398. (O1908 ^name predict-no +)
  7399. (S1 ^operator O1908 +)
  7400. Retracting propose*predict-yes
  7401. -->
  7402. (O1907 ^name predict-yes +)
  7403. (S1 ^operator O1907 +)
  7404. Retracting elaborate*reward*based*on*reward
  7405. -->
  7406. (R957 ^value 1 +)
  7407. (R1 ^reward R957 +)
  7408. Retracting elaborate*copy-dir-to-output-link
  7409. -->
  7410. (I3 ^dir R +)
  7411. Retracting rl*prefer*rvt*predict-no*H0*4
  7412. -->
  7413. (S1 ^operator O1908 = 0.2572473895009633)
  7414. Retracting rl*prefer*rvt*predict-no*H0*4*v1*H1*39
  7415. -->
  7416. (S1 ^operator O1908 = -0.1377248055371832)
  7417. Retracting rl*prefer*rvt*predict-yes*H0*3
  7418. -->
  7419. (S1 ^operator O1907 = 0.736829027581098)
  7420. Retracting rl*prefer*rvt*predict-yes*H0*3*v1*H1*40
  7421. -->
  7422. (S1 ^operator O1907 = 0.2631666904115852)
  7423. =>WM: (13449: S1 ^operator O1910 +)
  7424. =>WM: (13448: S1 ^operator O1909 +)
  7425. =>WM: (13447: I3 ^dir U)
  7426. =>WM: (13446: O1910 ^name predict-no)
  7427. =>WM: (13445: O1909 ^name predict-yes)
  7428. =>WM: (13444: R958 ^value 1)
  7429. =>WM: (13443: R1 ^reward R958)
  7430. =>WM: (13442: I3 ^see 1)
  7431. <=WM: (13433: S1 ^operator O1907 +)
  7432. <=WM: (13435: S1 ^operator O1907)
  7433. <=WM: (13434: S1 ^operator O1908 +)
  7434. <=WM: (13432: I3 ^dir R)
  7435. <=WM: (13428: R1 ^reward R957)
  7436. <=WM: (13427: I3 ^see 0)
  7437. <=WM: (13431: O1908 ^name predict-no)
  7438. <=WM: (13430: O1907 ^name predict-yes)
  7439. <=WM: (13429: R957 ^value 1)
  7440. --- Inner Elaboration Phase, active level 1 (S1) ---
  7441. Firing prefer*rvt*predict-yes*H0
  7442. -->
  7443. Firing rl*prefer*rvt*predict-yes*H0*1
  7444. -->
  7445. (S1 ^operator O1909 = 0.)
  7446. Firing prefer*rvt*predict-no*H0
  7447. -->
  7448. Firing rl*prefer*rvt*predict-no*H0*2
  7449. -->
  7450. (S1 ^operator O1910 = 0.9999999999999999)
  7451. inner elaboration loop at bottom goal.
  7452. Retracting rl*prefer*rvt*predict-no*H0*2
  7453. -->
  7454. (S1 ^operator O1908 = 0.9999999999999999)
  7455. Retracting rl*prefer*rvt*predict-yes*H0*1
  7456. -->
  7457. (S1 ^operator O1907 = 0.)
  7458. --- END Proposal Phase ---
  7459. --- Decision Phase ---
  7460. RL update rl*prefer*rvt*predict-yes*H0*3 0.748236 -0.0114073 0.736829 -> 0.748237 -0.0114068 0.73683(R,m,v=1,0.892405,0.0966298)
  7461. RL update rl*prefer*rvt*predict-yes*H0*3*v1*H1*40 0.251763 0.0114042 0.263167 -> 0.251763 0.0114046 0.263167(R,m,v=1,1,0)
  7462. =>WM: (13450: S1 ^operator O1910)
  7463. 955: O: O1910 (predict-no)
  7464. --- END Decision Phase ---
  7465. --- Application Phase ---
  7466. --- Firing Productions (PE) For State At Depth 1 ---
  7467. --- Inner Elaboration Phase, active level 1 (S1) ---
  7468. Firing apply*operator
  7469. -->
  7470. (I3 ^predict-no N955 + :O )
  7471. Firing apply*operator*complete
  7472. -->
  7473. (I3 ^predict-yes N954 - :O )
  7474. inner elaboration loop at bottom goal.
  7475. --- Change Working Memory (PE) ---
  7476. =>WM: (13451: I3 ^predict-no N955)
  7477. <=WM: (13437: N954 ^status complete)
  7478. <=WM: (13436: I3 ^predict-yes N954)
  7479. --- Firing Productions (IE) For State At Depth 1 ---
  7480. --- Inner Elaboration Phase, active level 1 (S1) ---
  7481. Firing monitor*world
  7482. -->
  7483. I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
  7484. --- Change Working Memory (IE) ---
  7485. --- END Application Phase ---
  7486. --- Output Phase ---
  7487. ENV: Agent did: predict-no for direction U in state State-B
  7488. In State-B moving U
  7489. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  7490. predict error 0
  7491. dir: dir isR
  7492. --- END Output Phase ---
  7493. /|\--- Input Phase ---
  7494. =>WM: (13455: I2 ^dir R)
  7495. =>WM: (13454: I2 ^reward 1)
  7496. =>WM: (13453: I2 ^see 0)
  7497. =>WM: (13452: N955 ^status complete)
  7498. <=WM: (13440: I2 ^dir U)
  7499. <=WM: (13439: I2 ^reward 1)
  7500. <=WM: (13438: I2 ^see 1)
  7501. =>WM: (13456: I2 ^level-1 R1-root)
  7502. <=WM: (13441: I2 ^level-1 R1-root)
  7503. --- END Input Phase ---
  7504. --- Proposal Phase ---
  7505. --- Inner Elaboration Phase, active level 1 (S1) ---
  7506. Firing rl*prefer*rvt*predict-yes*H0*3*v1*H1*37
  7507. -->
  7508. (S1 ^operator O1909 = -0.3011268063455669)
  7509. Firing rl*prefer*rvt*predict-no*H0*4*v1*H1*36
  7510. -->
  7511. (S1 ^operator O1910 = 0.7427518011874024)
  7512. Firing prefer*rvt*predict-no*H0*4*v1*H1
  7513. -->
  7514. Firing prefer*rvt*predict-yes*H0*3*v1*H1
  7515. -->
  7516. Firing elaborate*copy-see-to-output-link
  7517. -->
  7518. (I3 ^see 0 +)
  7519. Firing elaborate*reward*based*on*reward
  7520. -->
  7521. (R959 ^value 1 +)
  7522. (R1 ^reward R959 +)
  7523. Firing propose*predict-yes
  7524. -->
  7525. (O1911 ^name predict-yes +)
  7526. (S1 ^operator O1911 +)
  7527. Firing propose*predict-no
  7528. -->
  7529. (O1912 ^name predict-no +)
  7530. (S1 ^operator O1912 +)
  7531. Firing rl*prefer*rvt*predict-no*H0*4
  7532. -->
  7533. (S1 ^operator O1910 = 0.2572473895009633)
  7534. Firing rl*prefer*rvt*predict-yes*H0*3
  7535. -->
  7536. (S1 ^operator O1909 = 0.7368296698821956)
  7537. Firing prefer*rvt*predict-yes*H0
  7538. -->
  7539. Firing prefer*rvt*predict-no*H0
  7540. -->
  7541. Firing elaborate*copy-dir-to-output-link
  7542. -->
  7543. (I3 ^dir R +)
  7544. inner elaboration loop at bottom goal.
  7545. Retracting elaborate*copy-see-to-output-link
  7546. -->
  7547. (I3 ^see 1 +)
  7548. Retracting propose*predict-no
  7549. -->
  7550. (O1910 ^name predict-no +)
  7551. (S1 ^operator O1910 +)
  7552. Retracting propose*predict-yes
  7553. -->
  7554. (O1909 ^name predict-yes +)
  7555. (S1 ^operator O1909 +)
  7556. Retracting elaborate*reward*based*on*reward
  7557. -->
  7558. (R958 ^value 1 +)
  7559. (R1 ^reward R958 +)
  7560. Retracting elaborate*copy-dir-to-output-link
  7561. -->
  7562. (I3 ^dir U +)
  7563. Retracting rl*prefer*rvt*predict-no*H0*2
  7564. -->
  7565. (S1 ^operator O1910 = 0.9999999999999999)
  7566. Retracting rl*prefer*rvt*predict-yes*H0*1
  7567. -->
  7568. (S1 ^operator O1909 = 0.)
  7569. =>WM: (13464: S1 ^operator O1912 +)
  7570. =>WM: (13463: S1 ^operator O1911 +)
  7571. =>WM: (13462: I3 ^dir R)
  7572. =>WM: (13461: O1912 ^name predict-no)
  7573. =>WM: (13460: O1911 ^name predict-yes)
  7574. =>WM: (13459: R959 ^value 1)
  7575. =>WM: (13458: R1 ^reward R959)
  7576. =>WM: (13457: I3 ^see 0)
  7577. <=WM: (13448: S1 ^operator O1909 +)
  7578. <=WM: (13449: S1 ^operator O1910 +)
  7579. <=WM: (13450: S1 ^operator O1910)
  7580. <=WM: (13447: I3 ^dir U)
  7581. <=WM: (13443: R1 ^reward R958)
  7582. <=WM: (13442: I3 ^see 1)
  7583. <=WM: (13446: O1910 ^name predict-no)
  7584. <=WM: (13445: O1909 ^name predict-yes)
  7585. <=WM: (13444: R958 ^value 1)
  7586. --- Inner Elaboration Phase, active level 1 (S1) ---
  7587. Firing prefer*rvt*predict-yes*H0
  7588. -->
  7589. Firing rl*prefer*rvt*predict-yes*H0*3*v1*H1*37
  7590. -->
  7591. (S1 ^operator O1911 = -0.3011268063455669)
  7592. Firing rl*prefer*rvt*predict-yes*H0*3
  7593. -->
  7594. (S1 ^operator O1911 = 0.7368296698821956)
  7595. Firing prefer*rvt*predict-yes*H0*3*v1*H1
  7596. -->
  7597. Firing prefer*rvt*predict-no*H0
  7598. -->
  7599. Firing rl*prefer*rvt*predict-no*H0*4*v1*H1*36
  7600. -->
  7601. (S1 ^operator O1912 = 0.7427518011874024)
  7602. Firing rl*prefer*rvt*predict-no*H0*4
  7603. -->
  7604. (S1 ^operator O1912 = 0.2572473895009633)
  7605. Firing prefer*rvt*predict-no*H0*4*v1*H1
  7606. -->
  7607. inner elaboration loop at bottom goal.
  7608. Retracting rl*prefer*rvt*predict-no*H0*4
  7609. -->
  7610. (S1 ^operator O1910 = 0.2572473895009633)
  7611. Retracting rl*prefer*rvt*predict-no*H0*4*v1*H1*36
  7612. -->
  7613. (S1 ^operator O1910 = 0.7427518011874024)
  7614. Retracting rl*prefer*rvt*predict-yes*H0*3
  7615. -->
  7616. (S1 ^operator O1909 = 0.7368296698821956)
  7617. Retracting rl*prefer*rvt*predict-yes*H0*3*v1*H1*37
  7618. -->
  7619. (S1 ^operator O1909 = -0.3011268063455669)
  7620. --- END Proposal Phase ---
  7621. --- Decision Phase ---
  7622. RL update rl*prefer*rvt*predict-no*H0*2 1 0 1 -> 1 0 1(R,m,v=1,1,0)
  7623. =>WM: (13465: S1 ^operator O1912)
  7624. 956: O: O1912 (predict-no)
  7625. --- END Decision Phase ---
  7626. --- Application Phase ---
  7627. --- Firing Productions (PE) For State At Depth 1 ---
  7628. --- Inner Elaboration Phase, active level 1 (S1) ---
  7629. Firing apply*operator
  7630. -->
  7631. (I3 ^predict-no N956 + :O )
  7632. Firing apply*operator*complete
  7633. -->
  7634. (I3 ^predict-no N955 - :O )
  7635. inner elaboration loop at bottom goal.
  7636. --- Change Working Memory (PE) ---
  7637. =>WM: (13466: I3 ^predict-no N956)
  7638. <=WM: (13452: N955 ^status complete)
  7639. <=WM: (13451: I3 ^predict-no N955)
  7640. --- Firing Productions (IE) For State At Depth 1 ---
  7641. --- Inner Elaboration Phase, active level 1 (S1) ---
  7642. Firing monitor*world
  7643. -->
  7644. I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
  7645. --- Change Working Memory (IE) ---
  7646. --- END Application Phase ---
  7647. --- Output Phase ---
  7648. ENV: Agent did: predict-no for direction R in state State-B
  7649. In State-B moving R
  7650. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  7651. predict error 0
  7652. dir: dir isR
  7653. --- END Output Phase ---
  7654. -/|--- Input Phase ---
  7655. =>WM: (13470: I2 ^dir R)
  7656. =>WM: (13469: I2 ^reward 1)
  7657. =>WM: (13468: I2 ^see 0)
  7658. =>WM: (13467: N956 ^status complete)
  7659. <=WM: (13455: I2 ^dir R)
  7660. <=WM: (13454: I2 ^reward 1)
  7661. <=WM: (13453: I2 ^see 0)
  7662. =>WM: (13471: I2 ^level-1 R0-root)
  7663. <=WM: (13456: I2 ^level-1 R1-root)
  7664. --- END Input Phase ---
  7665. --- Proposal Phase ---
  7666. --- Inner Elaboration Phase, active level 1 (S1) ---
  7667. Firing rl*prefer*rvt*predict-no*H0*4*v1*H1*41
  7668. -->
  7669. (S1 ^operator O1912 = 0.7427606592568701)
  7670. Firing rl*prefer*rvt*predict-yes*H0*3*v1*H1*42
  7671. -->
  7672. (S1 ^operator O1911 = -0.1989581826229297)
  7673. Firing prefer*rvt*predict-no*H0*4*v1*H1
  7674. -->
  7675. Firing prefer*rvt*predict-yes*H0*3*v1*H1
  7676. -->
  7677. Firing elaborate*copy-see-to-output-link
  7678. -->
  7679. (I3 ^see 0 +)
  7680. Firing elaborate*reward*based*on*reward
  7681. -->
  7682. (R960 ^value 1 +)
  7683. (R1 ^reward R960 +)
  7684. Firing propose*predict-yes
  7685. -->
  7686. (O1913 ^name predict-yes +)
  7687. (S1 ^operator O1913 +)
  7688. Firing propose*predict-no
  7689. -->
  7690. (O1914 ^name predict-no +)
  7691. (S1 ^operator O1914 +)
  7692. Firing rl*prefer*rvt*predict-no*H0*4
  7693. -->
  7694. (S1 ^operator O1912 = 0.2572473895009633)
  7695. Firing rl*prefer*rvt*predict-yes*H0*3
  7696. -->
  7697. (S1 ^operator O1911 = 0.7368296698821956)
  7698. Firing prefer*rvt*predict-yes*H0
  7699. -->
  7700. Firing prefer*rvt*predict-no*H0
  7701. -->
  7702. Firing elaborate*copy-dir-to-output-link
  7703. -->
  7704. (I3 ^dir R +)
  7705. inner elaboration loop at bottom goal.
  7706. Retracting elaborate*copy-see-to-output-link
  7707. -->
  7708. (I3 ^see 0 +)
  7709. Retracting propose*predict-no
  7710. -->
  7711. (O1912 ^name predict-no +)
  7712. (S1 ^operator O1912 +)
  7713. Retracting propose*predict-yes
  7714. -->
  7715. (O1911 ^name predict-yes +)
  7716. (S1 ^operator O1911 +)
  7717. Retracting elaborate*reward*based*on*reward
  7718. -->
  7719. (R959 ^value 1 +)
  7720. (R1 ^reward R959 +)
  7721. Retracting elaborate*copy-dir-to-output-link
  7722. -->
  7723. (I3 ^dir R +)
  7724. Retracting rl*prefer*rvt*predict-no*H0*4
  7725. -->
  7726. (S1 ^operator O1912 = 0.2572473895009633)
  7727. Retracting rl*prefer*rvt*predict-no*H0*4*v1*H1*36
  7728. -->
  7729. (S1 ^operator O1912 = 0.7427518011874024)
  7730. Retracting rl*prefer*rvt*predict-yes*H0*3
  7731. -->
  7732. (S1 ^operator O1911 = 0.7368296698821956)
  7733. Retracting rl*prefer*rvt*predict-yes*H0*3*v1*H1*37
  7734. -->
  7735. (S1 ^operator O1911 = -0.3011268063455669)
  7736. =>WM: (13477: S1 ^operator O1914 +)
  7737. =>WM: (13476: S1 ^operator O1913 +)
  7738. =>WM: (13475: O1914 ^name predict-no)
  7739. =>WM: (13474: O1913 ^name predict-yes)
  7740. =>WM: (13473: R960 ^value 1)
  7741. =>WM: (13472: R1 ^reward R960)
  7742. <=WM: (13463: S1 ^operator O1911 +)
  7743. <=WM: (13464: S1 ^operator O1912 +)
  7744. <=WM: (13465: S1 ^operator O1912)
  7745. <=WM: (13458: R1 ^reward R959)
  7746. <=WM: (13461: O1912 ^name predict-no)
  7747. <=WM: (13460: O1911 ^name predict-yes)
  7748. <=WM: (13459: R959 ^value 1)
  7749. --- Inner Elaboration Phase, active level 1 (S1) ---
  7750. Firing prefer*rvt*predict-yes*H0
  7751. -->
  7752. Firing rl*prefer*rvt*predict-yes*H0*3
  7753. -->
  7754. (S1 ^operator O1913 = 0.7368296698821956)
  7755. Firing prefer*rvt*predict-yes*H0*3*v1*H1
  7756. -->
  7757. Firing rl*prefer*rvt*predict-yes*H0*3*v1*H1*42
  7758. -->
  7759. (S1 ^operator O1913 = -0.1989581826229297)
  7760. Firing prefer*rvt*predict-no*H0
  7761. -->
  7762. Firing rl*prefer*rvt*predict-no*H0*4
  7763. -->
  7764. (S1 ^operator O1914 = 0.2572473895009633)
  7765. Firing prefer*rvt*predict-no*H0*4*v1*H1
  7766. -->
  7767. Firing rl*prefer*rvt*predict-no*H0*4*v1*H1*41
  7768. -->
  7769. (S1 ^operator O1914 = 0.7427606592568701)
  7770. inner elaboration loop at bottom goal.
  7771. Retracting rl*prefer*rvt*predict-no*H0*4
  7772. -->
  7773. (S1 ^operator O1912 = 0.2572473895009633)
  7774. Retracting rl*prefer*rvt*predict-no*H0*4*v1*H1*41
  7775. -->
  7776. (S1 ^operator O1912 = 0.7427606592568701)
  7777. Retracting rl*prefer*rvt*predict-yes*H0*3
  7778. -->
  7779. (S1 ^operator O1911 = 0.7368296698821956)
  7780. Retracting rl*prefer*rvt*predict-yes*H0*3*v1*H1*42
  7781. -->
  7782. (S1 ^operator O1911 = -0.1989581826229297)
  7783. --- END Proposal Phase ---
  7784. --- Decision Phase ---
  7785. RL update rl*prefer*rvt*predict-no*H0*4 0.586137 -0.32889 0.257247 -> 0.586137 -0.32889 0.257248(R,m,v=1,0.855422,0.124425)
  7786. RL update rl*prefer*rvt*predict-no*H0*4*v1*H1*36 0.413862 0.32889 0.742752 -> 0.413862 0.32889 0.742752(R,m,v=1,1,0)
  7787. =>WM: (13478: S1 ^operator O1914)
  7788. 957: O: O1914 (predict-no)
  7789. --- END Decision Phase ---
  7790. --- Application Phase ---
  7791. --- Firing Productions (PE) For State At Depth 1 ---
  7792. --- Inner Elaboration Phase, active level 1 (S1) ---
  7793. Firing apply*operator
  7794. -->
  7795. (I3 ^predict-no N957 + :O )
  7796. Firing apply*operator*complete
  7797. -->
  7798. (I3 ^predict-no N956 - :O )
  7799. inner elaboration loop at bottom goal.
  7800. --- Change Working Memory (PE) ---
  7801. =>WM: (13479: I3 ^predict-no N957)
  7802. <=WM: (13467: N956 ^status complete)
  7803. <=WM: (13466: I3 ^predict-no N956)
  7804. --- Firing Productions (IE) For State At Depth 1 ---
  7805. --- Inner Elaboration Phase, active level 1 (S1) ---
  7806. Firing monitor*world
  7807. -->
  7808. I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
  7809. --- Change Working Memory (IE) ---
  7810. --- END Application Phase ---
  7811. --- Output Phase ---
  7812. ENV: Agent did: predict-no for direction R in state State-B
  7813. In State-B moving R
  7814. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  7815. predict error 0
  7816. dir: dir isL
  7817. --- END Output Phase ---
  7818. \---- Input Phase ---
  7819. =>WM: (13483: I2 ^dir L)
  7820. =>WM: (13482: I2 ^reward 1)
  7821. =>WM: (13481: I2 ^see 0)
  7822. =>WM: (13480: N957 ^status complete)
  7823. <=WM: (13470: I2 ^dir R)
  7824. <=WM: (13469: I2 ^reward 1)
  7825. <=WM: (13468: I2 ^see 0)
  7826. =>WM: (13484: I2 ^level-1 R0-root)
  7827. <=WM: (13471: I2 ^level-1 R0-root)
  7828. --- END Input Phase ---
  7829. --- Proposal Phase ---
  7830. --- Inner Elaboration Phase, active level 1 (S1) ---
  7831. Firing rl*prefer*rvt*predict-no*H0*6*v1*H1*38
  7832. -->
  7833. (S1 ^operator O1914 = 0.04178081990804111)
  7834. Firing rl*prefer*rvt*predict-yes*H0*5*v1*H1*30
  7835. -->
  7836. (S1 ^operator O1913 = 0.5681124792401879)
  7837. Firing prefer*rvt*predict-no*H0*6*v1*H1
  7838. -->
  7839. Firing prefer*rvt*predict-yes*H0*5*v1*H1
  7840. -->
  7841. Firing elaborate*copy-see-to-output-link
  7842. -->
  7843. (I3 ^see 0 +)
  7844. Firing elaborate*reward*based*on*reward
  7845. -->
  7846. (R961 ^value 1 +)
  7847. (R1 ^reward R961 +)
  7848. Firing propose*predict-yes
  7849. -->
  7850. (O1915 ^name predict-yes +)
  7851. (S1 ^operator O1915 +)
  7852. Firing propose*predict-no
  7853. -->
  7854. (O1916 ^name predict-no +)
  7855. (S1 ^operator O1916 +)
  7856. Firing rl*prefer*rvt*predict-no*H0*6
  7857. -->
  7858. (S1 ^operator O1914 = 0.3289450941277776)
  7859. Firing rl*prefer*rvt*predict-yes*H0*5
  7860. -->
  7861. (S1 ^operator O1913 = 0.4318889542566386)
  7862. Firing prefer*rvt*predict-yes*H0
  7863. -->
  7864. Firing prefer*rvt*predict-no*H0
  7865. -->
  7866. Firing elaborate*copy-dir-to-output-link
  7867. -->
  7868. (I3 ^dir L +)
  7869. inner elaboration loop at bottom goal.
  7870. Retracting elaborate*copy-see-to-output-link
  7871. -->
  7872. (I3 ^see 0 +)
  7873. Retracting propose*predict-no
  7874. -->
  7875. (O1914 ^name predict-no +)
  7876. (S1 ^operator O1914 +)
  7877. Retracting propose*predict-yes
  7878. -->
  7879. (O1913 ^name predict-yes +)
  7880. (S1 ^operator O1913 +)
  7881. Retracting elaborate*reward*based*on*reward
  7882. -->
  7883. (R960 ^value 1 +)
  7884. (R1 ^reward R960 +)
  7885. Retracting elaborate*copy-dir-to-output-link
  7886. -->
  7887. (I3 ^dir R +)
  7888. Retracting rl*prefer*rvt*predict-no*H0*4*v1*H1*41
  7889. -->
  7890. (S1 ^operator O1914 = 0.7427606592568701)
  7891. Retracting rl*prefer*rvt*predict-no*H0*4
  7892. -->
  7893. (S1 ^operator O1914 = 0.2572475108977085)
  7894. Retracting rl*prefer*rvt*predict-yes*H0*3*v1*H1*42
  7895. -->
  7896. (S1 ^operator O1913 = -0.1989581826229297)
  7897. Retracting rl*prefer*rvt*predict-yes*H0*3
  7898. -->
  7899. (S1 ^operator O1913 = 0.7368296698821956)
  7900. =>WM: (13491: S1 ^operator O1916 +)
  7901. =>WM: (13490: S1 ^operator O1915 +)
  7902. =>WM: (13489: I3 ^dir L)
  7903. =>WM: (13488: O1916 ^name predict-no)
  7904. =>WM: (13487: O1915 ^name predict-yes)
  7905. =>WM: (13486: R961 ^value 1)
  7906. =>WM: (13485: R1 ^reward R961)
  7907. <=WM: (13476: S1 ^operator O1913 +)
  7908. <=WM: (13477: S1 ^operator O1914 +)
  7909. <=WM: (13478: S1 ^operator O1914)
  7910. <=WM: (13462: I3 ^dir R)
  7911. <=WM: (13472: R1 ^reward R960)
  7912. <=WM: (13475: O1914 ^name predict-no)
  7913. <=WM: (13474: O1913 ^name predict-yes)
  7914. <=WM: (13473: R960 ^value 1)
  7915. --- Inner Elaboration Phase, active level 1 (S1) ---
  7916. Firing prefer*rvt*predict-yes*H0
  7917. -->
  7918. Firing rl*prefer*rvt*predict-yes*H0*5*v1*H1*30
  7919. -->
  7920. (S1 ^operator O1915 = 0.5681124792401879)
  7921. Firing rl*prefer*rvt*predict-yes*H0*5
  7922. -->
  7923. (S1 ^operator O1915 = 0.4318889542566386)
  7924. Firing prefer*rvt*predict-yes*H0*5*v1*H1
  7925. -->
  7926. Firing prefer*rvt*predict-no*H0
  7927. -->
  7928. Firing rl*prefer*rvt*predict-no*H0*6*v1*H1*38
  7929. -->
  7930. (S1 ^operator O1916 = 0.04178081990804111)
  7931. Firing rl*prefer*rvt*predict-no*H0*6
  7932. -->
  7933. (S1 ^operator O1916 = 0.3289450941277776)
  7934. Firing prefer*rvt*predict-no*H0*6*v1*H1
  7935. -->
  7936. inner elaboration loop at bottom goal.
  7937. Retracting rl*prefer*rvt*predict-no*H0*6
  7938. -->
  7939. (S1 ^operator O1914 = 0.3289450941277776)
  7940. Retracting rl*prefer*rvt*predict-no*H0*6*v1*H1*38
  7941. -->
  7942. (S1 ^operator O1914 = 0.04178081990804111)
  7943. Retracting rl*prefer*rvt*predict-yes*H0*5
  7944. -->
  7945. (S1 ^operator O1913 = 0.4318889542566386)
  7946. Retracting rl*prefer*rvt*predict-yes*H0*5*v1*H1*30
  7947. -->
  7948. (S1 ^operator O1913 = 0.5681124792401879)
  7949. --- END Proposal Phase ---
  7950. --- Decision Phase ---
  7951. RL update rl*prefer*rvt*predict-no*H0*4 0.586137 -0.32889 0.257248 -> 0.586136 -0.32889 0.257246(R,m,v=1,0.856287,0.123801)
  7952. RL update rl*prefer*rvt*predict-no*H0*4*v1*H1*41 0.413869 0.328891 0.742761 -> 0.413868 0.328891 0.742759(R,m,v=1,1,0)
  7953. =>WM: (13492: S1 ^operator O1915)
  7954. 958: O: O1915 (predict-yes)
  7955. --- END Decision Phase ---
  7956. --- Application Phase ---
  7957. --- Firing Productions (PE) For State At Depth 1 ---
  7958. --- Inner Elaboration Phase, active level 1 (S1) ---
  7959. Firing apply*operator
  7960. -->
  7961. (I3 ^predict-yes N958 + :O )
  7962. Firing apply*operator*complete
  7963. -->
  7964. (I3 ^predict-no N957 - :O )
  7965. inner elaboration loop at bottom goal.
  7966. --- Change Working Memory (PE) ---
  7967. =>WM: (13493: I3 ^predict-yes N958)
  7968. <=WM: (13480: N957 ^status complete)
  7969. <=WM: (13479: I3 ^predict-no N957)
  7970. --- Firing Productions (IE) For State At Depth 1 ---
  7971. --- Inner Elaboration Phase, active level 1 (S1) ---
  7972. Firing monitor*world
  7973. -->
  7974. I see 1 and I'm going to do: predict-yes inner elaboration loop at bottom goal.
  7975. --- Change Working Memory (IE) ---
  7976. --- END Application Phase ---
  7977. --- Output Phase ---
  7978. ENV: Agent did: predict-yes for direction L in state State-B
  7979. In State-B moving L
  7980. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  7981. predict error 0
  7982. dir: dir isU
  7983. --- END Output Phase ---
  7984. /|--- Input Phase ---
  7985. =>WM: (13497: I2 ^dir U)
  7986. =>WM: (13496: I2 ^reward 1)
  7987. =>WM: (13495: I2 ^see 1)
  7988. =>WM: (13494: N958 ^status complete)
  7989. <=WM: (13483: I2 ^dir L)
  7990. <=WM: (13482: I2 ^reward 1)
  7991. <=WM: (13481: I2 ^see 0)
  7992. =>WM: (13498: I2 ^level-1 L1-root)
  7993. <=WM: (13484: I2 ^level-1 R0-root)
  7994. --- END Input Phase ---
  7995. --- Proposal Phase ---
  7996. --- Inner Elaboration Phase, active level 1 (S1) ---
  7997. Firing elaborate*copy-see-to-output-link
  7998. -->
  7999. (I3 ^see 1 +)
  8000. Firing elaborate*reward*based*on*reward
  8001. -->
  8002. (R962 ^value 1 +)
  8003. (R1 ^reward R962 +)
  8004. Firing propose*predict-yes
  8005. -->
  8006. (O1917 ^name predict-yes +)
  8007. (S1 ^operator O1917 +)
  8008. Firing propose*predict-no
  8009. -->
  8010. (O1918 ^name predict-no +)
  8011. (S1 ^operator O1918 +)
  8012. Firing rl*prefer*rvt*predict-no*H0*2
  8013. -->
  8014. (S1 ^operator O1916 = 0.9999999999999999)
  8015. Firing rl*prefer*rvt*predict-yes*H0*1
  8016. -->
  8017. (S1 ^operator O1915 = 0.)
  8018. Firing prefer*rvt*predict-yes*H0
  8019. -->
  8020. Firing prefer*rvt*predict-no*H0
  8021. -->
  8022. Firing elaborate*copy-dir-to-output-link
  8023. -->
  8024. (I3 ^dir U +)
  8025. inner elaboration loop at bottom goal.
  8026. Retracting elaborate*copy-see-to-output-link
  8027. -->
  8028. (I3 ^see 0 +)
  8029. Retracting propose*predict-no
  8030. -->
  8031. (O1916 ^name predict-no +)
  8032. (S1 ^operator O1916 +)
  8033. Retracting propose*predict-yes
  8034. -->
  8035. (O1915 ^name predict-yes +)
  8036. (S1 ^operator O1915 +)
  8037. Retracting elaborate*reward*based*on*reward
  8038. -->
  8039. (R961 ^value 1 +)
  8040. (R1 ^reward R961 +)
  8041. Retracting elaborate*copy-dir-to-output-link
  8042. -->
  8043. (I3 ^dir L +)
  8044. Retracting rl*prefer*rvt*predict-no*H0*6
  8045. -->
  8046. (S1 ^operator O1916 = 0.3289450941277776)
  8047. Retracting rl*prefer*rvt*predict-no*H0*6*v1*H1*38
  8048. -->
  8049. (S1 ^operator O1916 = 0.04178081990804111)
  8050. Retracting rl*prefer*rvt*predict-yes*H0*5
  8051. -->
  8052. (S1 ^operator O1915 = 0.4318889542566386)
  8053. Retracting rl*prefer*rvt*predict-yes*H0*5*v1*H1*30
  8054. -->
  8055. (S1 ^operator O1915 = 0.5681124792401879)
  8056. =>WM: (13506: S1 ^operator O1918 +)
  8057. =>WM: (13505: S1 ^operator O1917 +)
  8058. =>WM: (13504: I3 ^dir U)
  8059. =>WM: (13503: O1918 ^name predict-no)
  8060. =>WM: (13502: O1917 ^name predict-yes)
  8061. =>WM: (13501: R962 ^value 1)
  8062. =>WM: (13500: R1 ^reward R962)
  8063. =>WM: (13499: I3 ^see 1)
  8064. <=WM: (13490: S1 ^operator O1915 +)
  8065. <=WM: (13492: S1 ^operator O1915)
  8066. <=WM: (13491: S1 ^operator O1916 +)
  8067. <=WM: (13489: I3 ^dir L)
  8068. <=WM: (13485: R1 ^reward R961)
  8069. <=WM: (13457: I3 ^see 0)
  8070. <=WM: (13488: O1916 ^name predict-no)
  8071. <=WM: (13487: O1915 ^name predict-yes)
  8072. <=WM: (13486: R961 ^value 1)
  8073. --- Inner Elaboration Phase, active level 1 (S1) ---
  8074. Firing prefer*rvt*predict-yes*H0
  8075. -->
  8076. Firing rl*prefer*rvt*predict-yes*H0*1
  8077. -->
  8078. (S1 ^operator O1917 = 0.)
  8079. Firing prefer*rvt*predict-no*H0
  8080. -->
  8081. Firing rl*prefer*rvt*predict-no*H0*2
  8082. -->
  8083. (S1 ^operator O1918 = 0.9999999999999999)
  8084. inner elaboration loop at bottom goal.
  8085. Retracting rl*prefer*rvt*predict-no*H0*2
  8086. -->
  8087. (S1 ^operator O1916 = 0.9999999999999999)
  8088. Retracting rl*prefer*rvt*predict-yes*H0*1
  8089. -->
  8090. (S1 ^operator O1915 = 0.)
  8091. --- END Proposal Phase ---
  8092. --- Decision Phase ---
  8093. RL update rl*prefer*rvt*predict-yes*H0*5 0.683775 -0.251886 0.431889 -> 0.683775 -0.251886 0.431889(R,m,v=1,0.920245,0.0738469)
  8094. RL update rl*prefer*rvt*predict-yes*H0*5*v1*H1*30 0.316226 0.251886 0.568112 -> 0.316226 0.251886 0.568112(R,m,v=1,1,0)
  8095. =>WM: (13507: S1 ^operator O1918)
  8096. 959: O: O1918 (predict-no)
  8097. --- END Decision Phase ---
  8098. --- Application Phase ---
  8099. --- Firing Productions (PE) For State At Depth 1 ---
  8100. --- Inner Elaboration Phase, active level 1 (S1) ---
  8101. Firing apply*operator
  8102. -->
  8103. (I3 ^predict-no N959 + :O )
  8104. Firing apply*operator*complete
  8105. -->
  8106. (I3 ^predict-yes N958 - :O )
  8107. inner elaboration loop at bottom goal.
  8108. --- Change Working Memory (PE) ---
  8109. =>WM: (13508: I3 ^predict-no N959)
  8110. <=WM: (13494: N958 ^status complete)
  8111. <=WM: (13493: I3 ^predict-yes N958)
  8112. --- Firing Productions (IE) For State At Depth 1 ---
  8113. --- Inner Elaboration Phase, active level 1 (S1) ---
  8114. Firing monitor*world
  8115. -->
  8116. I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
  8117. --- Change Working Memory (IE) ---
  8118. --- END Application Phase ---
  8119. --- Output Phase ---
  8120. ENV: Agent did: predict-no for direction U in state State-A
  8121. In State-A moving U
  8122. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  8123. predict error 0
  8124. dir: dir isL
  8125. --- END Output Phase ---
  8126. \-/--- Input Phase ---
  8127. =>WM: (13512: I2 ^dir L)
  8128. =>WM: (13511: I2 ^reward 1)
  8129. =>WM: (13510: I2 ^see 0)
  8130. =>WM: (13509: N959 ^status complete)
  8131. <=WM: (13497: I2 ^dir U)
  8132. <=WM: (13496: I2 ^reward 1)
  8133. <=WM: (13495: I2 ^see 1)
  8134. =>WM: (13513: I2 ^level-1 L1-root)
  8135. <=WM: (13498: I2 ^level-1 L1-root)
  8136. --- END Input Phase ---
  8137. --- Proposal Phase ---
  8138. --- Inner Elaboration Phase, active level 1 (S1) ---
  8139. Firing rl*prefer*rvt*predict-no*H0*6*v1*H1*43
  8140. -->
  8141. (S1 ^operator O1918 = 0.671051122743914)
  8142. Firing rl*prefer*rvt*predict-yes*H0*5*v1*H1*31
  8143. -->
  8144. (S1 ^operator O1917 = -0.06092862110810815)
  8145. Firing prefer*rvt*predict-no*H0*6*v1*H1
  8146. -->
  8147. Firing prefer*rvt*predict-yes*H0*5*v1*H1
  8148. -->
  8149. Firing elaborate*copy-see-to-output-link
  8150. -->
  8151. (I3 ^see 0 +)
  8152. Firing elaborate*reward*based*on*reward
  8153. -->
  8154. (R963 ^value 1 +)
  8155. (R1 ^reward R963 +)
  8156. Firing propose*predict-yes
  8157. -->
  8158. (O1919 ^name predict-yes +)
  8159. (S1 ^operator O1919 +)
  8160. Firing propose*predict-no
  8161. -->
  8162. (O1920 ^name predict-no +)
  8163. (S1 ^operator O1920 +)
  8164. Firing rl*prefer*rvt*predict-no*H0*6
  8165. -->
  8166. (S1 ^operator O1918 = 0.3289450941277776)
  8167. Firing rl*prefer*rvt*predict-yes*H0*5
  8168. -->
  8169. (S1 ^operator O1917 = 0.4318887392321146)
  8170. Firing prefer*rvt*predict-yes*H0
  8171. -->
  8172. Firing prefer*rvt*predict-no*H0
  8173. -->
  8174. Firing elaborate*copy-dir-to-output-link
  8175. -->
  8176. (I3 ^dir L +)
  8177. inner elaboration loop at bottom goal.
  8178. Retracting elaborate*copy-see-to-output-link
  8179. -->
  8180. (I3 ^see 1 +)
  8181. Retracting propose*predict-no
  8182. -->
  8183. (O1918 ^name predict-no +)
  8184. (S1 ^operator O1918 +)
  8185. Retracting propose*predict-yes
  8186. -->
  8187. (O1917 ^name predict-yes +)
  8188. (S1 ^operator O1917 +)
  8189. Retracting elaborate*reward*based*on*reward
  8190. -->
  8191. (R962 ^value 1 +)
  8192. (R1 ^reward R962 +)
  8193. Retracting elaborate*copy-dir-to-output-link
  8194. -->
  8195. (I3 ^dir U +)
  8196. Retracting rl*prefer*rvt*predict-no*H0*2
  8197. -->
  8198. (S1 ^operator O1918 = 0.9999999999999999)
  8199. Retracting rl*prefer*rvt*predict-yes*H0*1
  8200. -->
  8201. (S1 ^operator O1917 = 0.)
  8202. =>WM: (13521: S1 ^operator O1920 +)
  8203. =>WM: (13520: S1 ^operator O1919 +)
  8204. =>WM: (13519: I3 ^dir L)
  8205. =>WM: (13518: O1920 ^name predict-no)
  8206. =>WM: (13517: O1919 ^name predict-yes)
  8207. =>WM: (13516: R963 ^value 1)
  8208. =>WM: (13515: R1 ^reward R963)
  8209. =>WM: (13514: I3 ^see 0)
  8210. <=WM: (13505: S1 ^operator O1917 +)
  8211. <=WM: (13506: S1 ^operator O1918 +)
  8212. <=WM: (13507: S1 ^operator O1918)
  8213. <=WM: (13504: I3 ^dir U)
  8214. <=WM: (13500: R1 ^reward R962)
  8215. <=WM: (13499: I3 ^see 1)
  8216. <=WM: (13503: O1918 ^name predict-no)
  8217. <=WM: (13502: O1917 ^name predict-yes)
  8218. <=WM: (13501: R962 ^value 1)
  8219. --- Inner Elaboration Phase, active level 1 (S1) ---
  8220. Firing prefer*rvt*predict-yes*H0
  8221. -->
  8222. Firing rl*prefer*rvt*predict-yes*H0*5*v1*H1*31
  8223. -->
  8224. (S1 ^operator O1919 = -0.06092862110810815)
  8225. Firing rl*prefer*rvt*predict-yes*H0*5
  8226. -->
  8227. (S1 ^operator O1919 = 0.4318887392321146)
  8228. Firing prefer*rvt*predict-yes*H0*5*v1*H1
  8229. -->
  8230. Firing prefer*rvt*predict-no*H0
  8231. -->
  8232. Firing rl*prefer*rvt*predict-no*H0*6*v1*H1*43
  8233. -->
  8234. (S1 ^operator O1920 = 0.671051122743914)
  8235. Firing rl*prefer*rvt*predict-no*H0*6
  8236. -->
  8237. (S1 ^operator O1920 = 0.3289450941277776)
  8238. Firing prefer*rvt*predict-no*H0*6*v1*H1
  8239. -->
  8240. inner elaboration loop at bottom goal.
  8241. Retracting rl*prefer*rvt*predict-no*H0*6
  8242. -->
  8243. (S1 ^operator O1918 = 0.3289450941277776)
  8244. Retracting rl*prefer*rvt*predict-no*H0*6*v1*H1*43
  8245. -->
  8246. (S1 ^operator O1918 = 0.671051122743914)
  8247. Retracting rl*prefer*rvt*predict-yes*H0*5
  8248. -->
  8249. (S1 ^operator O1917 = 0.4318887392321146)
  8250. Retracting rl*prefer*rvt*predict-yes*H0*5*v1*H1*31
  8251. -->
  8252. (S1 ^operator O1917 = -0.06092862110810815)
  8253. --- END Proposal Phase ---
  8254. --- Decision Phase ---
  8255. RL update rl*prefer*rvt*predict-no*H0*2 1 0 1 -> 1 0 1(R,m,v=1,1,0)
  8256. =>WM: (13522: S1 ^operator O1920)
  8257. 960: O: O1920 (predict-no)
  8258. --- END Decision Phase ---
  8259. --- Application Phase ---
  8260. --- Firing Productions (PE) For State At Depth 1 ---
  8261. --- Inner Elaboration Phase, active level 1 (S1) ---
  8262. Firing apply*operator
  8263. -->
  8264. (I3 ^predict-no N960 + :O )
  8265. Firing apply*operator*complete
  8266. -->
  8267. (I3 ^predict-no N959 - :O )
  8268. inner elaboration loop at bottom goal.
  8269. --- Change Working Memory (PE) ---
  8270. =>WM: (13523: I3 ^predict-no N960)
  8271. <=WM: (13509: N959 ^status complete)
  8272. <=WM: (13508: I3 ^predict-no N959)
  8273. --- Firing Productions (IE) For State At Depth 1 ---
  8274. --- Inner Elaboration Phase, active level 1 (S1) ---
  8275. Firing monitor*world
  8276. -->
  8277. I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
  8278. --- Change Working Memory (IE) ---
  8279. --- END Application Phase ---
  8280. --- Output Phase ---
  8281. ENV: Agent did: predict-no for direction L in state State-A
  8282. In State-A moving L
  8283. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  8284. predict error 0
  8285. dir: dir isU
  8286. --- END Output Phase ---
  8287. |\---- Input Phase ---
  8288. =>WM: (13527: I2 ^dir U)
  8289. =>WM: (13526: I2 ^reward 1)
  8290. =>WM: (13525: I2 ^see 0)
  8291. =>WM: (13524: N960 ^status complete)
  8292. <=WM: (13512: I2 ^dir L)
  8293. <=WM: (13511: I2 ^reward 1)
  8294. <=WM: (13510: I2 ^see 0)
  8295. =>WM: (13528: I2 ^level-1 L0-root)
  8296. <=WM: (13513: I2 ^level-1 L1-root)
  8297. --- END Input Phase ---
  8298. --- Proposal Phase ---
  8299. --- Inner Elaboration Phase, active level 1 (S1) ---
  8300. Firing elaborate*copy-see-to-output-link
  8301. -->
  8302. (I3 ^see 0 +)
  8303. Firing elaborate*reward*based*on*reward
  8304. -->
  8305. (R964 ^value 1 +)
  8306. (R1 ^reward R964 +)
  8307. Firing propose*predict-yes
  8308. -->
  8309. (O1921 ^name predict-yes +)
  8310. (S1 ^operator O1921 +)
  8311. Firing propose*predict-no
  8312. -->
  8313. (O1922 ^name predict-no +)
  8314. (S1 ^operator O1922 +)
  8315. Firing rl*prefer*rvt*predict-no*H0*2
  8316. -->
  8317. (S1 ^operator O1920 = 0.9999999999999999)
  8318. Firing rl*prefer*rvt*predict-yes*H0*1
  8319. -->
  8320. (S1 ^operator O1919 = 0.)
  8321. Firing prefer*rvt*predict-yes*H0
  8322. -->
  8323. Firing prefer*rvt*predict-no*H0
  8324. -->
  8325. Firing elaborate*copy-dir-to-output-link
  8326. -->
  8327. (I3 ^dir U +)
  8328. inner elaboration loop at bottom goal.
  8329. Retracting elaborate*copy-see-to-output-link
  8330. -->
  8331. (I3 ^see 0 +)
  8332. Retracting propose*predict-no
  8333. -->
  8334. (O1920 ^name predict-no +)
  8335. (S1 ^operator O1920 +)
  8336. Retracting propose*predict-yes
  8337. -->
  8338. (O1919 ^name predict-yes +)
  8339. (S1 ^operator O1919 +)
  8340. Retracting elaborate*reward*based*on*reward
  8341. -->
  8342. (R963 ^value 1 +)
  8343. (R1 ^reward R963 +)
  8344. Retracting elaborate*copy-dir-to-output-link
  8345. -->
  8346. (I3 ^dir L +)
  8347. Retracting rl*prefer*rvt*predict-no*H0*6
  8348. -->
  8349. (S1 ^operator O1920 = 0.3289450941277776)
  8350. Retracting rl*prefer*rvt*predict-no*H0*6*v1*H1*43
  8351. -->
  8352. (S1 ^operator O1920 = 0.671051122743914)
  8353. Retracting rl*prefer*rvt*predict-yes*H0*5
  8354. -->
  8355. (S1 ^operator O1919 = 0.4318887392321146)
  8356. Retracting rl*prefer*rvt*predict-yes*H0*5*v1*H1*31
  8357. -->
  8358. (S1 ^operator O1919 = -0.06092862110810815)
  8359. =>WM: (13535: S1 ^operator O1922 +)
  8360. =>WM: (13534: S1 ^operator O1921 +)
  8361. =>WM: (13533: I3 ^dir U)
  8362. =>WM: (13532: O1922 ^name predict-no)
  8363. =>WM: (13531: O1921 ^name predict-yes)
  8364. =>WM: (13530: R964 ^value 1)
  8365. =>WM: (13529: R1 ^reward R964)
  8366. <=WM: (13520: S1 ^operator O1919 +)
  8367. <=WM: (13521: S1 ^operator O1920 +)
  8368. <=WM: (13522: S1 ^operator O1920)
  8369. <=WM: (13519: I3 ^dir L)
  8370. <=WM: (13515: R1 ^reward R963)
  8371. <=WM: (13518: O1920 ^name predict-no)
  8372. <=WM: (13517: O1919 ^name predict-yes)
  8373. <=WM: (13516: R963 ^value 1)
  8374. --- Inner Elaboration Phase, active level 1 (S1) ---
  8375. Firing prefer*rvt*predict-yes*H0
  8376. -->
  8377. Firing rl*prefer*rvt*predict-yes*H0*1
  8378. -->
  8379. (S1 ^operator O1921 = 0.)
  8380. Firing prefer*rvt*predict-no*H0
  8381. -->
  8382. Firing rl*prefer*rvt*predict-no*H0*2
  8383. -->
  8384. (S1 ^operator O1922 = 0.9999999999999999)
  8385. inner elaboration loop at bottom goal.
  8386. Retracting rl*prefer*rvt*predict-no*H0*2
  8387. -->
  8388. (S1 ^operator O1920 = 0.9999999999999999)
  8389. Retracting rl*prefer*rvt*predict-yes*H0*1
  8390. -->
  8391. (S1 ^operator O1919 = 0.)
  8392. --- END Proposal Phase ---
  8393. --- Decision Phase ---
  8394. RL update rl*prefer*rvt*predict-no*H0*6 0.565402 -0.236456 0.328945 -> 0.565403 -0.236457 0.328946(R,m,v=1,0.903226,0.0879765)
  8395. RL update rl*prefer*rvt*predict-no*H0*6*v1*H1*43 0.434591 0.23646 0.671051 -> 0.434592 0.23646 0.671052(R,m,v=1,1,0)
  8396. =>WM: (13536: S1 ^operator O1922)
  8397. 961: O: O1922 (predict-no)
  8398. --- END Decision Phase ---
  8399. --- Application Phase ---
  8400. --- Firing Productions (PE) For State At Depth 1 ---
  8401. --- Inner Elaboration Phase, active level 1 (S1) ---
  8402. Firing apply*operator
  8403. -->
  8404. (I3 ^predict-no N961 + :O )
  8405. Firing apply*operator*complete
  8406. -->
  8407. (I3 ^predict-no N960 - :O )
  8408. inner elaboration loop at bottom goal.
  8409. --- Change Working Memory (PE) ---
  8410. =>WM: (13537: I3 ^predict-no N961)
  8411. <=WM: (13524: N960 ^status complete)
  8412. <=WM: (13523: I3 ^predict-no N960)
  8413. --- Firing Productions (IE) For State At Depth 1 ---
  8414. --- Inner Elaboration Phase, active level 1 (S1) ---
  8415. Firing monitor*world
  8416. -->
  8417. I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
  8418. --- Change Working Memory (IE) ---
  8419. --- END Application Phase ---
  8420. --- Output Phase ---
  8421. ENV: Agent did: predict-no for direction U in state State-A
  8422. In State-A moving U
  8423. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  8424. predict error 0
  8425. dir: dir isR
  8426. --- END Output Phase ---
  8427. /--- Input Phase ---
  8428. =>WM: (13541: I2 ^dir R)
  8429. =>WM: (13540: I2 ^reward 1)
  8430. =>WM: (13539: I2 ^see 0)
  8431. =>WM: (13538: N961 ^status complete)
  8432. <=WM: (13527: I2 ^dir U)
  8433. <=WM: (13526: I2 ^reward 1)
  8434. <=WM: (13525: I2 ^see 0)
  8435. =>WM: (13542: I2 ^level-1 L0-root)
  8436. <=WM: (13528: I2 ^level-1 L0-root)
  8437. --- END Input Phase ---
  8438. --- Proposal Phase ---
  8439. --- Inner Elaboration Phase, active level 1 (S1) ---
  8440. Firing rl*prefer*rvt*predict-no*H0*4*v1*H1*34
  8441. -->
  8442. (S1 ^operator O1922 = -0.07401383653737587)
  8443. Firing rl*prefer*rvt*predict-yes*H0*3*v1*H1*35
  8444. -->
  8445. (S1 ^operator O1921 = 0.2631774632268827)
  8446. Firing prefer*rvt*predict-no*H0*4*v1*H1
  8447. -->
  8448. Firing prefer*rvt*predict-yes*H0*3*v1*H1
  8449. -->
  8450. Firing elaborate*copy-see-to-output-link
  8451. -->
  8452. (I3 ^see 0 +)
  8453. Firing elaborate*reward*based*on*reward
  8454. -->
  8455. (R965 ^value 1 +)
  8456. (R1 ^reward R965 +)
  8457. Firing propose*predict-yes
  8458. -->
  8459. (O1923 ^name predict-yes +)
  8460. (S1 ^operator O1923 +)
  8461. Firing propose*predict-no
  8462. -->
  8463. (O1924 ^name predict-no +)
  8464. (S1 ^operator O1924 +)
  8465. Firing rl*prefer*rvt*predict-no*H0*4
  8466. -->
  8467. (S1 ^operator O1922 = 0.2572462853745217)
  8468. Firing rl*prefer*rvt*predict-yes*H0*3
  8469. -->
  8470. (S1 ^operator O1921 = 0.7368296698821956)
  8471. Firing prefer*rvt*predict-yes*H0
  8472. -->
  8473. Firing prefer*rvt*predict-no*H0
  8474. -->
  8475. Firing elaborate*copy-dir-to-output-link
  8476. -->
  8477. (I3 ^dir R +)
  8478. inner elaboration loop at bottom goal.
  8479. Retracting elaborate*copy-see-to-output-link
  8480. -->
  8481. (I3 ^see 0 +)
  8482. Retracting propose*predict-no
  8483. -->
  8484. (O1922 ^name predict-no +)
  8485. (S1 ^operator O1922 +)
  8486. Retracting propose*predict-yes
  8487. -->
  8488. (O1921 ^name predict-yes +)
  8489. (S1 ^operator O1921 +)
  8490. Retracting elaborate*reward*based*on*reward
  8491. -->
  8492. (R964 ^value 1 +)
  8493. (R1 ^reward R964 +)
  8494. Retracting elaborate*copy-dir-to-output-link
  8495. -->
  8496. (I3 ^dir U +)
  8497. Retracting rl*prefer*rvt*predict-no*H0*2
  8498. -->
  8499. (S1 ^operator O1922 = 0.9999999999999999)
  8500. Retracting rl*prefer*rvt*predict-yes*H0*1
  8501. -->
  8502. (S1 ^operator O1921 = 0.)
  8503. =>WM: (13549: S1 ^operator O1924 +)
  8504. =>WM: (13548: S1 ^operator O1923 +)
  8505. =>WM: (13547: I3 ^dir R)
  8506. =>WM: (13546: O1924 ^name predict-no)
  8507. =>WM: (13545: O1923 ^name predict-yes)
  8508. =>WM: (13544: R965 ^value 1)
  8509. =>WM: (13543: R1 ^reward R965)
  8510. <=WM: (13534: S1 ^operator O1921 +)
  8511. <=WM: (13535: S1 ^operator O1922 +)
  8512. <=WM: (13536: S1 ^operator O1922)
  8513. <=WM: (13533: I3 ^dir U)
  8514. <=WM: (13529: R1 ^reward R964)
  8515. <=WM: (13532: O1922 ^name predict-no)
  8516. <=WM: (13531: O1921 ^name predict-yes)
  8517. <=WM: (13530: R964 ^value 1)
  8518. --- Inner Elaboration Phase, active level 1 (S1) ---
  8519. Firing prefer*rvt*predict-yes*H0
  8520. -->
  8521. Firing rl*prefer*rvt*predict-yes*H0*3*v1*H1*35
  8522. -->
  8523. (S1 ^operator O1923 = 0.2631774632268827)
  8524. Firing rl*prefer*rvt*predict-yes*H0*3
  8525. -->
  8526. (S1 ^operator O1923 = 0.7368296698821956)
  8527. Firing prefer*rvt*predict-yes*H0*3*v1*H1
  8528. -->
  8529. Firing prefer*rvt*predict-no*H0
  8530. -->
  8531. Firing rl*prefer*rvt*predict-no*H0*4*v1*H1*34
  8532. -->
  8533. (S1 ^operator O1924 = -0.07401383653737587)
  8534. Firing rl*prefer*rvt*predict-no*H0*4
  8535. -->
  8536. (S1 ^operator O1924 = 0.2572462853745217)
  8537. Firing prefer*rvt*predict-no*H0*4*v1*H1
  8538. -->
  8539. inner elaboration loop at bottom goal.
  8540. Retracting rl*prefer*rvt*predict-no*H0*4
  8541. -->
  8542. (S1 ^operator O1922 = 0.2572462853745217)
  8543. Retracting rl*prefer*rvt*predict-no*H0*4*v1*H1*34
  8544. -->
  8545. (S1 ^operator O1922 = -0.07401383653737587)
  8546. Retracting rl*prefer*rvt*predict-yes*H0*3
  8547. -->
  8548. (S1 ^operator O1921 = 0.7368296698821956)
  8549. Retracting rl*prefer*rvt*predict-yes*H0*3*v1*H1*35
  8550. -->
  8551. (S1 ^operator O1921 = 0.2631774632268827)
  8552. --- END Proposal Phase ---
  8553. --- Decision Phase ---
  8554. RL update rl*prefer*rvt*predict-no*H0*2 1 0 1 -> 1 0 1(R,m,v=1,1,0)
  8555. =>WM: (13550: S1 ^operator O1923)
  8556. 962: O: O1923 (predict-yes)
  8557. --- END Decision Phase ---
  8558. --- Application Phase ---
  8559. --- Firing Productions (PE) For State At Depth 1 ---
  8560. --- Inner Elaboration Phase, active level 1 (S1) ---
  8561. Firing apply*operator
  8562. -->
  8563. (I3 ^predict-yes N962 + :O )
  8564. Firing apply*operator*complete
  8565. -->
  8566. (I3 ^predict-no N961 - :O )
  8567. inner elaboration loop at bottom goal.
  8568. --- Change Working Memory (PE) ---
  8569. =>WM: (13551: I3 ^predict-yes N962)
  8570. <=WM: (13538: N961 ^status complete)
  8571. <=WM: (13537: I3 ^predict-no N961)
  8572. --- Firing Productions (IE) For State At Depth 1 ---
  8573. --- Inner Elaboration Phase, active level 1 (S1) ---
  8574. Firing monitor*world
  8575. -->
  8576. I see 1 and I'm going to do: predict-yes inner elaboration loop at bottom goal.
  8577. --- Change Working Memory (IE) ---
  8578. --- END Application Phase ---
  8579. --- Output Phase ---
  8580. ENV: Agent did: predict-yes for direction R in state State-A
  8581. In State-A moving R
  8582. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  8583. predict error 0
  8584. dir: dir isU
  8585. --- END Output Phase ---
  8586. |\---- Input Phase ---
  8587. =>WM: (13555: I2 ^dir U)
  8588. =>WM: (13554: I2 ^reward 1)
  8589. =>WM: (13553: I2 ^see 1)
  8590. =>WM: (13552: N962 ^status complete)
  8591. <=WM: (13541: I2 ^dir R)
  8592. <=WM: (13540: I2 ^reward 1)
  8593. <=WM: (13539: I2 ^see 0)
  8594. =>WM: (13556: I2 ^level-1 R1-root)
  8595. <=WM: (13542: I2 ^level-1 L0-root)
  8596. --- END Input Phase ---
  8597. --- Proposal Phase ---
  8598. --- Inner Elaboration Phase, active level 1 (S1) ---
  8599. Firing elaborate*copy-see-to-output-link
  8600. -->
  8601. (I3 ^see 1 +)
  8602. Firing elaborate*reward*based*on*reward
  8603. -->
  8604. (R966 ^value 1 +)
  8605. (R1 ^reward R966 +)
  8606. Firing propose*predict-yes
  8607. -->
  8608. (O1925 ^name predict-yes +)
  8609. (S1 ^operator O1925 +)
  8610. Firing propose*predict-no
  8611. -->
  8612. (O1926 ^name predict-no +)
  8613. (S1 ^operator O1926 +)
  8614. Firing rl*prefer*rvt*predict-no*H0*2
  8615. -->
  8616. (S1 ^operator O1924 = 0.9999999999999999)
  8617. Firing rl*prefer*rvt*predict-yes*H0*1
  8618. -->
  8619. (S1 ^operator O1923 = 0.)
  8620. Firing prefer*rvt*predict-yes*H0
  8621. -->
  8622. Firing prefer*rvt*predict-no*H0
  8623. -->
  8624. Firing elaborate*copy-dir-to-output-link
  8625. -->
  8626. (I3 ^dir U +)
  8627. inner elaboration loop at bottom goal.
  8628. Retracting elaborate*copy-see-to-output-link
  8629. -->
  8630. (I3 ^see 0 +)
  8631. Retracting propose*predict-no
  8632. -->
  8633. (O1924 ^name predict-no +)
  8634. (S1 ^operator O1924 +)
  8635. Retracting propose*predict-yes
  8636. -->
  8637. (O1923 ^name predict-yes +)
  8638. (S1 ^operator O1923 +)
  8639. Retracting elaborate*reward*based*on*reward
  8640. -->
  8641. (R965 ^value 1 +)
  8642. (R1 ^reward R965 +)
  8643. Retracting elaborate*copy-dir-to-output-link
  8644. -->
  8645. (I3 ^dir R +)
  8646. Retracting rl*prefer*rvt*predict-no*H0*4
  8647. -->
  8648. (S1 ^operator O1924 = 0.2572462853745217)
  8649. Retracting rl*prefer*rvt*predict-no*H0*4*v1*H1*34
  8650. -->
  8651. (S1 ^operator O1924 = -0.07401383653737587)
  8652. Retracting rl*prefer*rvt*predict-yes*H0*3
  8653. -->
  8654. (S1 ^operator O1923 = 0.7368296698821956)
  8655. Retracting rl*prefer*rvt*predict-yes*H0*3*v1*H1*35
  8656. -->
  8657. (S1 ^operator O1923 = 0.2631774632268827)
  8658. =>WM: (13564: S1 ^operator O1926 +)
  8659. =>WM: (13563: S1 ^operator O1925 +)
  8660. =>WM: (13562: I3 ^dir U)
  8661. =>WM: (13561: O1926 ^name predict-no)
  8662. =>WM: (13560: O1925 ^name predict-yes)
  8663. =>WM: (13559: R966 ^value 1)
  8664. =>WM: (13558: R1 ^reward R966)
  8665. =>WM: (13557: I3 ^see 1)
  8666. <=WM: (13548: S1 ^operator O1923 +)
  8667. <=WM: (13550: S1 ^operator O1923)
  8668. <=WM: (13549: S1 ^operator O1924 +)
  8669. <=WM: (13547: I3 ^dir R)
  8670. <=WM: (13543: R1 ^reward R965)
  8671. <=WM: (13514: I3 ^see 0)
  8672. <=WM: (13546: O1924 ^name predict-no)
  8673. <=WM: (13545: O1923 ^name predict-yes)
  8674. <=WM: (13544: R965 ^value 1)
  8675. --- Inner Elaboration Phase, active level 1 (S1) ---
  8676. Firing prefer*rvt*predict-yes*H0
  8677. -->
  8678. Firing rl*prefer*rvt*predict-yes*H0*1
  8679. -->
  8680. (S1 ^operator O1925 = 0.)
  8681. Firing prefer*rvt*predict-no*H0
  8682. -->
  8683. Firing rl*prefer*rvt*predict-no*H0*2
  8684. -->
  8685. (S1 ^operator O1926 = 0.9999999999999999)
  8686. inner elaboration loop at bottom goal.
  8687. Retracting rl*prefer*rvt*predict-no*H0*2
  8688. -->
  8689. (S1 ^operator O1924 = 0.9999999999999999)
  8690. Retracting rl*prefer*rvt*predict-yes*H0*1
  8691. -->
  8692. (S1 ^operator O1923 = 0.)
  8693. --- END Proposal Phase ---
  8694. --- Decision Phase ---
  8695. RL update rl*prefer*rvt*predict-yes*H0*3 0.748237 -0.0114068 0.73683 -> 0.748236 -0.0114076 0.736829(R,m,v=1,0.893082,0.0960911)
  8696. RL update rl*prefer*rvt*predict-yes*H0*3*v1*H1*35 0.251765 0.0114121 0.263177 -> 0.251765 0.0114113 0.263176(R,m,v=1,1,0)
  8697. =>WM: (13565: S1 ^operator O1926)
  8698. 963: O: O1926 (predict-no)
  8699. --- END Decision Phase ---
  8700. --- Application Phase ---
  8701. --- Firing Productions (PE) For State At Depth 1 ---
  8702. --- Inner Elaboration Phase, active level 1 (S1) ---
  8703. Firing apply*operator
  8704. -->
  8705. (I3 ^predict-no N963 + :O )
  8706. Firing apply*operator*complete
  8707. -->
  8708. (I3 ^predict-yes N962 - :O )
  8709. inner elaboration loop at bottom goal.
  8710. --- Change Working Memory (PE) ---
  8711. =>WM: (13566: I3 ^predict-no N963)
  8712. <=WM: (13552: N962 ^status complete)
  8713. <=WM: (13551: I3 ^predict-yes N962)
  8714. --- Firing Productions (IE) For State At Depth 1 ---
  8715. --- Inner Elaboration Phase, active level 1 (S1) ---
  8716. Firing monitor*world
  8717. -->
  8718. I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
  8719. --- Change Working Memory (IE) ---
  8720. --- END Application Phase ---
  8721. --- Output Phase ---
  8722. ENV: Agent did: predict-no for direction U in state State-B
  8723. In State-B moving U
  8724. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  8725. predict error 0
  8726. dir: dir isL
  8727. --- END Output Phase ---
  8728. /|\--- Input Phase ---
  8729. =>WM: (13570: I2 ^dir L)
  8730. =>WM: (13569: I2 ^reward 1)
  8731. =>WM: (13568: I2 ^see 0)
  8732. =>WM: (13567: N963 ^status complete)
  8733. <=WM: (13555: I2 ^dir U)
  8734. <=WM: (13554: I2 ^reward 1)
  8735. <=WM: (13553: I2 ^see 1)
  8736. =>WM: (13571: I2 ^level-1 R1-root)
  8737. <=WM: (13556: I2 ^level-1 R1-root)
  8738. --- END Input Phase ---
  8739. --- Proposal Phase ---
  8740. --- Inner Elaboration Phase, active level 1 (S1) ---
  8741. Firing rl*prefer*rvt*predict-yes*H0*5*v1*H1*45
  8742. -->
  8743. (S1 ^operator O1925 = 0.5681037396512361)
  8744. Firing rl*prefer*rvt*predict-no*H0*6*v1*H1*44
  8745. -->
  8746. (S1 ^operator O1926 = -0.1549421060161498)
  8747. Firing prefer*rvt*predict-no*H0*6*v1*H1
  8748. -->
  8749. Firing prefer*rvt*predict-yes*H0*5*v1*H1
  8750. -->
  8751. Firing elaborate*copy-see-to-output-link
  8752. -->
  8753. (I3 ^see 0 +)
  8754. Firing elaborate*reward*based*on*reward
  8755. -->
  8756. (R967 ^value 1 +)
  8757. (R1 ^reward R967 +)
  8758. Firing propose*predict-yes
  8759. -->
  8760. (O1927 ^name predict-yes +)
  8761. (S1 ^operator O1927 +)
  8762. Firing propose*predict-no
  8763. -->
  8764. (O1928 ^name predict-no +)
  8765. (S1 ^operator O1928 +)
  8766. Firing rl*prefer*rvt*predict-no*H0*6
  8767. -->
  8768. (S1 ^operator O1926 = 0.3289456615970239)
  8769. Firing rl*prefer*rvt*predict-yes*H0*5
  8770. -->
  8771. (S1 ^operator O1925 = 0.4318887392321146)
  8772. Firing prefer*rvt*predict-yes*H0
  8773. -->
  8774. Firing prefer*rvt*predict-no*H0
  8775. -->
  8776. Firing elaborate*copy-dir-to-output-link
  8777. -->
  8778. (I3 ^dir L +)
  8779. inner elaboration loop at bottom goal.
  8780. Retracting elaborate*copy-see-to-output-link
  8781. -->
  8782. (I3 ^see 1 +)
  8783. Retracting propose*predict-no
  8784. -->
  8785. (O1926 ^name predict-no +)
  8786. (S1 ^operator O1926 +)
  8787. Retracting propose*predict-yes
  8788. -->
  8789. (O1925 ^name predict-yes +)
  8790. (S1 ^operator O1925 +)
  8791. Retracting elaborate*reward*based*on*reward
  8792. -->
  8793. (R966 ^value 1 +)
  8794. (R1 ^reward R966 +)
  8795. Retracting elaborate*copy-dir-to-output-link
  8796. -->
  8797. (I3 ^dir U +)
  8798. Retracting rl*prefer*rvt*predict-no*H0*2
  8799. -->
  8800. (S1 ^operator O1926 = 0.9999999999999999)
  8801. Retracting rl*prefer*rvt*predict-yes*H0*1
  8802. -->
  8803. (S1 ^operator O1925 = 0.)
  8804. =>WM: (13579: S1 ^operator O1928 +)
  8805. =>WM: (13578: S1 ^operator O1927 +)
  8806. =>WM: (13577: I3 ^dir L)
  8807. =>WM: (13576: O1928 ^name predict-no)
  8808. =>WM: (13575: O1927 ^name predict-yes)
  8809. =>WM: (13574: R967 ^value 1)
  8810. =>WM: (13573: R1 ^reward R967)
  8811. =>WM: (13572: I3 ^see 0)
  8812. <=WM: (13563: S1 ^operator O1925 +)
  8813. <=WM: (13564: S1 ^operator O1926 +)
  8814. <=WM: (13565: S1 ^operator O1926)
  8815. <=WM: (13562: I3 ^dir U)
  8816. <=WM: (13558: R1 ^reward R966)
  8817. <=WM: (13557: I3 ^see 1)
  8818. <=WM: (13561: O1926 ^name predict-no)
  8819. <=WM: (13560: O1925 ^name predict-yes)
  8820. <=WM: (13559: R966 ^value 1)
  8821. --- Inner Elaboration Phase, active level 1 (S1) ---
  8822. Firing prefer*rvt*predict-yes*H0
  8823. -->
  8824. Firing rl*prefer*rvt*predict-yes*H0*5*v1*H1*45
  8825. -->
  8826. (S1 ^operator O1927 = 0.5681037396512361)
  8827. Firing rl*prefer*rvt*predict-yes*H0*5
  8828. -->
  8829. (S1 ^operator O1927 = 0.4318887392321146)
  8830. Firing prefer*rvt*predict-yes*H0*5*v1*H1
  8831. -->
  8832. Firing prefer*rvt*predict-no*H0
  8833. -->
  8834. Firing rl*prefer*rvt*predict-no*H0*6*v1*H1*44
  8835. -->
  8836. (S1 ^operator O1928 = -0.1549421060161498)
  8837. Firing rl*prefer*rvt*predict-no*H0*6
  8838. -->
  8839. (S1 ^operator O1928 = 0.3289456615970239)
  8840. Firing prefer*rvt*predict-no*H0*6*v1*H1
  8841. -->
  8842. inner elaboration loop at bottom goal.
  8843. Retracting rl*prefer*rvt*predict-no*H0*6
  8844. -->
  8845. (S1 ^operator O1926 = 0.3289456615970239)
  8846. Retracting rl*prefer*rvt*predict-no*H0*6*v1*H1*44
  8847. -->
  8848. (S1 ^operator O1926 = -0.1549421060161498)
  8849. Retracting rl*prefer*rvt*predict-yes*H0*5
  8850. -->
  8851. (S1 ^operator O1925 = 0.4318887392321146)
  8852. Retracting rl*prefer*rvt*predict-yes*H0*5*v1*H1*45
  8853. -->
  8854. (S1 ^operator O1925 = 0.5681037396512361)
  8855. --- END Proposal Phase ---
  8856. --- Decision Phase ---
  8857. RL update rl*prefer*rvt*predict-no*H0*2 1 0 1 -> 1 0 1(R,m,v=1,1,0)
  8858. =>WM: (13580: S1 ^operator O1927)
  8859. 964: O: O1927 (predict-yes)
  8860. --- END Decision Phase ---
  8861. --- Application Phase ---
  8862. --- Firing Productions (PE) For State At Depth 1 ---
  8863. --- Inner Elaboration Phase, active level 1 (S1) ---
  8864. Firing apply*operator
  8865. -->
  8866. (I3 ^predict-yes N964 + :O )
  8867. Firing apply*operator*complete
  8868. -->
  8869. (I3 ^predict-no N963 - :O )
  8870. inner elaboration loop at bottom goal.
  8871. --- Change Working Memory (PE) ---
  8872. =>WM: (13581: I3 ^predict-yes N964)
  8873. <=WM: (13567: N963 ^status complete)
  8874. <=WM: (13566: I3 ^predict-no N963)
  8875. --- Firing Productions (IE) For State At Depth 1 ---
  8876. --- Inner Elaboration Phase, active level 1 (S1) ---
  8877. Firing monitor*world
  8878. -->
  8879. I see 1 and I'm going to do: predict-yes inner elaboration loop at bottom goal.
  8880. --- Change Working Memory (IE) ---
  8881. --- END Application Phase ---
  8882. --- Output Phase ---
  8883. ENV: Agent did: predict-yes for direction L in state State-B
  8884. In State-B moving L
  8885. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  8886. predict error 0
  8887. dir: dir isU
  8888. --- END Output Phase ---
  8889. -/--- Input Phase ---
  8890. =>WM: (13585: I2 ^dir U)
  8891. =>WM: (13584: I2 ^reward 1)
  8892. =>WM: (13583: I2 ^see 1)
  8893. =>WM: (13582: N964 ^status complete)
  8894. <=WM: (13570: I2 ^dir L)
  8895. <=WM: (13569: I2 ^reward 1)
  8896. <=WM: (13568: I2 ^see 0)
  8897. =>WM: (13586: I2 ^level-1 L1-root)
  8898. <=WM: (13571: I2 ^level-1 R1-root)
  8899. --- END Input Phase ---
  8900. --- Proposal Phase ---
  8901. --- Inner Elaboration Phase, active level 1 (S1) ---
  8902. Firing elaborate*copy-see-to-output-link
  8903. -->
  8904. (I3 ^see 1 +)
  8905. Firing elaborate*reward*based*on*reward
  8906. -->
  8907. (R968 ^value 1 +)
  8908. (R1 ^reward R968 +)
  8909. Firing propose*predict-yes
  8910. -->
  8911. (O1929 ^name predict-yes +)
  8912. (S1 ^operator O1929 +)
  8913. Firing propose*predict-no
  8914. -->
  8915. (O1930 ^name predict-no +)
  8916. (S1 ^operator O1930 +)
  8917. Firing rl*prefer*rvt*predict-no*H0*2
  8918. -->
  8919. (S1 ^operator O1928 = 0.9999999999999999)
  8920. Firing rl*prefer*rvt*predict-yes*H0*1
  8921. -->
  8922. (S1 ^operator O1927 = 0.)
  8923. Firing prefer*rvt*predict-yes*H0
  8924. -->
  8925. Firing prefer*rvt*predict-no*H0
  8926. -->
  8927. Firing elaborate*copy-dir-to-output-link
  8928. -->
  8929. (I3 ^dir U +)
  8930. inner elaboration loop at bottom goal.
  8931. Retracting elaborate*copy-see-to-output-link
  8932. -->
  8933. (I3 ^see 0 +)
  8934. Retracting propose*predict-no
  8935. -->
  8936. (O1928 ^name predict-no +)
  8937. (S1 ^operator O1928 +)
  8938. Retracting propose*predict-yes
  8939. -->
  8940. (O1927 ^name predict-yes +)
  8941. (S1 ^operator O1927 +)
  8942. Retracting elaborate*reward*based*on*reward
  8943. -->
  8944. (R967 ^value 1 +)
  8945. (R1 ^reward R967 +)
  8946. Retracting elaborate*copy-dir-to-output-link
  8947. -->
  8948. (I3 ^dir L +)
  8949. Retracting rl*prefer*rvt*predict-no*H0*6
  8950. -->
  8951. (S1 ^operator O1928 = 0.3289456615970239)
  8952. Retracting rl*prefer*rvt*predict-no*H0*6*v1*H1*44
  8953. -->
  8954. (S1 ^operator O1928 = -0.1549421060161498)
  8955. Retracting rl*prefer*rvt*predict-yes*H0*5
  8956. -->
  8957. (S1 ^operator O1927 = 0.4318887392321146)
  8958. Retracting rl*prefer*rvt*predict-yes*H0*5*v1*H1*45
  8959. -->
  8960. (S1 ^operator O1927 = 0.5681037396512361)
  8961. =>WM: (13594: S1 ^operator O1930 +)
  8962. =>WM: (13593: S1 ^operator O1929 +)
  8963. =>WM: (13592: I3 ^dir U)
  8964. =>WM: (13591: O1930 ^name predict-no)
  8965. =>WM: (13590: O1929 ^name predict-yes)
  8966. =>WM: (13589: R968 ^value 1)
  8967. =>WM: (13588: R1 ^reward R968)
  8968. =>WM: (13587: I3 ^see 1)
  8969. <=WM: (13578: S1 ^operator O1927 +)
  8970. <=WM: (13580: S1 ^operator O1927)
  8971. <=WM: (13579: S1 ^operator O1928 +)
  8972. <=WM: (13577: I3 ^dir L)
  8973. <=WM: (13573: R1 ^reward R967)
  8974. <=WM: (13572: I3 ^see 0)
  8975. <=WM: (13576: O1928 ^name predict-no)
  8976. <=WM: (13575: O1927 ^name predict-yes)
  8977. <=WM: (13574: R967 ^value 1)
  8978. --- Inner Elaboration Phase, active level 1 (S1) ---
  8979. Firing prefer*rvt*predict-yes*H0
  8980. -->
  8981. Firing rl*prefer*rvt*predict-yes*H0*1
  8982. -->
  8983. (S1 ^operator O1929 = 0.)
  8984. Firing prefer*rvt*predict-no*H0
  8985. -->
  8986. Firing rl*prefer*rvt*predict-no*H0*2
  8987. -->
  8988. (S1 ^operator O1930 = 0.9999999999999999)
  8989. inner elaboration loop at bottom goal.
  8990. Retracting rl*prefer*rvt*predict-no*H0*2
  8991. -->
  8992. (S1 ^operator O1928 = 0.9999999999999999)
  8993. Retracting rl*prefer*rvt*predict-yes*H0*1
  8994. -->
  8995. (S1 ^operator O1927 = 0.)
  8996. --- END Proposal Phase ---
  8997. --- Decision Phase ---
  8998. RL update rl*prefer*rvt*predict-yes*H0*5 0.683775 -0.251886 0.431889 -> 0.683776 -0.251886 0.43189(R,m,v=1,0.920732,0.0734326)
  8999. RL update rl*prefer*rvt*predict-yes*H0*5*v1*H1*45 0.316218 0.251886 0.568104 -> 0.316219 0.251886 0.568105(R,m,v=1,1,0)
  9000. =>WM: (13595: S1 ^operator O1930)
  9001. 965: O: O1930 (predict-no)
  9002. --- END Decision Phase ---
  9003. --- Application Phase ---
  9004. --- Firing Productions (PE) For State At Depth 1 ---
  9005. --- Inner Elaboration Phase, active level 1 (S1) ---
  9006. Firing apply*operator
  9007. -->
  9008. (I3 ^predict-no N965 + :O )
  9009. Firing apply*operator*complete
  9010. -->
  9011. (I3 ^predict-yes N964 - :O )
  9012. inner elaboration loop at bottom goal.
  9013. --- Change Working Memory (PE) ---
  9014. =>WM: (13596: I3 ^predict-no N965)
  9015. <=WM: (13582: N964 ^status complete)
  9016. <=WM: (13581: I3 ^predict-yes N964)
  9017. --- Firing Productions (IE) For State At Depth 1 ---
  9018. --- Inner Elaboration Phase, active level 1 (S1) ---
  9019. Firing monitor*world
  9020. -->
  9021. I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
  9022. --- Change Working Memory (IE) ---
  9023. --- END Application Phase ---
  9024. --- Output Phase ---
  9025. ENV: Agent did: predict-no for direction U in state State-A
  9026. In State-A moving U
  9027. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  9028. predict error 0
  9029. dir: dir isL
  9030. --- END Output Phase ---
  9031. |\--- Input Phase ---
  9032. =>WM: (13600: I2 ^dir L)
  9033. =>WM: (13599: I2 ^reward 1)
  9034. =>WM: (13598: I2 ^see 0)
  9035. =>WM: (13597: N965 ^status complete)
  9036. <=WM: (13585: I2 ^dir U)
  9037. <=WM: (13584: I2 ^reward 1)
  9038. <=WM: (13583: I2 ^see 1)
  9039. =>WM: (13601: I2 ^level-1 L1-root)
  9040. <=WM: (13586: I2 ^level-1 L1-root)
  9041. --- END Input Phase ---
  9042. --- Proposal Phase ---
  9043. --- Inner Elaboration Phase, active level 1 (S1) ---
  9044. Firing rl*prefer*rvt*predict-no*H0*6*v1*H1*43
  9045. -->
  9046. (S1 ^operator O1930 = 0.6710516902131602)
  9047. Firing rl*prefer*rvt*predict-yes*H0*5*v1*H1*31
  9048. -->
  9049. (S1 ^operator O1929 = -0.06092862110810815)
  9050. Firing prefer*rvt*predict-no*H0*6*v1*H1
  9051. -->
  9052. Firing prefer*rvt*predict-yes*H0*5*v1*H1
  9053. -->
  9054. Firing elaborate*copy-see-to-output-link
  9055. -->
  9056. (I3 ^see 0 +)
  9057. Firing elaborate*reward*based*on*reward
  9058. -->
  9059. (R969 ^value 1 +)
  9060. (R1 ^reward R969 +)
  9061. Firing propose*predict-yes
  9062. -->
  9063. (O1931 ^name predict-yes +)
  9064. (S1 ^operator O1931 +)
  9065. Firing propose*predict-no
  9066. -->
  9067. (O1932 ^name predict-no +)
  9068. (S1 ^operator O1932 +)
  9069. Firing rl*prefer*rvt*predict-no*H0*6
  9070. -->
  9071. (S1 ^operator O1930 = 0.3289456615970239)
  9072. Firing rl*prefer*rvt*predict-yes*H0*5
  9073. -->
  9074. (S1 ^operator O1929 = 0.431889867399612)
  9075. Firing prefer*rvt*predict-yes*H0
  9076. -->
  9077. Firing prefer*rvt*predict-no*H0
  9078. -->
  9079. Firing elaborate*copy-dir-to-output-link
  9080. -->
  9081. (I3 ^dir L +)
  9082. inner elaboration loop at bottom goal.
  9083. Retracting elaborate*copy-see-to-output-link
  9084. -->
  9085. (I3 ^see 1 +)
  9086. Retracting propose*predict-no
  9087. -->
  9088. (O1930 ^name predict-no +)
  9089. (S1 ^operator O1930 +)
  9090. Retracting propose*predict-yes
  9091. -->
  9092. (O1929 ^name predict-yes +)
  9093. (S1 ^operator O1929 +)
  9094. Retracting elaborate*reward*based*on*reward
  9095. -->
  9096. (R968 ^value 1 +)
  9097. (R1 ^reward R968 +)
  9098. Retracting elaborate*copy-dir-to-output-link
  9099. -->
  9100. (I3 ^dir U +)
  9101. Retracting rl*prefer*rvt*predict-no*H0*2
  9102. -->
  9103. (S1 ^operator O1930 = 0.9999999999999999)
  9104. Retracting rl*prefer*rvt*predict-yes*H0*1
  9105. -->
  9106. (S1 ^operator O1929 = 0.)
  9107. =>WM: (13609: S1 ^operator O1932 +)
  9108. =>WM: (13608: S1 ^operator O1931 +)
  9109. =>WM: (13607: I3 ^dir L)
  9110. =>WM: (13606: O1932 ^name predict-no)
  9111. =>WM: (13605: O1931 ^name predict-yes)
  9112. =>WM: (13604: R969 ^value 1)
  9113. =>WM: (13603: R1 ^reward R969)
  9114. =>WM: (13602: I3 ^see 0)
  9115. <=WM: (13593: S1 ^operator O1929 +)
  9116. <=WM: (13594: S1 ^operator O1930 +)
  9117. <=WM: (13595: S1 ^operator O1930)
  9118. <=WM: (13592: I3 ^dir U)
  9119. <=WM: (13588: R1 ^reward R968)
  9120. <=WM: (13587: I3 ^see 1)
  9121. <=WM: (13591: O1930 ^name predict-no)
  9122. <=WM: (13590: O1929 ^name predict-yes)
  9123. <=WM: (13589: R968 ^value 1)
  9124. --- Inner Elaboration Phase, active level 1 (S1) ---
  9125. Firing prefer*rvt*predict-yes*H0
  9126. -->
  9127. Firing rl*prefer*rvt*predict-yes*H0*5*v1*H1*31
  9128. -->
  9129. (S1 ^operator O1931 = -0.06092862110810815)
  9130. Firing rl*prefer*rvt*predict-yes*H0*5
  9131. -->
  9132. (S1 ^operator O1931 = 0.431889867399612)
  9133. Firing prefer*rvt*predict-yes*H0*5*v1*H1
  9134. -->
  9135. Firing prefer*rvt*predict-no*H0
  9136. -->
  9137. Firing rl*prefer*rvt*predict-no*H0*6*v1*H1*43
  9138. -->
  9139. (S1 ^operator O1932 = 0.6710516902131602)
  9140. Firing rl*prefer*rvt*predict-no*H0*6
  9141. -->
  9142. (S1 ^operator O1932 = 0.3289456615970239)
  9143. Firing prefer*rvt*predict-no*H0*6*v1*H1
  9144. -->
  9145. inner elaboration loop at bottom goal.
  9146. Retracting rl*prefer*rvt*predict-no*H0*6
  9147. -->
  9148. (S1 ^operator O1930 = 0.3289456615970239)
  9149. Retracting rl*prefer*rvt*predict-no*H0*6*v1*H1*43
  9150. -->
  9151. (S1 ^operator O1930 = 0.6710516902131602)
  9152. Retracting rl*prefer*rvt*predict-yes*H0*5
  9153. -->
  9154. (S1 ^operator O1929 = 0.431889867399612)
  9155. Retracting rl*prefer*rvt*predict-yes*H0*5*v1*H1*31
  9156. -->
  9157. (S1 ^operator O1929 = -0.06092862110810815)
  9158. --- END Proposal Phase ---
  9159. --- Decision Phase ---
  9160. RL update rl*prefer*rvt*predict-no*H0*2 1 0 1 -> 1 0 1(R,m,v=1,1,0)
  9161. =>WM: (13610: S1 ^operator O1932)
  9162. 966: O: O1932 (predict-no)
  9163. --- END Decision Phase ---
  9164. --- Application Phase ---
  9165. --- Firing Productions (PE) For State At Depth 1 ---
  9166. --- Inner Elaboration Phase, active level 1 (S1) ---
  9167. Firing apply*operator
  9168. -->
  9169. (I3 ^predict-no N966 + :O )
  9170. Firing apply*operator*complete
  9171. -->
  9172. (I3 ^predict-no N965 - :O )
  9173. inner elaboration loop at bottom goal.
  9174. --- Change Working Memory (PE) ---
  9175. =>WM: (13611: I3 ^predict-no N966)
  9176. <=WM: (13597: N965 ^status complete)
  9177. <=WM: (13596: I3 ^predict-no N965)
  9178. --- Firing Productions (IE) For State At Depth 1 ---
  9179. --- Inner Elaboration Phase, active level 1 (S1) ---
  9180. Firing monitor*world
  9181. -->
  9182. I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
  9183. --- Change Working Memory (IE) ---
  9184. --- END Application Phase ---
  9185. --- Output Phase ---
  9186. ENV: Agent did: predict-no for direction L in state State-A
  9187. In State-A moving L
  9188. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  9189. predict error 0
  9190. dir: dir isR
  9191. --- END Output Phase ---
  9192. -/|--- Input Phase ---
  9193. =>WM: (13615: I2 ^dir R)
  9194. =>WM: (13614: I2 ^reward 1)
  9195. =>WM: (13613: I2 ^see 0)
  9196. =>WM: (13612: N966 ^status complete)
  9197. <=WM: (13600: I2 ^dir L)
  9198. <=WM: (13599: I2 ^reward 1)
  9199. <=WM: (13598: I2 ^see 0)
  9200. =>WM: (13616: I2 ^level-1 L0-root)
  9201. <=WM: (13601: I2 ^level-1 L1-root)
  9202. --- END Input Phase ---
  9203. --- Proposal Phase ---
  9204. --- Inner Elaboration Phase, active level 1 (S1) ---
  9205. Firing rl*prefer*rvt*predict-no*H0*4*v1*H1*34
  9206. -->
  9207. (S1 ^operator O1932 = -0.07401383653737587)
  9208. Firing rl*prefer*rvt*predict-yes*H0*3*v1*H1*35
  9209. -->
  9210. (S1 ^operator O1931 = 0.2631763932605209)
  9211. Firing prefer*rvt*predict-no*H0*4*v1*H1
  9212. -->
  9213. Firing prefer*rvt*predict-yes*H0*3*v1*H1
  9214. -->
  9215. Firing elaborate*copy-see-to-output-link
  9216. -->
  9217. (I3 ^see 0 +)
  9218. Firing elaborate*reward*based*on*reward
  9219. -->
  9220. (R970 ^value 1 +)
  9221. (R1 ^reward R970 +)
  9222. Firing propose*predict-yes
  9223. -->
  9224. (O1933 ^name predict-yes +)
  9225. (S1 ^operator O1933 +)
  9226. Firing propose*predict-no
  9227. -->
  9228. (O1934 ^name predict-no +)
  9229. (S1 ^operator O1934 +)
  9230. Firing rl*prefer*rvt*predict-no*H0*4
  9231. -->
  9232. (S1 ^operator O1932 = 0.2572462853745217)
  9233. Firing rl*prefer*rvt*predict-yes*H0*3
  9234. -->
  9235. (S1 ^operator O1931 = 0.7368285999158338)
  9236. Firing prefer*rvt*predict-yes*H0
  9237. -->
  9238. Firing prefer*rvt*predict-no*H0
  9239. -->
  9240. Firing elaborate*copy-dir-to-output-link
  9241. -->
  9242. (I3 ^dir R +)
  9243. inner elaboration loop at bottom goal.
  9244. Retracting elaborate*copy-see-to-output-link
  9245. -->
  9246. (I3 ^see 0 +)
  9247. Retracting propose*predict-no
  9248. -->
  9249. (O1932 ^name predict-no +)
  9250. (S1 ^operator O1932 +)
  9251. Retracting propose*predict-yes
  9252. -->
  9253. (O1931 ^name predict-yes +)
  9254. (S1 ^operator O1931 +)
  9255. Retracting elaborate*reward*based*on*reward
  9256. -->
  9257. (R969 ^value 1 +)
  9258. (R1 ^reward R969 +)
  9259. Retracting elaborate*copy-dir-to-output-link
  9260. -->
  9261. (I3 ^dir L +)
  9262. Retracting rl*prefer*rvt*predict-no*H0*6
  9263. -->
  9264. (S1 ^operator O1932 = 0.3289456615970239)
  9265. Retracting rl*prefer*rvt*predict-no*H0*6*v1*H1*43
  9266. -->
  9267. (S1 ^operator O1932 = 0.6710516902131602)
  9268. Retracting rl*prefer*rvt*predict-yes*H0*5
  9269. -->
  9270. (S1 ^operator O1931 = 0.431889867399612)
  9271. Retracting rl*prefer*rvt*predict-yes*H0*5*v1*H1*31
  9272. -->
  9273. (S1 ^operator O1931 = -0.06092862110810815)
  9274. =>WM: (13623: S1 ^operator O1934 +)
  9275. =>WM: (13622: S1 ^operator O1933 +)
  9276. =>WM: (13621: I3 ^dir R)
  9277. =>WM: (13620: O1934 ^name predict-no)
  9278. =>WM: (13619: O1933 ^name predict-yes)
  9279. =>WM: (13618: R970 ^value 1)
  9280. =>WM: (13617: R1 ^reward R970)
  9281. <=WM: (13608: S1 ^operator O1931 +)
  9282. <=WM: (13609: S1 ^operator O1932 +)
  9283. <=WM: (13610: S1 ^operator O1932)
  9284. <=WM: (13607: I3 ^dir L)
  9285. <=WM: (13603: R1 ^reward R969)
  9286. <=WM: (13606: O1932 ^name predict-no)
  9287. <=WM: (13605: O1931 ^name predict-yes)
  9288. <=WM: (13604: R969 ^value 1)
  9289. --- Inner Elaboration Phase, active level 1 (S1) ---
  9290. Firing prefer*rvt*predict-yes*H0
  9291. -->
  9292. Firing rl*prefer*rvt*predict-yes*H0*3
  9293. -->
  9294. (S1 ^operator O1933 = 0.7368285999158338)
  9295. Firing prefer*rvt*predict-yes*H0*3*v1*H1
  9296. -->
  9297. Firing rl*prefer*rvt*predict-yes*H0*3*v1*H1*35
  9298. -->
  9299. (S1 ^operator O1933 = 0.2631763932605209)
  9300. Firing prefer*rvt*predict-no*H0
  9301. -->
  9302. Firing rl*prefer*rvt*predict-no*H0*4
  9303. -->
  9304. (S1 ^operator O1934 = 0.2572462853745217)
  9305. Firing prefer*rvt*predict-no*H0*4*v1*H1
  9306. -->
  9307. Firing rl*prefer*rvt*predict-no*H0*4*v1*H1*34
  9308. -->
  9309. (S1 ^operator O1934 = -0.07401383653737587)
  9310. inner elaboration loop at bottom goal.
  9311. Retracting rl*prefer*rvt*predict-no*H0*4
  9312. -->
  9313. (S1 ^operator O1932 = 0.2572462853745217)
  9314. Retracting rl*prefer*rvt*predict-no*H0*4*v1*H1*34
  9315. -->
  9316. (S1 ^operator O1932 = -0.07401383653737587)
  9317. Retracting rl*prefer*rvt*predict-yes*H0*3
  9318. -->
  9319. (S1 ^operator O1931 = 0.7368285999158338)
  9320. Retracting rl*prefer*rvt*predict-yes*H0*3*v1*H1*35
  9321. -->
  9322. (S1 ^operator O1931 = 0.2631763932605209)
  9323. --- END Proposal Phase ---
  9324. --- Decision Phase ---
  9325. RL update rl*prefer*rvt*predict-no*H0*6 0.565403 -0.236457 0.328946 -> 0.565403 -0.236457 0.328946(R,m,v=1,0.903846,0.087469)
  9326. RL update rl*prefer*rvt*predict-no*H0*6*v1*H1*43 0.434592 0.23646 0.671052 -> 0.434593 0.236459 0.671052(R,m,v=1,1,0)
  9327. =>WM: (13624: S1 ^operator O1933)
  9328. 967: O: O1933 (predict-yes)
  9329. --- END Decision Phase ---
  9330. --- Application Phase ---
  9331. --- Firing Productions (PE) For State At Depth 1 ---
  9332. --- Inner Elaboration Phase, active level 1 (S1) ---
  9333. Firing apply*operator
  9334. -->
  9335. (I3 ^predict-yes N967 + :O )
  9336. Firing apply*operator*complete
  9337. -->
  9338. (I3 ^predict-no N966 - :O )
  9339. inner elaboration loop at bottom goal.
  9340. --- Change Working Memory (PE) ---
  9341. =>WM: (13625: I3 ^predict-yes N967)
  9342. <=WM: (13612: N966 ^status complete)
  9343. <=WM: (13611: I3 ^predict-no N966)
  9344. --- Firing Productions (IE) For State At Depth 1 ---
  9345. --- Inner Elaboration Phase, active level 1 (S1) ---
  9346. Firing monitor*world
  9347. -->
  9348. I see 1 and I'm going to do: predict-yes inner elaboration loop at bottom goal.
  9349. --- Change Working Memory (IE) ---
  9350. --- END Application Phase ---
  9351. --- Output Phase ---
  9352. ENV: Agent did: predict-yes for direction R in state State-A
  9353. In State-A moving R
  9354. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  9355. predict error 0
  9356. dir: dir isR
  9357. --- END Output Phase ---
  9358. \---- Input Phase ---
  9359. =>WM: (13629: I2 ^dir R)
  9360. =>WM: (13628: I2 ^reward 1)
  9361. =>WM: (13627: I2 ^see 1)
  9362. =>WM: (13626: N967 ^status complete)
  9363. <=WM: (13615: I2 ^dir R)
  9364. <=WM: (13614: I2 ^reward 1)
  9365. <=WM: (13613: I2 ^see 0)
  9366. =>WM: (13630: I2 ^level-1 R1-root)
  9367. <=WM: (13616: I2 ^level-1 L0-root)
  9368. --- END Input Phase ---
  9369. --- Proposal Phase ---
  9370. --- Inner Elaboration Phase, active level 1 (S1) ---
  9371. Firing rl*prefer*rvt*predict-yes*H0*3*v1*H1*37
  9372. -->
  9373. (S1 ^operator O1933 = -0.3011268063455669)
  9374. Firing rl*prefer*rvt*predict-no*H0*4*v1*H1*36
  9375. -->
  9376. (S1 ^operator O1934 = 0.7427519225841476)
  9377. Firing prefer*rvt*predict-no*H0*4*v1*H1
  9378. -->
  9379. Firing prefer*rvt*predict-yes*H0*3*v1*H1
  9380. -->
  9381. Firing elaborate*copy-see-to-output-link
  9382. -->
  9383. (I3 ^see 1 +)
  9384. Firing elaborate*reward*based*on*reward
  9385. -->
  9386. (R971 ^value 1 +)
  9387. (R1 ^reward R971 +)
  9388. Firing propose*predict-yes
  9389. -->
  9390. (O1935 ^name predict-yes +)
  9391. (S1 ^operator O1935 +)
  9392. Firing propose*predict-no
  9393. -->
  9394. (O1936 ^name predict-no +)
  9395. (S1 ^operator O1936 +)
  9396. Firing rl*prefer*rvt*predict-no*H0*4
  9397. -->
  9398. (S1 ^operator O1934 = 0.2572462853745217)
  9399. Firing rl*prefer*rvt*predict-yes*H0*3
  9400. -->
  9401. (S1 ^operator O1933 = 0.7368285999158338)
  9402. Firing prefer*rvt*predict-yes*H0
  9403. -->
  9404. Firing prefer*rvt*predict-no*H0
  9405. -->
  9406. Firing elaborate*copy-dir-to-output-link
  9407. -->
  9408. (I3 ^dir R +)
  9409. inner elaboration loop at bottom goal.
  9410. Retracting elaborate*copy-see-to-output-link
  9411. -->
  9412. (I3 ^see 0 +)
  9413. Retracting propose*predict-no
  9414. -->
  9415. (O1934 ^name predict-no +)
  9416. (S1 ^operator O1934 +)
  9417. Retracting propose*predict-yes
  9418. -->
  9419. (O1933 ^name predict-yes +)
  9420. (S1 ^operator O1933 +)
  9421. Retracting elaborate*reward*based*on*reward
  9422. -->
  9423. (R970 ^value 1 +)
  9424. (R1 ^reward R970 +)
  9425. Retracting elaborate*copy-dir-to-output-link
  9426. -->
  9427. (I3 ^dir R +)
  9428. Retracting rl*prefer*rvt*predict-no*H0*4*v1*H1*34
  9429. -->
  9430. (S1 ^operator O1934 = -0.07401383653737587)
  9431. Retracting rl*prefer*rvt*predict-no*H0*4
  9432. -->
  9433. (S1 ^operator O1934 = 0.2572462853745217)
  9434. Retracting rl*prefer*rvt*predict-yes*H0*3*v1*H1*35
  9435. -->
  9436. (S1 ^operator O1933 = 0.2631763932605209)
  9437. Retracting rl*prefer*rvt*predict-yes*H0*3
  9438. -->
  9439. (S1 ^operator O1933 = 0.7368285999158338)
  9440. =>WM: (13637: S1 ^operator O1936 +)
  9441. =>WM: (13636: S1 ^operator O1935 +)
  9442. =>WM: (13635: O1936 ^name predict-no)
  9443. =>WM: (13634: O1935 ^name predict-yes)
  9444. =>WM: (13633: R971 ^value 1)
  9445. =>WM: (13632: R1 ^reward R971)
  9446. =>WM: (13631: I3 ^see 1)
  9447. <=WM: (13622: S1 ^operator O1933 +)
  9448. <=WM: (13624: S1 ^operator O1933)
  9449. <=WM: (13623: S1 ^operator O1934 +)
  9450. <=WM: (13617: R1 ^reward R970)
  9451. <=WM: (13602: I3 ^see 0)
  9452. <=WM: (13620: O1934 ^name predict-no)
  9453. <=WM: (13619: O1933 ^name predict-yes)
  9454. <=WM: (13618: R970 ^value 1)
  9455. --- Inner Elaboration Phase, active level 1 (S1) ---
  9456. Firing prefer*rvt*predict-yes*H0
  9457. -->
  9458. Firing rl*prefer*rvt*predict-yes*H0*3
  9459. -->
  9460. (S1 ^operator O1935 = 0.7368285999158338)
  9461. Firing prefer*rvt*predict-yes*H0*3*v1*H1
  9462. -->
  9463. Firing rl*prefer*rvt*predict-yes*H0*3*v1*H1*37
  9464. -->
  9465. (S1 ^operator O1935 = -0.3011268063455669)
  9466. Firing prefer*rvt*predict-no*H0
  9467. -->
  9468. Firing rl*prefer*rvt*predict-no*H0*4
  9469. -->
  9470. (S1 ^operator O1936 = 0.2572462853745217)
  9471. Firing prefer*rvt*predict-no*H0*4*v1*H1
  9472. -->
  9473. Firing rl*prefer*rvt*predict-no*H0*4*v1*H1*36
  9474. -->
  9475. (S1 ^operator O1936 = 0.7427519225841476)
  9476. inner elaboration loop at bottom goal.
  9477. Retracting rl*prefer*rvt*predict-no*H0*4
  9478. -->
  9479. (S1 ^operator O1934 = 0.2572462853745217)
  9480. Retracting rl*prefer*rvt*predict-no*H0*4*v1*H1*36
  9481. -->
  9482. (S1 ^operator O1934 = 0.7427519225841476)
  9483. Retracting rl*prefer*rvt*predict-yes*H0*3
  9484. -->
  9485. (S1 ^operator O1933 = 0.7368285999158338)
  9486. Retracting rl*prefer*rvt*predict-yes*H0*3*v1*H1*37
  9487. -->
  9488. (S1 ^operator O1933 = -0.3011268063455669)
  9489. --- END Proposal Phase ---
  9490. --- Decision Phase ---
  9491. RL update rl*prefer*rvt*predict-yes*H0*3 0.748236 -0.0114076 0.736829 -> 0.748236 -0.0114082 0.736828(R,m,v=1,0.89375,0.0955582)
  9492. RL update rl*prefer*rvt*predict-yes*H0*3*v1*H1*35 0.251765 0.0114113 0.263176 -> 0.251765 0.0114107 0.263176(R,m,v=1,1,0)
  9493. =>WM: (13638: S1 ^operator O1936)
  9494. 968: O: O1936 (predict-no)
  9495. --- END Decision Phase ---
  9496. --- Application Phase ---
  9497. --- Firing Productions (PE) For State At Depth 1 ---
  9498. --- Inner Elaboration Phase, active level 1 (S1) ---
  9499. Firing apply*operator
  9500. -->
  9501. (I3 ^predict-no N968 + :O )
  9502. Firing apply*operator*complete
  9503. -->
  9504. (I3 ^predict-yes N967 - :O )
  9505. inner elaboration loop at bottom goal.
  9506. --- Change Working Memory (PE) ---
  9507. =>WM: (13639: I3 ^predict-no N968)
  9508. <=WM: (13626: N967 ^status complete)
  9509. <=WM: (13625: I3 ^predict-yes N967)
  9510. --- Firing Productions (IE) For State At Depth 1 ---
  9511. --- Inner Elaboration Phase, active level 1 (S1) ---
  9512. Firing monitor*world
  9513. -->
  9514. I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
  9515. --- Change Working Memory (IE) ---
  9516. --- END Application Phase ---
  9517. --- Output Phase ---
  9518. ENV: Agent did: predict-no for direction R in state State-B
  9519. In State-B moving R
  9520. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  9521. predict error 0
  9522. dir: dir isU
  9523. --- END Output Phase ---
  9524. /|\--- Input Phase ---
  9525. =>WM: (13643: I2 ^dir U)
  9526. =>WM: (13642: I2 ^reward 1)
  9527. =>WM: (13641: I2 ^see 0)
  9528. =>WM: (13640: N968 ^status complete)
  9529. <=WM: (13629: I2 ^dir R)
  9530. <=WM: (13628: I2 ^reward 1)
  9531. <=WM: (13627: I2 ^see 1)
  9532. =>WM: (13644: I2 ^level-1 R0-root)
  9533. <=WM: (13630: I2 ^level-1 R1-root)
  9534. --- END Input Phase ---
  9535. --- Proposal Phase ---
  9536. --- Inner Elaboration Phase, active level 1 (S1) ---
  9537. Firing elaborate*copy-see-to-output-link
  9538. -->
  9539. (I3 ^see 0 +)
  9540. Firing elaborate*reward*based*on*reward
  9541. -->
  9542. (R972 ^value 1 +)
  9543. (R1 ^reward R972 +)
  9544. Firing propose*predict-yes
  9545. -->
  9546. (O1937 ^name predict-yes +)
  9547. (S1 ^operator O1937 +)
  9548. Firing propose*predict-no
  9549. -->
  9550. (O1938 ^name predict-no +)
  9551. (S1 ^operator O1938 +)
  9552. Firing rl*prefer*rvt*predict-no*H0*2
  9553. -->
  9554. (S1 ^operator O1936 = 0.9999999999999999)
  9555. Firing rl*prefer*rvt*predict-yes*H0*1
  9556. -->
  9557. (S1 ^operator O1935 = 0.)
  9558. Firing prefer*rvt*predict-yes*H0
  9559. -->
  9560. Firing prefer*rvt*predict-no*H0
  9561. -->
  9562. Firing elaborate*copy-dir-to-output-link
  9563. -->
  9564. (I3 ^dir U +)
  9565. inner elaboration loop at bottom goal.
  9566. Retracting elaborate*copy-see-to-output-link
  9567. -->
  9568. (I3 ^see 1 +)
  9569. Retracting propose*predict-no
  9570. -->
  9571. (O1936 ^name predict-no +)
  9572. (S1 ^operator O1936 +)
  9573. Retracting propose*predict-yes
  9574. -->
  9575. (O1935 ^name predict-yes +)
  9576. (S1 ^operator O1935 +)
  9577. Retracting elaborate*reward*based*on*reward
  9578. -->
  9579. (R971 ^value 1 +)
  9580. (R1 ^reward R971 +)
  9581. Retracting elaborate*copy-dir-to-output-link
  9582. -->
  9583. (I3 ^dir R +)
  9584. Retracting rl*prefer*rvt*predict-no*H0*4*v1*H1*36
  9585. -->
  9586. (S1 ^operator O1936 = 0.7427519225841476)
  9587. Retracting rl*prefer*rvt*predict-no*H0*4
  9588. -->
  9589. (S1 ^operator O1936 = 0.2572462853745217)
  9590. Retracting rl*prefer*rvt*predict-yes*H0*3*v1*H1*37
  9591. -->
  9592. (S1 ^operator O1935 = -0.3011268063455669)
  9593. Retracting rl*prefer*rvt*predict-yes*H0*3
  9594. -->
  9595. (S1 ^operator O1935 = 0.7368278509393806)
  9596. =>WM: (13652: S1 ^operator O1938 +)
  9597. =>WM: (13651: S1 ^operator O1937 +)
  9598. =>WM: (13650: I3 ^dir U)
  9599. =>WM: (13649: O1938 ^name predict-no)
  9600. =>WM: (13648: O1937 ^name predict-yes)
  9601. =>WM: (13647: R972 ^value 1)
  9602. =>WM: (13646: R1 ^reward R972)
  9603. =>WM: (13645: I3 ^see 0)
  9604. <=WM: (13636: S1 ^operator O1935 +)
  9605. <=WM: (13637: S1 ^operator O1936 +)
  9606. <=WM: (13638: S1 ^operator O1936)
  9607. <=WM: (13621: I3 ^dir R)
  9608. <=WM: (13632: R1 ^reward R971)
  9609. <=WM: (13631: I3 ^see 1)
  9610. <=WM: (13635: O1936 ^name predict-no)
  9611. <=WM: (13634: O1935 ^name predict-yes)
  9612. <=WM: (13633: R971 ^value 1)
  9613. --- Inner Elaboration Phase, active level 1 (S1) ---
  9614. Firing prefer*rvt*predict-yes*H0
  9615. -->
  9616. Firing rl*prefer*rvt*predict-yes*H0*1
  9617. -->
  9618. (S1 ^operator O1937 = 0.)
  9619. Firing prefer*rvt*predict-no*H0
  9620. -->
  9621. Firing rl*prefer*rvt*predict-no*H0*2
  9622. -->
  9623. (S1 ^operator O1938 = 0.9999999999999999)
  9624. inner elaboration loop at bottom goal.
  9625. Retracting rl*prefer*rvt*predict-no*H0*2
  9626. -->
  9627. (S1 ^operator O1936 = 0.9999999999999999)
  9628. Retracting rl*prefer*rvt*predict-yes*H0*1
  9629. -->
  9630. (S1 ^operator O1935 = 0.)
  9631. --- END Proposal Phase ---
  9632. --- Decision Phase ---
  9633. RL update rl*prefer*rvt*predict-no*H0*4 0.586136 -0.32889 0.257246 -> 0.586136 -0.32889 0.257247(R,m,v=1,0.857143,0.123182)
  9634. RL update rl*prefer*rvt*predict-no*H0*4*v1*H1*36 0.413862 0.32889 0.742752 -> 0.413863 0.32889 0.742752(R,m,v=1,1,0)
  9635. =>WM: (13653: S1 ^operator O1938)
  9636. 969: O: O1938 (predict-no)
  9637. --- END Decision Phase ---
  9638. --- Application Phase ---
  9639. --- Firing Productions (PE) For State At Depth 1 ---
  9640. --- Inner Elaboration Phase, active level 1 (S1) ---
  9641. Firing apply*operator
  9642. -->
  9643. (I3 ^predict-no N969 + :O )
  9644. Firing apply*operator*complete
  9645. -->
  9646. (I3 ^predict-no N968 - :O )
  9647. inner elaboration loop at bottom goal.
  9648. --- Change Working Memory (PE) ---
  9649. =>WM: (13654: I3 ^predict-no N969)
  9650. <=WM: (13640: N968 ^status complete)
  9651. <=WM: (13639: I3 ^predict-no N968)
  9652. --- Firing Productions (IE) For State At Depth 1 ---
  9653. --- Inner Elaboration Phase, active level 1 (S1) ---
  9654. Firing monitor*world
  9655. -->
  9656. I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
  9657. --- Change Working Memory (IE) ---
  9658. --- END Application Phase ---
  9659. --- Output Phase ---
  9660. ENV: Agent did: predict-no for direction U in state State-B
  9661. In State-B moving U
  9662. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  9663. predict error 0
  9664. dir: dir isU
  9665. --- END Output Phase ---
  9666. -/|--- Input Phase ---
  9667. =>WM: (13658: I2 ^dir U)
  9668. =>WM: (13657: I2 ^reward 1)
  9669. =>WM: (13656: I2 ^see 0)
  9670. =>WM: (13655: N969 ^status complete)
  9671. <=WM: (13643: I2 ^dir U)
  9672. <=WM: (13642: I2 ^reward 1)
  9673. <=WM: (13641: I2 ^see 0)
  9674. =>WM: (13659: I2 ^level-1 R0-root)
  9675. <=WM: (13644: I2 ^level-1 R0-root)
  9676. --- END Input Phase ---
  9677. --- Proposal Phase ---
  9678. --- Inner Elaboration Phase, active level 1 (S1) ---
  9679. Firing elaborate*copy-see-to-output-link
  9680. -->
  9681. (I3 ^see 0 +)
  9682. Firing elaborate*reward*based*on*reward
  9683. -->
  9684. (R973 ^value 1 +)
  9685. (R1 ^reward R973 +)
  9686. Firing propose*predict-yes
  9687. -->
  9688. (O1939 ^name predict-yes +)
  9689. (S1 ^operator O1939 +)
  9690. Firing propose*predict-no
  9691. -->
  9692. (O1940 ^name predict-no +)
  9693. (S1 ^operator O1940 +)
  9694. Firing rl*prefer*rvt*predict-no*H0*2
  9695. -->
  9696. (S1 ^operator O1938 = 0.9999999999999999)
  9697. Firing rl*prefer*rvt*predict-yes*H0*1
  9698. -->
  9699. (S1 ^operator O1937 = 0.)
  9700. Firing prefer*rvt*predict-yes*H0
  9701. -->
  9702. Firing prefer*rvt*predict-no*H0
  9703. -->
  9704. Firing elaborate*copy-dir-to-output-link
  9705. -->
  9706. (I3 ^dir U +)
  9707. inner elaboration loop at bottom goal.
  9708. Retracting elaborate*copy-see-to-output-link
  9709. -->
  9710. (I3 ^see 0 +)
  9711. Retracting propose*predict-no
  9712. -->
  9713. (O1938 ^name predict-no +)
  9714. (S1 ^operator O1938 +)
  9715. Retracting propose*predict-yes
  9716. -->
  9717. (O1937 ^name predict-yes +)
  9718. (S1 ^operator O1937 +)
  9719. Retracting elaborate*reward*based*on*reward
  9720. -->
  9721. (R972 ^value 1 +)
  9722. (R1 ^reward R972 +)
  9723. Retracting elaborate*copy-dir-to-output-link
  9724. -->
  9725. (I3 ^dir U +)
  9726. Retracting rl*prefer*rvt*predict-no*H0*2
  9727. -->
  9728. (S1 ^operator O1938 = 0.9999999999999999)
  9729. Retracting rl*prefer*rvt*predict-yes*H0*1
  9730. -->
  9731. (S1 ^operator O1937 = 0.)
  9732. =>WM: (13665: S1 ^operator O1940 +)
  9733. =>WM: (13664: S1 ^operator O1939 +)
  9734. =>WM: (13663: O1940 ^name predict-no)
  9735. =>WM: (13662: O1939 ^name predict-yes)
  9736. =>WM: (13661: R973 ^value 1)
  9737. =>WM: (13660: R1 ^reward R973)
  9738. <=WM: (13651: S1 ^operator O1937 +)
  9739. <=WM: (13652: S1 ^operator O1938 +)
  9740. <=WM: (13653: S1 ^operator O1938)
  9741. <=WM: (13646: R1 ^reward R972)
  9742. <=WM: (13649: O1938 ^name predict-no)
  9743. <=WM: (13648: O1937 ^name predict-yes)
  9744. <=WM: (13647: R972 ^value 1)
  9745. --- Inner Elaboration Phase, active level 1 (S1) ---
  9746. Firing prefer*rvt*predict-yes*H0
  9747. -->
  9748. Firing rl*prefer*rvt*predict-yes*H0*1
  9749. -->
  9750. (S1 ^operator O1939 = 0.)
  9751. Firing prefer*rvt*predict-no*H0
  9752. -->
  9753. Firing rl*prefer*rvt*predict-no*H0*2
  9754. -->
  9755. (S1 ^operator O1940 = 0.9999999999999999)
  9756. inner elaboration loop at bottom goal.
  9757. Retracting rl*prefer*rvt*predict-no*H0*2
  9758. -->
  9759. (S1 ^operator O1938 = 0.9999999999999999)
  9760. Retracting rl*prefer*rvt*predict-yes*H0*1
  9761. -->
  9762. (S1 ^operator O1937 = 0.)
  9763. --- END Proposal Phase ---
  9764. --- Decision Phase ---
  9765. RL update rl*prefer*rvt*predict-no*H0*2 1 0 1 -> 1 0 1(R,m,v=1,1,0)
  9766. =>WM: (13666: S1 ^operator O1940)
  9767. 970: O: O1940 (predict-no)
  9768. --- END Decision Phase ---
  9769. --- Application Phase ---
  9770. --- Firing Productions (PE) For State At Depth 1 ---
  9771. --- Inner Elaboration Phase, active level 1 (S1) ---
  9772. Firing apply*operator
  9773. -->
  9774. (I3 ^predict-no N970 + :O )
  9775. Firing apply*operator*complete
  9776. -->
  9777. (I3 ^predict-no N969 - :O )
  9778. inner elaboration loop at bottom goal.
  9779. --- Change Working Memory (PE) ---
  9780. =>WM: (13667: I3 ^predict-no N970)
  9781. <=WM: (13655: N969 ^status complete)
  9782. <=WM: (13654: I3 ^predict-no N969)
  9783. --- Firing Productions (IE) For State At Depth 1 ---
  9784. --- Inner Elaboration Phase, active level 1 (S1) ---
  9785. Firing monitor*world
  9786. -->
  9787. I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
  9788. --- Change Working Memory (IE) ---
  9789. --- END Application Phase ---
  9790. --- Output Phase ---
  9791. ENV: Agent did: predict-no for direction U in state State-B
  9792. In State-B moving U
  9793. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  9794. predict error 0
  9795. dir: dir isL
  9796. --- END Output Phase ---
  9797. \---- Input Phase ---
  9798. =>WM: (13671: I2 ^dir L)
  9799. =>WM: (13670: I2 ^reward 1)
  9800. =>WM: (13669: I2 ^see 0)
  9801. =>WM: (13668: N970 ^status complete)
  9802. <=WM: (13658: I2 ^dir U)
  9803. <=WM: (13657: I2 ^reward 1)
  9804. <=WM: (13656: I2 ^see 0)
  9805. =>WM: (13672: I2 ^level-1 R0-root)
  9806. <=WM: (13659: I2 ^level-1 R0-root)
  9807. --- END Input Phase ---
  9808. --- Proposal Phase ---
  9809. --- Inner Elaboration Phase, active level 1 (S1) ---
  9810. Firing rl*prefer*rvt*predict-no*H0*6*v1*H1*38
  9811. -->
  9812. (S1 ^operator O1940 = 0.04178081990804111)
  9813. Firing rl*prefer*rvt*predict-yes*H0*5*v1*H1*30
  9814. -->
  9815. (S1 ^operator O1939 = 0.568112264215664)
  9816. Firing prefer*rvt*predict-no*H0*6*v1*H1
  9817. -->
  9818. Firing prefer*rvt*predict-yes*H0*5*v1*H1
  9819. -->
  9820. Firing elaborate*copy-see-to-output-link
  9821. -->
  9822. (I3 ^see 0 +)
  9823. Firing elaborate*reward*based*on*reward
  9824. -->
  9825. (R974 ^value 1 +)
  9826. (R1 ^reward R974 +)
  9827. Firing propose*predict-yes
  9828. -->
  9829. (O1941 ^name predict-yes +)
  9830. (S1 ^operator O1941 +)
  9831. Firing propose*predict-no
  9832. -->
  9833. (O1942 ^name predict-no +)
  9834. (S1 ^operator O1942 +)
  9835. Firing rl*prefer*rvt*predict-no*H0*6
  9836. -->
  9837. (S1 ^operator O1940 = 0.3289460588254962)
  9838. Firing rl*prefer*rvt*predict-yes*H0*5
  9839. -->
  9840. (S1 ^operator O1939 = 0.431889867399612)
  9841. Firing prefer*rvt*predict-yes*H0
  9842. -->
  9843. Firing prefer*rvt*predict-no*H0
  9844. -->
  9845. Firing elaborate*copy-dir-to-output-link
  9846. -->
  9847. (I3 ^dir L +)
  9848. inner elaboration loop at bottom goal.
  9849. Retracting elaborate*copy-see-to-output-link
  9850. -->
  9851. (I3 ^see 0 +)
  9852. Retracting propose*predict-no
  9853. -->
  9854. (O1940 ^name predict-no +)
  9855. (S1 ^operator O1940 +)
  9856. Retracting propose*predict-yes
  9857. -->
  9858. (O1939 ^name predict-yes +)
  9859. (S1 ^operator O1939 +)
  9860. Retracting elaborate*reward*based*on*reward
  9861. -->
  9862. (R973 ^value 1 +)
  9863. (R1 ^reward R973 +)
  9864. Retracting elaborate*copy-dir-to-output-link
  9865. -->
  9866. (I3 ^dir U +)
  9867. Retracting rl*prefer*rvt*predict-no*H0*2
  9868. -->
  9869. (S1 ^operator O1940 = 0.9999999999999999)
  9870. Retracting rl*prefer*rvt*predict-yes*H0*1
  9871. -->
  9872. (S1 ^operator O1939 = 0.)
  9873. =>WM: (13679: S1 ^operator O1942 +)
  9874. =>WM: (13678: S1 ^operator O1941 +)
  9875. =>WM: (13677: I3 ^dir L)
  9876. =>WM: (13676: O1942 ^name predict-no)
  9877. =>WM: (13675: O1941 ^name predict-yes)
  9878. =>WM: (13674: R974 ^value 1)
  9879. =>WM: (13673: R1 ^reward R974)
  9880. <=WM: (13664: S1 ^operator O1939 +)
  9881. <=WM: (13665: S1 ^operator O1940 +)
  9882. <=WM: (13666: S1 ^operator O1940)
  9883. <=WM: (13650: I3 ^dir U)
  9884. <=WM: (13660: R1 ^reward R973)
  9885. <=WM: (13663: O1940 ^name predict-no)
  9886. <=WM: (13662: O1939 ^name predict-yes)
  9887. <=WM: (13661: R973 ^value 1)
  9888. --- Inner Elaboration Phase, active level 1 (S1) ---
  9889. Firing prefer*rvt*predict-yes*H0
  9890. -->
  9891. Firing rl*prefer*rvt*predict-yes*H0*5*v1*H1*30
  9892. -->
  9893. (S1 ^operator O1941 = 0.568112264215664)
  9894. Firing rl*prefer*rvt*predict-yes*H0*5
  9895. -->
  9896. (S1 ^operator O1941 = 0.431889867399612)
  9897. Firing prefer*rvt*predict-yes*H0*5*v1*H1
  9898. -->
  9899. Firing prefer*rvt*predict-no*H0
  9900. -->
  9901. Firing rl*prefer*rvt*predict-no*H0*6*v1*H1*38
  9902. -->
  9903. (S1 ^operator O1942 = 0.04178081990804111)
  9904. Firing rl*prefer*rvt*predict-no*H0*6
  9905. -->
  9906. (S1 ^operator O1942 = 0.3289460588254962)
  9907. Firing prefer*rvt*predict-no*H0*6*v1*H1
  9908. -->
  9909. inner elaboration loop at bottom goal.
  9910. Retracting rl*prefer*rvt*predict-no*H0*6
  9911. -->
  9912. (S1 ^operator O1940 = 0.3289460588254962)
  9913. Retracting rl*prefer*rvt*predict-no*H0*6*v1*H1*38
  9914. -->
  9915. (S1 ^operator O1940 = 0.04178081990804111)
  9916. Retracting rl*prefer*rvt*predict-yes*H0*5
  9917. -->
  9918. (S1 ^operator O1939 = 0.431889867399612)
  9919. Retracting rl*prefer*rvt*predict-yes*H0*5*v1*H1*30
  9920. -->
  9921. (S1 ^operator O1939 = 0.568112264215664)
  9922. --- END Proposal Phase ---
  9923. --- Decision Phase ---
  9924. RL update rl*prefer*rvt*predict-no*H0*2 1 0 1 -> 1 0 1(R,m,v=1,1,0)
  9925. =>WM: (13680: S1 ^operator O1941)
  9926. 971: O: O1941 (predict-yes)
  9927. --- END Decision Phase ---
  9928. --- Application Phase ---
  9929. --- Firing Productions (PE) For State At Depth 1 ---
  9930. --- Inner Elaboration Phase, active level 1 (S1) ---
  9931. Firing apply*operator
  9932. -->
  9933. (I3 ^predict-yes N971 + :O )
  9934. Firing apply*operator*complete
  9935. -->
  9936. (I3 ^predict-no N970 - :O )
  9937. inner elaboration loop at bottom goal.
  9938. --- Change Working Memory (PE) ---
  9939. =>WM: (13681: I3 ^predict-yes N971)
  9940. <=WM: (13668: N970 ^status complete)
  9941. <=WM: (13667: I3 ^predict-no N970)
  9942. --- Firing Productions (IE) For State At Depth 1 ---
  9943. --- Inner Elaboration Phase, active level 1 (S1) ---
  9944. Firing monitor*world
  9945. -->
  9946. I see 1 and I'm going to do: predict-yes inner elaboration loop at bottom goal.
  9947. --- Change Working Memory (IE) ---
  9948. --- END Application Phase ---
  9949. --- Output Phase ---
  9950. ENV: Agent did: predict-yes for direction L in state State-B
  9951. In State-B moving L
  9952. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  9953. predict error 0
  9954. dir: dir isR
  9955. --- END Output Phase ---
  9956. /--- Input Phase ---
  9957. =>WM: (13685: I2 ^dir R)
  9958. =>WM: (13684: I2 ^reward 1)
  9959. =>WM: (13683: I2 ^see 1)
  9960. =>WM: (13682: N971 ^status complete)
  9961. <=WM: (13671: I2 ^dir L)
  9962. <=WM: (13670: I2 ^reward 1)
  9963. <=WM: (13669: I2 ^see 0)
  9964. =>WM: (13686: I2 ^level-1 L1-root)
  9965. <=WM: (13672: I2 ^level-1 R0-root)
  9966. --- END Input Phase ---
  9967. --- Proposal Phase ---
  9968. --- Inner Elaboration Phase, active level 1 (S1) ---
  9969. Firing rl*prefer*rvt*predict-no*H0*4*v1*H1*39
  9970. -->
  9971. (S1 ^operator O1942 = -0.1377248055371832)
  9972. Firing rl*prefer*rvt*predict-yes*H0*3*v1*H1*40
  9973. -->
  9974. (S1 ^operator O1941 = 0.2631673327126827)
  9975. Firing prefer*rvt*predict-no*H0*4*v1*H1
  9976. -->
  9977. Firing prefer*rvt*predict-yes*H0*3*v1*H1
  9978. -->
  9979. Firing elaborate*copy-see-to-output-link
  9980. -->
  9981. (I3 ^see 1 +)
  9982. Firing elaborate*reward*based*on*reward
  9983. -->
  9984. (R975 ^value 1 +)
  9985. (R1 ^reward R975 +)
  9986. Firing propose*predict-yes
  9987. -->
  9988. (O1943 ^name predict-yes +)
  9989. (S1 ^operator O1943 +)
  9990. Firing propose*predict-no
  9991. -->
  9992. (O1944 ^name predict-no +)
  9993. (S1 ^operator O1944 +)
  9994. Firing rl*prefer*rvt*predict-no*H0*4
  9995. -->
  9996. (S1 ^operator O1942 = 0.2572465541807213)
  9997. Firing rl*prefer*rvt*predict-yes*H0*3
  9998. -->
  9999. (S1 ^operator O1941 = 0.7368278509393806)
  10000. Firing prefer*rvt*predict-yes*H0
  10001. -->
  10002. Firing prefer*rvt*predict-no*H0
  10003. -->
  10004. Firing elaborate*copy-dir-to-output-link
  10005. -->
  10006. (I3 ^dir R +)
  10007. inner elaboration loop at bottom goal.
  10008. Retracting elaborate*copy-see-to-output-link
  10009. -->
  10010. (I3 ^see 0 +)
  10011. Retracting propose*predict-no
  10012. -->
  10013. (O1942 ^name predict-no +)
  10014. (S1 ^operator O1942 +)
  10015. Retracting propose*predict-yes
  10016. -->
  10017. (O1941 ^name predict-yes +)
  10018. (S1 ^operator O1941 +)
  10019. Retracting elaborate*reward*based*on*reward
  10020. -->
  10021. (R974 ^value 1 +)
  10022. (R1 ^reward R974 +)
  10023. Retracting elaborate*copy-dir-to-output-link
  10024. -->
  10025. (I3 ^dir L +)
  10026. Retracting rl*prefer*rvt*predict-no*H0*6
  10027. -->
  10028. (S1 ^operator O1942 = 0.3289460588254962)
  10029. Retracting rl*prefer*rvt*predict-no*H0*6*v1*H1*38
  10030. -->
  10031. (S1 ^operator O1942 = 0.04178081990804111)
  10032. Retracting rl*prefer*rvt*predict-yes*H0*5
  10033. -->
  10034. (S1 ^operator O1941 = 0.431889867399612)
  10035. Retracting rl*prefer*rvt*predict-yes*H0*5*v1*H1*30
  10036. -->
  10037. (S1 ^operator O1941 = 0.568112264215664)
  10038. =>WM: (13694: S1 ^operator O1944 +)
  10039. =>WM: (13693: S1 ^operator O1943 +)
  10040. =>WM: (13692: I3 ^dir R)
  10041. =>WM: (13691: O1944 ^name predict-no)
  10042. =>WM: (13690: O1943 ^name predict-yes)
  10043. =>WM: (13689: R975 ^value 1)
  10044. =>WM: (13688: R1 ^reward R975)
  10045. =>WM: (13687: I3 ^see 1)
  10046. <=WM: (13678: S1 ^operator O1941 +)
  10047. <=WM: (13680: S1 ^operator O1941)
  10048. <=WM: (13679: S1 ^operator O1942 +)
  10049. <=WM: (13677: I3 ^dir L)
  10050. <=WM: (13673: R1 ^reward R974)
  10051. <=WM: (13645: I3 ^see 0)
  10052. <=WM: (13676: O1942 ^name predict-no)
  10053. <=WM: (13675: O1941 ^name predict-yes)
  10054. <=WM: (13674: R974 ^value 1)
  10055. --- Inner Elaboration Phase, active level 1 (S1) ---
  10056. Firing prefer*rvt*predict-yes*H0
  10057. -->
  10058. Firing rl*prefer*rvt*predict-yes*H0*3
  10059. -->
  10060. (S1 ^operator O1943 = 0.7368278509393806)
  10061. Firing prefer*rvt*predict-yes*H0*3*v1*H1
  10062. -->
  10063. Firing rl*prefer*rvt*predict-yes*H0*3*v1*H1*40
  10064. -->
  10065. (S1 ^operator O1943 = 0.2631673327126827)
  10066. Firing prefer*rvt*predict-no*H0
  10067. -->
  10068. Firing rl*prefer*rvt*predict-no*H0*4
  10069. -->
  10070. (S1 ^operator O1944 = 0.2572465541807213)
  10071. Firing prefer*rvt*predict-no*H0*4*v1*H1
  10072. -->
  10073. Firing rl*prefer*rvt*predict-no*H0*4*v1*H1*39
  10074. -->
  10075. (S1 ^operator O1944 = -0.1377248055371832)
  10076. inner elaboration loop at bottom goal.
  10077. Retracting rl*prefer*rvt*predict-no*H0*4
  10078. -->
  10079. (S1 ^operator O1942 = 0.2572465541807213)
  10080. Retracting rl*prefer*rvt*predict-no*H0*4*v1*H1*39
  10081. -->
  10082. (S1 ^operator O1942 = -0.1377248055371832)
  10083. Retracting rl*prefer*rvt*predict-yes*H0*3
  10084. -->
  10085. (S1 ^operator O1941 = 0.7368278509393806)
  10086. Retracting rl*prefer*rvt*predict-yes*H0*3*v1*H1*40
  10087. -->
  10088. (S1 ^operator O1941 = 0.2631673327126827)
  10089. --- END Proposal Phase ---
  10090. --- Decision Phase ---
  10091. RL update rl*prefer*rvt*predict-yes*H0*5 0.683776 -0.251886 0.43189 -> 0.683776 -0.251886 0.43189(R,m,v=1,0.921212,0.0730229)
  10092. RL update rl*prefer*rvt*predict-yes*H0*5*v1*H1*30 0.316226 0.251886 0.568112 -> 0.316226 0.251886 0.568112(R,m,v=1,1,0)
  10093. =>WM: (13695: S1 ^operator O1943)
  10094. 972: O: O1943 (predict-yes)
  10095. --- END Decision Phase ---
  10096. --- Application Phase ---
  10097. --- Firing Productions (PE) For State At Depth 1 ---
  10098. --- Inner Elaboration Phase, active level 1 (S1) ---
  10099. Firing apply*operator
  10100. -->
  10101. (I3 ^predict-yes N972 + :O )
  10102. Firing apply*operator*complete
  10103. -->
  10104. (I3 ^predict-yes N971 - :O )
  10105. inner elaboration loop at bottom goal.
  10106. --- Change Working Memory (PE) ---
  10107. =>WM: (13696: I3 ^predict-yes N972)
  10108. <=WM: (13682: N971 ^status complete)
  10109. <=WM: (13681: I3 ^predict-yes N971)
  10110. --- Firing Productions (IE) For State At Depth 1 ---
  10111. --- Inner Elaboration Phase, active level 1 (S1) ---
  10112. Firing monitor*world
  10113. -->
  10114. I see 1 and I'm going to do: predict-yes inner elaboration loop at bottom goal.
  10115. --- Change Working Memory (IE) ---
  10116. --- END Application Phase ---
  10117. --- Output Phase ---
  10118. ENV: Agent did: predict-yes for direction R in state State-A
  10119. In State-A moving R
  10120. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  10121. predict error 0
  10122. dir: dir isL
  10123. --- END Output Phase ---
  10124. |\--- Input Phase ---
  10125. =>WM: (13700: I2 ^dir L)
  10126. =>WM: (13699: I2 ^reward 1)
  10127. =>WM: (13698: I2 ^see 1)
  10128. =>WM: (13697: N972 ^status complete)
  10129. <=WM: (13685: I2 ^dir R)
  10130. <=WM: (13684: I2 ^reward 1)
  10131. <=WM: (13683: I2 ^see 1)
  10132. =>WM: (13701: I2 ^level-1 R1-root)
  10133. <=WM: (13686: I2 ^level-1 L1-root)
  10134. --- END Input Phase ---
  10135. --- Proposal Phase ---
  10136. --- Inner Elaboration Phase, active level 1 (S1) ---
  10137. Firing rl*prefer*rvt*predict-yes*H0*5*v1*H1*45
  10138. -->
  10139. (S1 ^operator O1943 = 0.5681048678187335)
  10140. Firing rl*prefer*rvt*predict-no*H0*6*v1*H1*44
  10141. -->
  10142. (S1 ^operator O1944 = -0.1549421060161498)
  10143. Firing prefer*rvt*predict-no*H0*6*v1*H1
  10144. -->
  10145. Firing prefer*rvt*predict-yes*H0*5*v1*H1
  10146. -->
  10147. Firing elaborate*copy-see-to-output-link
  10148. -->
  10149. (I3 ^see 1 +)
  10150. Firing elaborate*reward*based*on*reward
  10151. -->
  10152. (R976 ^value 1 +)
  10153. (R1 ^reward R976 +)
  10154. Firing propose*predict-yes
  10155. -->
  10156. (O1945 ^name predict-yes +)
  10157. (S1 ^operator O1945 +)
  10158. Firing propose*predict-no
  10159. -->
  10160. (O1946 ^name predict-no +)
  10161. (S1 ^operator O1946 +)
  10162. Firing rl*prefer*rvt*predict-no*H0*6
  10163. -->
  10164. (S1 ^operator O1944 = 0.3289460588254962)
  10165. Firing rl*prefer*rvt*predict-yes*H0*5
  10166. -->
  10167. (S1 ^operator O1943 = 0.4318895476573206)
  10168. Firing prefer*rvt*predict-yes*H0
  10169. -->
  10170. Firing prefer*rvt*predict-no*H0
  10171. -->
  10172. Firing elaborate*copy-dir-to-output-link
  10173. -->
  10174. (I3 ^dir L +)
  10175. inner elaboration loop at bottom goal.
  10176. Retracting elaborate*copy-see-to-output-link
  10177. -->
  10178. (I3 ^see 1 +)
  10179. Retracting propose*predict-no
  10180. -->
  10181. (O1944 ^name predict-no +)
  10182. (S1 ^operator O1944 +)
  10183. Retracting propose*predict-yes
  10184. -->
  10185. (O1943 ^name predict-yes +)
  10186. (S1 ^operator O1943 +)
  10187. Retracting elaborate*reward*based*on*reward
  10188. -->
  10189. (R975 ^value 1 +)
  10190. (R1 ^reward R975 +)
  10191. Retracting elaborate*copy-dir-to-output-link
  10192. -->
  10193. (I3 ^dir R +)
  10194. Retracting rl*prefer*rvt*predict-no*H0*4*v1*H1*39
  10195. -->
  10196. (S1 ^operator O1944 = -0.1377248055371832)
  10197. Retracting rl*prefer*rvt*predict-no*H0*4
  10198. -->
  10199. (S1 ^operator O1944 = 0.2572465541807213)
  10200. Retracting rl*prefer*rvt*predict-yes*H0*3*v1*H1*40
  10201. -->
  10202. (S1 ^operator O1943 = 0.2631673327126827)
  10203. Retracting rl*prefer*rvt*predict-yes*H0*3
  10204. -->
  10205. (S1 ^operator O1943 = 0.7368278509393806)
  10206. =>WM: (13708: S1 ^operator O1946 +)
  10207. =>WM: (13707: S1 ^operator O1945 +)
  10208. =>WM: (13706: I3 ^dir L)
  10209. =>WM: (13705: O1946 ^name predict-no)
  10210. =>WM: (13704: O1945 ^name predict-yes)
  10211. =>WM: (13703: R976 ^value 1)
  10212. =>WM: (13702: R1 ^reward R976)
  10213. <=WM: (13693: S1 ^operator O1943 +)
  10214. <=WM: (13695: S1 ^operator O1943)
  10215. <=WM: (13694: S1 ^operator O1944 +)
  10216. <=WM: (13692: I3 ^dir R)
  10217. <=WM: (13688: R1 ^reward R975)
  10218. <=WM: (13691: O1944 ^name predict-no)
  10219. <=WM: (13690: O1943 ^name predict-yes)
  10220. <=WM: (13689: R975 ^value 1)
  10221. --- Inner Elaboration Phase, active level 1 (S1) ---
  10222. Firing prefer*rvt*predict-yes*H0
  10223. -->
  10224. Firing rl*prefer*rvt*predict-yes*H0*5
  10225. -->
  10226. (S1 ^operator O1945 = 0.4318895476573206)
  10227. Firing prefer*rvt*predict-yes*H0*5*v1*H1
  10228. -->
  10229. Firing rl*prefer*rvt*predict-yes*H0*5*v1*H1*45
  10230. -->
  10231. (S1 ^operator O1945 = 0.5681048678187335)
  10232. Firing prefer*rvt*predict-no*H0
  10233. -->
  10234. Firing rl*prefer*rvt*predict-no*H0*6
  10235. -->
  10236. (S1 ^operator O1946 = 0.3289460588254962)
  10237. Firing prefer*rvt*predict-no*H0*6*v1*H1
  10238. -->
  10239. Firing rl*prefer*rvt*predict-no*H0*6*v1*H1*44
  10240. -->
  10241. (S1 ^operator O1946 = -0.1549421060161498)
  10242. inner elaboration loop at bottom goal.
  10243. Retracting rl*prefer*rvt*predict-no*H0*6
  10244. -->
  10245. (S1 ^operator O1944 = 0.3289460588254962)
  10246. Retracting rl*prefer*rvt*predict-no*H0*6*v1*H1*44
  10247. -->
  10248. (S1 ^operator O1944 = -0.1549421060161498)
  10249. Retracting rl*prefer*rvt*predict-yes*H0*5
  10250. -->
  10251. (S1 ^operator O1943 = 0.4318895476573206)
  10252. Retracting rl*prefer*rvt*predict-yes*H0*5*v1*H1*45
  10253. -->
  10254. (S1 ^operator O1943 = 0.5681048678187335)
  10255. --- END Proposal Phase ---
  10256. --- Decision Phase ---
  10257. RL update rl*prefer*rvt*predict-yes*H0*3 0.748236 -0.0114082 0.736828 -> 0.748236 -0.0114076 0.736829(R,m,v=1,0.89441,0.0950311)
  10258. RL update rl*prefer*rvt*predict-yes*H0*3*v1*H1*40 0.251763 0.0114046 0.263167 -> 0.251763 0.0114052 0.263168(R,m,v=1,1,0)
  10259. =>WM: (13709: S1 ^operator O1945)
  10260. 973: O: O1945 (predict-yes)
  10261. --- END Decision Phase ---
  10262. --- Application Phase ---
  10263. --- Firing Productions (PE) For State At Depth 1 ---
  10264. --- Inner Elaboration Phase, active level 1 (S1) ---
  10265. Firing apply*operator
  10266. -->
  10267. (I3 ^predict-yes N973 + :O )
  10268. Firing apply*operator*complete
  10269. -->
  10270. (I3 ^predict-yes N972 - :O )
  10271. inner elaboration loop at bottom goal.
  10272. --- Change Working Memory (PE) ---
  10273. =>WM: (13710: I3 ^predict-yes N973)
  10274. <=WM: (13697: N972 ^status complete)
  10275. <=WM: (13696: I3 ^predict-yes N972)
  10276. --- Firing Productions (IE) For State At Depth 1 ---
  10277. --- Inner Elaboration Phase, active level 1 (S1) ---
  10278. Firing monitor*world
  10279. -->
  10280. I see 1 and I'm going to do: predict-yes inner elaboration loop at bottom goal.
  10281. --- Change Working Memory (IE) ---
  10282. --- END Application Phase ---
  10283. --- Output Phase ---
  10284. ENV: Agent did: predict-yes for direction L in state State-B
  10285. In State-B moving L
  10286. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  10287. predict error 0
  10288. dir: dir isU
  10289. --- END Output Phase ---
  10290. -/|--- Input Phase ---
  10291. =>WM: (13714: I2 ^dir U)
  10292. =>WM: (13713: I2 ^reward 1)
  10293. =>WM: (13712: I2 ^see 1)
  10294. =>WM: (13711: N973 ^status complete)
  10295. <=WM: (13700: I2 ^dir L)
  10296. <=WM: (13699: I2 ^reward 1)
  10297. <=WM: (13698: I2 ^see 1)
  10298. =>WM: (13715: I2 ^level-1 L1-root)
  10299. <=WM: (13701: I2 ^level-1 R1-root)
  10300. --- END Input Phase ---
  10301. --- Proposal Phase ---
  10302. --- Inner Elaboration Phase, active level 1 (S1) ---
  10303. Firing elaborate*copy-see-to-output-link
  10304. -->
  10305. (I3 ^see 1 +)
  10306. Firing elaborate*reward*based*on*reward
  10307. -->
  10308. (R977 ^value 1 +)
  10309. (R1 ^reward R977 +)
  10310. Firing propose*predict-yes
  10311. -->
  10312. (O1947 ^name predict-yes +)
  10313. (S1 ^operator O1947 +)
  10314. Firing propose*predict-no
  10315. -->
  10316. (O1948 ^name predict-no +)
  10317. (S1 ^operator O1948 +)
  10318. Firing rl*prefer*rvt*predict-no*H0*2
  10319. -->
  10320. (S1 ^operator O1946 = 0.9999999999999999)
  10321. Firing rl*prefer*rvt*predict-yes*H0*1
  10322. -->
  10323. (S1 ^operator O1945 = 0.)
  10324. Firing prefer*rvt*predict-yes*H0
  10325. -->
  10326. Firing prefer*rvt*predict-no*H0
  10327. -->
  10328. Firing elaborate*copy-dir-to-output-link
  10329. -->
  10330. (I3 ^dir U +)
  10331. inner elaboration loop at bottom goal.
  10332. Retracting elaborate*copy-see-to-output-link
  10333. -->
  10334. (I3 ^see 1 +)
  10335. Retracting propose*predict-no
  10336. -->
  10337. (O1946 ^name predict-no +)
  10338. (S1 ^operator O1946 +)
  10339. Retracting propose*predict-yes
  10340. -->
  10341. (O1945 ^name predict-yes +)
  10342. (S1 ^operator O1945 +)
  10343. Retracting elaborate*reward*based*on*reward
  10344. -->
  10345. (R976 ^value 1 +)
  10346. (R1 ^reward R976 +)
  10347. Retracting elaborate*copy-dir-to-output-link
  10348. -->
  10349. (I3 ^dir L +)
  10350. Retracting rl*prefer*rvt*predict-no*H0*6*v1*H1*44
  10351. -->
  10352. (S1 ^operator O1946 = -0.1549421060161498)
  10353. Retracting rl*prefer*rvt*predict-no*H0*6
  10354. -->
  10355. (S1 ^operator O1946 = 0.3289460588254962)
  10356. Retracting rl*prefer*rvt*predict-yes*H0*5*v1*H1*45
  10357. -->
  10358. (S1 ^operator O1945 = 0.5681048678187335)
  10359. Retracting rl*prefer*rvt*predict-yes*H0*5
  10360. -->
  10361. (S1 ^operator O1945 = 0.4318895476573206)
  10362. =>WM: (13722: S1 ^operator O1948 +)
  10363. =>WM: (13721: S1 ^operator O1947 +)
  10364. =>WM: (13720: I3 ^dir U)
  10365. =>WM: (13719: O1948 ^name predict-no)
  10366. =>WM: (13718: O1947 ^name predict-yes)
  10367. =>WM: (13717: R977 ^value 1)
  10368. =>WM: (13716: R1 ^reward R977)
  10369. <=WM: (13707: S1 ^operator O1945 +)
  10370. <=WM: (13709: S1 ^operator O1945)
  10371. <=WM: (13708: S1 ^operator O1946 +)
  10372. <=WM: (13706: I3 ^dir L)
  10373. <=WM: (13702: R1 ^reward R976)
  10374. <=WM: (13705: O1946 ^name predict-no)
  10375. <=WM: (13704: O1945 ^name predict-yes)
  10376. <=WM: (13703: R976 ^value 1)
  10377. --- Inner Elaboration Phase, active level 1 (S1) ---
  10378. Firing prefer*rvt*predict-yes*H0
  10379. -->
  10380. Firing rl*prefer*rvt*predict-yes*H0*1
  10381. -->
  10382. (S1 ^operator O1947 = 0.)
  10383. Firing prefer*rvt*predict-no*H0
  10384. -->
  10385. Firing rl*prefer*rvt*predict-no*H0*2
  10386. -->
  10387. (S1 ^operator O1948 = 0.9999999999999999)
  10388. inner elaboration loop at bottom goal.
  10389. Retracting rl*prefer*rvt*predict-no*H0*2
  10390. -->
  10391. (S1 ^operator O1946 = 0.9999999999999999)
  10392. Retracting rl*prefer*rvt*predict-yes*H0*1
  10393. -->
  10394. (S1 ^operator O1945 = 0.)
  10395. --- END Proposal Phase ---
  10396. --- Decision Phase ---
  10397. RL update rl*prefer*rvt*predict-yes*H0*5 0.683776 -0.251886 0.43189 -> 0.683777 -0.251886 0.43189(R,m,v=1,0.921687,0.0726177)
  10398. RL update rl*prefer*rvt*predict-yes*H0*5*v1*H1*45 0.316219 0.251886 0.568105 -> 0.31622 0.251886 0.568106(R,m,v=1,1,0)
  10399. =>WM: (13723: S1 ^operator O1948)
  10400. 974: O: O1948 (predict-no)
  10401. --- END Decision Phase ---
  10402. --- Application Phase ---
  10403. --- Firing Productions (PE) For State At Depth 1 ---
  10404. --- Inner Elaboration Phase, active level 1 (S1) ---
  10405. Firing apply*operator
  10406. -->
  10407. (I3 ^predict-no N974 + :O )
  10408. Firing apply*operator*complete
  10409. -->
  10410. (I3 ^predict-yes N973 - :O )
  10411. inner elaboration loop at bottom goal.
  10412. --- Change Working Memory (PE) ---
  10413. =>WM: (13724: I3 ^predict-no N974)
  10414. <=WM: (13711: N973 ^status complete)
  10415. <=WM: (13710: I3 ^predict-yes N973)
  10416. --- Firing Productions (IE) For State At Depth 1 ---
  10417. --- Inner Elaboration Phase, active level 1 (S1) ---
  10418. Firing monitor*world
  10419. -->
  10420. I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
  10421. --- Change Working Memory (IE) ---
  10422. --- END Application Phase ---
  10423. --- Output Phase ---
  10424. ENV: Agent did: predict-no for direction U in state State-A
  10425. In State-A moving U
  10426. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  10427. predict error 0
  10428. dir: dir isU
  10429. --- END Output Phase ---
  10430. \-/--- Input Phase ---
  10431. =>WM: (13728: I2 ^dir U)
  10432. =>WM: (13727: I2 ^reward 1)
  10433. =>WM: (13726: I2 ^see 0)
  10434. =>WM: (13725: N974 ^status complete)
  10435. <=WM: (13714: I2 ^dir U)
  10436. <=WM: (13713: I2 ^reward 1)
  10437. <=WM: (13712: I2 ^see 1)
  10438. =>WM: (13729: I2 ^level-1 L1-root)
  10439. <=WM: (13715: I2 ^level-1 L1-root)
  10440. --- END Input Phase ---
  10441. --- Proposal Phase ---
  10442. --- Inner Elaboration Phase, active level 1 (S1) ---
  10443. Firing elaborate*copy-see-to-output-link
  10444. -->
  10445. (I3 ^see 0 +)
  10446. Firing elaborate*reward*based*on*reward
  10447. -->
  10448. (R978 ^value 1 +)
  10449. (R1 ^reward R978 +)
  10450. Firing propose*predict-yes
  10451. -->
  10452. (O1949 ^name predict-yes +)
  10453. (S1 ^operator O1949 +)
  10454. Firing propose*predict-no
  10455. -->
  10456. (O1950 ^name predict-no +)
  10457. (S1 ^operator O1950 +)
  10458. Firing rl*prefer*rvt*predict-no*H0*2
  10459. -->
  10460. (S1 ^operator O1948 = 0.9999999999999999)
  10461. Firing rl*prefer*rvt*predict-yes*H0*1
  10462. -->
  10463. (S1 ^operator O1947 = 0.)
  10464. Firing prefer*rvt*predict-yes*H0
  10465. -->
  10466. Firing prefer*rvt*predict-no*H0
  10467. -->
  10468. Firing elaborate*copy-dir-to-output-link
  10469. -->
  10470. (I3 ^dir U +)
  10471. inner elaboration loop at bottom goal.
  10472. Retracting elaborate*copy-see-to-output-link
  10473. -->
  10474. (I3 ^see 1 +)
  10475. Retracting propose*predict-no
  10476. -->
  10477. (O1948 ^name predict-no +)
  10478. (S1 ^operator O1948 +)
  10479. Retracting propose*predict-yes
  10480. -->
  10481. (O1947 ^name predict-yes +)
  10482. (S1 ^operator O1947 +)
  10483. Retracting elaborate*reward*based*on*reward
  10484. -->
  10485. (R977 ^value 1 +)
  10486. (R1 ^reward R977 +)
  10487. Retracting elaborate*copy-dir-to-output-link
  10488. -->
  10489. (I3 ^dir U +)
  10490. Retracting rl*prefer*rvt*predict-no*H0*2
  10491. -->
  10492. (S1 ^operator O1948 = 0.9999999999999999)
  10493. Retracting rl*prefer*rvt*predict-yes*H0*1
  10494. -->
  10495. (S1 ^operator O1947 = 0.)
  10496. =>WM: (13736: S1 ^operator O1950 +)
  10497. =>WM: (13735: S1 ^operator O1949 +)
  10498. =>WM: (13734: O1950 ^name predict-no)
  10499. =>WM: (13733: O1949 ^name predict-yes)
  10500. =>WM: (13732: R978 ^value 1)
  10501. =>WM: (13731: R1 ^reward R978)
  10502. =>WM: (13730: I3 ^see 0)
  10503. <=WM: (13721: S1 ^operator O1947 +)
  10504. <=WM: (13722: S1 ^operator O1948 +)
  10505. <=WM: (13723: S1 ^operator O1948)
  10506. <=WM: (13716: R1 ^reward R977)
  10507. <=WM: (13687: I3 ^see 1)
  10508. <=WM: (13719: O1948 ^name predict-no)
  10509. <=WM: (13718: O1947 ^name predict-yes)
  10510. <=WM: (13717: R977 ^value 1)
  10511. --- Inner Elaboration Phase, active level 1 (S1) ---
  10512. Firing prefer*rvt*predict-yes*H0
  10513. -->
  10514. Firing rl*prefer*rvt*predict-yes*H0*1
  10515. -->
  10516. (S1 ^operator O1949 = 0.)
  10517. Firing prefer*rvt*predict-no*H0
  10518. -->
  10519. Firing rl*prefer*rvt*predict-no*H0*2
  10520. -->
  10521. (S1 ^operator O1950 = 0.9999999999999999)
  10522. inner elaboration loop at bottom goal.
  10523. Retracting rl*prefer*rvt*predict-no*H0*2
  10524. -->
  10525. (S1 ^operator O1948 = 0.9999999999999999)
  10526. Retracting rl*prefer*rvt*predict-yes*H0*1
  10527. -->
  10528. (S1 ^operator O1947 = 0.)
  10529. --- END Proposal Phase ---
  10530. --- Decision Phase ---
  10531. RL update rl*prefer*rvt*predict-no*H0*2 1 0 1 -> 1 0 1(R,m,v=1,1,0)
  10532. =>WM: (13737: S1 ^operator O1950)
  10533. 975: O: O1950 (predict-no)
  10534. --- END Decision Phase ---
  10535. --- Application Phase ---
  10536. --- Firing Productions (PE) For State At Depth 1 ---
  10537. --- Inner Elaboration Phase, active level 1 (S1) ---
  10538. Firing apply*operator
  10539. -->
  10540. (I3 ^predict-no N975 + :O )
  10541. Firing apply*operator*complete
  10542. -->
  10543. (I3 ^predict-no N974 - :O )
  10544. inner elaboration loop at bottom goal.
  10545. --- Change Working Memory (PE) ---
  10546. =>WM: (13738: I3 ^predict-no N975)
  10547. <=WM: (13725: N974 ^status complete)
  10548. <=WM: (13724: I3 ^predict-no N974)
  10549. --- Firing Productions (IE) For State At Depth 1 ---
  10550. --- Inner Elaboration Phase, active level 1 (S1) ---
  10551. Firing monitor*world
  10552. -->
  10553. I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
  10554. --- Change Working Memory (IE) ---
  10555. --- END Application Phase ---
  10556. --- Output Phase ---
  10557. ENV: Agent did: predict-no for direction U in state State-A
  10558. In State-A moving U
  10559. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  10560. predict error 0
  10561. dir: dir isR
  10562. --- END Output Phase ---
  10563. |\---- Input Phase ---
  10564. =>WM: (13742: I2 ^dir R)
  10565. =>WM: (13741: I2 ^reward 1)
  10566. =>WM: (13740: I2 ^see 0)
  10567. =>WM: (13739: N975 ^status complete)
  10568. <=WM: (13728: I2 ^dir U)
  10569. <=WM: (13727: I2 ^reward 1)
  10570. <=WM: (13726: I2 ^see 0)
  10571. =>WM: (13743: I2 ^level-1 L1-root)
  10572. <=WM: (13729: I2 ^level-1 L1-root)
  10573. --- END Input Phase ---
  10574. --- Proposal Phase ---
  10575. --- Inner Elaboration Phase, active level 1 (S1) ---
  10576. Firing rl*prefer*rvt*predict-no*H0*4*v1*H1*39
  10577. -->
  10578. (S1 ^operator O1950 = -0.1377248055371832)
  10579. Firing rl*prefer*rvt*predict-yes*H0*3*v1*H1*40
  10580. -->
  10581. (S1 ^operator O1949 = 0.2631680551648732)
  10582. Firing prefer*rvt*predict-no*H0*4*v1*H1
  10583. -->
  10584. Firing prefer*rvt*predict-yes*H0*3*v1*H1
  10585. -->
  10586. Firing elaborate*copy-see-to-output-link
  10587. -->
  10588. (I3 ^see 0 +)
  10589. Firing elaborate*reward*based*on*reward
  10590. -->
  10591. (R979 ^value 1 +)
  10592. (R1 ^reward R979 +)
  10593. Firing propose*predict-yes
  10594. -->
  10595. (O1951 ^name predict-yes +)
  10596. (S1 ^operator O1951 +)
  10597. Firing propose*predict-no
  10598. -->
  10599. (O1952 ^name predict-no +)
  10600. (S1 ^operator O1952 +)
  10601. Firing rl*prefer*rvt*predict-no*H0*4
  10602. -->
  10603. (S1 ^operator O1950 = 0.2572465541807213)
  10604. Firing rl*prefer*rvt*predict-yes*H0*3
  10605. -->
  10606. (S1 ^operator O1949 = 0.7368285733915712)
  10607. Firing prefer*rvt*predict-yes*H0
  10608. -->
  10609. Firing prefer*rvt*predict-no*H0
  10610. -->
  10611. Firing elaborate*copy-dir-to-output-link
  10612. -->
  10613. (I3 ^dir R +)
  10614. inner elaboration loop at bottom goal.
  10615. Retracting elaborate*copy-see-to-output-link
  10616. -->
  10617. (I3 ^see 0 +)
  10618. Retracting propose*predict-no
  10619. -->
  10620. (O1950 ^name predict-no +)
  10621. (S1 ^operator O1950 +)
  10622. Retracting propose*predict-yes
  10623. -->
  10624. (O1949 ^name predict-yes +)
  10625. (S1 ^operator O1949 +)
  10626. Retracting elaborate*reward*based*on*reward
  10627. -->
  10628. (R978 ^value 1 +)
  10629. (R1 ^reward R978 +)
  10630. Retracting elaborate*copy-dir-to-output-link
  10631. -->
  10632. (I3 ^dir U +)
  10633. Retracting rl*prefer*rvt*predict-no*H0*2
  10634. -->
  10635. (S1 ^operator O1950 = 0.9999999999999999)
  10636. Retracting rl*prefer*rvt*predict-yes*H0*1
  10637. -->
  10638. (S1 ^operator O1949 = 0.)
  10639. =>WM: (13750: S1 ^operator O1952 +)
  10640. =>WM: (13749: S1 ^operator O1951 +)
  10641. =>WM: (13748: I3 ^dir R)
  10642. =>WM: (13747: O1952 ^name predict-no)
  10643. =>WM: (13746: O1951 ^name predict-yes)
  10644. =>WM: (13745: R979 ^value 1)
  10645. =>WM: (13744: R1 ^reward R979)
  10646. <=WM: (13735: S1 ^operator O1949 +)
  10647. <=WM: (13736: S1 ^operator O1950 +)
  10648. <=WM: (13737: S1 ^operator O1950)
  10649. <=WM: (13720: I3 ^dir U)
  10650. <=WM: (13731: R1 ^reward R978)
  10651. <=WM: (13734: O1950 ^name predict-no)
  10652. <=WM: (13733: O1949 ^name predict-yes)
  10653. <=WM: (13732: R978 ^value 1)
  10654. --- Inner Elaboration Phase, active level 1 (S1) ---
  10655. Firing prefer*rvt*predict-yes*H0
  10656. -->
  10657. Firing rl*prefer*rvt*predict-yes*H0*3*v1*H1*40
  10658. -->
  10659. (S1 ^operator O1951 = 0.2631680551648732)
  10660. Firing rl*prefer*rvt*predict-yes*H0*3
  10661. -->
  10662. (S1 ^operator O1951 = 0.7368285733915712)
  10663. Firing prefer*rvt*predict-yes*H0*3*v1*H1
  10664. -->
  10665. Firing prefer*rvt*predict-no*H0
  10666. -->
  10667. Firing rl*prefer*rvt*predict-no*H0*4*v1*H1*39
  10668. -->
  10669. (S1 ^operator O1952 = -0.1377248055371832)
  10670. Firing rl*prefer*rvt*predict-no*H0*4
  10671. -->
  10672. (S1 ^operator O1952 = 0.2572465541807213)
  10673. Firing prefer*rvt*predict-no*H0*4*v1*H1
  10674. -->
  10675. inner elaboration loop at bottom goal.
  10676. Retracting rl*prefer*rvt*predict-no*H0*4
  10677. -->
  10678. (S1 ^operator O1950 = 0.2572465541807213)
  10679. Retracting rl*prefer*rvt*predict-no*H0*4*v1*H1*39
  10680. -->
  10681. (S1 ^operator O1950 = -0.1377248055371832)
  10682. Retracting rl*prefer*rvt*predict-yes*H0*3
  10683. -->
  10684. (S1 ^operator O1949 = 0.7368285733915712)
  10685. Retracting rl*prefer*rvt*predict-yes*H0*3*v1*H1*40
  10686. -->
  10687. (S1 ^operator O1949 = 0.2631680551648732)
  10688. --- END Proposal Phase ---
  10689. --- Decision Phase ---
  10690. RL update rl*prefer*rvt*predict-no*H0*2 1 0 1 -> 1 0 1(R,m,v=1,1,0)
  10691. =>WM: (13751: S1 ^operator O1951)
  10692. 976: O: O1951 (predict-yes)
  10693. --- END Decision Phase ---
  10694. --- Application Phase ---
  10695. --- Firing Productions (PE) For State At Depth 1 ---
  10696. --- Inner Elaboration Phase, active level 1 (S1) ---
  10697. Firing apply*operator
  10698. -->
  10699. (I3 ^predict-yes N976 + :O )
  10700. Firing apply*operator*complete
  10701. -->
  10702. (I3 ^predict-no N975 - :O )
  10703. inner elaboration loop at bottom goal.
  10704. --- Change Working Memory (PE) ---
  10705. =>WM: (13752: I3 ^predict-yes N976)
  10706. <=WM: (13739: N975 ^status complete)
  10707. <=WM: (13738: I3 ^predict-no N975)
  10708. --- Firing Productions (IE) For State At Depth 1 ---
  10709. --- Inner Elaboration Phase, active level 1 (S1) ---
  10710. Firing monitor*world
  10711. -->
  10712. I see 1 and I'm going to do: predict-yes inner elaboration loop at bottom goal.
  10713. --- Change Working Memory (IE) ---
  10714. --- END Application Phase ---
  10715. --- Output Phase ---
  10716. ENV: Agent did: predict-yes for direction R in state State-A
  10717. In State-A moving R
  10718. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  10719. predict error 0
  10720. dir: dir isU
  10721. --- END Output Phase ---
  10722. /|\--- Input Phase ---
  10723. =>WM: (13756: I2 ^dir U)
  10724. =>WM: (13755: I2 ^reward 1)
  10725. =>WM: (13754: I2 ^see 1)
  10726. =>WM: (13753: N976 ^status complete)
  10727. <=WM: (13742: I2 ^dir R)
  10728. <=WM: (13741: I2 ^reward 1)
  10729. <=WM: (13740: I2 ^see 0)
  10730. =>WM: (13757: I2 ^level-1 R1-root)
  10731. <=WM: (13743: I2 ^level-1 L1-root)
  10732. --- END Input Phase ---
  10733. --- Proposal Phase ---
  10734. --- Inner Elaboration Phase, active level 1 (S1) ---
  10735. Firing elaborate*copy-see-to-output-link
  10736. -->
  10737. (I3 ^see 1 +)
  10738. Firing elaborate*reward*based*on*reward
  10739. -->
  10740. (R980 ^value 1 +)
  10741. (R1 ^reward R980 +)
  10742. Firing propose*predict-yes
  10743. -->
  10744. (O1953 ^name predict-yes +)
  10745. (S1 ^operator O1953 +)
  10746. Firing propose*predict-no
  10747. -->
  10748. (O1954 ^name predict-no +)
  10749. (S1 ^operator O1954 +)
  10750. Firing rl*prefer*rvt*predict-no*H0*2
  10751. -->
  10752. (S1 ^operator O1952 = 0.9999999999999999)
  10753. Firing rl*prefer*rvt*predict-yes*H0*1
  10754. -->
  10755. (S1 ^operator O1951 = 0.)
  10756. Firing prefer*rvt*predict-yes*H0
  10757. -->
  10758. Firing prefer*rvt*predict-no*H0
  10759. -->
  10760. Firing elaborate*copy-dir-to-output-link
  10761. -->
  10762. (I3 ^dir U +)
  10763. inner elaboration loop at bottom goal.
  10764. Retracting elaborate*copy-see-to-output-link
  10765. -->
  10766. (I3 ^see 0 +)
  10767. Retracting propose*predict-no
  10768. -->
  10769. (O1952 ^name predict-no +)
  10770. (S1 ^operator O1952 +)
  10771. Retracting propose*predict-yes
  10772. -->
  10773. (O1951 ^name predict-yes +)
  10774. (S1 ^operator O1951 +)
  10775. Retracting elaborate*reward*based*on*reward
  10776. -->
  10777. (R979 ^value 1 +)
  10778. (R1 ^reward R979 +)
  10779. Retracting elaborate*copy-dir-to-output-link
  10780. -->
  10781. (I3 ^dir R +)
  10782. Retracting rl*prefer*rvt*predict-no*H0*4
  10783. -->
  10784. (S1 ^operator O1952 = 0.2572465541807213)
  10785. Retracting rl*prefer*rvt*predict-no*H0*4*v1*H1*39
  10786. -->
  10787. (S1 ^operator O1952 = -0.1377248055371832)
  10788. Retracting rl*prefer*rvt*predict-yes*H0*3
  10789. -->
  10790. (S1 ^operator O1951 = 0.7368285733915712)
  10791. Retracting rl*prefer*rvt*predict-yes*H0*3*v1*H1*40
  10792. -->
  10793. (S1 ^operator O1951 = 0.2631680551648732)
  10794. =>WM: (13765: S1 ^operator O1954 +)
  10795. =>WM: (13764: S1 ^operator O1953 +)
  10796. =>WM: (13763: I3 ^dir U)
  10797. =>WM: (13762: O1954 ^name predict-no)
  10798. =>WM: (13761: O1953 ^name predict-yes)
  10799. =>WM: (13760: R980 ^value 1)
  10800. =>WM: (13759: R1 ^reward R980)
  10801. =>WM: (13758: I3 ^see 1)
  10802. <=WM: (13749: S1 ^operator O1951 +)
  10803. <=WM: (13751: S1 ^operator O1951)
  10804. <=WM: (13750: S1 ^operator O1952 +)
  10805. <=WM: (13748: I3 ^dir R)
  10806. <=WM: (13744: R1 ^reward R979)
  10807. <=WM: (13730: I3 ^see 0)
  10808. <=WM: (13747: O1952 ^name predict-no)
  10809. <=WM: (13746: O1951 ^name predict-yes)
  10810. <=WM: (13745: R979 ^value 1)
  10811. --- Inner Elaboration Phase, active level 1 (S1) ---
  10812. Firing prefer*rvt*predict-yes*H0
  10813. -->
  10814. Firing rl*prefer*rvt*predict-yes*H0*1
  10815. -->
  10816. (S1 ^operator O1953 = 0.)
  10817. Firing prefer*rvt*predict-no*H0
  10818. -->
  10819. Firing rl*prefer*rvt*predict-no*H0*2
  10820. -->
  10821. (S1 ^operator O1954 = 0.9999999999999999)
  10822. inner elaboration loop at bottom goal.
  10823. Retracting rl*prefer*rvt*predict-no*H0*2
  10824. -->
  10825. (S1 ^operator O1952 = 0.9999999999999999)
  10826. Retracting rl*prefer*rvt*predict-yes*H0*1
  10827. -->
  10828. (S1 ^operator O1951 = 0.)
  10829. --- END Proposal Phase ---
  10830. --- Decision Phase ---
  10831. RL update rl*prefer*rvt*predict-yes*H0*3 0.748236 -0.0114076 0.736829 -> 0.748236 -0.0114073 0.736829(R,m,v=1,0.895062,0.0945096)
  10832. RL update rl*prefer*rvt*predict-yes*H0*3*v1*H1*40 0.251763 0.0114052 0.263168 -> 0.251763 0.0114055 0.263169(R,m,v=1,1,0)
  10833. =>WM: (13766: S1 ^operator O1954)
  10834. 977: O: O1954 (predict-no)
  10835. --- END Decision Phase ---
  10836. --- Application Phase ---
  10837. --- Firing Productions (PE) For State At Depth 1 ---
  10838. --- Inner Elaboration Phase, active level 1 (S1) ---
  10839. Firing apply*operator
  10840. -->
  10841. (I3 ^predict-no N977 + :O )
  10842. Firing apply*operator*complete
  10843. -->
  10844. (I3 ^predict-yes N976 - :O )
  10845. inner elaboration loop at bottom goal.
  10846. --- Change Working Memory (PE) ---
  10847. =>WM: (13767: I3 ^predict-no N977)
  10848. <=WM: (13753: N976 ^status complete)
  10849. <=WM: (13752: I3 ^predict-yes N976)
  10850. --- Firing Productions (IE) For State At Depth 1 ---
  10851. --- Inner Elaboration Phase, active level 1 (S1) ---
  10852. Firing monitor*world
  10853. -->
  10854. I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
  10855. --- Change Working Memory (IE) ---
  10856. --- END Application Phase ---
  10857. --- Output Phase ---
  10858. ENV: Agent did: predict-no for direction U in state State-B
  10859. In State-B moving U
  10860. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  10861. predict error 0
  10862. dir: dir isU
  10863. --- END Output Phase ---
  10864. -/|--- Input Phase ---
  10865. =>WM: (13771: I2 ^dir U)
  10866. =>WM: (13770: I2 ^reward 1)
  10867. =>WM: (13769: I2 ^see 0)
  10868. =>WM: (13768: N977 ^status complete)
  10869. <=WM: (13756: I2 ^dir U)
  10870. <=WM: (13755: I2 ^reward 1)
  10871. <=WM: (13754: I2 ^see 1)
  10872. =>WM: (13772: I2 ^level-1 R1-root)
  10873. <=WM: (13757: I2 ^level-1 R1-root)
  10874. --- END Input Phase ---
  10875. --- Proposal Phase ---
  10876. --- Inner Elaboration Phase, active level 1 (S1) ---
  10877. Firing elaborate*copy-see-to-output-link
  10878. -->
  10879. (I3 ^see 0 +)
  10880. Firing elaborate*reward*based*on*reward
  10881. -->
  10882. (R981 ^value 1 +)
  10883. (R1 ^reward R981 +)
  10884. Firing propose*predict-yes
  10885. -->
  10886. (O1955 ^name predict-yes +)
  10887. (S1 ^operator O1955 +)
  10888. Firing propose*predict-no
  10889. -->
  10890. (O1956 ^name predict-no +)
  10891. (S1 ^operator O1956 +)
  10892. Firing rl*prefer*rvt*predict-no*H0*2
  10893. -->
  10894. (S1 ^operator O1954 = 0.9999999999999999)
  10895. Firing rl*prefer*rvt*predict-yes*H0*1
  10896. -->
  10897. (S1 ^operator O1953 = 0.)
  10898. Firing prefer*rvt*predict-yes*H0
  10899. -->
  10900. Firing prefer*rvt*predict-no*H0
  10901. -->
  10902. Firing elaborate*copy-dir-to-output-link
  10903. -->
  10904. (I3 ^dir U +)
  10905. inner elaboration loop at bottom goal.
  10906. Retracting elaborate*copy-see-to-output-link
  10907. -->
  10908. (I3 ^see 1 +)
  10909. Retracting propose*predict-no
  10910. -->
  10911. (O1954 ^name predict-no +)
  10912. (S1 ^operator O1954 +)
  10913. Retracting propose*predict-yes
  10914. -->
  10915. (O1953 ^name predict-yes +)
  10916. (S1 ^operator O1953 +)
  10917. Retracting elaborate*reward*based*on*reward
  10918. -->
  10919. (R980 ^value 1 +)
  10920. (R1 ^reward R980 +)
  10921. Retracting elaborate*copy-dir-to-output-link
  10922. -->
  10923. (I3 ^dir U +)
  10924. Retracting rl*prefer*rvt*predict-no*H0*2
  10925. -->
  10926. (S1 ^operator O1954 = 0.9999999999999999)
  10927. Retracting rl*prefer*rvt*predict-yes*H0*1
  10928. -->
  10929. (S1 ^operator O1953 = 0.)
  10930. =>WM: (13779: S1 ^operator O1956 +)
  10931. =>WM: (13778: S1 ^operator O1955 +)
  10932. =>WM: (13777: O1956 ^name predict-no)
  10933. =>WM: (13776: O1955 ^name predict-yes)
  10934. =>WM: (13775: R981 ^value 1)
  10935. =>WM: (13774: R1 ^reward R981)
  10936. =>WM: (13773: I3 ^see 0)
  10937. <=WM: (13764: S1 ^operator O1953 +)
  10938. <=WM: (13765: S1 ^operator O1954 +)
  10939. <=WM: (13766: S1 ^operator O1954)
  10940. <=WM: (13759: R1 ^reward R980)
  10941. <=WM: (13758: I3 ^see 1)
  10942. <=WM: (13762: O1954 ^name predict-no)
  10943. <=WM: (13761: O1953 ^name predict-yes)
  10944. <=WM: (13760: R980 ^value 1)
  10945. --- Inner Elaboration Phase, active level 1 (S1) ---
  10946. Firing prefer*rvt*predict-yes*H0
  10947. -->
  10948. Firing rl*prefer*rvt*predict-yes*H0*1
  10949. -->
  10950. (S1 ^operator O1955 = 0.)
  10951. Firing prefer*rvt*predict-no*H0
  10952. -->
  10953. Firing rl*prefer*rvt*predict-no*H0*2
  10954. -->
  10955. (S1 ^operator O1956 = 0.9999999999999999)
  10956. inner elaboration loop at bottom goal.
  10957. Retracting rl*prefer*rvt*predict-no*H0*2
  10958. -->
  10959. (S1 ^operator O1954 = 0.9999999999999999)
  10960. Retracting rl*prefer*rvt*predict-yes*H0*1
  10961. -->
  10962. (S1 ^operator O1953 = 0.)
  10963. --- END Proposal Phase ---
  10964. --- Decision Phase ---
  10965. RL update rl*prefer*rvt*predict-no*H0*2 1 0 1 -> 1 0 1(R,m,v=1,1,0)
  10966. =>WM: (13780: S1 ^operator O1956)
  10967. 978: O: O1956 (predict-no)
  10968. --- END Decision Phase ---
  10969. --- Application Phase ---
  10970. --- Firing Productions (PE) For State At Depth 1 ---
  10971. --- Inner Elaboration Phase, active level 1 (S1) ---
  10972. Firing apply*operator
  10973. -->
  10974. (I3 ^predict-no N978 + :O )
  10975. Firing apply*operator*complete
  10976. -->
  10977. (I3 ^predict-no N977 - :O )
  10978. inner elaboration loop at bottom goal.
  10979. --- Change Working Memory (PE) ---
  10980. =>WM: (13781: I3 ^predict-no N978)
  10981. <=WM: (13768: N977 ^status complete)
  10982. <=WM: (13767: I3 ^predict-no N977)
  10983. --- Firing Productions (IE) For State At Depth 1 ---
  10984. --- Inner Elaboration Phase, active level 1 (S1) ---
  10985. Firing monitor*world
  10986. -->
  10987. I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
  10988. --- Change Working Memory (IE) ---
  10989. --- END Application Phase ---
  10990. --- Output Phase ---
  10991. ENV: Agent did: predict-no for direction U in state State-B
  10992. In State-B moving U
  10993. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  10994. predict error 0
  10995. dir: dir isR
  10996. --- END Output Phase ---
  10997. \-/--- Input Phase ---
  10998. =>WM: (13785: I2 ^dir R)
  10999. =>WM: (13784: I2 ^reward 1)
  11000. =>WM: (13783: I2 ^see 0)
  11001. =>WM: (13782: N978 ^status complete)
  11002. <=WM: (13771: I2 ^dir U)
  11003. <=WM: (13770: I2 ^reward 1)
  11004. <=WM: (13769: I2 ^see 0)
  11005. =>WM: (13786: I2 ^level-1 R1-root)
  11006. <=WM: (13772: I2 ^level-1 R1-root)
  11007. --- END Input Phase ---
  11008. --- Proposal Phase ---
  11009. --- Inner Elaboration Phase, active level 1 (S1) ---
  11010. Firing rl*prefer*rvt*predict-yes*H0*3*v1*H1*37
  11011. -->
  11012. (S1 ^operator O1955 = -0.3011268063455669)
  11013. Firing rl*prefer*rvt*predict-no*H0*4*v1*H1*36
  11014. -->
  11015. (S1 ^operator O1956 = 0.7427521913903472)
  11016. Firing prefer*rvt*predict-no*H0*4*v1*H1
  11017. -->
  11018. Firing prefer*rvt*predict-yes*H0*3*v1*H1
  11019. -->
  11020. Firing elaborate*copy-see-to-output-link
  11021. -->
  11022. (I3 ^see 0 +)
  11023. Firing elaborate*reward*based*on*reward
  11024. -->
  11025. (R982 ^value 1 +)
  11026. (R1 ^reward R982 +)
  11027. Firing propose*predict-yes
  11028. -->
  11029. (O1957 ^name predict-yes +)
  11030. (S1 ^operator O1957 +)
  11031. Firing propose*predict-no
  11032. -->
  11033. (O1958 ^name predict-no +)
  11034. (S1 ^operator O1958 +)
  11035. Firing rl*prefer*rvt*predict-no*H0*4
  11036. -->
  11037. (S1 ^operator O1956 = 0.2572465541807213)
  11038. Firing rl*prefer*rvt*predict-yes*H0*3
  11039. -->
  11040. (S1 ^operator O1955 = 0.7368290791081045)
  11041. Firing prefer*rvt*predict-yes*H0
  11042. -->
  11043. Firing prefer*rvt*predict-no*H0
  11044. -->
  11045. Firing elaborate*copy-dir-to-output-link
  11046. -->
  11047. (I3 ^dir R +)
  11048. inner elaboration loop at bottom goal.
  11049. Retracting elaborate*copy-see-to-output-link
  11050. -->
  11051. (I3 ^see 0 +)
  11052. Retracting propose*predict-no
  11053. -->
  11054. (O1956 ^name predict-no +)
  11055. (S1 ^operator O1956 +)
  11056. Retracting propose*predict-yes
  11057. -->
  11058. (O1955 ^name predict-yes +)
  11059. (S1 ^operator O1955 +)
  11060. Retracting elaborate*reward*based*on*reward
  11061. -->
  11062. (R981 ^value 1 +)
  11063. (R1 ^reward R981 +)
  11064. Retracting elaborate*copy-dir-to-output-link
  11065. -->
  11066. (I3 ^dir U +)
  11067. Retracting rl*prefer*rvt*predict-no*H0*2
  11068. -->
  11069. (S1 ^operator O1956 = 0.9999999999999999)
  11070. Retracting rl*prefer*rvt*predict-yes*H0*1
  11071. -->
  11072. (S1 ^operator O1955 = 0.)
  11073. =>WM: (13793: S1 ^operator O1958 +)
  11074. =>WM: (13792: S1 ^operator O1957 +)
  11075. =>WM: (13791: I3 ^dir R)
  11076. =>WM: (13790: O1958 ^name predict-no)
  11077. =>WM: (13789: O1957 ^name predict-yes)
  11078. =>WM: (13788: R982 ^value 1)
  11079. =>WM: (13787: R1 ^reward R982)
  11080. <=WM: (13778: S1 ^operator O1955 +)
  11081. <=WM: (13779: S1 ^operator O1956 +)
  11082. <=WM: (13780: S1 ^operator O1956)
  11083. <=WM: (13763: I3 ^dir U)
  11084. <=WM: (13774: R1 ^reward R981)
  11085. <=WM: (13777: O1956 ^name predict-no)
  11086. <=WM: (13776: O1955 ^name predict-yes)
  11087. <=WM: (13775: R981 ^value 1)
  11088. --- Inner Elaboration Phase, active level 1 (S1) ---
  11089. Firing prefer*rvt*predict-yes*H0
  11090. -->
  11091. Firing rl*prefer*rvt*predict-yes*H0*3*v1*H1*37
  11092. -->
  11093. (S1 ^operator O1957 = -0.3011268063455669)
  11094. Firing rl*prefer*rvt*predict-yes*H0*3
  11095. -->
  11096. (S1 ^operator O1957 = 0.7368290791081045)
  11097. Firing prefer*rvt*predict-yes*H0*3*v1*H1
  11098. -->
  11099. Firing prefer*rvt*predict-no*H0
  11100. -->
  11101. Firing rl*prefer*rvt*predict-no*H0*4*v1*H1*36
  11102. -->
  11103. (S1 ^operator O1958 = 0.7427521913903472)
  11104. Firing rl*prefer*rvt*predict-no*H0*4
  11105. -->
  11106. (S1 ^operator O1958 = 0.2572465541807213)
  11107. Firing prefer*rvt*predict-no*H0*4*v1*H1
  11108. -->
  11109. inner elaboration loop at bottom goal.
  11110. Retracting rl*prefer*rvt*predict-no*H0*4
  11111. -->
  11112. (S1 ^operator O1956 = 0.2572465541807213)
  11113. Retracting rl*prefer*rvt*predict-no*H0*4*v1*H1*36
  11114. -->
  11115. (S1 ^operator O1956 = 0.7427521913903472)
  11116. Retracting rl*prefer*rvt*predict-yes*H0*3
  11117. -->
  11118. (S1 ^operator O1955 = 0.7368290791081045)
  11119. Retracting rl*prefer*rvt*predict-yes*H0*3*v1*H1*37
  11120. -->
  11121. (S1 ^operator O1955 = -0.3011268063455669)
  11122. --- END Proposal Phase ---
  11123. --- Decision Phase ---
  11124. RL update rl*prefer*rvt*predict-no*H0*2 1 0 1 -> 1 0 1(R,m,v=1,1,0)
  11125. =>WM: (13794: S1 ^operator O1958)
  11126. 979: O: O1958 (predict-no)
  11127. --- END Decision Phase ---
  11128. --- Application Phase ---
  11129. --- Firing Productions (PE) For State At Depth 1 ---
  11130. --- Inner Elaboration Phase, active level 1 (S1) ---
  11131. Firing apply*operator
  11132. -->
  11133. (I3 ^predict-no N979 + :O )
  11134. Firing apply*operator*complete
  11135. -->
  11136. (I3 ^predict-no N978 - :O )
  11137. inner elaboration loop at bottom goal.
  11138. --- Change Working Memory (PE) ---
  11139. =>WM: (13795: I3 ^predict-no N979)
  11140. <=WM: (13782: N978 ^status complete)
  11141. <=WM: (13781: I3 ^predict-no N978)
  11142. --- Firing Productions (IE) For State At Depth 1 ---
  11143. --- Inner Elaboration Phase, active level 1 (S1) ---
  11144. Firing monitor*world
  11145. -->
  11146. I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
  11147. --- Change Working Memory (IE) ---
  11148. --- END Application Phase ---
  11149. --- Output Phase ---
  11150. ENV: Agent did: predict-no for direction R in state State-B
  11151. In State-B moving R
  11152. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  11153. predict error 0
  11154. dir: dir isU
  11155. --- END Output Phase ---
  11156. |--- Input Phase ---
  11157. =>WM: (13799: I2 ^dir U)
  11158. =>WM: (13798: I2 ^reward 1)
  11159. =>WM: (13797: I2 ^see 0)
  11160. =>WM: (13796: N979 ^status complete)
  11161. <=WM: (13785: I2 ^dir R)
  11162. <=WM: (13784: I2 ^reward 1)
  11163. <=WM: (13783: I2 ^see 0)
  11164. =>WM: (13800: I2 ^level-1 R0-root)
  11165. <=WM: (13786: I2 ^level-1 R1-root)
  11166. --- END Input Phase ---
  11167. --- Proposal Phase ---
  11168. --- Inner Elaboration Phase, active level 1 (S1) ---
  11169. Firing elaborate*copy-see-to-output-link
  11170. -->
  11171. (I3 ^see 0 +)
  11172. Firing elaborate*reward*based*on*reward
  11173. -->
  11174. (R983 ^value 1 +)
  11175. (R1 ^reward R983 +)
  11176. Firing propose*predict-yes
  11177. -->
  11178. (O1959 ^name predict-yes +)
  11179. (S1 ^operator O1959 +)
  11180. Firing propose*predict-no
  11181. -->
  11182. (O1960 ^name predict-no +)
  11183. (S1 ^operator O1960 +)
  11184. Firing rl*prefer*rvt*predict-no*H0*2
  11185. -->
  11186. (S1 ^operator O1958 = 0.9999999999999999)
  11187. Firing rl*prefer*rvt*predict-yes*H0*1
  11188. -->
  11189. (S1 ^operator O1957 = 0.)
  11190. Firing prefer*rvt*predict-yes*H0
  11191. -->
  11192. Firing prefer*rvt*predict-no*H0
  11193. -->
  11194. Firing elaborate*copy-dir-to-output-link
  11195. -->
  11196. (I3 ^dir U +)
  11197. inner elaboration loop at bottom goal.
  11198. Retracting elaborate*copy-see-to-output-link
  11199. -->
  11200. (I3 ^see 0 +)
  11201. Retracting propose*predict-no
  11202. -->
  11203. (O1958 ^name predict-no +)
  11204. (S1 ^operator O1958 +)
  11205. Retracting propose*predict-yes
  11206. -->
  11207. (O1957 ^name predict-yes +)
  11208. (S1 ^operator O1957 +)
  11209. Retracting elaborate*reward*based*on*reward
  11210. -->
  11211. (R982 ^value 1 +)
  11212. (R1 ^reward R982 +)
  11213. Retracting elaborate*copy-dir-to-output-link
  11214. -->
  11215. (I3 ^dir R +)
  11216. Retracting rl*prefer*rvt*predict-no*H0*4
  11217. -->
  11218. (S1 ^operator O1958 = 0.2572465541807213)
  11219. Retracting rl*prefer*rvt*predict-no*H0*4*v1*H1*36
  11220. -->
  11221. (S1 ^operator O1958 = 0.7427521913903472)
  11222. Retracting rl*prefer*rvt*predict-yes*H0*3
  11223. -->
  11224. (S1 ^operator O1957 = 0.7368290791081045)
  11225. Retracting rl*prefer*rvt*predict-yes*H0*3*v1*H1*37
  11226. -->
  11227. (S1 ^operator O1957 = -0.3011268063455669)
  11228. =>WM: (13807: S1 ^operator O1960 +)
  11229. =>WM: (13806: S1 ^operator O1959 +)
  11230. =>WM: (13805: I3 ^dir U)
  11231. =>WM: (13804: O1960 ^name predict-no)
  11232. =>WM: (13803: O1959 ^name predict-yes)
  11233. =>WM: (13802: R983 ^value 1)
  11234. =>WM: (13801: R1 ^reward R983)
  11235. <=WM: (13792: S1 ^operator O1957 +)
  11236. <=WM: (13793: S1 ^operator O1958 +)
  11237. <=WM: (13794: S1 ^operator O1958)
  11238. <=WM: (13791: I3 ^dir R)
  11239. <=WM: (13787: R1 ^reward R982)
  11240. <=WM: (13790: O1958 ^name predict-no)
  11241. <=WM: (13789: O1957 ^name predict-yes)
  11242. <=WM: (13788: R982 ^value 1)
  11243. --- Inner Elaboration Phase, active level 1 (S1) ---
  11244. Firing prefer*rvt*predict-yes*H0
  11245. -->
  11246. Firing rl*prefer*rvt*predict-yes*H0*1
  11247. -->
  11248. (S1 ^operator O1959 = 0.)
  11249. Firing prefer*rvt*predict-no*H0
  11250. -->
  11251. Firing rl*prefer*rvt*predict-no*H0*2
  11252. -->
  11253. (S1 ^operator O1960 = 0.9999999999999999)
  11254. inner elaboration loop at bottom goal.
  11255. Retracting rl*prefer*rvt*predict-no*H0*2
  11256. -->
  11257. (S1 ^operator O1958 = 0.9999999999999999)
  11258. Retracting rl*prefer*rvt*predict-yes*H0*1
  11259. -->
  11260. (S1 ^operator O1957 = 0.)
  11261. --- END Proposal Phase ---
  11262. --- Decision Phase ---
  11263. RL update rl*prefer*rvt*predict-no*H0*4 0.586136 -0.32889 0.257247 -> 0.586137 -0.32889 0.257247(R,m,v=1,0.857988,0.12257)
  11264. RL update rl*prefer*rvt*predict-no*H0*4*v1*H1*36 0.413863 0.32889 0.742752 -> 0.413863 0.32889 0.742752(R,m,v=1,1,0)
  11265. =>WM: (13808: S1 ^operator O1960)
  11266. 980: O: O1960 (predict-no)
  11267. --- END Decision Phase ---
  11268. --- Application Phase ---
  11269. --- Firing Productions (PE) For State At Depth 1 ---
  11270. --- Inner Elaboration Phase, active level 1 (S1) ---
  11271. Firing apply*operator
  11272. -->
  11273. (I3 ^predict-no N980 + :O )
  11274. Firing apply*operator*complete
  11275. -->
  11276. (I3 ^predict-no N979 - :O )
  11277. inner elaboration loop at bottom goal.
  11278. --- Change Working Memory (PE) ---
  11279. =>WM: (13809: I3 ^predict-no N980)
  11280. <=WM: (13796: N979 ^status complete)
  11281. <=WM: (13795: I3 ^predict-no N979)
  11282. --- Firing Productions (IE) For State At Depth 1 ---
  11283. --- Inner Elaboration Phase, active level 1 (S1) ---
  11284. Firing monitor*world
  11285. -->
  11286. I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
  11287. --- Change Working Memory (IE) ---
  11288. --- END Application Phase ---
  11289. --- Output Phase ---
  11290. ENV: Agent did: predict-no for direction U in state State-B
  11291. In State-B moving U
  11292. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  11293. predict error 0
  11294. dir: dir isU
  11295. --- END Output Phase ---
  11296. \-/--- Input Phase ---
  11297. =>WM: (13813: I2 ^dir U)
  11298. =>WM: (13812: I2 ^reward 1)
  11299. =>WM: (13811: I2 ^see 0)
  11300. =>WM: (13810: N980 ^status complete)
  11301. <=WM: (13799: I2 ^dir U)
  11302. <=WM: (13798: I2 ^reward 1)
  11303. <=WM: (13797: I2 ^see 0)
  11304. =>WM: (13814: I2 ^level-1 R0-root)
  11305. <=WM: (13800: I2 ^level-1 R0-root)
  11306. --- END Input Phase ---
  11307. --- Proposal Phase ---
  11308. --- Inner Elaboration Phase, active level 1 (S1) ---
  11309. Firing elaborate*copy-see-to-output-link
  11310. -->
  11311. (I3 ^see 0 +)
  11312. Firing elaborate*reward*based*on*reward
  11313. -->
  11314. (R984 ^value 1 +)
  11315. (R1 ^reward R984 +)
  11316. Firing propose*predict-yes
  11317. -->
  11318. (O1961 ^name predict-yes +)
  11319. (S1 ^operator O1961 +)
  11320. Firing propose*predict-no
  11321. -->
  11322. (O1962 ^name predict-no +)
  11323. (S1 ^operator O1962 +)
  11324. Firing rl*prefer*rvt*predict-no*H0*2
  11325. -->
  11326. (S1 ^operator O1960 = 0.9999999999999999)
  11327. Firing rl*prefer*rvt*predict-yes*H0*1
  11328. -->
  11329. (S1 ^operator O1959 = 0.)
  11330. Firing prefer*rvt*predict-yes*H0
  11331. -->
  11332. Firing prefer*rvt*predict-no*H0
  11333. -->
  11334. Firing elaborate*copy-dir-to-output-link
  11335. -->
  11336. (I3 ^dir U +)
  11337. inner elaboration loop at bottom goal.
  11338. Retracting elaborate*copy-see-to-output-link
  11339. -->
  11340. (I3 ^see 0 +)
  11341. Retracting propose*predict-no
  11342. -->
  11343. (O1960 ^name predict-no +)
  11344. (S1 ^operator O1960 +)
  11345. Retracting propose*predict-yes
  11346. -->
  11347. (O1959 ^name predict-yes +)
  11348. (S1 ^operator O1959 +)
  11349. Retracting elaborate*reward*based*on*reward
  11350. -->
  11351. (R983 ^value 1 +)
  11352. (R1 ^reward R983 +)
  11353. Retracting elaborate*copy-dir-to-output-link
  11354. -->
  11355. (I3 ^dir U +)
  11356. Retracting rl*prefer*rvt*predict-no*H0*2
  11357. -->
  11358. (S1 ^operator O1960 = 0.9999999999999999)
  11359. Retracting rl*prefer*rvt*predict-yes*H0*1
  11360. -->
  11361. (S1 ^operator O1959 = 0.)
  11362. =>WM: (13820: S1 ^operator O1962 +)
  11363. =>WM: (13819: S1 ^operator O1961 +)
  11364. =>WM: (13818: O1962 ^name predict-no)
  11365. =>WM: (13817: O1961 ^name predict-yes)
  11366. =>WM: (13816: R984 ^value 1)
  11367. =>WM: (13815: R1 ^reward R984)
  11368. <=WM: (13806: S1 ^operator O1959 +)
  11369. <=WM: (13807: S1 ^operator O1960 +)
  11370. <=WM: (13808: S1 ^operator O1960)
  11371. <=WM: (13801: R1 ^reward R983)
  11372. <=WM: (13804: O1960 ^name predict-no)
  11373. <=WM: (13803: O1959 ^name predict-yes)
  11374. <=WM: (13802: R983 ^value 1)
  11375. --- Inner Elaboration Phase, active level 1 (S1) ---
  11376. Firing prefer*rvt*predict-yes*H0
  11377. -->
  11378. Firing rl*prefer*rvt*predict-yes*H0*1
  11379. -->
  11380. (S1 ^operator O1961 = 0.)
  11381. Firing prefer*rvt*predict-no*H0
  11382. -->
  11383. Firing rl*prefer*rvt*predict-no*H0*2
  11384. -->
  11385. (S1 ^operator O1962 = 0.9999999999999999)
  11386. inner elaboration loop at bottom goal.
  11387. Retracting rl*prefer*rvt*predict-no*H0*2
  11388. -->
  11389. (S1 ^operator O1960 = 0.9999999999999999)
  11390. Retracting rl*prefer*rvt*predict-yes*H0*1
  11391. -->
  11392. (S1 ^operator O1959 = 0.)
  11393. --- END Proposal Phase ---
  11394. --- Decision Phase ---
  11395. RL update rl*prefer*rvt*predict-no*H0*2 1 0 1 -> 1 0 1(R,m,v=1,1,0)
  11396. =>WM: (13821: S1 ^operator O1962)
  11397. 981: O: O1962 (predict-no)
  11398. --- END Decision Phase ---
  11399. --- Application Phase ---
  11400. --- Firing Productions (PE) For State At Depth 1 ---
  11401. --- Inner Elaboration Phase, active level 1 (S1) ---
  11402. Firing apply*operator
  11403. -->
  11404. (I3 ^predict-no N981 + :O )
  11405. Firing apply*operator*complete
  11406. -->
  11407. (I3 ^predict-no N980 - :O )
  11408. inner elaboration loop at bottom goal.
  11409. --- Change Working Memory (PE) ---
  11410. =>WM: (13822: I3 ^predict-no N981)
  11411. <=WM: (13810: N980 ^status complete)
  11412. <=WM: (13809: I3 ^predict-no N980)
  11413. --- Firing Productions (IE) For State At Depth 1 ---
  11414. --- Inner Elaboration Phase, active level 1 (S1) ---
  11415. Firing monitor*world
  11416. -->
  11417. I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
  11418. --- Change Working Memory (IE) ---
  11419. --- END Application Phase ---
  11420. --- Output Phase ---
  11421. ENV: Agent did: predict-no for direction U in state State-B
  11422. In State-B moving U
  11423. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  11424. predict error 0
  11425. dir: dir isL
  11426. --- END Output Phase ---
  11427. |--- Input Phase ---
  11428. =>WM: (13826: I2 ^dir L)
  11429. =>WM: (13825: I2 ^reward 1)
  11430. =>WM: (13824: I2 ^see 0)
  11431. =>WM: (13823: N981 ^status complete)
  11432. <=WM: (13813: I2 ^dir U)
  11433. <=WM: (13812: I2 ^reward 1)
  11434. <=WM: (13811: I2 ^see 0)
  11435. =>WM: (13827: I2 ^level-1 R0-root)
  11436. <=WM: (13814: I2 ^level-1 R0-root)
  11437. --- END Input Phase ---
  11438. --- Proposal Phase ---
  11439. --- Inner Elaboration Phase, active level 1 (S1) ---
  11440. Firing rl*prefer*rvt*predict-no*H0*6*v1*H1*38
  11441. -->
  11442. (S1 ^operator O1962 = 0.04178081990804111)
  11443. Firing rl*prefer*rvt*predict-yes*H0*5*v1*H1*30
  11444. -->
  11445. (S1 ^operator O1961 = 0.5681119444733725)
  11446. Firing prefer*rvt*predict-no*H0*6*v1*H1
  11447. -->
  11448. Firing prefer*rvt*predict-yes*H0*5*v1*H1
  11449. -->
  11450. Firing elaborate*copy-see-to-output-link
  11451. -->
  11452. (I3 ^see 0 +)
  11453. Firing elaborate*reward*based*on*reward
  11454. -->
  11455. (R985 ^value 1 +)
  11456. (R1 ^reward R985 +)
  11457. Firing propose*predict-yes
  11458. -->
  11459. (O1963 ^name predict-yes +)
  11460. (S1 ^operator O1963 +)
  11461. Firing propose*predict-no
  11462. -->
  11463. (O1964 ^name predict-no +)
  11464. (S1 ^operator O1964 +)
  11465. Firing rl*prefer*rvt*predict-no*H0*6
  11466. -->
  11467. (S1 ^operator O1962 = 0.3289460588254962)
  11468. Firing rl*prefer*rvt*predict-yes*H0*5
  11469. -->
  11470. (S1 ^operator O1961 = 0.4318903853359125)
  11471. Firing prefer*rvt*predict-yes*H0
  11472. -->
  11473. Firing prefer*rvt*predict-no*H0
  11474. -->
  11475. Firing elaborate*copy-dir-to-output-link
  11476. -->
  11477. (I3 ^dir L +)
  11478. inner elaboration loop at bottom goal.
  11479. Retracting elaborate*copy-see-to-output-link
  11480. -->
  11481. (I3 ^see 0 +)
  11482. Retracting propose*predict-no
  11483. -->
  11484. (O1962 ^name predict-no +)
  11485. (S1 ^operator O1962 +)
  11486. Retracting propose*predict-yes
  11487. -->
  11488. (O1961 ^name predict-yes +)
  11489. (S1 ^operator O1961 +)
  11490. Retracting elaborate*reward*based*on*reward
  11491. -->
  11492. (R984 ^value 1 +)
  11493. (R1 ^reward R984 +)
  11494. Retracting elaborate*copy-dir-to-output-link
  11495. -->
  11496. (I3 ^dir U +)
  11497. Retracting rl*prefer*rvt*predict-no*H0*2
  11498. -->
  11499. (S1 ^operator O1962 = 0.9999999999999999)
  11500. Retracting rl*prefer*rvt*predict-yes*H0*1
  11501. -->
  11502. (S1 ^operator O1961 = 0.)
  11503. =>WM: (13834: S1 ^operator O1964 +)
  11504. =>WM: (13833: S1 ^operator O1963 +)
  11505. =>WM: (13832: I3 ^dir L)
  11506. =>WM: (13831: O1964 ^name predict-no)
  11507. =>WM: (13830: O1963 ^name predict-yes)
  11508. =>WM: (13829: R985 ^value 1)
  11509. =>WM: (13828: R1 ^reward R985)
  11510. <=WM: (13819: S1 ^operator O1961 +)
  11511. <=WM: (13820: S1 ^operator O1962 +)
  11512. <=WM: (13821: S1 ^operator O1962)
  11513. <=WM: (13805: I3 ^dir U)
  11514. <=WM: (13815: R1 ^reward R984)
  11515. <=WM: (13818: O1962 ^name predict-no)
  11516. <=WM: (13817: O1961 ^name predict-yes)
  11517. <=WM: (13816: R984 ^value 1)
  11518. --- Inner Elaboration Phase, active level 1 (S1) ---
  11519. Firing prefer*rvt*predict-yes*H0
  11520. -->
  11521. Firing rl*prefer*rvt*predict-yes*H0*5*v1*H1*30
  11522. -->
  11523. (S1 ^operator O1963 = 0.5681119444733725)
  11524. Firing rl*prefer*rvt*predict-yes*H0*5
  11525. -->
  11526. (S1 ^operator O1963 = 0.4318903853359125)
  11527. Firing prefer*rvt*predict-yes*H0*5*v1*H1
  11528. -->
  11529. Firing prefer*rvt*predict-no*H0
  11530. -->
  11531. Firing rl*prefer*rvt*predict-no*H0*6*v1*H1*38
  11532. -->
  11533. (S1 ^operator O1964 = 0.04178081990804111)
  11534. Firing rl*prefer*rvt*predict-no*H0*6
  11535. -->
  11536. (S1 ^operator O1964 = 0.3289460588254962)
  11537. Firing prefer*rvt*predict-no*H0*6*v1*H1
  11538. -->
  11539. inner elaboration loop at bottom goal.
  11540. Retracting rl*prefer*rvt*predict-no*H0*6
  11541. -->
  11542. (S1 ^operator O1962 = 0.3289460588254962)
  11543. Retracting rl*prefer*rvt*predict-no*H0*6*v1*H1*38
  11544. -->
  11545. (S1 ^operator O1962 = 0.04178081990804111)
  11546. Retracting rl*prefer*rvt*predict-yes*H0*5
  11547. -->
  11548. (S1 ^operator O1961 = 0.4318903853359125)
  11549. Retracting rl*prefer*rvt*predict-yes*H0*5*v1*H1*30
  11550. -->
  11551. (S1 ^operator O1961 = 0.5681119444733725)
  11552. --- END Proposal Phase ---
  11553. --- Decision Phase ---
  11554. RL update rl*prefer*rvt*predict-no*H0*2 1 0 1 -> 1 0 1(R,m,v=1,1,0)
  11555. =>WM: (13835: S1 ^operator O1963)
  11556. 982: O: O1963 (predict-yes)
  11557. --- END Decision Phase ---
  11558. --- Application Phase ---
  11559. --- Firing Productions (PE) For State At Depth 1 ---
  11560. --- Inner Elaboration Phase, active level 1 (S1) ---
  11561. Firing apply*operator
  11562. -->
  11563. (I3 ^predict-yes N982 + :O )
  11564. Firing apply*operator*complete
  11565. -->
  11566. (I3 ^predict-no N981 - :O )
  11567. inner elaboration loop at bottom goal.
  11568. --- Change Working Memory (PE) ---
  11569. =>WM: (13836: I3 ^predict-yes N982)
  11570. <=WM: (13823: N981 ^status complete)
  11571. <=WM: (13822: I3 ^predict-no N981)
  11572. --- Firing Productions (IE) For State At Depth 1 ---
  11573. --- Inner Elaboration Phase, active level 1 (S1) ---
  11574. Firing monitor*world
  11575. -->
  11576. I see 1 and I'm going to do: predict-yes inner elaboration loop at bottom goal.
  11577. --- Change Working Memory (IE) ---
  11578. --- END Application Phase ---
  11579. --- Output Phase ---
  11580. ENV: Agent did: predict-yes for direction L in state State-B
  11581. In State-B moving L
  11582. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  11583. predict error 0
  11584. dir: dir isU
  11585. --- END Output Phase ---
  11586. \--- Input Phase ---
  11587. =>WM: (13840: I2 ^dir U)
  11588. =>WM: (13839: I2 ^reward 1)
  11589. =>WM: (13838: I2 ^see 1)
  11590. =>WM: (13837: N982 ^status complete)
  11591. <=WM: (13826: I2 ^dir L)
  11592. <=WM: (13825: I2 ^reward 1)
  11593. <=WM: (13824: I2 ^see 0)
  11594. =>WM: (13841: I2 ^level-1 L1-root)
  11595. <=WM: (13827: I2 ^level-1 R0-root)
  11596. --- END Input Phase ---
  11597. --- Proposal Phase ---
  11598. --- Inner Elaboration Phase, active level 1 (S1) ---
  11599. Firing elaborate*copy-see-to-output-link
  11600. -->
  11601. (I3 ^see 1 +)
  11602. Firing elaborate*reward*based*on*reward
  11603. -->
  11604. (R986 ^value 1 +)
  11605. (R1 ^reward R986 +)
  11606. Firing propose*predict-yes
  11607. -->
  11608. (O1965 ^name predict-yes +)
  11609. (S1 ^operator O1965 +)
  11610. Firing propose*predict-no
  11611. -->
  11612. (O1966 ^name predict-no +)
  11613. (S1 ^operator O1966 +)
  11614. Firing rl*prefer*rvt*predict-no*H0*2
  11615. -->
  11616. (S1 ^operator O1964 = 0.9999999999999999)
  11617. Firing rl*prefer*rvt*predict-yes*H0*1
  11618. -->
  11619. (S1 ^operator O1963 = 0.)
  11620. Firing prefer*rvt*predict-yes*H0
  11621. -->
  11622. Firing prefer*rvt*predict-no*H0
  11623. -->
  11624. Firing elaborate*copy-dir-to-output-link
  11625. -->
  11626. (I3 ^dir U +)
  11627. inner elaboration loop at bottom goal.
  11628. Retracting elaborate*copy-see-to-output-link
  11629. -->
  11630. (I3 ^see 0 +)
  11631. Retracting propose*predict-no
  11632. -->
  11633. (O1964 ^name predict-no +)
  11634. (S1 ^operator O1964 +)
  11635. Retracting propose*predict-yes
  11636. -->
  11637. (O1963 ^name predict-yes +)
  11638. (S1 ^operator O1963 +)
  11639. Retracting elaborate*reward*based*on*reward
  11640. -->
  11641. (R985 ^value 1 +)
  11642. (R1 ^reward R985 +)
  11643. Retracting elaborate*copy-dir-to-output-link
  11644. -->
  11645. (I3 ^dir L +)
  11646. Retracting rl*prefer*rvt*predict-no*H0*6
  11647. -->
  11648. (S1 ^operator O1964 = 0.3289460588254962)
  11649. Retracting rl*prefer*rvt*predict-no*H0*6*v1*H1*38
  11650. -->
  11651. (S1 ^operator O1964 = 0.04178081990804111)
  11652. Retracting rl*prefer*rvt*predict-yes*H0*5
  11653. -->
  11654. (S1 ^operator O1963 = 0.4318903853359125)
  11655. Retracting rl*prefer*rvt*predict-yes*H0*5*v1*H1*30
  11656. -->
  11657. (S1 ^operator O1963 = 0.5681119444733725)
  11658. =>WM: (13849: S1 ^operator O1966 +)
  11659. =>WM: (13848: S1 ^operator O1965 +)
  11660. =>WM: (13847: I3 ^dir U)
  11661. =>WM: (13846: O1966 ^name predict-no)
  11662. =>WM: (13845: O1965 ^name predict-yes)
  11663. =>WM: (13844: R986 ^value 1)
  11664. =>WM: (13843: R1 ^reward R986)
  11665. =>WM: (13842: I3 ^see 1)
  11666. <=WM: (13833: S1 ^operator O1963 +)
  11667. <=WM: (13835: S1 ^operator O1963)
  11668. <=WM: (13834: S1 ^operator O1964 +)
  11669. <=WM: (13832: I3 ^dir L)
  11670. <=WM: (13828: R1 ^reward R985)
  11671. <=WM: (13773: I3 ^see 0)
  11672. <=WM: (13831: O1964 ^name predict-no)
  11673. <=WM: (13830: O1963 ^name predict-yes)
  11674. <=WM: (13829: R985 ^value 1)
  11675. --- Inner Elaboration Phase, active level 1 (S1) ---
  11676. Firing prefer*rvt*predict-yes*H0
  11677. -->
  11678. Firing rl*prefer*rvt*predict-yes*H0*1
  11679. -->
  11680. (S1 ^operator O1965 = 0.)
  11681. Firing prefer*rvt*predict-no*H0
  11682. -->
  11683. Firing rl*prefer*rvt*predict-no*H0*2
  11684. -->
  11685. (S1 ^operator O1966 = 0.9999999999999999)
  11686. inner elaboration loop at bottom goal.
  11687. Retracting rl*prefer*rvt*predict-no*H0*2
  11688. -->
  11689. (S1 ^operator O1964 = 0.9999999999999999)
  11690. Retracting rl*prefer*rvt*predict-yes*H0*1
  11691. -->
  11692. (S1 ^operator O1963 = 0.)
  11693. --- END Proposal Phase ---
  11694. --- Decision Phase ---
  11695. RL update rl*prefer*rvt*predict-yes*H0*5 0.683777 -0.251886 0.43189 -> 0.683776 -0.251886 0.43189(R,m,v=1,0.922156,0.072217)
  11696. RL update rl*prefer*rvt*predict-yes*H0*5*v1*H1*30 0.316226 0.251886 0.568112 -> 0.316225 0.251886 0.568112(R,m,v=1,1,0)
  11697. =>WM: (13850: S1 ^operator O1966)
  11698. 983: O: O1966 (predict-no)
  11699. --- END Decision Phase ---
  11700. --- Application Phase ---
  11701. --- Firing Productions (PE) For State At Depth 1 ---
  11702. --- Inner Elaboration Phase, active level 1 (S1) ---
  11703. Firing apply*operator
  11704. -->
  11705. (I3 ^predict-no N983 + :O )
  11706. Firing apply*operator*complete
  11707. -->
  11708. (I3 ^predict-yes N982 - :O )
  11709. inner elaboration loop at bottom goal.
  11710. --- Change Working Memory (PE) ---
  11711. =>WM: (13851: I3 ^predict-no N983)
  11712. <=WM: (13837: N982 ^status complete)
  11713. <=WM: (13836: I3 ^predict-yes N982)
  11714. --- Firing Productions (IE) For State At Depth 1 ---
  11715. --- Inner Elaboration Phase, active level 1 (S1) ---
  11716. Firing monitor*world
  11717. -->
  11718. I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
  11719. --- Change Working Memory (IE) ---
  11720. --- END Application Phase ---
  11721. --- Output Phase ---
  11722. ENV: Agent did: predict-no for direction U in state State-A
  11723. In State-A moving U
  11724. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  11725. predict error 0
  11726. dir: dir isL
  11727. --- END Output Phase ---
  11728. -/|--- Input Phase ---
  11729. =>WM: (13855: I2 ^dir L)
  11730. =>WM: (13854: I2 ^reward 1)
  11731. =>WM: (13853: I2 ^see 0)
  11732. =>WM: (13852: N983 ^status complete)
  11733. <=WM: (13840: I2 ^dir U)
  11734. <=WM: (13839: I2 ^reward 1)
  11735. <=WM: (13838: I2 ^see 1)
  11736. =>WM: (13856: I2 ^level-1 L1-root)
  11737. <=WM: (13841: I2 ^level-1 L1-root)
  11738. --- END Input Phase ---
  11739. --- Proposal Phase ---
  11740. --- Inner Elaboration Phase, active level 1 (S1) ---
  11741. Firing rl*prefer*rvt*predict-no*H0*6*v1*H1*43
  11742. -->
  11743. (S1 ^operator O1966 = 0.6710520874416326)
  11744. Firing rl*prefer*rvt*predict-yes*H0*5*v1*H1*31
  11745. -->
  11746. (S1 ^operator O1965 = -0.06092862110810815)
  11747. Firing prefer*rvt*predict-no*H0*6*v1*H1
  11748. -->
  11749. Firing prefer*rvt*predict-yes*H0*5*v1*H1
  11750. -->
  11751. Firing elaborate*copy-see-to-output-link
  11752. -->
  11753. (I3 ^see 0 +)
  11754. Firing elaborate*reward*based*on*reward
  11755. -->
  11756. (R987 ^value 1 +)
  11757. (R1 ^reward R987 +)
  11758. Firing propose*predict-yes
  11759. -->
  11760. (O1967 ^name predict-yes +)
  11761. (S1 ^operator O1967 +)
  11762. Firing propose*predict-no
  11763. -->
  11764. (O1968 ^name predict-no +)
  11765. (S1 ^operator O1968 +)
  11766. Firing rl*prefer*rvt*predict-no*H0*6
  11767. -->
  11768. (S1 ^operator O1966 = 0.3289460588254962)
  11769. Firing rl*prefer*rvt*predict-yes*H0*5
  11770. -->
  11771. (S1 ^operator O1965 = 0.4318900358645197)
  11772. Firing prefer*rvt*predict-yes*H0
  11773. -->
  11774. Firing prefer*rvt*predict-no*H0
  11775. -->
  11776. Firing elaborate*copy-dir-to-output-link
  11777. -->
  11778. (I3 ^dir L +)
  11779. inner elaboration loop at bottom goal.
  11780. Retracting elaborate*copy-see-to-output-link
  11781. -->
  11782. (I3 ^see 1 +)
  11783. Retracting propose*predict-no
  11784. -->
  11785. (O1966 ^name predict-no +)
  11786. (S1 ^operator O1966 +)
  11787. Retracting propose*predict-yes
  11788. -->
  11789. (O1965 ^name predict-yes +)
  11790. (S1 ^operator O1965 +)
  11791. Retracting elaborate*reward*based*on*reward
  11792. -->
  11793. (R986 ^value 1 +)
  11794. (R1 ^reward R986 +)
  11795. Retracting elaborate*copy-dir-to-output-link
  11796. -->
  11797. (I3 ^dir U +)
  11798. Retracting rl*prefer*rvt*predict-no*H0*2
  11799. -->
  11800. (S1 ^operator O1966 = 0.9999999999999999)
  11801. Retracting rl*prefer*rvt*predict-yes*H0*1
  11802. -->
  11803. (S1 ^operator O1965 = 0.)
  11804. =>WM: (13864: S1 ^operator O1968 +)
  11805. =>WM: (13863: S1 ^operator O1967 +)
  11806. =>WM: (13862: I3 ^dir L)
  11807. =>WM: (13861: O1968 ^name predict-no)
  11808. =>WM: (13860: O1967 ^name predict-yes)
  11809. =>WM: (13859: R987 ^value 1)
  11810. =>WM: (13858: R1 ^reward R987)
  11811. =>WM: (13857: I3 ^see 0)
  11812. <=WM: (13848: S1 ^operator O1965 +)
  11813. <=WM: (13849: S1 ^operator O1966 +)
  11814. <=WM: (13850: S1 ^operator O1966)
  11815. <=WM: (13847: I3 ^dir U)
  11816. <=WM: (13843: R1 ^reward R986)
  11817. <=WM: (13842: I3 ^see 1)
  11818. <=WM: (13846: O1966 ^name predict-no)
  11819. <=WM: (13845: O1965 ^name predict-yes)
  11820. <=WM: (13844: R986 ^value 1)
  11821. --- Inner Elaboration Phase, active level 1 (S1) ---
  11822. Firing prefer*rvt*predict-yes*H0
  11823. -->
  11824. Firing rl*prefer*rvt*predict-yes*H0*5*v1*H1*31
  11825. -->
  11826. (S1 ^operator O1967 = -0.06092862110810815)
  11827. Firing rl*prefer*rvt*predict-yes*H0*5
  11828. -->
  11829. (S1 ^operator O1967 = 0.4318900358645197)
  11830. Firing prefer*rvt*predict-yes*H0*5*v1*H1
  11831. -->
  11832. Firing prefer*rvt*predict-no*H0
  11833. -->
  11834. Firing rl*prefer*rvt*predict-no*H0*6*v1*H1*43
  11835. -->
  11836. (S1 ^operator O1968 = 0.6710520874416326)
  11837. Firing rl*prefer*rvt*predict-no*H0*6
  11838. -->
  11839. (S1 ^operator O1968 = 0.3289460588254962)
  11840. Firing prefer*rvt*predict-no*H0*6*v1*H1
  11841. -->
  11842. inner elaboration loop at bottom goal.
  11843. Retracting rl*prefer*rvt*predict-no*H0*6
  11844. -->
  11845. (S1 ^operator O1966 = 0.3289460588254962)
  11846. Retracting rl*prefer*rvt*predict-no*H0*6*v1*H1*43
  11847. -->
  11848. (S1 ^operator O1966 = 0.6710520874416326)
  11849. Retracting rl*prefer*rvt*predict-yes*H0*5
  11850. -->
  11851. (S1 ^operator O1965 = 0.4318900358645197)
  11852. Retracting rl*prefer*rvt*predict-yes*H0*5*v1*H1*31
  11853. -->
  11854. (S1 ^operator O1965 = -0.06092862110810815)
  11855. --- END Proposal Phase ---
  11856. --- Decision Phase ---
  11857. RL update rl*prefer*rvt*predict-no*H0*2 1 0 1 -> 1 0 1(R,m,v=1,1,0)
  11858. =>WM: (13865: S1 ^operator O1968)
  11859. 984: O: O1968 (predict-no)
  11860. --- END Decision Phase ---
  11861. --- Application Phase ---
  11862. --- Firing Productions (PE) For State At Depth 1 ---
  11863. --- Inner Elaboration Phase, active level 1 (S1) ---
  11864. Firing apply*operator
  11865. -->
  11866. (I3 ^predict-no N984 + :O )
  11867. Firing apply*operator*complete
  11868. -->
  11869. (I3 ^predict-no N983 - :O )
  11870. inner elaboration loop at bottom goal.
  11871. --- Change Working Memory (PE) ---
  11872. =>WM: (13866: I3 ^predict-no N984)
  11873. <=WM: (13852: N983 ^status complete)
  11874. <=WM: (13851: I3 ^predict-no N983)
  11875. --- Firing Productions (IE) For State At Depth 1 ---
  11876. --- Inner Elaboration Phase, active level 1 (S1) ---
  11877. Firing monitor*world
  11878. -->
  11879. I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
  11880. --- Change Working Memory (IE) ---
  11881. --- END Application Phase ---
  11882. --- Output Phase ---
  11883. ENV: Agent did: predict-no for direction L in state State-A
  11884. In State-A moving L
  11885. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  11886. predict error 0
  11887. dir: dir isU
  11888. --- END Output Phase ---
  11889. \---- Input Phase ---
  11890. =>WM: (13870: I2 ^dir U)
  11891. =>WM: (13869: I2 ^reward 1)
  11892. =>WM: (13868: I2 ^see 0)
  11893. =>WM: (13867: N984 ^status complete)
  11894. <=WM: (13855: I2 ^dir L)
  11895. <=WM: (13854: I2 ^reward 1)
  11896. <=WM: (13853: I2 ^see 0)
  11897. =>WM: (13871: I2 ^level-1 L0-root)
  11898. <=WM: (13856: I2 ^level-1 L1-root)
  11899. --- END Input Phase ---
  11900. --- Proposal Phase ---
  11901. --- Inner Elaboration Phase, active level 1 (S1) ---
  11902. Firing elaborate*copy-see-to-output-link
  11903. -->
  11904. (I3 ^see 0 +)
  11905. Firing elaborate*reward*based*on*reward
  11906. -->
  11907. (R988 ^value 1 +)
  11908. (R1 ^reward R988 +)
  11909. Firing propose*predict-yes
  11910. -->
  11911. (O1969 ^name predict-yes +)
  11912. (S1 ^operator O1969 +)
  11913. Firing propose*predict-no
  11914. -->
  11915. (O1970 ^name predict-no +)
  11916. (S1 ^operator O1970 +)
  11917. Firing rl*prefer*rvt*predict-no*H0*2
  11918. -->
  11919. (S1 ^operator O1968 = 0.9999999999999999)
  11920. Firing rl*prefer*rvt*predict-yes*H0*1
  11921. -->
  11922. (S1 ^operator O1967 = 0.)
  11923. Firing prefer*rvt*predict-yes*H0
  11924. -->
  11925. Firing prefer*rvt*predict-no*H0
  11926. -->
  11927. Firing elaborate*copy-dir-to-output-link
  11928. -->
  11929. (I3 ^dir U +)
  11930. inner elaboration loop at bottom goal.
  11931. Retracting elaborate*copy-see-to-output-link
  11932. -->
  11933. (I3 ^see 0 +)
  11934. Retracting propose*predict-no
  11935. -->
  11936. (O1968 ^name predict-no +)
  11937. (S1 ^operator O1968 +)
  11938. Retracting propose*predict-yes
  11939. -->
  11940. (O1967 ^name predict-yes +)
  11941. (S1 ^operator O1967 +)
  11942. Retracting elaborate*reward*based*on*reward
  11943. -->
  11944. (R987 ^value 1 +)
  11945. (R1 ^reward R987 +)
  11946. Retracting elaborate*copy-dir-to-output-link
  11947. -->
  11948. (I3 ^dir L +)
  11949. Retracting rl*prefer*rvt*predict-no*H0*6
  11950. -->
  11951. (S1 ^operator O1968 = 0.3289460588254962)
  11952. Retracting rl*prefer*rvt*predict-no*H0*6*v1*H1*43
  11953. -->
  11954. (S1 ^operator O1968 = 0.6710520874416326)
  11955. Retracting rl*prefer*rvt*predict-yes*H0*5
  11956. -->
  11957. (S1 ^operator O1967 = 0.4318900358645197)
  11958. Retracting rl*prefer*rvt*predict-yes*H0*5*v1*H1*31
  11959. -->
  11960. (S1 ^operator O1967 = -0.06092862110810815)
  11961. =>WM: (13878: S1 ^operator O1970 +)
  11962. =>WM: (13877: S1 ^operator O1969 +)
  11963. =>WM: (13876: I3 ^dir U)
  11964. =>WM: (13875: O1970 ^name predict-no)
  11965. =>WM: (13874: O1969 ^name predict-yes)
  11966. =>WM: (13873: R988 ^value 1)
  11967. =>WM: (13872: R1 ^reward R988)
  11968. <=WM: (13863: S1 ^operator O1967 +)
  11969. <=WM: (13864: S1 ^operator O1968 +)
  11970. <=WM: (13865: S1 ^operator O1968)
  11971. <=WM: (13862: I3 ^dir L)
  11972. <=WM: (13858: R1 ^reward R987)
  11973. <=WM: (13861: O1968 ^name predict-no)
  11974. <=WM: (13860: O1967 ^name predict-yes)
  11975. <=WM: (13859: R987 ^value 1)
  11976. --- Inner Elaboration Phase, active level 1 (S1) ---
  11977. Firing prefer*rvt*predict-yes*H0
  11978. -->
  11979. Firing rl*prefer*rvt*predict-yes*H0*1
  11980. -->
  11981. (S1 ^operator O1969 = 0.)
  11982. Firing prefer*rvt*predict-no*H0
  11983. -->
  11984. Firing rl*prefer*rvt*predict-no*H0*2
  11985. -->
  11986. (S1 ^operator O1970 = 0.9999999999999999)
  11987. inner elaboration loop at bottom goal.
  11988. Retracting rl*prefer*rvt*predict-no*H0*2
  11989. -->
  11990. (S1 ^operator O1968 = 0.9999999999999999)
  11991. Retracting rl*prefer*rvt*predict-yes*H0*1
  11992. -->
  11993. (S1 ^operator O1967 = 0.)
  11994. --- END Proposal Phase ---
  11995. --- Decision Phase ---
  11996. RL update rl*prefer*rvt*predict-no*H0*6 0.565403 -0.236457 0.328946 -> 0.565404 -0.236458 0.328946(R,m,v=1,0.904459,0.0869672)
  11997. RL update rl*prefer*rvt*predict-no*H0*6*v1*H1*43 0.434593 0.236459 0.671052 -> 0.434593 0.236459 0.671052(R,m,v=1,1,0)
  11998. =>WM: (13879: S1 ^operator O1970)
  11999. 985: O: O1970 (predict-no)
  12000. --- END Decision Phase ---
  12001. --- Application Phase ---
  12002. --- Firing Productions (PE) For State At Depth 1 ---
  12003. --- Inner Elaboration Phase, active level 1 (S1) ---
  12004. Firing apply*operator
  12005. -->
  12006. (I3 ^predict-no N985 + :O )
  12007. Firing apply*operator*complete
  12008. -->
  12009. (I3 ^predict-no N984 - :O )
  12010. inner elaboration loop at bottom goal.
  12011. --- Change Working Memory (PE) ---
  12012. =>WM: (13880: I3 ^predict-no N985)
  12013. <=WM: (13867: N984 ^status complete)
  12014. <=WM: (13866: I3 ^predict-no N984)
  12015. --- Firing Productions (IE) For State At Depth 1 ---
  12016. --- Inner Elaboration Phase, active level 1 (S1) ---
  12017. Firing monitor*world
  12018. -->
  12019. I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
  12020. --- Change Working Memory (IE) ---
  12021. --- END Application Phase ---
  12022. --- Output Phase ---
  12023. ENV: Agent did: predict-no for direction U in state State-A
  12024. In State-A moving U
  12025. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  12026. predict error 0
  12027. dir: dir isR
  12028. --- END Output Phase ---
  12029. /|\-sleeping...
  12030. /--- Input Phase ---
  12031. =>WM: (13884: I2 ^dir R)
  12032. =>WM: (13883: I2 ^reward 1)
  12033. =>WM: (13882: I2 ^see 0)
  12034. =>WM: (13881: N985 ^status complete)
  12035. <=WM: (13870: I2 ^dir U)
  12036. <=WM: (13869: I2 ^reward 1)
  12037. <=WM: (13868: I2 ^see 0)
  12038. =>WM: (13885: I2 ^level-1 L0-root)
  12039. <=WM: (13871: I2 ^level-1 L0-root)
  12040. --- END Input Phase ---
  12041. --- Proposal Phase ---
  12042. --- Inner Elaboration Phase, active level 1 (S1) ---
  12043. Firing rl*prefer*rvt*predict-no*H0*4*v1*H1*34
  12044. -->
  12045. (S1 ^operator O1970 = -0.07401383653737587)
  12046. Firing rl*prefer*rvt*predict-yes*H0*3*v1*H1*35
  12047. -->
  12048. (S1 ^operator O1969 = 0.2631756442840678)
  12049. Firing prefer*rvt*predict-no*H0*4*v1*H1
  12050. -->
  12051. Firing prefer*rvt*predict-yes*H0*3*v1*H1
  12052. -->
  12053. Firing elaborate*copy-see-to-output-link
  12054. -->
  12055. (I3 ^see 0 +)
  12056. Firing elaborate*reward*based*on*reward
  12057. -->
  12058. (R989 ^value 1 +)
  12059. (R1 ^reward R989 +)
  12060. Firing propose*predict-yes
  12061. -->
  12062. (O1971 ^name predict-yes +)
  12063. (S1 ^operator O1971 +)
  12064. Firing propose*predict-no
  12065. -->
  12066. (O1972 ^name predict-no +)
  12067. (S1 ^operator O1972 +)
  12068. Firing rl*prefer*rvt*predict-no*H0*4
  12069. -->
  12070. (S1 ^operator O1970 = 0.257246742345061)
  12071. Firing rl*prefer*rvt*predict-yes*H0*3
  12072. -->
  12073. (S1 ^operator O1969 = 0.7368290791081045)
  12074. Firing prefer*rvt*predict-yes*H0
  12075. -->
  12076. Firing prefer*rvt*predict-no*H0
  12077. -->
  12078. Firing elaborate*copy-dir-to-output-link
  12079. -->
  12080. (I3 ^dir R +)
  12081. inner elaboration loop at bottom goal.
  12082. Retracting elaborate*copy-see-to-output-link
  12083. -->
  12084. (I3 ^see 0 +)
  12085. Retracting propose*predict-no
  12086. -->
  12087. (O1970 ^name predict-no +)
  12088. (S1 ^operator O1970 +)
  12089. Retracting propose*predict-yes
  12090. -->
  12091. (O1969 ^name predict-yes +)
  12092. (S1 ^operator O1969 +)
  12093. Retracting elaborate*reward*based*on*reward
  12094. -->
  12095. (R988 ^value 1 +)
  12096. (R1 ^reward R988 +)
  12097. Retracting elaborate*copy-dir-to-output-link
  12098. -->
  12099. (I3 ^dir U +)
  12100. Retracting rl*prefer*rvt*predict-no*H0*2
  12101. -->
  12102. (S1 ^operator O1970 = 0.9999999999999999)
  12103. Retracting rl*prefer*rvt*predict-yes*H0*1
  12104. -->
  12105. (S1 ^operator O1969 = 0.)
  12106. =>WM: (13892: S1 ^operator O1972 +)
  12107. =>WM: (13891: S1 ^operator O1971 +)
  12108. =>WM: (13890: I3 ^dir R)
  12109. =>WM: (13889: O1972 ^name predict-no)
  12110. =>WM: (13888: O1971 ^name predict-yes)
  12111. =>WM: (13887: R989 ^value 1)
  12112. =>WM: (13886: R1 ^reward R989)
  12113. <=WM: (13877: S1 ^operator O1969 +)
  12114. <=WM: (13878: S1 ^operator O1970 +)
  12115. <=WM: (13879: S1 ^operator O1970)
  12116. <=WM: (13876: I3 ^dir U)
  12117. <=WM: (13872: R1 ^reward R988)
  12118. <=WM: (13875: O1970 ^name predict-no)
  12119. <=WM: (13874: O1969 ^name predict-yes)
  12120. <=WM: (13873: R988 ^value 1)
  12121. --- Inner Elaboration Phase, active level 1 (S1) ---
  12122. Firing prefer*rvt*predict-yes*H0
  12123. -->
  12124. Firing rl*prefer*rvt*predict-yes*H0*3*v1*H1*35
  12125. -->
  12126. (S1 ^operator O1971 = 0.2631756442840678)
  12127. Firing rl*prefer*rvt*predict-yes*H0*3
  12128. -->
  12129. (S1 ^operator O1971 = 0.7368290791081045)
  12130. Firing prefer*rvt*predict-yes*H0*3*v1*H1
  12131. -->
  12132. Firing prefer*rvt*predict-no*H0
  12133. -->
  12134. Firing rl*prefer*rvt*predict-no*H0*4*v1*H1*34
  12135. -->
  12136. (S1 ^operator O1972 = -0.07401383653737587)
  12137. Firing rl*prefer*rvt*predict-no*H0*4
  12138. -->
  12139. (S1 ^operator O1972 = 0.257246742345061)
  12140. Firing prefer*rvt*predict-no*H0*4*v1*H1
  12141. -->
  12142. inner elaboration loop at bottom goal.
  12143. Retracting rl*prefer*rvt*predict-no*H0*4
  12144. -->
  12145. (S1 ^operator O1970 = 0.257246742345061)
  12146. Retracting rl*prefer*rvt*predict-no*H0*4*v1*H1*34
  12147. -->
  12148. (S1 ^operator O1970 = -0.07401383653737587)
  12149. Retracting rl*prefer*rvt*predict-yes*H0*3
  12150. -->
  12151. (S1 ^operator O1969 = 0.7368290791081045)
  12152. Retracting rl*prefer*rvt*predict-yes*H0*3*v1*H1*35
  12153. -->
  12154. (S1 ^operator O1969 = 0.2631756442840678)
  12155. --- END Proposal Phase ---
  12156. --- Decision Phase ---
  12157. RL update rl*prefer*rvt*predict-no*H0*2 1 0 1 -> 1 0 1(R,m,v=1,1,0)
  12158. =>WM: (13893: S1 ^operator O1971)
  12159. 986: O: O1971 (predict-yes)
  12160. --- END Decision Phase ---
  12161. --- Application Phase ---
  12162. --- Firing Productions (PE) For State At Depth 1 ---
  12163. --- Inner Elaboration Phase, active level 1 (S1) ---
  12164. Firing apply*operator
  12165. -->
  12166. (I3 ^predict-yes N986 + :O )
  12167. Firing apply*operator*complete
  12168. -->
  12169. (I3 ^predict-no N985 - :O )
  12170. inner elaboration loop at bottom goal.
  12171. --- Change Working Memory (PE) ---
  12172. =>WM: (13894: I3 ^predict-yes N986)
  12173. <=WM: (13881: N985 ^status complete)
  12174. <=WM: (13880: I3 ^predict-no N985)
  12175. --- Firing Productions (IE) For State At Depth 1 ---
  12176. --- Inner Elaboration Phase, active level 1 (S1) ---
  12177. Firing monitor*world
  12178. -->
  12179. I see 1 and I'm going to do: predict-yes inner elaboration loop at bottom goal.
  12180. --- Change Working Memory (IE) ---
  12181. --- END Application Phase ---
  12182. --- Output Phase ---
  12183. ENV: Agent did: predict-yes for direction R in state State-A
  12184. In State-A moving R
  12185. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  12186. predict error 0
  12187. dir: dir isU
  12188. --- END Output Phase ---
  12189. |\--- Input Phase ---
  12190. =>WM: (13898: I2 ^dir U)
  12191. =>WM: (13897: I2 ^reward 1)
  12192. =>WM: (13896: I2 ^see 1)
  12193. =>WM: (13895: N986 ^status complete)
  12194. <=WM: (13884: I2 ^dir R)
  12195. <=WM: (13883: I2 ^reward 1)
  12196. <=WM: (13882: I2 ^see 0)
  12197. =>WM: (13899: I2 ^level-1 R1-root)
  12198. <=WM: (13885: I2 ^level-1 L0-root)
  12199. --- END Input Phase ---
  12200. --- Proposal Phase ---
  12201. --- Inner Elaboration Phase, active level 1 (S1) ---
  12202. Firing elaborate*copy-see-to-output-link
  12203. -->
  12204. (I3 ^see 1 +)
  12205. Firing elaborate*reward*based*on*reward
  12206. -->
  12207. (R990 ^value 1 +)
  12208. (R1 ^reward R990 +)
  12209. Firing propose*predict-yes
  12210. -->
  12211. (O1973 ^name predict-yes +)
  12212. (S1 ^operator O1973 +)
  12213. Firing propose*predict-no
  12214. -->
  12215. (O1974 ^name predict-no +)
  12216. (S1 ^operator O1974 +)
  12217. Firing rl*prefer*rvt*predict-no*H0*2
  12218. -->
  12219. (S1 ^operator O1972 = 0.9999999999999999)
  12220. Firing rl*prefer*rvt*predict-yes*H0*1
  12221. -->
  12222. (S1 ^operator O1971 = 0.)
  12223. Firing prefer*rvt*predict-yes*H0
  12224. -->
  12225. Firing prefer*rvt*predict-no*H0
  12226. -->
  12227. Firing elaborate*copy-dir-to-output-link
  12228. -->
  12229. (I3 ^dir U +)
  12230. inner elaboration loop at bottom goal.
  12231. Retracting elaborate*copy-see-to-output-link
  12232. -->
  12233. (I3 ^see 0 +)
  12234. Retracting propose*predict-no
  12235. -->
  12236. (O1972 ^name predict-no +)
  12237. (S1 ^operator O1972 +)
  12238. Retracting propose*predict-yes
  12239. -->
  12240. (O1971 ^name predict-yes +)
  12241. (S1 ^operator O1971 +)
  12242. Retracting elaborate*reward*based*on*reward
  12243. -->
  12244. (R989 ^value 1 +)
  12245. (R1 ^reward R989 +)
  12246. Retracting elaborate*copy-dir-to-output-link
  12247. -->
  12248. (I3 ^dir R +)
  12249. Retracting rl*prefer*rvt*predict-no*H0*4
  12250. -->
  12251. (S1 ^operator O1972 = 0.257246742345061)
  12252. Retracting rl*prefer*rvt*predict-no*H0*4*v1*H1*34
  12253. -->
  12254. (S1 ^operator O1972 = -0.07401383653737587)
  12255. Retracting rl*prefer*rvt*predict-yes*H0*3
  12256. -->
  12257. (S1 ^operator O1971 = 0.7368290791081045)
  12258. Retracting rl*prefer*rvt*predict-yes*H0*3*v1*H1*35
  12259. -->
  12260. (S1 ^operator O1971 = 0.2631756442840678)
  12261. =>WM: (13907: S1 ^operator O1974 +)
  12262. =>WM: (13906: S1 ^operator O1973 +)
  12263. =>WM: (13905: I3 ^dir U)
  12264. =>WM: (13904: O1974 ^name predict-no)
  12265. =>WM: (13903: O1973 ^name predict-yes)
  12266. =>WM: (13902: R990 ^value 1)
  12267. =>WM: (13901: R1 ^reward R990)
  12268. =>WM: (13900: I3 ^see 1)
  12269. <=WM: (13891: S1 ^operator O1971 +)
  12270. <=WM: (13893: S1 ^operator O1971)
  12271. <=WM: (13892: S1 ^operator O1972 +)
  12272. <=WM: (13890: I3 ^dir R)
  12273. <=WM: (13886: R1 ^reward R989)
  12274. <=WM: (13857: I3 ^see 0)
  12275. <=WM: (13889: O1972 ^name predict-no)
  12276. <=WM: (13888: O1971 ^name predict-yes)
  12277. <=WM: (13887: R989 ^value 1)
  12278. --- Inner Elaboration Phase, active level 1 (S1) ---
  12279. Firing prefer*rvt*predict-yes*H0
  12280. -->
  12281. Firing rl*prefer*rvt*predict-yes*H0*1
  12282. -->
  12283. (S1 ^operator O1973 = 0.)
  12284. Firing prefer*rvt*predict-no*H0
  12285. -->
  12286. Firing rl*prefer*rvt*predict-no*H0*2
  12287. -->
  12288. (S1 ^operator O1974 = 0.9999999999999999)
  12289. inner elaboration loop at bottom goal.
  12290. Retracting rl*prefer*rvt*predict-no*H0*2
  12291. -->
  12292. (S1 ^operator O1972 = 0.9999999999999999)
  12293. Retracting rl*prefer*rvt*predict-yes*H0*1
  12294. -->
  12295. (S1 ^operator O1971 = 0.)
  12296. --- END Proposal Phase ---
  12297. --- Decision Phase ---
  12298. RL update rl*prefer*rvt*predict-yes*H0*3 0.748236 -0.0114073 0.736829 -> 0.748236 -0.0114078 0.736828(R,m,v=1,0.895706,0.0939938)
  12299. RL update rl*prefer*rvt*predict-yes*H0*3*v1*H1*35 0.251765 0.0114107 0.263176 -> 0.251765 0.0114102 0.263175(R,m,v=1,1,0)
  12300. =>WM: (13908: S1 ^operator O1974)
  12301. 987: O: O1974 (predict-no)
  12302. --- END Decision Phase ---
  12303. --- Application Phase ---
  12304. --- Firing Productions (PE) For State At Depth 1 ---
  12305. --- Inner Elaboration Phase, active level 1 (S1) ---
  12306. Firing apply*operator
  12307. -->
  12308. (I3 ^predict-no N987 + :O )
  12309. Firing apply*operator*complete
  12310. -->
  12311. (I3 ^predict-yes N986 - :O )
  12312. inner elaboration loop at bottom goal.
  12313. --- Change Working Memory (PE) ---
  12314. =>WM: (13909: I3 ^predict-no N987)
  12315. <=WM: (13895: N986 ^status complete)
  12316. <=WM: (13894: I3 ^predict-yes N986)
  12317. --- Firing Productions (IE) For State At Depth 1 ---
  12318. --- Inner Elaboration Phase, active level 1 (S1) ---
  12319. Firing monitor*world
  12320. -->
  12321. I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
  12322. --- Change Working Memory (IE) ---
  12323. --- END Application Phase ---
  12324. --- Output Phase ---
  12325. ENV: Agent did: predict-no for direction U in state State-B
  12326. In State-B moving U
  12327. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  12328. predict error 0
  12329. dir: dir isR
  12330. --- END Output Phase ---
  12331. -/|--- Input Phase ---
  12332. =>WM: (13913: I2 ^dir R)
  12333. =>WM: (13912: I2 ^reward 1)
  12334. =>WM: (13911: I2 ^see 0)
  12335. =>WM: (13910: N987 ^status complete)
  12336. <=WM: (13898: I2 ^dir U)
  12337. <=WM: (13897: I2 ^reward 1)
  12338. <=WM: (13896: I2 ^see 1)
  12339. =>WM: (13914: I2 ^level-1 R1-root)
  12340. <=WM: (13899: I2 ^level-1 R1-root)
  12341. --- END Input Phase ---
  12342. --- Proposal Phase ---
  12343. --- Inner Elaboration Phase, active level 1 (S1) ---
  12344. Firing rl*prefer*rvt*predict-yes*H0*3*v1*H1*37
  12345. -->
  12346. (S1 ^operator O1973 = -0.3011268063455669)
  12347. Firing rl*prefer*rvt*predict-no*H0*4*v1*H1*36
  12348. -->
  12349. (S1 ^operator O1974 = 0.7427523795546869)
  12350. Firing prefer*rvt*predict-no*H0*4*v1*H1
  12351. -->
  12352. Firing prefer*rvt*predict-yes*H0*3*v1*H1
  12353. -->
  12354. Firing elaborate*copy-see-to-output-link
  12355. -->
  12356. (I3 ^see 0 +)
  12357. Firing elaborate*reward*based*on*reward
  12358. -->
  12359. (R991 ^value 1 +)
  12360. (R1 ^reward R991 +)
  12361. Firing propose*predict-yes
  12362. -->
  12363. (O1975 ^name predict-yes +)
  12364. (S1 ^operator O1975 +)
  12365. Firing propose*predict-no
  12366. -->
  12367. (O1976 ^name predict-no +)
  12368. (S1 ^operator O1976 +)
  12369. Firing rl*prefer*rvt*predict-no*H0*4
  12370. -->
  12371. (S1 ^operator O1974 = 0.257246742345061)
  12372. Firing rl*prefer*rvt*predict-yes*H0*3
  12373. -->
  12374. (S1 ^operator O1973 = 0.7368283705992786)
  12375. Firing prefer*rvt*predict-yes*H0
  12376. -->
  12377. Firing prefer*rvt*predict-no*H0
  12378. -->
  12379. Firing elaborate*copy-dir-to-output-link
  12380. -->
  12381. (I3 ^dir R +)
  12382. inner elaboration loop at bottom goal.
  12383. Retracting elaborate*copy-see-to-output-link
  12384. -->
  12385. (I3 ^see 1 +)
  12386. Retracting propose*predict-no
  12387. -->
  12388. (O1974 ^name predict-no +)
  12389. (S1 ^operator O1974 +)
  12390. Retracting propose*predict-yes
  12391. -->
  12392. (O1973 ^name predict-yes +)
  12393. (S1 ^operator O1973 +)
  12394. Retracting elaborate*reward*based*on*reward
  12395. -->
  12396. (R990 ^value 1 +)
  12397. (R1 ^reward R990 +)
  12398. Retracting elaborate*copy-dir-to-output-link
  12399. -->
  12400. (I3 ^dir U +)
  12401. Retracting rl*prefer*rvt*predict-no*H0*2
  12402. -->
  12403. (S1 ^operator O1974 = 0.9999999999999999)
  12404. Retracting rl*prefer*rvt*predict-yes*H0*1
  12405. -->
  12406. (S1 ^operator O1973 = 0.)
  12407. =>WM: (13922: S1 ^operator O1976 +)
  12408. =>WM: (13921: S1 ^operator O1975 +)
  12409. =>WM: (13920: I3 ^dir R)
  12410. =>WM: (13919: O1976 ^name predict-no)
  12411. =>WM: (13918: O1975 ^name predict-yes)
  12412. =>WM: (13917: R991 ^value 1)
  12413. =>WM: (13916: R1 ^reward R991)
  12414. =>WM: (13915: I3 ^see 0)
  12415. <=WM: (13906: S1 ^operator O1973 +)
  12416. <=WM: (13907: S1 ^operator O1974 +)
  12417. <=WM: (13908: S1 ^operator O1974)
  12418. <=WM: (13905: I3 ^dir U)
  12419. <=WM: (13901: R1 ^reward R990)
  12420. <=WM: (13900: I3 ^see 1)
  12421. <=WM: (13904: O1974 ^name predict-no)
  12422. <=WM: (13903: O1973 ^name predict-yes)
  12423. <=WM: (13902: R990 ^value 1)
  12424. --- Inner Elaboration Phase, active level 1 (S1) ---
  12425. Firing prefer*rvt*predict-yes*H0
  12426. -->
  12427. Firing rl*prefer*rvt*predict-yes*H0*3*v1*H1*37
  12428. -->
  12429. (S1 ^operator O1975 = -0.3011268063455669)
  12430. Firing rl*prefer*rvt*predict-yes*H0*3
  12431. -->
  12432. (S1 ^operator O1975 = 0.7368283705992786)
  12433. Firing prefer*rvt*predict-yes*H0*3*v1*H1
  12434. -->
  12435. Firing prefer*rvt*predict-no*H0
  12436. -->
  12437. Firing rl*prefer*rvt*predict-no*H0*4*v1*H1*36
  12438. -->
  12439. (S1 ^operator O1976 = 0.7427523795546869)
  12440. Firing rl*prefer*rvt*predict-no*H0*4
  12441. -->
  12442. (S1 ^operator O1976 = 0.257246742345061)
  12443. Firing prefer*rvt*predict-no*H0*4*v1*H1
  12444. -->
  12445. inner elaboration loop at bottom goal.
  12446. Retracting rl*prefer*rvt*predict-no*H0*4
  12447. -->
  12448. (S1 ^operator O1974 = 0.257246742345061)
  12449. Retracting rl*prefer*rvt*predict-no*H0*4*v1*H1*36
  12450. -->
  12451. (S1 ^operator O1974 = 0.7427523795546869)
  12452. Retracting rl*prefer*rvt*predict-yes*H0*3
  12453. -->
  12454. (S1 ^operator O1973 = 0.7368283705992786)
  12455. Retracting rl*prefer*rvt*predict-yes*H0*3*v1*H1*37
  12456. -->
  12457. (S1 ^operator O1973 = -0.3011268063455669)
  12458. --- END Proposal Phase ---
  12459. --- Decision Phase ---
  12460. RL update rl*prefer*rvt*predict-no*H0*2 1 0 1 -> 1 0 1(R,m,v=1,1,0)
  12461. =>WM: (13923: S1 ^operator O1976)
  12462. 988: O: O1976 (predict-no)
  12463. --- END Decision Phase ---
  12464. --- Application Phase ---
  12465. --- Firing Productions (PE) For State At Depth 1 ---
  12466. --- Inner Elaboration Phase, active level 1 (S1) ---
  12467. Firing apply*operator
  12468. -->
  12469. (I3 ^predict-no N988 + :O )
  12470. Firing apply*operator*complete
  12471. -->
  12472. (I3 ^predict-no N987 - :O )
  12473. inner elaboration loop at bottom goal.
  12474. --- Change Working Memory (PE) ---
  12475. =>WM: (13924: I3 ^predict-no N988)
  12476. <=WM: (13910: N987 ^status complete)
  12477. <=WM: (13909: I3 ^predict-no N987)
  12478. --- Firing Productions (IE) For State At Depth 1 ---
  12479. --- Inner Elaboration Phase, active level 1 (S1) ---
  12480. Firing monitor*world
  12481. -->
  12482. I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
  12483. --- Change Working Memory (IE) ---
  12484. --- END Application Phase ---
  12485. --- Output Phase ---
  12486. ENV: Agent did: predict-no for direction R in state State-B
  12487. In State-B moving R
  12488. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  12489. predict error 0
  12490. dir: dir isR
  12491. --- END Output Phase ---
  12492. \-/--- Input Phase ---
  12493. =>WM: (13928: I2 ^dir R)
  12494. =>WM: (13927: I2 ^reward 1)
  12495. =>WM: (13926: I2 ^see 0)
  12496. =>WM: (13925: N988 ^status complete)
  12497. <=WM: (13913: I2 ^dir R)
  12498. <=WM: (13912: I2 ^reward 1)
  12499. <=WM: (13911: I2 ^see 0)
  12500. =>WM: (13929: I2 ^level-1 R0-root)
  12501. <=WM: (13914: I2 ^level-1 R1-root)
  12502. --- END Input Phase ---
  12503. --- Proposal Phase ---
  12504. --- Inner Elaboration Phase, active level 1 (S1) ---
  12505. Firing rl*prefer*rvt*predict-no*H0*4*v1*H1*41
  12506. -->
  12507. (S1 ^operator O1976 = 0.7427594337336832)
  12508. Firing rl*prefer*rvt*predict-yes*H0*3*v1*H1*42
  12509. -->
  12510. (S1 ^operator O1975 = -0.1989581826229297)
  12511. Firing prefer*rvt*predict-no*H0*4*v1*H1
  12512. -->
  12513. Firing prefer*rvt*predict-yes*H0*3*v1*H1
  12514. -->
  12515. Firing elaborate*copy-see-to-output-link
  12516. -->
  12517. (I3 ^see 0 +)
  12518. Firing elaborate*reward*based*on*reward
  12519. -->
  12520. (R992 ^value 1 +)
  12521. (R1 ^reward R992 +)
  12522. Firing propose*predict-yes
  12523. -->
  12524. (O1977 ^name predict-yes +)
  12525. (S1 ^operator O1977 +)
  12526. Firing propose*predict-no
  12527. -->
  12528. (O1978 ^name predict-no +)
  12529. (S1 ^operator O1978 +)
  12530. Firing rl*prefer*rvt*predict-no*H0*4
  12531. -->
  12532. (S1 ^operator O1976 = 0.257246742345061)
  12533. Firing rl*prefer*rvt*predict-yes*H0*3
  12534. -->
  12535. (S1 ^operator O1975 = 0.7368283705992786)
  12536. Firing prefer*rvt*predict-yes*H0
  12537. -->
  12538. Firing prefer*rvt*predict-no*H0
  12539. -->
  12540. Firing elaborate*copy-dir-to-output-link
  12541. -->
  12542. (I3 ^dir R +)
  12543. inner elaboration loop at bottom goal.
  12544. Retracting elaborate*copy-see-to-output-link
  12545. -->
  12546. (I3 ^see 0 +)
  12547. Retracting propose*predict-no
  12548. -->
  12549. (O1976 ^name predict-no +)
  12550. (S1 ^operator O1976 +)
  12551. Retracting propose*predict-yes
  12552. -->
  12553. (O1975 ^name predict-yes +)
  12554. (S1 ^operator O1975 +)
  12555. Retracting elaborate*reward*based*on*reward
  12556. -->
  12557. (R991 ^value 1 +)
  12558. (R1 ^reward R991 +)
  12559. Retracting elaborate*copy-dir-to-output-link
  12560. -->
  12561. (I3 ^dir R +)
  12562. Retracting rl*prefer*rvt*predict-no*H0*4
  12563. -->
  12564. (S1 ^operator O1976 = 0.257246742345061)
  12565. Retracting rl*prefer*rvt*predict-no*H0*4*v1*H1*36
  12566. -->
  12567. (S1 ^operator O1976 = 0.7427523795546869)
  12568. Retracting rl*prefer*rvt*predict-yes*H0*3
  12569. -->
  12570. (S1 ^operator O1975 = 0.7368283705992786)
  12571. Retracting rl*prefer*rvt*predict-yes*H0*3*v1*H1*37
  12572. -->
  12573. (S1 ^operator O1975 = -0.3011268063455669)
  12574. =>WM: (13935: S1 ^operator O1978 +)
  12575. =>WM: (13934: S1 ^operator O1977 +)
  12576. =>WM: (13933: O1978 ^name predict-no)
  12577. =>WM: (13932: O1977 ^name predict-yes)
  12578. =>WM: (13931: R992 ^value 1)
  12579. =>WM: (13930: R1 ^reward R992)
  12580. <=WM: (13921: S1 ^operator O1975 +)
  12581. <=WM: (13922: S1 ^operator O1976 +)
  12582. <=WM: (13923: S1 ^operator O1976)
  12583. <=WM: (13916: R1 ^reward R991)
  12584. <=WM: (13919: O1976 ^name predict-no)
  12585. <=WM: (13918: O1975 ^name predict-yes)
  12586. <=WM: (13917: R991 ^value 1)
  12587. --- Inner Elaboration Phase, active level 1 (S1) ---
  12588. Firing prefer*rvt*predict-yes*H0
  12589. -->
  12590. Firing rl*prefer*rvt*predict-yes*H0*3
  12591. -->
  12592. (S1 ^operator O1977 = 0.7368283705992786)
  12593. Firing prefer*rvt*predict-yes*H0*3*v1*H1
  12594. -->
  12595. Firing rl*prefer*rvt*predict-yes*H0*3*v1*H1*42
  12596. -->
  12597. (S1 ^operator O1977 = -0.1989581826229297)
  12598. Firing prefer*rvt*predict-no*H0
  12599. -->
  12600. Firing rl*prefer*rvt*predict-no*H0*4
  12601. -->
  12602. (S1 ^operator O1978 = 0.257246742345061)
  12603. Firing prefer*rvt*predict-no*H0*4*v1*H1
  12604. -->
  12605. Firing rl*prefer*rvt*predict-no*H0*4*v1*H1*41
  12606. -->
  12607. (S1 ^operator O1978 = 0.7427594337336832)
  12608. inner elaboration loop at bottom goal.
  12609. Retracting rl*prefer*rvt*predict-no*H0*4
  12610. -->
  12611. (S1 ^operator O1976 = 0.257246742345061)
  12612. Retracting rl*prefer*rvt*predict-no*H0*4*v1*H1*41
  12613. -->
  12614. (S1 ^operator O1976 = 0.7427594337336832)
  12615. Retracting rl*prefer*rvt*predict-yes*H0*3
  12616. -->
  12617. (S1 ^operator O1975 = 0.7368283705992786)
  12618. Retracting rl*prefer*rvt*predict-yes*H0*3*v1*H1*42
  12619. -->
  12620. (S1 ^operator O1975 = -0.1989581826229297)
  12621. --- END Proposal Phase ---
  12622. --- Decision Phase ---
  12623. RL update rl*prefer*rvt*predict-no*H0*4 0.586137 -0.32889 0.257247 -> 0.586137 -0.32889 0.257247(R,m,v=1,0.858824,0.121963)
  12624. RL update rl*prefer*rvt*predict-no*H0*4*v1*H1*36 0.413863 0.32889 0.742752 -> 0.413863 0.32889 0.742753(R,m,v=1,1,0)
  12625. =>WM: (13936: S1 ^operator O1978)
  12626. 989: O: O1978 (predict-no)
  12627. --- END Decision Phase ---
  12628. --- Application Phase ---
  12629. --- Firing Productions (PE) For State At Depth 1 ---
  12630. --- Inner Elaboration Phase, active level 1 (S1) ---
  12631. Firing apply*operator
  12632. -->
  12633. (I3 ^predict-no N989 + :O )
  12634. Firing apply*operator*complete
  12635. -->
  12636. (I3 ^predict-no N988 - :O )
  12637. inner elaboration loop at bottom goal.
  12638. --- Change Working Memory (PE) ---
  12639. =>WM: (13937: I3 ^predict-no N989)
  12640. <=WM: (13925: N988 ^status complete)
  12641. <=WM: (13924: I3 ^predict-no N988)
  12642. --- Firing Productions (IE) For State At Depth 1 ---
  12643. --- Inner Elaboration Phase, active level 1 (S1) ---
  12644. Firing monitor*world
  12645. -->
  12646. I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
  12647. --- Change Working Memory (IE) ---
  12648. --- END Application Phase ---
  12649. --- Output Phase ---
  12650. ENV: Agent did: predict-no for direction R in state State-B
  12651. In State-B moving R
  12652. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  12653. predict error 0
  12654. dir: dir isL
  12655. --- END Output Phase ---
  12656. |\---- Input Phase ---
  12657. =>WM: (13941: I2 ^dir L)
  12658. =>WM: (13940: I2 ^reward 1)
  12659. =>WM: (13939: I2 ^see 0)
  12660. =>WM: (13938: N989 ^status complete)
  12661. <=WM: (13928: I2 ^dir R)
  12662. <=WM: (13927: I2 ^reward 1)
  12663. <=WM: (13926: I2 ^see 0)
  12664. =>WM: (13942: I2 ^level-1 R0-root)
  12665. <=WM: (13929: I2 ^level-1 R0-root)
  12666. --- END Input Phase ---
  12667. --- Proposal Phase ---
  12668. --- Inner Elaboration Phase, active level 1 (S1) ---
  12669. Firing rl*prefer*rvt*predict-no*H0*6*v1*H1*38
  12670. -->
  12671. (S1 ^operator O1978 = 0.04178081990804111)
  12672. Firing rl*prefer*rvt*predict-yes*H0*5*v1*H1*30
  12673. -->
  12674. (S1 ^operator O1977 = 0.5681115950019797)
  12675. Firing prefer*rvt*predict-no*H0*6*v1*H1
  12676. -->
  12677. Firing prefer*rvt*predict-yes*H0*5*v1*H1
  12678. -->
  12679. Firing elaborate*copy-see-to-output-link
  12680. -->
  12681. (I3 ^see 0 +)
  12682. Firing elaborate*reward*based*on*reward
  12683. -->
  12684. (R993 ^value 1 +)
  12685. (R1 ^reward R993 +)
  12686. Firing propose*predict-yes
  12687. -->
  12688. (O1979 ^name predict-yes +)
  12689. (S1 ^operator O1979 +)
  12690. Firing propose*predict-no
  12691. -->
  12692. (O1980 ^name predict-no +)
  12693. (S1 ^operator O1980 +)
  12694. Firing rl*prefer*rvt*predict-no*H0*6
  12695. -->
  12696. (S1 ^operator O1978 = 0.3289463368854268)
  12697. Firing rl*prefer*rvt*predict-yes*H0*5
  12698. -->
  12699. (S1 ^operator O1977 = 0.4318900358645197)
  12700. Firing prefer*rvt*predict-yes*H0
  12701. -->
  12702. Firing prefer*rvt*predict-no*H0
  12703. -->
  12704. Firing elaborate*copy-dir-to-output-link
  12705. -->
  12706. (I3 ^dir L +)
  12707. inner elaboration loop at bottom goal.
  12708. Retracting elaborate*copy-see-to-output-link
  12709. -->
  12710. (I3 ^see 0 +)
  12711. Retracting propose*predict-no
  12712. -->
  12713. (O1978 ^name predict-no +)
  12714. (S1 ^operator O1978 +)
  12715. Retracting propose*predict-yes
  12716. -->
  12717. (O1977 ^name predict-yes +)
  12718. (S1 ^operator O1977 +)
  12719. Retracting elaborate*reward*based*on*reward
  12720. -->
  12721. (R992 ^value 1 +)
  12722. (R1 ^reward R992 +)
  12723. Retracting elaborate*copy-dir-to-output-link
  12724. -->
  12725. (I3 ^dir R +)
  12726. Retracting rl*prefer*rvt*predict-no*H0*4*v1*H1*41
  12727. -->
  12728. (S1 ^operator O1978 = 0.7427594337336832)
  12729. Retracting rl*prefer*rvt*predict-no*H0*4
  12730. -->
  12731. (S1 ^operator O1978 = 0.2572468740600988)
  12732. Retracting rl*prefer*rvt*predict-yes*H0*3*v1*H1*42
  12733. -->
  12734. (S1 ^operator O1977 = -0.1989581826229297)
  12735. Retracting rl*prefer*rvt*predict-yes*H0*3
  12736. -->
  12737. (S1 ^operator O1977 = 0.7368283705992786)
  12738. =>WM: (13949: S1 ^operator O1980 +)
  12739. =>WM: (13948: S1 ^operator O1979 +)
  12740. =>WM: (13947: I3 ^dir L)
  12741. =>WM: (13946: O1980 ^name predict-no)
  12742. =>WM: (13945: O1979 ^name predict-yes)
  12743. =>WM: (13944: R993 ^value 1)
  12744. =>WM: (13943: R1 ^reward R993)
  12745. <=WM: (13934: S1 ^operator O1977 +)
  12746. <=WM: (13935: S1 ^operator O1978 +)
  12747. <=WM: (13936: S1 ^operator O1978)
  12748. <=WM: (13920: I3 ^dir R)
  12749. <=WM: (13930: R1 ^reward R992)
  12750. <=WM: (13933: O1978 ^name predict-no)
  12751. <=WM: (13932: O1977 ^name predict-yes)
  12752. <=WM: (13931: R992 ^value 1)
  12753. --- Inner Elaboration Phase, active level 1 (S1) ---
  12754. Firing prefer*rvt*predict-yes*H0
  12755. -->
  12756. Firing rl*prefer*rvt*predict-yes*H0*5*v1*H1*30
  12757. -->
  12758. (S1 ^operator O1979 = 0.5681115950019797)
  12759. Firing rl*prefer*rvt*predict-yes*H0*5
  12760. -->
  12761. (S1 ^operator O1979 = 0.4318900358645197)
  12762. Firing prefer*rvt*predict-yes*H0*5*v1*H1
  12763. -->
  12764. Firing prefer*rvt*predict-no*H0
  12765. -->
  12766. Firing rl*prefer*rvt*predict-no*H0*6*v1*H1*38
  12767. -->
  12768. (S1 ^operator O1980 = 0.04178081990804111)
  12769. Firing rl*prefer*rvt*predict-no*H0*6
  12770. -->
  12771. (S1 ^operator O1980 = 0.3289463368854268)
  12772. Firing prefer*rvt*predict-no*H0*6*v1*H1
  12773. -->
  12774. inner elaboration loop at bottom goal.
  12775. Retracting rl*prefer*rvt*predict-no*H0*6
  12776. -->
  12777. (S1 ^operator O1978 = 0.3289463368854268)
  12778. Retracting rl*prefer*rvt*predict-no*H0*6*v1*H1*38
  12779. -->
  12780. (S1 ^operator O1978 = 0.04178081990804111)
  12781. Retracting rl*prefer*rvt*predict-yes*H0*5
  12782. -->
  12783. (S1 ^operator O1977 = 0.4318900358645197)
  12784. Retracting rl*prefer*rvt*predict-yes*H0*5*v1*H1*30
  12785. -->
  12786. (S1 ^operator O1977 = 0.5681115950019797)
  12787. --- END Proposal Phase ---
  12788. --- Decision Phase ---
  12789. RL update rl*prefer*rvt*predict-no*H0*4 0.586137 -0.32889 0.257247 -> 0.586136 -0.32889 0.257246(R,m,v=1,0.859649,0.121362)
  12790. RL update rl*prefer*rvt*predict-no*H0*4*v1*H1*41 0.413868 0.328891 0.742759 -> 0.413868 0.328891 0.742758(R,m,v=1,1,0)
  12791. =>WM: (13950: S1 ^operator O1979)
  12792. 990: O: O1979 (predict-yes)
  12793. --- END Decision Phase ---
  12794. --- Application Phase ---
  12795. --- Firing Productions (PE) For State At Depth 1 ---
  12796. --- Inner Elaboration Phase, active level 1 (S1) ---
  12797. Firing apply*operator
  12798. -->
  12799. (I3 ^predict-yes N990 + :O )
  12800. Firing apply*operator*complete
  12801. -->
  12802. (I3 ^predict-no N989 - :O )
  12803. inner elaboration loop at bottom goal.
  12804. --- Change Working Memory (PE) ---
  12805. =>WM: (13951: I3 ^predict-yes N990)
  12806. <=WM: (13938: N989 ^status complete)
  12807. <=WM: (13937: I3 ^predict-no N989)
  12808. --- Firing Productions (IE) For State At Depth 1 ---
  12809. --- Inner Elaboration Phase, active level 1 (S1) ---
  12810. Firing monitor*world
  12811. -->
  12812. I see 1 and I'm going to do: predict-yes inner elaboration loop at bottom goal.
  12813. --- Change Working Memory (IE) ---
  12814. --- END Application Phase ---
  12815. --- Output Phase ---
  12816. ENV: Agent did: predict-yes for direction L in state State-B
  12817. In State-B moving L
  12818. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  12819. predict error 0
  12820. dir: dir isU
  12821. --- END Output Phase ---
  12822. /|\--- Input Phase ---
  12823. =>WM: (13955: I2 ^dir U)
  12824. =>WM: (13954: I2 ^reward 1)
  12825. =>WM: (13953: I2 ^see 1)
  12826. =>WM: (13952: N990 ^status complete)
  12827. <=WM: (13941: I2 ^dir L)
  12828. <=WM: (13940: I2 ^reward 1)
  12829. <=WM: (13939: I2 ^see 0)
  12830. =>WM: (13956: I2 ^level-1 L1-root)
  12831. <=WM: (13942: I2 ^level-1 R0-root)
  12832. --- END Input Phase ---
  12833. --- Proposal Phase ---
  12834. --- Inner Elaboration Phase, active level 1 (S1) ---
  12835. Firing elaborate*copy-see-to-output-link
  12836. -->
  12837. (I3 ^see 1 +)
  12838. Firing elaborate*reward*based*on*reward
  12839. -->
  12840. (R994 ^value 1 +)
  12841. (R1 ^reward R994 +)
  12842. Firing propose*predict-yes
  12843. -->
  12844. (O1981 ^name predict-yes +)
  12845. (S1 ^operator O1981 +)
  12846. Firing propose*predict-no
  12847. -->
  12848. (O1982 ^name predict-no +)
  12849. (S1 ^operator O1982 +)
  12850. Firing rl*prefer*rvt*predict-no*H0*2
  12851. -->
  12852. (S1 ^operator O1980 = 0.9999999999999999)
  12853. Firing rl*prefer*rvt*predict-yes*H0*1
  12854. -->
  12855. (S1 ^operator O1979 = 0.)
  12856. Firing prefer*rvt*predict-yes*H0
  12857. -->
  12858. Firing prefer*rvt*predict-no*H0
  12859. -->
  12860. Firing elaborate*copy-dir-to-output-link
  12861. -->
  12862. (I3 ^dir U +)
  12863. inner elaboration loop at bottom goal.
  12864. Retracting elaborate*copy-see-to-output-link
  12865. -->
  12866. (I3 ^see 0 +)
  12867. Retracting propose*predict-no
  12868. -->
  12869. (O1980 ^name predict-no +)
  12870. (S1 ^operator O1980 +)
  12871. Retracting propose*predict-yes
  12872. -->
  12873. (O1979 ^name predict-yes +)
  12874. (S1 ^operator O1979 +)
  12875. Retracting elaborate*reward*based*on*reward
  12876. -->
  12877. (R993 ^value 1 +)
  12878. (R1 ^reward R993 +)
  12879. Retracting elaborate*copy-dir-to-output-link
  12880. -->
  12881. (I3 ^dir L +)
  12882. Retracting rl*prefer*rvt*predict-no*H0*6
  12883. -->
  12884. (S1 ^operator O1980 = 0.3289463368854268)
  12885. Retracting rl*prefer*rvt*predict-no*H0*6*v1*H1*38
  12886. -->
  12887. (S1 ^operator O1980 = 0.04178081990804111)
  12888. Retracting rl*prefer*rvt*predict-yes*H0*5
  12889. -->
  12890. (S1 ^operator O1979 = 0.4318900358645197)
  12891. Retracting rl*prefer*rvt*predict-yes*H0*5*v1*H1*30
  12892. -->
  12893. (S1 ^operator O1979 = 0.5681115950019797)
  12894. =>WM: (13964: S1 ^operator O1982 +)
  12895. =>WM: (13963: S1 ^operator O1981 +)
  12896. =>WM: (13962: I3 ^dir U)
  12897. =>WM: (13961: O1982 ^name predict-no)
  12898. =>WM: (13960: O1981 ^name predict-yes)
  12899. =>WM: (13959: R994 ^value 1)
  12900. =>WM: (13958: R1 ^reward R994)
  12901. =>WM: (13957: I3 ^see 1)
  12902. <=WM: (13948: S1 ^operator O1979 +)
  12903. <=WM: (13950: S1 ^operator O1979)
  12904. <=WM: (13949: S1 ^operator O1980 +)
  12905. <=WM: (13947: I3 ^dir L)
  12906. <=WM: (13943: R1 ^reward R993)
  12907. <=WM: (13915: I3 ^see 0)
  12908. <=WM: (13946: O1980 ^name predict-no)
  12909. <=WM: (13945: O1979 ^name predict-yes)
  12910. <=WM: (13944: R993 ^value 1)
  12911. --- Inner Elaboration Phase, active level 1 (S1) ---
  12912. Firing prefer*rvt*predict-yes*H0
  12913. -->
  12914. Firing rl*prefer*rvt*predict-yes*H0*1
  12915. -->
  12916. (S1 ^operator O1981 = 0.)
  12917. Firing prefer*rvt*predict-no*H0
  12918. -->
  12919. Firing rl*prefer*rvt*predict-no*H0*2
  12920. -->
  12921. (S1 ^operator O1982 = 0.9999999999999999)
  12922. inner elaboration loop at bottom goal.
  12923. Retracting rl*prefer*rvt*predict-no*H0*2
  12924. -->
  12925. (S1 ^operator O1980 = 0.9999999999999999)
  12926. Retracting rl*prefer*rvt*predict-yes*H0*1
  12927. -->
  12928. (S1 ^operator O1979 = 0.)
  12929. --- END Proposal Phase ---
  12930. --- Decision Phase ---
  12931. RL update rl*prefer*rvt*predict-yes*H0*5 0.683776 -0.251886 0.43189 -> 0.683776 -0.251886 0.43189(R,m,v=1,0.922619,0.0718206)
  12932. RL update rl*prefer*rvt*predict-yes*H0*5*v1*H1*30 0.316225 0.251886 0.568112 -> 0.316225 0.251886 0.568111(R,m,v=1,1,0)
  12933. =>WM: (13965: S1 ^operator O1982)
  12934. 991: O: O1982 (predict-no)
  12935. --- END Decision Phase ---
  12936. --- Application Phase ---
  12937. --- Firing Productions (PE) For State At Depth 1 ---
  12938. --- Inner Elaboration Phase, active level 1 (S1) ---
  12939. Firing apply*operator
  12940. -->
  12941. (I3 ^predict-no N991 + :O )
  12942. Firing apply*operator*complete
  12943. -->
  12944. (I3 ^predict-yes N990 - :O )
  12945. inner elaboration loop at bottom goal.
  12946. --- Change Working Memory (PE) ---
  12947. =>WM: (13966: I3 ^predict-no N991)
  12948. <=WM: (13952: N990 ^status complete)
  12949. <=WM: (13951: I3 ^predict-yes N990)
  12950. --- Firing Productions (IE) For State At Depth 1 ---
  12951. --- Inner Elaboration Phase, active level 1 (S1) ---
  12952. Firing monitor*world
  12953. -->
  12954. I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
  12955. --- Change Working Memory (IE) ---
  12956. --- END Application Phase ---
  12957. --- Output Phase ---
  12958. ENV: Agent did: predict-no for direction U in state State-A
  12959. In State-A moving U
  12960. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  12961. predict error 0
  12962. dir: dir isR
  12963. --- END Output Phase ---
  12964. ---- Input Phase ---
  12965. =>WM: (13970: I2 ^dir R)
  12966. =>WM: (13969: I2 ^reward 1)
  12967. =>WM: (13968: I2 ^see 0)
  12968. =>WM: (13967: N991 ^status complete)
  12969. <=WM: (13955: I2 ^dir U)
  12970. <=WM: (13954: I2 ^reward 1)
  12971. <=WM: (13953: I2 ^see 1)
  12972. =>WM: (13971: I2 ^level-1 L1-root)
  12973. <=WM: (13956: I2 ^level-1 L1-root)
  12974. --- END Input Phase ---
  12975. --- Proposal Phase ---
  12976. --- Inner Elaboration Phase, active level 1 (S1) ---
  12977. Firing rl*prefer*rvt*predict-no*H0*4*v1*H1*39
  12978. -->
  12979. (S1 ^operator O1982 = -0.1377248055371832)
  12980. Firing rl*prefer*rvt*predict-yes*H0*3*v1*H1*40
  12981. -->
  12982. (S1 ^operator O1981 = 0.2631685608814066)
  12983. Firing prefer*rvt*predict-no*H0*4*v1*H1
  12984. -->
  12985. Firing prefer*rvt*predict-yes*H0*3*v1*H1
  12986. -->
  12987. Firing elaborate*copy-see-to-output-link
  12988. -->
  12989. (I3 ^see 0 +)
  12990. Firing elaborate*reward*based*on*reward
  12991. -->
  12992. (R995 ^value 1 +)
  12993. (R1 ^reward R995 +)
  12994. Firing propose*predict-yes
  12995. -->
  12996. (O1983 ^name predict-yes +)
  12997. (S1 ^operator O1983 +)
  12998. Firing propose*predict-no
  12999. -->
  13000. (O1984 ^name predict-no +)
  13001. (S1 ^operator O1984 +)
  13002. Firing rl*prefer*rvt*predict-no*H0*4
  13003. -->
  13004. (S1 ^operator O1982 = 0.2572459278910315)
  13005. Firing rl*prefer*rvt*predict-yes*H0*3
  13006. -->
  13007. (S1 ^operator O1981 = 0.7368283705992786)
  13008. Firing prefer*rvt*predict-yes*H0
  13009. -->
  13010. Firing prefer*rvt*predict-no*H0
  13011. -->
  13012. Firing elaborate*copy-dir-to-output-link
  13013. -->
  13014. (I3 ^dir R +)
  13015. inner elaboration loop at bottom goal.
  13016. Retracting elaborate*copy-see-to-output-link
  13017. -->
  13018. (I3 ^see 1 +)
  13019. Retracting propose*predict-no
  13020. -->
  13021. (O1982 ^name predict-no +)
  13022. (S1 ^operator O1982 +)
  13023. Retracting propose*predict-yes
  13024. -->
  13025. (O1981 ^name predict-yes +)
  13026. (S1 ^operator O1981 +)
  13027. Retracting elaborate*reward*based*on*reward
  13028. -->
  13029. (R994 ^value 1 +)
  13030. (R1 ^reward R994 +)
  13031. Retracting elaborate*copy-dir-to-output-link
  13032. -->
  13033. (I3 ^dir U +)
  13034. Retracting rl*prefer*rvt*predict-no*H0*2
  13035. -->
  13036. (S1 ^operator O1982 = 0.9999999999999999)
  13037. Retracting rl*prefer*rvt*predict-yes*H0*1
  13038. -->
  13039. (S1 ^operator O1981 = 0.)
  13040. =>WM: (13979: S1 ^operator O1984 +)
  13041. =>WM: (13978: S1 ^operator O1983 +)
  13042. =>WM: (13977: I3 ^dir R)
  13043. =>WM: (13976: O1984 ^name predict-no)
  13044. =>WM: (13975: O1983 ^name predict-yes)
  13045. =>WM: (13974: R995 ^value 1)
  13046. =>WM: (13973: R1 ^reward R995)
  13047. =>WM: (13972: I3 ^see 0)
  13048. <=WM: (13963: S1 ^operator O1981 +)
  13049. <=WM: (13964: S1 ^operator O1982 +)
  13050. <=WM: (13965: S1 ^operator O1982)
  13051. <=WM: (13962: I3 ^dir U)
  13052. <=WM: (13958: R1 ^reward R994)
  13053. <=WM: (13957: I3 ^see 1)
  13054. <=WM: (13961: O1982 ^name predict-no)
  13055. <=WM: (13960: O1981 ^name predict-yes)
  13056. <=WM: (13959: R994 ^value 1)
  13057. --- Inner Elaboration Phase, active level 1 (S1) ---
  13058. Firing prefer*rvt*predict-yes*H0
  13059. -->
  13060. Firing rl*prefer*rvt*predict-yes*H0*3*v1*H1*40
  13061. -->
  13062. (S1 ^operator O1983 = 0.2631685608814066)
  13063. Firing rl*prefer*rvt*predict-yes*H0*3
  13064. -->
  13065. (S1 ^operator O1983 = 0.7368283705992786)
  13066. Firing prefer*rvt*predict-yes*H0*3*v1*H1
  13067. -->
  13068. Firing prefer*rvt*predict-no*H0
  13069. -->
  13070. Firing rl*prefer*rvt*predict-no*H0*4*v1*H1*39
  13071. -->
  13072. (S1 ^operator O1984 = -0.1377248055371832)
  13073. Firing rl*prefer*rvt*predict-no*H0*4
  13074. -->
  13075. (S1 ^operator O1984 = 0.2572459278910315)
  13076. Firing prefer*rvt*predict-no*H0*4*v1*H1
  13077. -->
  13078. inner elaboration loop at bottom goal.
  13079. Retracting rl*prefer*rvt*predict-no*H0*4
  13080. -->
  13081. (S1 ^operator O1982 = 0.2572459278910315)
  13082. Retracting rl*prefer*rvt*predict-no*H0*4*v1*H1*39
  13083. -->
  13084. (S1 ^operator O1982 = -0.1377248055371832)
  13085. Retracting rl*prefer*rvt*predict-yes*H0*3
  13086. -->
  13087. (S1 ^operator O1981 = 0.7368283705992786)
  13088. Retracting rl*prefer*rvt*predict-yes*H0*3*v1*H1*40
  13089. -->
  13090. (S1 ^operator O1981 = 0.2631685608814066)
  13091. --- END Proposal Phase ---
  13092. --- Decision Phase ---
  13093. RL update rl*prefer*rvt*predict-no*H0*2 1 0 1 -> 1 0 1(R,m,v=1,1,0)
  13094. =>WM: (13980: S1 ^operator O1983)
  13095. 992: O: O1983 (predict-yes)
  13096. --- END Decision Phase ---
  13097. --- Application Phase ---
  13098. --- Firing Productions (PE) For State At Depth 1 ---
  13099. --- Inner Elaboration Phase, active level 1 (S1) ---
  13100. Firing apply*operator
  13101. -->
  13102. (I3 ^predict-yes N992 + :O )
  13103. Firing apply*operator*complete
  13104. -->
  13105. (I3 ^predict-no N991 - :O )
  13106. inner elaboration loop at bottom goal.
  13107. --- Change Working Memory (PE) ---
  13108. =>WM: (13981: I3 ^predict-yes N992)
  13109. <=WM: (13967: N991 ^status complete)
  13110. <=WM: (13966: I3 ^predict-no N991)
  13111. --- Firing Productions (IE) For State At Depth 1 ---
  13112. --- Inner Elaboration Phase, active level 1 (S1) ---
  13113. Firing monitor*world
  13114. -->
  13115. I see 1 and I'm going to do: predict-yes inner elaboration loop at bottom goal.
  13116. --- Change Working Memory (IE) ---
  13117. --- END Application Phase ---
  13118. --- Output Phase ---
  13119. ENV: Agent did: predict-yes for direction R in state State-A
  13120. In State-A moving R
  13121. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  13122. predict error 0
  13123. dir: dir isU
  13124. --- END Output Phase ---
  13125. /|\--- Input Phase ---
  13126. =>WM: (13985: I2 ^dir U)
  13127. =>WM: (13984: I2 ^reward 1)
  13128. =>WM: (13983: I2 ^see 1)
  13129. =>WM: (13982: N992 ^status complete)
  13130. <=WM: (13970: I2 ^dir R)
  13131. <=WM: (13969: I2 ^reward 1)
  13132. <=WM: (13968: I2 ^see 0)
  13133. =>WM: (13986: I2 ^level-1 R1-root)
  13134. <=WM: (13971: I2 ^level-1 L1-root)
  13135. --- END Input Phase ---
  13136. --- Proposal Phase ---
  13137. --- Inner Elaboration Phase, active level 1 (S1) ---
  13138. Firing elaborate*copy-see-to-output-link
  13139. -->
  13140. (I3 ^see 1 +)
  13141. Firing elaborate*reward*based*on*reward
  13142. -->
  13143. (R996 ^value 1 +)
  13144. (R1 ^reward R996 +)
  13145. Firing propose*predict-yes
  13146. -->
  13147. (O1985 ^name predict-yes +)
  13148. (S1 ^operator O1985 +)
  13149. Firing propose*predict-no
  13150. -->
  13151. (O1986 ^name predict-no +)
  13152. (S1 ^operator O1986 +)
  13153. Firing rl*prefer*rvt*predict-no*H0*2
  13154. -->
  13155. (S1 ^operator O1984 = 0.9999999999999999)
  13156. Firing rl*prefer*rvt*predict-yes*H0*1
  13157. -->
  13158. (S1 ^operator O1983 = 0.)
  13159. Firing prefer*rvt*predict-yes*H0
  13160. -->
  13161. Firing prefer*rvt*predict-no*H0
  13162. -->
  13163. Firing elaborate*copy-dir-to-output-link
  13164. -->
  13165. (I3 ^dir U +)
  13166. inner elaboration loop at bottom goal.
  13167. Retracting elaborate*copy-see-to-output-link
  13168. -->
  13169. (I3 ^see 0 +)
  13170. Retracting propose*predict-no
  13171. -->
  13172. (O1984 ^name predict-no +)
  13173. (S1 ^operator O1984 +)
  13174. Retracting propose*predict-yes
  13175. -->
  13176. (O1983 ^name predict-yes +)
  13177. (S1 ^operator O1983 +)
  13178. Retracting elaborate*reward*based*on*reward
  13179. -->
  13180. (R995 ^value 1 +)
  13181. (R1 ^reward R995 +)
  13182. Retracting elaborate*copy-dir-to-output-link
  13183. -->
  13184. (I3 ^dir R +)
  13185. Retracting rl*prefer*rvt*predict-no*H0*4
  13186. -->
  13187. (S1 ^operator O1984 = 0.2572459278910315)
  13188. Retracting rl*prefer*rvt*predict-no*H0*4*v1*H1*39
  13189. -->
  13190. (S1 ^operator O1984 = -0.1377248055371832)
  13191. Retracting rl*prefer*rvt*predict-yes*H0*3
  13192. -->
  13193. (S1 ^operator O1983 = 0.7368283705992786)
  13194. Retracting rl*prefer*rvt*predict-yes*H0*3*v1*H1*40
  13195. -->
  13196. (S1 ^operator O1983 = 0.2631685608814066)
  13197. =>WM: (13994: S1 ^operator O1986 +)
  13198. =>WM: (13993: S1 ^operator O1985 +)
  13199. =>WM: (13992: I3 ^dir U)
  13200. =>WM: (13991: O1986 ^name predict-no)
  13201. =>WM: (13990: O1985 ^name predict-yes)
  13202. =>WM: (13989: R996 ^value 1)
  13203. =>WM: (13988: R1 ^reward R996)
  13204. =>WM: (13987: I3 ^see 1)
  13205. <=WM: (13978: S1 ^operator O1983 +)
  13206. <=WM: (13980: S1 ^operator O1983)
  13207. <=WM: (13979: S1 ^operator O1984 +)
  13208. <=WM: (13977: I3 ^dir R)
  13209. <=WM: (13973: R1 ^reward R995)
  13210. <=WM: (13972: I3 ^see 0)
  13211. <=WM: (13976: O1984 ^name predict-no)
  13212. <=WM: (13975: O1983 ^name predict-yes)
  13213. <=WM: (13974: R995 ^value 1)
  13214. --- Inner Elaboration Phase, active level 1 (S1) ---
  13215. Firing prefer*rvt*predict-yes*H0
  13216. -->
  13217. Firing rl*prefer*rvt*predict-yes*H0*1
  13218. -->
  13219. (S1 ^operator O1985 = 0.)
  13220. Firing prefer*rvt*predict-no*H0
  13221. -->
  13222. Firing rl*prefer*rvt*predict-no*H0*2
  13223. -->
  13224. (S1 ^operator O1986 = 0.9999999999999999)
  13225. inner elaboration loop at bottom goal.
  13226. Retracting rl*prefer*rvt*predict-no*H0*2
  13227. -->
  13228. (S1 ^operator O1984 = 0.9999999999999999)
  13229. Retracting rl*prefer*rvt*predict-yes*H0*1
  13230. -->
  13231. (S1 ^operator O1983 = 0.)
  13232. --- END Proposal Phase ---
  13233. --- Decision Phase ---
  13234. RL update rl*prefer*rvt*predict-yes*H0*3 0.748236 -0.0114078 0.736828 -> 0.748236 -0.0114074 0.736829(R,m,v=1,0.896341,0.0934835)
  13235. RL update rl*prefer*rvt*predict-yes*H0*3*v1*H1*40 0.251763 0.0114055 0.263169 -> 0.251763 0.0114059 0.263169(R,m,v=1,1,0)
  13236. =>WM: (13995: S1 ^operator O1986)
  13237. 993: O: O1986 (predict-no)
  13238. --- END Decision Phase ---
  13239. --- Application Phase ---
  13240. --- Firing Productions (PE) For State At Depth 1 ---
  13241. --- Inner Elaboration Phase, active level 1 (S1) ---
  13242. Firing apply*operator
  13243. -->
  13244. (I3 ^predict-no N993 + :O )
  13245. Firing apply*operator*complete
  13246. -->
  13247. (I3 ^predict-yes N992 - :O )
  13248. inner elaboration loop at bottom goal.
  13249. --- Change Working Memory (PE) ---
  13250. =>WM: (13996: I3 ^predict-no N993)
  13251. <=WM: (13982: N992 ^status complete)
  13252. <=WM: (13981: I3 ^predict-yes N992)
  13253. --- Firing Productions (IE) For State At Depth 1 ---
  13254. --- Inner Elaboration Phase, active level 1 (S1) ---
  13255. Firing monitor*world
  13256. -->
  13257. I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
  13258. --- Change Working Memory (IE) ---
  13259. --- END Application Phase ---
  13260. --- Output Phase ---
  13261. ENV: Agent did: predict-no for direction U in state State-B
  13262. In State-B moving U
  13263. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  13264. predict error 0
  13265. dir: dir isL
  13266. --- END Output Phase ---
  13267. -/--- Input Phase ---
  13268. =>WM: (14000: I2 ^dir L)
  13269. =>WM: (13999: I2 ^reward 1)
  13270. =>WM: (13998: I2 ^see 0)
  13271. =>WM: (13997: N993 ^status complete)
  13272. <=WM: (13985: I2 ^dir U)
  13273. <=WM: (13984: I2 ^reward 1)
  13274. <=WM: (13983: I2 ^see 1)
  13275. =>WM: (14001: I2 ^level-1 R1-root)
  13276. <=WM: (13986: I2 ^level-1 R1-root)
  13277. --- END Input Phase ---
  13278. --- Proposal Phase ---
  13279. --- Inner Elaboration Phase, active level 1 (S1) ---
  13280. Firing rl*prefer*rvt*predict-yes*H0*5*v1*H1*45
  13281. -->
  13282. (S1 ^operator O1985 = 0.5681057054973254)
  13283. Firing rl*prefer*rvt*predict-no*H0*6*v1*H1*44
  13284. -->
  13285. (S1 ^operator O1986 = -0.1549421060161498)
  13286. Firing prefer*rvt*predict-no*H0*6*v1*H1
  13287. -->
  13288. Firing prefer*rvt*predict-yes*H0*5*v1*H1
  13289. -->
  13290. Firing elaborate*copy-see-to-output-link
  13291. -->
  13292. (I3 ^see 0 +)
  13293. Firing elaborate*reward*based*on*reward
  13294. -->
  13295. (R997 ^value 1 +)
  13296. (R1 ^reward R997 +)
  13297. Firing propose*predict-yes
  13298. -->
  13299. (O1987 ^name predict-yes +)
  13300. (S1 ^operator O1987 +)
  13301. Firing propose*predict-no
  13302. -->
  13303. (O1988 ^name predict-no +)
  13304. (S1 ^operator O1988 +)
  13305. Firing rl*prefer*rvt*predict-no*H0*6
  13306. -->
  13307. (S1 ^operator O1986 = 0.3289463368854268)
  13308. Firing rl*prefer*rvt*predict-yes*H0*5
  13309. -->
  13310. (S1 ^operator O1985 = 0.4318897912345449)
  13311. Firing prefer*rvt*predict-yes*H0
  13312. -->
  13313. Firing prefer*rvt*predict-no*H0
  13314. -->
  13315. Firing elaborate*copy-dir-to-output-link
  13316. -->
  13317. (I3 ^dir L +)
  13318. inner elaboration loop at bottom goal.
  13319. Retracting elaborate*copy-see-to-output-link
  13320. -->
  13321. (I3 ^see 1 +)
  13322. Retracting propose*predict-no
  13323. -->
  13324. (O1986 ^name predict-no +)
  13325. (S1 ^operator O1986 +)
  13326. Retracting propose*predict-yes
  13327. -->
  13328. (O1985 ^name predict-yes +)
  13329. (S1 ^operator O1985 +)
  13330. Retracting elaborate*reward*based*on*reward
  13331. -->
  13332. (R996 ^value 1 +)
  13333. (R1 ^reward R996 +)
  13334. Retracting elaborate*copy-dir-to-output-link
  13335. -->
  13336. (I3 ^dir U +)
  13337. Retracting rl*prefer*rvt*predict-no*H0*2
  13338. -->
  13339. (S1 ^operator O1986 = 0.9999999999999999)
  13340. Retracting rl*prefer*rvt*predict-yes*H0*1
  13341. -->
  13342. (S1 ^operator O1985 = 0.)
  13343. =>WM: (14009: S1 ^operator O1988 +)
  13344. =>WM: (14008: S1 ^operator O1987 +)
  13345. =>WM: (14007: I3 ^dir L)
  13346. =>WM: (14006: O1988 ^name predict-no)
  13347. =>WM: (14005: O1987 ^name predict-yes)
  13348. =>WM: (14004: R997 ^value 1)
  13349. =>WM: (14003: R1 ^reward R997)
  13350. =>WM: (14002: I3 ^see 0)
  13351. <=WM: (13993: S1 ^operator O1985 +)
  13352. <=WM: (13994: S1 ^operator O1986 +)
  13353. <=WM: (13995: S1 ^operator O1986)
  13354. <=WM: (13992: I3 ^dir U)
  13355. <=WM: (13988: R1 ^reward R996)
  13356. <=WM: (13987: I3 ^see 1)
  13357. <=WM: (13991: O1986 ^name predict-no)
  13358. <=WM: (13990: O1985 ^name predict-yes)
  13359. <=WM: (13989: R996 ^value 1)
  13360. --- Inner Elaboration Phase, active level 1 (S1) ---
  13361. Firing prefer*rvt*predict-yes*H0
  13362. -->
  13363. Firing rl*prefer*rvt*predict-yes*H0*5*v1*H1*45
  13364. -->
  13365. (S1 ^operator O1987 = 0.5681057054973254)
  13366. Firing rl*prefer*rvt*predict-yes*H0*5
  13367. -->
  13368. (S1 ^operator O1987 = 0.4318897912345449)
  13369. Firing prefer*rvt*predict-yes*H0*5*v1*H1
  13370. -->
  13371. Firing prefer*rvt*predict-no*H0
  13372. -->
  13373. Firing rl*prefer*rvt*predict-no*H0*6*v1*H1*44
  13374. -->
  13375. (S1 ^operator O1988 = -0.1549421060161498)
  13376. Firing rl*prefer*rvt*predict-no*H0*6
  13377. -->
  13378. (S1 ^operator O1988 = 0.3289463368854268)
  13379. Firing prefer*rvt*predict-no*H0*6*v1*H1
  13380. -->
  13381. inner elaboration loop at bottom goal.
  13382. Retracting rl*prefer*rvt*predict-no*H0*6
  13383. -->
  13384. (S1 ^operator O1986 = 0.3289463368854268)
  13385. Retracting rl*prefer*rvt*predict-no*H0*6*v1*H1*44
  13386. -->
  13387. (S1 ^operator O1986 = -0.1549421060161498)
  13388. Retracting rl*prefer*rvt*predict-yes*H0*5
  13389. -->
  13390. (S1 ^operator O1985 = 0.4318897912345449)
  13391. Retracting rl*prefer*rvt*predict-yes*H0*5*v1*H1*45
  13392. -->
  13393. (S1 ^operator O1985 = 0.5681057054973254)
  13394. --- END Proposal Phase ---
  13395. --- Decision Phase ---
  13396. RL update rl*prefer*rvt*predict-no*H0*2 1 0 1 -> 1 0 1(R,m,v=1,1,0)
  13397. =>WM: (14010: S1 ^operator O1987)
  13398. 994: O: O1987 (predict-yes)
  13399. --- END Decision Phase ---
  13400. --- Application Phase ---
  13401. --- Firing Productions (PE) For State At Depth 1 ---
  13402. --- Inner Elaboration Phase, active level 1 (S1) ---
  13403. Firing apply*operator
  13404. -->
  13405. (I3 ^predict-yes N994 + :O )
  13406. Firing apply*operator*complete
  13407. -->
  13408. (I3 ^predict-no N993 - :O )
  13409. inner elaboration loop at bottom goal.
  13410. --- Change Working Memory (PE) ---
  13411. =>WM: (14011: I3 ^predict-yes N994)
  13412. <=WM: (13997: N993 ^status complete)
  13413. <=WM: (13996: I3 ^predict-no N993)
  13414. --- Firing Productions (IE) For State At Depth 1 ---
  13415. --- Inner Elaboration Phase, active level 1 (S1) ---
  13416. Firing monitor*world
  13417. -->
  13418. I see 1 and I'm going to do: predict-yes inner elaboration loop at bottom goal.
  13419. --- Change Working Memory (IE) ---
  13420. --- END Application Phase ---
  13421. --- Output Phase ---
  13422. ENV: Agent did: predict-yes for direction L in state State-B
  13423. In State-B moving L
  13424. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  13425. predict error 0
  13426. dir: dir isL
  13427. --- END Output Phase ---
  13428. |\---- Input Phase ---
  13429. =>WM: (14015: I2 ^dir L)
  13430. =>WM: (14014: I2 ^reward 1)
  13431. =>WM: (14013: I2 ^see 1)
  13432. =>WM: (14012: N994 ^status complete)
  13433. <=WM: (14000: I2 ^dir L)
  13434. <=WM: (13999: I2 ^reward 1)
  13435. <=WM: (13998: I2 ^see 0)
  13436. =>WM: (14016: I2 ^level-1 L1-root)
  13437. <=WM: (14001: I2 ^level-1 R1-root)
  13438. --- END Input Phase ---
  13439. --- Proposal Phase ---
  13440. --- Inner Elaboration Phase, active level 1 (S1) ---
  13441. Firing rl*prefer*rvt*predict-no*H0*6*v1*H1*43
  13442. -->
  13443. (S1 ^operator O1988 = 0.6710523655015633)
  13444. Firing rl*prefer*rvt*predict-yes*H0*5*v1*H1*31
  13445. -->
  13446. (S1 ^operator O1987 = -0.06092862110810815)
  13447. Firing prefer*rvt*predict-no*H0*6*v1*H1
  13448. -->
  13449. Firing prefer*rvt*predict-yes*H0*5*v1*H1
  13450. -->
  13451. Firing elaborate*copy-see-to-output-link
  13452. -->
  13453. (I3 ^see 1 +)
  13454. Firing elaborate*reward*based*on*reward
  13455. -->
  13456. (R998 ^value 1 +)
  13457. (R1 ^reward R998 +)
  13458. Firing propose*predict-yes
  13459. -->
  13460. (O1989 ^name predict-yes +)
  13461. (S1 ^operator O1989 +)
  13462. Firing propose*predict-no
  13463. -->
  13464. (O1990 ^name predict-no +)
  13465. (S1 ^operator O1990 +)
  13466. Firing rl*prefer*rvt*predict-no*H0*6
  13467. -->
  13468. (S1 ^operator O1988 = 0.3289463368854268)
  13469. Firing rl*prefer*rvt*predict-yes*H0*5
  13470. -->
  13471. (S1 ^operator O1987 = 0.4318897912345449)
  13472. Firing prefer*rvt*predict-yes*H0
  13473. -->
  13474. Firing prefer*rvt*predict-no*H0
  13475. -->
  13476. Firing elaborate*copy-dir-to-output-link
  13477. -->
  13478. (I3 ^dir L +)
  13479. inner elaboration loop at bottom goal.
  13480. Retracting elaborate*copy-see-to-output-link
  13481. -->
  13482. (I3 ^see 0 +)
  13483. Retracting propose*predict-no
  13484. -->
  13485. (O1988 ^name predict-no +)
  13486. (S1 ^operator O1988 +)
  13487. Retracting propose*predict-yes
  13488. -->
  13489. (O1987 ^name predict-yes +)
  13490. (S1 ^operator O1987 +)
  13491. Retracting elaborate*reward*based*on*reward
  13492. -->
  13493. (R997 ^value 1 +)
  13494. (R1 ^reward R997 +)
  13495. Retracting elaborate*copy-dir-to-output-link
  13496. -->
  13497. (I3 ^dir L +)
  13498. Retracting rl*prefer*rvt*predict-no*H0*6
  13499. -->
  13500. (S1 ^operator O1988 = 0.3289463368854268)
  13501. Retracting rl*prefer*rvt*predict-no*H0*6*v1*H1*44
  13502. -->
  13503. (S1 ^operator O1988 = -0.1549421060161498)
  13504. Retracting rl*prefer*rvt*predict-yes*H0*5
  13505. -->
  13506. (S1 ^operator O1987 = 0.4318897912345449)
  13507. Retracting rl*prefer*rvt*predict-yes*H0*5*v1*H1*45
  13508. -->
  13509. (S1 ^operator O1987 = 0.5681057054973254)
  13510. =>WM: (14023: S1 ^operator O1990 +)
  13511. =>WM: (14022: S1 ^operator O1989 +)
  13512. =>WM: (14021: O1990 ^name predict-no)
  13513. =>WM: (14020: O1989 ^name predict-yes)
  13514. =>WM: (14019: R998 ^value 1)
  13515. =>WM: (14018: R1 ^reward R998)
  13516. =>WM: (14017: I3 ^see 1)
  13517. <=WM: (14008: S1 ^operator O1987 +)
  13518. <=WM: (14010: S1 ^operator O1987)
  13519. <=WM: (14009: S1 ^operator O1988 +)
  13520. <=WM: (14003: R1 ^reward R997)
  13521. <=WM: (14002: I3 ^see 0)
  13522. <=WM: (14006: O1988 ^name predict-no)
  13523. <=WM: (14005: O1987 ^name predict-yes)
  13524. <=WM: (14004: R997 ^value 1)
  13525. --- Inner Elaboration Phase, active level 1 (S1) ---
  13526. Firing prefer*rvt*predict-yes*H0
  13527. -->
  13528. Firing rl*prefer*rvt*predict-yes*H0*5
  13529. -->
  13530. (S1 ^operator O1989 = 0.4318897912345449)
  13531. Firing prefer*rvt*predict-yes*H0*5*v1*H1
  13532. -->
  13533. Firing rl*prefer*rvt*predict-yes*H0*5*v1*H1*31
  13534. -->
  13535. (S1 ^operator O1989 = -0.06092862110810815)
  13536. Firing prefer*rvt*predict-no*H0
  13537. -->
  13538. Firing rl*prefer*rvt*predict-no*H0*6
  13539. -->
  13540. (S1 ^operator O1990 = 0.3289463368854268)
  13541. Firing prefer*rvt*predict-no*H0*6*v1*H1
  13542. -->
  13543. Firing rl*prefer*rvt*predict-no*H0*6*v1*H1*43
  13544. -->
  13545. (S1 ^operator O1990 = 0.6710523655015633)
  13546. inner elaboration loop at bottom goal.
  13547. Retracting rl*prefer*rvt*predict-no*H0*6
  13548. -->
  13549. (S1 ^operator O1988 = 0.3289463368854268)
  13550. Retracting rl*prefer*rvt*predict-no*H0*6*v1*H1*43
  13551. -->
  13552. (S1 ^operator O1988 = 0.6710523655015633)
  13553. Retracting rl*prefer*rvt*predict-yes*H0*5
  13554. -->
  13555. (S1 ^operator O1987 = 0.4318897912345449)
  13556. Retracting rl*prefer*rvt*predict-yes*H0*5*v1*H1*31
  13557. -->
  13558. (S1 ^operator O1987 = -0.06092862110810815)
  13559. --- END Proposal Phase ---
  13560. --- Decision Phase ---
  13561. RL update rl*prefer*rvt*predict-yes*H0*5 0.683776 -0.251886 0.43189 -> 0.683777 -0.251886 0.43189(R,m,v=1,0.923077,0.0714286)
  13562. RL update rl*prefer*rvt*predict-yes*H0*5*v1*H1*45 0.31622 0.251886 0.568106 -> 0.31622 0.251886 0.568106(R,m,v=1,1,0)
  13563. =>WM: (14024: S1 ^operator O1990)
  13564. 995: O: O1990 (predict-no)
  13565. --- END Decision Phase ---
  13566. --- Application Phase ---
  13567. --- Firing Productions (PE) For State At Depth 1 ---
  13568. --- Inner Elaboration Phase, active level 1 (S1) ---
  13569. Firing apply*operator
  13570. -->
  13571. (I3 ^predict-no N995 + :O )
  13572. Firing apply*operator*complete
  13573. -->
  13574. (I3 ^predict-yes N994 - :O )
  13575. inner elaboration loop at bottom goal.
  13576. --- Change Working Memory (PE) ---
  13577. =>WM: (14025: I3 ^predict-no N995)
  13578. <=WM: (14012: N994 ^status complete)
  13579. <=WM: (14011: I3 ^predict-yes N994)
  13580. --- Firing Productions (IE) For State At Depth 1 ---
  13581. --- Inner Elaboration Phase, active level 1 (S1) ---
  13582. Firing monitor*world
  13583. -->
  13584. I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
  13585. --- Change Working Memory (IE) ---
  13586. --- END Application Phase ---
  13587. --- Output Phase ---
  13588. ENV: Agent did: predict-no for direction L in state State-A
  13589. In State-A moving L
  13590. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  13591. predict error 0
  13592. dir: dir isL
  13593. --- END Output Phase ---
  13594. /|\--- Input Phase ---
  13595. =>WM: (14029: I2 ^dir L)
  13596. =>WM: (14028: I2 ^reward 1)
  13597. =>WM: (14027: I2 ^see 0)
  13598. =>WM: (14026: N995 ^status complete)
  13599. <=WM: (14015: I2 ^dir L)
  13600. <=WM: (14014: I2 ^reward 1)
  13601. <=WM: (14013: I2 ^see 1)
  13602. =>WM: (14030: I2 ^level-1 L0-root)
  13603. <=WM: (14016: I2 ^level-1 L1-root)
  13604. --- END Input Phase ---
  13605. --- Proposal Phase ---
  13606. --- Inner Elaboration Phase, active level 1 (S1) ---
  13607. Firing rl*prefer*rvt*predict-no*H0*6*v1*H1*33
  13608. -->
  13609. (S1 ^operator O1990 = 0.6710552574919724)
  13610. Firing rl*prefer*rvt*predict-yes*H0*5*v1*H1*32
  13611. -->
  13612. (S1 ^operator O1989 = 0.02602968095631553)
  13613. Firing prefer*rvt*predict-no*H0*6*v1*H1
  13614. -->
  13615. Firing prefer*rvt*predict-yes*H0*5*v1*H1
  13616. -->
  13617. Firing elaborate*copy-see-to-output-link
  13618. -->
  13619. (I3 ^see 0 +)
  13620. Firing elaborate*reward*based*on*reward
  13621. -->
  13622. (R999 ^value 1 +)
  13623. (R1 ^reward R999 +)
  13624. Firing propose*predict-yes
  13625. -->
  13626. (O1991 ^name predict-yes +)
  13627. (S1 ^operator O1991 +)
  13628. Firing propose*predict-no
  13629. -->
  13630. (O1992 ^name predict-no +)
  13631. (S1 ^operator O1992 +)
  13632. Firing rl*prefer*rvt*predict-no*H0*6
  13633. -->
  13634. (S1 ^operator O1990 = 0.3289463368854268)
  13635. Firing rl*prefer*rvt*predict-yes*H0*5
  13636. -->
  13637. (S1 ^operator O1989 = 0.4318904667247643)
  13638. Firing prefer*rvt*predict-yes*H0
  13639. -->
  13640. Firing prefer*rvt*predict-no*H0
  13641. -->
  13642. Firing elaborate*copy-dir-to-output-link
  13643. -->
  13644. (I3 ^dir L +)
  13645. inner elaboration loop at bottom goal.
  13646. Retracting elaborate*copy-see-to-output-link
  13647. -->
  13648. (I3 ^see 1 +)
  13649. Retracting propose*predict-no
  13650. -->
  13651. (O1990 ^name predict-no +)
  13652. (S1 ^operator O1990 +)
  13653. Retracting propose*predict-yes
  13654. -->
  13655. (O1989 ^name predict-yes +)
  13656. (S1 ^operator O1989 +)
  13657. Retracting elaborate*reward*based*on*reward
  13658. -->
  13659. (R998 ^value 1 +)
  13660. (R1 ^reward R998 +)
  13661. Retracting elaborate*copy-dir-to-output-link
  13662. -->
  13663. (I3 ^dir L +)
  13664. Retracting rl*prefer*rvt*predict-no*H0*6*v1*H1*43
  13665. -->
  13666. (S1 ^operator O1990 = 0.6710523655015633)
  13667. Retracting rl*prefer*rvt*predict-no*H0*6
  13668. -->
  13669. (S1 ^operator O1990 = 0.3289463368854268)
  13670. Retracting rl*prefer*rvt*predict-yes*H0*5*v1*H1*31
  13671. -->
  13672. (S1 ^operator O1989 = -0.06092862110810815)
  13673. Retracting rl*prefer*rvt*predict-yes*H0*5
  13674. -->
  13675. (S1 ^operator O1989 = 0.4318904667247643)
  13676. =>WM: (14037: S1 ^operator O1992 +)
  13677. =>WM: (14036: S1 ^operator O1991 +)
  13678. =>WM: (14035: O1992 ^name predict-no)
  13679. =>WM: (14034: O1991 ^name predict-yes)
  13680. =>WM: (14033: R999 ^value 1)
  13681. =>WM: (14032: R1 ^reward R999)
  13682. =>WM: (14031: I3 ^see 0)
  13683. <=WM: (14022: S1 ^operator O1989 +)
  13684. <=WM: (14023: S1 ^operator O1990 +)
  13685. <=WM: (14024: S1 ^operator O1990)
  13686. <=WM: (14018: R1 ^reward R998)
  13687. <=WM: (14017: I3 ^see 1)
  13688. <=WM: (14021: O1990 ^name predict-no)
  13689. <=WM: (14020: O1989 ^name predict-yes)
  13690. <=WM: (14019: R998 ^value 1)
  13691. --- Inner Elaboration Phase, active level 1 (S1) ---
  13692. Firing prefer*rvt*predict-yes*H0
  13693. -->
  13694. Firing rl*prefer*rvt*predict-yes*H0*5
  13695. -->
  13696. (S1 ^operator O1991 = 0.4318904667247643)
  13697. Firing prefer*rvt*predict-yes*H0*5*v1*H1
  13698. -->
  13699. Firing rl*prefer*rvt*predict-yes*H0*5*v1*H1*32
  13700. -->
  13701. (S1 ^operator O1991 = 0.02602968095631553)
  13702. Firing prefer*rvt*predict-no*H0
  13703. -->
  13704. Firing rl*prefer*rvt*predict-no*H0*6
  13705. -->
  13706. (S1 ^operator O1992 = 0.3289463368854268)
  13707. Firing prefer*rvt*predict-no*H0*6*v1*H1
  13708. -->
  13709. Firing rl*prefer*rvt*predict-no*H0*6*v1*H1*33
  13710. -->
  13711. (S1 ^operator O1992 = 0.6710552574919724)
  13712. inner elaboration loop at bottom goal.
  13713. Retracting rl*prefer*rvt*predict-no*H0*6
  13714. -->
  13715. (S1 ^operator O1990 = 0.3289463368854268)
  13716. Retracting rl*prefer*rvt*predict-no*H0*6*v1*H1*33
  13717. -->
  13718. (S1 ^operator O1990 = 0.6710552574919724)
  13719. Retracting rl*prefer*rvt*predict-yes*H0*5
  13720. -->
  13721. (S1 ^operator O1989 = 0.4318904667247643)
  13722. Retracting rl*prefer*rvt*predict-yes*H0*5*v1*H1*32
  13723. -->
  13724. (S1 ^operator O1989 = 0.02602968095631553)
  13725. --- END Proposal Phase ---
  13726. --- Decision Phase ---
  13727. RL update rl*prefer*rvt*predict-no*H0*6 0.565404 -0.236458 0.328946 -> 0.565404 -0.236458 0.328947(R,m,v=1,0.905063,0.086471)
  13728. RL update rl*prefer*rvt*predict-no*H0*6*v1*H1*43 0.434593 0.236459 0.671052 -> 0.434594 0.236459 0.671053(R,m,v=1,1,0)
  13729. =>WM: (14038: S1 ^operator O1992)
  13730. 996: O: O1992 (predict-no)
  13731. --- END Decision Phase ---
  13732. --- Application Phase ---
  13733. --- Firing Productions (PE) For State At Depth 1 ---
  13734. --- Inner Elaboration Phase, active level 1 (S1) ---
  13735. Firing apply*operator
  13736. -->
  13737. (I3 ^predict-no N996 + :O )
  13738. Firing apply*operator*complete
  13739. -->
  13740. (I3 ^predict-no N995 - :O )
  13741. inner elaboration loop at bottom goal.
  13742. --- Change Working Memory (PE) ---
  13743. =>WM: (14039: I3 ^predict-no N996)
  13744. <=WM: (14026: N995 ^status complete)
  13745. <=WM: (14025: I3 ^predict-no N995)
  13746. --- Firing Productions (IE) For State At Depth 1 ---
  13747. --- Inner Elaboration Phase, active level 1 (S1) ---
  13748. Firing monitor*world
  13749. -->
  13750. I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
  13751. --- Change Working Memory (IE) ---
  13752. --- END Application Phase ---
  13753. --- Output Phase ---
  13754. ENV: Agent did: predict-no for direction L in state State-A
  13755. In State-A moving L
  13756. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  13757. predict error 0
  13758. dir: dir isL
  13759. --- END Output Phase ---
  13760. -/|--- Input Phase ---
  13761. =>WM: (14043: I2 ^dir L)
  13762. =>WM: (14042: I2 ^reward 1)
  13763. =>WM: (14041: I2 ^see 0)
  13764. =>WM: (14040: N996 ^status complete)
  13765. <=WM: (14029: I2 ^dir L)
  13766. <=WM: (14028: I2 ^reward 1)
  13767. <=WM: (14027: I2 ^see 0)
  13768. =>WM: (14044: I2 ^level-1 L0-root)
  13769. <=WM: (14030: I2 ^level-1 L0-root)
  13770. --- END Input Phase ---
  13771. --- Proposal Phase ---
  13772. --- Inner Elaboration Phase, active level 1 (S1) ---
  13773. Firing rl*prefer*rvt*predict-no*H0*6*v1*H1*33
  13774. -->
  13775. (S1 ^operator O1992 = 0.6710552574919724)
  13776. Firing rl*prefer*rvt*predict-yes*H0*5*v1*H1*32
  13777. -->
  13778. (S1 ^operator O1991 = 0.02602968095631553)
  13779. Firing prefer*rvt*predict-no*H0*6*v1*H1
  13780. -->
  13781. Firing prefer*rvt*predict-yes*H0*5*v1*H1
  13782. -->
  13783. Firing elaborate*copy-see-to-output-link
  13784. -->
  13785. (I3 ^see 0 +)
  13786. Firing elaborate*reward*based*on*reward
  13787. -->
  13788. (R1000 ^value 1 +)
  13789. (R1 ^reward R1000 +)
  13790. Firing propose*predict-yes
  13791. -->
  13792. (O1993 ^name predict-yes +)
  13793. (S1 ^operator O1993 +)
  13794. Firing propose*predict-no
  13795. -->
  13796. (O1994 ^name predict-no +)
  13797. (S1 ^operator O1994 +)
  13798. Firing rl*prefer*rvt*predict-no*H0*6
  13799. -->
  13800. (S1 ^operator O1992 = 0.3289465315273784)
  13801. Firing rl*prefer*rvt*predict-yes*H0*5
  13802. -->
  13803. (S1 ^operator O1991 = 0.4318904667247643)
  13804. Firing prefer*rvt*predict-yes*H0
  13805. -->
  13806. Firing prefer*rvt*predict-no*H0
  13807. -->
  13808. Firing elaborate*copy-dir-to-output-link
  13809. -->
  13810. (I3 ^dir L +)
  13811. inner elaboration loop at bottom goal.
  13812. Retracting elaborate*copy-see-to-output-link
  13813. -->
  13814. (I3 ^see 0 +)
  13815. Retracting propose*predict-no
  13816. -->
  13817. (O1992 ^name predict-no +)
  13818. (S1 ^operator O1992 +)
  13819. Retracting propose*predict-yes
  13820. -->
  13821. (O1991 ^name predict-yes +)
  13822. (S1 ^operator O1991 +)
  13823. Retracting elaborate*reward*based*on*reward
  13824. -->
  13825. (R999 ^value 1 +)
  13826. (R1 ^reward R999 +)
  13827. Retracting elaborate*copy-dir-to-output-link
  13828. -->
  13829. (I3 ^dir L +)
  13830. Retracting rl*prefer*rvt*predict-no*H0*6*v1*H1*33
  13831. -->
  13832. (S1 ^operator O1992 = 0.6710552574919724)
  13833. Retracting rl*prefer*rvt*predict-no*H0*6
  13834. -->
  13835. (S1 ^operator O1992 = 0.3289465315273784)
  13836. Retracting rl*prefer*rvt*predict-yes*H0*5*v1*H1*32
  13837. -->
  13838. (S1 ^operator O1991 = 0.02602968095631553)
  13839. Retracting rl*prefer*rvt*predict-yes*H0*5
  13840. -->
  13841. (S1 ^operator O1991 = 0.4318904667247643)
  13842. =>WM: (14050: S1 ^operator O1994 +)
  13843. =>WM: (14049: S1 ^operator O1993 +)
  13844. =>WM: (14048: O1994 ^name predict-no)
  13845. =>WM: (14047: O1993 ^name predict-yes)
  13846. =>WM: (14046: R1000 ^value 1)
  13847. =>WM: (14045: R1 ^reward R1000)
  13848. <=WM: (14036: S1 ^operator O1991 +)
  13849. <=WM: (14037: S1 ^operator O1992 +)
  13850. <=WM: (14038: S1 ^operator O1992)
  13851. <=WM: (14032: R1 ^reward R999)
  13852. <=WM: (14035: O1992 ^name predict-no)
  13853. <=WM: (14034: O1991 ^name predict-yes)
  13854. <=WM: (14033: R999 ^value 1)
  13855. --- Inner Elaboration Phase, active level 1 (S1) ---
  13856. Firing prefer*rvt*predict-yes*H0
  13857. -->
  13858. Firing rl*prefer*rvt*predict-yes*H0*5
  13859. -->
  13860. (S1 ^operator O1993 = 0.4318904667247643)
  13861. Firing prefer*rvt*predict-yes*H0*5*v1*H1
  13862. -->
  13863. Firing rl*prefer*rvt*predict-yes*H0*5*v1*H1*32
  13864. -->
  13865. (S1 ^operator O1993 = 0.02602968095631553)
  13866. Firing prefer*rvt*predict-no*H0
  13867. -->
  13868. Firing rl*prefer*rvt*predict-no*H0*6
  13869. -->
  13870. (S1 ^operator O1994 = 0.3289465315273784)
  13871. Firing prefer*rvt*predict-no*H0*6*v1*H1
  13872. -->
  13873. Firing rl*prefer*rvt*predict-no*H0*6*v1*H1*33
  13874. -->
  13875. (S1 ^operator O1994 = 0.6710552574919724)
  13876. inner elaboration loop at bottom goal.
  13877. Retracting rl*prefer*rvt*predict-no*H0*6
  13878. -->
  13879. (S1 ^operator O1992 = 0.3289465315273784)
  13880. Retracting rl*prefer*rvt*predict-no*H0*6*v1*H1*33
  13881. -->
  13882. (S1 ^operator O1992 = 0.6710552574919724)
  13883. Retracting rl*prefer*rvt*predict-yes*H0*5
  13884. -->
  13885. (S1 ^operator O1991 = 0.4318904667247643)
  13886. Retracting rl*prefer*rvt*predict-yes*H0*5*v1*H1*32
  13887. -->
  13888. (S1 ^operator O1991 = 0.02602968095631553)
  13889. --- END Proposal Phase ---
  13890. --- Decision Phase ---
  13891. RL update rl*prefer*rvt*predict-no*H0*6 0.565404 -0.236458 0.328947 -> 0.565404 -0.236458 0.328946(R,m,v=1,0.90566,0.0859804)
  13892. RL update rl*prefer*rvt*predict-no*H0*6*v1*H1*33 0.434599 0.236456 0.671055 -> 0.434599 0.236456 0.671055(R,m,v=1,1,0)
  13893. =>WM: (14051: S1 ^operator O1994)
  13894. 997: O: O1994 (predict-no)
  13895. --- END Decision Phase ---
  13896. --- Application Phase ---
  13897. --- Firing Productions (PE) For State At Depth 1 ---
  13898. --- Inner Elaboration Phase, active level 1 (S1) ---
  13899. Firing apply*operator
  13900. -->
  13901. (I3 ^predict-no N997 + :O )
  13902. Firing apply*operator*complete
  13903. -->
  13904. (I3 ^predict-no N996 - :O )
  13905. inner elaboration loop at bottom goal.
  13906. --- Change Working Memory (PE) ---
  13907. =>WM: (14052: I3 ^predict-no N997)
  13908. <=WM: (14040: N996 ^status complete)
  13909. <=WM: (14039: I3 ^predict-no N996)
  13910. --- Firing Productions (IE) For State At Depth 1 ---
  13911. --- Inner Elaboration Phase, active level 1 (S1) ---
  13912. Firing monitor*world
  13913. -->
  13914. I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
  13915. --- Change Working Memory (IE) ---
  13916. --- END Application Phase ---
  13917. --- Output Phase ---
  13918. ENV: Agent did: predict-no for direction L in state State-A
  13919. In State-A moving L
  13920. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  13921. predict error 0
  13922. dir: dir isU
  13923. --- END Output Phase ---
  13924. \---- Input Phase ---
  13925. =>WM: (14056: I2 ^dir U)
  13926. =>WM: (14055: I2 ^reward 1)
  13927. =>WM: (14054: I2 ^see 0)
  13928. =>WM: (14053: N997 ^status complete)
  13929. <=WM: (14043: I2 ^dir L)
  13930. <=WM: (14042: I2 ^reward 1)
  13931. <=WM: (14041: I2 ^see 0)
  13932. =>WM: (14057: I2 ^level-1 L0-root)
  13933. <=WM: (14044: I2 ^level-1 L0-root)
  13934. --- END Input Phase ---
  13935. --- Proposal Phase ---
  13936. --- Inner Elaboration Phase, active level 1 (S1) ---
  13937. Firing elaborate*copy-see-to-output-link
  13938. -->
  13939. (I3 ^see 0 +)
  13940. Firing elaborate*reward*based*on*reward
  13941. -->
  13942. (R1001 ^value 1 +)
  13943. (R1 ^reward R1001 +)
  13944. Firing propose*predict-yes
  13945. -->
  13946. (O1995 ^name predict-yes +)
  13947. (S1 ^operator O1995 +)
  13948. Firing propose*predict-no
  13949. -->
  13950. (O1996 ^name predict-no +)
  13951. (S1 ^operator O1996 +)
  13952. Firing rl*prefer*rvt*predict-no*H0*2
  13953. -->
  13954. (S1 ^operator O1994 = 0.9999999999999999)
  13955. Firing rl*prefer*rvt*predict-yes*H0*1
  13956. -->
  13957. (S1 ^operator O1993 = 0.)
  13958. Firing prefer*rvt*predict-yes*H0
  13959. -->
  13960. Firing prefer*rvt*predict-no*H0
  13961. -->
  13962. Firing elaborate*copy-dir-to-output-link
  13963. -->
  13964. (I3 ^dir U +)
  13965. inner elaboration loop at bottom goal.
  13966. Retracting elaborate*copy-see-to-output-link
  13967. -->
  13968. (I3 ^see 0 +)
  13969. Retracting propose*predict-no
  13970. -->
  13971. (O1994 ^name predict-no +)
  13972. (S1 ^operator O1994 +)
  13973. Retracting propose*predict-yes
  13974. -->
  13975. (O1993 ^name predict-yes +)
  13976. (S1 ^operator O1993 +)
  13977. Retracting elaborate*reward*based*on*reward
  13978. -->
  13979. (R1000 ^value 1 +)
  13980. (R1 ^reward R1000 +)
  13981. Retracting elaborate*copy-dir-to-output-link
  13982. -->
  13983. (I3 ^dir L +)
  13984. Retracting rl*prefer*rvt*predict-no*H0*6*v1*H1*33
  13985. -->
  13986. (S1 ^operator O1994 = 0.6710549891390698)
  13987. Retracting rl*prefer*rvt*predict-no*H0*6
  13988. -->
  13989. (S1 ^operator O1994 = 0.3289462631744757)
  13990. Retracting rl*prefer*rvt*predict-yes*H0*5*v1*H1*32
  13991. -->
  13992. (S1 ^operator O1993 = 0.02602968095631553)
  13993. Retracting rl*prefer*rvt*predict-yes*H0*5
  13994. -->
  13995. (S1 ^operator O1993 = 0.4318904667247643)
  13996. =>WM: (14064: S1 ^operator O1996 +)
  13997. =>WM: (14063: S1 ^operator O1995 +)
  13998. =>WM: (14062: I3 ^dir U)
  13999. =>WM: (14061: O1996 ^name predict-no)
  14000. =>WM: (14060: O1995 ^name predict-yes)
  14001. =>WM: (14059: R1001 ^value 1)
  14002. =>WM: (14058: R1 ^reward R1001)
  14003. <=WM: (14049: S1 ^operator O1993 +)
  14004. <=WM: (14050: S1 ^operator O1994 +)
  14005. <=WM: (14051: S1 ^operator O1994)
  14006. <=WM: (14007: I3 ^dir L)
  14007. <=WM: (14045: R1 ^reward R1000)
  14008. <=WM: (14048: O1994 ^name predict-no)
  14009. <=WM: (14047: O1993 ^name predict-yes)
  14010. <=WM: (14046: R1000 ^value 1)
  14011. --- Inner Elaboration Phase, active level 1 (S1) ---
  14012. Firing prefer*rvt*predict-yes*H0
  14013. -->
  14014. Firing rl*prefer*rvt*predict-yes*H0*1
  14015. -->
  14016. (S1 ^operator O1995 = 0.)
  14017. Firing prefer*rvt*predict-no*H0
  14018. -->
  14019. Firing rl*prefer*rvt*predict-no*H0*2
  14020. -->
  14021. (S1 ^operator O1996 = 0.9999999999999999)
  14022. inner elaboration loop at bottom goal.
  14023. Retracting rl*prefer*rvt*predict-no*H0*2
  14024. -->
  14025. (S1 ^operator O1994 = 0.9999999999999999)
  14026. Retracting rl*prefer*rvt*predict-yes*H0*1
  14027. -->
  14028. (S1 ^operator O1993 = 0.)
  14029. --- END Proposal Phase ---
  14030. --- Decision Phase ---
  14031. RL update rl*prefer*rvt*predict-no*H0*6 0.565404 -0.236458 0.328946 -> 0.565404 -0.236457 0.328946(R,m,v=1,0.90625,0.0854953)
  14032. RL update rl*prefer*rvt*predict-no*H0*6*v1*H1*33 0.434599 0.236456 0.671055 -> 0.434598 0.236457 0.671055(R,m,v=1,1,0)
  14033. =>WM: (14065: S1 ^operator O1996)
  14034. 998: O: O1996 (predict-no)
  14035. --- END Decision Phase ---
  14036. --- Application Phase ---
  14037. --- Firing Productions (PE) For State At Depth 1 ---
  14038. --- Inner Elaboration Phase, active level 1 (S1) ---
  14039. Firing apply*operator
  14040. -->
  14041. (I3 ^predict-no N998 + :O )
  14042. Firing apply*operator*complete
  14043. -->
  14044. (I3 ^predict-no N997 - :O )
  14045. inner elaboration loop at bottom goal.
  14046. --- Change Working Memory (PE) ---
  14047. =>WM: (14066: I3 ^predict-no N998)
  14048. <=WM: (14053: N997 ^status complete)
  14049. <=WM: (14052: I3 ^predict-no N997)
  14050. --- Firing Productions (IE) For State At Depth 1 ---
  14051. --- Inner Elaboration Phase, active level 1 (S1) ---
  14052. Firing monitor*world
  14053. -->
  14054. I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
  14055. --- Change Working Memory (IE) ---
  14056. --- END Application Phase ---
  14057. --- Output Phase ---
  14058. ENV: Agent did: predict-no for direction U in state State-A
  14059. In State-A moving U
  14060. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  14061. predict error 0
  14062. dir: dir isU
  14063. --- END Output Phase ---
  14064. /|\--- Input Phase ---
  14065. =>WM: (14070: I2 ^dir U)
  14066. =>WM: (14069: I2 ^reward 1)
  14067. =>WM: (14068: I2 ^see 0)
  14068. =>WM: (14067: N998 ^status complete)
  14069. <=WM: (14056: I2 ^dir U)
  14070. <=WM: (14055: I2 ^reward 1)
  14071. <=WM: (14054: I2 ^see 0)
  14072. =>WM: (14071: I2 ^level-1 L0-root)
  14073. <=WM: (14057: I2 ^level-1 L0-root)
  14074. --- END Input Phase ---
  14075. --- Proposal Phase ---
  14076. --- Inner Elaboration Phase, active level 1 (S1) ---
  14077. Firing elaborate*copy-see-to-output-link
  14078. -->
  14079. (I3 ^see 0 +)
  14080. Firing elaborate*reward*based*on*reward
  14081. -->
  14082. (R1002 ^value 1 +)
  14083. (R1 ^reward R1002 +)
  14084. Firing propose*predict-yes
  14085. -->
  14086. (O1997 ^name predict-yes +)
  14087. (S1 ^operator O1997 +)
  14088. Firing propose*predict-no
  14089. -->
  14090. (O1998 ^name predict-no +)
  14091. (S1 ^operator O1998 +)
  14092. Firing rl*prefer*rvt*predict-no*H0*2
  14093. -->
  14094. (S1 ^operator O1996 = 0.9999999999999999)
  14095. Firing rl*prefer*rvt*predict-yes*H0*1
  14096. -->
  14097. (S1 ^operator O1995 = 0.)
  14098. Firing prefer*rvt*predict-yes*H0
  14099. -->
  14100. Firing prefer*rvt*predict-no*H0
  14101. -->
  14102. Firing elaborate*copy-dir-to-output-link
  14103. -->
  14104. (I3 ^dir U +)
  14105. inner elaboration loop at bottom goal.
  14106. Retracting elaborate*copy-see-to-output-link
  14107. -->
  14108. (I3 ^see 0 +)
  14109. Retracting propose*predict-no
  14110. -->
  14111. (O1996 ^name predict-no +)
  14112. (S1 ^operator O1996 +)
  14113. Retracting propose*predict-yes
  14114. -->
  14115. (O1995 ^name predict-yes +)
  14116. (S1 ^operator O1995 +)
  14117. Retracting elaborate*reward*based*on*reward
  14118. -->
  14119. (R1001 ^value 1 +)
  14120. (R1 ^reward R1001 +)
  14121. Retracting elaborate*copy-dir-to-output-link
  14122. -->
  14123. (I3 ^dir U +)
  14124. Retracting rl*prefer*rvt*predict-no*H0*2
  14125. -->
  14126. (S1 ^operator O1996 = 0.9999999999999999)
  14127. Retracting rl*prefer*rvt*predict-yes*H0*1
  14128. -->
  14129. (S1 ^operator O1995 = 0.)
  14130. =>WM: (14077: S1 ^operator O1998 +)
  14131. =>WM: (14076: S1 ^operator O1997 +)
  14132. =>WM: (14075: O1998 ^name predict-no)
  14133. =>WM: (14074: O1997 ^name predict-yes)
  14134. =>WM: (14073: R1002 ^value 1)
  14135. =>WM: (14072: R1 ^reward R1002)
  14136. <=WM: (14063: S1 ^operator O1995 +)
  14137. <=WM: (14064: S1 ^operator O1996 +)
  14138. <=WM: (14065: S1 ^operator O1996)
  14139. <=WM: (14058: R1 ^reward R1001)
  14140. <=WM: (14061: O1996 ^name predict-no)
  14141. <=WM: (14060: O1995 ^name predict-yes)
  14142. <=WM: (14059: R1001 ^value 1)
  14143. --- Inner Elaboration Phase, active level 1 (S1) ---
  14144. Firing prefer*rvt*predict-yes*H0
  14145. -->
  14146. Firing rl*prefer*rvt*predict-yes*H0*1
  14147. -->
  14148. (S1 ^operator O1997 = 0.)
  14149. Firing prefer*rvt*predict-no*H0
  14150. -->
  14151. Firing rl*prefer*rvt*predict-no*H0*2
  14152. -->
  14153. (S1 ^operator O1998 = 0.9999999999999999)
  14154. inner elaboration loop at bottom goal.
  14155. Retracting rl*prefer*rvt*predict-no*H0*2
  14156. -->
  14157. (S1 ^operator O1996 = 0.9999999999999999)
  14158. Retracting rl*prefer*rvt*predict-yes*H0*1
  14159. -->
  14160. (S1 ^operator O1995 = 0.)
  14161. --- END Proposal Phase ---
  14162. --- Decision Phase ---
  14163. RL update rl*prefer*rvt*predict-no*H0*2 1 0 1 -> 1 0 1(R,m,v=1,1,0)
  14164. =>WM: (14078: S1 ^operator O1998)
  14165. 999: O: O1998 (predict-no)
  14166. --- END Decision Phase ---
  14167. --- Application Phase ---
  14168. --- Firing Productions (PE) For State At Depth 1 ---
  14169. --- Inner Elaboration Phase, active level 1 (S1) ---
  14170. Firing apply*operator
  14171. -->
  14172. (I3 ^predict-no N999 + :O )
  14173. Firing apply*operator*complete
  14174. -->
  14175. (I3 ^predict-no N998 - :O )
  14176. inner elaboration loop at bottom goal.
  14177. --- Change Working Memory (PE) ---
  14178. =>WM: (14079: I3 ^predict-no N999)
  14179. <=WM: (14067: N998 ^status complete)
  14180. <=WM: (14066: I3 ^predict-no N998)
  14181. --- Firing Productions (IE) For State At Depth 1 ---
  14182. --- Inner Elaboration Phase, active level 1 (S1) ---
  14183. Firing monitor*world
  14184. -->
  14185. I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
  14186. --- Change Working Memory (IE) ---
  14187. --- END Application Phase ---
  14188. --- Output Phase ---
  14189. ENV: Agent did: predict-no for direction U in state State-A
  14190. In State-A moving U
  14191. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  14192. predict error 0
  14193. dir: dir isR
  14194. --- END Output Phase ---
  14195. ---- Input Phase ---
  14196. =>WM: (14083: I2 ^dir R)
  14197. =>WM: (14082: I2 ^reward 1)
  14198. =>WM: (14081: I2 ^see 0)
  14199. =>WM: (14080: N999 ^status complete)
  14200. <=WM: (14070: I2 ^dir U)
  14201. <=WM: (14069: I2 ^reward 1)
  14202. <=WM: (14068: I2 ^see 0)
  14203. =>WM: (14084: I2 ^level-1 L0-root)
  14204. <=WM: (14071: I2 ^level-1 L0-root)
  14205. --- END Input Phase ---
  14206. --- Proposal Phase ---
  14207. --- Inner Elaboration Phase, active level 1 (S1) ---
  14208. Firing rl*prefer*rvt*predict-no*H0*4*v1*H1*34
  14209. -->
  14210. (S1 ^operator O1998 = -0.07401383653737587)
  14211. Firing rl*prefer*rvt*predict-yes*H0*3*v1*H1*35
  14212. -->
  14213. (S1 ^operator O1997 = 0.263174935775242)
  14214. Firing prefer*rvt*predict-no*H0*4*v1*H1
  14215. -->
  14216. Firing prefer*rvt*predict-yes*H0*3*v1*H1
  14217. -->
  14218. Firing elaborate*copy-see-to-output-link
  14219. -->
  14220. (I3 ^see 0 +)
  14221. Firing elaborate*reward*based*on*reward
  14222. -->
  14223. (R1003 ^value 1 +)
  14224. (R1 ^reward R1003 +)
  14225. Firing propose*predict-yes
  14226. -->
  14227. (O1999 ^name predict-yes +)
  14228. (S1 ^operator O1999 +)
  14229. Firing propose*predict-no
  14230. -->
  14231. (O2000 ^name predict-no +)
  14232. (S1 ^operator O2000 +)
  14233. Firing rl*prefer*rvt*predict-no*H0*4
  14234. -->
  14235. (S1 ^operator O1998 = 0.2572459278910315)
  14236. Firing rl*prefer*rvt*predict-yes*H0*3
  14237. -->
  14238. (S1 ^operator O1997 = 0.7368288308771758)
  14239. Firing prefer*rvt*predict-yes*H0
  14240. -->
  14241. Firing prefer*rvt*predict-no*H0
  14242. -->
  14243. Firing elaborate*copy-dir-to-output-link
  14244. -->
  14245. (I3 ^dir R +)
  14246. inner elaboration loop at bottom goal.
  14247. Retracting elaborate*copy-see-to-output-link
  14248. -->
  14249. (I3 ^see 0 +)
  14250. Retracting propose*predict-no
  14251. -->
  14252. (O1998 ^name predict-no +)
  14253. (S1 ^operator O1998 +)
  14254. Retracting propose*predict-yes
  14255. -->
  14256. (O1997 ^name predict-yes +)
  14257. (S1 ^operator O1997 +)
  14258. Retracting elaborate*reward*based*on*reward
  14259. -->
  14260. (R1002 ^value 1 +)
  14261. (R1 ^reward R1002 +)
  14262. Retracting elaborate*copy-dir-to-output-link
  14263. -->
  14264. (I3 ^dir U +)
  14265. Retracting rl*prefer*rvt*predict-no*H0*2
  14266. -->
  14267. (S1 ^operator O1998 = 0.9999999999999999)
  14268. Retracting rl*prefer*rvt*predict-yes*H0*1
  14269. -->
  14270. (S1 ^operator O1997 = 0.)
  14271. =>WM: (14091: S1 ^operator O2000 +)
  14272. =>WM: (14090: S1 ^operator O1999 +)
  14273. =>WM: (14089: I3 ^dir R)
  14274. =>WM: (14088: O2000 ^name predict-no)
  14275. =>WM: (14087: O1999 ^name predict-yes)
  14276. =>WM: (14086: R1003 ^value 1)
  14277. =>WM: (14085: R1 ^reward R1003)
  14278. <=WM: (14076: S1 ^operator O1997 +)
  14279. <=WM: (14077: S1 ^operator O1998 +)
  14280. <=WM: (14078: S1 ^operator O1998)
  14281. <=WM: (14062: I3 ^dir U)
  14282. <=WM: (14072: R1 ^reward R1002)
  14283. <=WM: (14075: O1998 ^name predict-no)
  14284. <=WM: (14074: O1997 ^name predict-yes)
  14285. <=WM: (14073: R1002 ^value 1)
  14286. --- Inner Elaboration Phase, active level 1 (S1) ---
  14287. Firing prefer*rvt*predict-yes*H0
  14288. -->
  14289. Firing rl*prefer*rvt*predict-yes*H0*3*v1*H1*35
  14290. -->
  14291. (S1 ^operator O1999 = 0.263174935775242)
  14292. Firing rl*prefer*rvt*predict-yes*H0*3
  14293. -->
  14294. (S1 ^operator O1999 = 0.7368288308771758)
  14295. Firing prefer*rvt*predict-yes*H0*3*v1*H1
  14296. -->
  14297. Firing prefer*rvt*predict-no*H0
  14298. -->
  14299. Firing rl*prefer*rvt*predict-no*H0*4*v1*H1*34
  14300. -->
  14301. (S1 ^operator O2000 = -0.07401383653737587)
  14302. Firing rl*prefer*rvt*predict-no*H0*4
  14303. -->
  14304. (S1 ^operator O2000 = 0.2572459278910315)
  14305. Firing prefer*rvt*predict-no*H0*4*v1*H1
  14306. -->
  14307. inner elaboration loop at bottom goal.
  14308. Retracting rl*prefer*rvt*predict-no*H0*4
  14309. -->
  14310. (S1 ^operator O1998 = 0.2572459278910315)
  14311. Retracting rl*prefer*rvt*predict-no*H0*4*v1*H1*34
  14312. -->
  14313. (S1 ^operator O1998 = -0.07401383653737587)
  14314. Retracting rl*prefer*rvt*predict-yes*H0*3
  14315. -->
  14316. (S1 ^operator O1997 = 0.7368288308771758)
  14317. Retracting rl*prefer*rvt*predict-yes*H0*3*v1*H1*35
  14318. -->
  14319. (S1 ^operator O1997 = 0.263174935775242)
  14320. --- END Proposal Phase ---
  14321. --- Decision Phase ---
  14322. RL update rl*prefer*rvt*predict-no*H0*2 1 0 1 -> 1 0 1(R,m,v=1,1,0)
  14323. =>WM: (14092: S1 ^operator O1999)
  14324. 1000: O: O1999 (predict-yes)
  14325. --- END Decision Phase ---
  14326. --- Application Phase ---
  14327. --- Firing Productions (PE) For State At Depth 1 ---
  14328. --- Inner Elaboration Phase, active level 1 (S1) ---
  14329. Firing apply*operator
  14330. -->
  14331. (I3 ^predict-yes N1000 + :O )
  14332. Firing apply*operator*complete
  14333. -->
  14334. (I3 ^predict-no N999 - :O )
  14335. inner elaboration loop at bottom goal.
  14336. --- Change Working Memory (PE) ---
  14337. =>WM: (14093: I3 ^predict-yes N1000)
  14338. <=WM: (14080: N999 ^status complete)
  14339. <=WM: (14079: I3 ^predict-no N999)
  14340. --- Firing Productions (IE) For State At Depth 1 ---
  14341. --- Inner Elaboration Phase, active level 1 (S1) ---
  14342. Firing monitor*world
  14343. -->
  14344. I see 1 and I'm going to do: predict-yes inner elaboration loop at bottom goal.
  14345. --- Change Working Memory (IE) ---
  14346. --- END Application Phase ---
  14347. --- Output Phase ---
  14348. ENV: Agent did: predict-yes for direction R in state State-A
  14349. In State-A moving R
  14350. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  14351. predict error 0
  14352. dir: dir isU
  14353. --- END Output Phase ---
  14354. /|\-/|\-/|\--- Input Phase ---
  14355. =>WM: (14097: I2 ^dir U)
  14356. =>WM: (14096: I2 ^reward 1)
  14357. =>WM: (14095: I2 ^see 1)
  14358. =>WM: (14094: N1000 ^status complete)
  14359. <=WM: (14083: I2 ^dir R)
  14360. <=WM: (14082: I2 ^reward 1)
  14361. <=WM: (14081: I2 ^see 0)
  14362. =>WM: (14098: I2 ^level-1 R1-root)
  14363. <=WM: (14084: I2 ^level-1 L0-root)
  14364. --- END Input Phase ---
  14365. --- Proposal Phase ---
  14366. --- Inner Elaboration Phase, active level 1 (S1) ---
  14367. Firing elaborate*copy-see-to-output-link
  14368. -->
  14369. (I3 ^see 1 +)
  14370. Firing elaborate*reward*based*on*reward
  14371. -->
  14372. (R1004 ^value 1 +)
  14373. (R1 ^reward R1004 +)
  14374. Firing propose*predict-yes
  14375. -->
  14376. (O2001 ^name predict-yes +)
  14377. (S1 ^operator O2001 +)
  14378. Firing propose*predict-no
  14379. -->
  14380. (O2002 ^name predict-no +)
  14381. (S1 ^operator O2002 +)
  14382. Firing rl*prefer*rvt*predict-no*H0*2
  14383. -->
  14384. (S1 ^operator O2000 = 0.9999999999999999)
  14385. Firing rl*prefer*rvt*predict-yes*H0*1
  14386. -->
  14387. (S1 ^operator O1999 = 0.)
  14388. Firing prefer*rvt*predict-yes*H0
  14389. -->
  14390. Firing prefer*rvt*predict-no*H0
  14391. -->
  14392. Firing elaborate*copy-dir-to-output-link
  14393. -->
  14394. (I3 ^dir U +)
  14395. inner elaboration loop at bottom goal.
  14396. Retracting elaborate*copy-see-to-output-link
  14397. -->
  14398. (I3 ^see 0 +)
  14399. Retracting propose*predict-no
  14400. -->
  14401. (O2000 ^name predict-no +)
  14402. (S1 ^operator O2000 +)
  14403. Retracting propose*predict-yes
  14404. -->
  14405. (O1999 ^name predict-yes +)
  14406. (S1 ^operator O1999 +)
  14407. Retracting elaborate*reward*based*on*reward
  14408. -->
  14409. (R1003 ^value 1 +)
  14410. (R1 ^reward R1003 +)
  14411. Retracting elaborate*copy-dir-to-output-link
  14412. -->
  14413. (I3 ^dir R +)
  14414. Retracting rl*prefer*rvt*predict-no*H0*4
  14415. -->
  14416. (S1 ^operator O2000 = 0.2572459278910315)
  14417. Retracting rl*prefer*rvt*predict-no*H0*4*v1*H1*34
  14418. -->
  14419. (S1 ^operator O2000 = -0.07401383653737587)
  14420. Retracting rl*prefer*rvt*predict-yes*H0*3
  14421. -->
  14422. (S1 ^operator O1999 = 0.7368288308771758)
  14423. Retracting rl*prefer*rvt*predict-yes*H0*3*v1*H1*35
  14424. -->
  14425. (S1 ^operator O1999 = 0.263174935775242)
  14426. =>WM: (14106: S1 ^operator O2002 +)
  14427. =>WM: (14105: S1 ^operator O2001 +)
  14428. =>WM: (14104: I3 ^dir U)
  14429. =>WM: (14103: O2002 ^name predict-no)
  14430. =>WM: (14102: O2001 ^name predict-yes)
  14431. =>WM: (14101: R1004 ^value 1)
  14432. =>WM: (14100: R1 ^reward R1004)
  14433. =>WM: (14099: I3 ^see 1)
  14434. <=WM: (14090: S1 ^operator O1999 +)
  14435. <=WM: (14092: S1 ^operator O1999)
  14436. <=WM: (14091: S1 ^operator O2000 +)
  14437. <=WM: (14089: I3 ^dir R)
  14438. <=WM: (14085: R1 ^reward R1003)
  14439. <=WM: (14031: I3 ^see 0)
  14440. <=WM: (14088: O2000 ^name predict-no)
  14441. <=WM: (14087: O1999 ^name predict-yes)
  14442. <=WM: (14086: R1003 ^value 1)
  14443. --- Inner Elaboration Phase, active level 1 (S1) ---
  14444. Firing prefer*rvt*predict-yes*H0
  14445. -->
  14446. Firing rl*prefer*rvt*predict-yes*H0*1
  14447. -->
  14448. (S1 ^operator O2001 = 0.)
  14449. Firing prefer*rvt*predict-no*H0
  14450. -->
  14451. Firing rl*prefer*rvt*predict-no*H0*2
  14452. -->
  14453. (S1 ^operator O2002 = 0.9999999999999999)
  14454. inner elaboration loop at bottom goal.
  14455. Retracting rl*prefer*rvt*predict-no*H0*2
  14456. -->
  14457. (S1 ^operator O2000 = 0.9999999999999999)
  14458. Retracting rl*prefer*rvt*predict-yes*H0*1
  14459. -->
  14460. (S1 ^operator O1999 = 0.)
  14461. --- END Proposal Phase ---
  14462. --- Decision Phase ---
  14463. RL update rl*prefer*rvt*predict-yes*H0*3 0.748236 -0.0114074 0.736829 -> 0.748236 -0.0114079 0.736828(R,m,v=1,0.89697,0.0929786)
  14464. RL update rl*prefer*rvt*predict-yes*H0*3*v1*H1*35 0.251765 0.0114102 0.263175 -> 0.251765 0.0114098 0.263174(R,m,v=1,1,0)
  14465. =>WM: (14107: S1 ^operator O2002)
  14466. 1001: O: O2002 (predict-no)
  14467. --- END Decision Phase ---
  14468. --- Application Phase ---
  14469. --- Firing Productions (PE) For State At Depth 1 ---
  14470. --- Inner Elaboration Phase, active level 1 (S1) ---
  14471. Firing apply*operator
  14472. -->
  14473. (I3 ^predict-no N1001 + :O )
  14474. Firing apply*operator*complete
  14475. -->
  14476. (I3 ^predict-yes N1000 - :O )
  14477. inner elaboration loop at bottom goal.
  14478. --- Change Working Memory (PE) ---
  14479. =>WM: (14108: I3 ^predict-no N1001)
  14480. <=WM: (14094: N1000 ^status complete)
  14481. <=WM: (14093: I3 ^predict-yes N1000)
  14482. --- Firing Productions (IE) For State At Depth 1 ---
  14483. --- Inner Elaboration Phase, active level 1 (S1) ---
  14484. Firing monitor*world
  14485. -->
  14486. I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
  14487. --- Change Working Memory (IE) ---
  14488. --- END Application Phase ---
  14489. --- Output Phase ---
  14490. ENV: Agent did: predict-no for direction U in state State-B
  14491. In State-B moving U
  14492. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  14493. predict error 0
  14494. dir: dir isU
  14495. --- END Output Phase ---
  14496. ---- Input Phase ---
  14497. =>WM: (14112: I2 ^dir U)
  14498. =>WM: (14111: I2 ^reward 1)
  14499. =>WM: (14110: I2 ^see 0)
  14500. =>WM: (14109: N1001 ^status complete)
  14501. <=WM: (14097: I2 ^dir U)
  14502. <=WM: (14096: I2 ^reward 1)
  14503. <=WM: (14095: I2 ^see 1)
  14504. =>WM: (14113: I2 ^level-1 R1-root)
  14505. <=WM: (14098: I2 ^level-1 R1-root)
  14506. --- END Input Phase ---
  14507. --- Proposal Phase ---
  14508. --- Inner Elaboration Phase, active level 1 (S1) ---
  14509. Firing elaborate*copy-see-to-output-link
  14510. -->
  14511. (I3 ^see 0 +)
  14512. Firing elaborate*reward*based*on*reward
  14513. -->
  14514. (R1005 ^value 1 +)
  14515. (R1 ^reward R1005 +)
  14516. Firing propose*predict-yes
  14517. -->
  14518. (O2003 ^name predict-yes +)
  14519. (S1 ^operator O2003 +)
  14520. Firing propose*predict-no
  14521. -->
  14522. (O2004 ^name predict-no +)
  14523. (S1 ^operator O2004 +)
  14524. Firing rl*prefer*rvt*predict-no*H0*2
  14525. -->
  14526. (S1 ^operator O2002 = 0.9999999999999999)
  14527. Firing rl*prefer*rvt*predict-yes*H0*1
  14528. -->
  14529. (S1 ^operator O2001 = 0.)
  14530. Firing prefer*rvt*predict-yes*H0
  14531. -->
  14532. Firing prefer*rvt*predict-no*H0
  14533. -->
  14534. Firing elaborate*copy-dir-to-output-link
  14535. -->
  14536. (I3 ^dir U +)
  14537. inner elaboration loop at bottom goal.
  14538. Retracting elaborate*copy-see-to-output-link
  14539. -->
  14540. (I3 ^see 1 +)
  14541. Retracting propose*predict-no
  14542. -->
  14543. (O2002 ^name predict-no +)
  14544. (S1 ^operator O2002 +)
  14545. Retracting propose*predict-yes
  14546. -->
  14547. (O2001 ^name predict-yes +)
  14548. (S1 ^operator O2001 +)
  14549. Retracting elaborate*reward*based*on*reward
  14550. -->
  14551. (R1004 ^value 1 +)
  14552. (R1 ^reward R1004 +)
  14553. Retracting elaborate*copy-dir-to-output-link
  14554. -->
  14555. (I3 ^dir U +)
  14556. Retracting rl*prefer*rvt*predict-no*H0*2
  14557. -->
  14558. (S1 ^operator O2002 = 0.9999999999999999)
  14559. Retracting rl*prefer*rvt*predict-yes*H0*1
  14560. -->
  14561. (S1 ^operator O2001 = 0.)
  14562. =>WM: (14120: S1 ^operator O2004 +)
  14563. =>WM: (14119: S1 ^operator O2003 +)
  14564. =>WM: (14118: O2004 ^name predict-no)
  14565. =>WM: (14117: O2003 ^name predict-yes)
  14566. =>WM: (14116: R1005 ^value 1)
  14567. =>WM: (14115: R1 ^reward R1005)
  14568. =>WM: (14114: I3 ^see 0)
  14569. <=WM: (14105: S1 ^operator O2001 +)
  14570. <=WM: (14106: S1 ^operator O2002 +)
  14571. <=WM: (14107: S1 ^operator O2002)
  14572. <=WM: (14100: R1 ^reward R1004)
  14573. <=WM: (14099: I3 ^see 1)
  14574. <=WM: (14103: O2002 ^name predict-no)
  14575. <=WM: (14102: O2001 ^name predict-yes)
  14576. <=WM: (14101: R1004 ^value 1)
  14577. --- Inner Elaboration Phase, active level 1 (S1) ---
  14578. Firing prefer*rvt*predict-yes*H0
  14579. -->
  14580. Firing rl*prefer*rvt*predict-yes*H0*1
  14581. -->
  14582. (S1 ^operator O2003 = 0.)
  14583. Firing prefer*rvt*predict-no*H0
  14584. -->
  14585. Firing rl*prefer*rvt*predict-no*H0*2
  14586. -->
  14587. (S1 ^operator O2004 = 0.9999999999999999)
  14588. inner elaboration loop at bottom goal.
  14589. Retracting rl*prefer*rvt*predict-no*H0*2
  14590. -->
  14591. (S1 ^operator O2002 = 0.9999999999999999)
  14592. Retracting rl*prefer*rvt*predict-yes*H0*1
  14593. -->
  14594. (S1 ^operator O2001 = 0.)
  14595. --- END Proposal Phase ---
  14596. --- Decision Phase ---
  14597. RL update rl*prefer*rvt*predict-no*H0*2 1 0 1 -> 1 0 1(R,m,v=1,1,0)
  14598. =>WM: (14121: S1 ^operator O2004)
  14599. 1002: O: O2004 (predict-no)
  14600. --- END Decision Phase ---
  14601. --- Application Phase ---
  14602. --- Firing Productions (PE) For State At Depth 1 ---
  14603. --- Inner Elaboration Phase, active level 1 (S1) ---
  14604. Firing apply*operator
  14605. -->
  14606. (I3 ^predict-no N1002 + :O )
  14607. Firing apply*operator*complete
  14608. -->
  14609. (I3 ^predict-no N1001 - :O )
  14610. inner elaboration loop at bottom goal.
  14611. --- Change Working Memory (PE) ---
  14612. =>WM: (14122: I3 ^predict-no N1002)
  14613. <=WM: (14109: N1001 ^status complete)
  14614. <=WM: (14108: I3 ^predict-no N1001)
  14615. --- Firing Productions (IE) For State At Depth 1 ---
  14616. --- Inner Elaboration Phase, active level 1 (S1) ---
  14617. Firing monitor*world
  14618. -->
  14619. I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
  14620. --- Change Working Memory (IE) ---
  14621. --- END Application Phase ---
  14622. --- Output Phase ---
  14623. ENV: Agent did: predict-no for direction U in state State-B
  14624. In State-B moving U
  14625. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  14626. predict error 0
  14627. dir: dir isU
  14628. --- END Output Phase ---
  14629. /|\--- Input Phase ---
  14630. =>WM: (14126: I2 ^dir U)
  14631. =>WM: (14125: I2 ^reward 1)
  14632. =>WM: (14124: I2 ^see 0)
  14633. =>WM: (14123: N1002 ^status complete)
  14634. <=WM: (14112: I2 ^dir U)
  14635. <=WM: (14111: I2 ^reward 1)
  14636. <=WM: (14110: I2 ^see 0)
  14637. =>WM: (14127: I2 ^level-1 R1-root)
  14638. <=WM: (14113: I2 ^level-1 R1-root)
  14639. --- END Input Phase ---
  14640. --- Proposal Phase ---
  14641. --- Inner Elaboration Phase, active level 1 (S1) ---
  14642. Firing elaborate*copy-see-to-output-link
  14643. -->
  14644. (I3 ^see 0 +)
  14645. Firing elaborate*reward*based*on*reward
  14646. -->
  14647. (R1006 ^value 1 +)
  14648. (R1 ^reward R1006 +)
  14649. Firing propose*predict-yes
  14650. -->
  14651. (O2005 ^name predict-yes +)
  14652. (S1 ^operator O2005 +)
  14653. Firing propose*predict-no
  14654. -->
  14655. (O2006 ^name predict-no +)
  14656. (S1 ^operator O2006 +)
  14657. Firing rl*prefer*rvt*predict-no*H0*2
  14658. -->
  14659. (S1 ^operator O2004 = 0.9999999999999999)
  14660. Firing rl*prefer*rvt*predict-yes*H0*1
  14661. -->
  14662. (S1 ^operator O2003 = 0.)
  14663. Firing prefer*rvt*predict-yes*H0
  14664. -->
  14665. Firing prefer*rvt*predict-no*H0
  14666. -->
  14667. Firing elaborate*copy-dir-to-output-link
  14668. -->
  14669. (I3 ^dir U +)
  14670. inner elaboration loop at bottom goal.
  14671. Retracting elaborate*copy-see-to-output-link
  14672. -->
  14673. (I3 ^see 0 +)
  14674. Retracting propose*predict-no
  14675. -->
  14676. (O2004 ^name predict-no +)
  14677. (S1 ^operator O2004 +)
  14678. Retracting propose*predict-yes
  14679. -->
  14680. (O2003 ^name predict-yes +)
  14681. (S1 ^operator O2003 +)
  14682. Retracting elaborate*reward*based*on*reward
  14683. -->
  14684. (R1005 ^value 1 +)
  14685. (R1 ^reward R1005 +)
  14686. Retracting elaborate*copy-dir-to-output-link
  14687. -->
  14688. (I3 ^dir U +)
  14689. Retracting rl*prefer*rvt*predict-no*H0*2
  14690. -->
  14691. (S1 ^operator O2004 = 0.9999999999999999)
  14692. Retracting rl*prefer*rvt*predict-yes*H0*1
  14693. -->
  14694. (S1 ^operator O2003 = 0.)
  14695. =>WM: (14133: S1 ^operator O2006 +)
  14696. =>WM: (14132: S1 ^operator O2005 +)
  14697. =>WM: (14131: O2006 ^name predict-no)
  14698. =>WM: (14130: O2005 ^name predict-yes)
  14699. =>WM: (14129: R1006 ^value 1)
  14700. =>WM: (14128: R1 ^reward R1006)
  14701. <=WM: (14119: S1 ^operator O2003 +)
  14702. <=WM: (14120: S1 ^operator O2004 +)
  14703. <=WM: (14121: S1 ^operator O2004)
  14704. <=WM: (14115: R1 ^reward R1005)
  14705. <=WM: (14118: O2004 ^name predict-no)
  14706. <=WM: (14117: O2003 ^name predict-yes)
  14707. <=WM: (14116: R1005 ^value 1)
  14708. --- Inner Elaboration Phase, active level 1 (S1) ---
  14709. Firing prefer*rvt*predict-yes*H0
  14710. -->
  14711. Firing rl*prefer*rvt*predict-yes*H0*1
  14712. -->
  14713. (S1 ^operator O2005 = 0.)
  14714. Firing prefer*rvt*predict-no*H0
  14715. -->
  14716. Firing rl*prefer*rvt*predict-no*H0*2
  14717. -->
  14718. (S1 ^operator O2006 = 0.9999999999999999)
  14719. inner elaboration loop at bottom goal.
  14720. Retracting rl*prefer*rvt*predict-no*H0*2
  14721. -->
  14722. (S1 ^operator O2004 = 0.9999999999999999)
  14723. Retracting rl*prefer*rvt*predict-yes*H0*1
  14724. -->
  14725. (S1 ^operator O2003 = 0.)
  14726. --- END Proposal Phase ---
  14727. --- Decision Phase ---
  14728. RL update rl*prefer*rvt*predict-no*H0*2 1 0 1 -> 1 0 1(R,m,v=1,1,0)
  14729. =>WM: (14134: S1 ^operator O2006)
  14730. 1003: O: O2006 (predict-no)
  14731. --- END Decision Phase ---
  14732. --- Application Phase ---
  14733. --- Firing Productions (PE) For State At Depth 1 ---
  14734. --- Inner Elaboration Phase, active level 1 (S1) ---
  14735. Firing apply*operator
  14736. -->
  14737. (I3 ^predict-no N1003 + :O )
  14738. Firing apply*operator*complete
  14739. -->
  14740. (I3 ^predict-no N1002 - :O )
  14741. inner elaboration loop at bottom goal.
  14742. --- Change Working Memory (PE) ---
  14743. =>WM: (14135: I3 ^predict-no N1003)
  14744. <=WM: (14123: N1002 ^status complete)
  14745. <=WM: (14122: I3 ^predict-no N1002)
  14746. --- Firing Productions (IE) For State At Depth 1 ---
  14747. --- Inner Elaboration Phase, active level 1 (S1) ---
  14748. Firing monitor*world
  14749. -->
  14750. I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
  14751. --- Change Working Memory (IE) ---
  14752. --- END Application Phase ---
  14753. --- Output Phase ---
  14754. ENV: Agent did: predict-no for direction U in state State-B
  14755. In State-B moving U
  14756. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  14757. predict error 0
  14758. dir: dir isU
  14759. --- END Output Phase ---
  14760. -/|--- Input Phase ---
  14761. =>WM: (14139: I2 ^dir U)
  14762. =>WM: (14138: I2 ^reward 1)
  14763. =>WM: (14137: I2 ^see 0)
  14764. =>WM: (14136: N1003 ^status complete)
  14765. <=WM: (14126: I2 ^dir U)
  14766. <=WM: (14125: I2 ^reward 1)
  14767. <=WM: (14124: I2 ^see 0)
  14768. =>WM: (14140: I2 ^level-1 R1-root)
  14769. <=WM: (14127: I2 ^level-1 R1-root)
  14770. --- END Input Phase ---
  14771. --- Proposal Phase ---
  14772. --- Inner Elaboration Phase, active level 1 (S1) ---
  14773. Firing elaborate*copy-see-to-output-link
  14774. -->
  14775. (I3 ^see 0 +)
  14776. Firing elaborate*reward*based*on*reward
  14777. -->
  14778. (R1007 ^value 1 +)
  14779. (R1 ^reward R1007 +)
  14780. Firing propose*predict-yes
  14781. -->
  14782. (O2007 ^name predict-yes +)
  14783. (S1 ^operator O2007 +)
  14784. Firing propose*predict-no
  14785. -->
  14786. (O2008 ^name predict-no +)
  14787. (S1 ^operator O2008 +)
  14788. Firing rl*prefer*rvt*predict-no*H0*2
  14789. -->
  14790. (S1 ^operator O2006 = 0.9999999999999999)
  14791. Firing rl*prefer*rvt*predict-yes*H0*1
  14792. -->
  14793. (S1 ^operator O2005 = 0.)
  14794. Firing prefer*rvt*predict-yes*H0
  14795. -->
  14796. Firing prefer*rvt*predict-no*H0
  14797. -->
  14798. Firing elaborate*copy-dir-to-output-link
  14799. -->
  14800. (I3 ^dir U +)
  14801. inner elaboration loop at bottom goal.
  14802. Retracting elaborate*copy-see-to-output-link
  14803. -->
  14804. (I3 ^see 0 +)
  14805. Retracting propose*predict-no
  14806. -->
  14807. (O2006 ^name predict-no +)
  14808. (S1 ^operator O2006 +)
  14809. Retracting propose*predict-yes
  14810. -->
  14811. (O2005 ^name predict-yes +)
  14812. (S1 ^operator O2005 +)
  14813. Retracting elaborate*reward*based*on*reward
  14814. -->
  14815. (R1006 ^value 1 +)
  14816. (R1 ^reward R1006 +)
  14817. Retracting elaborate*copy-dir-to-output-link
  14818. -->
  14819. (I3 ^dir U +)
  14820. Retracting rl*prefer*rvt*predict-no*H0*2
  14821. -->
  14822. (S1 ^operator O2006 = 0.9999999999999999)
  14823. Retracting rl*prefer*rvt*predict-yes*H0*1
  14824. -->
  14825. (S1 ^operator O2005 = 0.)
  14826. =>WM: (14146: S1 ^operator O2008 +)
  14827. =>WM: (14145: S1 ^operator O2007 +)
  14828. =>WM: (14144: O2008 ^name predict-no)
  14829. =>WM: (14143: O2007 ^name predict-yes)
  14830. =>WM: (14142: R1007 ^value 1)
  14831. =>WM: (14141: R1 ^reward R1007)
  14832. <=WM: (14132: S1 ^operator O2005 +)
  14833. <=WM: (14133: S1 ^operator O2006 +)
  14834. <=WM: (14134: S1 ^operator O2006)
  14835. <=WM: (14128: R1 ^reward R1006)
  14836. <=WM: (14131: O2006 ^name predict-no)
  14837. <=WM: (14130: O2005 ^name predict-yes)
  14838. <=WM: (14129: R1006 ^value 1)
  14839. --- Inner Elaboration Phase, active level 1 (S1) ---
  14840. Firing prefer*rvt*predict-yes*H0
  14841. -->
  14842. Firing rl*prefer*rvt*predict-yes*H0*1
  14843. -->
  14844. (S1 ^operator O2007 = 0.)
  14845. Firing prefer*rvt*predict-no*H0
  14846. -->
  14847. Firing rl*prefer*rvt*predict-no*H0*2
  14848. -->
  14849. (S1 ^operator O2008 = 0.9999999999999999)
  14850. inner elaboration loop at bottom goal.
  14851. Retracting rl*prefer*rvt*predict-no*H0*2
  14852. -->
  14853. (S1 ^operator O2006 = 0.9999999999999999)
  14854. Retracting rl*prefer*rvt*predict-yes*H0*1
  14855. -->
  14856. (S1 ^operator O2005 = 0.)
  14857. --- END Proposal Phase ---
  14858. --- Decision Phase ---
  14859. RL update rl*prefer*rvt*predict-no*H0*2 1 0 1 -> 1 0 1(R,m,v=1,1,0)
  14860. =>WM: (14147: S1 ^operator O2008)
  14861. 1004: O: O2008 (predict-no)
  14862. --- END Decision Phase ---
  14863. --- Application Phase ---
  14864. --- Firing Productions (PE) For State At Depth 1 ---
  14865. --- Inner Elaboration Phase, active level 1 (S1) ---
  14866. Firing apply*operator
  14867. -->
  14868. (I3 ^predict-no N1004 + :O )
  14869. Firing apply*operator*complete
  14870. -->
  14871. (I3 ^predict-no N1003 - :O )
  14872. inner elaboration loop at bottom goal.
  14873. --- Change Working Memory (PE) ---
  14874. =>WM: (14148: I3 ^predict-no N1004)
  14875. <=WM: (14136: N1003 ^status complete)
  14876. <=WM: (14135: I3 ^predict-no N1003)
  14877. --- Firing Productions (IE) For State At Depth 1 ---
  14878. --- Inner Elaboration Phase, active level 1 (S1) ---
  14879. Firing monitor*world
  14880. -->
  14881. I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
  14882. --- Change Working Memory (IE) ---
  14883. --- END Application Phase ---
  14884. --- Output Phase ---
  14885. ENV: Agent did: predict-no for direction U in state State-B
  14886. In State-B moving U
  14887. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  14888. predict error 0
  14889. dir: dir isL
  14890. --- END Output Phase ---
  14891. \---- Input Phase ---
  14892. =>WM: (14152: I2 ^dir L)
  14893. =>WM: (14151: I2 ^reward 1)
  14894. =>WM: (14150: I2 ^see 0)
  14895. =>WM: (14149: N1004 ^status complete)
  14896. <=WM: (14139: I2 ^dir U)
  14897. <=WM: (14138: I2 ^reward 1)
  14898. <=WM: (14137: I2 ^see 0)
  14899. =>WM: (14153: I2 ^level-1 R1-root)
  14900. <=WM: (14140: I2 ^level-1 R1-root)
  14901. --- END Input Phase ---
  14902. --- Proposal Phase ---
  14903. --- Inner Elaboration Phase, active level 1 (S1) ---
  14904. Firing rl*prefer*rvt*predict-yes*H0*5*v1*H1*45
  14905. -->
  14906. (S1 ^operator O2007 = 0.5681063809875448)
  14907. Firing rl*prefer*rvt*predict-no*H0*6*v1*H1*44
  14908. -->
  14909. (S1 ^operator O2008 = -0.1549421060161498)
  14910. Firing prefer*rvt*predict-no*H0*6*v1*H1
  14911. -->
  14912. Firing prefer*rvt*predict-yes*H0*5*v1*H1
  14913. -->
  14914. Firing elaborate*copy-see-to-output-link
  14915. -->
  14916. (I3 ^see 0 +)
  14917. Firing elaborate*reward*based*on*reward
  14918. -->
  14919. (R1008 ^value 1 +)
  14920. (R1 ^reward R1008 +)
  14921. Firing propose*predict-yes
  14922. -->
  14923. (O2009 ^name predict-yes +)
  14924. (S1 ^operator O2009 +)
  14925. Firing propose*predict-no
  14926. -->
  14927. (O2010 ^name predict-no +)
  14928. (S1 ^operator O2010 +)
  14929. Firing rl*prefer*rvt*predict-no*H0*6
  14930. -->
  14931. (S1 ^operator O2008 = 0.3289460753274439)
  14932. Firing rl*prefer*rvt*predict-yes*H0*5
  14933. -->
  14934. (S1 ^operator O2007 = 0.4318904667247643)
  14935. Firing prefer*rvt*predict-yes*H0
  14936. -->
  14937. Firing prefer*rvt*predict-no*H0
  14938. -->
  14939. Firing elaborate*copy-dir-to-output-link
  14940. -->
  14941. (I3 ^dir L +)
  14942. inner elaboration loop at bottom goal.
  14943. Retracting elaborate*copy-see-to-output-link
  14944. -->
  14945. (I3 ^see 0 +)
  14946. Retracting propose*predict-no
  14947. -->
  14948. (O2008 ^name predict-no +)
  14949. (S1 ^operator O2008 +)
  14950. Retracting propose*predict-yes
  14951. -->
  14952. (O2007 ^name predict-yes +)
  14953. (S1 ^operator O2007 +)
  14954. Retracting elaborate*reward*based*on*reward
  14955. -->
  14956. (R1007 ^value 1 +)
  14957. (R1 ^reward R1007 +)
  14958. Retracting elaborate*copy-dir-to-output-link
  14959. -->
  14960. (I3 ^dir U +)
  14961. Retracting rl*prefer*rvt*predict-no*H0*2
  14962. -->
  14963. (S1 ^operator O2008 = 0.9999999999999999)
  14964. Retracting rl*prefer*rvt*predict-yes*H0*1
  14965. -->
  14966. (S1 ^operator O2007 = 0.)
  14967. =>WM: (14160: S1 ^operator O2010 +)
  14968. =>WM: (14159: S1 ^operator O2009 +)
  14969. =>WM: (14158: I3 ^dir L)
  14970. =>WM: (14157: O2010 ^name predict-no)
  14971. =>WM: (14156: O2009 ^name predict-yes)
  14972. =>WM: (14155: R1008 ^value 1)
  14973. =>WM: (14154: R1 ^reward R1008)
  14974. <=WM: (14145: S1 ^operator O2007 +)
  14975. <=WM: (14146: S1 ^operator O2008 +)
  14976. <=WM: (14147: S1 ^operator O2008)
  14977. <=WM: (14104: I3 ^dir U)
  14978. <=WM: (14141: R1 ^reward R1007)
  14979. <=WM: (14144: O2008 ^name predict-no)
  14980. <=WM: (14143: O2007 ^name predict-yes)
  14981. <=WM: (14142: R1007 ^value 1)
  14982. --- Inner Elaboration Phase, active level 1 (S1) ---
  14983. Firing prefer*rvt*predict-yes*H0
  14984. -->
  14985. Firing rl*prefer*rvt*predict-yes*H0*5*v1*H1*45
  14986. -->
  14987. (S1 ^operator O2009 = 0.5681063809875448)
  14988. Firing rl*prefer*rvt*predict-yes*H0*5
  14989. -->
  14990. (S1 ^operator O2009 = 0.4318904667247643)
  14991. Firing prefer*rvt*predict-yes*H0*5*v1*H1
  14992. -->
  14993. Firing prefer*rvt*predict-no*H0
  14994. -->
  14995. Firing rl*prefer*rvt*predict-no*H0*6*v1*H1*44
  14996. -->
  14997. (S1 ^operator O2010 = -0.1549421060161498)
  14998. Firing rl*prefer*rvt*predict-no*H0*6
  14999. -->
  15000. (S1 ^operator O2010 = 0.3289460753274439)
  15001. Firing prefer*rvt*predict-no*H0*6*v1*H1
  15002. -->
  15003. inner elaboration loop at bottom goal.
  15004. Retracting rl*prefer*rvt*predict-no*H0*6
  15005. -->
  15006. (S1 ^operator O2008 = 0.3289460753274439)
  15007. Retracting rl*prefer*rvt*predict-no*H0*6*v1*H1*44
  15008. -->
  15009. (S1 ^operator O2008 = -0.1549421060161498)
  15010. Retracting rl*prefer*rvt*predict-yes*H0*5
  15011. -->
  15012. (S1 ^operator O2007 = 0.4318904667247643)
  15013. Retracting rl*prefer*rvt*predict-yes*H0*5*v1*H1*45
  15014. -->
  15015. (S1 ^operator O2007 = 0.5681063809875448)
  15016. --- END Proposal Phase ---
  15017. --- Decision Phase ---
  15018. RL update rl*prefer*rvt*predict-no*H0*2 1 0 1 -> 1 0 1(R,m,v=1,1,0)
  15019. =>WM: (14161: S1 ^operator O2009)
  15020. 1005: O: O2009 (predict-yes)
  15021. --- END Decision Phase ---
  15022. --- Application Phase ---
  15023. --- Firing Productions (PE) For State At Depth 1 ---
  15024. --- Inner Elaboration Phase, active level 1 (S1) ---
  15025. Firing apply*operator
  15026. -->
  15027. (I3 ^predict-yes N1005 + :O )
  15028. Firing apply*operator*complete
  15029. -->
  15030. (I3 ^predict-no N1004 - :O )
  15031. inner elaboration loop at bottom goal.
  15032. --- Change Working Memory (PE) ---
  15033. =>WM: (14162: I3 ^predict-yes N1005)
  15034. <=WM: (14149: N1004 ^status complete)
  15035. <=WM: (14148: I3 ^predict-no N1004)
  15036. --- Firing Productions (IE) For State At Depth 1 ---
  15037. --- Inner Elaboration Phase, active level 1 (S1) ---
  15038. Firing monitor*world
  15039. -->
  15040. I see 1 and I'm going to do: predict-yes inner elaboration loop at bottom goal.
  15041. --- Change Working Memory (IE) ---
  15042. --- END Application Phase ---
  15043. --- Output Phase ---
  15044. ENV: Agent did: predict-yes for direction L in state State-B
  15045. In State-B moving L
  15046. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  15047. predict error 0
  15048. dir: dir isR
  15049. --- END Output Phase ---
  15050. /--- Input Phase ---
  15051. =>WM: (14166: I2 ^dir R)
  15052. =>WM: (14165: I2 ^reward 1)
  15053. =>WM: (14164: I2 ^see 1)
  15054. =>WM: (14163: N1005 ^status complete)
  15055. <=WM: (14152: I2 ^dir L)
  15056. <=WM: (14151: I2 ^reward 1)
  15057. <=WM: (14150: I2 ^see 0)
  15058. =>WM: (14167: I2 ^level-1 L1-root)
  15059. <=WM: (14153: I2 ^level-1 R1-root)
  15060. --- END Input Phase ---
  15061. --- Proposal Phase ---
  15062. --- Inner Elaboration Phase, active level 1 (S1) ---
  15063. Firing rl*prefer*rvt*predict-no*H0*4*v1*H1*39
  15064. -->
  15065. (S1 ^operator O2010 = -0.1377248055371832)
  15066. Firing rl*prefer*rvt*predict-yes*H0*3*v1*H1*40
  15067. -->
  15068. (S1 ^operator O2009 = 0.2631690211593038)
  15069. Firing prefer*rvt*predict-no*H0*4*v1*H1
  15070. -->
  15071. Firing prefer*rvt*predict-yes*H0*3*v1*H1
  15072. -->
  15073. Firing elaborate*copy-see-to-output-link
  15074. -->
  15075. (I3 ^see 1 +)
  15076. Firing elaborate*reward*based*on*reward
  15077. -->
  15078. (R1009 ^value 1 +)
  15079. (R1 ^reward R1009 +)
  15080. Firing propose*predict-yes
  15081. -->
  15082. (O2011 ^name predict-yes +)
  15083. (S1 ^operator O2011 +)
  15084. Firing propose*predict-no
  15085. -->
  15086. (O2012 ^name predict-no +)
  15087. (S1 ^operator O2012 +)
  15088. Firing rl*prefer*rvt*predict-no*H0*4
  15089. -->
  15090. (S1 ^operator O2010 = 0.2572459278910315)
  15091. Firing rl*prefer*rvt*predict-yes*H0*3
  15092. -->
  15093. (S1 ^operator O2009 = 0.7368282658793132)
  15094. Firing prefer*rvt*predict-yes*H0
  15095. -->
  15096. Firing prefer*rvt*predict-no*H0
  15097. -->
  15098. Firing elaborate*copy-dir-to-output-link
  15099. -->
  15100. (I3 ^dir R +)
  15101. inner elaboration loop at bottom goal.
  15102. Retracting elaborate*copy-see-to-output-link
  15103. -->
  15104. (I3 ^see 0 +)
  15105. Retracting propose*predict-no
  15106. -->
  15107. (O2010 ^name predict-no +)
  15108. (S1 ^operator O2010 +)
  15109. Retracting propose*predict-yes
  15110. -->
  15111. (O2009 ^name predict-yes +)
  15112. (S1 ^operator O2009 +)
  15113. Retracting elaborate*reward*based*on*reward
  15114. -->
  15115. (R1008 ^value 1 +)
  15116. (R1 ^reward R1008 +)
  15117. Retracting elaborate*copy-dir-to-output-link
  15118. -->
  15119. (I3 ^dir L +)
  15120. Retracting rl*prefer*rvt*predict-no*H0*6
  15121. -->
  15122. (S1 ^operator O2010 = 0.3289460753274439)
  15123. Retracting rl*prefer*rvt*predict-no*H0*6*v1*H1*44
  15124. -->
  15125. (S1 ^operator O2010 = -0.1549421060161498)
  15126. Retracting rl*prefer*rvt*predict-yes*H0*5
  15127. -->
  15128. (S1 ^operator O2009 = 0.4318904667247643)
  15129. Retracting rl*prefer*rvt*predict-yes*H0*5*v1*H1*45
  15130. -->
  15131. (S1 ^operator O2009 = 0.5681063809875448)
  15132. =>WM: (14175: S1 ^operator O2012 +)
  15133. =>WM: (14174: S1 ^operator O2011 +)
  15134. =>WM: (14173: I3 ^dir R)
  15135. =>WM: (14172: O2012 ^name predict-no)
  15136. =>WM: (14171: O2011 ^name predict-yes)
  15137. =>WM: (14170: R1009 ^value 1)
  15138. =>WM: (14169: R1 ^reward R1009)
  15139. =>WM: (14168: I3 ^see 1)
  15140. <=WM: (14159: S1 ^operator O2009 +)
  15141. <=WM: (14161: S1 ^operator O2009)
  15142. <=WM: (14160: S1 ^operator O2010 +)
  15143. <=WM: (14158: I3 ^dir L)
  15144. <=WM: (14154: R1 ^reward R1008)
  15145. <=WM: (14114: I3 ^see 0)
  15146. <=WM: (14157: O2010 ^name predict-no)
  15147. <=WM: (14156: O2009 ^name predict-yes)
  15148. <=WM: (14155: R1008 ^value 1)
  15149. --- Inner Elaboration Phase, active level 1 (S1) ---
  15150. Firing prefer*rvt*predict-yes*H0
  15151. -->
  15152. Firing rl*prefer*rvt*predict-yes*H0*3
  15153. -->
  15154. (S1 ^operator O2011 = 0.7368282658793132)
  15155. Firing prefer*rvt*predict-yes*H0*3*v1*H1
  15156. -->
  15157. Firing rl*prefer*rvt*predict-yes*H0*3*v1*H1*40
  15158. -->
  15159. (S1 ^operator O2011 = 0.2631690211593038)
  15160. Firing prefer*rvt*predict-no*H0
  15161. -->
  15162. Firing rl*prefer*rvt*predict-no*H0*4
  15163. -->
  15164. (S1 ^operator O2012 = 0.2572459278910315)
  15165. Firing prefer*rvt*predict-no*H0*4*v1*H1
  15166. -->
  15167. Firing rl*prefer*rvt*predict-no*H0*4*v1*H1*39
  15168. -->
  15169. (S1 ^operator O2012 = -0.1377248055371832)
  15170. inner elaboration loop at bottom goal.
  15171. Retracting rl*prefer*rvt*predict-no*H0*4
  15172. -->
  15173. (S1 ^operator O2010 = 0.2572459278910315)
  15174. Retracting rl*prefer*rvt*predict-no*H0*4*v1*H1*39
  15175. -->
  15176. (S1 ^operator O2010 = -0.1377248055371832)
  15177. Retracting rl*prefer*rvt*predict-yes*H0*3
  15178. -->
  15179. (S1 ^operator O2009 = 0.7368282658793132)
  15180. Retracting rl*prefer*rvt*predict-yes*H0*3*v1*H1*40
  15181. -->
  15182. (S1 ^operator O2009 = 0.2631690211593038)
  15183. --- END Proposal Phase ---
  15184. --- Decision Phase ---
  15185. RL update rl*prefer*rvt*predict-yes*H0*5 0.683777 -0.251886 0.43189 -> 0.683777 -0.251886 0.431891(R,m,v=1,0.923529,0.0710407)
  15186. RL update rl*prefer*rvt*predict-yes*H0*5*v1*H1*45 0.31622 0.251886 0.568106 -> 0.316221 0.251886 0.568107(R,m,v=1,1,0)
  15187. =>WM: (14176: S1 ^operator O2011)
  15188. 1006: O: O2011 (predict-yes)
  15189. --- END Decision Phase ---
  15190. --- Application Phase ---
  15191. --- Firing Productions (PE) For State At Depth 1 ---
  15192. --- Inner Elaboration Phase, active level 1 (S1) ---
  15193. Firing apply*operator
  15194. -->
  15195. (I3 ^predict-yes N1006 + :O )
  15196. Firing apply*operator*complete
  15197. -->
  15198. (I3 ^predict-yes N1005 - :O )
  15199. inner elaboration loop at bottom goal.
  15200. --- Change Working Memory (PE) ---
  15201. =>WM: (14177: I3 ^predict-yes N1006)
  15202. <=WM: (14163: N1005 ^status complete)
  15203. <=WM: (14162: I3 ^predict-yes N1005)
  15204. --- Firing Productions (IE) For State At Depth 1 ---
  15205. --- Inner Elaboration Phase, active level 1 (S1) ---
  15206. Firing monitor*world
  15207. -->
  15208. I see 1 and I'm going to do: predict-yes inner elaboration loop at bottom goal.
  15209. --- Change Working Memory (IE) ---
  15210. --- END Application Phase ---
  15211. --- Output Phase ---
  15212. ENV: Agent did: predict-yes for direction R in state State-A
  15213. In State-A moving R
  15214. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  15215. predict error 0
  15216. dir: dir isR
  15217. --- END Output Phase ---
  15218. |\--- Input Phase ---
  15219. =>WM: (14181: I2 ^dir R)
  15220. =>WM: (14180: I2 ^reward 1)
  15221. =>WM: (14179: I2 ^see 1)
  15222. =>WM: (14178: N1006 ^status complete)
  15223. <=WM: (14166: I2 ^dir R)
  15224. <=WM: (14165: I2 ^reward 1)
  15225. <=WM: (14164: I2 ^see 1)
  15226. =>WM: (14182: I2 ^level-1 R1-root)
  15227. <=WM: (14167: I2 ^level-1 L1-root)
  15228. --- END Input Phase ---
  15229. --- Proposal Phase ---
  15230. --- Inner Elaboration Phase, active level 1 (S1) ---
  15231. Firing rl*prefer*rvt*predict-yes*H0*3*v1*H1*37
  15232. -->
  15233. (S1 ^operator O2011 = -0.3011268063455669)
  15234. Firing rl*prefer*rvt*predict-no*H0*4*v1*H1*36
  15235. -->
  15236. (S1 ^operator O2012 = 0.7427525112697247)
  15237. Firing prefer*rvt*predict-no*H0*4*v1*H1
  15238. -->
  15239. Firing prefer*rvt*predict-yes*H0*3*v1*H1
  15240. -->
  15241. Firing elaborate*copy-see-to-output-link
  15242. -->
  15243. (I3 ^see 1 +)
  15244. Firing elaborate*reward*based*on*reward
  15245. -->
  15246. (R1010 ^value 1 +)
  15247. (R1 ^reward R1010 +)
  15248. Firing propose*predict-yes
  15249. -->
  15250. (O2013 ^name predict-yes +)
  15251. (S1 ^operator O2013 +)
  15252. Firing propose*predict-no
  15253. -->
  15254. (O2014 ^name predict-no +)
  15255. (S1 ^operator O2014 +)
  15256. Firing rl*prefer*rvt*predict-no*H0*4
  15257. -->
  15258. (S1 ^operator O2012 = 0.2572459278910315)
  15259. Firing rl*prefer*rvt*predict-yes*H0*3
  15260. -->
  15261. (S1 ^operator O2011 = 0.7368282658793132)
  15262. Firing prefer*rvt*predict-yes*H0
  15263. -->
  15264. Firing prefer*rvt*predict-no*H0
  15265. -->
  15266. Firing elaborate*copy-dir-to-output-link
  15267. -->
  15268. (I3 ^dir R +)
  15269. inner elaboration loop at bottom goal.
  15270. Retracting elaborate*copy-see-to-output-link
  15271. -->
  15272. (I3 ^see 1 +)
  15273. Retracting propose*predict-no
  15274. -->
  15275. (O2012 ^name predict-no +)
  15276. (S1 ^operator O2012 +)
  15277. Retracting propose*predict-yes
  15278. -->
  15279. (O2011 ^name predict-yes +)
  15280. (S1 ^operator O2011 +)
  15281. Retracting elaborate*reward*based*on*reward
  15282. -->
  15283. (R1009 ^value 1 +)
  15284. (R1 ^reward R1009 +)
  15285. Retracting elaborate*copy-dir-to-output-link
  15286. -->
  15287. (I3 ^dir R +)
  15288. Retracting rl*prefer*rvt*predict-no*H0*4*v1*H1*39
  15289. -->
  15290. (S1 ^operator O2012 = -0.1377248055371832)
  15291. Retracting rl*prefer*rvt*predict-no*H0*4
  15292. -->
  15293. (S1 ^operator O2012 = 0.2572459278910315)
  15294. Retracting rl*prefer*rvt*predict-yes*H0*3*v1*H1*40
  15295. -->
  15296. (S1 ^operator O2011 = 0.2631690211593038)
  15297. Retracting rl*prefer*rvt*predict-yes*H0*3
  15298. -->
  15299. (S1 ^operator O2011 = 0.7368282658793132)
  15300. =>WM: (14188: S1 ^operator O2014 +)
  15301. =>WM: (14187: S1 ^operator O2013 +)
  15302. =>WM: (14186: O2014 ^name predict-no)
  15303. =>WM: (14185: O2013 ^name predict-yes)
  15304. =>WM: (14184: R1010 ^value 1)
  15305. =>WM: (14183: R1 ^reward R1010)
  15306. <=WM: (14174: S1 ^operator O2011 +)
  15307. <=WM: (14176: S1 ^operator O2011)
  15308. <=WM: (14175: S1 ^operator O2012 +)
  15309. <=WM: (14169: R1 ^reward R1009)
  15310. <=WM: (14172: O2012 ^name predict-no)
  15311. <=WM: (14171: O2011 ^name predict-yes)
  15312. <=WM: (14170: R1009 ^value 1)
  15313. --- Inner Elaboration Phase, active level 1 (S1) ---
  15314. Firing prefer*rvt*predict-yes*H0
  15315. -->
  15316. Firing rl*prefer*rvt*predict-yes*H0*3
  15317. -->
  15318. (S1 ^operator O2013 = 0.7368282658793132)
  15319. Firing prefer*rvt*predict-yes*H0*3*v1*H1
  15320. -->
  15321. Firing rl*prefer*rvt*predict-yes*H0*3*v1*H1*37
  15322. -->
  15323. (S1 ^operator O2013 = -0.3011268063455669)
  15324. Firing prefer*rvt*predict-no*H0
  15325. -->
  15326. Firing rl*prefer*rvt*predict-no*H0*4
  15327. -->
  15328. (S1 ^operator O2014 = 0.2572459278910315)
  15329. Firing prefer*rvt*predict-no*H0*4*v1*H1
  15330. -->
  15331. Firing rl*prefer*rvt*predict-no*H0*4*v1*H1*36
  15332. -->
  15333. (S1 ^operator O2014 = 0.7427525112697247)
  15334. inner elaboration loop at bottom goal.
  15335. Retracting rl*prefer*rvt*predict-no*H0*4
  15336. -->
  15337. (S1 ^operator O2012 = 0.2572459278910315)
  15338. Retracting rl*prefer*rvt*predict-no*H0*4*v1*H1*36
  15339. -->
  15340. (S1 ^operator O2012 = 0.7427525112697247)
  15341. Retracting rl*prefer*rvt*predict-yes*H0*3
  15342. -->
  15343. (S1 ^operator O2011 = 0.7368282658793132)
  15344. Retracting rl*prefer*rvt*predict-yes*H0*3*v1*H1*37
  15345. -->
  15346. (S1 ^operator O2011 = -0.3011268063455669)
  15347. --- END Proposal Phase ---
  15348. --- Decision Phase ---
  15349. RL update rl*prefer*rvt*predict-yes*H0*3 0.748236 -0.0114079 0.736828 -> 0.748236 -0.0114076 0.736829(R,m,v=1,0.89759,0.092479)
  15350. RL update rl*prefer*rvt*predict-yes*H0*3*v1*H1*40 0.251763 0.0114059 0.263169 -> 0.251763 0.0114062 0.263169(R,m,v=1,1,0)
  15351. =>WM: (14189: S1 ^operator O2014)
  15352. 1007: O: O2014 (predict-no)
  15353. --- END Decision Phase ---
  15354. --- Application Phase ---
  15355. --- Firing Productions (PE) For State At Depth 1 ---
  15356. --- Inner Elaboration Phase, active level 1 (S1) ---
  15357. Firing apply*operator
  15358. -->
  15359. (I3 ^predict-no N1007 + :O )
  15360. Firing apply*operator*complete
  15361. -->
  15362. (I3 ^predict-yes N1006 - :O )
  15363. inner elaboration loop at bottom goal.
  15364. --- Change Working Memory (PE) ---
  15365. =>WM: (14190: I3 ^predict-no N1007)
  15366. <=WM: (14178: N1006 ^status complete)
  15367. <=WM: (14177: I3 ^predict-yes N1006)
  15368. --- Firing Productions (IE) For State At Depth 1 ---
  15369. --- Inner Elaboration Phase, active level 1 (S1) ---
  15370. Firing monitor*world
  15371. -->
  15372. I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
  15373. --- Change Working Memory (IE) ---
  15374. --- END Application Phase ---
  15375. --- Output Phase ---
  15376. ENV: Agent did: predict-no for direction R in state State-B
  15377. In State-B moving R
  15378. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  15379. predict error 0
  15380. dir: dir isU
  15381. --- END Output Phase ---
  15382. -/|--- Input Phase ---
  15383. =>WM: (14194: I2 ^dir U)
  15384. =>WM: (14193: I2 ^reward 1)
  15385. =>WM: (14192: I2 ^see 0)
  15386. =>WM: (14191: N1007 ^status complete)
  15387. <=WM: (14181: I2 ^dir R)
  15388. <=WM: (14180: I2 ^reward 1)
  15389. <=WM: (14179: I2 ^see 1)
  15390. =>WM: (14195: I2 ^level-1 R0-root)
  15391. <=WM: (14182: I2 ^level-1 R1-root)
  15392. --- END Input Phase ---
  15393. --- Proposal Phase ---
  15394. --- Inner Elaboration Phase, active level 1 (S1) ---
  15395. Firing elaborate*copy-see-to-output-link
  15396. -->
  15397. (I3 ^see 0 +)
  15398. Firing elaborate*reward*based*on*reward
  15399. -->
  15400. (R1011 ^value 1 +)
  15401. (R1 ^reward R1011 +)
  15402. Firing propose*predict-yes
  15403. -->
  15404. (O2015 ^name predict-yes +)
  15405. (S1 ^operator O2015 +)
  15406. Firing propose*predict-no
  15407. -->
  15408. (O2016 ^name predict-no +)
  15409. (S1 ^operator O2016 +)
  15410. Firing rl*prefer*rvt*predict-no*H0*2
  15411. -->
  15412. (S1 ^operator O2014 = 0.9999999999999999)
  15413. Firing rl*prefer*rvt*predict-yes*H0*1
  15414. -->
  15415. (S1 ^operator O2013 = 0.)
  15416. Firing prefer*rvt*predict-yes*H0
  15417. -->
  15418. Firing prefer*rvt*predict-no*H0
  15419. -->
  15420. Firing elaborate*copy-dir-to-output-link
  15421. -->
  15422. (I3 ^dir U +)
  15423. inner elaboration loop at bottom goal.
  15424. Retracting elaborate*copy-see-to-output-link
  15425. -->
  15426. (I3 ^see 1 +)
  15427. Retracting propose*predict-no
  15428. -->
  15429. (O2014 ^name predict-no +)
  15430. (S1 ^operator O2014 +)
  15431. Retracting propose*predict-yes
  15432. -->
  15433. (O2013 ^name predict-yes +)
  15434. (S1 ^operator O2013 +)
  15435. Retracting elaborate*reward*based*on*reward
  15436. -->
  15437. (R1010 ^value 1 +)
  15438. (R1 ^reward R1010 +)
  15439. Retracting elaborate*copy-dir-to-output-link
  15440. -->
  15441. (I3 ^dir R +)
  15442. Retracting rl*prefer*rvt*predict-no*H0*4*v1*H1*36
  15443. -->
  15444. (S1 ^operator O2014 = 0.7427525112697247)
  15445. Retracting rl*prefer*rvt*predict-no*H0*4
  15446. -->
  15447. (S1 ^operator O2014 = 0.2572459278910315)
  15448. Retracting rl*prefer*rvt*predict-yes*H0*3*v1*H1*37
  15449. -->
  15450. (S1 ^operator O2013 = -0.3011268063455669)
  15451. Retracting rl*prefer*rvt*predict-yes*H0*3
  15452. -->
  15453. (S1 ^operator O2013 = 0.7368286728235206)
  15454. =>WM: (14203: S1 ^operator O2016 +)
  15455. =>WM: (14202: S1 ^operator O2015 +)
  15456. =>WM: (14201: I3 ^dir U)
  15457. =>WM: (14200: O2016 ^name predict-no)
  15458. =>WM: (14199: O2015 ^name predict-yes)
  15459. =>WM: (14198: R1011 ^value 1)
  15460. =>WM: (14197: R1 ^reward R1011)
  15461. =>WM: (14196: I3 ^see 0)
  15462. <=WM: (14187: S1 ^operator O2013 +)
  15463. <=WM: (14188: S1 ^operator O2014 +)
  15464. <=WM: (14189: S1 ^operator O2014)
  15465. <=WM: (14173: I3 ^dir R)
  15466. <=WM: (14183: R1 ^reward R1010)
  15467. <=WM: (14168: I3 ^see 1)
  15468. <=WM: (14186: O2014 ^name predict-no)
  15469. <=WM: (14185: O2013 ^name predict-yes)
  15470. <=WM: (14184: R1010 ^value 1)
  15471. --- Inner Elaboration Phase, active level 1 (S1) ---
  15472. Firing prefer*rvt*predict-yes*H0
  15473. -->
  15474. Firing rl*prefer*rvt*predict-yes*H0*1
  15475. -->
  15476. (S1 ^operator O2015 = 0.)
  15477. Firing prefer*rvt*predict-no*H0
  15478. -->
  15479. Firing rl*prefer*rvt*predict-no*H0*2
  15480. -->
  15481. (S1 ^operator O2016 = 0.9999999999999999)
  15482. inner elaboration loop at bottom goal.
  15483. Retracting rl*prefer*rvt*predict-no*H0*2
  15484. -->
  15485. (S1 ^operator O2014 = 0.9999999999999999)
  15486. Retracting rl*prefer*rvt*predict-yes*H0*1
  15487. -->
  15488. (S1 ^operator O2013 = 0.)
  15489. --- END Proposal Phase ---
  15490. --- Decision Phase ---
  15491. RL update rl*prefer*rvt*predict-no*H0*4 0.586136 -0.32889 0.257246 -> 0.586136 -0.32889 0.257246(R,m,v=1,0.860465,0.120767)
  15492. RL update rl*prefer*rvt*predict-no*H0*4*v1*H1*36 0.413863 0.32889 0.742753 -> 0.413863 0.32889 0.742753(R,m,v=1,1,0)
  15493. =>WM: (14204: S1 ^operator O2016)
  15494. 1008: O: O2016 (predict-no)
  15495. --- END Decision Phase ---
  15496. --- Application Phase ---
  15497. --- Firing Productions (PE) For State At Depth 1 ---
  15498. --- Inner Elaboration Phase, active level 1 (S1) ---
  15499. Firing apply*operator
  15500. -->
  15501. (I3 ^predict-no N1008 + :O )
  15502. Firing apply*operator*complete
  15503. -->
  15504. (I3 ^predict-no N1007 - :O )
  15505. inner elaboration loop at bottom goal.
  15506. --- Change Working Memory (PE) ---
  15507. =>WM: (14205: I3 ^predict-no N1008)
  15508. <=WM: (14191: N1007 ^status complete)
  15509. <=WM: (14190: I3 ^predict-no N1007)
  15510. --- Firing Productions (IE) For State At Depth 1 ---
  15511. --- Inner Elaboration Phase, active level 1 (S1) ---
  15512. Firing monitor*world
  15513. -->
  15514. I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
  15515. --- Change Working Memory (IE) ---
  15516. --- END Application Phase ---
  15517. --- Output Phase ---
  15518. ENV: Agent did: predict-no for direction U in state State-B
  15519. In State-B moving U
  15520. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  15521. predict error 0
  15522. dir: dir isL
  15523. --- END Output Phase ---
  15524. \---- Input Phase ---
  15525. =>WM: (14209: I2 ^dir L)
  15526. =>WM: (14208: I2 ^reward 1)
  15527. =>WM: (14207: I2 ^see 0)
  15528. =>WM: (14206: N1008 ^status complete)
  15529. <=WM: (14194: I2 ^dir U)
  15530. <=WM: (14193: I2 ^reward 1)
  15531. <=WM: (14192: I2 ^see 0)
  15532. =>WM: (14210: I2 ^level-1 R0-root)
  15533. <=WM: (14195: I2 ^level-1 R0-root)
  15534. --- END Input Phase ---
  15535. --- Proposal Phase ---
  15536. --- Inner Elaboration Phase, active level 1 (S1) ---
  15537. Firing rl*prefer*rvt*predict-no*H0*6*v1*H1*38
  15538. -->
  15539. (S1 ^operator O2016 = 0.04178081990804111)
  15540. Firing rl*prefer*rvt*predict-yes*H0*5*v1*H1*30
  15541. -->
  15542. (S1 ^operator O2015 = 0.5681113503720048)
  15543. Firing prefer*rvt*predict-no*H0*6*v1*H1
  15544. -->
  15545. Firing prefer*rvt*predict-yes*H0*5*v1*H1
  15546. -->
  15547. Firing elaborate*copy-see-to-output-link
  15548. -->
  15549. (I3 ^see 0 +)
  15550. Firing elaborate*reward*based*on*reward
  15551. -->
  15552. (R1012 ^value 1 +)
  15553. (R1 ^reward R1012 +)
  15554. Firing propose*predict-yes
  15555. -->
  15556. (O2017 ^name predict-yes +)
  15557. (S1 ^operator O2017 +)
  15558. Firing propose*predict-no
  15559. -->
  15560. (O2018 ^name predict-no +)
  15561. (S1 ^operator O2018 +)
  15562. Firing rl*prefer*rvt*predict-no*H0*6
  15563. -->
  15564. (S1 ^operator O2016 = 0.3289460753274439)
  15565. Firing rl*prefer*rvt*predict-yes*H0*5
  15566. -->
  15567. (S1 ^operator O2015 = 0.4318909395679179)
  15568. Firing prefer*rvt*predict-yes*H0
  15569. -->
  15570. Firing prefer*rvt*predict-no*H0
  15571. -->
  15572. Firing elaborate*copy-dir-to-output-link
  15573. -->
  15574. (I3 ^dir L +)
  15575. inner elaboration loop at bottom goal.
  15576. Retracting elaborate*copy-see-to-output-link
  15577. -->
  15578. (I3 ^see 0 +)
  15579. Retracting propose*predict-no
  15580. -->
  15581. (O2016 ^name predict-no +)
  15582. (S1 ^operator O2016 +)
  15583. Retracting propose*predict-yes
  15584. -->
  15585. (O2015 ^name predict-yes +)
  15586. (S1 ^operator O2015 +)
  15587. Retracting elaborate*reward*based*on*reward
  15588. -->
  15589. (R1011 ^value 1 +)
  15590. (R1 ^reward R1011 +)
  15591. Retracting elaborate*copy-dir-to-output-link
  15592. -->
  15593. (I3 ^dir U +)
  15594. Retracting rl*prefer*rvt*predict-no*H0*2
  15595. -->
  15596. (S1 ^operator O2016 = 0.9999999999999999)
  15597. Retracting rl*prefer*rvt*predict-yes*H0*1
  15598. -->
  15599. (S1 ^operator O2015 = 0.)
  15600. =>WM: (14217: S1 ^operator O2018 +)
  15601. =>WM: (14216: S1 ^operator O2017 +)
  15602. =>WM: (14215: I3 ^dir L)
  15603. =>WM: (14214: O2018 ^name predict-no)
  15604. =>WM: (14213: O2017 ^name predict-yes)
  15605. =>WM: (14212: R1012 ^value 1)
  15606. =>WM: (14211: R1 ^reward R1012)
  15607. <=WM: (14202: S1 ^operator O2015 +)
  15608. <=WM: (14203: S1 ^operator O2016 +)
  15609. <=WM: (14204: S1 ^operator O2016)
  15610. <=WM: (14201: I3 ^dir U)
  15611. <=WM: (14197: R1 ^reward R1011)
  15612. <=WM: (14200: O2016 ^name predict-no)
  15613. <=WM: (14199: O2015 ^name predict-yes)
  15614. <=WM: (14198: R1011 ^value 1)
  15615. --- Inner Elaboration Phase, active level 1 (S1) ---
  15616. Firing prefer*rvt*predict-yes*H0
  15617. -->
  15618. Firing rl*prefer*rvt*predict-yes*H0*5*v1*H1*30
  15619. -->
  15620. (S1 ^operator O2017 = 0.5681113503720048)
  15621. Firing rl*prefer*rvt*predict-yes*H0*5
  15622. -->
  15623. (S1 ^operator O2017 = 0.4318909395679179)
  15624. Firing prefer*rvt*predict-yes*H0*5*v1*H1
  15625. -->
  15626. Firing prefer*rvt*predict-no*H0
  15627. -->
  15628. Firing rl*prefer*rvt*predict-no*H0*6*v1*H1*38
  15629. -->
  15630. (S1 ^operator O2018 = 0.04178081990804111)
  15631. Firing rl*prefer*rvt*predict-no*H0*6
  15632. -->
  15633. (S1 ^operator O2018 = 0.3289460753274439)
  15634. Firing prefer*rvt*predict-no*H0*6*v1*H1
  15635. -->
  15636. inner elaboration loop at bottom goal.
  15637. Retracting rl*prefer*rvt*predict-no*H0*6
  15638. -->
  15639. (S1 ^operator O2016 = 0.3289460753274439)
  15640. Retracting rl*prefer*rvt*predict-no*H0*6*v1*H1*38
  15641. -->
  15642. (S1 ^operator O2016 = 0.04178081990804111)
  15643. Retracting rl*prefer*rvt*predict-yes*H0*5
  15644. -->
  15645. (S1 ^operator O2015 = 0.4318909395679179)
  15646. Retracting rl*prefer*rvt*predict-yes*H0*5*v1*H1*30
  15647. -->
  15648. (S1 ^operator O2015 = 0.5681113503720048)
  15649. --- END Proposal Phase ---
  15650. --- Decision Phase ---
  15651. RL update rl*prefer*rvt*predict-no*H0*2 1 0 1 -> 1 0 1(R,m,v=1,1,0)
  15652. =>WM: (14218: S1 ^operator O2017)
  15653. 1009: O: O2017 (predict-yes)
  15654. --- END Decision Phase ---
  15655. --- Application Phase ---
  15656. --- Firing Productions (PE) For State At Depth 1 ---
  15657. --- Inner Elaboration Phase, active level 1 (S1) ---
  15658. Firing apply*operator
  15659. -->
  15660. (I3 ^predict-yes N1009 + :O )
  15661. Firing apply*operator*complete
  15662. -->
  15663. (I3 ^predict-no N1008 - :O )
  15664. inner elaboration loop at bottom goal.
  15665. --- Change Working Me