PageRenderTime 149ms CodeModel.GetById 22ms RepoModel.GetById 0ms app.codeStats 1ms

/flipv2/20121113-091142-2.5K-ReLST-asneeded_epochs_50_5runs_noalphadecay/stdout-flip-2.5K_2.txt

https://bitbucket.org/evan13579b/soar-ziggurat
Plain Text | 16403 lines | 15691 code | 712 blank | 0 comment | 0 complexity | ae41ef928b75e51ad6a30e3f8df7ff51 MD5 | raw file
Possible License(s): BSD-3-Clause
  1. Seeding... 2
  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 2 ...
  10. soar> Entering slave mode:
  11. - log file 'rl-slave-2.5K_2.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 isL
  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 L in state State-A
  40. In State-A moving L
  41. ENV: (next state, see, prediction correct?) = (State-A, 0, False)
  42. predict error 1
  43. dir: dir isL
  44. /|\4: O: O7 (predict-yes)
  45. I see 0 and I'm going to do: predict-yes
  46. ENV: Agent did: predict-yes for direction L in state State-A
  47. In State-A moving L
  48. ENV: (next state, see, prediction correct?) = (State-A, 0, False)
  49. predict error 1
  50. dir: dir isU
  51. -/5: O: O10 (predict-no)
  52. I see 0 and I'm going to do: predict-no
  53. ENV: Agent did: predict-no for direction U in state State-A
  54. In State-A moving U
  55. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  56. predict error 0
  57. dir: dir isU
  58. |\-6: O: O12 (predict-no)
  59. I see 1 and I'm going to do: predict-no
  60. ENV: Agent did: predict-no for direction U in state State-A
  61. In State-A moving U
  62. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  63. predict error 0
  64. dir: dir isU
  65. /|7: O: O14 (predict-no)
  66. I see 1 and I'm going to do: predict-no
  67. ENV: Agent did: predict-no for direction U in state State-A
  68. In State-A moving U
  69. ENV: (next state, see, prediction correct?) = (State-A, 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-A
  75. In State-A moving L
  76. ENV: (next state, see, prediction correct?) = (State-A, 0, False)
  77. predict error 1
  78. dir: dir isR
  79. |9: O: O17 (predict-yes)
  80. I see 0 and I'm going to do: predict-yes
  81. ENV: Agent did: predict-yes for direction 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 isR
  93. /11: O: O21 (predict-yes)
  94. I see 0 and I'm going to do: predict-yes
  95. ENV: Agent did: predict-yes for direction R in state State-B
  96. In State-B moving R
  97. ENV: (next state, see, prediction correct?) = (State-B, 0, False)
  98. predict error 1
  99. dir: dir isL
  100. rule alias: '*'
  101. rule alias: '*'
  102. rule alias: '*'
  103. rule alias: '*'
  104. |12: O: O24 (predict-no)
  105. I see 0 and I'm going to do: predict-no
  106. ENV: Agent did: predict-no for direction L in state State-B
  107. In State-B moving L
  108. ENV: (next state, see, prediction correct?) = (State-A, 1, False)
  109. predict error 1
  110. dir: dir isR
  111. \-/13: O: O25 (predict-yes)
  112. I see 0 and I'm going to do: predict-yes
  113. ENV: Agent did: predict-yes for direction R in state State-A
  114. In State-A moving R
  115. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  116. predict error 0
  117. dir: dir isR
  118. |\14: O: O27 (predict-yes)
  119. I see 1 and I'm going to do: predict-yes
  120. ENV: Agent did: predict-yes for direction R in state State-B
  121. In State-B moving R
  122. ENV: (next state, see, prediction correct?) = (State-B, 0, False)
  123. predict error 1
  124. dir: dir isU
  125. -15: O: O30 (predict-no)
  126. I see 0 and I'm going to do: predict-no
  127. ENV: Agent did: predict-no for direction U in state State-B
  128. In State-B moving U
  129. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  130. predict error 0
  131. dir: dir isU
  132. /|\16: O: O32 (predict-no)
  133. I see 1 and I'm going to do: predict-no
  134. ENV: Agent did: predict-no for direction U in state State-B
  135. In State-B moving U
  136. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  137. predict error 0
  138. dir: dir isU
  139. -/|17: O: O34 (predict-no)
  140. I see 1 and I'm going to do: predict-no
  141. ENV: Agent did: predict-no for direction U in state State-B
  142. In State-B moving U
  143. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  144. predict error 0
  145. dir: dir isR
  146. \-/18: O: O35 (predict-yes)
  147. I see 1 and I'm going to do: predict-yes
  148. ENV: Agent did: predict-yes for direction R in state State-B
  149. In State-B moving R
  150. ENV: (next state, see, prediction correct?) = (State-B, 0, False)
  151. predict error 1
  152. dir: dir isR
  153. |\-19: O: O37 (predict-yes)
  154. I see 0 and I'm going to do: predict-yes
  155. ENV: Agent did: predict-yes for direction R in state State-B
  156. In State-B moving R
  157. ENV: (next state, see, prediction correct?) = (State-B, 0, False)
  158. predict error 1
  159. dir: dir isL
  160. /|20: O: O39 (predict-yes)
  161. I see 0 and I'm going to do: predict-yes
  162. ENV: Agent did: predict-yes for direction L in state State-B
  163. In State-B moving L
  164. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  165. predict error 0
  166. dir: dir isL
  167. \-21: O: O42 (predict-no)
  168. I see 1 and I'm going to do: predict-no
  169. ENV: Agent did: predict-no for direction L in state State-A
  170. In State-A moving L
  171. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  172. predict error 0
  173. dir: dir isL
  174. /22: O: O43 (predict-yes)
  175. I see 1 and I'm going to do: predict-yes
  176. ENV: Agent did: predict-yes for direction L in state State-A
  177. In State-A moving L
  178. ENV: (next state, see, prediction correct?) = (State-A, 0, False)
  179. predict error 1
  180. dir: dir isR
  181. |\-/23: O: O45 (predict-yes)
  182. I see 0 and I'm going to do: predict-yes
  183. ENV: Agent did: predict-yes for direction R in state State-A
  184. In State-A moving R
  185. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  186. predict error 0
  187. dir: dir isL
  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 L in state State-B
  191. In State-B moving L
  192. ENV: (next state, see, prediction correct?) = (State-A, 1, False)
  193. predict error 1
  194. dir: dir isR
  195. -25: O: O49 (predict-yes)
  196. I see 0 and I'm going to do: predict-yes
  197. ENV: Agent did: predict-yes for direction R in state State-A
  198. In State-A moving R
  199. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  200. predict error 0
  201. dir: dir isU
  202. /|\-sleeping...
  203. /26: O: O52 (predict-no)
  204. I see 1 and I'm going to do: predict-no
  205. ENV: Agent did: predict-no for direction U in state State-B
  206. In State-B moving U
  207. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  208. predict error 0
  209. dir: dir isR
  210. |\-27: O: O53 (predict-yes)
  211. I see 1 and I'm going to do: predict-yes
  212. ENV: Agent did: predict-yes for direction R in state State-B
  213. In State-B moving R
  214. ENV: (next state, see, prediction correct?) = (State-B, 0, False)
  215. predict error 1
  216. dir: dir isR
  217. /|28: O: O55 (predict-yes)
  218. I see 0 and I'm going to do: predict-yes
  219. ENV: Agent did: predict-yes for direction R in state State-B
  220. In State-B moving R
  221. ENV: (next state, see, prediction correct?) = (State-B, 0, False)
  222. predict error 1
  223. dir: dir isL
  224. \-29: O: O58 (predict-no)
  225. I see 0 and I'm going to do: predict-no
  226. ENV: Agent did: predict-no for direction L in state State-B
  227. In State-B moving L
  228. ENV: (next state, see, prediction correct?) = (State-A, 1, False)
  229. predict error 1
  230. dir: dir isL
  231. /|\30: O: O59 (predict-yes)
  232. I see 0 and I'm going to do: predict-yes
  233. ENV: Agent did: predict-yes for direction L in state State-A
  234. In State-A moving L
  235. ENV: (next state, see, prediction correct?) = (State-A, 0, False)
  236. predict error 1
  237. dir: dir isL
  238. -/31: O: O61 (predict-yes)
  239. I see 0 and I'm going to do: predict-yes
  240. ENV: Agent did: predict-yes for direction L in state State-A
  241. In State-A moving L
  242. ENV: (next state, see, prediction correct?) = (State-A, 0, False)
  243. predict error 1
  244. dir: dir isL
  245. |32: O: O63 (predict-yes)
  246. I see 0 and I'm going to do: predict-yes
  247. ENV: Agent did: predict-yes for direction L in state State-A
  248. In State-A moving L
  249. ENV: (next state, see, prediction correct?) = (State-A, 0, False)
  250. predict error 1
  251. dir: dir isR
  252. \-/33: O: O66 (predict-no)
  253. I see 0 and I'm going to do: predict-no
  254. ENV: Agent did: predict-no for direction R in state State-A
  255. In State-A moving R
  256. ENV: (next state, see, prediction correct?) = (State-B, 1, False)
  257. predict error 1
  258. dir: dir isU
  259. |\-34: O: O68 (predict-no)
  260. I see 0 and I'm going to do: predict-no
  261. ENV: Agent did: predict-no for direction U in state State-B
  262. In State-B moving U
  263. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  264. predict error 0
  265. dir: dir isU
  266. /|\35: O: O70 (predict-no)
  267. I see 1 and I'm going to do: predict-no
  268. ENV: Agent did: predict-no for direction U in state State-B
  269. In State-B moving U
  270. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  271. predict error 0
  272. dir: dir isL
  273. -/36: O: O72 (predict-no)
  274. I see 1 and I'm going to do: predict-no
  275. ENV: Agent did: predict-no for direction L in state State-B
  276. In State-B moving L
  277. ENV: (next state, see, prediction correct?) = (State-A, 1, False)
  278. predict error 1
  279. dir: dir isU
  280. |\-/37: O: O74 (predict-no)
  281. I see 0 and I'm going to do: predict-no
  282. ENV: Agent did: predict-no for direction U in state State-A
  283. In State-A moving U
  284. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  285. predict error 0
  286. dir: dir isU
  287. |\-38: O: O75 (predict-yes)
  288. I see 1 and I'm going to do: predict-yes
  289. ENV: Agent did: predict-yes for direction U in state State-A
  290. In State-A moving U
  291. ENV: (next state, see, prediction correct?) = (State-A, 0, False)
  292. predict error 1
  293. dir: dir isU
  294. /|\39: O: O77 (predict-yes)
  295. I see 0 and I'm going to do: predict-yes
  296. ENV: Agent did: predict-yes for direction U in state State-A
  297. In State-A moving U
  298. ENV: (next state, see, prediction correct?) = (State-A, 0, False)
  299. predict error 1
  300. dir: dir isU
  301. -/40: O: O80 (predict-no)
  302. I see 0 and I'm going to do: predict-no
  303. ENV: Agent did: predict-no for direction U in state State-A
  304. In State-A moving U
  305. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  306. predict error 0
  307. dir: dir isU
  308. |\-41: O: O82 (predict-no)
  309. I see 1 and I'm going to do: predict-no
  310. ENV: Agent did: predict-no for direction U in state State-A
  311. In State-A moving U
  312. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  313. predict error 0
  314. dir: dir isU
  315. /42: O: O84 (predict-no)
  316. I see 1 and I'm going to do: predict-no
  317. ENV: Agent did: predict-no for direction U in state State-A
  318. In State-A moving U
  319. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  320. predict error 0
  321. dir: dir isR
  322. |\-43: O: O85 (predict-yes)
  323. I see 1 and I'm going to do: predict-yes
  324. ENV: Agent did: predict-yes for direction R in state State-A
  325. In State-A moving R
  326. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  327. predict error 0
  328. dir: dir isU
  329. /|\44: O: O88 (predict-no)
  330. I see 1 and I'm going to do: predict-no
  331. ENV: Agent did: predict-no for direction U in state State-B
  332. In State-B moving U
  333. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  334. predict error 0
  335. dir: dir isU
  336. -45: O: O90 (predict-no)
  337. I see 1 and I'm going to do: predict-no
  338. ENV: Agent did: predict-no for direction U in state State-B
  339. In State-B moving U
  340. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  341. predict error 0
  342. dir: dir isL
  343. /|\-46: O: O92 (predict-no)
  344. I see 1 and I'm going to do: predict-no
  345. ENV: Agent did: predict-no for direction L in state State-B
  346. In State-B moving L
  347. ENV: (next state, see, prediction correct?) = (State-A, 1, False)
  348. predict error 1
  349. dir: dir isU
  350. /|47: O: O94 (predict-no)
  351. I see 0 and I'm going to do: predict-no
  352. ENV: Agent did: predict-no for direction U in state State-A
  353. In State-A moving U
  354. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  355. predict error 0
  356. dir: dir isU
  357. \-48: O: O96 (predict-no)
  358. I see 1 and I'm going to do: predict-no
  359. ENV: Agent did: predict-no for direction U in state State-A
  360. In State-A moving U
  361. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  362. predict error 0
  363. dir: dir isR
  364. /|49: O: O97 (predict-yes)
  365. I see 1 and I'm going to do: predict-yes
  366. ENV: Agent did: predict-yes for direction R in state State-A
  367. In State-A moving R
  368. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  369. predict error 0
  370. dir: dir isR
  371. \-/50: O: O99 (predict-yes)
  372. I see 1 and I'm going to do: predict-yes
  373. ENV: Agent did: predict-yes for direction R in state State-B
  374. In State-B moving R
  375. ENV: (next state, see, prediction correct?) = (State-B, 0, False)
  376. predict error 1
  377. dir: dir isR
  378. |\-/|\-sleeping...
  379. /51: O: O101 (predict-yes)
  380. I see 0 and I'm going to do: predict-yes
  381. ENV: Agent did: predict-yes for direction R in state State-B
  382. In State-B moving R
  383. ENV: (next state, see, prediction correct?) = (State-B, 0, False)
  384. predict error 1
  385. dir: dir isU
  386. rule alias: '*'
  387. |52: O: O104 (predict-no)
  388. I see 0 and I'm going to do: predict-no
  389. ENV: Agent did: predict-no for direction U in state State-B
  390. In State-B moving U
  391. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  392. predict error 0
  393. dir: dir isR
  394. \-/53: O: O105 (predict-yes)
  395. I see 1 and I'm going to do: predict-yes
  396. ENV: Agent did: predict-yes for direction R in state State-B
  397. In State-B moving R
  398. ENV: (next state, see, prediction correct?) = (State-B, 0, False)
  399. predict error 1
  400. dir: dir isU
  401. |\-54: O: O108 (predict-no)
  402. I see 0 and I'm going to do: predict-no
  403. ENV: Agent did: predict-no for direction U in state State-B
  404. In State-B moving U
  405. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  406. predict error 0
  407. dir: dir isR
  408. /|55: O: O109 (predict-yes)
  409. I see 1 and I'm going to do: predict-yes
  410. ENV: Agent did: predict-yes for direction R in state State-B
  411. In State-B moving R
  412. ENV: (next state, see, prediction correct?) = (State-B, 0, False)
  413. predict error 1
  414. dir: dir isU
  415. \-56: O: O112 (predict-no)
  416. I see 0 and I'm going to do: predict-no
  417. ENV: Agent did: predict-no for direction U in state State-B
  418. In State-B moving U
  419. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  420. predict error 0
  421. dir: dir isU
  422. /|\57: O: O114 (predict-no)
  423. I see 1 and I'm going to do: predict-no
  424. ENV: Agent did: predict-no for direction U in state State-B
  425. In State-B moving U
  426. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  427. predict error 0
  428. dir: dir isR
  429. -/|58: O: O115 (predict-yes)
  430. I see 1 and I'm going to do: predict-yes
  431. ENV: Agent did: predict-yes for direction R in state State-B
  432. In State-B moving R
  433. ENV: (next state, see, prediction correct?) = (State-B, 0, False)
  434. predict error 1
  435. dir: dir isR
  436. \-59: O: O117 (predict-yes)
  437. I see 0 and I'm going to do: predict-yes
  438. ENV: Agent did: predict-yes for direction R in state State-B
  439. In State-B moving R
  440. ENV: (next state, see, prediction correct?) = (State-B, 0, False)
  441. predict error 1
  442. dir: dir isU
  443. /|60: O: O120 (predict-no)
  444. I see 0 and I'm going to do: predict-no
  445. ENV: Agent did: predict-no for direction U in state State-B
  446. In State-B moving U
  447. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  448. predict error 0
  449. dir: dir isU
  450. \-/61: O: O121 (predict-yes)
  451. I see 1 and I'm going to do: predict-yes
  452. ENV: Agent did: predict-yes for direction U in state State-B
  453. In State-B moving U
  454. ENV: (next state, see, prediction correct?) = (State-B, 0, False)
  455. predict error 1
  456. dir: dir isR
  457. |62: O: O123 (predict-yes)
  458. I see 0 and I'm going to do: predict-yes
  459. ENV: Agent did: predict-yes for direction R in state State-B
  460. In State-B moving R
  461. ENV: (next state, see, prediction correct?) = (State-B, 0, False)
  462. predict error 1
  463. dir: dir isL
  464. \-/|63: O: O126 (predict-no)
  465. I see 0 and I'm going to do: predict-no
  466. ENV: Agent did: predict-no for direction L in state State-B
  467. In State-B moving L
  468. ENV: (next state, see, prediction correct?) = (State-A, 1, False)
  469. predict error 1
  470. dir: dir isL
  471. \-/64: O: O128 (predict-no)
  472. I see 0 and I'm going to do: predict-no
  473. ENV: Agent did: predict-no for direction L in state State-A
  474. In State-A moving L
  475. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  476. predict error 0
  477. dir: dir isU
  478. |\-65: O: O130 (predict-no)
  479. I see 1 and I'm going to do: predict-no
  480. ENV: Agent did: predict-no for direction U in state State-A
  481. In State-A moving U
  482. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  483. predict error 0
  484. dir: dir isL
  485. /|66: O: O132 (predict-no)
  486. I see 1 and I'm going to do: predict-no
  487. ENV: Agent did: predict-no for direction L in state State-A
  488. In State-A moving L
  489. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  490. predict error 0
  491. dir: dir isU
  492. \-/67: O: O134 (predict-no)
  493. I see 1 and I'm going to do: predict-no
  494. ENV: Agent did: predict-no for direction U in state State-A
  495. In State-A moving U
  496. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  497. predict error 0
  498. dir: dir isL
  499. |\-68: O: O136 (predict-no)
  500. I see 1 and I'm going to do: predict-no
  501. ENV: Agent did: predict-no for direction L in state State-A
  502. In State-A moving L
  503. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  504. predict error 0
  505. dir: dir isU
  506. /|\69: O: O138 (predict-no)
  507. I see 1 and I'm going to do: predict-no
  508. ENV: Agent did: predict-no for direction U in state State-A
  509. In State-A moving U
  510. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  511. predict error 0
  512. dir: dir isL
  513. -/|\70: O: O140 (predict-no)
  514. I see 1 and I'm going to do: predict-no
  515. ENV: Agent did: predict-no for direction L in state State-A
  516. In State-A moving L
  517. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  518. predict error 0
  519. dir: dir isU
  520. -/|71: O: O142 (predict-no)
  521. I see 1 and I'm going to do: predict-no
  522. ENV: Agent did: predict-no for direction U in state State-A
  523. In State-A moving U
  524. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  525. predict error 0
  526. dir: dir isU
  527. rule alias: '*'
  528. rule alias: '*'
  529. rule alias: '*'
  530. rule alias: '*'
  531. rule alias: '*'
  532. rule alias: '*'
  533. \72: O: O144 (predict-no)
  534. I see 1 and I'm going to do: predict-no
  535. ENV: Agent did: predict-no for direction U in state State-A
  536. In State-A moving U
  537. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  538. predict error 0
  539. dir: dir isR
  540. -/|73: O: O145 (predict-yes)
  541. I see 1 and I'm going to do: predict-yes
  542. ENV: Agent did: predict-yes for direction R in state State-A
  543. In State-A moving R
  544. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  545. predict error 0
  546. dir: dir isR
  547. \-/|74: O: O147 (predict-yes)
  548. I see 1 and I'm going to do: predict-yes
  549. ENV: Agent did: predict-yes for direction R in state State-B
  550. In State-B moving R
  551. ENV: (next state, see, prediction correct?) = (State-B, 0, False)
  552. predict error 1
  553. dir: dir isR
  554. \-/75: O: O149 (predict-yes)
  555. I see 0 and I'm going to do: predict-yes
  556. ENV: Agent did: predict-yes for direction R in state State-B
  557. In State-B moving R
  558. ENV: (next state, see, prediction correct?) = (State-B, 0, False)
  559. predict error 1
  560. dir: dir isR
  561. |\76: O: O151 (predict-yes)
  562. I see 0 and I'm going to do: predict-yes
  563. ENV: Agent did: predict-yes for direction R in state State-B
  564. In State-B moving R
  565. ENV: (next state, see, prediction correct?) = (State-B, 0, False)
  566. predict error 1
  567. dir: dir isL
  568. -/|77: O: O154 (predict-no)
  569. I see 0 and I'm going to do: predict-no
  570. ENV: Agent did: predict-no for direction L in state State-B
  571. In State-B moving L
  572. ENV: (next state, see, prediction correct?) = (State-A, 1, False)
  573. predict error 1
  574. dir: dir isL
  575. \-/78: O: O156 (predict-no)
  576. I see 0 and I'm going to do: predict-no
  577. ENV: Agent did: predict-no for direction L in state State-A
  578. In State-A moving L
  579. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  580. predict error 0
  581. dir: dir isR
  582. |\79: O: O157 (predict-yes)
  583. I see 1 and I'm going to do: predict-yes
  584. ENV: Agent did: predict-yes for direction R in state State-A
  585. In State-A moving R
  586. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  587. predict error 0
  588. dir: dir isU
  589. -/|80: O: O160 (predict-no)
  590. I see 1 and I'm going to do: predict-no
  591. ENV: Agent did: predict-no for direction U in state State-B
  592. In State-B moving U
  593. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  594. predict error 0
  595. dir: dir isR
  596. \-81: O: O161 (predict-yes)
  597. I see 1 and I'm going to do: predict-yes
  598. ENV: Agent did: predict-yes for direction R in state State-B
  599. In State-B moving R
  600. ENV: (next state, see, prediction correct?) = (State-B, 0, False)
  601. predict error 1
  602. dir: dir isL
  603. rule alias: '*'
  604. rule alias: '*'
  605. /82: O: O164 (predict-no)
  606. I see 0 and I'm going to do: predict-no
  607. ENV: Agent did: predict-no for direction L in state State-B
  608. In State-B moving L
  609. ENV: (next state, see, prediction correct?) = (State-A, 1, False)
  610. predict error 1
  611. dir: dir isU
  612. |\-83: O: O165 (predict-yes)
  613. I see 0 and I'm going to do: predict-yes
  614. ENV: Agent did: predict-yes for direction U in state State-A
  615. In State-A moving U
  616. ENV: (next state, see, prediction correct?) = (State-A, 0, False)
  617. predict error 1
  618. dir: dir isU
  619. /|\84: O: O168 (predict-no)
  620. I see 0 and I'm going to do: predict-no
  621. ENV: Agent did: predict-no for direction U in state State-A
  622. In State-A moving U
  623. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  624. predict error 0
  625. dir: dir isU
  626. -/85: O: O169 (predict-yes)
  627. I see 1 and I'm going to do: predict-yes
  628. ENV: Agent did: predict-yes for direction U in state State-A
  629. In State-A moving U
  630. ENV: (next state, see, prediction correct?) = (State-A, 0, False)
  631. predict error 1
  632. dir: dir isL
  633. |\86: O: O172 (predict-no)
  634. I see 0 and I'm going to do: predict-no
  635. ENV: Agent did: predict-no for direction L in state State-A
  636. In State-A moving L
  637. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  638. predict error 0
  639. dir: dir isU
  640. -/87: O: O174 (predict-no)
  641. I see 1 and I'm going to do: predict-no
  642. ENV: Agent did: predict-no for direction U in state State-A
  643. In State-A moving U
  644. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  645. predict error 0
  646. dir: dir isL
  647. |\88: O: O176 (predict-no)
  648. I see 1 and I'm going to do: predict-no
  649. ENV: Agent did: predict-no for direction L in state State-A
  650. In State-A moving L
  651. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  652. predict error 0
  653. dir: dir isR
  654. -/|89: O: O177 (predict-yes)
  655. I see 1 and I'm going to do: predict-yes
  656. ENV: Agent did: predict-yes for direction R in state State-A
  657. In State-A moving R
  658. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  659. predict error 0
  660. dir: dir isL
  661. \-/90: O: O180 (predict-no)
  662. I see 1 and I'm going to do: predict-no
  663. ENV: Agent did: predict-no for direction L in state State-B
  664. In State-B moving L
  665. ENV: (next state, see, prediction correct?) = (State-A, 1, False)
  666. predict error 1
  667. dir: dir isL
  668. |\91: O: O182 (predict-no)
  669. I see 0 and I'm going to do: predict-no
  670. ENV: Agent did: predict-no for direction L in state State-A
  671. In State-A moving L
  672. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  673. predict error 0
  674. dir: dir isU
  675. rule alias: '*'
  676. rule alias: '*'
  677. -92: O: O184 (predict-no)
  678. I see 1 and I'm going to do: predict-no
  679. ENV: Agent did: predict-no for direction U in state State-A
  680. In State-A moving U
  681. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  682. predict error 0
  683. dir: dir isL
  684. /|\93: O: O186 (predict-no)
  685. I see 1 and I'm going to do: predict-no
  686. ENV: Agent did: predict-no for direction L in state State-A
  687. In State-A moving L
  688. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  689. predict error 0
  690. dir: dir isR
  691. -/|94: O: O187 (predict-yes)
  692. I see 1 and I'm going to do: predict-yes
  693. ENV: Agent did: predict-yes for direction R in state State-A
  694. In State-A moving R
  695. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  696. predict error 0
  697. dir: dir isU
  698. \-/95: O: O190 (predict-no)
  699. I see 1 and I'm going to do: predict-no
  700. ENV: Agent did: predict-no for direction U in state State-B
  701. In State-B moving U
  702. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  703. predict error 0
  704. dir: dir isL
  705. |96: O: O192 (predict-no)
  706. I see 1 and I'm going to do: predict-no
  707. ENV: Agent did: predict-no for direction L in state State-B
  708. In State-B moving L
  709. ENV: (next state, see, prediction correct?) = (State-A, 1, False)
  710. predict error 1
  711. dir: dir isL
  712. \-/97: O: O194 (predict-no)
  713. I see 0 and I'm going to do: predict-no
  714. ENV: Agent did: predict-no for direction L in state State-A
  715. In State-A moving L
  716. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  717. predict error 0
  718. dir: dir isU
  719. |\98: O: O196 (predict-no)
  720. I see 1 and I'm going to do: predict-no
  721. ENV: Agent did: predict-no for direction U in state State-A
  722. In State-A moving U
  723. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  724. predict error 0
  725. dir: dir isR
  726. -/|99: O: O197 (predict-yes)
  727. I see 1 and I'm going to do: predict-yes
  728. ENV: Agent did: predict-yes for direction R in state State-A
  729. In State-A moving R
  730. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  731. predict error 0
  732. dir: dir isU
  733. \-/100: O: O200 (predict-no)
  734. I see 1 and I'm going to do: predict-no
  735. ENV: Agent did: predict-no for direction U in state State-B
  736. In State-B moving U
  737. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  738. predict error 0
  739. dir: dir isL
  740. |\-101: O: O202 (predict-no)
  741. I see 1 and I'm going to do: predict-no
  742. ENV: Agent did: predict-no for direction L in state State-B
  743. In State-B moving L
  744. ENV: (next state, see, prediction correct?) = (State-A, 1, False)
  745. predict error 1
  746. dir: dir isR
  747. /|102: O: O203 (predict-yes)
  748. I see 0 and I'm going to do: predict-yes
  749. ENV: Agent did: predict-yes for direction R in state State-A
  750. In State-A moving R
  751. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  752. predict error 0
  753. dir: dir isL
  754. \-/103: O: O206 (predict-no)
  755. I see 1 and I'm going to do: predict-no
  756. ENV: Agent did: predict-no for direction L in state State-B
  757. In State-B moving L
  758. ENV: (next state, see, prediction correct?) = (State-A, 1, False)
  759. predict error 1
  760. dir: dir isU
  761. |\104: O: O208 (predict-no)
  762. I see 0 and I'm going to do: predict-no
  763. ENV: Agent did: predict-no for direction U in state State-A
  764. In State-A moving U
  765. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  766. predict error 0
  767. dir: dir isL
  768. -/|105: O: O210 (predict-no)
  769. I see 1 and I'm going to do: predict-no
  770. ENV: Agent did: predict-no for direction L in state State-A
  771. In State-A moving L
  772. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  773. predict error 0
  774. dir: dir isU
  775. \-/106: O: O212 (predict-no)
  776. I see 1 and I'm going to do: predict-no
  777. ENV: Agent did: predict-no for direction U in state State-A
  778. In State-A moving U
  779. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  780. predict error 0
  781. dir: dir isL
  782. |\107: O: O214 (predict-no)
  783. I see 1 and I'm going to do: predict-no
  784. ENV: Agent did: predict-no for direction L in state State-A
  785. In State-A moving L
  786. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  787. predict error 0
  788. dir: dir isU
  789. -/|108: O: O216 (predict-no)
  790. I see 1 and I'm going to do: predict-no
  791. ENV: Agent did: predict-no for direction U in state State-A
  792. In State-A moving U
  793. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  794. predict error 0
  795. dir: dir isL
  796. \-109: O: O218 (predict-no)
  797. I see 1 and I'm going to do: predict-no
  798. ENV: Agent did: predict-no for direction L in state State-A
  799. In State-A moving L
  800. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  801. predict error 0
  802. dir: dir isL
  803. /|110: O: O220 (predict-no)
  804. I see 1 and I'm going to do: predict-no
  805. ENV: Agent did: predict-no for direction L in state State-A
  806. In State-A moving L
  807. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  808. predict error 0
  809. dir: dir isU
  810. \-/|111: O: O222 (predict-no)
  811. I see 1 and I'm going to do: predict-no
  812. ENV: Agent did: predict-no for direction U in state State-A
  813. In State-A moving U
  814. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  815. predict error 0
  816. dir: dir isL
  817. rule alias: '*'
  818. \112: O: O224 (predict-no)
  819. I see 1 and I'm going to do: predict-no
  820. ENV: Agent did: predict-no for direction L in state State-A
  821. In State-A moving L
  822. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  823. predict error 0
  824. dir: dir isL
  825. -/|113: O: O226 (predict-no)
  826. I see 1 and I'm going to do: predict-no
  827. ENV: Agent did: predict-no for direction L in state State-A
  828. In State-A moving L
  829. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  830. predict error 0
  831. dir: dir isU
  832. \-/114: O: O228 (predict-no)
  833. I see 1 and I'm going to do: predict-no
  834. ENV: Agent did: predict-no for direction U in state State-A
  835. In State-A moving U
  836. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  837. predict error 0
  838. dir: dir isR
  839. |\115: O: O229 (predict-yes)
  840. I see 1 and I'm going to do: predict-yes
  841. ENV: Agent did: predict-yes for direction R in state State-A
  842. In State-A moving R
  843. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  844. predict error 0
  845. dir: dir isL
  846. -/116: O: O232 (predict-no)
  847. I see 1 and I'm going to do: predict-no
  848. ENV: Agent did: predict-no for direction L in state State-B
  849. In State-B moving L
  850. ENV: (next state, see, prediction correct?) = (State-A, 1, False)
  851. predict error 1
  852. dir: dir isU
  853. |\-117: O: O234 (predict-no)
  854. I see 0 and I'm going to do: predict-no
  855. ENV: Agent did: predict-no for direction U in state State-A
  856. In State-A moving U
  857. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  858. predict error 0
  859. dir: dir isL
  860. /|118: O: O236 (predict-no)
  861. I see 1 and I'm going to do: predict-no
  862. ENV: Agent did: predict-no for direction L in state State-A
  863. In State-A moving L
  864. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  865. predict error 0
  866. dir: dir isL
  867. \-/119: O: O238 (predict-no)
  868. I see 1 and I'm going to do: predict-no
  869. ENV: Agent did: predict-no for direction L in state State-A
  870. In State-A moving L
  871. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  872. predict error 0
  873. dir: dir isR
  874. |\-120: O: O240 (predict-no)
  875. I see 1 and I'm going to do: predict-no
  876. ENV: Agent did: predict-no for direction R in state State-A
  877. In State-A moving R
  878. ENV: (next state, see, prediction correct?) = (State-B, 1, False)
  879. predict error 1
  880. dir: dir isR
  881. /|121: O: O241 (predict-yes)
  882. I see 0 and I'm going to do: predict-yes
  883. ENV: Agent did: predict-yes for direction R in state State-B
  884. In State-B moving R
  885. ENV: (next state, see, prediction correct?) = (State-B, 0, False)
  886. predict error 1
  887. dir: dir isU
  888. \122: O: O244 (predict-no)
  889. I see 0 and I'm going to do: predict-no
  890. ENV: Agent did: predict-no for direction U in state State-B
  891. In State-B moving U
  892. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  893. predict error 0
  894. dir: dir isL
  895. -/123: O: O246 (predict-no)
  896. I see 1 and I'm going to do: predict-no
  897. ENV: Agent did: predict-no for direction L in state State-B
  898. In State-B moving L
  899. ENV: (next state, see, prediction correct?) = (State-A, 1, False)
  900. predict error 1
  901. dir: dir isR
  902. |\-124: O: O247 (predict-yes)
  903. I see 0 and I'm going to do: predict-yes
  904. ENV: Agent did: predict-yes for direction R in state State-A
  905. In State-A moving R
  906. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  907. predict error 0
  908. dir: dir isL
  909. /|\125: O: O250 (predict-no)
  910. I see 1 and I'm going to do: predict-no
  911. ENV: Agent did: predict-no for direction L in state State-B
  912. In State-B moving L
  913. ENV: (next state, see, prediction correct?) = (State-A, 1, False)
  914. predict error 1
  915. dir: dir isR
  916. -/126: O: O251 (predict-yes)
  917. I see 0 and I'm going to do: predict-yes
  918. ENV: Agent did: predict-yes for direction R in state State-A
  919. In State-A moving R
  920. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  921. predict error 0
  922. dir: dir isU
  923. |127: O: O254 (predict-no)
  924. I see 1 and I'm going to do: predict-no
  925. ENV: Agent did: predict-no for direction U in state State-B
  926. In State-B moving U
  927. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  928. predict error 0
  929. dir: dir isU
  930. \-/128: O: O255 (predict-yes)
  931. I see 1 and I'm going to do: predict-yes
  932. ENV: Agent did: predict-yes for direction U in state State-B
  933. In State-B moving U
  934. ENV: (next state, see, prediction correct?) = (State-B, 0, False)
  935. predict error 1
  936. dir: dir isU
  937. |129: O: O258 (predict-no)
  938. I see 0 and I'm going to do: predict-no
  939. ENV: Agent did: predict-no for direction U in state State-B
  940. In State-B moving U
  941. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  942. predict error 0
  943. dir: dir isU
  944. \130: O: O260 (predict-no)
  945. I see 1 and I'm going to do: predict-no
  946. ENV: Agent did: predict-no for direction U in state State-B
  947. In State-B moving U
  948. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  949. predict error 0
  950. dir: dir isU
  951. -/|131: O: O262 (predict-no)
  952. I see 1 and I'm going to do: predict-no
  953. ENV: Agent did: predict-no for direction U in state State-B
  954. In State-B moving U
  955. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  956. predict error 0
  957. dir: dir isU
  958. \132: O: O264 (predict-no)
  959. I see 1 and I'm going to do: predict-no
  960. ENV: Agent did: predict-no for direction U in state State-B
  961. In State-B moving U
  962. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  963. predict error 0
  964. dir: dir isR
  965. -/|133: O: O265 (predict-yes)
  966. I see 1 and I'm going to do: predict-yes
  967. ENV: Agent did: predict-yes for direction R in state State-B
  968. In State-B moving R
  969. ENV: (next state, see, prediction correct?) = (State-B, 0, False)
  970. predict error 1
  971. dir: dir isL
  972. \-/|134: O: O268 (predict-no)
  973. I see 0 and I'm going to do: predict-no
  974. ENV: Agent did: predict-no for direction L in state State-B
  975. In State-B moving L
  976. ENV: (next state, see, prediction correct?) = (State-A, 1, False)
  977. predict error 1
  978. dir: dir isR
  979. \-135: O: O269 (predict-yes)
  980. I see 0 and I'm going to do: predict-yes
  981. ENV: Agent did: predict-yes for direction R in state State-A
  982. In State-A moving R
  983. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  984. predict error 0
  985. dir: dir isL
  986. /|\136: O: O271 (predict-yes)
  987. I see 1 and I'm going to do: predict-yes
  988. ENV: Agent did: predict-yes for direction L in state State-B
  989. In State-B moving L
  990. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  991. predict error 0
  992. dir: dir isL
  993. -/|137: O: O274 (predict-no)
  994. I see 1 and I'm going to do: predict-no
  995. ENV: Agent did: predict-no for direction L in state State-A
  996. In State-A moving L
  997. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  998. predict error 0
  999. dir: dir isR
  1000. \-/138: O: O275 (predict-yes)
  1001. I see 1 and I'm going to do: predict-yes
  1002. ENV: Agent did: predict-yes for direction R in state State-A
  1003. In State-A moving R
  1004. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  1005. predict error 0
  1006. dir: dir isU
  1007. |\139: O: O278 (predict-no)
  1008. I see 1 and I'm going to do: predict-no
  1009. ENV: Agent did: predict-no for direction U in state State-B
  1010. In State-B moving U
  1011. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  1012. predict error 0
  1013. dir: dir isL
  1014. -/|140: O: O279 (predict-yes)
  1015. I see 1 and I'm going to do: predict-yes
  1016. ENV: Agent did: predict-yes for direction L in state State-B
  1017. In State-B moving L
  1018. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  1019. predict error 0
  1020. dir: dir isR
  1021. \-/141: O: O281 (predict-yes)
  1022. I see 1 and I'm going to do: predict-yes
  1023. ENV: Agent did: predict-yes for direction R in state State-A
  1024. In State-A moving R
  1025. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  1026. predict error 0
  1027. dir: dir isR
  1028. |142: O: O283 (predict-yes)
  1029. I see 1 and I'm going to do: predict-yes
  1030. ENV: Agent did: predict-yes for direction R in state State-B
  1031. In State-B moving R
  1032. ENV: (next state, see, prediction correct?) = (State-B, 0, False)
  1033. predict error 1
  1034. dir: dir isR
  1035. \-/143: O: O286 (predict-no)
  1036. I see 0 and I'm going to do: predict-no
  1037. ENV: Agent did: predict-no for direction R in state State-B
  1038. In State-B moving R
  1039. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  1040. predict error 0
  1041. dir: dir isL
  1042. |\144: O: O287 (predict-yes)
  1043. I see 1 and I'm going to do: predict-yes
  1044. ENV: Agent did: predict-yes for direction L in state State-B
  1045. In State-B moving L
  1046. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  1047. predict error 0
  1048. dir: dir isU
  1049. -/145: O: O290 (predict-no)
  1050. I see 1 and I'm going to do: predict-no
  1051. ENV: Agent did: predict-no for direction U in state State-A
  1052. In State-A moving U
  1053. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  1054. predict error 0
  1055. dir: dir isL
  1056. |\-146: O: O292 (predict-no)
  1057. I see 1 and I'm going to do: predict-no
  1058. ENV: Agent did: predict-no for direction L in state State-A
  1059. In State-A moving L
  1060. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  1061. predict error 0
  1062. dir: dir isR
  1063. /|\147: O: O293 (predict-yes)
  1064. I see 1 and I'm going to do: predict-yes
  1065. ENV: Agent did: predict-yes for direction R in state State-A
  1066. In State-A moving R
  1067. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  1068. predict error 0
  1069. dir: dir isR
  1070. -/|148: O: O296 (predict-no)
  1071. I see 1 and I'm going to do: predict-no
  1072. ENV: Agent did: predict-no for direction R in state State-B
  1073. In State-B moving R
  1074. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  1075. predict error 0
  1076. dir: dir isL
  1077. \149: O: O297 (predict-yes)
  1078. I see 1 and I'm going to do: predict-yes
  1079. ENV: Agent did: predict-yes for direction L in state State-B
  1080. In State-B moving L
  1081. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  1082. predict error 0
  1083. dir: dir isR
  1084. -/|150: O: O299 (predict-yes)
  1085. I see 1 and I'm going to do: predict-yes
  1086. ENV: Agent did: predict-yes for direction R in state State-A
  1087. In State-A moving R
  1088. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  1089. predict error 0
  1090. dir: dir isL
  1091. \-/151: O: O301 (predict-yes)
  1092. I see 1 and I'm going to do: predict-yes
  1093. ENV: Agent did: predict-yes for direction L in state State-B
  1094. In State-B moving L
  1095. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  1096. predict error 0
  1097. dir: dir isL
  1098. rule alias: '*'
  1099. rule alias: '*'
  1100. rule alias: '*'
  1101. |152: O: O304 (predict-no)
  1102. I see 1 and I'm going to do: predict-no
  1103. ENV: Agent did: predict-no for direction L in state State-A
  1104. In State-A moving L
  1105. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  1106. predict error 0
  1107. dir: dir isL
  1108. \153: O: O306 (predict-no)
  1109. I see 1 and I'm going to do: predict-no
  1110. ENV: Agent did: predict-no for direction L in state State-A
  1111. In State-A moving L
  1112. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  1113. predict error 0
  1114. dir: dir isL
  1115. -/154: O: O308 (predict-no)
  1116. I see 1 and I'm going to do: predict-no
  1117. ENV: Agent did: predict-no for direction L in state State-A
  1118. In State-A moving L
  1119. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  1120. predict error 0
  1121. dir: dir isL
  1122. |\-155: O: O310 (predict-no)
  1123. I see 1 and I'm going to do: predict-no
  1124. ENV: Agent did: predict-no for direction L in state State-A
  1125. In State-A moving L
  1126. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  1127. predict error 0
  1128. dir: dir isR
  1129. /|156: O: O311 (predict-yes)
  1130. I see 1 and I'm going to do: predict-yes
  1131. ENV: Agent did: predict-yes for direction R in state State-A
  1132. In State-A moving R
  1133. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  1134. predict error 0
  1135. dir: dir isR
  1136. \-/|157: O: O314 (predict-no)
  1137. I see 1 and I'm going to do: predict-no
  1138. ENV: Agent did: predict-no for direction R in state State-B
  1139. In State-B moving R
  1140. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  1141. predict error 0
  1142. dir: dir isU
  1143. \-/158: O: O316 (predict-no)
  1144. I see 1 and I'm going to do: predict-no
  1145. ENV: Agent did: predict-no for direction U in state State-B
  1146. In State-B moving U
  1147. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  1148. predict error 0
  1149. dir: dir isU
  1150. |\159: O: O318 (predict-no)
  1151. I see 1 and I'm going to do: predict-no
  1152. ENV: Agent did: predict-no for direction U in state State-B
  1153. In State-B moving U
  1154. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  1155. predict error 0
  1156. dir: dir isU
  1157. -/|160: O: O320 (predict-no)
  1158. I see 1 and I'm going to do: predict-no
  1159. ENV: Agent did: predict-no for direction U in state State-B
  1160. In State-B moving U
  1161. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  1162. predict error 0
  1163. dir: dir isL
  1164. \-/161: O: O321 (predict-yes)
  1165. I see 1 and I'm going to do: predict-yes
  1166. ENV: Agent did: predict-yes for direction L in state State-B
  1167. In State-B moving L
  1168. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  1169. predict error 0
  1170. dir: dir isR
  1171. |162: O: O323 (predict-yes)
  1172. I see 1 and I'm going to do: predict-yes
  1173. ENV: Agent did: predict-yes for direction R in state State-A
  1174. In State-A moving R
  1175. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  1176. predict error 0
  1177. dir: dir isL
  1178. \-163: O: O325 (predict-yes)
  1179. I see 1 and I'm going to do: predict-yes
  1180. ENV: Agent did: predict-yes for direction L in state State-B
  1181. In State-B moving L
  1182. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  1183. predict error 0
  1184. dir: dir isR
  1185. /|\-164: O: O327 (predict-yes)
  1186. I see 1 and I'm going to do: predict-yes
  1187. ENV: Agent did: predict-yes for direction R in state State-A
  1188. In State-A moving R
  1189. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  1190. predict error 0
  1191. dir: dir isR
  1192. /|\165: O: O330 (predict-no)
  1193. I see 1 and I'm going to do: predict-no
  1194. ENV: Agent did: predict-no for direction R in state State-B
  1195. In State-B moving R
  1196. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  1197. predict error 0
  1198. dir: dir isU
  1199. -/166: O: O332 (predict-no)
  1200. I see 1 and I'm going to do: predict-no
  1201. ENV: Agent did: predict-no for direction U in state State-B
  1202. In State-B moving U
  1203. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  1204. predict error 0
  1205. dir: dir isU
  1206. |\-/167: O: O334 (predict-no)
  1207. I see 1 and I'm going to do: predict-no
  1208. ENV: Agent did: predict-no for direction U in state State-B
  1209. In State-B moving U
  1210. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  1211. predict error 0
  1212. dir: dir isL
  1213. |\168: O: O335 (predict-yes)
  1214. I see 1 and I'm going to do: predict-yes
  1215. ENV: Agent did: predict-yes for direction L in state State-B
  1216. In State-B moving L
  1217. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  1218. predict error 0
  1219. dir: dir isR
  1220. -/|169: O: O337 (predict-yes)
  1221. I see 1 and I'm going to do: predict-yes
  1222. ENV: Agent did: predict-yes for direction R in state State-A
  1223. In State-A moving R
  1224. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  1225. predict error 0
  1226. dir: dir isR
  1227. \-/170: O: O340 (predict-no)
  1228. I see 1 and I'm going to do: predict-no
  1229. ENV: Agent did: predict-no for direction R in state State-B
  1230. In State-B moving R
  1231. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  1232. predict error 0
  1233. dir: dir isL
  1234. |\171: O: O341 (predict-yes)
  1235. I see 1 and I'm going to do: predict-yes
  1236. ENV: Agent did: predict-yes for direction L in state State-B
  1237. In State-B moving L
  1238. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  1239. predict error 0
  1240. dir: dir isL
  1241. -172: O: O344 (predict-no)
  1242. I see 1 and I'm going to do: predict-no
  1243. ENV: Agent did: predict-no for direction L in state State-A
  1244. In State-A moving L
  1245. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  1246. predict error 0
  1247. dir: dir isR
  1248. /|173: O: O345 (predict-yes)
  1249. I see 1 and I'm going to do: predict-yes
  1250. ENV: Agent did: predict-yes for direction R in state State-A
  1251. In State-A moving R
  1252. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  1253. predict error 0
  1254. dir: dir isL
  1255. \-174: O: O347 (predict-yes)
  1256. I see 1 and I'm going to do: predict-yes
  1257. ENV: Agent did: predict-yes for direction L in state State-B
  1258. In State-B moving L
  1259. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  1260. predict error 0
  1261. dir: dir isU
  1262. /|\175: O: O350 (predict-no)
  1263. I see 1 and I'm going to do: predict-no
  1264. ENV: Agent did: predict-no for direction U in state State-A
  1265. In State-A moving U
  1266. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  1267. predict error 0
  1268. dir: dir isL
  1269. -/|\176: O: O352 (predict-no)
  1270. I see 1 and I'm going to do: predict-no
  1271. ENV: Agent did: predict-no for direction L in state State-A
  1272. In State-A moving L
  1273. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  1274. predict error 0
  1275. dir: dir isL
  1276. -/|177: O: O354 (predict-no)
  1277. I see 1 and I'm going to do: predict-no
  1278. ENV: Agent did: predict-no for direction L in state State-A
  1279. In State-A moving L
  1280. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  1281. predict error 0
  1282. dir: dir isL
  1283. \-178: O: O356 (predict-no)
  1284. I see 1 and I'm going to do: predict-no
  1285. ENV: Agent did: predict-no for direction L in state State-A
  1286. In State-A moving L
  1287. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  1288. predict error 0
  1289. dir: dir isL
  1290. /179: O: O358 (predict-no)
  1291. I see 1 and I'm going to do: predict-no
  1292. ENV: Agent did: predict-no for direction L in state State-A
  1293. In State-A moving L
  1294. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  1295. predict error 0
  1296. dir: dir isL
  1297. |\-180: O: O360 (predict-no)
  1298. I see 1 and I'm going to do: predict-no
  1299. ENV: Agent did: predict-no for direction L in state State-A
  1300. In State-A moving L
  1301. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  1302. predict error 0
  1303. dir: dir isR
  1304. /|\181: O: O361 (predict-yes)
  1305. I see 1 and I'm going to do: predict-yes
  1306. ENV: Agent did: predict-yes for direction R in state State-A
  1307. In State-A moving R
  1308. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  1309. predict error 0
  1310. dir: dir isR
  1311. -182: O: O364 (predict-no)
  1312. I see 1 and I'm going to do: predict-no
  1313. ENV: Agent did: predict-no for direction R in state State-B
  1314. In State-B moving R
  1315. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  1316. predict error 0
  1317. dir: dir isL
  1318. /|183: O: O365 (predict-yes)
  1319. I see 1 and I'm going to do: predict-yes
  1320. ENV: Agent did: predict-yes for direction L in state State-B
  1321. In State-B moving L
  1322. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  1323. predict error 0
  1324. dir: dir isR
  1325. \-/184: O: O367 (predict-yes)
  1326. I see 1 and I'm going to do: predict-yes
  1327. ENV: Agent did: predict-yes for direction R in state State-A
  1328. In State-A moving R
  1329. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  1330. predict error 0
  1331. dir: dir isL
  1332. |\185: O: O369 (predict-yes)
  1333. I see 1 and I'm going to do: predict-yes
  1334. ENV: Agent did: predict-yes for direction L in state State-B
  1335. In State-B moving L
  1336. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  1337. predict error 0
  1338. dir: dir isU
  1339. -/|186: O: O372 (predict-no)
  1340. I see 1 and I'm going to do: predict-no
  1341. ENV: Agent did: predict-no for direction U in state State-A
  1342. In State-A moving U
  1343. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  1344. predict error 0
  1345. dir: dir isU
  1346. \-187: O: O374 (predict-no)
  1347. I see 1 and I'm going to do: predict-no
  1348. ENV: Agent did: predict-no for direction U in state State-A
  1349. In State-A moving U
  1350. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  1351. predict error 0
  1352. dir: dir isU
  1353. /|\188: O: O376 (predict-no)
  1354. I see 1 and I'm going to do: predict-no
  1355. ENV: Agent did: predict-no for direction U in state State-A
  1356. In State-A moving U
  1357. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  1358. predict error 0
  1359. dir: dir isR
  1360. -/|189: O: O378 (predict-no)
  1361. I see 1 and I'm going to do: predict-no
  1362. ENV: Agent did: predict-no for direction R in state State-A
  1363. In State-A moving R
  1364. ENV: (next state, see, prediction correct?) = (State-B, 1, False)
  1365. predict error 1
  1366. dir: dir isR
  1367. \-190: O: O380 (predict-no)
  1368. I see 0 and I'm going to do: predict-no
  1369. ENV: Agent did: predict-no for direction R in state State-B
  1370. In State-B moving R
  1371. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  1372. predict error 0
  1373. dir: dir isR
  1374. /|\191: O: O382 (predict-no)
  1375. I see 1 and I'm going to do: predict-no
  1376. ENV: Agent did: predict-no for direction R in state State-B
  1377. In State-B moving R
  1378. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  1379. predict error 0
  1380. dir: dir isL
  1381. rule alias: '*'
  1382. -192: O: O383 (predict-yes)
  1383. I see 1 and I'm going to do: predict-yes
  1384. ENV: Agent did: predict-yes for direction L in state State-B
  1385. In State-B moving L
  1386. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  1387. predict error 0
  1388. dir: dir isR
  1389. /|\193: O: O385 (predict-yes)
  1390. I see 1 and I'm going to do: predict-yes
  1391. ENV: Agent did: predict-yes for direction R in state State-A
  1392. In State-A moving R
  1393. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  1394. predict error 0
  1395. dir: dir isR
  1396. -/194: O: O388 (predict-no)
  1397. I see 1 and I'm going to do: predict-no
  1398. ENV: Agent did: predict-no for direction R in state State-B
  1399. In State-B moving R
  1400. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  1401. predict error 0
  1402. dir: dir isL
  1403. |\-195: O: O389 (predict-yes)
  1404. I see 1 and I'm going to do: predict-yes
  1405. ENV: Agent did: predict-yes for direction L in state State-B
  1406. In State-B moving L
  1407. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  1408. predict error 0
  1409. dir: dir isL
  1410. /|\196: O: O392 (predict-no)
  1411. I see 1 and I'm going to do: predict-no
  1412. ENV: Agent did: predict-no for direction L in state State-A
  1413. In State-A moving L
  1414. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  1415. predict error 0
  1416. dir: dir isU
  1417. -/|197: O: O394 (predict-no)
  1418. I see 1 and I'm going to do: predict-no
  1419. ENV: Agent did: predict-no for direction U in state State-A
  1420. In State-A moving U
  1421. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  1422. predict error 0
  1423. dir: dir isR
  1424. \-/198: O: O395 (predict-yes)
  1425. I see 1 and I'm going to do: predict-yes
  1426. ENV: Agent did: predict-yes for direction R in state State-A
  1427. In State-A moving R
  1428. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  1429. predict error 0
  1430. dir: dir isR
  1431. |\-199: O: O398 (predict-no)
  1432. I see 1 and I'm going to do: predict-no
  1433. ENV: Agent did: predict-no for direction R in state State-B
  1434. In State-B moving R
  1435. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  1436. predict error 0
  1437. dir: dir isU
  1438. /|200: O: O400 (predict-no)
  1439. I see 1 and I'm going to do: predict-no
  1440. ENV: Agent did: predict-no for direction U in state State-B
  1441. In State-B moving U
  1442. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  1443. predict error 0
  1444. dir: dir isR
  1445. \-/|\-/201: O: O402 (predict-no)
  1446. I see 1 and I'm going to do: predict-no
  1447. ENV: Agent did: predict-no for direction R in state State-B
  1448. In State-B moving R
  1449. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  1450. predict error 0
  1451. dir: dir isL
  1452. |202: O: O403 (predict-yes)
  1453. I see 1 and I'm going to do: predict-yes
  1454. ENV: Agent did: predict-yes for direction L in state State-B
  1455. In State-B moving L
  1456. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  1457. predict error 0
  1458. dir: dir isU
  1459. \-203: O: O406 (predict-no)
  1460. I see 1 and I'm going to do: predict-no
  1461. ENV: Agent did: predict-no for direction U in state State-A
  1462. In State-A moving U
  1463. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  1464. predict error 0
  1465. dir: dir isR
  1466. /|\204: O: O407 (predict-yes)
  1467. I see 1 and I'm going to do: predict-yes
  1468. ENV: Agent did: predict-yes for direction R in state State-A
  1469. In State-A moving R
  1470. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  1471. predict error 0
  1472. dir: dir isL
  1473. -/|205: O: O409 (predict-yes)
  1474. I see 1 and I'm going to do: predict-yes
  1475. ENV: Agent did: predict-yes for direction L in state State-B
  1476. In State-B moving L
  1477. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  1478. predict error 0
  1479. dir: dir isU
  1480. \-/206: O: O411 (predict-yes)
  1481. I see 1 and I'm going to do: predict-yes
  1482. ENV: Agent did: predict-yes for direction U in state State-A
  1483. In State-A moving U
  1484. ENV: (next state, see, prediction correct?) = (State-A, 0, False)
  1485. predict error 1
  1486. dir: dir isL
  1487. |\207: O: O414 (predict-no)
  1488. I see 0 and I'm going to do: predict-no
  1489. ENV: Agent did: predict-no for direction L in state State-A
  1490. In State-A moving L
  1491. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  1492. predict error 0
  1493. dir: dir isL
  1494. -/|208: O: O416 (predict-no)
  1495. I see 1 and I'm going to do: predict-no
  1496. ENV: Agent did: predict-no for direction L in state State-A
  1497. In State-A moving L
  1498. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  1499. predict error 0
  1500. dir: dir isU
  1501. \-209: O: O418 (predict-no)
  1502. I see 1 and I'm going to do: predict-no
  1503. ENV: Agent did: predict-no for direction U in state State-A
  1504. In State-A moving U
  1505. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  1506. predict error 0
  1507. dir: dir isU
  1508. /|\-210: O: O420 (predict-no)
  1509. I see 1 and I'm going to do: predict-no
  1510. ENV: Agent did: predict-no for direction U in state State-A
  1511. In State-A moving U
  1512. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  1513. predict error 0
  1514. dir: dir isL
  1515. /|211: O: O422 (predict-no)
  1516. I see 1 and I'm going to do: predict-no
  1517. ENV: Agent did: predict-no for direction L in state State-A
  1518. In State-A moving L
  1519. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  1520. predict error 0
  1521. dir: dir isR
  1522. \212: O: O423 (predict-yes)
  1523. I see 1 and I'm going to do: predict-yes
  1524. ENV: Agent did: predict-yes for direction R in state State-A
  1525. In State-A moving R
  1526. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  1527. predict error 0
  1528. dir: dir isR
  1529. -/213: O: O426 (predict-no)
  1530. I see 1 and I'm going to do: predict-no
  1531. ENV: Agent did: predict-no for direction R in state State-B
  1532. In State-B moving R
  1533. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  1534. predict error 0
  1535. dir: dir isR
  1536. |\-214: O: O428 (predict-no)
  1537. I see 1 and I'm going to do: predict-no
  1538. ENV: Agent did: predict-no for direction R in state State-B
  1539. In State-B moving R
  1540. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  1541. predict error 0
  1542. dir: dir isL
  1543. /|\215: O: O429 (predict-yes)
  1544. I see 1 and I'm going to do: predict-yes
  1545. ENV: Agent did: predict-yes for direction L in state State-B
  1546. In State-B moving L
  1547. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  1548. predict error 0
  1549. dir: dir isR
  1550. -/216: O: O431 (predict-yes)
  1551. I see 1 and I'm going to do: predict-yes
  1552. ENV: Agent did: predict-yes for direction R in state State-A
  1553. In State-A moving R
  1554. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  1555. predict error 0
  1556. dir: dir isL
  1557. |\217: O: O433 (predict-yes)
  1558. I see 1 and I'm going to do: predict-yes
  1559. ENV: Agent did: predict-yes for direction L in state State-B
  1560. In State-B moving L
  1561. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  1562. predict error 0
  1563. dir: dir isL
  1564. -/|218: O: O436 (predict-no)
  1565. I see 1 and I'm going to do: predict-no
  1566. ENV: Agent did: predict-no for direction L in state State-A
  1567. In State-A moving L
  1568. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  1569. predict error 0
  1570. dir: dir isR
  1571. \-/219: O: O437 (predict-yes)
  1572. I see 1 and I'm going to do: predict-yes
  1573. ENV: Agent did: predict-yes for direction R in state State-A
  1574. In State-A moving R
  1575. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  1576. predict error 0
  1577. dir: dir isU
  1578. |\-220: O: O440 (predict-no)
  1579. I see 1 and I'm going to do: predict-no
  1580. ENV: Agent did: predict-no for direction U in state State-B
  1581. In State-B moving U
  1582. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  1583. predict error 0
  1584. dir: dir isL
  1585. /|221: O: O441 (predict-yes)
  1586. I see 1 and I'm going to do: predict-yes
  1587. ENV: Agent did: predict-yes for direction L in state State-B
  1588. In State-B moving L
  1589. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  1590. predict error 0
  1591. dir: dir isU
  1592. \222: O: O444 (predict-no)
  1593. I see 1 and I'm going to do: predict-no
  1594. ENV: Agent did: predict-no for direction U in state State-A
  1595. In State-A moving U
  1596. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  1597. predict error 0
  1598. dir: dir isL
  1599. -/223: O: O446 (predict-no)
  1600. I see 1 and I'm going to do: predict-no
  1601. ENV: Agent did: predict-no for direction L in state State-A
  1602. In State-A moving L
  1603. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  1604. predict error 0
  1605. dir: dir isR
  1606. |\224: O: O447 (predict-yes)
  1607. I see 1 and I'm going to do: predict-yes
  1608. ENV: Agent did: predict-yes for direction R in state State-A
  1609. In State-A moving R
  1610. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  1611. predict error 0
  1612. dir: dir isR
  1613. -/225: O: O450 (predict-no)
  1614. I see 1 and I'm going to do: predict-no
  1615. ENV: Agent did: predict-no for direction R in state State-B
  1616. In State-B moving R
  1617. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  1618. predict error 0
  1619. dir: dir isR
  1620. |\226: O: O452 (predict-no)
  1621. I see 1 and I'm going to do: predict-no
  1622. ENV: Agent did: predict-no for direction R in state State-B
  1623. In State-B moving R
  1624. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  1625. predict error 0
  1626. dir: dir isU
  1627. -/227: O: O454 (predict-no)
  1628. I see 1 and I'm going to do: predict-no
  1629. ENV: Agent did: predict-no for direction U in state State-B
  1630. In State-B moving U
  1631. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  1632. predict error 0
  1633. dir: dir isR
  1634. |\-228: O: O455 (predict-yes)
  1635. I see 1 and I'm going to do: predict-yes
  1636. ENV: Agent did: predict-yes for direction R in state State-B
  1637. In State-B moving R
  1638. ENV: (next state, see, prediction correct?) = (State-B, 0, False)
  1639. predict error 1
  1640. dir: dir isL
  1641. /|\229: O: O457 (predict-yes)
  1642. I see 0 and I'm going to do: predict-yes
  1643. ENV: Agent did: predict-yes for direction L in state State-B
  1644. In State-B moving L
  1645. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  1646. predict error 0
  1647. dir: dir isL
  1648. -/230: O: O460 (predict-no)
  1649. I see 1 and I'm going to do: predict-no
  1650. ENV: Agent did: predict-no for direction L in state State-A
  1651. In State-A moving L
  1652. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  1653. predict error 0
  1654. dir: dir isL
  1655. |\-231: O: O462 (predict-no)
  1656. I see 1 and I'm going to do: predict-no
  1657. ENV: Agent did: predict-no for direction L in state State-A
  1658. In State-A moving L
  1659. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  1660. predict error 0
  1661. dir: dir isU
  1662. /232: O: O464 (predict-no)
  1663. I see 1 and I'm going to do: predict-no
  1664. ENV: Agent did: predict-no for direction U in state State-A
  1665. In State-A moving U
  1666. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  1667. predict error 0
  1668. dir: dir isR
  1669. |\-233: O: O465 (predict-yes)
  1670. I see 1 and I'm going to do: predict-yes
  1671. ENV: Agent did: predict-yes for direction R in state State-A
  1672. In State-A moving R
  1673. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  1674. predict error 0
  1675. dir: dir isU
  1676. /|\234: O: O468 (predict-no)
  1677. I see 1 and I'm going to do: predict-no
  1678. ENV: Agent did: predict-no for direction U in state State-B
  1679. In State-B moving U
  1680. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  1681. predict error 0
  1682. dir: dir isU
  1683. -/|235: O: O470 (predict-no)
  1684. I see 1 and I'm going to do: predict-no
  1685. ENV: Agent did: predict-no for direction U in state State-B
  1686. In State-B moving U
  1687. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  1688. predict error 0
  1689. dir: dir isL
  1690. \-236: O: O471 (predict-yes)
  1691. I see 1 and I'm going to do: predict-yes
  1692. ENV: Agent did: predict-yes for direction L in state State-B
  1693. In State-B moving L
  1694. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  1695. predict error 0
  1696. dir: dir isR
  1697. /|\237: O: O473 (predict-yes)
  1698. I see 1 and I'm going to do: predict-yes
  1699. ENV: Agent did: predict-yes for direction R in state State-A
  1700. In State-A moving R
  1701. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  1702. predict error 0
  1703. dir: dir isU
  1704. -238: O: O476 (predict-no)
  1705. I see 1 and I'm going to do: predict-no
  1706. ENV: Agent did: predict-no for direction U in state State-B
  1707. In State-B moving U
  1708. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  1709. predict error 0
  1710. dir: dir isU
  1711. /239: O: O478 (predict-no)
  1712. I see 1 and I'm going to do: predict-no
  1713. ENV: Agent did: predict-no for direction U in state State-B
  1714. In State-B moving U
  1715. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  1716. predict error 0
  1717. dir: dir isR
  1718. |\-240: O: O480 (predict-no)
  1719. I see 1 and I'm going to do: predict-no
  1720. ENV: Agent did: predict-no for direction R in state State-B
  1721. In State-B moving R
  1722. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  1723. predict error 0
  1724. dir: dir isR
  1725. /|\241: O: O482 (predict-no)
  1726. I see 1 and I'm going to do: predict-no
  1727. ENV: Agent did: predict-no for direction R in state State-B
  1728. In State-B moving R
  1729. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  1730. predict error 0
  1731. dir: dir isR
  1732. -242: O: O484 (predict-no)
  1733. I see 1 and I'm going to do: predict-no
  1734. ENV: Agent did: predict-no for direction R in state State-B
  1735. In State-B moving R
  1736. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  1737. predict error 0
  1738. dir: dir isU
  1739. /|\243: O: O486 (predict-no)
  1740. I see 1 and I'm going to do: predict-no
  1741. ENV: Agent did: predict-no for direction U in state State-B
  1742. In State-B moving U
  1743. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  1744. predict error 0
  1745. dir: dir isL
  1746. -/244: O: O487 (predict-yes)
  1747. I see 1 and I'm going to do: predict-yes
  1748. ENV: Agent did: predict-yes for direction L in state State-B
  1749. In State-B moving L
  1750. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  1751. predict error 0
  1752. dir: dir isR
  1753. |245: O: O489 (predict-yes)
  1754. I see 1 and I'm going to do: predict-yes
  1755. ENV: Agent did: predict-yes for direction R in state State-A
  1756. In State-A moving R
  1757. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  1758. predict error 0
  1759. dir: dir isR
  1760. \-246: O: O492 (predict-no)
  1761. I see 1 and I'm going to do: predict-no
  1762. ENV: Agent did: predict-no for direction R in state State-B
  1763. In State-B moving R
  1764. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  1765. predict error 0
  1766. dir: dir isU
  1767. /|\247: O: O494 (predict-no)
  1768. I see 1 and I'm going to do: predict-no
  1769. ENV: Agent did: predict-no for direction U in state State-B
  1770. In State-B moving U
  1771. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  1772. predict error 0
  1773. dir: dir isU
  1774. -/|248: O: O496 (predict-no)
  1775. I see 1 and I'm going to do: predict-no
  1776. ENV: Agent did: predict-no for direction U in state State-B
  1777. In State-B moving U
  1778. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  1779. predict error 0
  1780. dir: dir isU
  1781. \-249: O: O497 (predict-yes)
  1782. I see 1 and I'm going to do: predict-yes
  1783. ENV: Agent did: predict-yes for direction U in state State-B
  1784. In State-B moving U
  1785. ENV: (next state, see, prediction correct?) = (State-B, 0, False)
  1786. predict error 1
  1787. dir: dir isU
  1788. /|\-250: O: O499 (predict-yes)
  1789. I see 0 and I'm going to do: predict-yes
  1790. ENV: Agent did: predict-yes for direction U in state State-B
  1791. In State-B moving U
  1792. ENV: (next state, see, prediction correct?) = (State-B, 0, False)
  1793. predict error 1
  1794. dir: dir isL
  1795. /|\251: O: O501 (predict-yes)
  1796. I see 0 and I'm going to do: predict-yes
  1797. ENV: Agent did: predict-yes for direction L in state State-B
  1798. In State-B moving L
  1799. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  1800. predict error 0
  1801. dir: dir isL
  1802. -252: O: O504 (predict-no)
  1803. I see 1 and I'm going to do: predict-no
  1804. ENV: Agent did: predict-no for direction L in state State-A
  1805. In State-A moving L
  1806. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  1807. predict error 0
  1808. dir: dir isR
  1809. /|\-sleeping...
  1810. /253: O: O505 (predict-yes)
  1811. I see 1 and I'm going to do: predict-yes
  1812. ENV: Agent did: predict-yes for direction R in state State-A
  1813. In State-A moving R
  1814. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  1815. predict error 0
  1816. dir: dir isL
  1817. |\-254: O: O507 (predict-yes)
  1818. I see 1 and I'm going to do: predict-yes
  1819. ENV: Agent did: predict-yes for direction L in state State-B
  1820. In State-B moving L
  1821. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  1822. predict error 0
  1823. dir: dir isR
  1824. /255: O: O509 (predict-yes)
  1825. I see 1 and I'm going to do: predict-yes
  1826. ENV: Agent did: predict-yes for direction R in state State-A
  1827. In State-A moving R
  1828. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  1829. predict error 0
  1830. dir: dir isU
  1831. |\-/256: O: O512 (predict-no)
  1832. I see 1 and I'm going to do: predict-no
  1833. ENV: Agent did: predict-no for direction U in state State-B
  1834. In State-B moving U
  1835. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  1836. predict error 0
  1837. dir: dir isU
  1838. |\257: O: O514 (predict-no)
  1839. I see 1 and I'm going to do: predict-no
  1840. ENV: Agent did: predict-no for direction U in state State-B
  1841. In State-B moving U
  1842. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  1843. predict error 0
  1844. dir: dir isR
  1845. -/|258: O: O516 (predict-no)
  1846. I see 1 and I'm going to do: predict-no
  1847. ENV: Agent did: predict-no for direction R in state State-B
  1848. In State-B moving R
  1849. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  1850. predict error 0
  1851. dir: dir isU
  1852. \-259: O: O518 (predict-no)
  1853. I see 1 and I'm going to do: predict-no
  1854. ENV: Agent did: predict-no for direction U in state State-B
  1855. In State-B moving U
  1856. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  1857. predict error 0
  1858. dir: dir isL
  1859. /|260: O: O519 (predict-yes)
  1860. I see 1 and I'm going to do: predict-yes
  1861. ENV: Agent did: predict-yes for direction L in state State-B
  1862. In State-B moving L
  1863. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  1864. predict error 0
  1865. dir: dir isR
  1866. \-261: O: O521 (predict-yes)
  1867. I see 1 and I'm going to do: predict-yes
  1868. ENV: Agent did: predict-yes for direction R in state State-A
  1869. In State-A moving R
  1870. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  1871. predict error 0
  1872. dir: dir isU
  1873. /262: O: O524 (predict-no)
  1874. I see 1 and I'm going to do: predict-no
  1875. ENV: Agent did: predict-no for direction U in state State-B
  1876. In State-B moving U
  1877. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  1878. predict error 0
  1879. dir: dir isL
  1880. |\-263: O: O525 (predict-yes)
  1881. I see 1 and I'm going to do: predict-yes
  1882. ENV: Agent did: predict-yes for direction L in state State-B
  1883. In State-B moving L
  1884. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  1885. predict error 0
  1886. dir: dir isR
  1887. /|\264: O: O527 (predict-yes)
  1888. I see 1 and I'm going to do: predict-yes
  1889. ENV: Agent did: predict-yes for direction R in state State-A
  1890. In State-A moving R
  1891. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  1892. predict error 0
  1893. dir: dir isL
  1894. -/265: O: O529 (predict-yes)
  1895. I see 1 and I'm going to do: predict-yes
  1896. ENV: Agent did: predict-yes for direction L in state State-B
  1897. In State-B moving L
  1898. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  1899. predict error 0
  1900. dir: dir isL
  1901. |\-266: O: O532 (predict-no)
  1902. I see 1 and I'm going to do: predict-no
  1903. ENV: Agent did: predict-no for direction L in state State-A
  1904. In State-A moving L
  1905. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  1906. predict error 0
  1907. dir: dir isU
  1908. /267: O: O534 (predict-no)
  1909. I see 1 and I'm going to do: predict-no
  1910. ENV: Agent did: predict-no for direction U in state State-A
  1911. In State-A moving U
  1912. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  1913. predict error 0
  1914. dir: dir isU
  1915. |\-/sleeping...
  1916. |268: O: O536 (predict-no)
  1917. I see 1 and I'm going to do: predict-no
  1918. ENV: Agent did: predict-no for direction U in state State-A
  1919. In State-A moving U
  1920. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  1921. predict error 0
  1922. dir: dir isR
  1923. \-/269: O: O537 (predict-yes)
  1924. I see 1 and I'm going to do: predict-yes
  1925. ENV: Agent did: predict-yes for direction R in state State-A
  1926. In State-A moving R
  1927. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  1928. predict error 0
  1929. dir: dir isL
  1930. |\-/270: O: O539 (predict-yes)
  1931. I see 1 and I'm going to do: predict-yes
  1932. ENV: Agent did: predict-yes for direction L in state State-B
  1933. In State-B moving L
  1934. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  1935. predict error 0
  1936. dir: dir isL
  1937. |\-/271: O: O542 (predict-no)
  1938. I see 1 and I'm going to do: predict-no
  1939. ENV: Agent did: predict-no for direction L in state State-A
  1940. In State-A moving L
  1941. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  1942. predict error 0
  1943. dir: dir isL
  1944. |272: O: O544 (predict-no)
  1945. I see 1 and I'm going to do: predict-no
  1946. ENV: Agent did: predict-no for direction L in state State-A
  1947. In State-A moving L
  1948. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  1949. predict error 0
  1950. dir: dir isU
  1951. \-/273: O: O546 (predict-no)
  1952. I see 1 and I'm going to do: predict-no
  1953. ENV: Agent did: predict-no for direction U in state State-A
  1954. In State-A moving U
  1955. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  1956. predict error 0
  1957. dir: dir isU
  1958. |\-274: O: O548 (predict-no)
  1959. I see 1 and I'm going to do: predict-no
  1960. ENV: Agent did: predict-no for direction U in state State-A
  1961. In State-A moving U
  1962. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  1963. predict error 0
  1964. dir: dir isR
  1965. /|275: O: O549 (predict-yes)
  1966. I see 1 and I'm going to do: predict-yes
  1967. ENV: Agent did: predict-yes for direction R in state State-A
  1968. In State-A moving R
  1969. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  1970. predict error 0
  1971. dir: dir isR
  1972. \-/276: O: O552 (predict-no)
  1973. I see 1 and I'm going to do: predict-no
  1974. ENV: Agent did: predict-no for direction R in state State-B
  1975. In State-B moving R
  1976. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  1977. predict error 0
  1978. dir: dir isL
  1979. |\-/277: O: O553 (predict-yes)
  1980. I see 1 and I'm going to do: predict-yes
  1981. ENV: Agent did: predict-yes for direction L in state State-B
  1982. In State-B moving L
  1983. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  1984. predict error 0
  1985. dir: dir isR
  1986. |\278: O: O555 (predict-yes)
  1987. I see 1 and I'm going to do: predict-yes
  1988. ENV: Agent did: predict-yes for direction R in state State-A
  1989. In State-A moving R
  1990. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  1991. predict error 0
  1992. dir: dir isU
  1993. -/|\279: O: O558 (predict-no)
  1994. I see 1 and I'm going to do: predict-no
  1995. ENV: Agent did: predict-no for direction U in state State-B
  1996. In State-B moving U
  1997. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  1998. predict error 0
  1999. dir: dir isU
  2000. -/|280: O: O560 (predict-no)
  2001. I see 1 and I'm going to do: predict-no
  2002. ENV: Agent did: predict-no for direction U in state State-B
  2003. In State-B moving U
  2004. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2005. predict error 0
  2006. dir: dir isL
  2007. \-/281: O: O561 (predict-yes)
  2008. I see 1 and I'm going to do: predict-yes
  2009. ENV: Agent did: predict-yes for direction L in state State-B
  2010. In State-B moving L
  2011. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  2012. predict error 0
  2013. dir: dir isR
  2014. |282: O: O563 (predict-yes)
  2015. I see 1 and I'm going to do: predict-yes
  2016. ENV: Agent did: predict-yes for direction R in state State-A
  2017. In State-A moving R
  2018. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  2019. predict error 0
  2020. dir: dir isU
  2021. \-/283: O: O566 (predict-no)
  2022. I see 1 and I'm going to do: predict-no
  2023. ENV: Agent did: predict-no for direction U in state State-B
  2024. In State-B moving U
  2025. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2026. predict error 0
  2027. dir: dir isL
  2028. |\284: O: O567 (predict-yes)
  2029. I see 1 and I'm going to do: predict-yes
  2030. ENV: Agent did: predict-yes for direction L in state State-B
  2031. In State-B moving L
  2032. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  2033. predict error 0
  2034. dir: dir isU
  2035. -/|285: O: O570 (predict-no)
  2036. I see 1 and I'm going to do: predict-no
  2037. ENV: Agent did: predict-no for direction U in state State-A
  2038. In State-A moving U
  2039. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  2040. predict error 0
  2041. dir: dir isR
  2042. \-/286: O: O571 (predict-yes)
  2043. I see 1 and I'm going to do: predict-yes
  2044. ENV: Agent did: predict-yes for direction R in state State-A
  2045. In State-A moving R
  2046. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  2047. predict error 0
  2048. dir: dir isU
  2049. |\-287: O: O574 (predict-no)
  2050. I see 1 and I'm going to do: predict-no
  2051. ENV: Agent did: predict-no for direction U in state State-B
  2052. In State-B moving U
  2053. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2054. predict error 0
  2055. dir: dir isR
  2056. /|\288: O: O576 (predict-no)
  2057. I see 1 and I'm going to do: predict-no
  2058. ENV: Agent did: predict-no for direction R in state State-B
  2059. In State-B moving R
  2060. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2061. predict error 0
  2062. dir: dir isU
  2063. -289: O: O578 (predict-no)
  2064. I see 1 and I'm going to do: predict-no
  2065. ENV: Agent did: predict-no for direction U in state State-B
  2066. In State-B moving U
  2067. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2068. predict error 0
  2069. dir: dir isU
  2070. /|\290: O: O580 (predict-no)
  2071. I see 1 and I'm going to do: predict-no
  2072. ENV: Agent did: predict-no for direction U in state State-B
  2073. In State-B moving U
  2074. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2075. predict error 0
  2076. dir: dir isR
  2077. -/|291: O: O582 (predict-no)
  2078. I see 1 and I'm going to do: predict-no
  2079. ENV: Agent did: predict-no for direction R in state State-B
  2080. In State-B moving R
  2081. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2082. predict error 0
  2083. dir: dir isL
  2084. \292: O: O584 (predict-no)
  2085. I see 1 and I'm going to do: predict-no
  2086. ENV: Agent did: predict-no for direction L in state State-B
  2087. In State-B moving L
  2088. ENV: (next state, see, prediction correct?) = (State-A, 1, False)
  2089. predict error 1
  2090. dir: dir isR
  2091. -293: O: O585 (predict-yes)
  2092. I see 0 and I'm going to do: predict-yes
  2093. ENV: Agent did: predict-yes for direction R in state State-A
  2094. In State-A moving R
  2095. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  2096. predict error 0
  2097. dir: dir isL
  2098. /|294: O: O587 (predict-yes)
  2099. I see 1 and I'm going to do: predict-yes
  2100. ENV: Agent did: predict-yes for direction L in state State-B
  2101. In State-B moving L
  2102. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  2103. predict error 0
  2104. dir: dir isR
  2105. \-295: O: O590 (predict-no)
  2106. I see 1 and I'm going to do: predict-no
  2107. ENV: Agent did: predict-no for direction R in state State-A
  2108. In State-A moving R
  2109. ENV: (next state, see, prediction correct?) = (State-B, 1, False)
  2110. predict error 1
  2111. dir: dir isU
  2112. /|\-296: O: O592 (predict-no)
  2113. I see 0 and I'm going to do: predict-no
  2114. ENV: Agent did: predict-no for direction U in state State-B
  2115. In State-B moving U
  2116. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2117. predict error 0
  2118. dir: dir isL
  2119. /297: O: O593 (predict-yes)
  2120. I see 1 and I'm going to do: predict-yes
  2121. ENV: Agent did: predict-yes for direction L in state State-B
  2122. In State-B moving L
  2123. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  2124. predict error 0
  2125. dir: dir isR
  2126. |\-298: O: O595 (predict-yes)
  2127. I see 1 and I'm going to do: predict-yes
  2128. ENV: Agent did: predict-yes for direction R in state State-A
  2129. In State-A moving R
  2130. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  2131. predict error 0
  2132. dir: dir isR
  2133. /|\299: O: O598 (predict-no)
  2134. I see 1 and I'm going to do: predict-no
  2135. ENV: Agent did: predict-no for direction R in state State-B
  2136. In State-B moving R
  2137. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2138. predict error 0
  2139. dir: dir isR
  2140. -/|300: O: O600 (predict-no)
  2141. I see 1 and I'm going to do: predict-no
  2142. ENV: Agent did: predict-no for direction R in state State-B
  2143. In State-B moving R
  2144. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2145. predict error 0
  2146. dir: dir isU
  2147. \-/|\301: O: O602 (predict-no)
  2148. I see 1 and I'm going to do: predict-no
  2149. ENV: Agent did: predict-no for direction U in state State-B
  2150. In State-B moving U
  2151. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2152. predict error 0
  2153. dir: dir isU
  2154. -302: O: O604 (predict-no)
  2155. I see 1 and I'm going to do: predict-no
  2156. ENV: Agent did: predict-no for direction U in state State-B
  2157. In State-B moving U
  2158. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2159. predict error 0
  2160. dir: dir isU
  2161. /|\303: O: O606 (predict-no)
  2162. I see 1 and I'm going to do: predict-no
  2163. ENV: Agent did: predict-no for direction U in state State-B
  2164. In State-B moving U
  2165. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2166. predict error 0
  2167. dir: dir isR
  2168. -/|304: O: O608 (predict-no)
  2169. I see 1 and I'm going to do: predict-no
  2170. ENV: Agent did: predict-no for direction R in state State-B
  2171. In State-B moving R
  2172. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2173. predict error 0
  2174. dir: dir isU
  2175. \-/305: O: O610 (predict-no)
  2176. I see 1 and I'm going to do: predict-no
  2177. ENV: Agent did: predict-no for direction U in state State-B
  2178. In State-B moving U
  2179. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2180. predict error 0
  2181. dir: dir isL
  2182. |\-/306: O: O611 (predict-yes)
  2183. I see 1 and I'm going to do: predict-yes
  2184. ENV: Agent did: predict-yes for direction L in state State-B
  2185. In State-B moving L
  2186. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  2187. predict error 0
  2188. dir: dir isU
  2189. |\-307: O: O614 (predict-no)
  2190. I see 1 and I'm going to do: predict-no
  2191. ENV: Agent did: predict-no for direction U in state State-A
  2192. In State-A moving U
  2193. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  2194. predict error 0
  2195. dir: dir isR
  2196. /|\308: O: O615 (predict-yes)
  2197. I see 1 and I'm going to do: predict-yes
  2198. ENV: Agent did: predict-yes for direction R in state State-A
  2199. In State-A moving R
  2200. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  2201. predict error 0
  2202. dir: dir isU
  2203. -309: O: O618 (predict-no)
  2204. I see 1 and I'm going to do: predict-no
  2205. ENV: Agent did: predict-no for direction U in state State-B
  2206. In State-B moving U
  2207. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2208. predict error 0
  2209. dir: dir isU
  2210. /|\310: O: O620 (predict-no)
  2211. I see 1 and I'm going to do: predict-no
  2212. ENV: Agent did: predict-no for direction U in state State-B
  2213. In State-B moving U
  2214. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2215. predict error 0
  2216. dir: dir isL
  2217. -/|311: O: O621 (predict-yes)
  2218. I see 1 and I'm going to do: predict-yes
  2219. ENV: Agent did: predict-yes for direction L in state State-B
  2220. In State-B moving L
  2221. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  2222. predict error 0
  2223. dir: dir isR
  2224. \312: O: O623 (predict-yes)
  2225. I see 1 and I'm going to do: predict-yes
  2226. ENV: Agent did: predict-yes for direction R in state State-A
  2227. In State-A moving R
  2228. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  2229. predict error 0
  2230. dir: dir isR
  2231. -/|313: O: O626 (predict-no)
  2232. I see 1 and I'm going to do: predict-no
  2233. ENV: Agent did: predict-no for direction R in state State-B
  2234. In State-B moving R
  2235. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2236. predict error 0
  2237. dir: dir isU
  2238. \-314: O: O628 (predict-no)
  2239. I see 1 and I'm going to do: predict-no
  2240. ENV: Agent did: predict-no for direction U in state State-B
  2241. In State-B moving U
  2242. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2243. predict error 0
  2244. dir: dir isU
  2245. /|315: O: O629 (predict-yes)
  2246. I see 1 and I'm going to do: predict-yes
  2247. ENV: Agent did: predict-yes for direction U in state State-B
  2248. In State-B moving U
  2249. ENV: (next state, see, prediction correct?) = (State-B, 0, False)
  2250. predict error 1
  2251. dir: dir isR
  2252. \-/316: O: O631 (predict-yes)
  2253. I see 0 and I'm going to do: predict-yes
  2254. ENV: Agent did: predict-yes for direction R in state State-B
  2255. In State-B moving R
  2256. ENV: (next state, see, prediction correct?) = (State-B, 0, False)
  2257. predict error 1
  2258. dir: dir isL
  2259. |\-317: O: O633 (predict-yes)
  2260. I see 0 and I'm going to do: predict-yes
  2261. ENV: Agent did: predict-yes for direction L in state State-B
  2262. In State-B moving L
  2263. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  2264. predict error 0
  2265. dir: dir isR
  2266. /|318: O: O635 (predict-yes)
  2267. I see 1 and I'm going to do: predict-yes
  2268. ENV: Agent did: predict-yes for direction R in state State-A
  2269. In State-A moving R
  2270. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  2271. predict error 0
  2272. dir: dir isU
  2273. \-319: O: O638 (predict-no)
  2274. I see 1 and I'm going to do: predict-no
  2275. ENV: Agent did: predict-no for direction U in state State-B
  2276. In State-B moving U
  2277. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2278. predict error 0
  2279. dir: dir isU
  2280. /|320: O: O640 (predict-no)
  2281. I see 1 and I'm going to do: predict-no
  2282. ENV: Agent did: predict-no for direction U in state State-B
  2283. In State-B moving U
  2284. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2285. predict error 0
  2286. dir: dir isR
  2287. \-/321: O: O642 (predict-no)
  2288. I see 1 and I'm going to do: predict-no
  2289. ENV: Agent did: predict-no for direction R in state State-B
  2290. In State-B moving R
  2291. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2292. predict error 0
  2293. dir: dir isU
  2294. |322: O: O644 (predict-no)
  2295. I see 1 and I'm going to do: predict-no
  2296. ENV: Agent did: predict-no for direction U in state State-B
  2297. In State-B moving U
  2298. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2299. predict error 0
  2300. dir: dir isL
  2301. \-323: O: O646 (predict-no)
  2302. I see 1 and I'm going to do: predict-no
  2303. ENV: Agent did: predict-no for direction L in state State-B
  2304. In State-B moving L
  2305. ENV: (next state, see, prediction correct?) = (State-A, 1, False)
  2306. predict error 1
  2307. dir: dir isU
  2308. /|\324: O: O648 (predict-no)
  2309. I see 0 and I'm going to do: predict-no
  2310. ENV: Agent did: predict-no for direction U in state State-A
  2311. In State-A moving U
  2312. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  2313. predict error 0
  2314. dir: dir isU
  2315. -/|325: O: O650 (predict-no)
  2316. I see 1 and I'm going to do: predict-no
  2317. ENV: Agent did: predict-no for direction U in state State-A
  2318. In State-A moving U
  2319. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  2320. predict error 0
  2321. dir: dir isR
  2322. \-/326: O: O651 (predict-yes)
  2323. I see 1 and I'm going to do: predict-yes
  2324. ENV: Agent did: predict-yes for direction R in state State-A
  2325. In State-A moving R
  2326. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  2327. predict error 0
  2328. dir: dir isU
  2329. |\-/327: O: O654 (predict-no)
  2330. I see 1 and I'm going to do: predict-no
  2331. ENV: Agent did: predict-no for direction U in state State-B
  2332. In State-B moving U
  2333. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2334. predict error 0
  2335. dir: dir isU
  2336. |\-328: O: O656 (predict-no)
  2337. I see 1 and I'm going to do: predict-no
  2338. ENV: Agent did: predict-no for direction U in state State-B
  2339. In State-B moving U
  2340. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2341. predict error 0
  2342. dir: dir isL
  2343. /|\329: O: O657 (predict-yes)
  2344. I see 1 and I'm going to do: predict-yes
  2345. ENV: Agent did: predict-yes for direction L in state State-B
  2346. In State-B moving L
  2347. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  2348. predict error 0
  2349. dir: dir isU
  2350. -/|\sleeping...
  2351. -330: O: O660 (predict-no)
  2352. I see 1 and I'm going to do: predict-no
  2353. ENV: Agent did: predict-no for direction U in state State-A
  2354. In State-A moving U
  2355. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  2356. predict error 0
  2357. dir: dir isU
  2358. /|\331: O: O662 (predict-no)
  2359. I see 1 and I'm going to do: predict-no
  2360. ENV: Agent did: predict-no for direction U in state State-A
  2361. In State-A moving U
  2362. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  2363. predict error 0
  2364. dir: dir isL
  2365. -332: O: O664 (predict-no)
  2366. I see 1 and I'm going to do: predict-no
  2367. ENV: Agent did: predict-no for direction L in state State-A
  2368. In State-A moving L
  2369. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  2370. predict error 0
  2371. dir: dir isU
  2372. /|333: O: O666 (predict-no)
  2373. I see 1 and I'm going to do: predict-no
  2374. ENV: Agent did: predict-no for direction U in state State-A
  2375. In State-A moving U
  2376. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  2377. predict error 0
  2378. dir: dir isR
  2379. \-334: O: O667 (predict-yes)
  2380. I see 1 and I'm going to do: predict-yes
  2381. ENV: Agent did: predict-yes for direction R in state State-A
  2382. In State-A moving R
  2383. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  2384. predict error 0
  2385. dir: dir isL
  2386. /|\335: O: O669 (predict-yes)
  2387. I see 1 and I'm going to do: predict-yes
  2388. ENV: Agent did: predict-yes for direction L in state State-B
  2389. In State-B moving L
  2390. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  2391. predict error 0
  2392. dir: dir isU
  2393. -/|336: O: O672 (predict-no)
  2394. I see 1 and I'm going to do: predict-no
  2395. ENV: Agent did: predict-no for direction U in state State-A
  2396. In State-A moving U
  2397. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  2398. predict error 0
  2399. dir: dir isL
  2400. \-337: O: O674 (predict-no)
  2401. I see 1 and I'm going to do: predict-no
  2402. ENV: Agent did: predict-no for direction L in state State-A
  2403. In State-A moving L
  2404. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  2405. predict error 0
  2406. dir: dir isR
  2407. /|338: O: O675 (predict-yes)
  2408. I see 1 and I'm going to do: predict-yes
  2409. ENV: Agent did: predict-yes for direction R in state State-A
  2410. In State-A moving R
  2411. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  2412. predict error 0
  2413. dir: dir isR
  2414. \-339: O: O678 (predict-no)
  2415. I see 1 and I'm going to do: predict-no
  2416. ENV: Agent did: predict-no for direction R in state State-B
  2417. In State-B moving R
  2418. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2419. predict error 0
  2420. dir: dir isL
  2421. /|\340: O: O679 (predict-yes)
  2422. I see 1 and I'm going to do: predict-yes
  2423. ENV: Agent did: predict-yes for direction L in state State-B
  2424. In State-B moving L
  2425. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  2426. predict error 0
  2427. dir: dir isR
  2428. -/341: O: O681 (predict-yes)
  2429. I see 1 and I'm going to do: predict-yes
  2430. ENV: Agent did: predict-yes for direction R in state State-A
  2431. In State-A moving R
  2432. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  2433. predict error 0
  2434. dir: dir isR
  2435. |342: O: O684 (predict-no)
  2436. I see 1 and I'm going to do: predict-no
  2437. ENV: Agent did: predict-no for direction R in state State-B
  2438. In State-B moving R
  2439. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2440. predict error 0
  2441. dir: dir isL
  2442. \-343: O: O685 (predict-yes)
  2443. I see 1 and I'm going to do: predict-yes
  2444. ENV: Agent did: predict-yes for direction L in state State-B
  2445. In State-B moving L
  2446. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  2447. predict error 0
  2448. dir: dir isU
  2449. /|\344: O: O688 (predict-no)
  2450. I see 1 and I'm going to do: predict-no
  2451. ENV: Agent did: predict-no for direction U in state State-A
  2452. In State-A moving U
  2453. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  2454. predict error 0
  2455. dir: dir isL
  2456. -/|345: O: O690 (predict-no)
  2457. I see 1 and I'm going to do: predict-no
  2458. ENV: Agent did: predict-no for direction L in state State-A
  2459. In State-A moving L
  2460. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  2461. predict error 0
  2462. dir: dir isL
  2463. \-/346: O: O692 (predict-no)
  2464. I see 1 and I'm going to do: predict-no
  2465. ENV: Agent did: predict-no for direction L in state State-A
  2466. In State-A moving L
  2467. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  2468. predict error 0
  2469. dir: dir isR
  2470. |\347: O: O693 (predict-yes)
  2471. I see 1 and I'm going to do: predict-yes
  2472. ENV: Agent did: predict-yes for direction R in state State-A
  2473. In State-A moving R
  2474. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  2475. predict error 0
  2476. dir: dir isU
  2477. -/|348: O: O696 (predict-no)
  2478. I see 1 and I'm going to do: predict-no
  2479. ENV: Agent did: predict-no for direction U in state State-B
  2480. In State-B moving U
  2481. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2482. predict error 0
  2483. dir: dir isR
  2484. \-/349: O: O698 (predict-no)
  2485. I see 1 and I'm going to do: predict-no
  2486. ENV: Agent did: predict-no for direction R in state State-B
  2487. In State-B moving R
  2488. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2489. predict error 0
  2490. dir: dir isU
  2491. |\350: O: O700 (predict-no)
  2492. I see 1 and I'm going to do: predict-no
  2493. ENV: Agent did: predict-no for direction U in state State-B
  2494. In State-B moving U
  2495. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2496. predict error 0
  2497. dir: dir isR
  2498. -/|351: O: O702 (predict-no)
  2499. I see 1 and I'm going to do: predict-no
  2500. ENV: Agent did: predict-no for direction R in state State-B
  2501. In State-B moving R
  2502. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2503. predict error 0
  2504. dir: dir isU
  2505. \352: O: O704 (predict-no)
  2506. I see 1 and I'm going to do: predict-no
  2507. ENV: Agent did: predict-no for direction U in state State-B
  2508. In State-B moving U
  2509. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2510. predict error 0
  2511. dir: dir isR
  2512. -/|353: O: O706 (predict-no)
  2513. I see 1 and I'm going to do: predict-no
  2514. ENV: Agent did: predict-no for direction R in state State-B
  2515. In State-B moving R
  2516. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2517. predict error 0
  2518. dir: dir isL
  2519. \-/354: O: O707 (predict-yes)
  2520. I see 1 and I'm going to do: predict-yes
  2521. ENV: Agent did: predict-yes for direction L in state State-B
  2522. In State-B moving L
  2523. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  2524. predict error 0
  2525. dir: dir isR
  2526. |\355: O: O709 (predict-yes)
  2527. I see 1 and I'm going to do: predict-yes
  2528. ENV: Agent did: predict-yes for direction R in state State-A
  2529. In State-A moving R
  2530. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  2531. predict error 0
  2532. dir: dir isL
  2533. -/|356: O: O711 (predict-yes)
  2534. I see 1 and I'm going to do: predict-yes
  2535. ENV: Agent did: predict-yes for direction L in state State-B
  2536. In State-B moving L
  2537. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  2538. predict error 0
  2539. dir: dir isL
  2540. \-/357: O: O714 (predict-no)
  2541. I see 1 and I'm going to do: predict-no
  2542. ENV: Agent did: predict-no for direction L in state State-A
  2543. In State-A moving L
  2544. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  2545. predict error 0
  2546. dir: dir isU
  2547. |\-358: O: O716 (predict-no)
  2548. I see 1 and I'm going to do: predict-no
  2549. ENV: Agent did: predict-no for direction U in state State-A
  2550. In State-A moving U
  2551. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  2552. predict error 0
  2553. dir: dir isL
  2554. /|\359: O: O718 (predict-no)
  2555. I see 1 and I'm going to do: predict-no
  2556. ENV: Agent did: predict-no for direction L in state State-A
  2557. In State-A moving L
  2558. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  2559. predict error 0
  2560. dir: dir isU
  2561. -/|360: O: O719 (predict-yes)
  2562. I see 1 and I'm going to do: predict-yes
  2563. ENV: Agent did: predict-yes for direction U in state State-A
  2564. In State-A moving U
  2565. ENV: (next state, see, prediction correct?) = (State-A, 0, False)
  2566. predict error 1
  2567. dir: dir isU
  2568. \-/361: O: O722 (predict-no)
  2569. I see 0 and I'm going to do: predict-no
  2570. ENV: Agent did: predict-no for direction U in state State-A
  2571. In State-A moving U
  2572. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  2573. predict error 0
  2574. dir: dir isR
  2575. |362: O: O723 (predict-yes)
  2576. I see 1 and I'm going to do: predict-yes
  2577. ENV: Agent did: predict-yes for direction R in state State-A
  2578. In State-A moving R
  2579. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  2580. predict error 0
  2581. dir: dir isU
  2582. \-/363: O: O726 (predict-no)
  2583. I see 1 and I'm going to do: predict-no
  2584. ENV: Agent did: predict-no for direction U in state State-B
  2585. In State-B moving U
  2586. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2587. predict error 0
  2588. dir: dir isU
  2589. |\364: O: O728 (predict-no)
  2590. I see 1 and I'm going to do: predict-no
  2591. ENV: Agent did: predict-no for direction U in state State-B
  2592. In State-B moving U
  2593. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2594. predict error 0
  2595. dir: dir isU
  2596. -/|365: O: O730 (predict-no)
  2597. I see 1 and I'm going to do: predict-no
  2598. ENV: Agent did: predict-no for direction U in state State-B
  2599. In State-B moving U
  2600. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2601. predict error 0
  2602. dir: dir isL
  2603. \-/366: O: O731 (predict-yes)
  2604. I see 1 and I'm going to do: predict-yes
  2605. ENV: Agent did: predict-yes for direction L in state State-B
  2606. In State-B moving L
  2607. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  2608. predict error 0
  2609. dir: dir isL
  2610. |\367: O: O734 (predict-no)
  2611. I see 1 and I'm going to do: predict-no
  2612. ENV: Agent did: predict-no for direction L in state State-A
  2613. In State-A moving L
  2614. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  2615. predict error 0
  2616. dir: dir isR
  2617. -/368: O: O735 (predict-yes)
  2618. I see 1 and I'm going to do: predict-yes
  2619. ENV: Agent did: predict-yes for direction R in state State-A
  2620. In State-A moving R
  2621. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  2622. predict error 0
  2623. dir: dir isR
  2624. |\-369: O: O738 (predict-no)
  2625. I see 1 and I'm going to do: predict-no
  2626. ENV: Agent did: predict-no for direction R in state State-B
  2627. In State-B moving R
  2628. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2629. predict error 0
  2630. dir: dir isL
  2631. /|\370: O: O739 (predict-yes)
  2632. I see 1 and I'm going to do: predict-yes
  2633. ENV: Agent did: predict-yes for direction L in state State-B
  2634. In State-B moving L
  2635. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  2636. predict error 0
  2637. dir: dir isL
  2638. -/|371: O: O741 (predict-yes)
  2639. I see 1 and I'm going to do: predict-yes
  2640. ENV: Agent did: predict-yes for direction L in state State-A
  2641. In State-A moving L
  2642. ENV: (next state, see, prediction correct?) = (State-A, 0, False)
  2643. predict error 1
  2644. dir: dir isR
  2645. \372: O: O743 (predict-yes)
  2646. I see 0 and I'm going to do: predict-yes
  2647. ENV: Agent did: predict-yes for direction R in state State-A
  2648. In State-A moving R
  2649. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  2650. predict error 0
  2651. dir: dir isU
  2652. -/|373: O: O746 (predict-no)
  2653. I see 1 and I'm going to do: predict-no
  2654. ENV: Agent did: predict-no for direction U in state State-B
  2655. In State-B moving U
  2656. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2657. predict error 0
  2658. dir: dir isR
  2659. \374: O: O748 (predict-no)
  2660. I see 1 and I'm going to do: predict-no
  2661. ENV: Agent did: predict-no for direction R in state State-B
  2662. In State-B moving R
  2663. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2664. predict error 0
  2665. dir: dir isR
  2666. -/375: O: O750 (predict-no)
  2667. I see 1 and I'm going to do: predict-no
  2668. ENV: Agent did: predict-no for direction R in state State-B
  2669. In State-B moving R
  2670. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2671. predict error 0
  2672. dir: dir isR
  2673. |\-376: O: O752 (predict-no)
  2674. I see 1 and I'm going to do: predict-no
  2675. ENV: Agent did: predict-no for direction R in state State-B
  2676. In State-B moving R
  2677. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2678. predict error 0
  2679. dir: dir isR
  2680. /|377: O: O754 (predict-no)
  2681. I see 1 and I'm going to do: predict-no
  2682. ENV: Agent did: predict-no for direction R in state State-B
  2683. In State-B moving R
  2684. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2685. predict error 0
  2686. dir: dir isU
  2687. \-378: O: O756 (predict-no)
  2688. I see 1 and I'm going to do: predict-no
  2689. ENV: Agent did: predict-no for direction U in state State-B
  2690. In State-B moving U
  2691. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2692. predict error 0
  2693. dir: dir isL
  2694. /|\-379: O: O757 (predict-yes)
  2695. I see 1 and I'm going to do: predict-yes
  2696. ENV: Agent did: predict-yes for direction L in state State-B
  2697. In State-B moving L
  2698. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  2699. predict error 0
  2700. dir: dir isR
  2701. /|380: O: O759 (predict-yes)
  2702. I see 1 and I'm going to do: predict-yes
  2703. ENV: Agent did: predict-yes for direction R in state State-A
  2704. In State-A moving R
  2705. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  2706. predict error 0
  2707. dir: dir isR
  2708. \-/381: O: O762 (predict-no)
  2709. I see 1 and I'm going to do: predict-no
  2710. ENV: Agent did: predict-no for direction R in state State-B
  2711. In State-B moving R
  2712. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2713. predict error 0
  2714. dir: dir isR
  2715. |382: O: O764 (predict-no)
  2716. I see 1 and I'm going to do: predict-no
  2717. ENV: Agent did: predict-no for direction R in state State-B
  2718. In State-B moving R
  2719. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2720. predict error 0
  2721. dir: dir isU
  2722. \383: O: O766 (predict-no)
  2723. I see 1 and I'm going to do: predict-no
  2724. ENV: Agent did: predict-no for direction U in state State-B
  2725. In State-B moving U
  2726. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2727. predict error 0
  2728. dir: dir isL
  2729. -/|384: O: O767 (predict-yes)
  2730. I see 1 and I'm going to do: predict-yes
  2731. ENV: Agent did: predict-yes for direction L in state State-B
  2732. In State-B moving L
  2733. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  2734. predict error 0
  2735. dir: dir isU
  2736. \-/385: O: O770 (predict-no)
  2737. I see 1 and I'm going to do: predict-no
  2738. ENV: Agent did: predict-no for direction U in state State-A
  2739. In State-A moving U
  2740. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  2741. predict error 0
  2742. dir: dir isL
  2743. |\-386: O: O772 (predict-no)
  2744. I see 1 and I'm going to do: predict-no
  2745. ENV: Agent did: predict-no for direction L in state State-A
  2746. In State-A moving L
  2747. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  2748. predict error 0
  2749. dir: dir isR
  2750. /|\387: O: O773 (predict-yes)
  2751. I see 1 and I'm going to do: predict-yes
  2752. ENV: Agent did: predict-yes for direction R in state State-A
  2753. In State-A moving R
  2754. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  2755. predict error 0
  2756. dir: dir isU
  2757. -/|388: O: O776 (predict-no)
  2758. I see 1 and I'm going to do: predict-no
  2759. ENV: Agent did: predict-no for direction U in state State-B
  2760. In State-B moving U
  2761. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2762. predict error 0
  2763. dir: dir isR
  2764. \-/389: O: O778 (predict-no)
  2765. I see 1 and I'm going to do: predict-no
  2766. ENV: Agent did: predict-no for direction R in state State-B
  2767. In State-B moving R
  2768. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2769. predict error 0
  2770. dir: dir isR
  2771. |\390: O: O780 (predict-no)
  2772. I see 1 and I'm going to do: predict-no
  2773. ENV: Agent did: predict-no for direction R in state State-B
  2774. In State-B moving R
  2775. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2776. predict error 0
  2777. dir: dir isU
  2778. -/|391: O: O782 (predict-no)
  2779. I see 1 and I'm going to do: predict-no
  2780. ENV: Agent did: predict-no for direction U in state State-B
  2781. In State-B moving U
  2782. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2783. predict error 0
  2784. dir: dir isL
  2785. \392: O: O783 (predict-yes)
  2786. I see 1 and I'm going to do: predict-yes
  2787. ENV: Agent did: predict-yes for direction L in state State-B
  2788. In State-B moving L
  2789. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  2790. predict error 0
  2791. dir: dir isR
  2792. -/|393: O: O786 (predict-no)
  2793. I see 1 and I'm going to do: predict-no
  2794. ENV: Agent did: predict-no for direction R in state State-A
  2795. In State-A moving R
  2796. ENV: (next state, see, prediction correct?) = (State-B, 1, False)
  2797. predict error 1
  2798. dir: dir isR
  2799. \-/394: O: O788 (predict-no)
  2800. I see 0 and I'm going to do: predict-no
  2801. ENV: Agent did: predict-no for direction R in state State-B
  2802. In State-B moving R
  2803. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2804. predict error 0
  2805. dir: dir isR
  2806. |\395: O: O790 (predict-no)
  2807. I see 1 and I'm going to do: predict-no
  2808. ENV: Agent did: predict-no for direction R in state State-B
  2809. In State-B moving R
  2810. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2811. predict error 0
  2812. dir: dir isU
  2813. -/|396: O: O792 (predict-no)
  2814. I see 1 and I'm going to do: predict-no
  2815. ENV: Agent did: predict-no for direction U in state State-B
  2816. In State-B moving U
  2817. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2818. predict error 0
  2819. dir: dir isU
  2820. \-/397: O: O794 (predict-no)
  2821. I see 1 and I'm going to do: predict-no
  2822. ENV: Agent did: predict-no for direction U in state State-B
  2823. In State-B moving U
  2824. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2825. predict error 0
  2826. dir: dir isR
  2827. |\398: O: O796 (predict-no)
  2828. I see 1 and I'm going to do: predict-no
  2829. ENV: Agent did: predict-no for direction R in state State-B
  2830. In State-B moving R
  2831. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2832. predict error 0
  2833. dir: dir isL
  2834. -/399: O: O797 (predict-yes)
  2835. I see 1 and I'm going to do: predict-yes
  2836. ENV: Agent did: predict-yes for direction L in state State-B
  2837. In State-B moving L
  2838. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  2839. predict error 0
  2840. dir: dir isL
  2841. |\-400: O: O800 (predict-no)
  2842. I see 1 and I'm going to do: predict-no
  2843. ENV: Agent did: predict-no for direction L in state State-A
  2844. In State-A moving L
  2845. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  2846. predict error 0
  2847. dir: dir isR
  2848. /|\-sleeping...
  2849. /401: O: O801 (predict-yes)
  2850. I see 1 and I'm going to do: predict-yes
  2851. ENV: Agent did: predict-yes for direction R in state State-A
  2852. In State-A moving R
  2853. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  2854. predict error 0
  2855. dir: dir isL
  2856. |402: O: O803 (predict-yes)
  2857. I see 1 and I'm going to do: predict-yes
  2858. ENV: Agent did: predict-yes for direction L in state State-B
  2859. In State-B moving L
  2860. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  2861. predict error 0
  2862. dir: dir isL
  2863. \-/403: O: O806 (predict-no)
  2864. I see 1 and I'm going to do: predict-no
  2865. ENV: Agent did: predict-no for direction L in state State-A
  2866. In State-A moving L
  2867. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  2868. predict error 0
  2869. dir: dir isU
  2870. |\-404: O: O807 (predict-yes)
  2871. I see 1 and I'm going to do: predict-yes
  2872. ENV: Agent did: predict-yes for direction U in state State-A
  2873. In State-A moving U
  2874. ENV: (next state, see, prediction correct?) = (State-A, 0, False)
  2875. predict error 1
  2876. dir: dir isL
  2877. /|405: O: O810 (predict-no)
  2878. I see 0 and I'm going to do: predict-no
  2879. ENV: Agent did: predict-no for direction L in state State-A
  2880. In State-A moving L
  2881. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  2882. predict error 0
  2883. dir: dir isU
  2884. \-406: O: O812 (predict-no)
  2885. I see 1 and I'm going to do: predict-no
  2886. ENV: Agent did: predict-no for direction U in state State-A
  2887. In State-A moving U
  2888. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  2889. predict error 0
  2890. dir: dir isR
  2891. /|407: O: O813 (predict-yes)
  2892. I see 1 and I'm going to do: predict-yes
  2893. ENV: Agent did: predict-yes for direction R in state State-A
  2894. In State-A moving R
  2895. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  2896. predict error 0
  2897. dir: dir isR
  2898. \-408: O: O816 (predict-no)
  2899. I see 1 and I'm going to do: predict-no
  2900. ENV: Agent did: predict-no for direction R in state State-B
  2901. In State-B moving R
  2902. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2903. predict error 0
  2904. dir: dir isL
  2905. /|\409: O: O817 (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. -410: O: O820 (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 isR
  2919. /|\411: O: O821 (predict-yes)
  2920. I see 1 and I'm going to do: predict-yes
  2921. ENV: Agent did: predict-yes for direction R in state State-A
  2922. In State-A moving R
  2923. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  2924. predict error 0
  2925. dir: dir isL
  2926. -412: O: O823 (predict-yes)
  2927. I see 1 and I'm going to do: predict-yes
  2928. ENV: Agent did: predict-yes for direction L in state State-B
  2929. In State-B moving L
  2930. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  2931. predict error 0
  2932. dir: dir isR
  2933. /|\413: O: O825 (predict-yes)
  2934. I see 1 and I'm going to do: predict-yes
  2935. ENV: Agent did: predict-yes for direction R in state State-A
  2936. In State-A moving R
  2937. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  2938. predict error 0
  2939. dir: dir isL
  2940. -/|414: O: O827 (predict-yes)
  2941. I see 1 and I'm going to do: predict-yes
  2942. ENV: Agent did: predict-yes for direction L in state State-B
  2943. In State-B moving L
  2944. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  2945. predict error 0
  2946. dir: dir isU
  2947. \-415: O: O830 (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-A
  2950. In State-A moving U
  2951. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  2952. predict error 0
  2953. dir: dir isU
  2954. /|\-416: O: O832 (predict-no)
  2955. I see 1 and I'm going to do: predict-no
  2956. ENV: Agent did: predict-no for direction U in state State-A
  2957. In State-A moving U
  2958. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  2959. predict error 0
  2960. dir: dir isR
  2961. /|\417: O: O833 (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 isR
  2968. -/418: O: O836 (predict-no)
  2969. I see 1 and I'm going to do: predict-no
  2970. ENV: Agent did: predict-no for direction R in state State-B
  2971. In State-B moving R
  2972. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2973. predict error 0
  2974. dir: dir isU
  2975. |\419: O: O838 (predict-no)
  2976. I see 1 and I'm going to do: predict-no
  2977. ENV: Agent did: predict-no for direction U in state State-B
  2978. In State-B moving U
  2979. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2980. predict error 0
  2981. dir: dir isL
  2982. -/|420: O: O839 (predict-yes)
  2983. I see 1 and I'm going to do: predict-yes
  2984. ENV: Agent did: predict-yes for direction L in state State-B
  2985. In State-B moving L
  2986. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  2987. predict error 0
  2988. dir: dir isL
  2989. \421: O: O842 (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. -422: O: O844 (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 isL
  3003. /|\423: O: O846 (predict-no)
  3004. I see 1 and I'm going to do: predict-no
  3005. ENV: Agent did: predict-no for direction L in state State-A
  3006. In State-A moving L
  3007. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3008. predict error 0
  3009. dir: dir isU
  3010. -/|424: O: O848 (predict-no)
  3011. I see 1 and I'm going to do: predict-no
  3012. ENV: Agent did: predict-no for direction U in state State-A
  3013. In State-A moving U
  3014. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3015. predict error 0
  3016. dir: dir isR
  3017. \-/425: O: O849 (predict-yes)
  3018. I see 1 and I'm going to do: predict-yes
  3019. ENV: Agent did: predict-yes for direction R in state State-A
  3020. In State-A moving R
  3021. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  3022. predict error 0
  3023. dir: dir isR
  3024. |\426: O: O852 (predict-no)
  3025. I see 1 and I'm going to do: predict-no
  3026. ENV: Agent did: predict-no for direction R in state State-B
  3027. In State-B moving R
  3028. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3029. predict error 0
  3030. dir: dir isU
  3031. -/|427: O: O854 (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. \-428: O: O855 (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. /|\429: O: O858 (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. -/|430: O: O859 (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. \-431: O: O862 (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 isU
  3066. /432: O: O864 (predict-no)
  3067. I see 1 and I'm going to do: predict-no
  3068. ENV: Agent did: predict-no for direction U in state State-B
  3069. In State-B moving U
  3070. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3071. predict error 0
  3072. dir: dir isR
  3073. |\-433: O: O866 (predict-no)
  3074. I see 1 and I'm going to do: predict-no
  3075. ENV: Agent did: predict-no for direction R in state State-B
  3076. In State-B moving R
  3077. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3078. predict error 0
  3079. dir: dir isU
  3080. /|434: O: O868 (predict-no)
  3081. I see 1 and I'm going to do: predict-no
  3082. ENV: Agent did: predict-no for direction U in state State-B
  3083. In State-B moving U
  3084. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3085. predict error 0
  3086. dir: dir isU
  3087. \-/435: O: O870 (predict-no)
  3088. I see 1 and I'm going to do: predict-no
  3089. ENV: Agent did: predict-no for direction U in state State-B
  3090. In State-B moving U
  3091. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3092. predict error 0
  3093. dir: dir isR
  3094. |\-436: O: O872 (predict-no)
  3095. I see 1 and I'm going to do: predict-no
  3096. ENV: Agent did: predict-no for direction R in state State-B
  3097. In State-B moving R
  3098. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3099. predict error 0
  3100. dir: dir isU
  3101. /|437: O: O874 (predict-no)
  3102. I see 1 and I'm going to do: predict-no
  3103. ENV: Agent did: predict-no for direction U in state State-B
  3104. In State-B moving U
  3105. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3106. predict error 0
  3107. dir: dir isU
  3108. \-/438: O: O876 (predict-no)
  3109. I see 1 and I'm going to do: predict-no
  3110. ENV: Agent did: predict-no for direction U in state State-B
  3111. In State-B moving U
  3112. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3113. predict error 0
  3114. dir: dir isU
  3115. |\-439: O: O878 (predict-no)
  3116. I see 1 and I'm going to do: predict-no
  3117. ENV: Agent did: predict-no for direction U in state State-B
  3118. In State-B moving U
  3119. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3120. predict error 0
  3121. dir: dir isU
  3122. /|\440: O: O880 (predict-no)
  3123. I see 1 and I'm going to do: predict-no
  3124. ENV: Agent did: predict-no for direction U in state State-B
  3125. In State-B moving U
  3126. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3127. predict error 0
  3128. dir: dir isU
  3129. -/|441: O: O882 (predict-no)
  3130. I see 1 and I'm going to do: predict-no
  3131. ENV: Agent did: predict-no for direction U in state State-B
  3132. In State-B moving U
  3133. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3134. predict error 0
  3135. dir: dir isU
  3136. \442: O: O884 (predict-no)
  3137. I see 1 and I'm going to do: predict-no
  3138. ENV: Agent did: predict-no for direction U in state State-B
  3139. In State-B moving U
  3140. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3141. predict error 0
  3142. dir: dir isU
  3143. -/|\443: O: O886 (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 isU
  3150. -/444: O: O888 (predict-no)
  3151. I see 1 and I'm going to do: predict-no
  3152. ENV: Agent did: predict-no for direction U in state State-B
  3153. In State-B moving U
  3154. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3155. predict error 0
  3156. dir: dir isL
  3157. |\445: O: O889 (predict-yes)
  3158. I see 1 and I'm going to do: predict-yes
  3159. ENV: Agent did: predict-yes for direction L in state State-B
  3160. In State-B moving L
  3161. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  3162. predict error 0
  3163. dir: dir isR
  3164. -/|446: O: O891 (predict-yes)
  3165. I see 1 and I'm going to do: predict-yes
  3166. ENV: Agent did: predict-yes for direction R in state State-A
  3167. In State-A moving R
  3168. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  3169. predict error 0
  3170. dir: dir isU
  3171. \-/447: O: O894 (predict-no)
  3172. I see 1 and I'm going to do: predict-no
  3173. ENV: Agent did: predict-no for direction U in state State-B
  3174. In State-B moving U
  3175. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3176. predict error 0
  3177. dir: dir isR
  3178. |\-448: O: O896 (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. /|\449: O: O898 (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. -/|450: O: O899 (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. \-/451: O: O902 (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. |452: O: O903 (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 isR
  3213. \-/453: O: O906 (predict-no)
  3214. I see 1 and I'm going to do: predict-no
  3215. ENV: Agent did: predict-no for direction R in state State-B
  3216. In State-B moving R
  3217. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3218. predict error 0
  3219. dir: dir isU
  3220. |\454: O: O908 (predict-no)
  3221. I see 1 and I'm going to do: predict-no
  3222. ENV: Agent did: predict-no for direction U in state State-B
  3223. In State-B moving U
  3224. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3225. predict error 0
  3226. dir: dir isL
  3227. -/455: O: O909 (predict-yes)
  3228. I see 1 and I'm going to do: predict-yes
  3229. ENV: Agent did: predict-yes for direction L in state State-B
  3230. In State-B moving L
  3231. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  3232. predict error 0
  3233. dir: dir isU
  3234. |456: O: O912 (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 isL
  3241. \-/457: O: O914 (predict-no)
  3242. I see 1 and I'm going to do: predict-no
  3243. ENV: Agent did: predict-no for direction L in state State-A
  3244. In State-A moving L
  3245. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3246. predict error 0
  3247. dir: dir isL
  3248. |\458: O: O916 (predict-no)
  3249. I see 1 and I'm going to do: predict-no
  3250. ENV: Agent did: predict-no for direction L in state State-A
  3251. In State-A moving L
  3252. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3253. predict error 0
  3254. dir: dir isR
  3255. -/|459: O: O917 (predict-yes)
  3256. I see 1 and I'm going to do: predict-yes
  3257. ENV: Agent did: predict-yes for direction R in state State-A
  3258. In State-A moving R
  3259. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  3260. predict error 0
  3261. dir: dir isR
  3262. \-/460: O: O920 (predict-no)
  3263. I see 1 and I'm going to do: predict-no
  3264. ENV: Agent did: predict-no for direction R in state State-B
  3265. In State-B moving R
  3266. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3267. predict error 0
  3268. dir: dir isU
  3269. |\-461: O: O922 (predict-no)
  3270. I see 1 and I'm going to do: predict-no
  3271. ENV: Agent did: predict-no for direction U in state State-B
  3272. In State-B moving U
  3273. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3274. predict error 0
  3275. dir: dir isU
  3276. /462: O: O924 (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 isU
  3283. |\-463: O: O926 (predict-no)
  3284. I see 1 and I'm going to do: predict-no
  3285. ENV: Agent did: predict-no for direction U in state State-B
  3286. In State-B moving U
  3287. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3288. predict error 0
  3289. dir: dir isR
  3290. /|\464: O: O928 (predict-no)
  3291. I see 1 and I'm going to do: predict-no
  3292. ENV: Agent did: predict-no for direction R in state State-B
  3293. In State-B moving R
  3294. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3295. predict error 0
  3296. dir: dir isR
  3297. -/|465: O: O930 (predict-no)
  3298. I see 1 and I'm going to do: predict-no
  3299. ENV: Agent did: predict-no for direction R in state State-B
  3300. In State-B moving R
  3301. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3302. predict error 0
  3303. dir: dir isL
  3304. \-/466: O: O931 (predict-yes)
  3305. I see 1 and I'm going to do: predict-yes
  3306. ENV: Agent did: predict-yes for direction L in state State-B
  3307. In State-B moving L
  3308. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  3309. predict error 0
  3310. dir: dir isU
  3311. |\-467: O: O934 (predict-no)
  3312. I see 1 and I'm going to do: predict-no
  3313. ENV: Agent did: predict-no for direction U in state State-A
  3314. In State-A moving U
  3315. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3316. predict error 0
  3317. dir: dir isR
  3318. /|\468: O: O935 (predict-yes)
  3319. I see 1 and I'm going to do: predict-yes
  3320. ENV: Agent did: predict-yes for direction R in state State-A
  3321. In State-A moving R
  3322. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  3323. predict error 0
  3324. dir: dir isL
  3325. -/|469: O: O937 (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 isR
  3332. \-/470: O: O939 (predict-yes)
  3333. I see 1 and I'm going to do: predict-yes
  3334. ENV: Agent did: predict-yes for direction R in state State-A
  3335. In State-A moving R
  3336. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  3337. predict error 0
  3338. dir: dir isL
  3339. |\471: O: O941 (predict-yes)
  3340. I see 1 and I'm going to do: predict-yes
  3341. ENV: Agent did: predict-yes for direction L in state State-B
  3342. In State-B moving L
  3343. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  3344. predict error 0
  3345. dir: dir isL
  3346. -472: O: O944 (predict-no)
  3347. I see 1 and I'm going to do: predict-no
  3348. ENV: Agent did: predict-no for direction L in state State-A
  3349. In State-A moving L
  3350. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3351. predict error 0
  3352. dir: dir isU
  3353. /|\473: O: O946 (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-A
  3356. In State-A moving U
  3357. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3358. predict error 0
  3359. dir: dir isL
  3360. -/|474: O: O948 (predict-no)
  3361. I see 1 and I'm going to do: predict-no
  3362. ENV: Agent did: predict-no for direction L in state State-A
  3363. In State-A moving L
  3364. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3365. predict error 0
  3366. dir: dir isL
  3367. \-/475: O: O950 (predict-no)
  3368. I see 1 and I'm going to do: predict-no
  3369. ENV: Agent did: predict-no for direction L in state State-A
  3370. In State-A moving L
  3371. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3372. predict error 0
  3373. dir: dir isL
  3374. |\-/476: O: O952 (predict-no)
  3375. I see 1 and I'm going to do: predict-no
  3376. ENV: Agent did: predict-no for direction L in state State-A
  3377. In State-A moving L
  3378. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3379. predict error 0
  3380. dir: dir isL
  3381. |\-477: O: O954 (predict-no)
  3382. I see 1 and I'm going to do: predict-no
  3383. ENV: Agent did: predict-no for direction L in state State-A
  3384. In State-A moving L
  3385. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3386. predict error 0
  3387. dir: dir isR
  3388. /|\478: O: O955 (predict-yes)
  3389. I see 1 and I'm going to do: predict-yes
  3390. ENV: Agent did: predict-yes for direction R in state State-A
  3391. In State-A moving R
  3392. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  3393. predict error 0
  3394. dir: dir isL
  3395. -/|479: O: O957 (predict-yes)
  3396. I see 1 and I'm going to do: predict-yes
  3397. ENV: Agent did: predict-yes for direction L in state State-B
  3398. In State-B moving L
  3399. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  3400. predict error 0
  3401. dir: dir isR
  3402. \480: O: O959 (predict-yes)
  3403. I see 1 and I'm going to do: predict-yes
  3404. ENV: Agent did: predict-yes for direction R in state State-A
  3405. In State-A moving R
  3406. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  3407. predict error 0
  3408. dir: dir isL
  3409. -/|481: O: O961 (predict-yes)
  3410. I see 1 and I'm going to do: predict-yes
  3411. ENV: Agent did: predict-yes for direction L in state State-B
  3412. In State-B moving L
  3413. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  3414. predict error 0
  3415. dir: dir isL
  3416. \482: O: O964 (predict-no)
  3417. I see 1 and I'm going to do: predict-no
  3418. ENV: Agent did: predict-no for direction L in state State-A
  3419. In State-A moving L
  3420. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3421. predict error 0
  3422. dir: dir isR
  3423. -/|483: O: O965 (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 isR
  3430. \484: O: O968 (predict-no)
  3431. I see 1 and I'm going to do: predict-no
  3432. ENV: Agent did: predict-no for direction R in state State-B
  3433. In State-B moving R
  3434. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3435. predict error 0
  3436. dir: dir isR
  3437. -/|485: O: O970 (predict-no)
  3438. I see 1 and I'm going to do: predict-no
  3439. ENV: Agent did: predict-no for direction R in state State-B
  3440. In State-B moving R
  3441. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3442. predict error 0
  3443. dir: dir isU
  3444. \-/486: O: O972 (predict-no)
  3445. I see 1 and I'm going to do: predict-no
  3446. ENV: Agent did: predict-no for direction U in state State-B
  3447. In State-B moving U
  3448. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3449. predict error 0
  3450. dir: dir isL
  3451. |\-487: O: O973 (predict-yes)
  3452. I see 1 and I'm going to do: predict-yes
  3453. ENV: Agent did: predict-yes for direction L in state State-B
  3454. In State-B moving L
  3455. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  3456. predict error 0
  3457. dir: dir isL
  3458. /|\488: O: O976 (predict-no)
  3459. I see 1 and I'm going to do: predict-no
  3460. ENV: Agent did: predict-no for direction L in state State-A
  3461. In State-A moving L
  3462. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3463. predict error 0
  3464. dir: dir isU
  3465. -/|489: O: O978 (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-A
  3468. In State-A moving U
  3469. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3470. predict error 0
  3471. dir: dir isR
  3472. \-/490: O: O979 (predict-yes)
  3473. I see 1 and I'm going to do: predict-yes
  3474. ENV: Agent did: predict-yes for direction R in state State-A
  3475. In State-A moving R
  3476. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  3477. predict error 0
  3478. dir: dir isU
  3479. |\-491: O: O982 (predict-no)
  3480. I see 1 and I'm going to do: predict-no
  3481. ENV: Agent did: predict-no for direction U in state State-B
  3482. In State-B moving U
  3483. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3484. predict error 0
  3485. dir: dir isL
  3486. /492: O: O983 (predict-yes)
  3487. I see 1 and I'm going to do: predict-yes
  3488. ENV: Agent did: predict-yes for direction L in state State-B
  3489. In State-B moving L
  3490. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  3491. predict error 0
  3492. dir: dir isR
  3493. |\-493: O: O985 (predict-yes)
  3494. I see 1 and I'm going to do: predict-yes
  3495. ENV: Agent did: predict-yes for direction R in state State-A
  3496. In State-A moving R
  3497. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  3498. predict error 0
  3499. dir: dir isU
  3500. /|\494: O: O988 (predict-no)
  3501. I see 1 and I'm going to do: predict-no
  3502. ENV: Agent did: predict-no for direction U in state State-B
  3503. In State-B moving U
  3504. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3505. predict error 0
  3506. dir: dir isR
  3507. -/|495: O: O990 (predict-no)
  3508. I see 1 and I'm going to do: predict-no
  3509. ENV: Agent did: predict-no for direction R in state State-B
  3510. In State-B moving R
  3511. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3512. predict error 0
  3513. dir: dir isU
  3514. \-/496: O: O992 (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 isR
  3521. |\-497: O: O994 (predict-no)
  3522. I see 1 and I'm going to do: predict-no
  3523. ENV: Agent did: predict-no for direction R in state State-B
  3524. In State-B moving R
  3525. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3526. predict error 0
  3527. dir: dir isR
  3528. /|\498: O: O996 (predict-no)
  3529. I see 1 and I'm going to do: predict-no
  3530. ENV: Agent did: predict-no for direction R in state State-B
  3531. In State-B moving R
  3532. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3533. predict error 0
  3534. dir: dir isU
  3535. -/499: O: O998 (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-B
  3538. In State-B moving U
  3539. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3540. predict error 0
  3541. dir: dir isR
  3542. |\-500: O: O1000 (predict-no)
  3543. I see 1 and I'm going to do: predict-no
  3544. ENV: Agent did: predict-no for direction R in state State-B
  3545. In State-B moving R
  3546. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3547. predict error 0
  3548. dir: dir isR
  3549. /|\-/|501: O: O1002 (predict-no)
  3550. I see 1 and I'm going to do: predict-no
  3551. ENV: Agent did: predict-no for direction R in state State-B
  3552. In State-B moving R
  3553. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3554. predict error 0
  3555. dir: dir isR
  3556. \502: O: O1004 (predict-no)
  3557. I see 1 and I'm going to do: predict-no
  3558. ENV: Agent did: predict-no for direction R in state State-B
  3559. In State-B moving R
  3560. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3561. predict error 0
  3562. dir: dir isL
  3563. -/|503: O: O1005 (predict-yes)
  3564. I see 1 and I'm going to do: predict-yes
  3565. ENV: Agent did: predict-yes for direction L in state State-B
  3566. In State-B moving L
  3567. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  3568. predict error 0
  3569. dir: dir isU
  3570. \-/504: O: O1008 (predict-no)
  3571. I see 1 and I'm going to do: predict-no
  3572. ENV: Agent did: predict-no for direction U in state State-A
  3573. In State-A moving U
  3574. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3575. predict error 0
  3576. dir: dir isR
  3577. |505: O: O1009 (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 isR
  3584. \-/506: O: O1012 (predict-no)
  3585. I see 1 and I'm going to do: predict-no
  3586. ENV: Agent did: predict-no for direction R in state State-B
  3587. In State-B moving R
  3588. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3589. predict error 0
  3590. dir: dir isR
  3591. |\-507: O: O1014 (predict-no)
  3592. I see 1 and I'm going to do: predict-no
  3593. ENV: Agent did: predict-no for direction R in state State-B
  3594. In State-B moving R
  3595. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3596. predict error 0
  3597. dir: dir isU
  3598. /|\508: O: O1016 (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-B
  3601. In State-B moving U
  3602. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3603. predict error 0
  3604. dir: dir isU
  3605. -/|509: O: O1018 (predict-no)
  3606. I see 1 and I'm going to do: predict-no
  3607. ENV: Agent did: predict-no for direction U in state State-B
  3608. In State-B moving U
  3609. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3610. predict error 0
  3611. dir: dir isU
  3612. \-/510: O: O1020 (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-B
  3615. In State-B moving U
  3616. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3617. predict error 0
  3618. dir: dir isR
  3619. |\-/511: O: O1022 (predict-no)
  3620. I see 1 and I'm going to do: predict-no
  3621. ENV: Agent did: predict-no for direction R in state State-B
  3622. In State-B moving R
  3623. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3624. predict error 0
  3625. dir: dir isR
  3626. |512: O: O1024 (predict-no)
  3627. I see 1 and I'm going to do: predict-no
  3628. ENV: Agent did: predict-no for direction R in state State-B
  3629. In State-B moving R
  3630. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3631. predict error 0
  3632. dir: dir isR
  3633. \-/513: O: O1026 (predict-no)
  3634. I see 1 and I'm going to do: predict-no
  3635. ENV: Agent did: predict-no for direction R in state State-B
  3636. In State-B moving R
  3637. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3638. predict error 0
  3639. dir: dir isL
  3640. |\-514: O: O1027 (predict-yes)
  3641. I see 1 and I'm going to do: predict-yes
  3642. ENV: Agent did: predict-yes for direction L in state State-B
  3643. In State-B moving L
  3644. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  3645. predict error 0
  3646. dir: dir isL
  3647. /|\515: O: O1030 (predict-no)
  3648. I see 1 and I'm going to do: predict-no
  3649. ENV: Agent did: predict-no for direction L in state State-A
  3650. In State-A moving L
  3651. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3652. predict error 0
  3653. dir: dir isU
  3654. -/516: O: O1032 (predict-no)
  3655. I see 1 and I'm going to do: predict-no
  3656. ENV: Agent did: predict-no for direction U in state State-A
  3657. In State-A moving U
  3658. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3659. predict error 0
  3660. dir: dir isL
  3661. |\517: O: O1034 (predict-no)
  3662. I see 1 and I'm going to do: predict-no
  3663. ENV: Agent did: predict-no for direction L in state State-A
  3664. In State-A moving L
  3665. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3666. predict error 0
  3667. dir: dir isU
  3668. -/|\518: O: O1036 (predict-no)
  3669. I see 1 and I'm going to do: predict-no
  3670. ENV: Agent did: predict-no for direction U in state State-A
  3671. In State-A moving U
  3672. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3673. predict error 0
  3674. dir: dir isU
  3675. -/|519: O: O1038 (predict-no)
  3676. I see 1 and I'm going to do: predict-no
  3677. ENV: Agent did: predict-no for direction U in state State-A
  3678. In State-A moving U
  3679. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3680. predict error 0
  3681. dir: dir isU
  3682. \-520: O: O1040 (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-A
  3685. In State-A moving U
  3686. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3687. predict error 0
  3688. dir: dir isL
  3689. /521: O: O1042 (predict-no)
  3690. I see 1 and I'm going to do: predict-no
  3691. ENV: Agent did: predict-no for direction L in state State-A
  3692. In State-A moving L
  3693. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3694. predict error 0
  3695. dir: dir isL
  3696. |522: O: O1044 (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 isU
  3703. \-/523: O: O1046 (predict-no)
  3704. I see 1 and I'm going to do: predict-no
  3705. ENV: Agent did: predict-no for direction U in state State-A
  3706. In State-A moving U
  3707. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3708. predict error 0
  3709. dir: dir isL
  3710. |\-524: O: O1048 (predict-no)
  3711. I see 1 and I'm going to do: predict-no
  3712. ENV: Agent did: predict-no for direction L in state State-A
  3713. In State-A moving L
  3714. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3715. predict error 0
  3716. dir: dir isL
  3717. /|\525: O: O1050 (predict-no)
  3718. I see 1 and I'm going to do: predict-no
  3719. ENV: Agent did: predict-no for direction L in state State-A
  3720. In State-A moving L
  3721. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3722. predict error 0
  3723. dir: dir isR
  3724. -/|526: O: O1051 (predict-yes)
  3725. I see 1 and I'm going to do: predict-yes
  3726. ENV: Agent did: predict-yes for direction R in state State-A
  3727. In State-A moving R
  3728. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  3729. predict error 0
  3730. dir: dir isL
  3731. \-/527: O: O1053 (predict-yes)
  3732. I see 1 and I'm going to do: predict-yes
  3733. ENV: Agent did: predict-yes for direction L in state State-B
  3734. In State-B moving L
  3735. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  3736. predict error 0
  3737. dir: dir isL
  3738. |\528: O: O1056 (predict-no)
  3739. I see 1 and I'm going to do: predict-no
  3740. ENV: Agent did: predict-no for direction L in state State-A
  3741. In State-A moving L
  3742. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3743. predict error 0
  3744. dir: dir isU
  3745. -/|529: O: O1058 (predict-no)
  3746. I see 1 and I'm going to do: predict-no
  3747. ENV: Agent did: predict-no for direction U in state State-A
  3748. In State-A moving U
  3749. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3750. predict error 0
  3751. dir: dir isL
  3752. \-530: O: O1060 (predict-no)
  3753. I see 1 and I'm going to do: predict-no
  3754. ENV: Agent did: predict-no for direction L in state State-A
  3755. In State-A moving L
  3756. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3757. predict error 0
  3758. dir: dir isU
  3759. /|\531: O: O1062 (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. -532: O: O1063 (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. /|\533: O: O1065 (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. -/|534: O: O1068 (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. \-/535: O: O1070 (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. |\-536: O: O1071 (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 isR
  3801. /|\537: O: O1074 (predict-no)
  3802. I see 1 and I'm going to do: predict-no
  3803. ENV: Agent did: predict-no for direction R in state State-B
  3804. In State-B moving R
  3805. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3806. predict error 0
  3807. dir: dir isL
  3808. -/538: O: O1075 (predict-yes)
  3809. I see 1 and I'm going to do: predict-yes
  3810. ENV: Agent did: predict-yes for direction L in state State-B
  3811. In State-B moving L
  3812. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  3813. predict error 0
  3814. dir: dir isR
  3815. |\539: O: O1077 (predict-yes)
  3816. I see 1 and I'm going to do: predict-yes
  3817. ENV: Agent did: predict-yes for direction R in state State-A
  3818. In State-A moving R
  3819. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  3820. predict error 0
  3821. dir: dir isL
  3822. -/|\540: O: O1079 (predict-yes)
  3823. I see 1 and I'm going to do: predict-yes
  3824. ENV: Agent did: predict-yes for direction L in state State-B
  3825. In State-B moving L
  3826. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  3827. predict error 0
  3828. dir: dir isL
  3829. -/|541: O: O1082 (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 isU
  3836. \542: O: O1084 (predict-no)
  3837. I see 1 and I'm going to do: predict-no
  3838. ENV: Agent did: predict-no for direction U in state State-A
  3839. In State-A moving U
  3840. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3841. predict error 0
  3842. dir: dir isU
  3843. -/|\sleeping...
  3844. -543: O: O1086 (predict-no)
  3845. I see 1 and I'm going to do: predict-no
  3846. ENV: Agent did: predict-no for direction U in state State-A
  3847. In State-A moving U
  3848. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3849. predict error 0
  3850. dir: dir isR
  3851. /|\544: O: O1087 (predict-yes)
  3852. I see 1 and I'm going to do: predict-yes
  3853. ENV: Agent did: predict-yes for direction R in state State-A
  3854. In State-A moving R
  3855. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  3856. predict error 0
  3857. dir: dir isU
  3858. -/|545: O: O1090 (predict-no)
  3859. I see 1 and I'm going to do: predict-no
  3860. ENV: Agent did: predict-no for direction U in state State-B
  3861. In State-B moving U
  3862. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3863. predict error 0
  3864. dir: dir isU
  3865. \-/546: O: O1092 (predict-no)
  3866. I see 1 and I'm going to do: predict-no
  3867. ENV: Agent did: predict-no for direction U in state State-B
  3868. In State-B moving U
  3869. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3870. predict error 0
  3871. dir: dir isL
  3872. |\-547: O: O1093 (predict-yes)
  3873. I see 1 and I'm going to do: predict-yes
  3874. ENV: Agent did: predict-yes for direction L in state State-B
  3875. In State-B moving L
  3876. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  3877. predict error 0
  3878. dir: dir isR
  3879. /|548: O: O1095 (predict-yes)
  3880. I see 1 and I'm going to do: predict-yes
  3881. ENV: Agent did: predict-yes for direction R in state State-A
  3882. In State-A moving R
  3883. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  3884. predict error 0
  3885. dir: dir isL
  3886. \-/549: O: O1097 (predict-yes)
  3887. I see 1 and I'm going to do: predict-yes
  3888. ENV: Agent did: predict-yes for direction L in state State-B
  3889. In State-B moving L
  3890. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  3891. predict error 0
  3892. dir: dir isL
  3893. |\550: O: O1100 (predict-no)
  3894. I see 1 and I'm going to do: predict-no
  3895. ENV: Agent did: predict-no for direction L in state State-A
  3896. In State-A moving L
  3897. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3898. predict error 0
  3899. dir: dir isL
  3900. -/551: O: O1102 (predict-no)
  3901. I see 1 and I'm going to do: predict-no
  3902. ENV: Agent did: predict-no for direction L in state State-A
  3903. In State-A moving L
  3904. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3905. predict error 0
  3906. dir: dir isL
  3907. |552: O: O1104 (predict-no)
  3908. I see 1 and I'm going to do: predict-no
  3909. ENV: Agent did: predict-no for direction L in state State-A
  3910. In State-A moving L
  3911. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3912. predict error 0
  3913. dir: dir isL
  3914. \-/553: O: O1106 (predict-no)
  3915. I see 1 and I'm going to do: predict-no
  3916. ENV: Agent did: predict-no for direction L in state State-A
  3917. In State-A moving L
  3918. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3919. predict error 0
  3920. dir: dir isL
  3921. |\-554: O: O1108 (predict-no)
  3922. I see 1 and I'm going to do: predict-no
  3923. ENV: Agent did: predict-no for direction L in state State-A
  3924. In State-A moving L
  3925. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3926. predict error 0
  3927. dir: dir isR
  3928. /|\555: O: O1109 (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. -/|556: O: O1112 (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 isU
  3942. \-/557: O: O1114 (predict-no)
  3943. I see 1 and I'm going to do: predict-no
  3944. ENV: Agent did: predict-no for direction U in state State-B
  3945. In State-B moving U
  3946. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3947. predict error 0
  3948. dir: dir isU
  3949. |\558: O: O1116 (predict-no)
  3950. I see 1 and I'm going to do: predict-no
  3951. ENV: Agent did: predict-no for direction U in state State-B
  3952. In State-B moving U
  3953. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3954. predict error 0
  3955. dir: dir isU
  3956. -/|559: O: O1118 (predict-no)
  3957. I see 1 and I'm going to do: predict-no
  3958. ENV: Agent did: predict-no for direction U in state State-B
  3959. In State-B moving U
  3960. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3961. predict error 0
  3962. dir: dir isR
  3963. \-/|560: O: O1120 (predict-no)
  3964. I see 1 and I'm going to do: predict-no
  3965. ENV: Agent did: predict-no for direction R in state State-B
  3966. In State-B moving R
  3967. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3968. predict error 0
  3969. dir: dir isU
  3970. \561: O: O1122 (predict-no)
  3971. I see 1 and I'm going to do: predict-no
  3972. ENV: Agent did: predict-no for direction U in state State-B
  3973. In State-B moving U
  3974. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3975. predict error 0
  3976. dir: dir isL
  3977. -562: O: O1123 (predict-yes)
  3978. I see 1 and I'm going to do: predict-yes
  3979. ENV: Agent did: predict-yes for direction L in state State-B
  3980. In State-B moving L
  3981. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  3982. predict error 0
  3983. dir: dir isL
  3984. /|\563: O: O1126 (predict-no)
  3985. I see 1 and I'm going to do: predict-no
  3986. ENV: Agent did: predict-no for direction L in state State-A
  3987. In State-A moving L
  3988. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3989. predict error 0
  3990. dir: dir isU
  3991. -/|564: O: O1128 (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-A
  3994. In State-A moving U
  3995. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3996. predict error 0
  3997. dir: dir isR
  3998. \565: O: O1129 (predict-yes)
  3999. I see 1 and I'm going to do: predict-yes
  4000. ENV: Agent did: predict-yes for direction R in state State-A
  4001. In State-A moving R
  4002. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  4003. predict error 0
  4004. dir: dir isL
  4005. -/|566: O: O1131 (predict-yes)
  4006. I see 1 and I'm going to do: predict-yes
  4007. ENV: Agent did: predict-yes for direction L in state State-B
  4008. In State-B moving L
  4009. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  4010. predict error 0
  4011. dir: dir isR
  4012. \-/567: O: O1133 (predict-yes)
  4013. I see 1 and I'm going to do: predict-yes
  4014. ENV: Agent did: predict-yes for direction R in state State-A
  4015. In State-A moving R
  4016. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  4017. predict error 0
  4018. dir: dir isL
  4019. |568: O: O1135 (predict-yes)
  4020. I see 1 and I'm going to do: predict-yes
  4021. ENV: Agent did: predict-yes for direction L in state State-B
  4022. In State-B moving L
  4023. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  4024. predict error 0
  4025. dir: dir isR
  4026. \-/569: O: O1137 (predict-yes)
  4027. I see 1 and I'm going to do: predict-yes
  4028. ENV: Agent did: predict-yes for direction R in state State-A
  4029. In State-A moving R
  4030. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  4031. predict error 0
  4032. dir: dir isR
  4033. |\-570: O: O1140 (predict-no)
  4034. I see 1 and I'm going to do: predict-no
  4035. ENV: Agent did: predict-no for direction R in state State-B
  4036. In State-B moving R
  4037. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4038. predict error 0
  4039. dir: dir isR
  4040. /|571: O: O1142 (predict-no)
  4041. I see 1 and I'm going to do: predict-no
  4042. ENV: Agent did: predict-no for direction R in state State-B
  4043. In State-B moving R
  4044. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4045. predict error 0
  4046. dir: dir isU
  4047. \572: O: O1144 (predict-no)
  4048. I see 1 and I'm going to do: predict-no
  4049. ENV: Agent did: predict-no for direction U in state State-B
  4050. In State-B moving U
  4051. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4052. predict error 0
  4053. dir: dir isU
  4054. -/573: O: O1146 (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 isR
  4061. |\-574: O: O1148 (predict-no)
  4062. I see 1 and I'm going to do: predict-no
  4063. ENV: Agent did: predict-no for direction R in state State-B
  4064. In State-B moving R
  4065. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4066. predict error 0
  4067. dir: dir isR
  4068. /|575: O: O1150 (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 isL
  4075. \-/576: O: O1151 (predict-yes)
  4076. I see 1 and I'm going to do: predict-yes
  4077. ENV: Agent did: predict-yes for direction L in state State-B
  4078. In State-B moving L
  4079. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  4080. predict error 0
  4081. dir: dir isU
  4082. |\577: O: O1154 (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-A
  4085. In State-A moving U
  4086. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4087. predict error 0
  4088. dir: dir isU
  4089. -/|578: O: O1156 (predict-no)
  4090. I see 1 and I'm going to do: predict-no
  4091. ENV: Agent did: predict-no for direction U in state State-A
  4092. In State-A moving U
  4093. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4094. predict error 0
  4095. dir: dir isL
  4096. \-/579: O: O1158 (predict-no)
  4097. I see 1 and I'm going to do: predict-no
  4098. ENV: Agent did: predict-no for direction L in state State-A
  4099. In State-A moving L
  4100. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4101. predict error 0
  4102. dir: dir isU
  4103. |\580: O: O1160 (predict-no)
  4104. I see 1 and I'm going to do: predict-no
  4105. ENV: Agent did: predict-no for direction U in state State-A
  4106. In State-A moving U
  4107. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4108. predict error 0
  4109. dir: dir isU
  4110. -/|581: O: O1162 (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-A
  4113. In State-A moving U
  4114. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4115. predict error 0
  4116. dir: dir isR
  4117. \582: O: O1163 (predict-yes)
  4118. I see 1 and I'm going to do: predict-yes
  4119. ENV: Agent did: predict-yes for direction R in state State-A
  4120. In State-A moving R
  4121. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  4122. predict error 0
  4123. dir: dir isL
  4124. -/|583: O: O1165 (predict-yes)
  4125. I see 1 and I'm going to do: predict-yes
  4126. ENV: Agent did: predict-yes for direction L in state State-B
  4127. In State-B moving L
  4128. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  4129. predict error 0
  4130. dir: dir isR
  4131. \-/584: O: O1167 (predict-yes)
  4132. I see 1 and I'm going to do: predict-yes
  4133. ENV: Agent did: predict-yes for direction R in state State-A
  4134. In State-A moving R
  4135. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  4136. predict error 0
  4137. dir: dir isL
  4138. |\-585: O: O1169 (predict-yes)
  4139. I see 1 and I'm going to do: predict-yes
  4140. ENV: Agent did: predict-yes for direction L in state State-B
  4141. In State-B moving L
  4142. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  4143. predict error 0
  4144. dir: dir isL
  4145. /|586: O: O1172 (predict-no)
  4146. I see 1 and I'm going to do: predict-no
  4147. ENV: Agent did: predict-no for direction L in state State-A
  4148. In State-A moving L
  4149. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4150. predict error 0
  4151. dir: dir isR
  4152. \-/|587: O: O1173 (predict-yes)
  4153. I see 1 and I'm going to do: predict-yes
  4154. ENV: Agent did: predict-yes for direction R in state State-A
  4155. In State-A moving R
  4156. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  4157. predict error 0
  4158. dir: dir isR
  4159. \588: O: O1176 (predict-no)
  4160. I see 1 and I'm going to do: predict-no
  4161. ENV: Agent did: predict-no for direction R in state State-B
  4162. In State-B moving R
  4163. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4164. predict error 0
  4165. dir: dir isR
  4166. -/|589: O: O1178 (predict-no)
  4167. I see 1 and I'm going to do: predict-no
  4168. ENV: Agent did: predict-no for direction R in state State-B
  4169. In State-B moving R
  4170. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4171. predict error 0
  4172. dir: dir isU
  4173. \-590: O: O1180 (predict-no)
  4174. I see 1 and I'm going to do: predict-no
  4175. ENV: Agent did: predict-no for direction U in state State-B
  4176. In State-B moving U
  4177. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4178. predict error 0
  4179. dir: dir isU
  4180. /|591: O: O1182 (predict-no)
  4181. I see 1 and I'm going to do: predict-no
  4182. ENV: Agent did: predict-no for direction U in state State-B
  4183. In State-B moving U
  4184. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4185. predict error 0
  4186. dir: dir isR
  4187. \592: O: O1184 (predict-no)
  4188. I see 1 and I'm going to do: predict-no
  4189. ENV: Agent did: predict-no for direction R in state State-B
  4190. In State-B moving R
  4191. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4192. predict error 0
  4193. dir: dir isL
  4194. -/|593: O: O1185 (predict-yes)
  4195. I see 1 and I'm going to do: predict-yes
  4196. ENV: Agent did: predict-yes for direction L in state State-B
  4197. In State-B moving L
  4198. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  4199. predict error 0
  4200. dir: dir isU
  4201. \-/594: O: O1188 (predict-no)
  4202. I see 1 and I'm going to do: predict-no
  4203. ENV: Agent did: predict-no for direction U in state State-A
  4204. In State-A moving U
  4205. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4206. predict error 0
  4207. dir: dir isU
  4208. |\-595: O: O1190 (predict-no)
  4209. I see 1 and I'm going to do: predict-no
  4210. ENV: Agent did: predict-no for direction U in state State-A
  4211. In State-A moving U
  4212. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4213. predict error 0
  4214. dir: dir isU
  4215. /|\596: O: O1192 (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. -/|597: O: O1193 (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 isL
  4229. \-/598: O: O1195 (predict-yes)
  4230. I see 1 and I'm going to do: predict-yes
  4231. ENV: Agent did: predict-yes for direction L in state State-B
  4232. In State-B moving L
  4233. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  4234. predict error 0
  4235. dir: dir isL
  4236. |\599: O: O1198 (predict-no)
  4237. I see 1 and I'm going to do: predict-no
  4238. ENV: Agent did: predict-no for direction L in state State-A
  4239. In State-A moving L
  4240. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4241. predict error 0
  4242. dir: dir isL
  4243. -/600: O: O1200 (predict-no)
  4244. I see 1 and I'm going to do: predict-no
  4245. ENV: Agent did: predict-no for direction L in state State-A
  4246. In State-A moving L
  4247. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4248. predict error 0
  4249. dir: dir isR
  4250. |\601: O: O1201 (predict-yes)
  4251. I see 1 and I'm going to do: predict-yes
  4252. ENV: Agent did: predict-yes for direction R in state State-A
  4253. In State-A moving R
  4254. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  4255. predict error 0
  4256. dir: dir isR
  4257. -602: O: O1204 (predict-no)
  4258. I see 1 and I'm going to do: predict-no
  4259. ENV: Agent did: predict-no for direction R in state State-B
  4260. In State-B moving R
  4261. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4262. predict error 0
  4263. dir: dir isL
  4264. /|\603: O: O1205 (predict-yes)
  4265. I see 1 and I'm going to do: predict-yes
  4266. ENV: Agent did: predict-yes for direction L in state State-B
  4267. In State-B moving L
  4268. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  4269. predict error 0
  4270. dir: dir isU
  4271. -/604: O: O1208 (predict-no)
  4272. I see 1 and I'm going to do: predict-no
  4273. ENV: Agent did: predict-no for direction U in state State-A
  4274. In State-A moving U
  4275. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4276. predict error 0
  4277. dir: dir isU
  4278. |\605: O: O1210 (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 isU
  4285. -/606: O: O1212 (predict-no)
  4286. I see 1 and I'm going to do: predict-no
  4287. ENV: Agent did: predict-no for direction U in state State-A
  4288. In State-A moving U
  4289. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4290. predict error 0
  4291. dir: dir isR
  4292. |\-607: O: O1213 (predict-yes)
  4293. I see 1 and I'm going to do: predict-yes
  4294. ENV: Agent did: predict-yes for direction R in state State-A
  4295. In State-A moving R
  4296. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  4297. predict error 0
  4298. dir: dir isL
  4299. /|\608: O: O1215 (predict-yes)
  4300. I see 1 and I'm going to do: predict-yes
  4301. ENV: Agent did: predict-yes for direction L in state State-B
  4302. In State-B moving L
  4303. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  4304. predict error 0
  4305. dir: dir isL
  4306. -/|609: O: O1218 (predict-no)
  4307. I see 1 and I'm going to do: predict-no
  4308. ENV: Agent did: predict-no for direction L in state State-A
  4309. In State-A moving L
  4310. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4311. predict error 0
  4312. dir: dir isU
  4313. \-610: O: O1220 (predict-no)
  4314. I see 1 and I'm going to do: predict-no
  4315. ENV: Agent did: predict-no for direction U in state State-A
  4316. In State-A moving U
  4317. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4318. predict error 0
  4319. dir: dir isU
  4320. /611: O: O1222 (predict-no)
  4321. I see 1 and I'm going to do: predict-no
  4322. ENV: Agent did: predict-no for direction U in state State-A
  4323. In State-A moving U
  4324. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4325. predict error 0
  4326. dir: dir isL
  4327. |612: O: O1224 (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 isU
  4334. \-613: O: O1226 (predict-no)
  4335. I see 1 and I'm going to do: predict-no
  4336. ENV: Agent did: predict-no for direction U in state State-A
  4337. In State-A moving U
  4338. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4339. predict error 0
  4340. dir: dir isR
  4341. /|614: O: O1227 (predict-yes)
  4342. I see 1 and I'm going to do: predict-yes
  4343. ENV: Agent did: predict-yes for direction R in state State-A
  4344. In State-A moving R
  4345. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  4346. predict error 0
  4347. dir: dir isR
  4348. \-/|615: O: O1230 (predict-no)
  4349. I see 1 and I'm going to do: predict-no
  4350. ENV: Agent did: predict-no for direction R in state State-B
  4351. In State-B moving R
  4352. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4353. predict error 0
  4354. dir: dir isR
  4355. \-616: O: O1232 (predict-no)
  4356. I see 1 and I'm going to do: predict-no
  4357. ENV: Agent did: predict-no for direction R in state State-B
  4358. In State-B moving R
  4359. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4360. predict error 0
  4361. dir: dir isU
  4362. /|617: O: O1234 (predict-no)
  4363. I see 1 and I'm going to do: predict-no
  4364. ENV: Agent did: predict-no for direction U in state State-B
  4365. In State-B moving U
  4366. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4367. predict error 0
  4368. dir: dir isR
  4369. \-/618: O: O1236 (predict-no)
  4370. I see 1 and I'm going to do: predict-no
  4371. ENV: Agent did: predict-no for direction R in state State-B
  4372. In State-B moving R
  4373. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4374. predict error 0
  4375. dir: dir isR
  4376. |\619: O: O1238 (predict-no)
  4377. I see 1 and I'm going to do: predict-no
  4378. ENV: Agent did: predict-no for direction R in state State-B
  4379. In State-B moving R
  4380. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4381. predict error 0
  4382. dir: dir isL
  4383. -/|620: O: O1239 (predict-yes)
  4384. I see 1 and I'm going to do: predict-yes
  4385. ENV: Agent did: predict-yes for direction L in state State-B
  4386. In State-B moving L
  4387. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  4388. predict error 0
  4389. dir: dir isU
  4390. \-/621: O: O1242 (predict-no)
  4391. I see 1 and I'm going to do: predict-no
  4392. ENV: Agent did: predict-no for direction U in state State-A
  4393. In State-A moving U
  4394. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4395. predict error 0
  4396. dir: dir isL
  4397. |622: O: O1244 (predict-no)
  4398. I see 1 and I'm going to do: predict-no
  4399. ENV: Agent did: predict-no for direction L in state State-A
  4400. In State-A moving L
  4401. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4402. predict error 0
  4403. dir: dir isU
  4404. \-/623: O: O1246 (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. |\624: O: O1248 (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 isL
  4418. -/|625: O: O1250 (predict-no)
  4419. I see 1 and I'm going to do: predict-no
  4420. ENV: Agent did: predict-no for direction L in state State-A
  4421. In State-A moving L
  4422. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4423. predict error 0
  4424. dir: dir isR
  4425. \-/626: O: O1251 (predict-yes)
  4426. I see 1 and I'm going to do: predict-yes
  4427. ENV: Agent did: predict-yes for direction R in state State-A
  4428. In State-A moving R
  4429. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  4430. predict error 0
  4431. dir: dir isR
  4432. |\627: O: O1254 (predict-no)
  4433. I see 1 and I'm going to do: predict-no
  4434. ENV: Agent did: predict-no for direction R in state State-B
  4435. In State-B moving R
  4436. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4437. predict error 0
  4438. dir: dir isR
  4439. -/|628: O: O1256 (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 isU
  4446. \-/|629: O: O1258 (predict-no)
  4447. I see 1 and I'm going to do: predict-no
  4448. ENV: Agent did: predict-no for direction U in state State-B
  4449. In State-B moving U
  4450. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4451. predict error 0
  4452. dir: dir isL
  4453. \-/630: O: O1259 (predict-yes)
  4454. I see 1 and I'm going to do: predict-yes
  4455. ENV: Agent did: predict-yes for direction L in state State-B
  4456. In State-B moving L
  4457. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  4458. predict error 0
  4459. dir: dir isU
  4460. |\-631: O: O1262 (predict-no)
  4461. I see 1 and I'm going to do: predict-no
  4462. ENV: Agent did: predict-no for direction U in state State-A
  4463. In State-A moving U
  4464. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4465. predict error 0
  4466. dir: dir isU
  4467. /632: O: O1264 (predict-no)
  4468. I see 1 and I'm going to do: predict-no
  4469. ENV: Agent did: predict-no for direction U in state State-A
  4470. In State-A moving U
  4471. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4472. predict error 0
  4473. dir: dir isU
  4474. |\-633: O: O1266 (predict-no)
  4475. I see 1 and I'm going to do: predict-no
  4476. ENV: Agent did: predict-no for direction U in state State-A
  4477. In State-A moving U
  4478. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4479. predict error 0
  4480. dir: dir isR
  4481. /|\634: O: O1267 (predict-yes)
  4482. I see 1 and I'm going to do: predict-yes
  4483. ENV: Agent did: predict-yes for direction R in state State-A
  4484. In State-A moving R
  4485. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  4486. predict error 0
  4487. dir: dir isR
  4488. -/|635: O: O1270 (predict-no)
  4489. I see 1 and I'm going to do: predict-no
  4490. ENV: Agent did: predict-no for direction R in state State-B
  4491. In State-B moving R
  4492. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4493. predict error 0
  4494. dir: dir isR
  4495. \636: O: O1272 (predict-no)
  4496. I see 1 and I'm going to do: predict-no
  4497. ENV: Agent did: predict-no for direction R in state State-B
  4498. In State-B moving R
  4499. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4500. predict error 0
  4501. dir: dir isR
  4502. -/|637: O: O1274 (predict-no)
  4503. I see 1 and I'm going to do: predict-no
  4504. ENV: Agent did: predict-no for direction R in state State-B
  4505. In State-B moving R
  4506. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4507. predict error 0
  4508. dir: dir isL
  4509. \-/638: O: O1275 (predict-yes)
  4510. I see 1 and I'm going to do: predict-yes
  4511. ENV: Agent did: predict-yes for direction L in state State-B
  4512. In State-B moving L
  4513. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  4514. predict error 0
  4515. dir: dir isL
  4516. |\-639: O: O1278 (predict-no)
  4517. I see 1 and I'm going to do: predict-no
  4518. ENV: Agent did: predict-no for direction L in state State-A
  4519. In State-A moving L
  4520. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4521. predict error 0
  4522. dir: dir isR
  4523. /|\640: O: O1279 (predict-yes)
  4524. I see 1 and I'm going to do: predict-yes
  4525. ENV: Agent did: predict-yes for direction R in state State-A
  4526. In State-A moving R
  4527. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  4528. predict error 0
  4529. dir: dir isL
  4530. -/641: O: O1281 (predict-yes)
  4531. I see 1 and I'm going to do: predict-yes
  4532. ENV: Agent did: predict-yes for direction L in state State-B
  4533. In State-B moving L
  4534. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  4535. predict error 0
  4536. dir: dir isR
  4537. |642: O: O1283 (predict-yes)
  4538. I see 1 and I'm going to do: predict-yes
  4539. ENV: Agent did: predict-yes for direction R in state State-A
  4540. In State-A moving R
  4541. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  4542. predict error 0
  4543. dir: dir isR
  4544. \-643: O: O1286 (predict-no)
  4545. I see 1 and I'm going to do: predict-no
  4546. ENV: Agent did: predict-no for direction R in state State-B
  4547. In State-B moving R
  4548. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4549. predict error 0
  4550. dir: dir isL
  4551. /|\644: O: O1287 (predict-yes)
  4552. I see 1 and I'm going to do: predict-yes
  4553. ENV: Agent did: predict-yes for direction L in state State-B
  4554. In State-B moving L
  4555. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  4556. predict error 0
  4557. dir: dir isL
  4558. -/|645: O: O1290 (predict-no)
  4559. I see 1 and I'm going to do: predict-no
  4560. ENV: Agent did: predict-no for direction L in state State-A
  4561. In State-A moving L
  4562. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4563. predict error 0
  4564. dir: dir isR
  4565. \646: O: O1291 (predict-yes)
  4566. I see 1 and I'm going to do: predict-yes
  4567. ENV: Agent did: predict-yes for direction R in state State-A
  4568. In State-A moving R
  4569. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  4570. predict error 0
  4571. dir: dir isU
  4572. -/647: O: O1294 (predict-no)
  4573. I see 1 and I'm going to do: predict-no
  4574. ENV: Agent did: predict-no for direction U in state State-B
  4575. In State-B moving U
  4576. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4577. predict error 0
  4578. dir: dir isL
  4579. |\648: O: O1295 (predict-yes)
  4580. I see 1 and I'm going to do: predict-yes
  4581. ENV: Agent did: predict-yes for direction L in state State-B
  4582. In State-B moving L
  4583. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  4584. predict error 0
  4585. dir: dir isR
  4586. -/|649: O: O1297 (predict-yes)
  4587. I see 1 and I'm going to do: predict-yes
  4588. ENV: Agent did: predict-yes for direction R in state State-A
  4589. In State-A moving R
  4590. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  4591. predict error 0
  4592. dir: dir isR
  4593. \-650: O: O1300 (predict-no)
  4594. I see 1 and I'm going to do: predict-no
  4595. ENV: Agent did: predict-no for direction R in state State-B
  4596. In State-B moving R
  4597. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4598. predict error 0
  4599. dir: dir isU
  4600. /|651: O: O1302 (predict-no)
  4601. I see 1 and I'm going to do: predict-no
  4602. ENV: Agent did: predict-no for direction U in state State-B
  4603. In State-B moving U
  4604. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4605. predict error 0
  4606. dir: dir isU
  4607. \652: O: O1304 (predict-no)
  4608. I see 1 and I'm going to do: predict-no
  4609. ENV: Agent did: predict-no for direction U in state State-B
  4610. In State-B moving U
  4611. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4612. predict error 0
  4613. dir: dir isL
  4614. -/|653: O: O1305 (predict-yes)
  4615. I see 1 and I'm going to do: predict-yes
  4616. ENV: Agent did: predict-yes for direction L in state State-B
  4617. In State-B moving L
  4618. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  4619. predict error 0
  4620. dir: dir isL
  4621. \654: O: O1308 (predict-no)
  4622. I see 1 and I'm going to do: predict-no
  4623. ENV: Agent did: predict-no for direction L in state State-A
  4624. In State-A moving L
  4625. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4626. predict error 0
  4627. dir: dir isU
  4628. -/|655: O: O1310 (predict-no)
  4629. I see 1 and I'm going to do: predict-no
  4630. ENV: Agent did: predict-no for direction U in state State-A
  4631. In State-A moving U
  4632. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4633. predict error 0
  4634. dir: dir isL
  4635. \-/656: O: O1312 (predict-no)
  4636. I see 1 and I'm going to do: predict-no
  4637. ENV: Agent did: predict-no for direction L in state State-A
  4638. In State-A moving L
  4639. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4640. predict error 0
  4641. dir: dir isL
  4642. |\657: O: O1314 (predict-no)
  4643. I see 1 and I'm going to do: predict-no
  4644. ENV: Agent did: predict-no for direction L in state State-A
  4645. In State-A moving L
  4646. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4647. predict error 0
  4648. dir: dir isU
  4649. -/|658: O: O1316 (predict-no)
  4650. I see 1 and I'm going to do: predict-no
  4651. ENV: Agent did: predict-no for direction U in state State-A
  4652. In State-A moving U
  4653. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4654. predict error 0
  4655. dir: dir isL
  4656. \-659: O: O1318 (predict-no)
  4657. I see 1 and I'm going to do: predict-no
  4658. ENV: Agent did: predict-no for direction L in state State-A
  4659. In State-A moving L
  4660. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4661. predict error 0
  4662. dir: dir isL
  4663. /|\660: O: O1320 (predict-no)
  4664. I see 1 and I'm going to do: predict-no
  4665. ENV: Agent did: predict-no for direction L in state State-A
  4666. In State-A moving L
  4667. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4668. predict error 0
  4669. dir: dir isL
  4670. -/|661: O: O1322 (predict-no)
  4671. I see 1 and I'm going to do: predict-no
  4672. ENV: Agent did: predict-no for direction L in state State-A
  4673. In State-A moving L
  4674. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4675. predict error 0
  4676. dir: dir isL
  4677. \662: O: O1324 (predict-no)
  4678. I see 1 and I'm going to do: predict-no
  4679. ENV: Agent did: predict-no for direction L in state State-A
  4680. In State-A moving L
  4681. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4682. predict error 0
  4683. dir: dir isU
  4684. -663: O: O1326 (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 isR
  4691. /664: O: O1327 (predict-yes)
  4692. I see 1 and I'm going to do: predict-yes
  4693. ENV: Agent did: predict-yes for direction R in state State-A
  4694. In State-A moving R
  4695. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  4696. predict error 0
  4697. dir: dir isR
  4698. |\-665: O: O1330 (predict-no)
  4699. I see 1 and I'm going to do: predict-no
  4700. ENV: Agent did: predict-no for direction R in state State-B
  4701. In State-B moving R
  4702. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4703. predict error 0
  4704. dir: dir isR
  4705. /|\666: O: O1332 (predict-no)
  4706. I see 1 and I'm going to do: predict-no
  4707. ENV: Agent did: predict-no for direction R in state State-B
  4708. In State-B moving R
  4709. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4710. predict error 0
  4711. dir: dir isU
  4712. -/|667: O: O1334 (predict-no)
  4713. I see 1 and I'm going to do: predict-no
  4714. ENV: Agent did: predict-no for direction U in state State-B
  4715. In State-B moving U
  4716. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4717. predict error 0
  4718. dir: dir isL
  4719. \-668: O: O1335 (predict-yes)
  4720. I see 1 and I'm going to do: predict-yes
  4721. ENV: Agent did: predict-yes for direction L in state State-B
  4722. In State-B moving L
  4723. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  4724. predict error 0
  4725. dir: dir isR
  4726. /|\669: O: O1337 (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 isL
  4733. -/|670: O: O1339 (predict-yes)
  4734. I see 1 and I'm going to do: predict-yes
  4735. ENV: Agent did: predict-yes for direction L in state State-B
  4736. In State-B moving L
  4737. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  4738. predict error 0
  4739. dir: dir isL
  4740. \-/671: O: O1342 (predict-no)
  4741. I see 1 and I'm going to do: predict-no
  4742. ENV: Agent did: predict-no for direction L in state State-A
  4743. In State-A moving L
  4744. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4745. predict error 0
  4746. dir: dir isR
  4747. |672: O: O1343 (predict-yes)
  4748. I see 1 and I'm going to do: predict-yes
  4749. ENV: Agent did: predict-yes for direction R in state State-A
  4750. In State-A moving R
  4751. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  4752. predict error 0
  4753. dir: dir isR
  4754. \-/673: O: O1346 (predict-no)
  4755. I see 1 and I'm going to do: predict-no
  4756. ENV: Agent did: predict-no for direction R in state State-B
  4757. In State-B moving R
  4758. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4759. predict error 0
  4760. dir: dir isL
  4761. |\-674: O: O1347 (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 isR
  4768. /|\675: O: O1349 (predict-yes)
  4769. I see 1 and I'm going to do: predict-yes
  4770. ENV: Agent did: predict-yes for direction R in state State-A
  4771. In State-A moving R
  4772. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  4773. predict error 0
  4774. dir: dir isU
  4775. -/|676: O: O1352 (predict-no)
  4776. I see 1 and I'm going to do: predict-no
  4777. ENV: Agent did: predict-no for direction U in state State-B
  4778. In State-B moving U
  4779. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4780. predict error 0
  4781. dir: dir isR
  4782. \-677: O: O1354 (predict-no)
  4783. I see 1 and I'm going to do: predict-no
  4784. ENV: Agent did: predict-no for direction R in state State-B
  4785. In State-B moving R
  4786. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4787. predict error 0
  4788. dir: dir isR
  4789. /678: O: O1356 (predict-no)
  4790. I see 1 and I'm going to do: predict-no
  4791. ENV: Agent did: predict-no for direction R in state State-B
  4792. In State-B moving R
  4793. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4794. predict error 0
  4795. dir: dir isU
  4796. |\679: O: O1358 (predict-no)
  4797. I see 1 and I'm going to do: predict-no
  4798. ENV: Agent did: predict-no for direction U in state State-B
  4799. In State-B moving U
  4800. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4801. predict error 0
  4802. dir: dir isU
  4803. -/|680: O: O1360 (predict-no)
  4804. I see 1 and I'm going to do: predict-no
  4805. ENV: Agent did: predict-no for direction U in state State-B
  4806. In State-B moving U
  4807. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4808. predict error 0
  4809. dir: dir isL
  4810. \-/681: O: O1361 (predict-yes)
  4811. I see 1 and I'm going to do: predict-yes
  4812. ENV: Agent did: predict-yes for direction L in state State-B
  4813. In State-B moving L
  4814. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  4815. predict error 0
  4816. dir: dir isL
  4817. |682: O: O1364 (predict-no)
  4818. I see 1 and I'm going to do: predict-no
  4819. ENV: Agent did: predict-no for direction L in state State-A
  4820. In State-A moving L
  4821. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4822. predict error 0
  4823. dir: dir isU
  4824. \-683: O: O1366 (predict-no)
  4825. I see 1 and I'm going to do: predict-no
  4826. ENV: Agent did: predict-no for direction U in state State-A
  4827. In State-A moving U
  4828. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4829. predict error 0
  4830. dir: dir isU
  4831. /|\684: O: O1368 (predict-no)
  4832. I see 1 and I'm going to do: predict-no
  4833. ENV: Agent did: predict-no for direction U in state State-A
  4834. In State-A moving U
  4835. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4836. predict error 0
  4837. dir: dir isL
  4838. -/|685: O: O1370 (predict-no)
  4839. I see 1 and I'm going to do: predict-no
  4840. ENV: Agent did: predict-no for direction L in state State-A
  4841. In State-A moving L
  4842. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4843. predict error 0
  4844. dir: dir isU
  4845. \-686: O: O1372 (predict-no)
  4846. I see 1 and I'm going to do: predict-no
  4847. ENV: Agent did: predict-no for direction U in state State-A
  4848. In State-A moving U
  4849. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4850. predict error 0
  4851. dir: dir isU
  4852. /|\687: O: O1374 (predict-no)
  4853. I see 1 and I'm going to do: predict-no
  4854. ENV: Agent did: predict-no for direction U in state State-A
  4855. In State-A moving U
  4856. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4857. predict error 0
  4858. dir: dir isR
  4859. -/|688: O: O1375 (predict-yes)
  4860. I see 1 and I'm going to do: predict-yes
  4861. ENV: Agent did: predict-yes for direction R in state State-A
  4862. In State-A moving R
  4863. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  4864. predict error 0
  4865. dir: dir isU
  4866. \-/689: O: O1378 (predict-no)
  4867. I see 1 and I'm going to do: predict-no
  4868. ENV: Agent did: predict-no for direction U in state State-B
  4869. In State-B moving U
  4870. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4871. predict error 0
  4872. dir: dir isR
  4873. |690: O: O1380 (predict-no)
  4874. I see 1 and I'm going to do: predict-no
  4875. ENV: Agent did: predict-no for direction R in state State-B
  4876. In State-B moving R
  4877. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4878. predict error 0
  4879. dir: dir isL
  4880. \-/691: O: O1381 (predict-yes)
  4881. I see 1 and I'm going to do: predict-yes
  4882. ENV: Agent did: predict-yes for direction L in state State-B
  4883. In State-B moving L
  4884. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  4885. predict error 0
  4886. dir: dir isL
  4887. |692: O: O1384 (predict-no)
  4888. I see 1 and I'm going to do: predict-no
  4889. ENV: Agent did: predict-no for direction L in state State-A
  4890. In State-A moving L
  4891. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4892. predict error 0
  4893. dir: dir isL
  4894. \-693: O: O1386 (predict-no)
  4895. I see 1 and I'm going to do: predict-no
  4896. ENV: Agent did: predict-no for direction L in state State-A
  4897. In State-A moving L
  4898. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4899. predict error 0
  4900. dir: dir isR
  4901. /|\694: O: O1387 (predict-yes)
  4902. I see 1 and I'm going to do: predict-yes
  4903. ENV: Agent did: predict-yes for direction R in state State-A
  4904. In State-A moving R
  4905. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  4906. predict error 0
  4907. dir: dir isL
  4908. -/|695: O: O1389 (predict-yes)
  4909. I see 1 and I'm going to do: predict-yes
  4910. ENV: Agent did: predict-yes for direction L in state State-B
  4911. In State-B moving L
  4912. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  4913. predict error 0
  4914. dir: dir isR
  4915. \696: O: O1391 (predict-yes)
  4916. I see 1 and I'm going to do: predict-yes
  4917. ENV: Agent did: predict-yes for direction R in state State-A
  4918. In State-A moving R
  4919. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  4920. predict error 0
  4921. dir: dir isR
  4922. -/|697: O: O1394 (predict-no)
  4923. I see 1 and I'm going to do: predict-no
  4924. ENV: Agent did: predict-no for direction R in state State-B
  4925. In State-B moving R
  4926. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4927. predict error 0
  4928. dir: dir isR
  4929. \698: O: O1396 (predict-no)
  4930. I see 1 and I'm going to do: predict-no
  4931. ENV: Agent did: predict-no for direction R in state State-B
  4932. In State-B moving R
  4933. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4934. predict error 0
  4935. dir: dir isU
  4936. -/|699: O: O1398 (predict-no)
  4937. I see 1 and I'm going to do: predict-no
  4938. ENV: Agent did: predict-no for direction U in state State-B
  4939. In State-B moving U
  4940. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4941. predict error 0
  4942. dir: dir isR
  4943. \-/700: O: O1400 (predict-no)
  4944. I see 1 and I'm going to do: predict-no
  4945. ENV: Agent did: predict-no for direction R in state State-B
  4946. In State-B moving R
  4947. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4948. predict error 0
  4949. dir: dir isR
  4950. |\701: O: O1402 (predict-no)
  4951. I see 1 and I'm going to do: predict-no
  4952. ENV: Agent did: predict-no for direction R in state State-B
  4953. In State-B moving R
  4954. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4955. predict error 0
  4956. dir: dir isR
  4957. -702: O: O1404 (predict-no)
  4958. I see 1 and I'm going to do: predict-no
  4959. ENV: Agent did: predict-no for direction R in state State-B
  4960. In State-B moving R
  4961. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4962. predict error 0
  4963. dir: dir isL
  4964. /|703: O: O1405 (predict-yes)
  4965. I see 1 and I'm going to do: predict-yes
  4966. ENV: Agent did: predict-yes for direction L in state State-B
  4967. In State-B moving L
  4968. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  4969. predict error 0
  4970. dir: dir isL
  4971. \-/704: O: O1408 (predict-no)
  4972. I see 1 and I'm going to do: predict-no
  4973. ENV: Agent did: predict-no for direction L in state State-A
  4974. In State-A moving L
  4975. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4976. predict error 0
  4977. dir: dir isR
  4978. |\-705: O: O1409 (predict-yes)
  4979. I see 1 and I'm going to do: predict-yes
  4980. ENV: Agent did: predict-yes for direction R in state State-A
  4981. In State-A moving R
  4982. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  4983. predict error 0
  4984. dir: dir isU
  4985. /|\706: O: O1412 (predict-no)
  4986. I see 1 and I'm going to do: predict-no
  4987. ENV: Agent did: predict-no for direction U in state State-B
  4988. In State-B moving U
  4989. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4990. predict error 0
  4991. dir: dir isL
  4992. -/|707: O: O1413 (predict-yes)
  4993. I see 1 and I'm going to do: predict-yes
  4994. ENV: Agent did: predict-yes for direction L in state State-B
  4995. In State-B moving L
  4996. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  4997. predict error 0
  4998. dir: dir isU
  4999. \-/708: O: O1416 (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-A
  5002. In State-A moving U
  5003. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  5004. predict error 0
  5005. dir: dir isU
  5006. |\-709: O: O1418 (predict-no)
  5007. I see 1 and I'm going to do: predict-no
  5008. ENV: Agent did: predict-no for direction U in state State-A
  5009. In State-A moving U
  5010. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  5011. predict error 0
  5012. dir: dir isL
  5013. /|\710: O: O1420 (predict-no)
  5014. I see 1 and I'm going to do: predict-no
  5015. ENV: Agent did: predict-no for direction L in state State-A
  5016. In State-A moving L
  5017. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  5018. predict error 0
  5019. dir: dir isU
  5020. -/|711: O: O1422 (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. \712: O: O1423 (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. -/713: O: O1426 (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 isL
  5041. |\-714: O: O1427 (predict-yes)
  5042. I see 1 and I'm going to do: predict-yes
  5043. ENV: Agent did: predict-yes for direction L in state State-B
  5044. In State-B moving L
  5045. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  5046. predict error 0
  5047. dir: dir isR
  5048. /|\715: O: O1429 (predict-yes)
  5049. I see 1 and I'm going to do: predict-yes
  5050. ENV: Agent did: predict-yes for direction R in state State-A
  5051. In State-A moving R
  5052. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  5053. predict error 0
  5054. dir: dir isR
  5055. -/|716: O: O1432 (predict-no)
  5056. I see 1 and I'm going to do: predict-no
  5057. ENV: Agent did: predict-no for direction R in state State-B
  5058. In State-B moving R
  5059. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5060. predict error 0
  5061. dir: dir isU
  5062. \717: O: O1434 (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 isR
  5069. -/|718: O: O1436 (predict-no)
  5070. I see 1 and I'm going to do: predict-no
  5071. ENV: Agent did: predict-no for direction R in state State-B
  5072. In State-B moving R
  5073. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5074. predict error 0
  5075. dir: dir isU
  5076. \-/719: O: O1438 (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 isU
  5083. |\-720: O: O1440 (predict-no)
  5084. I see 1 and I'm going to do: predict-no
  5085. ENV: Agent did: predict-no for direction U in state State-B
  5086. In State-B moving U
  5087. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5088. predict error 0
  5089. dir: dir isL
  5090. /|\721: O: O1441 (predict-yes)
  5091. I see 1 and I'm going to do: predict-yes
  5092. ENV: Agent did: predict-yes for direction L in state State-B
  5093. In State-B moving L
  5094. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  5095. predict error 0
  5096. dir: dir isL
  5097. -722: O: O1444 (predict-no)
  5098. I see 1 and I'm going to do: predict-no
  5099. ENV: Agent did: predict-no for direction L in state State-A
  5100. In State-A moving L
  5101. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  5102. predict error 0
  5103. dir: dir isR
  5104. /|723: O: O1445 (predict-yes)
  5105. I see 1 and I'm going to do: predict-yes
  5106. ENV: Agent did: predict-yes for direction R in state State-A
  5107. In State-A moving R
  5108. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  5109. predict error 0
  5110. dir: dir isL
  5111. \-/724: O: O1447 (predict-yes)
  5112. I see 1 and I'm going to do: predict-yes
  5113. ENV: Agent did: predict-yes for direction L in state State-B
  5114. In State-B moving L
  5115. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  5116. predict error 0
  5117. dir: dir isL
  5118. |\-725: O: O1450 (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. /|\726: O: O1452 (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 isR
  5132. -/727: O: O1453 (predict-yes)
  5133. I see 1 and I'm going to do: predict-yes
  5134. ENV: Agent did: predict-yes for direction R in state State-A
  5135. In State-A moving R
  5136. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  5137. predict error 0
  5138. dir: dir isR
  5139. |\-728: O: O1456 (predict-no)
  5140. I see 1 and I'm going to do: predict-no
  5141. ENV: Agent did: predict-no for direction R in state State-B
  5142. In State-B moving R
  5143. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5144. predict error 0
  5145. dir: dir isR
  5146. /|\729: O: O1458 (predict-no)
  5147. I see 1 and I'm going to do: predict-no
  5148. ENV: Agent did: predict-no for direction R in state State-B
  5149. In State-B moving R
  5150. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5151. predict error 0
  5152. dir: dir isU
  5153. -/|730: O: O1460 (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-B
  5156. In State-B moving U
  5157. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5158. predict error 0
  5159. dir: dir isL
  5160. \-/731: O: O1461 (predict-yes)
  5161. I see 1 and I'm going to do: predict-yes
  5162. ENV: Agent did: predict-yes for direction L in state State-B
  5163. In State-B moving L
  5164. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  5165. predict error 0
  5166. dir: dir isR
  5167. |732: O: O1463 (predict-yes)
  5168. I see 1 and I'm going to do: predict-yes
  5169. ENV: Agent did: predict-yes for direction R in state State-A
  5170. In State-A moving R
  5171. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  5172. predict error 0
  5173. dir: dir isL
  5174. \-/733: O: O1465 (predict-yes)
  5175. I see 1 and I'm going to do: predict-yes
  5176. ENV: Agent did: predict-yes for direction L in state State-B
  5177. In State-B moving L
  5178. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  5179. predict error 0
  5180. dir: dir isU
  5181. |\734: O: O1468 (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-A
  5184. In State-A moving U
  5185. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  5186. predict error 0
  5187. dir: dir isR
  5188. -/|735: O: O1469 (predict-yes)
  5189. I see 1 and I'm going to do: predict-yes
  5190. ENV: Agent did: predict-yes for direction R in state State-A
  5191. In State-A moving R
  5192. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  5193. predict error 0
  5194. dir: dir isL
  5195. \-/736: O: O1471 (predict-yes)
  5196. I see 1 and I'm going to do: predict-yes
  5197. ENV: Agent did: predict-yes for direction L in state State-B
  5198. In State-B moving L
  5199. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  5200. predict error 0
  5201. dir: dir isL
  5202. |\-737: O: O1474 (predict-no)
  5203. I see 1 and I'm going to do: predict-no
  5204. ENV: Agent did: predict-no for direction L in state State-A
  5205. In State-A moving L
  5206. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  5207. predict error 0
  5208. dir: dir isR
  5209. /|\738: O: O1475 (predict-yes)
  5210. I see 1 and I'm going to do: predict-yes
  5211. ENV: Agent did: predict-yes for direction R in state State-A
  5212. In State-A moving R
  5213. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  5214. predict error 0
  5215. dir: dir isR
  5216. -/|739: O: O1478 (predict-no)
  5217. I see 1 and I'm going to do: predict-no
  5218. ENV: Agent did: predict-no for direction R in state State-B
  5219. In State-B moving R
  5220. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5221. predict error 0
  5222. dir: dir isU
  5223. \-740: O: O1480 (predict-no)
  5224. I see 1 and I'm going to do: predict-no
  5225. ENV: Agent did: predict-no for direction U in state State-B
  5226. In State-B moving U
  5227. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5228. predict error 0
  5229. dir: dir isR
  5230. /|\741: O: O1482 (predict-no)
  5231. I see 1 and I'm going to do: predict-no
  5232. ENV: Agent did: predict-no for direction R in state State-B
  5233. In State-B moving R
  5234. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5235. predict error 0
  5236. dir: dir isR
  5237. -742: O: O1484 (predict-no)
  5238. I see 1 and I'm going to do: predict-no
  5239. ENV: Agent did: predict-no for direction R in state State-B
  5240. In State-B moving R
  5241. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5242. predict error 0
  5243. dir: dir isU
  5244. /|\743: O: O1486 (predict-no)
  5245. I see 1 and I'm going to do: predict-no
  5246. ENV: Agent did: predict-no for direction U in state State-B
  5247. In State-B moving U
  5248. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5249. predict error 0
  5250. dir: dir isR
  5251. -/|744: O: O1488 (predict-no)
  5252. I see 1 and I'm going to do: predict-no
  5253. ENV: Agent did: predict-no for direction R in state State-B
  5254. In State-B moving R
  5255. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5256. predict error 0
  5257. dir: dir isL
  5258. \-/745: O: O1489 (predict-yes)
  5259. I see 1 and I'm going to do: predict-yes
  5260. ENV: Agent did: predict-yes for direction L in state State-B
  5261. In State-B moving L
  5262. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  5263. predict error 0
  5264. dir: dir isU
  5265. |\746: O: O1492 (predict-no)
  5266. I see 1 and I'm going to do: predict-no
  5267. ENV: Agent did: predict-no for direction U in state State-A
  5268. In State-A moving U
  5269. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  5270. predict error 0
  5271. dir: dir isR
  5272. -/|747: O: O1493 (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 isU
  5279. \-748: O: O1496 (predict-no)
  5280. I see 1 and I'm going to do: predict-no
  5281. ENV: Agent did: predict-no for direction U in state State-B
  5282. In State-B moving U
  5283. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5284. predict error 0
  5285. dir: dir isR
  5286. /|\749: O: O1498 (predict-no)
  5287. I see 1 and I'm going to do: predict-no
  5288. ENV: Agent did: predict-no for direction R in state State-B
  5289. In State-B moving R
  5290. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5291. predict error 0
  5292. dir: dir isU
  5293. -/750: O: O1500 (predict-no)
  5294. I see 1 and I'm going to do: predict-no
  5295. ENV: Agent did: predict-no for direction U in state State-B
  5296. In State-B moving U
  5297. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5298. predict error 0
  5299. dir: dir isU
  5300. |\751: O: O1502 (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-B
  5303. In State-B moving U
  5304. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5305. predict error 0
  5306. dir: dir isR
  5307. -752: O: O1504 (predict-no)
  5308. I see 1 and I'm going to do: predict-no
  5309. ENV: Agent did: predict-no for direction R in state State-B
  5310. In State-B moving R
  5311. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5312. predict error 0
  5313. dir: dir isU
  5314. /|\753: O: O1506 (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-B
  5317. In State-B moving U
  5318. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5319. predict error 0
  5320. dir: dir isL
  5321. -/|754: O: O1507 (predict-yes)
  5322. I see 1 and I'm going to do: predict-yes
  5323. ENV: Agent did: predict-yes for direction L in state State-B
  5324. In State-B moving L
  5325. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  5326. predict error 0
  5327. dir: dir isR
  5328. \-/755: O: O1509 (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. |\-756: O: O1512 (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. /|\757: O: O1513 (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. -/758: O: O1516 (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 isU
  5356. |\-759: O: O1518 (predict-no)
  5357. I see 1 and I'm going to do: predict-no
  5358. ENV: Agent did: predict-no for direction U in state State-A
  5359. In State-A moving U
  5360. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  5361. predict error 0
  5362. dir: dir isU
  5363. /|760: O: O1520 (predict-no)
  5364. I see 1 and I'm going to do: predict-no
  5365. ENV: Agent did: predict-no for direction U in state State-A
  5366. In State-A moving U
  5367. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  5368. predict error 0
  5369. dir: dir isU
  5370. \-/761: O: O1522 (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-A
  5373. In State-A moving U
  5374. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  5375. predict error 0
  5376. dir: dir isL
  5377. |762: O: O1524 (predict-no)
  5378. I see 1 and I'm going to do: predict-no
  5379. ENV: Agent did: predict-no for direction L in state State-A
  5380. In State-A moving L
  5381. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  5382. predict error 0
  5383. dir: dir isR
  5384. \-/763: O: O1525 (predict-yes)
  5385. I see 1 and I'm going to do: predict-yes
  5386. ENV: Agent did: predict-yes for direction R in state State-A
  5387. In State-A moving R
  5388. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  5389. predict error 0
  5390. dir: dir isR
  5391. |764: O: O1528 (predict-no)
  5392. I see 1 and I'm going to do: predict-no
  5393. ENV: Agent did: predict-no for direction R in state State-B
  5394. In State-B moving R
  5395. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5396. predict error 0
  5397. dir: dir isR
  5398. \-/765: O: O1530 (predict-no)
  5399. I see 1 and I'm going to do: predict-no
  5400. ENV: Agent did: predict-no for direction R in state State-B
  5401. In State-B moving R
  5402. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5403. predict error 0
  5404. dir: dir isR
  5405. |\766: O: O1532 (predict-no)
  5406. I see 1 and I'm going to do: predict-no
  5407. ENV: Agent did: predict-no for direction R in state State-B
  5408. In State-B moving R
  5409. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5410. predict error 0
  5411. dir: dir isU
  5412. -/|767: O: O1534 (predict-no)
  5413. I see 1 and I'm going to do: predict-no
  5414. ENV: Agent did: predict-no for direction U in state State-B
  5415. In State-B moving U
  5416. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5417. predict error 0
  5418. dir: dir isL
  5419. \-/768: O: O1535 (predict-yes)
  5420. I see 1 and I'm going to do: predict-yes
  5421. ENV: Agent did: predict-yes for direction L in state State-B
  5422. In State-B moving L
  5423. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  5424. predict error 0
  5425. dir: dir isL
  5426. |\-769: O: O1538 (predict-no)
  5427. I see 1 and I'm going to do: predict-no
  5428. ENV: Agent did: predict-no for direction L in state State-A
  5429. In State-A moving L
  5430. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  5431. predict error 0
  5432. dir: dir isR
  5433. /|770: O: O1539 (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. \-/771: O: O1542 (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 isU
  5447. |772: O: O1544 (predict-no)
  5448. I see 1 and I'm going to do: predict-no
  5449. ENV: Agent did: predict-no for direction U in state State-B
  5450. In State-B moving U
  5451. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5452. predict error 0
  5453. dir: dir isU
  5454. \-/773: O: O1546 (predict-no)
  5455. I see 1 and I'm going to do: predict-no
  5456. ENV: Agent did: predict-no for direction U in state State-B
  5457. In State-B moving U
  5458. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5459. predict error 0
  5460. dir: dir isL
  5461. |\-774: O: O1547 (predict-yes)
  5462. I see 1 and I'm going to do: predict-yes
  5463. ENV: Agent did: predict-yes for direction L in state State-B
  5464. In State-B moving L
  5465. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  5466. predict error 0
  5467. dir: dir isU
  5468. /|\775: O: O1550 (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-A
  5471. In State-A moving U
  5472. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  5473. predict error 0
  5474. dir: dir isL
  5475. -/776: O: O1552 (predict-no)
  5476. I see 1 and I'm going to do: predict-no
  5477. ENV: Agent did: predict-no for direction L in state State-A
  5478. In State-A moving L
  5479. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  5480. predict error 0
  5481. dir: dir isL
  5482. |\-777: O: O1554 (predict-no)
  5483. I see 1 and I'm going to do: predict-no
  5484. ENV: Agent did: predict-no for direction L in state State-A
  5485. In State-A moving L
  5486. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  5487. predict error 0
  5488. dir: dir isU
  5489. /|\778: O: O1556 (predict-no)
  5490. I see 1 and I'm going to do: predict-no
  5491. ENV: Agent did: predict-no for direction U in state State-A
  5492. In State-A moving U
  5493. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  5494. predict error 0
  5495. dir: dir isU
  5496. -/|779: O: O1558 (predict-no)
  5497. I see 1 and I'm going to do: predict-no
  5498. ENV: Agent did: predict-no for direction U in state State-A
  5499. In State-A moving U
  5500. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  5501. predict error 0
  5502. dir: dir isR
  5503. \-/780: O: O1559 (predict-yes)
  5504. I see 1 and I'm going to do: predict-yes
  5505. ENV: Agent did: predict-yes for direction R in state State-A
  5506. In State-A moving R
  5507. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  5508. predict error 0
  5509. dir: dir isU
  5510. |\-781: O: O1562 (predict-no)
  5511. I see 1 and I'm going to do: predict-no
  5512. ENV: Agent did: predict-no for direction U in state State-B
  5513. In State-B moving U
  5514. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5515. predict error 0
  5516. dir: dir isL
  5517. /782: O: O1563 (predict-yes)
  5518. I see 1 and I'm going to do: predict-yes
  5519. ENV: Agent did: predict-yes for direction L in state State-B
  5520. In State-B moving L
  5521. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  5522. predict error 0
  5523. dir: dir isR
  5524. |783: O: O1565 (predict-yes)
  5525. I see 1 and I'm going to do: predict-yes
  5526. ENV: Agent did: predict-yes for direction R in state State-A
  5527. In State-A moving R
  5528. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  5529. predict error 0
  5530. dir: dir isL
  5531. \-/784: O: O1567 (predict-yes)
  5532. I see 1 and I'm going to do: predict-yes
  5533. ENV: Agent did: predict-yes for direction L in state State-B
  5534. In State-B moving L
  5535. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  5536. predict error 0
  5537. dir: dir isL
  5538. |\-/785: O: O1570 (predict-no)
  5539. I see 1 and I'm going to do: predict-no
  5540. ENV: Agent did: predict-no for direction L in state State-A
  5541. In State-A moving L
  5542. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  5543. predict error 0
  5544. dir: dir isL
  5545. |\-786: O: O1572 (predict-no)
  5546. I see 1 and I'm going to do: predict-no
  5547. ENV: Agent did: predict-no for direction L in state State-A
  5548. In State-A moving L
  5549. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  5550. predict error 0
  5551. dir: dir isL
  5552. /|787: O: O1574 (predict-no)
  5553. I see 1 and I'm going to do: predict-no
  5554. ENV: Agent did: predict-no for direction L in state State-A
  5555. In State-A moving L
  5556. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  5557. predict error 0
  5558. dir: dir isR
  5559. \-/788: O: O1575 (predict-yes)
  5560. I see 1 and I'm going to do: predict-yes
  5561. ENV: Agent did: predict-yes for direction R in state State-A
  5562. In State-A moving R
  5563. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  5564. predict error 0
  5565. dir: dir isR
  5566. |\-789: O: O1578 (predict-no)
  5567. I see 1 and I'm going to do: predict-no
  5568. ENV: Agent did: predict-no for direction R in state State-B
  5569. In State-B moving R
  5570. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5571. predict error 0
  5572. dir: dir isL
  5573. /|790: O: O1579 (predict-yes)
  5574. I see 1 and I'm going to do: predict-yes
  5575. ENV: Agent did: predict-yes for direction L in state State-B
  5576. In State-B moving L
  5577. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  5578. predict error 0
  5579. dir: dir isR
  5580. \791: O: O1581 (predict-yes)
  5581. I see 1 and I'm going to do: predict-yes
  5582. ENV: Agent did: predict-yes for direction R in state State-A
  5583. In State-A moving R
  5584. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  5585. predict error 0
  5586. dir: dir isL
  5587. -792: O: O1583 (predict-yes)
  5588. I see 1 and I'm going to do: predict-yes
  5589. ENV: Agent did: predict-yes for direction L in state State-B
  5590. In State-B moving L
  5591. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  5592. predict error 0
  5593. dir: dir isR
  5594. /|\793: O: O1585 (predict-yes)
  5595. I see 1 and I'm going to do: predict-yes
  5596. ENV: Agent did: predict-yes for direction R in state State-A
  5597. In State-A moving R
  5598. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  5599. predict error 0
  5600. dir: dir isR
  5601. -/|794: O: O1588 (predict-no)
  5602. I see 1 and I'm going to do: predict-no
  5603. ENV: Agent did: predict-no for direction R in state State-B
  5604. In State-B moving R
  5605. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5606. predict error 0
  5607. dir: dir isR
  5608. \-/795: O: O1590 (predict-no)
  5609. I see 1 and I'm going to do: predict-no
  5610. ENV: Agent did: predict-no for direction R in state State-B
  5611. In State-B moving R
  5612. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5613. predict error 0
  5614. dir: dir isU
  5615. |\-796: O: O1592 (predict-no)
  5616. I see 1 and I'm going to do: predict-no
  5617. ENV: Agent did: predict-no for direction U in state State-B
  5618. In State-B moving U
  5619. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5620. predict error 0
  5621. dir: dir isL
  5622. /|797: O: O1593 (predict-yes)
  5623. I see 1 and I'm going to do: predict-yes
  5624. ENV: Agent did: predict-yes for direction L in state State-B
  5625. In State-B moving L
  5626. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  5627. predict error 0
  5628. dir: dir isR
  5629. \-/798: O: O1595 (predict-yes)
  5630. I see 1 and I'm going to do: predict-yes
  5631. ENV: Agent did: predict-yes for direction R in state State-A
  5632. In State-A moving R
  5633. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  5634. predict error 0
  5635. dir: dir isR
  5636. |\799: O: O1598 (predict-no)
  5637. I see 1 and I'm going to do: predict-no
  5638. ENV: Agent did: predict-no for direction R in state State-B
  5639. In State-B moving R
  5640. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5641. predict error 0
  5642. dir: dir isR
  5643. -/|800: O: O1600 (predict-no)
  5644. I see 1 and I'm going to do: predict-no
  5645. ENV: Agent did: predict-no for direction R in state State-B
  5646. In State-B moving R
  5647. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5648. predict error 0
  5649. dir: dir isU
  5650. \-801: O: O1602 (predict-no)
  5651. I see 1 and I'm going to do: predict-no
  5652. ENV: Agent did: predict-no for direction U in state State-B
  5653. In State-B moving U
  5654. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5655. predict error 0
  5656. dir: dir isR
  5657. /802: O: O1604 (predict-no)
  5658. I see 1 and I'm going to do: predict-no
  5659. ENV: Agent did: predict-no for direction R in state State-B
  5660. In State-B moving R
  5661. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5662. predict error 0
  5663. dir: dir isR
  5664. |\-803: O: O1606 (predict-no)
  5665. I see 1 and I'm going to do: predict-no
  5666. ENV: Agent did: predict-no for direction R in state State-B
  5667. In State-B moving R
  5668. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5669. predict error 0
  5670. dir: dir isR
  5671. /|804: O: O1608 (predict-no)
  5672. I see 1 and I'm going to do: predict-no
  5673. ENV: Agent did: predict-no for direction R in state State-B
  5674. In State-B moving R
  5675. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5676. predict error 0
  5677. dir: dir isR
  5678. \-/805: O: O1610 (predict-no)
  5679. I see 1 and I'm going to do: predict-no
  5680. ENV: Agent did: predict-no for direction R in state State-B
  5681. In State-B moving R
  5682. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5683. predict error 0
  5684. dir: dir isU
  5685. |\-806: O: O1612 (predict-no)
  5686. I see 1 and I'm going to do: predict-no
  5687. ENV: Agent did: predict-no for direction U in state State-B
  5688. In State-B moving U
  5689. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5690. predict error 0
  5691. dir: dir isU
  5692. /|\807: O: O1614 (predict-no)
  5693. I see 1 and I'm going to do: predict-no
  5694. ENV: Agent did: predict-no for direction U in state State-B
  5695. In State-B moving U
  5696. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5697. predict error 0
  5698. dir: dir isR
  5699. -/808: O: O1616 (predict-no)
  5700. I see 1 and I'm going to do: predict-no
  5701. ENV: Agent did: predict-no for direction R in state State-B
  5702. In State-B moving R
  5703. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5704. predict error 0
  5705. dir: dir isL
  5706. |\-/809: O: O1617 (predict-yes)
  5707. I see 1 and I'm going to do: predict-yes
  5708. ENV: Agent did: predict-yes for direction L in state State-B
  5709. In State-B moving L
  5710. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  5711. predict error 0
  5712. dir: dir isR
  5713. |\-810: O: O1619 (predict-yes)
  5714. I see 1 and I'm going to do: predict-yes
  5715. ENV: Agent did: predict-yes for direction R in state State-A
  5716. In State-A moving R
  5717. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  5718. predict error 0
  5719. dir: dir isL
  5720. /|\811: O: O1621 (predict-yes)
  5721. I see 1 and I'm going to do: predict-yes
  5722. ENV: Agent did: predict-yes for direction L in state State-B
  5723. In State-B moving L
  5724. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  5725. predict error 0
  5726. dir: dir isR
  5727. -812: O: O1623 (predict-yes)
  5728. I see 1 and I'm going to do: predict-yes
  5729. ENV: Agent did: predict-yes for direction R in state State-A
  5730. In State-A moving R
  5731. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  5732. predict error 0
  5733. dir: dir isL
  5734. /813: O: O1625 (predict-yes)
  5735. I see 1 and I'm going to do: predict-yes
  5736. ENV: Agent did: predict-yes for direction L in state State-B
  5737. In State-B moving L
  5738. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  5739. predict error 0
  5740. dir: dir isU
  5741. |814: O: O1628 (predict-no)
  5742. I see 1 and I'm going to do: predict-no
  5743. ENV: Agent did: predict-no for direction U in state State-A
  5744. In State-A moving U
  5745. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  5746. predict error 0
  5747. dir: dir isU
  5748. \-815: O: O1630 (predict-no)
  5749. I see 1 and I'm going to do: predict-no
  5750. ENV: Agent did: predict-no for direction U in state State-A
  5751. In State-A moving U
  5752. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  5753. predict error 0
  5754. dir: dir isR
  5755. /|\816: O: O1631 (predict-yes)
  5756. I see 1 and I'm going to do: predict-yes
  5757. ENV: Agent did: predict-yes for direction R in state State-A
  5758. In State-A moving R
  5759. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  5760. predict error 0
  5761. dir: dir isR
  5762. -/|817: O: O1634 (predict-no)
  5763. I see 1 and I'm going to do: predict-no
  5764. ENV: Agent did: predict-no for direction R in state State-B
  5765. In State-B moving R
  5766. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5767. predict error 0
  5768. dir: dir isL
  5769. \-818: O: O1635 (predict-yes)
  5770. I see 1 and I'm going to do: predict-yes
  5771. ENV: Agent did: predict-yes for direction L in state State-B
  5772. In State-B moving L
  5773. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  5774. predict error 0
  5775. dir: dir isR
  5776. /|\819: O: O1637 (predict-yes)
  5777. I see 1 and I'm going to do: predict-yes
  5778. ENV: Agent did: predict-yes for direction R in state State-A
  5779. In State-A moving R
  5780. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  5781. predict error 0
  5782. dir: dir isR
  5783. -/|820: O: O1640 (predict-no)
  5784. I see 1 and I'm going to do: predict-no
  5785. ENV: Agent did: predict-no for direction R in state State-B
  5786. In State-B moving R
  5787. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5788. predict error 0
  5789. dir: dir isR
  5790. \-/821: O: O1642 (predict-no)
  5791. I see 1 and I'm going to do: predict-no
  5792. ENV: Agent did: predict-no for direction R in state State-B
  5793. In State-B moving R
  5794. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5795. predict error 0
  5796. dir: dir isL
  5797. |822: O: O1643 (predict-yes)
  5798. I see 1 and I'm going to do: predict-yes
  5799. ENV: Agent did: predict-yes for direction L in state State-B
  5800. In State-B moving L
  5801. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  5802. predict error 0
  5803. dir: dir isL
  5804. \-/823: O: O1646 (predict-no)
  5805. I see 1 and I'm going to do: predict-no
  5806. ENV: Agent did: predict-no for direction L in state State-A
  5807. In State-A moving L
  5808. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  5809. predict error 0
  5810. dir: dir isU
  5811. |\-824: O: O1648 (predict-no)
  5812. I see 1 and I'm going to do: predict-no
  5813. ENV: Agent did: predict-no for direction U in state State-A
  5814. In State-A moving U
  5815. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  5816. predict error 0
  5817. dir: dir isU
  5818. /|\825: O: O1650 (predict-no)
  5819. I see 1 and I'm going to do: predict-no
  5820. ENV: Agent did: predict-no for direction U in state State-A
  5821. In State-A moving U
  5822. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  5823. predict error 0
  5824. dir: dir isU
  5825. -/|826: O: O1652 (predict-no)
  5826. I see 1 and I'm going to do: predict-no
  5827. ENV: Agent did: predict-no for direction U in state State-A
  5828. In State-A moving U
  5829. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  5830. predict error 0
  5831. dir: dir isR
  5832. \-827: O: O1653 (predict-yes)
  5833. I see 1 and I'm going to do: predict-yes
  5834. ENV: Agent did: predict-yes for direction R in state State-A
  5835. In State-A moving R
  5836. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  5837. predict error 0
  5838. dir: dir isL
  5839. /|\-828: O: O1655 (predict-yes)
  5840. I see 1 and I'm going to do: predict-yes
  5841. ENV: Agent did: predict-yes for direction L in state State-B
  5842. In State-B moving L
  5843. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  5844. predict error 0
  5845. dir: dir isL
  5846. /|829: O: O1658 (predict-no)
  5847. I see 1 and I'm going to do: predict-no
  5848. ENV: Agent did: predict-no for direction L in state State-A
  5849. In State-A moving L
  5850. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  5851. predict error 0
  5852. dir: dir isU
  5853. \-/830: O: O1660 (predict-no)
  5854. I see 1 and I'm going to do: predict-no
  5855. ENV: Agent did: predict-no for direction U in state State-A
  5856. In State-A moving U
  5857. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  5858. predict error 0
  5859. dir: dir isU
  5860. |\-831: O: O1662 (predict-no)
  5861. I see 1 and I'm going to do: predict-no
  5862. ENV: Agent did: predict-no for direction U in state State-A
  5863. In State-A moving U
  5864. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  5865. predict error 0
  5866. dir: dir isR
  5867. /832: O: O1663 (predict-yes)
  5868. I see 1 and I'm going to do: predict-yes
  5869. ENV: Agent did: predict-yes for direction R in state State-A
  5870. In State-A moving R
  5871. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  5872. predict error 0
  5873. dir: dir isR
  5874. |\-833: O: O1666 (predict-no)
  5875. I see 1 and I'm going to do: predict-no
  5876. ENV: Agent did: predict-no for direction R in state State-B
  5877. In State-B moving R
  5878. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5879. predict error 0
  5880. dir: dir isU
  5881. /|\834: O: O1668 (predict-no)
  5882. I see 1 and I'm going to do: predict-no
  5883. ENV: Agent did: predict-no for direction U in state State-B
  5884. In State-B moving U
  5885. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5886. predict error 0
  5887. dir: dir isL
  5888. -/|835: O: O1669 (predict-yes)
  5889. I see 1 and I'm going to do: predict-yes
  5890. ENV: Agent did: predict-yes for direction L in state State-B
  5891. In State-B moving L
  5892. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  5893. predict error 0
  5894. dir: dir isU
  5895. \-/836: O: O1672 (predict-no)
  5896. I see 1 and I'm going to do: predict-no
  5897. ENV: Agent did: predict-no for direction U in state State-A
  5898. In State-A moving U
  5899. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  5900. predict error 0
  5901. dir: dir isR
  5902. |\837: O: O1673 (predict-yes)
  5903. I see 1 and I'm going to do: predict-yes
  5904. ENV: Agent did: predict-yes for direction R in state State-A
  5905. In State-A moving R
  5906. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  5907. predict error 0
  5908. dir: dir isU
  5909. -/|838: O: O1676 (predict-no)
  5910. I see 1 and I'm going to do: predict-no
  5911. ENV: Agent did: predict-no for direction U in state State-B
  5912. In State-B moving U
  5913. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5914. predict error 0
  5915. dir: dir isR
  5916. \-/839: O: O1678 (predict-no)
  5917. I see 1 and I'm going to do: predict-no
  5918. ENV: Agent did: predict-no for direction R in state State-B
  5919. In State-B moving R
  5920. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5921. predict error 0
  5922. dir: dir isR
  5923. |840: O: O1680 (predict-no)
  5924. I see 1 and I'm going to do: predict-no
  5925. ENV: Agent did: predict-no for direction R in state State-B
  5926. In State-B moving R
  5927. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5928. predict error 0
  5929. dir: dir isR
  5930. \-841: O: O1682 (predict-no)
  5931. I see 1 and I'm going to do: predict-no
  5932. ENV: Agent did: predict-no for direction R in state State-B
  5933. In State-B moving R
  5934. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5935. predict error 0
  5936. dir: dir isR
  5937. /842: O: O1684 (predict-no)
  5938. I see 1 and I'm going to do: predict-no
  5939. ENV: Agent did: predict-no for direction R in state State-B
  5940. In State-B moving R
  5941. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5942. predict error 0
  5943. dir: dir isR
  5944. |\-843: O: O1686 (predict-no)
  5945. I see 1 and I'm going to do: predict-no
  5946. ENV: Agent did: predict-no for direction R in state State-B
  5947. In State-B moving R
  5948. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5949. predict error 0
  5950. dir: dir isU
  5951. /|844: O: O1688 (predict-no)
  5952. I see 1 and I'm going to do: predict-no
  5953. ENV: Agent did: predict-no for direction U in state State-B
  5954. In State-B moving U
  5955. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5956. predict error 0
  5957. dir: dir isU
  5958. \-/845: O: O1690 (predict-no)
  5959. I see 1 and I'm going to do: predict-no
  5960. ENV: Agent did: predict-no for direction U in state State-B
  5961. In State-B moving U
  5962. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5963. predict error 0
  5964. dir: dir isR
  5965. |\-846: O: O1692 (predict-no)
  5966. I see 1 and I'm going to do: predict-no
  5967. ENV: Agent did: predict-no for direction R in state State-B
  5968. In State-B moving R
  5969. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5970. predict error 0
  5971. dir: dir isR
  5972. /|\847: O: O1694 (predict-no)
  5973. I see 1 and I'm going to do: predict-no
  5974. ENV: Agent did: predict-no for direction R in state State-B
  5975. In State-B moving R
  5976. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5977. predict error 0
  5978. dir: dir isU
  5979. -/848: O: O1696 (predict-no)
  5980. I see 1 and I'm going to do: predict-no
  5981. ENV: Agent did: predict-no for direction U in state State-B
  5982. In State-B moving U
  5983. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5984. predict error 0
  5985. dir: dir isU
  5986. |\-849: O: O1698 (predict-no)
  5987. I see 1 and I'm going to do: predict-no
  5988. ENV: Agent did: predict-no for direction U in state State-B
  5989. In State-B moving U
  5990. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5991. predict error 0
  5992. dir: dir isR
  5993. /|\850: O: O1700 (predict-no)
  5994. I see 1 and I'm going to do: predict-no
  5995. ENV: Agent did: predict-no for direction R in state State-B
  5996. In State-B moving R
  5997. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5998. predict error 0
  5999. dir: dir isU
  6000. -/|851: O: O1702 (predict-no)
  6001. I see 1 and I'm going to do: predict-no
  6002. ENV: Agent did: predict-no for direction U in state State-B
  6003. In State-B moving U
  6004. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  6005. predict error 0
  6006. dir: dir isL
  6007. \852: O: O1703 (predict-yes)
  6008. I see 1 and I'm going to do: predict-yes
  6009. ENV: Agent did: predict-yes for direction L in state State-B
  6010. In State-B moving L
  6011. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  6012. predict error 0
  6013. dir: dir isR
  6014. -/|853: O: O1705 (predict-yes)
  6015. I see 1 and I'm going to do: predict-yes
  6016. ENV: Agent did: predict-yes for direction R in state State-A
  6017. In State-A moving R
  6018. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  6019. predict error 0
  6020. dir: dir isR
  6021. \-/854: O: O1708 (predict-no)
  6022. I see 1 and I'm going to do: predict-no
  6023. ENV: Agent did: predict-no for direction R in state State-B
  6024. In State-B moving R
  6025. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  6026. predict error 0
  6027. dir: dir isR
  6028. |\-855: O: O1710 (predict-no)
  6029. I see 1 and I'm going to do: predict-no
  6030. ENV: Agent did: predict-no for direction R in state State-B
  6031. In State-B moving R
  6032. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  6033. predict error 0
  6034. dir: dir isU
  6035. /|\856: O: O1712 (predict-no)
  6036. I see 1 and I'm going to do: predict-no
  6037. ENV: Agent did: predict-no for direction U in state State-B
  6038. In State-B moving U
  6039. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  6040. predict error 0
  6041. dir: dir isU
  6042. -/|857: O: O1714 (predict-no)
  6043. I see 1 and I'm going to do: predict-no
  6044. ENV: Agent did: predict-no for direction U in state State-B
  6045. In State-B moving U
  6046. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  6047. predict error 0
  6048. dir: dir isR
  6049. \-/858: O: O1716 (predict-no)
  6050. I see 1 and I'm going to do: predict-no
  6051. ENV: Agent did: predict-no for direction R in state State-B
  6052. In State-B moving R
  6053. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  6054. predict error 0
  6055. dir: dir isR
  6056. |\-/859: O: O1718 (predict-no)
  6057. I see 1 and I'm going to do: predict-no
  6058. ENV: Agent did: predict-no for direction R in state State-B
  6059. In State-B moving R
  6060. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  6061. predict error 0
  6062. dir: dir isU
  6063. |\-860: O: O1720 (predict-no)
  6064. I see 1 and I'm going to do: predict-no
  6065. ENV: Agent did: predict-no for direction U in state State-B
  6066. In State-B moving U
  6067. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  6068. predict error 0
  6069. dir: dir isU
  6070. /861: O: O1722 (predict-no)
  6071. I see 1 and I'm going to do: predict-no
  6072. ENV: Agent did: predict-no for direction U in state State-B
  6073. In State-B moving U
  6074. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  6075. predict error 0
  6076. dir: dir isR
  6077. |862: O: O1724 (predict-no)
  6078. I see 1 and I'm going to do: predict-no
  6079. ENV: Agent did: predict-no for direction R in state State-B
  6080. In State-B moving R
  6081. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  6082. predict error 0
  6083. dir: dir isU
  6084. \-863: O: O1726 (predict-no)
  6085. I see 1 and I'm going to do: predict-no
  6086. ENV: Agent did: predict-no for direction U in state State-B
  6087. In State-B moving U
  6088. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  6089. predict error 0
  6090. dir: dir isR
  6091. /|864: O: O1728 (predict-no)
  6092. I see 1 and I'm going to do: predict-no
  6093. ENV: Agent did: predict-no for direction R in state State-B
  6094. In State-B moving R
  6095. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  6096. predict error 0
  6097. dir: dir isL
  6098. \-/865: O: O1729 (predict-yes)
  6099. I see 1 and I'm going to do: predict-yes
  6100. ENV: Agent did: predict-yes for direction L in state State-B
  6101. In State-B moving L
  6102. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  6103. predict error 0
  6104. dir: dir isR
  6105. |\-866: O: O1731 (predict-yes)
  6106. I see 1 and I'm going to do: predict-yes
  6107. ENV: Agent did: predict-yes for direction R in state State-A
  6108. In State-A moving R
  6109. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  6110. predict error 0
  6111. dir: dir isR
  6112. /|867: O: O1734 (predict-no)
  6113. I see 1 and I'm going to do: predict-no
  6114. ENV: Agent did: predict-no for direction R in state State-B
  6115. In State-B moving R
  6116. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  6117. predict error 0
  6118. dir: dir isR
  6119. \-/868: O: O1736 (predict-no)
  6120. I see 1 and I'm going to do: predict-no
  6121. ENV: Agent did: predict-no for direction R in state State-B
  6122. In State-B moving R
  6123. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  6124. predict error 0
  6125. dir: dir isR
  6126. |\869: O: O1738 (predict-no)
  6127. I see 1 and I'm going to do: predict-no
  6128. ENV: Agent did: predict-no for direction R in state State-B
  6129. In State-B moving R
  6130. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  6131. predict error 0
  6132. dir: dir isU
  6133. -/|870: O: O1740 (predict-no)
  6134. I see 1 and I'm going to do: predict-no
  6135. ENV: Agent did: predict-no for direction U in state State-B
  6136. In State-B moving U
  6137. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  6138. predict error 0
  6139. dir: dir isU
  6140. \-/871: O: O1742 (predict-no)
  6141. I see 1 and I'm going to do: predict-no
  6142. ENV: Agent did: predict-no for direction U in state State-B
  6143. In State-B moving U
  6144. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  6145. predict error 0
  6146. dir: dir isR
  6147. |872: O: O1744 (predict-no)
  6148. I see 1 and I'm going to do: predict-no
  6149. ENV: Agent did: predict-no for direction R in state State-B
  6150. In State-B moving R
  6151. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  6152. predict error 0
  6153. dir: dir isU
  6154. \-/873: O: O1746 (predict-no)
  6155. I see 1 and I'm going to do: predict-no
  6156. ENV: Agent did: predict-no for direction U in state State-B
  6157. In State-B moving U
  6158. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  6159. predict error 0
  6160. dir: dir isR
  6161. |\874: O: O1748 (predict-no)
  6162. I see 1 and I'm going to do: predict-no
  6163. ENV: Agent did: predict-no for direction R in state State-B
  6164. In State-B moving R
  6165. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  6166. predict error 0
  6167. dir: dir isR
  6168. -/|875: O: O1750 (predict-no)
  6169. I see 1 and I'm going to do: predict-no
  6170. ENV: Agent did: predict-no for direction R in state State-B
  6171. In State-B moving R
  6172. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  6173. predict error 0
  6174. dir: dir isR
  6175. \-/876: O: O1752 (predict-no)
  6176. I see 1 and I'm going to do: predict-no
  6177. ENV: Agent did: predict-no for direction R in state State-B
  6178. In State-B moving R
  6179. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  6180. predict error 0
  6181. dir: dir isU
  6182. |\-877: O: O1754 (predict-no)
  6183. I see 1 and I'm going to do: predict-no
  6184. ENV: Agent did: predict-no for direction U in state State-B
  6185. In State-B moving U
  6186. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  6187. predict error 0
  6188. dir: dir isU
  6189. /|878: O: O1756 (predict-no)
  6190. I see 1 and I'm going to do: predict-no
  6191. ENV: Agent did: predict-no for direction U in state State-B
  6192. In State-B moving U
  6193. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  6194. predict error 0
  6195. dir: dir isU
  6196. \-/879: O: O1758 (predict-no)
  6197. I see 1 and I'm going to do: predict-no
  6198. ENV: Agent did: predict-no for direction U in state State-B
  6199. In State-B moving U
  6200. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  6201. predict error 0
  6202. dir: dir isU
  6203. |\880: O: O1760 (predict-no)
  6204. I see 1 and I'm going to do: predict-no
  6205. ENV: Agent did: predict-no for direction U in state State-B
  6206. In State-B moving U
  6207. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  6208. predict error 0
  6209. dir: dir isR
  6210. -/881: O: O1762 (predict-no)
  6211. I see 1 and I'm going to do: predict-no
  6212. ENV: Agent did: predict-no for direction R in state State-B
  6213. In State-B moving R
  6214. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  6215. predict error 0
  6216. dir: dir isL
  6217. |882: O: O1763 (predict-yes)
  6218. I see 1 and I'm going to do: predict-yes
  6219. ENV: Agent did: predict-yes for direction L in state State-B
  6220. In State-B moving L
  6221. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  6222. predict error 0
  6223. dir: dir isR
  6224. \-/883: O: O1765 (predict-yes)
  6225. I see 1 and I'm going to do: predict-yes
  6226. ENV: Agent did: predict-yes for direction R in state State-A
  6227. In State-A moving R
  6228. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  6229. predict error 0
  6230. dir: dir isL
  6231. |\-884: O: O1767 (predict-yes)
  6232. I see 1 and I'm going to do: predict-yes
  6233. ENV: Agent did: predict-yes for direction L in state State-B
  6234. In State-B moving L
  6235. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  6236. predict error 0
  6237. dir: dir isU
  6238. /|\885: O: O1770 (predict-no)
  6239. I see 1 and I'm going to do: predict-no
  6240. ENV: Agent did: predict-no for direction U in state State-A
  6241. In State-A moving U
  6242. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  6243. predict error 0
  6244. dir: dir isR
  6245. -/|886: O: O1771 (predict-yes)
  6246. I see 1 and I'm going to do: predict-yes
  6247. ENV: Agent did: predict-yes for direction R in state State-A
  6248. In State-A moving R
  6249. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  6250. predict error 0
  6251. dir: dir isR
  6252. \-887: O: O1774 (predict-no)
  6253. I see 1 and I'm going to do: predict-no
  6254. ENV: Agent did: predict-no for direction R in state State-B
  6255. In State-B moving R
  6256. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  6257. predict error 0
  6258. dir: dir isU
  6259. /|\888: O: O1776 (predict-no)
  6260. I see 1 and I'm going to do: predict-no
  6261. ENV: Agent did: predict-no for direction U in state State-B
  6262. In State-B moving U
  6263. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  6264. predict error 0
  6265. dir: dir isL
  6266. -/889: O: O1777 (predict-yes)
  6267. I see 1 and I'm going to do: predict-yes
  6268. ENV: Agent did: predict-yes for direction L in state State-B
  6269. In State-B moving L
  6270. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  6271. predict error 0
  6272. dir: dir isU
  6273. |\-890: O: O1780 (predict-no)
  6274. I see 1 and I'm going to do: predict-no
  6275. ENV: Agent did: predict-no for direction U in state State-A
  6276. In State-A moving U
  6277. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  6278. predict error 0
  6279. dir: dir isL
  6280. /|\891: O: O1782 (predict-no)
  6281. I see 1 and I'm going to do: predict-no
  6282. ENV: Agent did: predict-no for direction L in state State-A
  6283. In State-A moving L
  6284. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  6285. predict error 0
  6286. dir: dir isL
  6287. -892: O: O1784 (predict-no)
  6288. I see 1 and I'm going to do: predict-no
  6289. ENV: Agent did: predict-no for direction L in state State-A
  6290. In State-A moving L
  6291. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  6292. predict error 0
  6293. dir: dir isR
  6294. /|893: O: O1785 (predict-yes)
  6295. I see 1 and I'm going to do: predict-yes
  6296. ENV: Agent did: predict-yes for direction R in state State-A
  6297. In State-A moving R
  6298. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  6299. predict error 0
  6300. dir: dir isR
  6301. \-/894: O: O1788 (predict-no)
  6302. I see 1 and I'm going to do: predict-no
  6303. ENV: Agent did: predict-no for direction R in state State-B
  6304. In State-B moving R
  6305. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  6306. predict error 0
  6307. dir: dir isU
  6308. |\-895: O: O1790 (predict-no)
  6309. I see 1 and I'm going to do: predict-no
  6310. ENV: Agent did: predict-no for direction U in state State-B
  6311. In State-B moving U
  6312. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  6313. predict error 0
  6314. dir: dir isR
  6315. /|\896: O: O1792 (predict-no)
  6316. I see 1 and I'm going to do: predict-no
  6317. ENV: Agent did: predict-no for direction R in state State-B
  6318. In State-B moving R
  6319. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  6320. predict error 0
  6321. dir: dir isL
  6322. -/897: O: O1793 (predict-yes)
  6323. I see 1 and I'm going to do: predict-yes
  6324. ENV: Agent did: predict-yes for direction L in state State-B
  6325. In State-B moving L
  6326. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  6327. predict error 0
  6328. dir: dir isL
  6329. |\-898: O: O1796 (predict-no)
  6330. I see 1 and I'm going to do: predict-no
  6331. ENV: Agent did: predict-no for direction L in state State-A
  6332. In State-A moving L
  6333. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  6334. predict error 0
  6335. dir: dir isL
  6336. /|\899: O: O1798 (predict-no)
  6337. I see 1 and I'm going to do: predict-no
  6338. ENV: Agent did: predict-no for direction L in state State-A
  6339. In State-A moving L
  6340. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  6341. predict error 0
  6342. dir: dir isR
  6343. -/900: O: O1799 (predict-yes)
  6344. I see 1 and I'm going to do: predict-yes
  6345. ENV: Agent did: predict-yes for direction R in state State-A
  6346. In State-A moving R
  6347. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  6348. predict error 0
  6349. dir: dir isU
  6350. |\901: O: O1802 (predict-no)
  6351. I see 1 and I'm going to do: predict-no
  6352. ENV: Agent did: predict-no for direction U in state State-B
  6353. In State-B moving U
  6354. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  6355. predict error 0
  6356. dir: dir isL
  6357. -902: O: O1803 (predict-yes)
  6358. I see 1 and I'm going to do: predict-yes
  6359. ENV: Agent did: predict-yes for direction L in state State-B
  6360. In State-B moving L
  6361. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  6362. predict error 0
  6363. dir: dir isL
  6364. /|\903: O: O1806 (predict-no)
  6365. I see 1 and I'm going to do: predict-no
  6366. ENV: Agent did: predict-no for direction L in state State-A
  6367. In State-A moving L
  6368. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  6369. predict error 0
  6370. dir: dir isR
  6371. -/|904: O: O1807 (predict-yes)
  6372. I see 1 and I'm going to do: predict-yes
  6373. ENV: Agent did: predict-yes for direction R in state State-A
  6374. In State-A moving R
  6375. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  6376. predict error 0
  6377. dir: dir isU
  6378. \-/905: O: O1810 (predict-no)
  6379. I see 1 and I'm going to do: predict-no
  6380. ENV: Agent did: predict-no for direction U in state State-B
  6381. In State-B moving U
  6382. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  6383. predict error 0
  6384. dir: dir isU
  6385. |\-906: O: O1812 (predict-no)
  6386. I see 1 and I'm going to do: predict-no
  6387. ENV: Agent did: predict-no for direction U in state State-B
  6388. In State-B moving U
  6389. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  6390. predict error 0
  6391. dir: dir isU
  6392. /|\907: O: O1814 (predict-no)
  6393. I see 1 and I'm going to do: predict-no
  6394. ENV: Agent did: predict-no for direction U in state State-B
  6395. In State-B moving U
  6396. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  6397. predict error 0
  6398. dir: dir isR
  6399. -/|908: O: O1816 (predict-no)
  6400. I see 1 and I'm going to do: predict-no
  6401. ENV: Agent did: predict-no for direction R in state State-B
  6402. In State-B moving R
  6403. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  6404. predict error 0
  6405. dir: dir isR
  6406. \-/909: O: O1818 (predict-no)
  6407. I see 1 and I'm going to do: predict-no
  6408. ENV: Agent did: predict-no for direction R in state State-B
  6409. In State-B moving R
  6410. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  6411. predict error 0
  6412. dir: dir isL
  6413. |\910: O: O1819 (predict-yes)
  6414. I see 1 and I'm going to do: predict-yes
  6415. ENV: Agent did: predict-yes for direction L in state State-B
  6416. In State-B moving L
  6417. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  6418. predict error 0
  6419. dir: dir isR
  6420. -/|911: O: O1821 (predict-yes)
  6421. I see 1 and I'm going to do: predict-yes
  6422. ENV: Agent did: predict-yes for direction R in state State-A
  6423. In State-A moving R
  6424. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  6425. predict error 0
  6426. dir: dir isL
  6427. \912: O: O1823 (predict-yes)
  6428. I see 1 and I'm going to do: predict-yes
  6429. ENV: Agent did: predict-yes for direction L in state State-B
  6430. In State-B moving L
  6431. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  6432. predict error 0
  6433. dir: dir isL
  6434. -/913: O: O1826 (predict-no)
  6435. I see 1 and I'm going to do: predict-no
  6436. ENV: Agent did: predict-no for direction L in state State-A
  6437. In State-A moving L
  6438. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  6439. predict error 0
  6440. dir: dir isU
  6441. |\-914: O: O1828 (predict-no)
  6442. I see 1 and I'm going to do: predict-no
  6443. ENV: Agent did: predict-no for direction U in state State-A
  6444. In State-A moving U
  6445. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  6446. predict error 0
  6447. dir: dir isR
  6448. /|915: O: O1829 (predict-yes)
  6449. I see 1 and I'm going to do: predict-yes
  6450. ENV: Agent did: predict-yes for direction R in state State-A
  6451. In State-A moving R
  6452. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  6453. predict error 0
  6454. dir: dir isU
  6455. \-/916: O: O1832 (predict-no)
  6456. I see 1 and I'm going to do: predict-no
  6457. ENV: Agent did: predict-no for direction U in state State-B
  6458. In State-B moving U
  6459. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  6460. predict error 0
  6461. dir: dir isR
  6462. |\-917: O: O1834 (predict-no)
  6463. I see 1 and I'm going to do: predict-no
  6464. ENV: Agent did: predict-no for direction R in state State-B
  6465. In State-B moving R
  6466. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  6467. predict error 0
  6468. dir: dir isL
  6469. /|\918: O: O1835 (predict-yes)
  6470. I see 1 and I'm going to do: predict-yes
  6471. ENV: Agent did: predict-yes for direction L in state State-B
  6472. In State-B moving L
  6473. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  6474. predict error 0
  6475. dir: dir isR
  6476. -/|919: O: O1837 (predict-yes)
  6477. I see 1 and I'm going to do: predict-yes
  6478. ENV: Agent did: predict-yes for direction R in state State-A
  6479. In State-A moving R
  6480. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  6481. predict error 0
  6482. dir: dir isR
  6483. \-/920: O: O1840 (predict-no)
  6484. I see 1 and I'm going to do: predict-no
  6485. ENV: Agent did: predict-no for direction R in state State-B
  6486. In State-B moving R
  6487. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  6488. predict error 0
  6489. dir: dir isL
  6490. |\-921: O: O1841 (predict-yes)
  6491. I see 1 and I'm going to do: predict-yes
  6492. ENV: Agent did: predict-yes for direction L in state State-B
  6493. In State-B moving L
  6494. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  6495. predict error 0
  6496. dir: dir isU
  6497. /922: O: O1844 (predict-no)
  6498. I see 1 and I'm going to do: predict-no
  6499. ENV: Agent did: predict-no for direction U in state State-A
  6500. In State-A moving U
  6501. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  6502. predict error 0
  6503. dir: dir isU
  6504. |\923: O: O1846 (predict-no)
  6505. I see 1 and I'm going to do: predict-no
  6506. ENV: Agent did: predict-no for direction U in state State-A
  6507. In State-A moving U
  6508. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  6509. predict error 0
  6510. dir: dir isL
  6511. -/|924: O: O1848 (predict-no)
  6512. I see 1 and I'm going to do: predict-no
  6513. ENV: Agent did: predict-no for direction L in state State-A
  6514. In State-A moving L
  6515. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  6516. predict error 0
  6517. dir: dir isL
  6518. \-/|925: O: O1850 (predict-no)
  6519. I see 1 and I'm going to do: predict-no
  6520. ENV: Agent did: predict-no for direction L in state State-A
  6521. In State-A moving L
  6522. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  6523. predict error 0
  6524. dir: dir isU
  6525. \-/926: O: O1852 (predict-no)
  6526. I see 1 and I'm going to do: predict-no
  6527. ENV: Agent did: predict-no for direction U in state State-A
  6528. In State-A moving U
  6529. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  6530. predict error 0
  6531. dir: dir isU
  6532. |\-927: O: O1854 (predict-no)
  6533. I see 1 and I'm going to do: predict-no
  6534. ENV: Agent did: predict-no for direction U in state State-A
  6535. In State-A moving U
  6536. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  6537. predict error 0
  6538. dir: dir isL
  6539. /|\928: O: O1856 (predict-no)
  6540. I see 1 and I'm going to do: predict-no
  6541. ENV: Agent did: predict-no for direction L in state State-A
  6542. In State-A moving L
  6543. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  6544. predict error 0
  6545. dir: dir isR
  6546. -/|929: O: O1857 (predict-yes)
  6547. I see 1 and I'm going to do: predict-yes
  6548. ENV: Agent did: predict-yes for direction R in state State-A
  6549. In State-A moving R
  6550. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  6551. predict error 0
  6552. dir: dir isL
  6553. \-930: O: O1859 (predict-yes)
  6554. I see 1 and I'm going to do: predict-yes
  6555. ENV: Agent did: predict-yes for direction L in state State-B
  6556. In State-B moving L
  6557. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  6558. predict error 0
  6559. dir: dir isU
  6560. /|\931: O: O1862 (predict-no)
  6561. I see 1 and I'm going to do: predict-no
  6562. ENV: Agent did: predict-no for direction U in state State-A
  6563. In State-A moving U
  6564. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  6565. predict error 0
  6566. dir: dir isR
  6567. -932: O: O1863 (predict-yes)
  6568. I see 1 and I'm going to do: predict-yes
  6569. ENV: Agent did: predict-yes for direction R in state State-A
  6570. In State-A moving R
  6571. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  6572. predict error 0
  6573. dir: dir isR
  6574. /|\933: O: O1866 (predict-no)
  6575. I see 1 and I'm going to do: predict-no
  6576. ENV: Agent did: predict-no for direction R in state State-B
  6577. In State-B moving R
  6578. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  6579. predict error 0
  6580. dir: dir isL
  6581. -934: O: O1867 (predict-yes)
  6582. I see 1 and I'm going to do: predict-yes
  6583. ENV: Agent did: predict-yes for direction L in state State-B
  6584. In State-B moving L
  6585. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  6586. predict error 0
  6587. dir: dir isR
  6588. /935: O: O1869 (predict-yes)
  6589. I see 1 and I'm going to do: predict-yes
  6590. ENV: Agent did: predict-yes for direction R in state State-A
  6591. In State-A moving R
  6592. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  6593. predict error 0
  6594. dir: dir isR
  6595. |\936: O: O1872 (predict-no)
  6596. I see 1 and I'm going to do: predict-no
  6597. ENV: Agent did: predict-no for direction R in state State-B
  6598. In State-B moving R
  6599. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  6600. predict error 0
  6601. dir: dir isR
  6602. -937: O: O1874 (predict-no)
  6603. I see 1 and I'm going to do: predict-no
  6604. ENV: Agent did: predict-no for direction R in state State-B
  6605. In State-B moving R
  6606. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  6607. predict error 0
  6608. dir: dir isL
  6609. /|\938: O: O1875 (predict-yes)
  6610. I see 1 and I'm going to do: predict-yes
  6611. ENV: Agent did: predict-yes for direction L in state State-B
  6612. In State-B moving L
  6613. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  6614. predict error 0
  6615. dir: dir isL
  6616. -/939: O: O1878 (predict-no)
  6617. I see 1 and I'm going to do: predict-no
  6618. ENV: Agent did: predict-no for direction L in state State-A
  6619. In State-A moving L
  6620. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  6621. predict error 0
  6622. dir: dir isU
  6623. |940: O: O1880 (predict-no)
  6624. I see 1 and I'm going to do: predict-no
  6625. ENV: Agent did: predict-no for direction U in state State-A
  6626. In State-A moving U
  6627. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  6628. predict error 0
  6629. dir: dir isU
  6630. \-/941: O: O1882 (predict-no)
  6631. I see 1 and I'm going to do: predict-no
  6632. ENV: Agent did: predict-no for direction U in state State-A
  6633. In State-A moving U
  6634. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  6635. predict error 0
  6636. dir: dir isU
  6637. |942: O: O1884 (predict-no)
  6638. I see 1 and I'm going to do: predict-no
  6639. ENV: Agent did: predict-no for direction U in state State-A
  6640. In State-A moving U
  6641. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  6642. predict error 0
  6643. dir: dir isR
  6644. \-/943: O: O1885 (predict-yes)
  6645. I see 1 and I'm going to do: predict-yes
  6646. ENV: Agent did: predict-yes for direction R in state State-A
  6647. In State-A moving R
  6648. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  6649. predict error 0
  6650. dir: dir isU
  6651. |\-944: O: O1888 (predict-no)
  6652. I see 1 and I'm going to do: predict-no
  6653. ENV: Agent did: predict-no for direction U in state State-B
  6654. In State-B moving U
  6655. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  6656. predict error 0
  6657. dir: dir isL
  6658. /|\945: O: O1889 (predict-yes)
  6659. I see 1 and I'm going to do: predict-yes
  6660. ENV: Agent did: predict-yes for direction L in state State-B
  6661. In State-B moving L
  6662. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  6663. predict error 0
  6664. dir: dir isL
  6665. -/946: O: O1892 (predict-no)
  6666. I see 1 and I'm going to do: predict-no
  6667. ENV: Agent did: predict-no for direction L in state State-A
  6668. In State-A moving L
  6669. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  6670. predict error 0
  6671. dir: dir isU
  6672. |\-947: O: O1894 (predict-no)
  6673. I see 1 and I'm going to do: predict-no
  6674. ENV: Agent did: predict-no for direction U in state State-A
  6675. In State-A moving U
  6676. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  6677. predict error 0
  6678. dir: dir isL
  6679. /|948: O: O1896 (predict-no)
  6680. I see 1 and I'm going to do: predict-no
  6681. ENV: Agent did: predict-no for direction L in state State-A
  6682. In State-A moving L
  6683. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  6684. predict error 0
  6685. dir: dir isL
  6686. \-/949: O: O1898 (predict-no)
  6687. I see 1 and I'm going to do: predict-no
  6688. ENV: Agent did: predict-no for direction L in state State-A
  6689. In State-A moving L
  6690. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  6691. predict error 0
  6692. dir: dir isU
  6693. |\-950: O: O1900 (predict-no)
  6694. I see 1 and I'm going to do: predict-no
  6695. ENV: Agent did: predict-no for direction U in state State-A
  6696. In State-A moving U
  6697. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  6698. predict error 0
  6699. dir: dir isL
  6700. /|\-/|\---- Input Phase ---
  6701. =>WM: (13326: I2 ^dir L)
  6702. =>WM: (13325: I2 ^reward 1)
  6703. =>WM: (13324: I2 ^see 0)
  6704. =>WM: (13323: N950 ^status complete)
  6705. <=WM: (13312: I2 ^dir U)
  6706. <=WM: (13311: I2 ^reward 1)
  6707. <=WM: (13310: I2 ^see 0)
  6708. =>WM: (13327: I2 ^level-1 L0-root)
  6709. <=WM: (13313: I2 ^level-1 L0-root)
  6710. --- END Input Phase ---
  6711. --- Proposal Phase ---
  6712. --- Inner Elaboration Phase, active level 1 (S1) ---
  6713. Firing rl*prefer*rvt*predict-yes*H0*3*H1*13
  6714. -->
  6715. (S1 ^operator O1899 = 0.07203)
  6716. Firing rl*prefer*rvt*predict-no*H0*4*H1*12
  6717. -->
  6718. (S1 ^operator O1900 = 0.5664894375976002)
  6719. Firing prefer*rvt*predict-no*H0*4*H1
  6720. -->
  6721. Firing prefer*rvt*predict-yes*H0*3*H1
  6722. -->
  6723. Firing elaborate*copy-see-to-output-link
  6724. -->
  6725. (I3 ^see 0 +)
  6726. Firing elaborate*reward*based*on*reward
  6727. -->
  6728. (R954 ^value 1 +)
  6729. (R1 ^reward R954 +)
  6730. Firing propose*predict-yes
  6731. -->
  6732. (O1901 ^name predict-yes +)
  6733. (S1 ^operator O1901 +)
  6734. Firing propose*predict-no
  6735. -->
  6736. (O1902 ^name predict-no +)
  6737. (S1 ^operator O1902 +)
  6738. Firing rl*prefer*rvt*predict-no*H0*4
  6739. -->
  6740. (S1 ^operator O1900 = 0.4334999153319997)
  6741. Firing rl*prefer*rvt*predict-yes*H0*3
  6742. -->
  6743. (S1 ^operator O1899 = 0.6069190364034727)
  6744. Firing prefer*rvt*predict-yes*H0
  6745. -->
  6746. Firing prefer*rvt*predict-no*H0
  6747. -->
  6748. Firing elaborate*copy-dir-to-output-link
  6749. -->
  6750. (I3 ^dir L +)
  6751. inner elaboration loop at bottom goal.
  6752. Retracting elaborate*copy-see-to-output-link
  6753. -->
  6754. (I3 ^see 0 +)
  6755. Retracting propose*predict-no
  6756. -->
  6757. (O1900 ^name predict-no +)
  6758. (S1 ^operator O1900 +)
  6759. Retracting propose*predict-yes
  6760. -->
  6761. (O1899 ^name predict-yes +)
  6762. (S1 ^operator O1899 +)
  6763. Retracting elaborate*reward*based*on*reward
  6764. -->
  6765. (R953 ^value 1 +)
  6766. (R1 ^reward R953 +)
  6767. Retracting elaborate*copy-dir-to-output-link
  6768. -->
  6769. (I3 ^dir U +)
  6770. Retracting rl*prefer*rvt*predict-no*H0*2
  6771. -->
  6772. (S1 ^operator O1900 = 0.9999999999999999)
  6773. Retracting rl*prefer*rvt*predict-yes*H0*1
  6774. -->
  6775. (S1 ^operator O1899 = 0.)
  6776. =>WM: (13334: S1 ^operator O1902 +)
  6777. =>WM: (13333: S1 ^operator O1901 +)
  6778. =>WM: (13332: I3 ^dir L)
  6779. =>WM: (13331: O1902 ^name predict-no)
  6780. =>WM: (13330: O1901 ^name predict-yes)
  6781. =>WM: (13329: R954 ^value 1)
  6782. =>WM: (13328: R1 ^reward R954)
  6783. <=WM: (13319: S1 ^operator O1899 +)
  6784. <=WM: (13320: S1 ^operator O1900 +)
  6785. <=WM: (13321: S1 ^operator O1900)
  6786. <=WM: (13318: I3 ^dir U)
  6787. <=WM: (13314: R1 ^reward R953)
  6788. <=WM: (13317: O1900 ^name predict-no)
  6789. <=WM: (13316: O1899 ^name predict-yes)
  6790. <=WM: (13315: R953 ^value 1)
  6791. --- Inner Elaboration Phase, active level 1 (S1) ---
  6792. Firing prefer*rvt*predict-yes*H0
  6793. -->
  6794. Firing rl*prefer*rvt*predict-yes*H0*3*H1*13
  6795. -->
  6796. (S1 ^operator O1901 = 0.07203)
  6797. Firing rl*prefer*rvt*predict-yes*H0*3
  6798. -->
  6799. (S1 ^operator O1901 = 0.6069190364034727)
  6800. Firing prefer*rvt*predict-yes*H0*3*H1
  6801. -->
  6802. Firing prefer*rvt*predict-no*H0
  6803. -->
  6804. Firing rl*prefer*rvt*predict-no*H0*4*H1*12
  6805. -->
  6806. (S1 ^operator O1902 = 0.5664894375976002)
  6807. Firing rl*prefer*rvt*predict-no*H0*4
  6808. -->
  6809. (S1 ^operator O1902 = 0.4334999153319997)
  6810. Firing prefer*rvt*predict-no*H0*4*H1
  6811. -->
  6812. inner elaboration loop at bottom goal.
  6813. Retracting rl*prefer*rvt*predict-no*H0*4
  6814. -->
  6815. (S1 ^operator O1900 = 0.4334999153319997)
  6816. Retracting rl*prefer*rvt*predict-no*H0*4*H1*12
  6817. -->
  6818. (S1 ^operator O1900 = 0.5664894375976002)
  6819. Retracting rl*prefer*rvt*predict-yes*H0*3
  6820. -->
  6821. (S1 ^operator O1899 = 0.6069190364034727)
  6822. Retracting rl*prefer*rvt*predict-yes*H0*3*H1*13
  6823. -->
  6824. (S1 ^operator O1899 = 0.07203)
  6825. --- END Proposal Phase ---
  6826. --- Decision Phase ---
  6827. RL update rl*prefer*rvt*predict-no*H0*2 1 0 1 -> 1 0 1(R,m,v=1,1,0)
  6828. =>WM: (13335: S1 ^operator O1902)
  6829. 951: O: O1902 (predict-no)
  6830. --- END Decision Phase ---
  6831. --- Application Phase ---
  6832. --- Firing Productions (PE) For State At Depth 1 ---
  6833. --- Inner Elaboration Phase, active level 1 (S1) ---
  6834. Firing apply*operator
  6835. -->
  6836. (I3 ^predict-no N951 + :O )
  6837. Firing apply*operator*complete
  6838. -->
  6839. (I3 ^predict-no N950 - :O )
  6840. inner elaboration loop at bottom goal.
  6841. --- Change Working Memory (PE) ---
  6842. =>WM: (13336: I3 ^predict-no N951)
  6843. <=WM: (13323: N950 ^status complete)
  6844. <=WM: (13322: I3 ^predict-no N950)
  6845. --- Firing Productions (IE) For State At Depth 1 ---
  6846. --- Inner Elaboration Phase, active level 1 (S1) ---
  6847. Firing monitor*world
  6848. -->
  6849. I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
  6850. --- Change Working Memory (IE) ---
  6851. --- END Application Phase ---
  6852. --- Output Phase ---
  6853. ENV: Agent did: predict-no for direction L in state State-A
  6854. In State-A moving L
  6855. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  6856. predict error 0
  6857. dir: dir isL
  6858. --- END Output Phase ---
  6859. /--- Input Phase ---
  6860. =>WM: (13340: I2 ^dir L)
  6861. =>WM: (13339: I2 ^reward 1)
  6862. =>WM: (13338: I2 ^see 0)
  6863. =>WM: (13337: N951 ^status complete)
  6864. <=WM: (13326: I2 ^dir L)
  6865. <=WM: (13325: I2 ^reward 1)
  6866. <=WM: (13324: I2 ^see 0)
  6867. =>WM: (13341: I2 ^level-1 L0-root)
  6868. <=WM: (13327: I2 ^level-1 L0-root)
  6869. --- END Input Phase ---
  6870. --- Proposal Phase ---
  6871. --- Inner Elaboration Phase, active level 1 (S1) ---
  6872. Firing rl*prefer*rvt*predict-yes*H0*3*H1*13
  6873. -->
  6874. (S1 ^operator O1901 = 0.07203)
  6875. Firing rl*prefer*rvt*predict-no*H0*4*H1*12
  6876. -->
  6877. (S1 ^operator O1902 = 0.5664894375976002)
  6878. Firing prefer*rvt*predict-no*H0*4*H1
  6879. -->
  6880. Firing prefer*rvt*predict-yes*H0*3*H1
  6881. -->
  6882. Firing elaborate*copy-see-to-output-link
  6883. -->
  6884. (I3 ^see 0 +)
  6885. Firing elaborate*reward*based*on*reward
  6886. -->
  6887. (R955 ^value 1 +)
  6888. (R1 ^reward R955 +)
  6889. Firing propose*predict-yes
  6890. -->
  6891. (O1903 ^name predict-yes +)
  6892. (S1 ^operator O1903 +)
  6893. Firing propose*predict-no
  6894. -->
  6895. (O1904 ^name predict-no +)
  6896. (S1 ^operator O1904 +)
  6897. Firing rl*prefer*rvt*predict-no*H0*4
  6898. -->
  6899. (S1 ^operator O1902 = 0.4334999153319997)
  6900. Firing rl*prefer*rvt*predict-yes*H0*3
  6901. -->
  6902. (S1 ^operator O1901 = 0.6069190364034727)
  6903. Firing prefer*rvt*predict-yes*H0
  6904. -->
  6905. Firing prefer*rvt*predict-no*H0
  6906. -->
  6907. Firing elaborate*copy-dir-to-output-link
  6908. -->
  6909. (I3 ^dir L +)
  6910. inner elaboration loop at bottom goal.
  6911. Retracting elaborate*copy-see-to-output-link
  6912. -->
  6913. (I3 ^see 0 +)
  6914. Retracting propose*predict-no
  6915. -->
  6916. (O1902 ^name predict-no +)
  6917. (S1 ^operator O1902 +)
  6918. Retracting propose*predict-yes
  6919. -->
  6920. (O1901 ^name predict-yes +)
  6921. (S1 ^operator O1901 +)
  6922. Retracting elaborate*reward*based*on*reward
  6923. -->
  6924. (R954 ^value 1 +)
  6925. (R1 ^reward R954 +)
  6926. Retracting elaborate*copy-dir-to-output-link
  6927. -->
  6928. (I3 ^dir L +)
  6929. Retracting rl*prefer*rvt*predict-no*H0*4
  6930. -->
  6931. (S1 ^operator O1902 = 0.4334999153319997)
  6932. Retracting rl*prefer*rvt*predict-no*H0*4*H1*12
  6933. -->
  6934. (S1 ^operator O1902 = 0.5664894375976002)
  6935. Retracting rl*prefer*rvt*predict-yes*H0*3
  6936. -->
  6937. (S1 ^operator O1901 = 0.6069190364034727)
  6938. Retracting rl*prefer*rvt*predict-yes*H0*3*H1*13
  6939. -->
  6940. (S1 ^operator O1901 = 0.07203)
  6941. =>WM: (13347: S1 ^operator O1904 +)
  6942. =>WM: (13346: S1 ^operator O1903 +)
  6943. =>WM: (13345: O1904 ^name predict-no)
  6944. =>WM: (13344: O1903 ^name predict-yes)
  6945. =>WM: (13343: R955 ^value 1)
  6946. =>WM: (13342: R1 ^reward R955)
  6947. <=WM: (13333: S1 ^operator O1901 +)
  6948. <=WM: (13334: S1 ^operator O1902 +)
  6949. <=WM: (13335: S1 ^operator O1902)
  6950. <=WM: (13328: R1 ^reward R954)
  6951. <=WM: (13331: O1902 ^name predict-no)
  6952. <=WM: (13330: O1901 ^name predict-yes)
  6953. <=WM: (13329: R954 ^value 1)
  6954. --- Inner Elaboration Phase, active level 1 (S1) ---
  6955. Firing prefer*rvt*predict-yes*H0
  6956. -->
  6957. Firing rl*prefer*rvt*predict-yes*H0*3*H1*13
  6958. -->
  6959. (S1 ^operator O1903 = 0.07203)
  6960. Firing rl*prefer*rvt*predict-yes*H0*3
  6961. -->
  6962. (S1 ^operator O1903 = 0.6069190364034727)
  6963. Firing prefer*rvt*predict-yes*H0*3*H1
  6964. -->
  6965. Firing prefer*rvt*predict-no*H0
  6966. -->
  6967. Firing rl*prefer*rvt*predict-no*H0*4*H1*12
  6968. -->
  6969. (S1 ^operator O1904 = 0.5664894375976002)
  6970. Firing rl*prefer*rvt*predict-no*H0*4
  6971. -->
  6972. (S1 ^operator O1904 = 0.4334999153319997)
  6973. Firing prefer*rvt*predict-no*H0*4*H1
  6974. -->
  6975. inner elaboration loop at bottom goal.
  6976. Retracting rl*prefer*rvt*predict-no*H0*4
  6977. -->
  6978. (S1 ^operator O1902 = 0.4334999153319997)
  6979. Retracting rl*prefer*rvt*predict-no*H0*4*H1*12
  6980. -->
  6981. (S1 ^operator O1902 = 0.5664894375976002)
  6982. Retracting rl*prefer*rvt*predict-yes*H0*3
  6983. -->
  6984. (S1 ^operator O1901 = 0.6069190364034727)
  6985. Retracting rl*prefer*rvt*predict-yes*H0*3*H1*13
  6986. -->
  6987. (S1 ^operator O1901 = 0.07203)
  6988. --- END Proposal Phase ---
  6989. --- Decision Phase ---
  6990. RL update rl*prefer*rvt*predict-no*H0*4 0.490216 -0.056716 0.4335 -> 0.490218 -0.056716 0.433502(R,m,v=1,0.882353,0.104489)
  6991. RL update rl*prefer*rvt*predict-no*H0*4*H1*12 0.509773 0.056716 0.566489 -> 0.509775 0.056716 0.566491(R,m,v=1,1,0)
  6992. =>WM: (13348: S1 ^operator O1904)
  6993. 952: O: O1904 (predict-no)
  6994. --- END Decision Phase ---
  6995. --- Application Phase ---
  6996. --- Firing Productions (PE) For State At Depth 1 ---
  6997. --- Inner Elaboration Phase, active level 1 (S1) ---
  6998. Firing apply*operator
  6999. -->
  7000. (I3 ^predict-no N952 + :O )
  7001. Firing apply*operator*complete
  7002. -->
  7003. (I3 ^predict-no N951 - :O )
  7004. inner elaboration loop at bottom goal.
  7005. --- Change Working Memory (PE) ---
  7006. =>WM: (13349: I3 ^predict-no N952)
  7007. <=WM: (13337: N951 ^status complete)
  7008. <=WM: (13336: I3 ^predict-no N951)
  7009. --- Firing Productions (IE) For State At Depth 1 ---
  7010. --- Inner Elaboration Phase, active level 1 (S1) ---
  7011. Firing monitor*world
  7012. -->
  7013. I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
  7014. --- Change Working Memory (IE) ---
  7015. --- END Application Phase ---
  7016. --- Output Phase ---
  7017. ENV: Agent did: predict-no for direction L in state State-A
  7018. In State-A moving L
  7019. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  7020. predict error 0
  7021. dir: dir isR
  7022. --- END Output Phase ---
  7023. |\---- Input Phase ---
  7024. =>WM: (13353: I2 ^dir R)
  7025. =>WM: (13352: I2 ^reward 1)
  7026. =>WM: (13351: I2 ^see 0)
  7027. =>WM: (13350: N952 ^status complete)
  7028. <=WM: (13340: I2 ^dir L)
  7029. <=WM: (13339: I2 ^reward 1)
  7030. <=WM: (13338: I2 ^see 0)
  7031. =>WM: (13354: I2 ^level-1 L0-root)
  7032. <=WM: (13341: I2 ^level-1 L0-root)
  7033. --- END Input Phase ---
  7034. --- Proposal Phase ---
  7035. --- Inner Elaboration Phase, active level 1 (S1) ---
  7036. Firing rl*prefer*rvt*predict-yes*H0*5*H1*14
  7037. -->
  7038. (S1 ^operator O1903 = 0.9322245630318109)
  7039. Firing rl*prefer*rvt*predict-no*H0*6*H1*19
  7040. -->
  7041. (S1 ^operator O1904 = 0.3)
  7042. Firing prefer*rvt*predict-no*H0*6*H1
  7043. -->
  7044. Firing prefer*rvt*predict-yes*H0*5*H1
  7045. -->
  7046. Firing elaborate*copy-see-to-output-link
  7047. -->
  7048. (I3 ^see 0 +)
  7049. Firing elaborate*reward*based*on*reward
  7050. -->
  7051. (R956 ^value 1 +)
  7052. (R1 ^reward R956 +)
  7053. Firing propose*predict-yes
  7054. -->
  7055. (O1905 ^name predict-yes +)
  7056. (S1 ^operator O1905 +)
  7057. Firing propose*predict-no
  7058. -->
  7059. (O1906 ^name predict-no +)
  7060. (S1 ^operator O1906 +)
  7061. Firing rl*prefer*rvt*predict-no*H0*6
  7062. -->
  7063. (S1 ^operator O1904 = 0.4643594311868555)
  7064. Firing rl*prefer*rvt*predict-yes*H0*5
  7065. -->
  7066. (S1 ^operator O1903 = 0.06777570562039392)
  7067. Firing prefer*rvt*predict-yes*H0
  7068. -->
  7069. Firing prefer*rvt*predict-no*H0
  7070. -->
  7071. Firing elaborate*copy-dir-to-output-link
  7072. -->
  7073. (I3 ^dir R +)
  7074. inner elaboration loop at bottom goal.
  7075. Retracting elaborate*copy-see-to-output-link
  7076. -->
  7077. (I3 ^see 0 +)
  7078. Retracting propose*predict-no
  7079. -->
  7080. (O1904 ^name predict-no +)
  7081. (S1 ^operator O1904 +)
  7082. Retracting propose*predict-yes
  7083. -->
  7084. (O1903 ^name predict-yes +)
  7085. (S1 ^operator O1903 +)
  7086. Retracting elaborate*reward*based*on*reward
  7087. -->
  7088. (R955 ^value 1 +)
  7089. (R1 ^reward R955 +)
  7090. Retracting elaborate*copy-dir-to-output-link
  7091. -->
  7092. (I3 ^dir L +)
  7093. Retracting rl*prefer*rvt*predict-no*H0*4
  7094. -->
  7095. (S1 ^operator O1904 = 0.4335015123925597)
  7096. Retracting rl*prefer*rvt*predict-no*H0*4*H1*12
  7097. -->
  7098. (S1 ^operator O1904 = 0.5664910346581602)
  7099. Retracting rl*prefer*rvt*predict-yes*H0*3
  7100. -->
  7101. (S1 ^operator O1903 = 0.6069190364034727)
  7102. Retracting rl*prefer*rvt*predict-yes*H0*3*H1*13
  7103. -->
  7104. (S1 ^operator O1903 = 0.07203)
  7105. =>WM: (13361: S1 ^operator O1906 +)
  7106. =>WM: (13360: S1 ^operator O1905 +)
  7107. =>WM: (13359: I3 ^dir R)
  7108. =>WM: (13358: O1906 ^name predict-no)
  7109. =>WM: (13357: O1905 ^name predict-yes)
  7110. =>WM: (13356: R956 ^value 1)
  7111. =>WM: (13355: R1 ^reward R956)
  7112. <=WM: (13346: S1 ^operator O1903 +)
  7113. <=WM: (13347: S1 ^operator O1904 +)
  7114. <=WM: (13348: S1 ^operator O1904)
  7115. <=WM: (13332: I3 ^dir L)
  7116. <=WM: (13342: R1 ^reward R955)
  7117. <=WM: (13345: O1904 ^name predict-no)
  7118. <=WM: (13344: O1903 ^name predict-yes)
  7119. <=WM: (13343: R955 ^value 1)
  7120. --- Inner Elaboration Phase, active level 1 (S1) ---
  7121. Firing prefer*rvt*predict-yes*H0
  7122. -->
  7123. Firing rl*prefer*rvt*predict-yes*H0*5*H1*14
  7124. -->
  7125. (S1 ^operator O1905 = 0.9322245630318109)
  7126. Firing rl*prefer*rvt*predict-yes*H0*5
  7127. -->
  7128. (S1 ^operator O1905 = 0.06777570562039392)
  7129. Firing prefer*rvt*predict-yes*H0*5*H1
  7130. -->
  7131. Firing prefer*rvt*predict-no*H0
  7132. -->
  7133. Firing rl*prefer*rvt*predict-no*H0*6*H1*19
  7134. -->
  7135. (S1 ^operator O1906 = 0.3)
  7136. Firing rl*prefer*rvt*predict-no*H0*6
  7137. -->
  7138. (S1 ^operator O1906 = 0.4643594311868555)
  7139. Firing prefer*rvt*predict-no*H0*6*H1
  7140. -->
  7141. inner elaboration loop at bottom goal.
  7142. Retracting rl*prefer*rvt*predict-no*H0*6
  7143. -->
  7144. (S1 ^operator O1904 = 0.4643594311868555)
  7145. Retracting rl*prefer*rvt*predict-no*H0*6*H1*19
  7146. -->
  7147. (S1 ^operator O1904 = 0.3)
  7148. Retracting rl*prefer*rvt*predict-yes*H0*5
  7149. -->
  7150. (S1 ^operator O1903 = 0.06777570562039392)
  7151. Retracting rl*prefer*rvt*predict-yes*H0*5*H1*14
  7152. -->
  7153. (S1 ^operator O1903 = 0.9322245630318109)
  7154. --- END Proposal Phase ---
  7155. --- Decision Phase ---
  7156. RL update rl*prefer*rvt*predict-no*H0*4 0.490218 -0.056716 0.433502 -> 0.490219 -0.056716 0.433503(R,m,v=1,0.883117,0.103896)
  7157. RL update rl*prefer*rvt*predict-no*H0*4*H1*12 0.509775 0.056716 0.566491 -> 0.509776 0.056716 0.566492(R,m,v=1,1,0)
  7158. =>WM: (13362: S1 ^operator O1905)
  7159. 953: O: O1905 (predict-yes)
  7160. --- END Decision Phase ---
  7161. --- Application Phase ---
  7162. --- Firing Productions (PE) For State At Depth 1 ---
  7163. --- Inner Elaboration Phase, active level 1 (S1) ---
  7164. Firing apply*operator
  7165. -->
  7166. (I3 ^predict-yes N953 + :O )
  7167. Firing apply*operator*complete
  7168. -->
  7169. (I3 ^predict-no N952 - :O )
  7170. inner elaboration loop at bottom goal.
  7171. --- Change Working Memory (PE) ---
  7172. =>WM: (13363: I3 ^predict-yes N953)
  7173. <=WM: (13350: N952 ^status complete)
  7174. <=WM: (13349: I3 ^predict-no N952)
  7175. --- Firing Productions (IE) For State At Depth 1 ---
  7176. --- Inner Elaboration Phase, active level 1 (S1) ---
  7177. Firing monitor*world
  7178. -->
  7179. I see 1 and I'm going to do: predict-yes inner elaboration loop at bottom goal.
  7180. --- Change Working Memory (IE) ---
  7181. --- END Application Phase ---
  7182. --- Output Phase ---
  7183. ENV: Agent did: predict-yes for direction R in state State-A
  7184. In State-A moving R
  7185. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  7186. predict error 0
  7187. dir: dir isU
  7188. --- END Output Phase ---
  7189. /|\--- Input Phase ---
  7190. =>WM: (13367: I2 ^dir U)
  7191. =>WM: (13366: I2 ^reward 1)
  7192. =>WM: (13365: I2 ^see 1)
  7193. =>WM: (13364: N953 ^status complete)
  7194. <=WM: (13353: I2 ^dir R)
  7195. <=WM: (13352: I2 ^reward 1)
  7196. <=WM: (13351: I2 ^see 0)
  7197. =>WM: (13368: I2 ^level-1 R1-root)
  7198. <=WM: (13354: I2 ^level-1 L0-root)
  7199. --- END Input Phase ---
  7200. --- Proposal Phase ---
  7201. --- Inner Elaboration Phase, active level 1 (S1) ---
  7202. Firing elaborate*copy-see-to-output-link
  7203. -->
  7204. (I3 ^see 1 +)
  7205. Firing elaborate*reward*based*on*reward
  7206. -->
  7207. (R957 ^value 1 +)
  7208. (R1 ^reward R957 +)
  7209. Firing propose*predict-yes
  7210. -->
  7211. (O1907 ^name predict-yes +)
  7212. (S1 ^operator O1907 +)
  7213. Firing propose*predict-no
  7214. -->
  7215. (O1908 ^name predict-no +)
  7216. (S1 ^operator O1908 +)
  7217. Firing rl*prefer*rvt*predict-no*H0*2
  7218. -->
  7219. (S1 ^operator O1906 = 0.9999999999999999)
  7220. Firing rl*prefer*rvt*predict-yes*H0*1
  7221. -->
  7222. (S1 ^operator O1905 = 0.)
  7223. Firing prefer*rvt*predict-yes*H0
  7224. -->
  7225. Firing prefer*rvt*predict-no*H0
  7226. -->
  7227. Firing elaborate*copy-dir-to-output-link
  7228. -->
  7229. (I3 ^dir U +)
  7230. inner elaboration loop at bottom goal.
  7231. Retracting elaborate*copy-see-to-output-link
  7232. -->
  7233. (I3 ^see 0 +)
  7234. Retracting propose*predict-no
  7235. -->
  7236. (O1906 ^name predict-no +)
  7237. (S1 ^operator O1906 +)
  7238. Retracting propose*predict-yes
  7239. -->
  7240. (O1905 ^name predict-yes +)
  7241. (S1 ^operator O1905 +)
  7242. Retracting elaborate*reward*based*on*reward
  7243. -->
  7244. (R956 ^value 1 +)
  7245. (R1 ^reward R956 +)
  7246. Retracting elaborate*copy-dir-to-output-link
  7247. -->
  7248. (I3 ^dir R +)
  7249. Retracting rl*prefer*rvt*predict-no*H0*6
  7250. -->
  7251. (S1 ^operator O1906 = 0.4643594311868555)
  7252. Retracting rl*prefer*rvt*predict-no*H0*6*H1*19
  7253. -->
  7254. (S1 ^operator O1906 = 0.3)
  7255. Retracting rl*prefer*rvt*predict-yes*H0*5
  7256. -->
  7257. (S1 ^operator O1905 = 0.06777570562039392)
  7258. Retracting rl*prefer*rvt*predict-yes*H0*5*H1*14
  7259. -->
  7260. (S1 ^operator O1905 = 0.9322245630318109)
  7261. =>WM: (13376: S1 ^operator O1908 +)
  7262. =>WM: (13375: S1 ^operator O1907 +)
  7263. =>WM: (13374: I3 ^dir U)
  7264. =>WM: (13373: O1908 ^name predict-no)
  7265. =>WM: (13372: O1907 ^name predict-yes)
  7266. =>WM: (13371: R957 ^value 1)
  7267. =>WM: (13370: R1 ^reward R957)
  7268. =>WM: (13369: I3 ^see 1)
  7269. <=WM: (13360: S1 ^operator O1905 +)
  7270. <=WM: (13362: S1 ^operator O1905)
  7271. <=WM: (13361: S1 ^operator O1906 +)
  7272. <=WM: (13359: I3 ^dir R)
  7273. <=WM: (13355: R1 ^reward R956)
  7274. <=WM: (13272: I3 ^see 0)
  7275. <=WM: (13358: O1906 ^name predict-no)
  7276. <=WM: (13357: O1905 ^name predict-yes)
  7277. <=WM: (13356: R956 ^value 1)
  7278. --- Inner Elaboration Phase, active level 1 (S1) ---
  7279. Firing prefer*rvt*predict-yes*H0
  7280. -->
  7281. Firing rl*prefer*rvt*predict-yes*H0*1
  7282. -->
  7283. (S1 ^operator O1907 = 0.)
  7284. Firing prefer*rvt*predict-no*H0
  7285. -->
  7286. Firing rl*prefer*rvt*predict-no*H0*2
  7287. -->
  7288. (S1 ^operator O1908 = 0.9999999999999999)
  7289. inner elaboration loop at bottom goal.
  7290. Retracting rl*prefer*rvt*predict-no*H0*2
  7291. -->
  7292. (S1 ^operator O1906 = 0.9999999999999999)
  7293. Retracting rl*prefer*rvt*predict-yes*H0*1
  7294. -->
  7295. (S1 ^operator O1905 = 0.)
  7296. --- END Proposal Phase ---
  7297. --- Decision Phase ---
  7298. RL update rl*prefer*rvt*predict-yes*H0*5 0.606208 -0.538432 0.0677757 -> 0.606208 -0.538432 0.0677757(R,m,v=1,0.867052,0.115943)
  7299. RL update rl*prefer*rvt*predict-yes*H0*5*H1*14 0.393793 0.538432 0.932225 -> 0.393793 0.538432 0.932225(R,m,v=1,1,0)
  7300. =>WM: (13377: S1 ^operator O1908)
  7301. 954: O: O1908 (predict-no)
  7302. --- END Decision Phase ---
  7303. --- Application Phase ---
  7304. --- Firing Productions (PE) For State At Depth 1 ---
  7305. --- Inner Elaboration Phase, active level 1 (S1) ---
  7306. Firing apply*operator
  7307. -->
  7308. (I3 ^predict-no N954 + :O )
  7309. Firing apply*operator*complete
  7310. -->
  7311. (I3 ^predict-yes N953 - :O )
  7312. inner elaboration loop at bottom goal.
  7313. --- Change Working Memory (PE) ---
  7314. =>WM: (13378: I3 ^predict-no N954)
  7315. <=WM: (13364: N953 ^status complete)
  7316. <=WM: (13363: I3 ^predict-yes N953)
  7317. --- Firing Productions (IE) For State At Depth 1 ---
  7318. --- Inner Elaboration Phase, active level 1 (S1) ---
  7319. Firing monitor*world
  7320. -->
  7321. I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
  7322. --- Change Working Memory (IE) ---
  7323. --- END Application Phase ---
  7324. --- Output Phase ---
  7325. ENV: Agent did: predict-no for direction U in state State-B
  7326. In State-B moving U
  7327. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  7328. predict error 0
  7329. dir: dir isL
  7330. --- END Output Phase ---
  7331. -/|--- Input Phase ---
  7332. =>WM: (13382: I2 ^dir L)
  7333. =>WM: (13381: I2 ^reward 1)
  7334. =>WM: (13380: I2 ^see 0)
  7335. =>WM: (13379: N954 ^status complete)
  7336. <=WM: (13367: I2 ^dir U)
  7337. <=WM: (13366: I2 ^reward 1)
  7338. <=WM: (13365: I2 ^see 1)
  7339. =>WM: (13383: I2 ^level-1 R1-root)
  7340. <=WM: (13368: I2 ^level-1 R1-root)
  7341. --- END Input Phase ---
  7342. --- Proposal Phase ---
  7343. --- Inner Elaboration Phase, active level 1 (S1) ---
  7344. Firing rl*prefer*rvt*predict-no*H0*4*H1*16
  7345. -->
  7346. (S1 ^operator O1908 = -0.2383263875547442)
  7347. Firing rl*prefer*rvt*predict-yes*H0*3*H1*17
  7348. -->
  7349. (S1 ^operator O1907 = 0.3930599948023051)
  7350. Firing prefer*rvt*predict-no*H0*4*H1
  7351. -->
  7352. Firing prefer*rvt*predict-yes*H0*3*H1
  7353. -->
  7354. Firing elaborate*copy-see-to-output-link
  7355. -->
  7356. (I3 ^see 0 +)
  7357. Firing elaborate*reward*based*on*reward
  7358. -->
  7359. (R958 ^value 1 +)
  7360. (R1 ^reward R958 +)
  7361. Firing propose*predict-yes
  7362. -->
  7363. (O1909 ^name predict-yes +)
  7364. (S1 ^operator O1909 +)
  7365. Firing propose*predict-no
  7366. -->
  7367. (O1910 ^name predict-no +)
  7368. (S1 ^operator O1910 +)
  7369. Firing rl*prefer*rvt*predict-no*H0*4
  7370. -->
  7371. (S1 ^operator O1908 = 0.4335026303349518)
  7372. Firing rl*prefer*rvt*predict-yes*H0*3
  7373. -->
  7374. (S1 ^operator O1907 = 0.6069190364034727)
  7375. Firing prefer*rvt*predict-yes*H0
  7376. -->
  7377. Firing prefer*rvt*predict-no*H0
  7378. -->
  7379. Firing elaborate*copy-dir-to-output-link
  7380. -->
  7381. (I3 ^dir L +)
  7382. inner elaboration loop at bottom goal.
  7383. Retracting elaborate*copy-see-to-output-link
  7384. -->
  7385. (I3 ^see 1 +)
  7386. Retracting propose*predict-no
  7387. -->
  7388. (O1908 ^name predict-no +)
  7389. (S1 ^operator O1908 +)
  7390. Retracting propose*predict-yes
  7391. -->
  7392. (O1907 ^name predict-yes +)
  7393. (S1 ^operator O1907 +)
  7394. Retracting elaborate*reward*based*on*reward
  7395. -->
  7396. (R957 ^value 1 +)
  7397. (R1 ^reward R957 +)
  7398. Retracting elaborate*copy-dir-to-output-link
  7399. -->
  7400. (I3 ^dir U +)
  7401. Retracting rl*prefer*rvt*predict-no*H0*2
  7402. -->
  7403. (S1 ^operator O1908 = 0.9999999999999999)
  7404. Retracting rl*prefer*rvt*predict-yes*H0*1
  7405. -->
  7406. (S1 ^operator O1907 = 0.)
  7407. =>WM: (13391: S1 ^operator O1910 +)
  7408. =>WM: (13390: S1 ^operator O1909 +)
  7409. =>WM: (13389: I3 ^dir L)
  7410. =>WM: (13388: O1910 ^name predict-no)
  7411. =>WM: (13387: O1909 ^name predict-yes)
  7412. =>WM: (13386: R958 ^value 1)
  7413. =>WM: (13385: R1 ^reward R958)
  7414. =>WM: (13384: I3 ^see 0)
  7415. <=WM: (13375: S1 ^operator O1907 +)
  7416. <=WM: (13376: S1 ^operator O1908 +)
  7417. <=WM: (13377: S1 ^operator O1908)
  7418. <=WM: (13374: I3 ^dir U)
  7419. <=WM: (13370: R1 ^reward R957)
  7420. <=WM: (13369: I3 ^see 1)
  7421. <=WM: (13373: O1908 ^name predict-no)
  7422. <=WM: (13372: O1907 ^name predict-yes)
  7423. <=WM: (13371: R957 ^value 1)
  7424. --- Inner Elaboration Phase, active level 1 (S1) ---
  7425. Firing prefer*rvt*predict-yes*H0
  7426. -->
  7427. Firing rl*prefer*rvt*predict-yes*H0*3*H1*17
  7428. -->
  7429. (S1 ^operator O1909 = 0.3930599948023051)
  7430. Firing rl*prefer*rvt*predict-yes*H0*3
  7431. -->
  7432. (S1 ^operator O1909 = 0.6069190364034727)
  7433. Firing prefer*rvt*predict-yes*H0*3*H1
  7434. -->
  7435. Firing prefer*rvt*predict-no*H0
  7436. -->
  7437. Firing rl*prefer*rvt*predict-no*H0*4*H1*16
  7438. -->
  7439. (S1 ^operator O1910 = -0.2383263875547442)
  7440. Firing rl*prefer*rvt*predict-no*H0*4
  7441. -->
  7442. (S1 ^operator O1910 = 0.4335026303349518)
  7443. Firing prefer*rvt*predict-no*H0*4*H1
  7444. -->
  7445. inner elaboration loop at bottom goal.
  7446. Retracting rl*prefer*rvt*predict-no*H0*4
  7447. -->
  7448. (S1 ^operator O1908 = 0.4335026303349518)
  7449. Retracting rl*prefer*rvt*predict-no*H0*4*H1*16
  7450. -->
  7451. (S1 ^operator O1908 = -0.2383263875547442)
  7452. Retracting rl*prefer*rvt*predict-yes*H0*3
  7453. -->
  7454. (S1 ^operator O1907 = 0.6069190364034727)
  7455. Retracting rl*prefer*rvt*predict-yes*H0*3*H1*17
  7456. -->
  7457. (S1 ^operator O1907 = 0.3930599948023051)
  7458. --- END Proposal Phase ---
  7459. --- Decision Phase ---
  7460. RL update rl*prefer*rvt*predict-no*H0*2 1 0 1 -> 1 0 1(R,m,v=1,1,0)
  7461. =>WM: (13392: S1 ^operator O1909)
  7462. 955: O: O1909 (predict-yes)
  7463. --- END Decision Phase ---
  7464. --- Application Phase ---
  7465. --- Firing Productions (PE) For State At Depth 1 ---
  7466. --- Inner Elaboration Phase, active level 1 (S1) ---
  7467. Firing apply*operator
  7468. -->
  7469. (I3 ^predict-yes N955 + :O )
  7470. Firing apply*operator*complete
  7471. -->
  7472. (I3 ^predict-no N954 - :O )
  7473. inner elaboration loop at bottom goal.
  7474. --- Change Working Memory (PE) ---
  7475. =>WM: (13393: I3 ^predict-yes N955)
  7476. <=WM: (13379: N954 ^status complete)
  7477. <=WM: (13378: I3 ^predict-no N954)
  7478. --- Firing Productions (IE) For State At Depth 1 ---
  7479. --- Inner Elaboration Phase, active level 1 (S1) ---
  7480. Firing monitor*world
  7481. -->
  7482. I see 1 and I'm going to do: predict-yes inner elaboration loop at bottom goal.
  7483. --- Change Working Memory (IE) ---
  7484. --- END Application Phase ---
  7485. --- Output Phase ---
  7486. ENV: Agent did: predict-yes for direction L in state State-B
  7487. In State-B moving L
  7488. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  7489. predict error 0
  7490. dir: dir isU
  7491. --- END Output Phase ---
  7492. \---- Input Phase ---
  7493. =>WM: (13397: I2 ^dir U)
  7494. =>WM: (13396: I2 ^reward 1)
  7495. =>WM: (13395: I2 ^see 1)
  7496. =>WM: (13394: N955 ^status complete)
  7497. <=WM: (13382: I2 ^dir L)
  7498. <=WM: (13381: I2 ^reward 1)
  7499. <=WM: (13380: I2 ^see 0)
  7500. =>WM: (13398: I2 ^level-1 L1-root)
  7501. <=WM: (13383: I2 ^level-1 R1-root)
  7502. --- END Input Phase ---
  7503. --- Proposal Phase ---
  7504. --- Inner Elaboration Phase, active level 1 (S1) ---
  7505. Firing elaborate*copy-see-to-output-link
  7506. -->
  7507. (I3 ^see 1 +)
  7508. Firing elaborate*reward*based*on*reward
  7509. -->
  7510. (R959 ^value 1 +)
  7511. (R1 ^reward R959 +)
  7512. Firing propose*predict-yes
  7513. -->
  7514. (O1911 ^name predict-yes +)
  7515. (S1 ^operator O1911 +)
  7516. Firing propose*predict-no
  7517. -->
  7518. (O1912 ^name predict-no +)
  7519. (S1 ^operator O1912 +)
  7520. Firing rl*prefer*rvt*predict-no*H0*2
  7521. -->
  7522. (S1 ^operator O1910 = 0.9999999999999999)
  7523. Firing rl*prefer*rvt*predict-yes*H0*1
  7524. -->
  7525. (S1 ^operator O1909 = 0.)
  7526. Firing prefer*rvt*predict-yes*H0
  7527. -->
  7528. Firing prefer*rvt*predict-no*H0
  7529. -->
  7530. Firing elaborate*copy-dir-to-output-link
  7531. -->
  7532. (I3 ^dir U +)
  7533. inner elaboration loop at bottom goal.
  7534. Retracting elaborate*copy-see-to-output-link
  7535. -->
  7536. (I3 ^see 0 +)
  7537. Retracting propose*predict-no
  7538. -->
  7539. (O1910 ^name predict-no +)
  7540. (S1 ^operator O1910 +)
  7541. Retracting propose*predict-yes
  7542. -->
  7543. (O1909 ^name predict-yes +)
  7544. (S1 ^operator O1909 +)
  7545. Retracting elaborate*reward*based*on*reward
  7546. -->
  7547. (R958 ^value 1 +)
  7548. (R1 ^reward R958 +)
  7549. Retracting elaborate*copy-dir-to-output-link
  7550. -->
  7551. (I3 ^dir L +)
  7552. Retracting rl*prefer*rvt*predict-no*H0*4
  7553. -->
  7554. (S1 ^operator O1910 = 0.4335026303349518)
  7555. Retracting rl*prefer*rvt*predict-no*H0*4*H1*16
  7556. -->
  7557. (S1 ^operator O1910 = -0.2383263875547442)
  7558. Retracting rl*prefer*rvt*predict-yes*H0*3
  7559. -->
  7560. (S1 ^operator O1909 = 0.6069190364034727)
  7561. Retracting rl*prefer*rvt*predict-yes*H0*3*H1*17
  7562. -->
  7563. (S1 ^operator O1909 = 0.3930599948023051)
  7564. =>WM: (13406: S1 ^operator O1912 +)
  7565. =>WM: (13405: S1 ^operator O1911 +)
  7566. =>WM: (13404: I3 ^dir U)
  7567. =>WM: (13403: O1912 ^name predict-no)
  7568. =>WM: (13402: O1911 ^name predict-yes)
  7569. =>WM: (13401: R959 ^value 1)
  7570. =>WM: (13400: R1 ^reward R959)
  7571. =>WM: (13399: I3 ^see 1)
  7572. <=WM: (13390: S1 ^operator O1909 +)
  7573. <=WM: (13392: S1 ^operator O1909)
  7574. <=WM: (13391: S1 ^operator O1910 +)
  7575. <=WM: (13389: I3 ^dir L)
  7576. <=WM: (13385: R1 ^reward R958)
  7577. <=WM: (13384: I3 ^see 0)
  7578. <=WM: (13388: O1910 ^name predict-no)
  7579. <=WM: (13387: O1909 ^name predict-yes)
  7580. <=WM: (13386: R958 ^value 1)
  7581. --- Inner Elaboration Phase, active level 1 (S1) ---
  7582. Firing prefer*rvt*predict-yes*H0
  7583. -->
  7584. Firing rl*prefer*rvt*predict-yes*H0*1
  7585. -->
  7586. (S1 ^operator O1911 = 0.)
  7587. Firing prefer*rvt*predict-no*H0
  7588. -->
  7589. Firing rl*prefer*rvt*predict-no*H0*2
  7590. -->
  7591. (S1 ^operator O1912 = 0.9999999999999999)
  7592. inner elaboration loop at bottom goal.
  7593. Retracting rl*prefer*rvt*predict-no*H0*2
  7594. -->
  7595. (S1 ^operator O1910 = 0.9999999999999999)
  7596. Retracting rl*prefer*rvt*predict-yes*H0*1
  7597. -->
  7598. (S1 ^operator O1909 = 0.)
  7599. --- END Proposal Phase ---
  7600. --- Decision Phase ---
  7601. RL update rl*prefer*rvt*predict-yes*H0*3 0.65614 -0.0492206 0.606919 -> 0.656143 -0.0492205 0.606922(R,m,v=1,0.944828,0.0524904)
  7602. RL update rl*prefer*rvt*predict-yes*H0*3*H1*17 0.34384 0.0492198 0.39306 -> 0.343843 0.0492199 0.393063(R,m,v=1,1,0)
  7603. =>WM: (13407: S1 ^operator O1912)
  7604. 956: O: O1912 (predict-no)
  7605. --- END Decision Phase ---
  7606. --- Application Phase ---
  7607. --- Firing Productions (PE) For State At Depth 1 ---
  7608. --- Inner Elaboration Phase, active level 1 (S1) ---
  7609. Firing apply*operator
  7610. -->
  7611. (I3 ^predict-no N956 + :O )
  7612. Firing apply*operator*complete
  7613. -->
  7614. (I3 ^predict-yes N955 - :O )
  7615. inner elaboration loop at bottom goal.
  7616. --- Change Working Memory (PE) ---
  7617. =>WM: (13408: I3 ^predict-no N956)
  7618. <=WM: (13394: N955 ^status complete)
  7619. <=WM: (13393: I3 ^predict-yes N955)
  7620. --- Firing Productions (IE) For State At Depth 1 ---
  7621. --- Inner Elaboration Phase, active level 1 (S1) ---
  7622. Firing monitor*world
  7623. -->
  7624. I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
  7625. --- Change Working Memory (IE) ---
  7626. --- END Application Phase ---
  7627. --- Output Phase ---
  7628. ENV: Agent did: predict-no for direction U in state State-A
  7629. In State-A moving U
  7630. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  7631. predict error 0
  7632. dir: dir isL
  7633. --- END Output Phase ---
  7634. /|\--- Input Phase ---
  7635. =>WM: (13412: I2 ^dir L)
  7636. =>WM: (13411: I2 ^reward 1)
  7637. =>WM: (13410: I2 ^see 0)
  7638. =>WM: (13409: N956 ^status complete)
  7639. <=WM: (13397: I2 ^dir U)
  7640. <=WM: (13396: I2 ^reward 1)
  7641. <=WM: (13395: I2 ^see 1)
  7642. =>WM: (13413: I2 ^level-1 L1-root)
  7643. <=WM: (13398: I2 ^level-1 L1-root)
  7644. --- END Input Phase ---
  7645. --- Proposal Phase ---
  7646. --- Inner Elaboration Phase, active level 1 (S1) ---
  7647. Firing rl*prefer*rvt*predict-yes*H0*3*H1*11
  7648. -->
  7649. (S1 ^operator O1911 = -0.03517433757196466)
  7650. Firing rl*prefer*rvt*predict-no*H0*4*H1*10
  7651. -->
  7652. (S1 ^operator O1912 = 0.5665137319453487)
  7653. Firing prefer*rvt*predict-no*H0*4*H1
  7654. -->
  7655. Firing prefer*rvt*predict-yes*H0*3*H1
  7656. -->
  7657. Firing elaborate*copy-see-to-output-link
  7658. -->
  7659. (I3 ^see 0 +)
  7660. Firing elaborate*reward*based*on*reward
  7661. -->
  7662. (R960 ^value 1 +)
  7663. (R1 ^reward R960 +)
  7664. Firing propose*predict-yes
  7665. -->
  7666. (O1913 ^name predict-yes +)
  7667. (S1 ^operator O1913 +)
  7668. Firing propose*predict-no
  7669. -->
  7670. (O1914 ^name predict-no +)
  7671. (S1 ^operator O1914 +)
  7672. Firing rl*prefer*rvt*predict-no*H0*4
  7673. -->
  7674. (S1 ^operator O1912 = 0.4335026303349518)
  7675. Firing rl*prefer*rvt*predict-yes*H0*3
  7676. -->
  7677. (S1 ^operator O1911 = 0.606922181722606)
  7678. Firing prefer*rvt*predict-yes*H0
  7679. -->
  7680. Firing prefer*rvt*predict-no*H0
  7681. -->
  7682. Firing elaborate*copy-dir-to-output-link
  7683. -->
  7684. (I3 ^dir L +)
  7685. inner elaboration loop at bottom goal.
  7686. Retracting elaborate*copy-see-to-output-link
  7687. -->
  7688. (I3 ^see 1 +)
  7689. Retracting propose*predict-no
  7690. -->
  7691. (O1912 ^name predict-no +)
  7692. (S1 ^operator O1912 +)
  7693. Retracting propose*predict-yes
  7694. -->
  7695. (O1911 ^name predict-yes +)
  7696. (S1 ^operator O1911 +)
  7697. Retracting elaborate*reward*based*on*reward
  7698. -->
  7699. (R959 ^value 1 +)
  7700. (R1 ^reward R959 +)
  7701. Retracting elaborate*copy-dir-to-output-link
  7702. -->
  7703. (I3 ^dir U +)
  7704. Retracting rl*prefer*rvt*predict-no*H0*2
  7705. -->
  7706. (S1 ^operator O1912 = 0.9999999999999999)
  7707. Retracting rl*prefer*rvt*predict-yes*H0*1
  7708. -->
  7709. (S1 ^operator O1911 = 0.)
  7710. =>WM: (13421: S1 ^operator O1914 +)
  7711. =>WM: (13420: S1 ^operator O1913 +)
  7712. =>WM: (13419: I3 ^dir L)
  7713. =>WM: (13418: O1914 ^name predict-no)
  7714. =>WM: (13417: O1913 ^name predict-yes)
  7715. =>WM: (13416: R960 ^value 1)
  7716. =>WM: (13415: R1 ^reward R960)
  7717. =>WM: (13414: I3 ^see 0)
  7718. <=WM: (13405: S1 ^operator O1911 +)
  7719. <=WM: (13406: S1 ^operator O1912 +)
  7720. <=WM: (13407: S1 ^operator O1912)
  7721. <=WM: (13404: I3 ^dir U)
  7722. <=WM: (13400: R1 ^reward R959)
  7723. <=WM: (13399: I3 ^see 1)
  7724. <=WM: (13403: O1912 ^name predict-no)
  7725. <=WM: (13402: O1911 ^name predict-yes)
  7726. <=WM: (13401: R959 ^value 1)
  7727. --- Inner Elaboration Phase, active level 1 (S1) ---
  7728. Firing prefer*rvt*predict-yes*H0
  7729. -->
  7730. Firing rl*prefer*rvt*predict-yes*H0*3*H1*11
  7731. -->
  7732. (S1 ^operator O1913 = -0.03517433757196466)
  7733. Firing rl*prefer*rvt*predict-yes*H0*3
  7734. -->
  7735. (S1 ^operator O1913 = 0.606922181722606)
  7736. Firing prefer*rvt*predict-yes*H0*3*H1
  7737. -->
  7738. Firing prefer*rvt*predict-no*H0
  7739. -->
  7740. Firing rl*prefer*rvt*predict-no*H0*4*H1*10
  7741. -->
  7742. (S1 ^operator O1914 = 0.5665137319453487)
  7743. Firing rl*prefer*rvt*predict-no*H0*4
  7744. -->
  7745. (S1 ^operator O1914 = 0.4335026303349518)
  7746. Firing prefer*rvt*predict-no*H0*4*H1
  7747. -->
  7748. inner elaboration loop at bottom goal.
  7749. Retracting rl*prefer*rvt*predict-no*H0*4
  7750. -->
  7751. (S1 ^operator O1912 = 0.4335026303349518)
  7752. Retracting rl*prefer*rvt*predict-no*H0*4*H1*10
  7753. -->
  7754. (S1 ^operator O1912 = 0.5665137319453487)
  7755. Retracting rl*prefer*rvt*predict-yes*H0*3
  7756. -->
  7757. (S1 ^operator O1911 = 0.606922181722606)
  7758. Retracting rl*prefer*rvt*predict-yes*H0*3*H1*11
  7759. -->
  7760. (S1 ^operator O1911 = -0.03517433757196466)
  7761. --- END Proposal Phase ---
  7762. --- Decision Phase ---
  7763. RL update rl*prefer*rvt*predict-no*H0*2 1 0 1 -> 1 0 1(R,m,v=1,1,0)
  7764. =>WM: (13422: S1 ^operator O1914)
  7765. 957: O: O1914 (predict-no)
  7766. --- END Decision Phase ---
  7767. --- Application Phase ---
  7768. --- Firing Productions (PE) For State At Depth 1 ---
  7769. --- Inner Elaboration Phase, active level 1 (S1) ---
  7770. Firing apply*operator
  7771. -->
  7772. (I3 ^predict-no N957 + :O )
  7773. Firing apply*operator*complete
  7774. -->
  7775. (I3 ^predict-no N956 - :O )
  7776. inner elaboration loop at bottom goal.
  7777. --- Change Working Memory (PE) ---
  7778. =>WM: (13423: I3 ^predict-no N957)
  7779. <=WM: (13409: N956 ^status complete)
  7780. <=WM: (13408: I3 ^predict-no N956)
  7781. --- Firing Productions (IE) For State At Depth 1 ---
  7782. --- Inner Elaboration Phase, active level 1 (S1) ---
  7783. Firing monitor*world
  7784. -->
  7785. I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
  7786. --- Change Working Memory (IE) ---
  7787. --- END Application Phase ---
  7788. --- Output Phase ---
  7789. ENV: Agent did: predict-no for direction L in state State-A
  7790. In State-A moving L
  7791. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  7792. predict error 0
  7793. dir: dir isR
  7794. --- END Output Phase ---
  7795. -/--- Input Phase ---
  7796. =>WM: (13427: I2 ^dir R)
  7797. =>WM: (13426: I2 ^reward 1)
  7798. =>WM: (13425: I2 ^see 0)
  7799. =>WM: (13424: N957 ^status complete)
  7800. <=WM: (13412: I2 ^dir L)
  7801. <=WM: (13411: I2 ^reward 1)
  7802. <=WM: (13410: I2 ^see 0)
  7803. =>WM: (13428: I2 ^level-1 L0-root)
  7804. <=WM: (13413: I2 ^level-1 L1-root)
  7805. --- END Input Phase ---
  7806. --- Proposal Phase ---
  7807. --- Inner Elaboration Phase, active level 1 (S1) ---
  7808. Firing rl*prefer*rvt*predict-yes*H0*5*H1*14
  7809. -->
  7810. (S1 ^operator O1913 = 0.9322245227339803)
  7811. Firing rl*prefer*rvt*predict-no*H0*6*H1*19
  7812. -->
  7813. (S1 ^operator O1914 = 0.3)
  7814. Firing prefer*rvt*predict-no*H0*6*H1
  7815. -->
  7816. Firing prefer*rvt*predict-yes*H0*5*H1
  7817. -->
  7818. Firing elaborate*copy-see-to-output-link
  7819. -->
  7820. (I3 ^see 0 +)
  7821. Firing elaborate*reward*based*on*reward
  7822. -->
  7823. (R961 ^value 1 +)
  7824. (R1 ^reward R961 +)
  7825. Firing propose*predict-yes
  7826. -->
  7827. (O1915 ^name predict-yes +)
  7828. (S1 ^operator O1915 +)
  7829. Firing propose*predict-no
  7830. -->
  7831. (O1916 ^name predict-no +)
  7832. (S1 ^operator O1916 +)
  7833. Firing rl*prefer*rvt*predict-no*H0*6
  7834. -->
  7835. (S1 ^operator O1914 = 0.4643594311868555)
  7836. Firing rl*prefer*rvt*predict-yes*H0*5
  7837. -->
  7838. (S1 ^operator O1913 = 0.06777566532256318)
  7839. Firing prefer*rvt*predict-yes*H0
  7840. -->
  7841. Firing prefer*rvt*predict-no*H0
  7842. -->
  7843. Firing elaborate*copy-dir-to-output-link
  7844. -->
  7845. (I3 ^dir R +)
  7846. inner elaboration loop at bottom goal.
  7847. Retracting elaborate*copy-see-to-output-link
  7848. -->
  7849. (I3 ^see 0 +)
  7850. Retracting propose*predict-no
  7851. -->
  7852. (O1914 ^name predict-no +)
  7853. (S1 ^operator O1914 +)
  7854. Retracting propose*predict-yes
  7855. -->
  7856. (O1913 ^name predict-yes +)
  7857. (S1 ^operator O1913 +)
  7858. Retracting elaborate*reward*based*on*reward
  7859. -->
  7860. (R960 ^value 1 +)
  7861. (R1 ^reward R960 +)
  7862. Retracting elaborate*copy-dir-to-output-link
  7863. -->
  7864. (I3 ^dir L +)
  7865. Retracting rl*prefer*rvt*predict-no*H0*4
  7866. -->
  7867. (S1 ^operator O1914 = 0.4335026303349518)
  7868. Retracting rl*prefer*rvt*predict-no*H0*4*H1*10
  7869. -->
  7870. (S1 ^operator O1914 = 0.5665137319453487)
  7871. Retracting rl*prefer*rvt*predict-yes*H0*3
  7872. -->
  7873. (S1 ^operator O1913 = 0.606922181722606)
  7874. Retracting rl*prefer*rvt*predict-yes*H0*3*H1*11
  7875. -->
  7876. (S1 ^operator O1913 = -0.03517433757196466)
  7877. =>WM: (13435: S1 ^operator O1916 +)
  7878. =>WM: (13434: S1 ^operator O1915 +)
  7879. =>WM: (13433: I3 ^dir R)
  7880. =>WM: (13432: O1916 ^name predict-no)
  7881. =>WM: (13431: O1915 ^name predict-yes)
  7882. =>WM: (13430: R961 ^value 1)
  7883. =>WM: (13429: R1 ^reward R961)
  7884. <=WM: (13420: S1 ^operator O1913 +)
  7885. <=WM: (13421: S1 ^operator O1914 +)
  7886. <=WM: (13422: S1 ^operator O1914)
  7887. <=WM: (13419: I3 ^dir L)
  7888. <=WM: (13415: R1 ^reward R960)
  7889. <=WM: (13418: O1914 ^name predict-no)
  7890. <=WM: (13417: O1913 ^name predict-yes)
  7891. <=WM: (13416: R960 ^value 1)
  7892. --- Inner Elaboration Phase, active level 1 (S1) ---
  7893. Firing prefer*rvt*predict-yes*H0
  7894. -->
  7895. Firing rl*prefer*rvt*predict-yes*H0*5
  7896. -->
  7897. (S1 ^operator O1915 = 0.06777566532256318)
  7898. Firing prefer*rvt*predict-yes*H0*5*H1
  7899. -->
  7900. Firing rl*prefer*rvt*predict-yes*H0*5*H1*14
  7901. -->
  7902. (S1 ^operator O1915 = 0.9322245227339803)
  7903. Firing prefer*rvt*predict-no*H0
  7904. -->
  7905. Firing rl*prefer*rvt*predict-no*H0*6
  7906. -->
  7907. (S1 ^operator O1916 = 0.4643594311868555)
  7908. Firing prefer*rvt*predict-no*H0*6*H1
  7909. -->
  7910. Firing rl*prefer*rvt*predict-no*H0*6*H1*19
  7911. -->
  7912. (S1 ^operator O1916 = 0.3)
  7913. inner elaboration loop at bottom goal.
  7914. Retracting rl*prefer*rvt*predict-no*H0*6
  7915. -->
  7916. (S1 ^operator O1914 = 0.4643594311868555)
  7917. Retracting rl*prefer*rvt*predict-no*H0*6*H1*19
  7918. -->
  7919. (S1 ^operator O1914 = 0.3)
  7920. Retracting rl*prefer*rvt*predict-yes*H0*5
  7921. -->
  7922. (S1 ^operator O1913 = 0.06777566532256318)
  7923. Retracting rl*prefer*rvt*predict-yes*H0*5*H1*14
  7924. -->
  7925. (S1 ^operator O1913 = 0.9322245227339803)
  7926. --- END Proposal Phase ---
  7927. --- Decision Phase ---
  7928. RL update rl*prefer*rvt*predict-no*H0*4 0.490219 -0.056716 0.433503 -> 0.490216 -0.056716 0.4335(R,m,v=1,0.883871,0.10331)
  7929. RL update rl*prefer*rvt*predict-no*H0*4*H1*10 0.509798 0.056716 0.566514 -> 0.509795 0.056716 0.566511(R,m,v=1,1,0)
  7930. =>WM: (13436: S1 ^operator O1915)
  7931. 958: O: O1915 (predict-yes)
  7932. --- END Decision Phase ---
  7933. --- Application Phase ---
  7934. --- Firing Productions (PE) For State At Depth 1 ---
  7935. --- Inner Elaboration Phase, active level 1 (S1) ---
  7936. Firing apply*operator
  7937. -->
  7938. (I3 ^predict-yes N958 + :O )
  7939. Firing apply*operator*complete
  7940. -->
  7941. (I3 ^predict-no N957 - :O )
  7942. inner elaboration loop at bottom goal.
  7943. --- Change Working Memory (PE) ---
  7944. =>WM: (13437: I3 ^predict-yes N958)
  7945. <=WM: (13424: N957 ^status complete)
  7946. <=WM: (13423: I3 ^predict-no N957)
  7947. --- Firing Productions (IE) For State At Depth 1 ---
  7948. --- Inner Elaboration Phase, active level 1 (S1) ---
  7949. Firing monitor*world
  7950. -->
  7951. I see 1 and I'm going to do: predict-yes inner elaboration loop at bottom goal.
  7952. --- Change Working Memory (IE) ---
  7953. --- END Application Phase ---
  7954. --- Output Phase ---
  7955. ENV: Agent did: predict-yes for direction R in state State-A
  7956. In State-A moving R
  7957. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  7958. predict error 0
  7959. dir: dir isR
  7960. --- END Output Phase ---
  7961. |\---- Input Phase ---
  7962. =>WM: (13441: I2 ^dir R)
  7963. =>WM: (13440: I2 ^reward 1)
  7964. =>WM: (13439: I2 ^see 1)
  7965. =>WM: (13438: N958 ^status complete)
  7966. <=WM: (13427: I2 ^dir R)
  7967. <=WM: (13426: I2 ^reward 1)
  7968. <=WM: (13425: I2 ^see 0)
  7969. =>WM: (13442: I2 ^level-1 R1-root)
  7970. <=WM: (13428: I2 ^level-1 L0-root)
  7971. --- END Input Phase ---
  7972. --- Proposal Phase ---
  7973. --- Inner Elaboration Phase, active level 1 (S1) ---
  7974. Firing rl*prefer*rvt*predict-no*H0*6*H1*20
  7975. -->
  7976. (S1 ^operator O1916 = 0.5356418274454072)
  7977. Firing rl*prefer*rvt*predict-yes*H0*5*H1*15
  7978. -->
  7979. (S1 ^operator O1915 = 0.2653409704952874)
  7980. Firing prefer*rvt*predict-no*H0*6*H1
  7981. -->
  7982. Firing prefer*rvt*predict-yes*H0*5*H1
  7983. -->
  7984. Firing elaborate*copy-see-to-output-link
  7985. -->
  7986. (I3 ^see 1 +)
  7987. Firing elaborate*reward*based*on*reward
  7988. -->
  7989. (R962 ^value 1 +)
  7990. (R1 ^reward R962 +)
  7991. Firing propose*predict-yes
  7992. -->
  7993. (O1917 ^name predict-yes +)
  7994. (S1 ^operator O1917 +)
  7995. Firing propose*predict-no
  7996. -->
  7997. (O1918 ^name predict-no +)
  7998. (S1 ^operator O1918 +)
  7999. Firing rl*prefer*rvt*predict-no*H0*6
  8000. -->
  8001. (S1 ^operator O1916 = 0.4643594311868555)
  8002. Firing rl*prefer*rvt*predict-yes*H0*5
  8003. -->
  8004. (S1 ^operator O1915 = 0.06777566532256318)
  8005. Firing prefer*rvt*predict-yes*H0
  8006. -->
  8007. Firing prefer*rvt*predict-no*H0
  8008. -->
  8009. Firing elaborate*copy-dir-to-output-link
  8010. -->
  8011. (I3 ^dir R +)
  8012. inner elaboration loop at bottom goal.
  8013. Retracting elaborate*copy-see-to-output-link
  8014. -->
  8015. (I3 ^see 0 +)
  8016. Retracting propose*predict-no
  8017. -->
  8018. (O1916 ^name predict-no +)
  8019. (S1 ^operator O1916 +)
  8020. Retracting propose*predict-yes
  8021. -->
  8022. (O1915 ^name predict-yes +)
  8023. (S1 ^operator O1915 +)
  8024. Retracting elaborate*reward*based*on*reward
  8025. -->
  8026. (R961 ^value 1 +)
  8027. (R1 ^reward R961 +)
  8028. Retracting elaborate*copy-dir-to-output-link
  8029. -->
  8030. (I3 ^dir R +)
  8031. Retracting rl*prefer*rvt*predict-no*H0*6*H1*19
  8032. -->
  8033. (S1 ^operator O1916 = 0.3)
  8034. Retracting rl*prefer*rvt*predict-no*H0*6
  8035. -->
  8036. (S1 ^operator O1916 = 0.4643594311868555)
  8037. Retracting rl*prefer*rvt*predict-yes*H0*5*H1*14
  8038. -->
  8039. (S1 ^operator O1915 = 0.9322245227339803)
  8040. Retracting rl*prefer*rvt*predict-yes*H0*5
  8041. -->
  8042. (S1 ^operator O1915 = 0.06777566532256318)
  8043. =>WM: (13449: S1 ^operator O1918 +)
  8044. =>WM: (13448: S1 ^operator O1917 +)
  8045. =>WM: (13447: O1918 ^name predict-no)
  8046. =>WM: (13446: O1917 ^name predict-yes)
  8047. =>WM: (13445: R962 ^value 1)
  8048. =>WM: (13444: R1 ^reward R962)
  8049. =>WM: (13443: I3 ^see 1)
  8050. <=WM: (13434: S1 ^operator O1915 +)
  8051. <=WM: (13436: S1 ^operator O1915)
  8052. <=WM: (13435: S1 ^operator O1916 +)
  8053. <=WM: (13429: R1 ^reward R961)
  8054. <=WM: (13414: I3 ^see 0)
  8055. <=WM: (13432: O1916 ^name predict-no)
  8056. <=WM: (13431: O1915 ^name predict-yes)
  8057. <=WM: (13430: R961 ^value 1)
  8058. --- Inner Elaboration Phase, active level 1 (S1) ---
  8059. Firing prefer*rvt*predict-yes*H0
  8060. -->
  8061. Firing rl*prefer*rvt*predict-yes*H0*5
  8062. -->
  8063. (S1 ^operator O1917 = 0.06777566532256318)
  8064. Firing prefer*rvt*predict-yes*H0*5*H1
  8065. -->
  8066. Firing rl*prefer*rvt*predict-yes*H0*5*H1*15
  8067. -->
  8068. (S1 ^operator O1917 = 0.2653409704952874)
  8069. Firing prefer*rvt*predict-no*H0
  8070. -->
  8071. Firing rl*prefer*rvt*predict-no*H0*6
  8072. -->
  8073. (S1 ^operator O1918 = 0.4643594311868555)
  8074. Firing prefer*rvt*predict-no*H0*6*H1
  8075. -->
  8076. Firing rl*prefer*rvt*predict-no*H0*6*H1*20
  8077. -->
  8078. (S1 ^operator O1918 = 0.5356418274454072)
  8079. inner elaboration loop at bottom goal.
  8080. Retracting rl*prefer*rvt*predict-no*H0*6
  8081. -->
  8082. (S1 ^operator O1916 = 0.4643594311868555)
  8083. Retracting rl*prefer*rvt*predict-no*H0*6*H1*20
  8084. -->
  8085. (S1 ^operator O1916 = 0.5356418274454072)
  8086. Retracting rl*prefer*rvt*predict-yes*H0*5
  8087. -->
  8088. (S1 ^operator O1915 = 0.06777566532256318)
  8089. Retracting rl*prefer*rvt*predict-yes*H0*5*H1*15
  8090. -->
  8091. (S1 ^operator O1915 = 0.2653409704952874)
  8092. --- END Proposal Phase ---
  8093. --- Decision Phase ---
  8094. RL update rl*prefer*rvt*predict-yes*H0*5 0.606208 -0.538432 0.0677757 -> 0.606208 -0.538432 0.0677756(R,m,v=1,0.867816,0.115374)
  8095. RL update rl*prefer*rvt*predict-yes*H0*5*H1*14 0.393793 0.538432 0.932225 -> 0.393793 0.538432 0.932224(R,m,v=1,1,0)
  8096. =>WM: (13450: S1 ^operator O1918)
  8097. 959: O: O1918 (predict-no)
  8098. --- END Decision Phase ---
  8099. --- Application Phase ---
  8100. --- Firing Productions (PE) For State At Depth 1 ---
  8101. --- Inner Elaboration Phase, active level 1 (S1) ---
  8102. Firing apply*operator
  8103. -->
  8104. (I3 ^predict-no N959 + :O )
  8105. Firing apply*operator*complete
  8106. -->
  8107. (I3 ^predict-yes N958 - :O )
  8108. inner elaboration loop at bottom goal.
  8109. --- Change Working Memory (PE) ---
  8110. =>WM: (13451: I3 ^predict-no N959)
  8111. <=WM: (13438: N958 ^status complete)
  8112. <=WM: (13437: I3 ^predict-yes N958)
  8113. --- Firing Productions (IE) For State At Depth 1 ---
  8114. --- Inner Elaboration Phase, active level 1 (S1) ---
  8115. Firing monitor*world
  8116. -->
  8117. I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
  8118. --- Change Working Memory (IE) ---
  8119. --- END Application Phase ---
  8120. --- Output Phase ---
  8121. ENV: Agent did: predict-no for direction R in state State-B
  8122. In State-B moving R
  8123. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  8124. predict error 0
  8125. dir: dir isL
  8126. --- END Output Phase ---
  8127. /|\--- Input Phase ---
  8128. =>WM: (13455: I2 ^dir L)
  8129. =>WM: (13454: I2 ^reward 1)
  8130. =>WM: (13453: I2 ^see 0)
  8131. =>WM: (13452: N959 ^status complete)
  8132. <=WM: (13441: I2 ^dir R)
  8133. <=WM: (13440: I2 ^reward 1)
  8134. <=WM: (13439: I2 ^see 1)
  8135. =>WM: (13456: I2 ^level-1 R0-root)
  8136. <=WM: (13442: I2 ^level-1 R1-root)
  8137. --- END Input Phase ---
  8138. --- Proposal Phase ---
  8139. --- Inner Elaboration Phase, active level 1 (S1) ---
  8140. Firing rl*prefer*rvt*predict-no*H0*4*H1*8
  8141. -->
  8142. (S1 ^operator O1918 = -0.2450868666562052)
  8143. Firing rl*prefer*rvt*predict-yes*H0*3*H1*9
  8144. -->
  8145. (S1 ^operator O1917 = 0.3930933791731328)
  8146. Firing prefer*rvt*predict-no*H0*4*H1
  8147. -->
  8148. Firing prefer*rvt*predict-yes*H0*3*H1
  8149. -->
  8150. Firing elaborate*copy-see-to-output-link
  8151. -->
  8152. (I3 ^see 0 +)
  8153. Firing elaborate*reward*based*on*reward
  8154. -->
  8155. (R963 ^value 1 +)
  8156. (R1 ^reward R963 +)
  8157. Firing propose*predict-yes
  8158. -->
  8159. (O1919 ^name predict-yes +)
  8160. (S1 ^operator O1919 +)
  8161. Firing propose*predict-no
  8162. -->
  8163. (O1920 ^name predict-no +)
  8164. (S1 ^operator O1920 +)
  8165. Firing rl*prefer*rvt*predict-no*H0*4
  8166. -->
  8167. (S1 ^operator O1918 = 0.4335001759929067)
  8168. Firing rl*prefer*rvt*predict-yes*H0*3
  8169. -->
  8170. (S1 ^operator O1917 = 0.606922181722606)
  8171. Firing prefer*rvt*predict-yes*H0
  8172. -->
  8173. Firing prefer*rvt*predict-no*H0
  8174. -->
  8175. Firing elaborate*copy-dir-to-output-link
  8176. -->
  8177. (I3 ^dir L +)
  8178. inner elaboration loop at bottom goal.
  8179. Retracting elaborate*copy-see-to-output-link
  8180. -->
  8181. (I3 ^see 1 +)
  8182. Retracting propose*predict-no
  8183. -->
  8184. (O1918 ^name predict-no +)
  8185. (S1 ^operator O1918 +)
  8186. Retracting propose*predict-yes
  8187. -->
  8188. (O1917 ^name predict-yes +)
  8189. (S1 ^operator O1917 +)
  8190. Retracting elaborate*reward*based*on*reward
  8191. -->
  8192. (R962 ^value 1 +)
  8193. (R1 ^reward R962 +)
  8194. Retracting elaborate*copy-dir-to-output-link
  8195. -->
  8196. (I3 ^dir R +)
  8197. Retracting rl*prefer*rvt*predict-no*H0*6*H1*20
  8198. -->
  8199. (S1 ^operator O1918 = 0.5356418274454072)
  8200. Retracting rl*prefer*rvt*predict-no*H0*6
  8201. -->
  8202. (S1 ^operator O1918 = 0.4643594311868555)
  8203. Retracting rl*prefer*rvt*predict-yes*H0*5*H1*15
  8204. -->
  8205. (S1 ^operator O1917 = 0.2653409704952874)
  8206. Retracting rl*prefer*rvt*predict-yes*H0*5
  8207. -->
  8208. (S1 ^operator O1917 = 0.06777563711408163)
  8209. =>WM: (13464: S1 ^operator O1920 +)
  8210. =>WM: (13463: S1 ^operator O1919 +)
  8211. =>WM: (13462: I3 ^dir L)
  8212. =>WM: (13461: O1920 ^name predict-no)
  8213. =>WM: (13460: O1919 ^name predict-yes)
  8214. =>WM: (13459: R963 ^value 1)
  8215. =>WM: (13458: R1 ^reward R963)
  8216. =>WM: (13457: I3 ^see 0)
  8217. <=WM: (13448: S1 ^operator O1917 +)
  8218. <=WM: (13449: S1 ^operator O1918 +)
  8219. <=WM: (13450: S1 ^operator O1918)
  8220. <=WM: (13433: I3 ^dir R)
  8221. <=WM: (13444: R1 ^reward R962)
  8222. <=WM: (13443: I3 ^see 1)
  8223. <=WM: (13447: O1918 ^name predict-no)
  8224. <=WM: (13446: O1917 ^name predict-yes)
  8225. <=WM: (13445: R962 ^value 1)
  8226. --- Inner Elaboration Phase, active level 1 (S1) ---
  8227. Firing prefer*rvt*predict-yes*H0
  8228. -->
  8229. Firing rl*prefer*rvt*predict-yes*H0*3
  8230. -->
  8231. (S1 ^operator O1919 = 0.606922181722606)
  8232. Firing prefer*rvt*predict-yes*H0*3*H1
  8233. -->
  8234. Firing rl*prefer*rvt*predict-yes*H0*3*H1*9
  8235. -->
  8236. (S1 ^operator O1919 = 0.3930933791731328)
  8237. Firing prefer*rvt*predict-no*H0
  8238. -->
  8239. Firing rl*prefer*rvt*predict-no*H0*4
  8240. -->
  8241. (S1 ^operator O1920 = 0.4335001759929067)
  8242. Firing prefer*rvt*predict-no*H0*4*H1
  8243. -->
  8244. Firing rl*prefer*rvt*predict-no*H0*4*H1*8
  8245. -->
  8246. (S1 ^operator O1920 = -0.2450868666562052)
  8247. inner elaboration loop at bottom goal.
  8248. Retracting rl*prefer*rvt*predict-no*H0*4
  8249. -->
  8250. (S1 ^operator O1918 = 0.4335001759929067)
  8251. Retracting rl*prefer*rvt*predict-no*H0*4*H1*8
  8252. -->
  8253. (S1 ^operator O1918 = -0.2450868666562052)
  8254. Retracting rl*prefer*rvt*predict-yes*H0*3
  8255. -->
  8256. (S1 ^operator O1917 = 0.606922181722606)
  8257. Retracting rl*prefer*rvt*predict-yes*H0*3*H1*9
  8258. -->
  8259. (S1 ^operator O1917 = 0.3930933791731328)
  8260. --- END Proposal Phase ---
  8261. --- Decision Phase ---
  8262. RL update rl*prefer*rvt*predict-no*H0*6 0.679081 -0.214722 0.464359 -> 0.679081 -0.214722 0.464359(R,m,v=1,0.970414,0.0288814)
  8263. RL update rl*prefer*rvt*predict-no*H0*6*H1*20 0.32092 0.214722 0.535642 -> 0.32092 0.214722 0.535642(R,m,v=1,1,0)
  8264. =>WM: (13465: S1 ^operator O1919)
  8265. 960: O: O1919 (predict-yes)
  8266. --- END Decision Phase ---
  8267. --- Application Phase ---
  8268. --- Firing Productions (PE) For State At Depth 1 ---
  8269. --- Inner Elaboration Phase, active level 1 (S1) ---
  8270. Firing apply*operator
  8271. -->
  8272. (I3 ^predict-yes N960 + :O )
  8273. Firing apply*operator*complete
  8274. -->
  8275. (I3 ^predict-no N959 - :O )
  8276. inner elaboration loop at bottom goal.
  8277. --- Change Working Memory (PE) ---
  8278. =>WM: (13466: I3 ^predict-yes N960)
  8279. <=WM: (13452: N959 ^status complete)
  8280. <=WM: (13451: I3 ^predict-no N959)
  8281. --- Firing Productions (IE) For State At Depth 1 ---
  8282. --- Inner Elaboration Phase, active level 1 (S1) ---
  8283. Firing monitor*world
  8284. -->
  8285. I see 1 and I'm going to do: predict-yes inner elaboration loop at bottom goal.
  8286. --- Change Working Memory (IE) ---
  8287. --- END Application Phase ---
  8288. --- Output Phase ---
  8289. ENV: Agent did: predict-yes for direction L in state State-B
  8290. In State-B moving L
  8291. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  8292. predict error 0
  8293. dir: dir isU
  8294. --- END Output Phase ---
  8295. ---- Input Phase ---
  8296. =>WM: (13470: I2 ^dir U)
  8297. =>WM: (13469: I2 ^reward 1)
  8298. =>WM: (13468: I2 ^see 1)
  8299. =>WM: (13467: N960 ^status complete)
  8300. <=WM: (13455: I2 ^dir L)
  8301. <=WM: (13454: I2 ^reward 1)
  8302. <=WM: (13453: I2 ^see 0)
  8303. =>WM: (13471: I2 ^level-1 L1-root)
  8304. <=WM: (13456: I2 ^level-1 R0-root)
  8305. --- END Input Phase ---
  8306. --- Proposal Phase ---
  8307. --- Inner Elaboration Phase, active level 1 (S1) ---
  8308. Firing elaborate*copy-see-to-output-link
  8309. -->
  8310. (I3 ^see 1 +)
  8311. Firing elaborate*reward*based*on*reward
  8312. -->
  8313. (R964 ^value 1 +)
  8314. (R1 ^reward R964 +)
  8315. Firing propose*predict-yes
  8316. -->
  8317. (O1921 ^name predict-yes +)
  8318. (S1 ^operator O1921 +)
  8319. Firing propose*predict-no
  8320. -->
  8321. (O1922 ^name predict-no +)
  8322. (S1 ^operator O1922 +)
  8323. Firing rl*prefer*rvt*predict-no*H0*2
  8324. -->
  8325. (S1 ^operator O1920 = 0.9999999999999999)
  8326. Firing rl*prefer*rvt*predict-yes*H0*1
  8327. -->
  8328. (S1 ^operator O1919 = 0.)
  8329. Firing prefer*rvt*predict-yes*H0
  8330. -->
  8331. Firing prefer*rvt*predict-no*H0
  8332. -->
  8333. Firing elaborate*copy-dir-to-output-link
  8334. -->
  8335. (I3 ^dir U +)
  8336. inner elaboration loop at bottom goal.
  8337. Retracting elaborate*copy-see-to-output-link
  8338. -->
  8339. (I3 ^see 0 +)
  8340. Retracting propose*predict-no
  8341. -->
  8342. (O1920 ^name predict-no +)
  8343. (S1 ^operator O1920 +)
  8344. Retracting propose*predict-yes
  8345. -->
  8346. (O1919 ^name predict-yes +)
  8347. (S1 ^operator O1919 +)
  8348. Retracting elaborate*reward*based*on*reward
  8349. -->
  8350. (R963 ^value 1 +)
  8351. (R1 ^reward R963 +)
  8352. Retracting elaborate*copy-dir-to-output-link
  8353. -->
  8354. (I3 ^dir L +)
  8355. Retracting rl*prefer*rvt*predict-no*H0*4*H1*8
  8356. -->
  8357. (S1 ^operator O1920 = -0.2450868666562052)
  8358. Retracting rl*prefer*rvt*predict-no*H0*4
  8359. -->
  8360. (S1 ^operator O1920 = 0.4335001759929067)
  8361. Retracting rl*prefer*rvt*predict-yes*H0*3*H1*9
  8362. -->
  8363. (S1 ^operator O1919 = 0.3930933791731328)
  8364. Retracting rl*prefer*rvt*predict-yes*H0*3
  8365. -->
  8366. (S1 ^operator O1919 = 0.606922181722606)
  8367. =>WM: (13479: S1 ^operator O1922 +)
  8368. =>WM: (13478: S1 ^operator O1921 +)
  8369. =>WM: (13477: I3 ^dir U)
  8370. =>WM: (13476: O1922 ^name predict-no)
  8371. =>WM: (13475: O1921 ^name predict-yes)
  8372. =>WM: (13474: R964 ^value 1)
  8373. =>WM: (13473: R1 ^reward R964)
  8374. =>WM: (13472: I3 ^see 1)
  8375. <=WM: (13463: S1 ^operator O1919 +)
  8376. <=WM: (13465: S1 ^operator O1919)
  8377. <=WM: (13464: S1 ^operator O1920 +)
  8378. <=WM: (13462: I3 ^dir L)
  8379. <=WM: (13458: R1 ^reward R963)
  8380. <=WM: (13457: I3 ^see 0)
  8381. <=WM: (13461: O1920 ^name predict-no)
  8382. <=WM: (13460: O1919 ^name predict-yes)
  8383. <=WM: (13459: R963 ^value 1)
  8384. --- Inner Elaboration Phase, active level 1 (S1) ---
  8385. Firing prefer*rvt*predict-yes*H0
  8386. -->
  8387. Firing rl*prefer*rvt*predict-yes*H0*1
  8388. -->
  8389. (S1 ^operator O1921 = 0.)
  8390. Firing prefer*rvt*predict-no*H0
  8391. -->
  8392. Firing rl*prefer*rvt*predict-no*H0*2
  8393. -->
  8394. (S1 ^operator O1922 = 0.9999999999999999)
  8395. inner elaboration loop at bottom goal.
  8396. Retracting rl*prefer*rvt*predict-no*H0*2
  8397. -->
  8398. (S1 ^operator O1920 = 0.9999999999999999)
  8399. Retracting rl*prefer*rvt*predict-yes*H0*1
  8400. -->
  8401. (S1 ^operator O1919 = 0.)
  8402. --- END Proposal Phase ---
  8403. --- Decision Phase ---
  8404. RL update rl*prefer*rvt*predict-yes*H0*3 0.656143 -0.0492205 0.606922 -> 0.65614 -0.0492205 0.60692(R,m,v=1,0.945205,0.0521493)
  8405. RL update rl*prefer*rvt*predict-yes*H0*3*H1*9 0.343872 0.049221 0.393093 -> 0.34387 0.0492209 0.393091(R,m,v=1,1,0)
  8406. =>WM: (13480: S1 ^operator O1922)
  8407. 961: O: O1922 (predict-no)
  8408. --- END Decision Phase ---
  8409. --- Application Phase ---
  8410. --- Firing Productions (PE) For State At Depth 1 ---
  8411. --- Inner Elaboration Phase, active level 1 (S1) ---
  8412. Firing apply*operator
  8413. -->
  8414. (I3 ^predict-no N961 + :O )
  8415. Firing apply*operator*complete
  8416. -->
  8417. (I3 ^predict-yes N960 - :O )
  8418. inner elaboration loop at bottom goal.
  8419. --- Change Working Memory (PE) ---
  8420. =>WM: (13481: I3 ^predict-no N961)
  8421. <=WM: (13467: N960 ^status complete)
  8422. <=WM: (13466: I3 ^predict-yes N960)
  8423. --- Firing Productions (IE) For State At Depth 1 ---
  8424. --- Inner Elaboration Phase, active level 1 (S1) ---
  8425. Firing monitor*world
  8426. -->
  8427. I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
  8428. --- Change Working Memory (IE) ---
  8429. --- END Application Phase ---
  8430. --- Output Phase ---
  8431. ENV: Agent did: predict-no for direction U in state State-A
  8432. In State-A moving U
  8433. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  8434. predict error 0
  8435. dir: dir isL
  8436. --- END Output Phase ---
  8437. /--- Input Phase ---
  8438. =>WM: (13485: I2 ^dir L)
  8439. =>WM: (13484: I2 ^reward 1)
  8440. =>WM: (13483: I2 ^see 0)
  8441. =>WM: (13482: N961 ^status complete)
  8442. <=WM: (13470: I2 ^dir U)
  8443. <=WM: (13469: I2 ^reward 1)
  8444. <=WM: (13468: I2 ^see 1)
  8445. =>WM: (13486: I2 ^level-1 L1-root)
  8446. <=WM: (13471: I2 ^level-1 L1-root)
  8447. --- END Input Phase ---
  8448. --- Proposal Phase ---
  8449. --- Inner Elaboration Phase, active level 1 (S1) ---
  8450. Firing rl*prefer*rvt*predict-yes*H0*3*H1*11
  8451. -->
  8452. (S1 ^operator O1921 = -0.03517433757196466)
  8453. Firing rl*prefer*rvt*predict-no*H0*4*H1*10
  8454. -->
  8455. (S1 ^operator O1922 = 0.5665112776033036)
  8456. Firing prefer*rvt*predict-no*H0*4*H1
  8457. -->
  8458. Firing prefer*rvt*predict-yes*H0*3*H1
  8459. -->
  8460. Firing elaborate*copy-see-to-output-link
  8461. -->
  8462. (I3 ^see 0 +)
  8463. Firing elaborate*reward*based*on*reward
  8464. -->
  8465. (R965 ^value 1 +)
  8466. (R1 ^reward R965 +)
  8467. Firing propose*predict-yes
  8468. -->
  8469. (O1923 ^name predict-yes +)
  8470. (S1 ^operator O1923 +)
  8471. Firing propose*predict-no
  8472. -->
  8473. (O1924 ^name predict-no +)
  8474. (S1 ^operator O1924 +)
  8475. Firing rl*prefer*rvt*predict-no*H0*4
  8476. -->
  8477. (S1 ^operator O1922 = 0.4335001759929067)
  8478. Firing rl*prefer*rvt*predict-yes*H0*3
  8479. -->
  8480. (S1 ^operator O1921 = 0.6069198475882451)
  8481. Firing prefer*rvt*predict-yes*H0
  8482. -->
  8483. Firing prefer*rvt*predict-no*H0
  8484. -->
  8485. Firing elaborate*copy-dir-to-output-link
  8486. -->
  8487. (I3 ^dir L +)
  8488. inner elaboration loop at bottom goal.
  8489. Retracting elaborate*copy-see-to-output-link
  8490. -->
  8491. (I3 ^see 1 +)
  8492. Retracting propose*predict-no
  8493. -->
  8494. (O1922 ^name predict-no +)
  8495. (S1 ^operator O1922 +)
  8496. Retracting propose*predict-yes
  8497. -->
  8498. (O1921 ^name predict-yes +)
  8499. (S1 ^operator O1921 +)
  8500. Retracting elaborate*reward*based*on*reward
  8501. -->
  8502. (R964 ^value 1 +)
  8503. (R1 ^reward R964 +)
  8504. Retracting elaborate*copy-dir-to-output-link
  8505. -->
  8506. (I3 ^dir U +)
  8507. Retracting rl*prefer*rvt*predict-no*H0*2
  8508. -->
  8509. (S1 ^operator O1922 = 0.9999999999999999)
  8510. Retracting rl*prefer*rvt*predict-yes*H0*1
  8511. -->
  8512. (S1 ^operator O1921 = 0.)
  8513. =>WM: (13494: S1 ^operator O1924 +)
  8514. =>WM: (13493: S1 ^operator O1923 +)
  8515. =>WM: (13492: I3 ^dir L)
  8516. =>WM: (13491: O1924 ^name predict-no)
  8517. =>WM: (13490: O1923 ^name predict-yes)
  8518. =>WM: (13489: R965 ^value 1)
  8519. =>WM: (13488: R1 ^reward R965)
  8520. =>WM: (13487: I3 ^see 0)
  8521. <=WM: (13478: S1 ^operator O1921 +)
  8522. <=WM: (13479: S1 ^operator O1922 +)
  8523. <=WM: (13480: S1 ^operator O1922)
  8524. <=WM: (13477: I3 ^dir U)
  8525. <=WM: (13473: R1 ^reward R964)
  8526. <=WM: (13472: I3 ^see 1)
  8527. <=WM: (13476: O1922 ^name predict-no)
  8528. <=WM: (13475: O1921 ^name predict-yes)
  8529. <=WM: (13474: R964 ^value 1)
  8530. --- Inner Elaboration Phase, active level 1 (S1) ---
  8531. Firing prefer*rvt*predict-yes*H0
  8532. -->
  8533. Firing rl*prefer*rvt*predict-yes*H0*3*H1*11
  8534. -->
  8535. (S1 ^operator O1923 = -0.03517433757196466)
  8536. Firing rl*prefer*rvt*predict-yes*H0*3
  8537. -->
  8538. (S1 ^operator O1923 = 0.6069198475882451)
  8539. Firing prefer*rvt*predict-yes*H0*3*H1
  8540. -->
  8541. Firing prefer*rvt*predict-no*H0
  8542. -->
  8543. Firing rl*prefer*rvt*predict-no*H0*4*H1*10
  8544. -->
  8545. (S1 ^operator O1924 = 0.5665112776033036)
  8546. Firing rl*prefer*rvt*predict-no*H0*4
  8547. -->
  8548. (S1 ^operator O1924 = 0.4335001759929067)
  8549. Firing prefer*rvt*predict-no*H0*4*H1
  8550. -->
  8551. inner elaboration loop at bottom goal.
  8552. Retracting rl*prefer*rvt*predict-no*H0*4
  8553. -->
  8554. (S1 ^operator O1922 = 0.4335001759929067)
  8555. Retracting rl*prefer*rvt*predict-no*H0*4*H1*10
  8556. -->
  8557. (S1 ^operator O1922 = 0.5665112776033036)
  8558. Retracting rl*prefer*rvt*predict-yes*H0*3
  8559. -->
  8560. (S1 ^operator O1921 = 0.6069198475882451)
  8561. Retracting rl*prefer*rvt*predict-yes*H0*3*H1*11
  8562. -->
  8563. (S1 ^operator O1921 = -0.03517433757196466)
  8564. --- END Proposal Phase ---
  8565. --- Decision Phase ---
  8566. RL update rl*prefer*rvt*predict-no*H0*2 1 0 1 -> 1 0 1(R,m,v=1,1,0)
  8567. =>WM: (13495: S1 ^operator O1924)
  8568. 962: O: O1924 (predict-no)
  8569. --- END Decision Phase ---
  8570. --- Application Phase ---
  8571. --- Firing Productions (PE) For State At Depth 1 ---
  8572. --- Inner Elaboration Phase, active level 1 (S1) ---
  8573. Firing apply*operator
  8574. -->
  8575. (I3 ^predict-no N962 + :O )
  8576. Firing apply*operator*complete
  8577. -->
  8578. (I3 ^predict-no N961 - :O )
  8579. inner elaboration loop at bottom goal.
  8580. --- Change Working Memory (PE) ---
  8581. =>WM: (13496: I3 ^predict-no N962)
  8582. <=WM: (13482: N961 ^status complete)
  8583. <=WM: (13481: I3 ^predict-no N961)
  8584. --- Firing Productions (IE) For State At Depth 1 ---
  8585. --- Inner Elaboration Phase, active level 1 (S1) ---
  8586. Firing monitor*world
  8587. -->
  8588. I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
  8589. --- Change Working Memory (IE) ---
  8590. --- END Application Phase ---
  8591. --- Output Phase ---
  8592. ENV: Agent did: predict-no for direction L in state State-A
  8593. In State-A moving L
  8594. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  8595. predict error 0
  8596. dir: dir isU
  8597. --- END Output Phase ---
  8598. |\---- Input Phase ---
  8599. =>WM: (13500: I2 ^dir U)
  8600. =>WM: (13499: I2 ^reward 1)
  8601. =>WM: (13498: I2 ^see 0)
  8602. =>WM: (13497: N962 ^status complete)
  8603. <=WM: (13485: I2 ^dir L)
  8604. <=WM: (13484: I2 ^reward 1)
  8605. <=WM: (13483: I2 ^see 0)
  8606. =>WM: (13501: I2 ^level-1 L0-root)
  8607. <=WM: (13486: I2 ^level-1 L1-root)
  8608. --- END Input Phase ---
  8609. --- Proposal Phase ---
  8610. --- Inner Elaboration Phase, active level 1 (S1) ---
  8611. Firing elaborate*copy-see-to-output-link
  8612. -->
  8613. (I3 ^see 0 +)
  8614. Firing elaborate*reward*based*on*reward
  8615. -->
  8616. (R966 ^value 1 +)
  8617. (R1 ^reward R966 +)
  8618. Firing propose*predict-yes
  8619. -->
  8620. (O1925 ^name predict-yes +)
  8621. (S1 ^operator O1925 +)
  8622. Firing propose*predict-no
  8623. -->
  8624. (O1926 ^name predict-no +)
  8625. (S1 ^operator O1926 +)
  8626. Firing rl*prefer*rvt*predict-no*H0*2
  8627. -->
  8628. (S1 ^operator O1924 = 0.9999999999999999)
  8629. Firing rl*prefer*rvt*predict-yes*H0*1
  8630. -->
  8631. (S1 ^operator O1923 = 0.)
  8632. Firing prefer*rvt*predict-yes*H0
  8633. -->
  8634. Firing prefer*rvt*predict-no*H0
  8635. -->
  8636. Firing elaborate*copy-dir-to-output-link
  8637. -->
  8638. (I3 ^dir U +)
  8639. inner elaboration loop at bottom goal.
  8640. Retracting elaborate*copy-see-to-output-link
  8641. -->
  8642. (I3 ^see 0 +)
  8643. Retracting propose*predict-no
  8644. -->
  8645. (O1924 ^name predict-no +)
  8646. (S1 ^operator O1924 +)
  8647. Retracting propose*predict-yes
  8648. -->
  8649. (O1923 ^name predict-yes +)
  8650. (S1 ^operator O1923 +)
  8651. Retracting elaborate*reward*based*on*reward
  8652. -->
  8653. (R965 ^value 1 +)
  8654. (R1 ^reward R965 +)
  8655. Retracting elaborate*copy-dir-to-output-link
  8656. -->
  8657. (I3 ^dir L +)
  8658. Retracting rl*prefer*rvt*predict-no*H0*4
  8659. -->
  8660. (S1 ^operator O1924 = 0.4335001759929067)
  8661. Retracting rl*prefer*rvt*predict-no*H0*4*H1*10
  8662. -->
  8663. (S1 ^operator O1924 = 0.5665112776033036)
  8664. Retracting rl*prefer*rvt*predict-yes*H0*3
  8665. -->
  8666. (S1 ^operator O1923 = 0.6069198475882451)
  8667. Retracting rl*prefer*rvt*predict-yes*H0*3*H1*11
  8668. -->
  8669. (S1 ^operator O1923 = -0.03517433757196466)
  8670. =>WM: (13508: S1 ^operator O1926 +)
  8671. =>WM: (13507: S1 ^operator O1925 +)
  8672. =>WM: (13506: I3 ^dir U)
  8673. =>WM: (13505: O1926 ^name predict-no)
  8674. =>WM: (13504: O1925 ^name predict-yes)
  8675. =>WM: (13503: R966 ^value 1)
  8676. =>WM: (13502: R1 ^reward R966)
  8677. <=WM: (13493: S1 ^operator O1923 +)
  8678. <=WM: (13494: S1 ^operator O1924 +)
  8679. <=WM: (13495: S1 ^operator O1924)
  8680. <=WM: (13492: I3 ^dir L)
  8681. <=WM: (13488: R1 ^reward R965)
  8682. <=WM: (13491: O1924 ^name predict-no)
  8683. <=WM: (13490: O1923 ^name predict-yes)
  8684. <=WM: (13489: R965 ^value 1)
  8685. --- Inner Elaboration Phase, active level 1 (S1) ---
  8686. Firing prefer*rvt*predict-yes*H0
  8687. -->
  8688. Firing rl*prefer*rvt*predict-yes*H0*1
  8689. -->
  8690. (S1 ^operator O1925 = 0.)
  8691. Firing prefer*rvt*predict-no*H0
  8692. -->
  8693. Firing rl*prefer*rvt*predict-no*H0*2
  8694. -->
  8695. (S1 ^operator O1926 = 0.9999999999999999)
  8696. inner elaboration loop at bottom goal.
  8697. Retracting rl*prefer*rvt*predict-no*H0*2
  8698. -->
  8699. (S1 ^operator O1924 = 0.9999999999999999)
  8700. Retracting rl*prefer*rvt*predict-yes*H0*1
  8701. -->
  8702. (S1 ^operator O1923 = 0.)
  8703. --- END Proposal Phase ---
  8704. --- Decision Phase ---
  8705. RL update rl*prefer*rvt*predict-no*H0*4 0.490216 -0.056716 0.4335 -> 0.490214 -0.056716 0.433498(R,m,v=1,0.884615,0.10273)
  8706. RL update rl*prefer*rvt*predict-no*H0*4*H1*10 0.509795 0.056716 0.566511 -> 0.509794 0.056716 0.56651(R,m,v=1,1,0)
  8707. =>WM: (13509: S1 ^operator O1926)
  8708. 963: O: O1926 (predict-no)
  8709. --- END Decision Phase ---
  8710. --- Application Phase ---
  8711. --- Firing Productions (PE) For State At Depth 1 ---
  8712. --- Inner Elaboration Phase, active level 1 (S1) ---
  8713. Firing apply*operator
  8714. -->
  8715. (I3 ^predict-no N963 + :O )
  8716. Firing apply*operator*complete
  8717. -->
  8718. (I3 ^predict-no N962 - :O )
  8719. inner elaboration loop at bottom goal.
  8720. --- Change Working Memory (PE) ---
  8721. =>WM: (13510: I3 ^predict-no N963)
  8722. <=WM: (13497: N962 ^status complete)
  8723. <=WM: (13496: I3 ^predict-no N962)
  8724. --- Firing Productions (IE) For State At Depth 1 ---
  8725. --- Inner Elaboration Phase, active level 1 (S1) ---
  8726. Firing monitor*world
  8727. -->
  8728. I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
  8729. --- Change Working Memory (IE) ---
  8730. --- END Application Phase ---
  8731. --- Output Phase ---
  8732. ENV: Agent did: predict-no for direction U in state State-A
  8733. In State-A moving U
  8734. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  8735. predict error 0
  8736. dir: dir isU
  8737. --- END Output Phase ---
  8738. /|\--- Input Phase ---
  8739. =>WM: (13514: I2 ^dir U)
  8740. =>WM: (13513: I2 ^reward 1)
  8741. =>WM: (13512: I2 ^see 0)
  8742. =>WM: (13511: N963 ^status complete)
  8743. <=WM: (13500: I2 ^dir U)
  8744. <=WM: (13499: I2 ^reward 1)
  8745. <=WM: (13498: I2 ^see 0)
  8746. =>WM: (13515: I2 ^level-1 L0-root)
  8747. <=WM: (13501: I2 ^level-1 L0-root)
  8748. --- END Input Phase ---
  8749. --- Proposal Phase ---
  8750. --- Inner Elaboration Phase, active level 1 (S1) ---
  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*2
  8767. -->
  8768. (S1 ^operator O1926 = 0.9999999999999999)
  8769. Firing rl*prefer*rvt*predict-yes*H0*1
  8770. -->
  8771. (S1 ^operator O1925 = 0.)
  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 U +)
  8779. inner elaboration loop at bottom goal.
  8780. Retracting elaborate*copy-see-to-output-link
  8781. -->
  8782. (I3 ^see 0 +)
  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: (13521: S1 ^operator O1928 +)
  8805. =>WM: (13520: S1 ^operator O1927 +)
  8806. =>WM: (13519: O1928 ^name predict-no)
  8807. =>WM: (13518: O1927 ^name predict-yes)
  8808. =>WM: (13517: R967 ^value 1)
  8809. =>WM: (13516: R1 ^reward R967)
  8810. <=WM: (13507: S1 ^operator O1925 +)
  8811. <=WM: (13508: S1 ^operator O1926 +)
  8812. <=WM: (13509: S1 ^operator O1926)
  8813. <=WM: (13502: R1 ^reward R966)
  8814. <=WM: (13505: O1926 ^name predict-no)
  8815. <=WM: (13504: O1925 ^name predict-yes)
  8816. <=WM: (13503: R966 ^value 1)
  8817. --- Inner Elaboration Phase, active level 1 (S1) ---
  8818. Firing prefer*rvt*predict-yes*H0
  8819. -->
  8820. Firing rl*prefer*rvt*predict-yes*H0*1
  8821. -->
  8822. (S1 ^operator O1927 = 0.)
  8823. Firing prefer*rvt*predict-no*H0
  8824. -->
  8825. Firing rl*prefer*rvt*predict-no*H0*2
  8826. -->
  8827. (S1 ^operator O1928 = 0.9999999999999999)
  8828. inner elaboration loop at bottom goal.
  8829. Retracting rl*prefer*rvt*predict-no*H0*2
  8830. -->
  8831. (S1 ^operator O1926 = 0.9999999999999999)
  8832. Retracting rl*prefer*rvt*predict-yes*H0*1
  8833. -->
  8834. (S1 ^operator O1925 = 0.)
  8835. --- END Proposal Phase ---
  8836. --- Decision Phase ---
  8837. RL update rl*prefer*rvt*predict-no*H0*2 1 0 1 -> 1 0 1(R,m,v=1,1,0)
  8838. =>WM: (13522: S1 ^operator O1928)
  8839. 964: O: O1928 (predict-no)
  8840. --- END Decision Phase ---
  8841. --- Application Phase ---
  8842. --- Firing Productions (PE) For State At Depth 1 ---
  8843. --- Inner Elaboration Phase, active level 1 (S1) ---
  8844. Firing apply*operator
  8845. -->
  8846. (I3 ^predict-no N964 + :O )
  8847. Firing apply*operator*complete
  8848. -->
  8849. (I3 ^predict-no N963 - :O )
  8850. inner elaboration loop at bottom goal.
  8851. --- Change Working Memory (PE) ---
  8852. =>WM: (13523: I3 ^predict-no N964)
  8853. <=WM: (13511: N963 ^status complete)
  8854. <=WM: (13510: I3 ^predict-no N963)
  8855. --- Firing Productions (IE) For State At Depth 1 ---
  8856. --- Inner Elaboration Phase, active level 1 (S1) ---
  8857. Firing monitor*world
  8858. -->
  8859. I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
  8860. --- Change Working Memory (IE) ---
  8861. --- END Application Phase ---
  8862. --- Output Phase ---
  8863. ENV: Agent did: predict-no for direction U in state State-A
  8864. In State-A moving U
  8865. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  8866. predict error 0
  8867. dir: dir isR
  8868. --- END Output Phase ---
  8869. -/--- Input Phase ---
  8870. =>WM: (13527: I2 ^dir R)
  8871. =>WM: (13526: I2 ^reward 1)
  8872. =>WM: (13525: I2 ^see 0)
  8873. =>WM: (13524: N964 ^status complete)
  8874. <=WM: (13514: I2 ^dir U)
  8875. <=WM: (13513: I2 ^reward 1)
  8876. <=WM: (13512: I2 ^see 0)
  8877. =>WM: (13528: I2 ^level-1 L0-root)
  8878. <=WM: (13515: I2 ^level-1 L0-root)
  8879. --- END Input Phase ---
  8880. --- Proposal Phase ---
  8881. --- Inner Elaboration Phase, active level 1 (S1) ---
  8882. Firing rl*prefer*rvt*predict-yes*H0*5*H1*14
  8883. -->
  8884. (S1 ^operator O1927 = 0.9322244945254987)
  8885. Firing rl*prefer*rvt*predict-no*H0*6*H1*19
  8886. -->
  8887. (S1 ^operator O1928 = 0.3)
  8888. Firing prefer*rvt*predict-no*H0*6*H1
  8889. -->
  8890. Firing prefer*rvt*predict-yes*H0*5*H1
  8891. -->
  8892. Firing elaborate*copy-see-to-output-link
  8893. -->
  8894. (I3 ^see 0 +)
  8895. Firing elaborate*reward*based*on*reward
  8896. -->
  8897. (R968 ^value 1 +)
  8898. (R1 ^reward R968 +)
  8899. Firing propose*predict-yes
  8900. -->
  8901. (O1929 ^name predict-yes +)
  8902. (S1 ^operator O1929 +)
  8903. Firing propose*predict-no
  8904. -->
  8905. (O1930 ^name predict-no +)
  8906. (S1 ^operator O1930 +)
  8907. Firing rl*prefer*rvt*predict-no*H0*6
  8908. -->
  8909. (S1 ^operator O1928 = 0.4643592423920161)
  8910. Firing rl*prefer*rvt*predict-yes*H0*5
  8911. -->
  8912. (S1 ^operator O1927 = 0.06777563711408163)
  8913. Firing prefer*rvt*predict-yes*H0
  8914. -->
  8915. Firing prefer*rvt*predict-no*H0
  8916. -->
  8917. Firing elaborate*copy-dir-to-output-link
  8918. -->
  8919. (I3 ^dir R +)
  8920. inner elaboration loop at bottom goal.
  8921. Retracting elaborate*copy-see-to-output-link
  8922. -->
  8923. (I3 ^see 0 +)
  8924. Retracting propose*predict-no
  8925. -->
  8926. (O1928 ^name predict-no +)
  8927. (S1 ^operator O1928 +)
  8928. Retracting propose*predict-yes
  8929. -->
  8930. (O1927 ^name predict-yes +)
  8931. (S1 ^operator O1927 +)
  8932. Retracting elaborate*reward*based*on*reward
  8933. -->
  8934. (R967 ^value 1 +)
  8935. (R1 ^reward R967 +)
  8936. Retracting elaborate*copy-dir-to-output-link
  8937. -->
  8938. (I3 ^dir U +)
  8939. Retracting rl*prefer*rvt*predict-no*H0*2
  8940. -->
  8941. (S1 ^operator O1928 = 0.9999999999999999)
  8942. Retracting rl*prefer*rvt*predict-yes*H0*1
  8943. -->
  8944. (S1 ^operator O1927 = 0.)
  8945. =>WM: (13535: S1 ^operator O1930 +)
  8946. =>WM: (13534: S1 ^operator O1929 +)
  8947. =>WM: (13533: I3 ^dir R)
  8948. =>WM: (13532: O1930 ^name predict-no)
  8949. =>WM: (13531: O1929 ^name predict-yes)
  8950. =>WM: (13530: R968 ^value 1)
  8951. =>WM: (13529: R1 ^reward R968)
  8952. <=WM: (13520: S1 ^operator O1927 +)
  8953. <=WM: (13521: S1 ^operator O1928 +)
  8954. <=WM: (13522: S1 ^operator O1928)
  8955. <=WM: (13506: I3 ^dir U)
  8956. <=WM: (13516: R1 ^reward R967)
  8957. <=WM: (13519: O1928 ^name predict-no)
  8958. <=WM: (13518: O1927 ^name predict-yes)
  8959. <=WM: (13517: R967 ^value 1)
  8960. --- Inner Elaboration Phase, active level 1 (S1) ---
  8961. Firing prefer*rvt*predict-yes*H0
  8962. -->
  8963. Firing rl*prefer*rvt*predict-yes*H0*5*H1*14
  8964. -->
  8965. (S1 ^operator O1929 = 0.9322244945254987)
  8966. Firing rl*prefer*rvt*predict-yes*H0*5
  8967. -->
  8968. (S1 ^operator O1929 = 0.06777563711408163)
  8969. Firing prefer*rvt*predict-yes*H0*5*H1
  8970. -->
  8971. Firing prefer*rvt*predict-no*H0
  8972. -->
  8973. Firing rl*prefer*rvt*predict-no*H0*6*H1*19
  8974. -->
  8975. (S1 ^operator O1930 = 0.3)
  8976. Firing rl*prefer*rvt*predict-no*H0*6
  8977. -->
  8978. (S1 ^operator O1930 = 0.4643592423920161)
  8979. Firing prefer*rvt*predict-no*H0*6*H1
  8980. -->
  8981. inner elaboration loop at bottom goal.
  8982. Retracting rl*prefer*rvt*predict-no*H0*6
  8983. -->
  8984. (S1 ^operator O1928 = 0.4643592423920161)
  8985. Retracting rl*prefer*rvt*predict-no*H0*6*H1*19
  8986. -->
  8987. (S1 ^operator O1928 = 0.3)
  8988. Retracting rl*prefer*rvt*predict-yes*H0*5
  8989. -->
  8990. (S1 ^operator O1927 = 0.06777563711408163)
  8991. Retracting rl*prefer*rvt*predict-yes*H0*5*H1*14
  8992. -->
  8993. (S1 ^operator O1927 = 0.9322244945254987)
  8994. --- END Proposal Phase ---
  8995. --- Decision Phase ---
  8996. RL update rl*prefer*rvt*predict-no*H0*2 1 0 1 -> 1 0 1(R,m,v=1,1,0)
  8997. =>WM: (13536: S1 ^operator O1929)
  8998. 965: O: O1929 (predict-yes)
  8999. --- END Decision Phase ---
  9000. --- Application Phase ---
  9001. --- Firing Productions (PE) For State At Depth 1 ---
  9002. --- Inner Elaboration Phase, active level 1 (S1) ---
  9003. Firing apply*operator
  9004. -->
  9005. (I3 ^predict-yes N965 + :O )
  9006. Firing apply*operator*complete
  9007. -->
  9008. (I3 ^predict-no N964 - :O )
  9009. inner elaboration loop at bottom goal.
  9010. --- Change Working Memory (PE) ---
  9011. =>WM: (13537: I3 ^predict-yes N965)
  9012. <=WM: (13524: N964 ^status complete)
  9013. <=WM: (13523: I3 ^predict-no N964)
  9014. --- Firing Productions (IE) For State At Depth 1 ---
  9015. --- Inner Elaboration Phase, active level 1 (S1) ---
  9016. Firing monitor*world
  9017. -->
  9018. I see 1 and I'm going to do: predict-yes inner elaboration loop at bottom goal.
  9019. --- Change Working Memory (IE) ---
  9020. --- END Application Phase ---
  9021. --- Output Phase ---
  9022. ENV: Agent did: predict-yes for direction R in state State-A
  9023. In State-A moving R
  9024. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  9025. predict error 0
  9026. dir: dir isU
  9027. --- END Output Phase ---
  9028. |\--- Input Phase ---
  9029. =>WM: (13541: I2 ^dir U)
  9030. =>WM: (13540: I2 ^reward 1)
  9031. =>WM: (13539: I2 ^see 1)
  9032. =>WM: (13538: N965 ^status complete)
  9033. <=WM: (13527: I2 ^dir R)
  9034. <=WM: (13526: I2 ^reward 1)
  9035. <=WM: (13525: I2 ^see 0)
  9036. =>WM: (13542: I2 ^level-1 R1-root)
  9037. <=WM: (13528: I2 ^level-1 L0-root)
  9038. --- END Input Phase ---
  9039. --- Proposal Phase ---
  9040. --- Inner Elaboration Phase, active level 1 (S1) ---
  9041. Firing elaborate*copy-see-to-output-link
  9042. -->
  9043. (I3 ^see 1 +)
  9044. Firing elaborate*reward*based*on*reward
  9045. -->
  9046. (R969 ^value 1 +)
  9047. (R1 ^reward R969 +)
  9048. Firing propose*predict-yes
  9049. -->
  9050. (O1931 ^name predict-yes +)
  9051. (S1 ^operator O1931 +)
  9052. Firing propose*predict-no
  9053. -->
  9054. (O1932 ^name predict-no +)
  9055. (S1 ^operator O1932 +)
  9056. Firing rl*prefer*rvt*predict-no*H0*2
  9057. -->
  9058. (S1 ^operator O1930 = 0.9999999999999999)
  9059. Firing rl*prefer*rvt*predict-yes*H0*1
  9060. -->
  9061. (S1 ^operator O1929 = 0.)
  9062. Firing prefer*rvt*predict-yes*H0
  9063. -->
  9064. Firing prefer*rvt*predict-no*H0
  9065. -->
  9066. Firing elaborate*copy-dir-to-output-link
  9067. -->
  9068. (I3 ^dir U +)
  9069. inner elaboration loop at bottom goal.
  9070. Retracting elaborate*copy-see-to-output-link
  9071. -->
  9072. (I3 ^see 0 +)
  9073. Retracting propose*predict-no
  9074. -->
  9075. (O1930 ^name predict-no +)
  9076. (S1 ^operator O1930 +)
  9077. Retracting propose*predict-yes
  9078. -->
  9079. (O1929 ^name predict-yes +)
  9080. (S1 ^operator O1929 +)
  9081. Retracting elaborate*reward*based*on*reward
  9082. -->
  9083. (R968 ^value 1 +)
  9084. (R1 ^reward R968 +)
  9085. Retracting elaborate*copy-dir-to-output-link
  9086. -->
  9087. (I3 ^dir R +)
  9088. Retracting rl*prefer*rvt*predict-no*H0*6
  9089. -->
  9090. (S1 ^operator O1930 = 0.4643592423920161)
  9091. Retracting rl*prefer*rvt*predict-no*H0*6*H1*19
  9092. -->
  9093. (S1 ^operator O1930 = 0.3)
  9094. Retracting rl*prefer*rvt*predict-yes*H0*5
  9095. -->
  9096. (S1 ^operator O1929 = 0.06777563711408163)
  9097. Retracting rl*prefer*rvt*predict-yes*H0*5*H1*14
  9098. -->
  9099. (S1 ^operator O1929 = 0.9322244945254987)
  9100. =>WM: (13550: S1 ^operator O1932 +)
  9101. =>WM: (13549: S1 ^operator O1931 +)
  9102. =>WM: (13548: I3 ^dir U)
  9103. =>WM: (13547: O1932 ^name predict-no)
  9104. =>WM: (13546: O1931 ^name predict-yes)
  9105. =>WM: (13545: R969 ^value 1)
  9106. =>WM: (13544: R1 ^reward R969)
  9107. =>WM: (13543: I3 ^see 1)
  9108. <=WM: (13534: S1 ^operator O1929 +)
  9109. <=WM: (13536: S1 ^operator O1929)
  9110. <=WM: (13535: S1 ^operator O1930 +)
  9111. <=WM: (13533: I3 ^dir R)
  9112. <=WM: (13529: R1 ^reward R968)
  9113. <=WM: (13487: I3 ^see 0)
  9114. <=WM: (13532: O1930 ^name predict-no)
  9115. <=WM: (13531: O1929 ^name predict-yes)
  9116. <=WM: (13530: R968 ^value 1)
  9117. --- Inner Elaboration Phase, active level 1 (S1) ---
  9118. Firing prefer*rvt*predict-yes*H0
  9119. -->
  9120. Firing rl*prefer*rvt*predict-yes*H0*1
  9121. -->
  9122. (S1 ^operator O1931 = 0.)
  9123. Firing prefer*rvt*predict-no*H0
  9124. -->
  9125. Firing rl*prefer*rvt*predict-no*H0*2
  9126. -->
  9127. (S1 ^operator O1932 = 0.9999999999999999)
  9128. inner elaboration loop at bottom goal.
  9129. Retracting rl*prefer*rvt*predict-no*H0*2
  9130. -->
  9131. (S1 ^operator O1930 = 0.9999999999999999)
  9132. Retracting rl*prefer*rvt*predict-yes*H0*1
  9133. -->
  9134. (S1 ^operator O1929 = 0.)
  9135. --- END Proposal Phase ---
  9136. --- Decision Phase ---
  9137. RL update rl*prefer*rvt*predict-yes*H0*5 0.606208 -0.538432 0.0677756 -> 0.606208 -0.538432 0.0677756(R,m,v=1,0.868571,0.114811)
  9138. RL update rl*prefer*rvt*predict-yes*H0*5*H1*14 0.393793 0.538432 0.932224 -> 0.393793 0.538432 0.932224(R,m,v=1,1,0)
  9139. =>WM: (13551: S1 ^operator O1932)
  9140. 966: O: O1932 (predict-no)
  9141. --- END Decision Phase ---
  9142. --- Application Phase ---
  9143. --- Firing Productions (PE) For State At Depth 1 ---
  9144. --- Inner Elaboration Phase, active level 1 (S1) ---
  9145. Firing apply*operator
  9146. -->
  9147. (I3 ^predict-no N966 + :O )
  9148. Firing apply*operator*complete
  9149. -->
  9150. (I3 ^predict-yes N965 - :O )
  9151. inner elaboration loop at bottom goal.
  9152. --- Change Working Memory (PE) ---
  9153. =>WM: (13552: I3 ^predict-no N966)
  9154. <=WM: (13538: N965 ^status complete)
  9155. <=WM: (13537: I3 ^predict-yes N965)
  9156. --- Firing Productions (IE) For State At Depth 1 ---
  9157. --- Inner Elaboration Phase, active level 1 (S1) ---
  9158. Firing monitor*world
  9159. -->
  9160. I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
  9161. --- Change Working Memory (IE) ---
  9162. --- END Application Phase ---
  9163. --- Output Phase ---
  9164. ENV: Agent did: predict-no for direction U in state State-B
  9165. In State-B moving U
  9166. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  9167. predict error 0
  9168. dir: dir isL
  9169. --- END Output Phase ---
  9170. -/|--- Input Phase ---
  9171. =>WM: (13556: I2 ^dir L)
  9172. =>WM: (13555: I2 ^reward 1)
  9173. =>WM: (13554: I2 ^see 0)
  9174. =>WM: (13553: N966 ^status complete)
  9175. <=WM: (13541: I2 ^dir U)
  9176. <=WM: (13540: I2 ^reward 1)
  9177. <=WM: (13539: I2 ^see 1)
  9178. =>WM: (13557: I2 ^level-1 R1-root)
  9179. <=WM: (13542: I2 ^level-1 R1-root)
  9180. --- END Input Phase ---
  9181. --- Proposal Phase ---
  9182. --- Inner Elaboration Phase, active level 1 (S1) ---
  9183. Firing rl*prefer*rvt*predict-no*H0*4*H1*16
  9184. -->
  9185. (S1 ^operator O1932 = -0.2383263875547442)
  9186. Firing rl*prefer*rvt*predict-yes*H0*3*H1*17
  9187. -->
  9188. (S1 ^operator O1931 = 0.3930631401214384)
  9189. Firing prefer*rvt*predict-no*H0*4*H1
  9190. -->
  9191. Firing prefer*rvt*predict-yes*H0*3*H1
  9192. -->
  9193. Firing elaborate*copy-see-to-output-link
  9194. -->
  9195. (I3 ^see 0 +)
  9196. Firing elaborate*reward*based*on*reward
  9197. -->
  9198. (R970 ^value 1 +)
  9199. (R1 ^reward R970 +)
  9200. Firing propose*predict-yes
  9201. -->
  9202. (O1933 ^name predict-yes +)
  9203. (S1 ^operator O1933 +)
  9204. Firing propose*predict-no
  9205. -->
  9206. (O1934 ^name predict-no +)
  9207. (S1 ^operator O1934 +)
  9208. Firing rl*prefer*rvt*predict-no*H0*4
  9209. -->
  9210. (S1 ^operator O1932 = 0.4334984579534752)
  9211. Firing rl*prefer*rvt*predict-yes*H0*3
  9212. -->
  9213. (S1 ^operator O1931 = 0.6069198475882451)
  9214. Firing prefer*rvt*predict-yes*H0
  9215. -->
  9216. Firing prefer*rvt*predict-no*H0
  9217. -->
  9218. Firing elaborate*copy-dir-to-output-link
  9219. -->
  9220. (I3 ^dir L +)
  9221. inner elaboration loop at bottom goal.
  9222. Retracting elaborate*copy-see-to-output-link
  9223. -->
  9224. (I3 ^see 1 +)
  9225. Retracting propose*predict-no
  9226. -->
  9227. (O1932 ^name predict-no +)
  9228. (S1 ^operator O1932 +)
  9229. Retracting propose*predict-yes
  9230. -->
  9231. (O1931 ^name predict-yes +)
  9232. (S1 ^operator O1931 +)
  9233. Retracting elaborate*reward*based*on*reward
  9234. -->
  9235. (R969 ^value 1 +)
  9236. (R1 ^reward R969 +)
  9237. Retracting elaborate*copy-dir-to-output-link
  9238. -->
  9239. (I3 ^dir U +)
  9240. Retracting rl*prefer*rvt*predict-no*H0*2
  9241. -->
  9242. (S1 ^operator O1932 = 0.9999999999999999)
  9243. Retracting rl*prefer*rvt*predict-yes*H0*1
  9244. -->
  9245. (S1 ^operator O1931 = 0.)
  9246. =>WM: (13565: S1 ^operator O1934 +)
  9247. =>WM: (13564: S1 ^operator O1933 +)
  9248. =>WM: (13563: I3 ^dir L)
  9249. =>WM: (13562: O1934 ^name predict-no)
  9250. =>WM: (13561: O1933 ^name predict-yes)
  9251. =>WM: (13560: R970 ^value 1)
  9252. =>WM: (13559: R1 ^reward R970)
  9253. =>WM: (13558: I3 ^see 0)
  9254. <=WM: (13549: S1 ^operator O1931 +)
  9255. <=WM: (13550: S1 ^operator O1932 +)
  9256. <=WM: (13551: S1 ^operator O1932)
  9257. <=WM: (13548: I3 ^dir U)
  9258. <=WM: (13544: R1 ^reward R969)
  9259. <=WM: (13543: I3 ^see 1)
  9260. <=WM: (13547: O1932 ^name predict-no)
  9261. <=WM: (13546: O1931 ^name predict-yes)
  9262. <=WM: (13545: R969 ^value 1)
  9263. --- Inner Elaboration Phase, active level 1 (S1) ---
  9264. Firing prefer*rvt*predict-yes*H0
  9265. -->
  9266. Firing rl*prefer*rvt*predict-yes*H0*3*H1*17
  9267. -->
  9268. (S1 ^operator O1933 = 0.3930631401214384)
  9269. Firing rl*prefer*rvt*predict-yes*H0*3
  9270. -->
  9271. (S1 ^operator O1933 = 0.6069198475882451)
  9272. Firing prefer*rvt*predict-yes*H0*3*H1
  9273. -->
  9274. Firing prefer*rvt*predict-no*H0
  9275. -->
  9276. Firing rl*prefer*rvt*predict-no*H0*4*H1*16
  9277. -->
  9278. (S1 ^operator O1934 = -0.2383263875547442)
  9279. Firing rl*prefer*rvt*predict-no*H0*4
  9280. -->
  9281. (S1 ^operator O1934 = 0.4334984579534752)
  9282. Firing prefer*rvt*predict-no*H0*4*H1
  9283. -->
  9284. inner elaboration loop at bottom goal.
  9285. Retracting rl*prefer*rvt*predict-no*H0*4
  9286. -->
  9287. (S1 ^operator O1932 = 0.4334984579534752)
  9288. Retracting rl*prefer*rvt*predict-no*H0*4*H1*16
  9289. -->
  9290. (S1 ^operator O1932 = -0.2383263875547442)
  9291. Retracting rl*prefer*rvt*predict-yes*H0*3
  9292. -->
  9293. (S1 ^operator O1931 = 0.6069198475882451)
  9294. Retracting rl*prefer*rvt*predict-yes*H0*3*H1*17
  9295. -->
  9296. (S1 ^operator O1931 = 0.3930631401214384)
  9297. --- END Proposal Phase ---
  9298. --- Decision Phase ---
  9299. RL update rl*prefer*rvt*predict-no*H0*2 1 0 1 -> 1 0 1(R,m,v=1,1,0)
  9300. =>WM: (13566: S1 ^operator O1933)
  9301. 967: O: O1933 (predict-yes)
  9302. --- END Decision Phase ---
  9303. --- Application Phase ---
  9304. --- Firing Productions (PE) For State At Depth 1 ---
  9305. --- Inner Elaboration Phase, active level 1 (S1) ---
  9306. Firing apply*operator
  9307. -->
  9308. (I3 ^predict-yes N967 + :O )
  9309. Firing apply*operator*complete
  9310. -->
  9311. (I3 ^predict-no N966 - :O )
  9312. inner elaboration loop at bottom goal.
  9313. --- Change Working Memory (PE) ---
  9314. =>WM: (13567: I3 ^predict-yes N967)
  9315. <=WM: (13553: N966 ^status complete)
  9316. <=WM: (13552: I3 ^predict-no N966)
  9317. --- Firing Productions (IE) For State At Depth 1 ---
  9318. --- Inner Elaboration Phase, active level 1 (S1) ---
  9319. Firing monitor*world
  9320. -->
  9321. I see 1 and I'm going to do: predict-yes inner elaboration loop at bottom goal.
  9322. --- Change Working Memory (IE) ---
  9323. --- END Application Phase ---
  9324. --- Output Phase ---
  9325. ENV: Agent did: predict-yes for direction L in state State-B
  9326. In State-B moving L
  9327. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  9328. predict error 0
  9329. dir: dir isL
  9330. --- END Output Phase ---
  9331. \---- Input Phase ---
  9332. =>WM: (13571: I2 ^dir L)
  9333. =>WM: (13570: I2 ^reward 1)
  9334. =>WM: (13569: I2 ^see 1)
  9335. =>WM: (13568: N967 ^status complete)
  9336. <=WM: (13556: I2 ^dir L)
  9337. <=WM: (13555: I2 ^reward 1)
  9338. <=WM: (13554: I2 ^see 0)
  9339. =>WM: (13572: I2 ^level-1 L1-root)
  9340. <=WM: (13557: I2 ^level-1 R1-root)
  9341. --- END Input Phase ---
  9342. --- Proposal Phase ---
  9343. --- Inner Elaboration Phase, active level 1 (S1) ---
  9344. Firing rl*prefer*rvt*predict-yes*H0*3*H1*11
  9345. -->
  9346. (S1 ^operator O1933 = -0.03517433757196466)
  9347. Firing rl*prefer*rvt*predict-no*H0*4*H1*10
  9348. -->
  9349. (S1 ^operator O1934 = 0.5665095595638719)
  9350. Firing prefer*rvt*predict-no*H0*4*H1
  9351. -->
  9352. Firing prefer*rvt*predict-yes*H0*3*H1
  9353. -->
  9354. Firing elaborate*copy-see-to-output-link
  9355. -->
  9356. (I3 ^see 1 +)
  9357. Firing elaborate*reward*based*on*reward
  9358. -->
  9359. (R971 ^value 1 +)
  9360. (R1 ^reward R971 +)
  9361. Firing propose*predict-yes
  9362. -->
  9363. (O1935 ^name predict-yes +)
  9364. (S1 ^operator O1935 +)
  9365. Firing propose*predict-no
  9366. -->
  9367. (O1936 ^name predict-no +)
  9368. (S1 ^operator O1936 +)
  9369. Firing rl*prefer*rvt*predict-no*H0*4
  9370. -->
  9371. (S1 ^operator O1934 = 0.4334984579534752)
  9372. Firing rl*prefer*rvt*predict-yes*H0*3
  9373. -->
  9374. (S1 ^operator O1933 = 0.6069198475882451)
  9375. Firing prefer*rvt*predict-yes*H0
  9376. -->
  9377. Firing prefer*rvt*predict-no*H0
  9378. -->
  9379. Firing elaborate*copy-dir-to-output-link
  9380. -->
  9381. (I3 ^dir L +)
  9382. inner elaboration loop at bottom goal.
  9383. Retracting elaborate*copy-see-to-output-link
  9384. -->
  9385. (I3 ^see 0 +)
  9386. Retracting propose*predict-no
  9387. -->
  9388. (O1934 ^name predict-no +)
  9389. (S1 ^operator O1934 +)
  9390. Retracting propose*predict-yes
  9391. -->
  9392. (O1933 ^name predict-yes +)
  9393. (S1 ^operator O1933 +)
  9394. Retracting elaborate*reward*based*on*reward
  9395. -->
  9396. (R970 ^value 1 +)
  9397. (R1 ^reward R970 +)
  9398. Retracting elaborate*copy-dir-to-output-link
  9399. -->
  9400. (I3 ^dir L +)
  9401. Retracting rl*prefer*rvt*predict-no*H0*4
  9402. -->
  9403. (S1 ^operator O1934 = 0.4334984579534752)
  9404. Retracting rl*prefer*rvt*predict-no*H0*4*H1*16
  9405. -->
  9406. (S1 ^operator O1934 = -0.2383263875547442)
  9407. Retracting rl*prefer*rvt*predict-yes*H0*3
  9408. -->
  9409. (S1 ^operator O1933 = 0.6069198475882451)
  9410. Retracting rl*prefer*rvt*predict-yes*H0*3*H1*17
  9411. -->
  9412. (S1 ^operator O1933 = 0.3930631401214384)
  9413. =>WM: (13579: S1 ^operator O1936 +)
  9414. =>WM: (13578: S1 ^operator O1935 +)
  9415. =>WM: (13577: O1936 ^name predict-no)
  9416. =>WM: (13576: O1935 ^name predict-yes)
  9417. =>WM: (13575: R971 ^value 1)
  9418. =>WM: (13574: R1 ^reward R971)
  9419. =>WM: (13573: I3 ^see 1)
  9420. <=WM: (13564: S1 ^operator O1933 +)
  9421. <=WM: (13566: S1 ^operator O1933)
  9422. <=WM: (13565: S1 ^operator O1934 +)
  9423. <=WM: (13559: R1 ^reward R970)
  9424. <=WM: (13558: I3 ^see 0)
  9425. <=WM: (13562: O1934 ^name predict-no)
  9426. <=WM: (13561: O1933 ^name predict-yes)
  9427. <=WM: (13560: R970 ^value 1)
  9428. --- Inner Elaboration Phase, active level 1 (S1) ---
  9429. Firing prefer*rvt*predict-yes*H0
  9430. -->
  9431. Firing rl*prefer*rvt*predict-yes*H0*3
  9432. -->
  9433. (S1 ^operator O1935 = 0.6069198475882451)
  9434. Firing prefer*rvt*predict-yes*H0*3*H1
  9435. -->
  9436. Firing rl*prefer*rvt*predict-yes*H0*3*H1*11
  9437. -->
  9438. (S1 ^operator O1935 = -0.03517433757196466)
  9439. Firing prefer*rvt*predict-no*H0
  9440. -->
  9441. Firing rl*prefer*rvt*predict-no*H0*4
  9442. -->
  9443. (S1 ^operator O1936 = 0.4334984579534752)
  9444. Firing prefer*rvt*predict-no*H0*4*H1
  9445. -->
  9446. Firing rl*prefer*rvt*predict-no*H0*4*H1*10
  9447. -->
  9448. (S1 ^operator O1936 = 0.5665095595638719)
  9449. inner elaboration loop at bottom goal.
  9450. Retracting rl*prefer*rvt*predict-no*H0*4
  9451. -->
  9452. (S1 ^operator O1934 = 0.4334984579534752)
  9453. Retracting rl*prefer*rvt*predict-no*H0*4*H1*10
  9454. -->
  9455. (S1 ^operator O1934 = 0.5665095595638719)
  9456. Retracting rl*prefer*rvt*predict-yes*H0*3
  9457. -->
  9458. (S1 ^operator O1933 = 0.6069198475882451)
  9459. Retracting rl*prefer*rvt*predict-yes*H0*3*H1*11
  9460. -->
  9461. (S1 ^operator O1933 = -0.03517433757196466)
  9462. --- END Proposal Phase ---
  9463. --- Decision Phase ---
  9464. RL update rl*prefer*rvt*predict-yes*H0*3 0.65614 -0.0492205 0.60692 -> 0.656143 -0.0492204 0.606922(R,m,v=1,0.945578,0.0518125)
  9465. RL update rl*prefer*rvt*predict-yes*H0*3*H1*17 0.343843 0.0492199 0.393063 -> 0.343846 0.04922 0.393066(R,m,v=1,1,0)
  9466. =>WM: (13580: S1 ^operator O1936)
  9467. 968: O: O1936 (predict-no)
  9468. --- END Decision Phase ---
  9469. --- Application Phase ---
  9470. --- Firing Productions (PE) For State At Depth 1 ---
  9471. --- Inner Elaboration Phase, active level 1 (S1) ---
  9472. Firing apply*operator
  9473. -->
  9474. (I3 ^predict-no N968 + :O )
  9475. Firing apply*operator*complete
  9476. -->
  9477. (I3 ^predict-yes N967 - :O )
  9478. inner elaboration loop at bottom goal.
  9479. --- Change Working Memory (PE) ---
  9480. =>WM: (13581: I3 ^predict-no N968)
  9481. <=WM: (13568: N967 ^status complete)
  9482. <=WM: (13567: I3 ^predict-yes N967)
  9483. --- Firing Productions (IE) For State At Depth 1 ---
  9484. --- Inner Elaboration Phase, active level 1 (S1) ---
  9485. Firing monitor*world
  9486. -->
  9487. I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
  9488. --- Change Working Memory (IE) ---
  9489. --- END Application Phase ---
  9490. --- Output Phase ---
  9491. ENV: Agent did: predict-no for direction L in state State-A
  9492. In State-A moving L
  9493. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  9494. predict error 0
  9495. dir: dir isR
  9496. --- END Output Phase ---
  9497. /|\--- Input Phase ---
  9498. =>WM: (13585: I2 ^dir R)
  9499. =>WM: (13584: I2 ^reward 1)
  9500. =>WM: (13583: I2 ^see 0)
  9501. =>WM: (13582: N968 ^status complete)
  9502. <=WM: (13571: I2 ^dir L)
  9503. <=WM: (13570: I2 ^reward 1)
  9504. <=WM: (13569: I2 ^see 1)
  9505. =>WM: (13586: I2 ^level-1 L0-root)
  9506. <=WM: (13572: I2 ^level-1 L1-root)
  9507. --- END Input Phase ---
  9508. --- Proposal Phase ---
  9509. --- Inner Elaboration Phase, active level 1 (S1) ---
  9510. Firing rl*prefer*rvt*predict-yes*H0*5*H1*14
  9511. -->
  9512. (S1 ^operator O1935 = 0.9322244747795617)
  9513. Firing rl*prefer*rvt*predict-no*H0*6*H1*19
  9514. -->
  9515. (S1 ^operator O1936 = 0.3)
  9516. Firing prefer*rvt*predict-no*H0*6*H1
  9517. -->
  9518. Firing prefer*rvt*predict-yes*H0*5*H1
  9519. -->
  9520. Firing elaborate*copy-see-to-output-link
  9521. -->
  9522. (I3 ^see 0 +)
  9523. Firing elaborate*reward*based*on*reward
  9524. -->
  9525. (R972 ^value 1 +)
  9526. (R1 ^reward R972 +)
  9527. Firing propose*predict-yes
  9528. -->
  9529. (O1937 ^name predict-yes +)
  9530. (S1 ^operator O1937 +)
  9531. Firing propose*predict-no
  9532. -->
  9533. (O1938 ^name predict-no +)
  9534. (S1 ^operator O1938 +)
  9535. Firing rl*prefer*rvt*predict-no*H0*6
  9536. -->
  9537. (S1 ^operator O1936 = 0.4643592423920161)
  9538. Firing rl*prefer*rvt*predict-yes*H0*5
  9539. -->
  9540. (S1 ^operator O1935 = 0.06777561736814464)
  9541. Firing prefer*rvt*predict-yes*H0
  9542. -->
  9543. Firing prefer*rvt*predict-no*H0
  9544. -->
  9545. Firing elaborate*copy-dir-to-output-link
  9546. -->
  9547. (I3 ^dir R +)
  9548. inner elaboration loop at bottom goal.
  9549. Retracting elaborate*copy-see-to-output-link
  9550. -->
  9551. (I3 ^see 1 +)
  9552. Retracting propose*predict-no
  9553. -->
  9554. (O1936 ^name predict-no +)
  9555. (S1 ^operator O1936 +)
  9556. Retracting propose*predict-yes
  9557. -->
  9558. (O1935 ^name predict-yes +)
  9559. (S1 ^operator O1935 +)
  9560. Retracting elaborate*reward*based*on*reward
  9561. -->
  9562. (R971 ^value 1 +)
  9563. (R1 ^reward R971 +)
  9564. Retracting elaborate*copy-dir-to-output-link
  9565. -->
  9566. (I3 ^dir L +)
  9567. Retracting rl*prefer*rvt*predict-no*H0*4*H1*10
  9568. -->
  9569. (S1 ^operator O1936 = 0.5665095595638719)
  9570. Retracting rl*prefer*rvt*predict-no*H0*4
  9571. -->
  9572. (S1 ^operator O1936 = 0.4334984579534752)
  9573. Retracting rl*prefer*rvt*predict-yes*H0*3*H1*11
  9574. -->
  9575. (S1 ^operator O1935 = -0.03517433757196466)
  9576. Retracting rl*prefer*rvt*predict-yes*H0*3
  9577. -->
  9578. (S1 ^operator O1935 = 0.6069223994317926)
  9579. =>WM: (13594: S1 ^operator O1938 +)
  9580. =>WM: (13593: S1 ^operator O1937 +)
  9581. =>WM: (13592: I3 ^dir R)
  9582. =>WM: (13591: O1938 ^name predict-no)
  9583. =>WM: (13590: O1937 ^name predict-yes)
  9584. =>WM: (13589: R972 ^value 1)
  9585. =>WM: (13588: R1 ^reward R972)
  9586. =>WM: (13587: I3 ^see 0)
  9587. <=WM: (13578: S1 ^operator O1935 +)
  9588. <=WM: (13579: S1 ^operator O1936 +)
  9589. <=WM: (13580: S1 ^operator O1936)
  9590. <=WM: (13563: I3 ^dir L)
  9591. <=WM: (13574: R1 ^reward R971)
  9592. <=WM: (13573: I3 ^see 1)
  9593. <=WM: (13577: O1936 ^name predict-no)
  9594. <=WM: (13576: O1935 ^name predict-yes)
  9595. <=WM: (13575: R971 ^value 1)
  9596. --- Inner Elaboration Phase, active level 1 (S1) ---
  9597. Firing prefer*rvt*predict-yes*H0
  9598. -->
  9599. Firing rl*prefer*rvt*predict-yes*H0*5
  9600. -->
  9601. (S1 ^operator O1937 = 0.06777561736814464)
  9602. Firing prefer*rvt*predict-yes*H0*5*H1
  9603. -->
  9604. Firing rl*prefer*rvt*predict-yes*H0*5*H1*14
  9605. -->
  9606. (S1 ^operator O1937 = 0.9322244747795617)
  9607. Firing prefer*rvt*predict-no*H0
  9608. -->
  9609. Firing rl*prefer*rvt*predict-no*H0*6
  9610. -->
  9611. (S1 ^operator O1938 = 0.4643592423920161)
  9612. Firing prefer*rvt*predict-no*H0*6*H1
  9613. -->
  9614. Firing rl*prefer*rvt*predict-no*H0*6*H1*19
  9615. -->
  9616. (S1 ^operator O1938 = 0.3)
  9617. inner elaboration loop at bottom goal.
  9618. Retracting rl*prefer*rvt*predict-no*H0*6
  9619. -->
  9620. (S1 ^operator O1936 = 0.4643592423920161)
  9621. Retracting rl*prefer*rvt*predict-no*H0*6*H1*19
  9622. -->
  9623. (S1 ^operator O1936 = 0.3)
  9624. Retracting rl*prefer*rvt*predict-yes*H0*5
  9625. -->
  9626. (S1 ^operator O1935 = 0.06777561736814464)
  9627. Retracting rl*prefer*rvt*predict-yes*H0*5*H1*14
  9628. -->
  9629. (S1 ^operator O1935 = 0.9322244747795617)
  9630. --- END Proposal Phase ---
  9631. --- Decision Phase ---
  9632. RL update rl*prefer*rvt*predict-no*H0*4 0.490214 -0.056716 0.433498 -> 0.490213 -0.056716 0.433497(R,m,v=1,0.88535,0.102156)
  9633. RL update rl*prefer*rvt*predict-no*H0*4*H1*10 0.509794 0.056716 0.56651 -> 0.509792 0.056716 0.566508(R,m,v=1,1,0)
  9634. =>WM: (13595: S1 ^operator O1937)
  9635. 969: O: O1937 (predict-yes)
  9636. --- END Decision Phase ---
  9637. --- Application Phase ---
  9638. --- Firing Productions (PE) For State At Depth 1 ---
  9639. --- Inner Elaboration Phase, active level 1 (S1) ---
  9640. Firing apply*operator
  9641. -->
  9642. (I3 ^predict-yes N969 + :O )
  9643. Firing apply*operator*complete
  9644. -->
  9645. (I3 ^predict-no N968 - :O )
  9646. inner elaboration loop at bottom goal.
  9647. --- Change Working Memory (PE) ---
  9648. =>WM: (13596: I3 ^predict-yes N969)
  9649. <=WM: (13582: N968 ^status complete)
  9650. <=WM: (13581: I3 ^predict-no N968)
  9651. --- Firing Productions (IE) For State At Depth 1 ---
  9652. --- Inner Elaboration Phase, active level 1 (S1) ---
  9653. Firing monitor*world
  9654. -->
  9655. I see 1 and I'm going to do: predict-yes inner elaboration loop at bottom goal.
  9656. --- Change Working Memory (IE) ---
  9657. --- END Application Phase ---
  9658. --- Output Phase ---
  9659. ENV: Agent did: predict-yes for direction R in state State-A
  9660. In State-A moving R
  9661. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  9662. predict error 0
  9663. dir: dir isL
  9664. --- END Output Phase ---
  9665. -/|--- Input Phase ---
  9666. =>WM: (13600: I2 ^dir L)
  9667. =>WM: (13599: I2 ^reward 1)
  9668. =>WM: (13598: I2 ^see 1)
  9669. =>WM: (13597: N969 ^status complete)
  9670. <=WM: (13585: I2 ^dir R)
  9671. <=WM: (13584: I2 ^reward 1)
  9672. <=WM: (13583: I2 ^see 0)
  9673. =>WM: (13601: I2 ^level-1 R1-root)
  9674. <=WM: (13586: I2 ^level-1 L0-root)
  9675. --- END Input Phase ---
  9676. --- Proposal Phase ---
  9677. --- Inner Elaboration Phase, active level 1 (S1) ---
  9678. Firing rl*prefer*rvt*predict-no*H0*4*H1*16
  9679. -->
  9680. (S1 ^operator O1938 = -0.2383263875547442)
  9681. Firing rl*prefer*rvt*predict-yes*H0*3*H1*17
  9682. -->
  9683. (S1 ^operator O1937 = 0.3930656919649859)
  9684. Firing prefer*rvt*predict-no*H0*4*H1
  9685. -->
  9686. Firing prefer*rvt*predict-yes*H0*3*H1
  9687. -->
  9688. Firing elaborate*copy-see-to-output-link
  9689. -->
  9690. (I3 ^see 1 +)
  9691. Firing elaborate*reward*based*on*reward
  9692. -->
  9693. (R973 ^value 1 +)
  9694. (R1 ^reward R973 +)
  9695. Firing propose*predict-yes
  9696. -->
  9697. (O1939 ^name predict-yes +)
  9698. (S1 ^operator O1939 +)
  9699. Firing propose*predict-no
  9700. -->
  9701. (O1940 ^name predict-no +)
  9702. (S1 ^operator O1940 +)
  9703. Firing rl*prefer*rvt*predict-no*H0*4
  9704. -->
  9705. (S1 ^operator O1938 = 0.4334972553258731)
  9706. Firing rl*prefer*rvt*predict-yes*H0*3
  9707. -->
  9708. (S1 ^operator O1937 = 0.6069223994317926)
  9709. Firing prefer*rvt*predict-yes*H0
  9710. -->
  9711. Firing prefer*rvt*predict-no*H0
  9712. -->
  9713. Firing elaborate*copy-dir-to-output-link
  9714. -->
  9715. (I3 ^dir L +)
  9716. inner elaboration loop at bottom goal.
  9717. Retracting elaborate*copy-see-to-output-link
  9718. -->
  9719. (I3 ^see 0 +)
  9720. Retracting propose*predict-no
  9721. -->
  9722. (O1938 ^name predict-no +)
  9723. (S1 ^operator O1938 +)
  9724. Retracting propose*predict-yes
  9725. -->
  9726. (O1937 ^name predict-yes +)
  9727. (S1 ^operator O1937 +)
  9728. Retracting elaborate*reward*based*on*reward
  9729. -->
  9730. (R972 ^value 1 +)
  9731. (R1 ^reward R972 +)
  9732. Retracting elaborate*copy-dir-to-output-link
  9733. -->
  9734. (I3 ^dir R +)
  9735. Retracting rl*prefer*rvt*predict-no*H0*6*H1*19
  9736. -->
  9737. (S1 ^operator O1938 = 0.3)
  9738. Retracting rl*prefer*rvt*predict-no*H0*6
  9739. -->
  9740. (S1 ^operator O1938 = 0.4643592423920161)
  9741. Retracting rl*prefer*rvt*predict-yes*H0*5*H1*14
  9742. -->
  9743. (S1 ^operator O1937 = 0.9322244747795617)
  9744. Retracting rl*prefer*rvt*predict-yes*H0*5
  9745. -->
  9746. (S1 ^operator O1937 = 0.06777561736814464)
  9747. =>WM: (13609: S1 ^operator O1940 +)
  9748. =>WM: (13608: S1 ^operator O1939 +)
  9749. =>WM: (13607: I3 ^dir L)
  9750. =>WM: (13606: O1940 ^name predict-no)
  9751. =>WM: (13605: O1939 ^name predict-yes)
  9752. =>WM: (13604: R973 ^value 1)
  9753. =>WM: (13603: R1 ^reward R973)
  9754. =>WM: (13602: I3 ^see 1)
  9755. <=WM: (13593: S1 ^operator O1937 +)
  9756. <=WM: (13595: S1 ^operator O1937)
  9757. <=WM: (13594: S1 ^operator O1938 +)
  9758. <=WM: (13592: I3 ^dir R)
  9759. <=WM: (13588: R1 ^reward R972)
  9760. <=WM: (13587: I3 ^see 0)
  9761. <=WM: (13591: O1938 ^name predict-no)
  9762. <=WM: (13590: O1937 ^name predict-yes)
  9763. <=WM: (13589: R972 ^value 1)
  9764. --- Inner Elaboration Phase, active level 1 (S1) ---
  9765. Firing prefer*rvt*predict-yes*H0
  9766. -->
  9767. Firing rl*prefer*rvt*predict-yes*H0*3
  9768. -->
  9769. (S1 ^operator O1939 = 0.6069223994317926)
  9770. Firing prefer*rvt*predict-yes*H0*3*H1
  9771. -->
  9772. Firing rl*prefer*rvt*predict-yes*H0*3*H1*17
  9773. -->
  9774. (S1 ^operator O1939 = 0.3930656919649859)
  9775. Firing prefer*rvt*predict-no*H0
  9776. -->
  9777. Firing rl*prefer*rvt*predict-no*H0*4
  9778. -->
  9779. (S1 ^operator O1940 = 0.4334972553258731)
  9780. Firing prefer*rvt*predict-no*H0*4*H1
  9781. -->
  9782. Firing rl*prefer*rvt*predict-no*H0*4*H1*16
  9783. -->
  9784. (S1 ^operator O1940 = -0.2383263875547442)
  9785. inner elaboration loop at bottom goal.
  9786. Retracting rl*prefer*rvt*predict-no*H0*4
  9787. -->
  9788. (S1 ^operator O1938 = 0.4334972553258731)
  9789. Retracting rl*prefer*rvt*predict-no*H0*4*H1*16
  9790. -->
  9791. (S1 ^operator O1938 = -0.2383263875547442)
  9792. Retracting rl*prefer*rvt*predict-yes*H0*3
  9793. -->
  9794. (S1 ^operator O1937 = 0.6069223994317926)
  9795. Retracting rl*prefer*rvt*predict-yes*H0*3*H1*17
  9796. -->
  9797. (S1 ^operator O1937 = 0.3930656919649859)
  9798. --- END Proposal Phase ---
  9799. --- Decision Phase ---
  9800. RL update rl*prefer*rvt*predict-yes*H0*5 0.606208 -0.538432 0.0677756 -> 0.606208 -0.538432 0.0677756(R,m,v=1,0.869318,0.114253)
  9801. RL update rl*prefer*rvt*predict-yes*H0*5*H1*14 0.393793 0.538432 0.932224 -> 0.393792 0.538432 0.932224(R,m,v=1,1,0)
  9802. =>WM: (13610: S1 ^operator O1939)
  9803. 970: O: O1939 (predict-yes)
  9804. --- END Decision Phase ---
  9805. --- Application Phase ---
  9806. --- Firing Productions (PE) For State At Depth 1 ---
  9807. --- Inner Elaboration Phase, active level 1 (S1) ---
  9808. Firing apply*operator
  9809. -->
  9810. (I3 ^predict-yes N970 + :O )
  9811. Firing apply*operator*complete
  9812. -->
  9813. (I3 ^predict-yes N969 - :O )
  9814. inner elaboration loop at bottom goal.
  9815. --- Change Working Memory (PE) ---
  9816. =>WM: (13611: I3 ^predict-yes N970)
  9817. <=WM: (13597: N969 ^status complete)
  9818. <=WM: (13596: I3 ^predict-yes N969)
  9819. --- Firing Productions (IE) For State At Depth 1 ---
  9820. --- Inner Elaboration Phase, active level 1 (S1) ---
  9821. Firing monitor*world
  9822. -->
  9823. I see 1 and I'm going to do: predict-yes inner elaboration loop at bottom goal.
  9824. --- Change Working Memory (IE) ---
  9825. --- END Application Phase ---
  9826. --- Output Phase ---
  9827. ENV: Agent did: predict-yes for direction L in state State-B
  9828. In State-B moving L
  9829. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  9830. predict error 0
  9831. dir: dir isU
  9832. --- END Output Phase ---
  9833. \-/|--- Input Phase ---
  9834. =>WM: (13615: I2 ^dir U)
  9835. =>WM: (13614: I2 ^reward 1)
  9836. =>WM: (13613: I2 ^see 1)
  9837. =>WM: (13612: N970 ^status complete)
  9838. <=WM: (13600: I2 ^dir L)
  9839. <=WM: (13599: I2 ^reward 1)
  9840. <=WM: (13598: I2 ^see 1)
  9841. =>WM: (13616: I2 ^level-1 L1-root)
  9842. <=WM: (13601: I2 ^level-1 R1-root)
  9843. --- END Input Phase ---
  9844. --- Proposal Phase ---
  9845. --- Inner Elaboration Phase, active level 1 (S1) ---
  9846. Firing elaborate*copy-see-to-output-link
  9847. -->
  9848. (I3 ^see 1 +)
  9849. Firing elaborate*reward*based*on*reward
  9850. -->
  9851. (R974 ^value 1 +)
  9852. (R1 ^reward R974 +)
  9853. Firing propose*predict-yes
  9854. -->
  9855. (O1941 ^name predict-yes +)
  9856. (S1 ^operator O1941 +)
  9857. Firing propose*predict-no
  9858. -->
  9859. (O1942 ^name predict-no +)
  9860. (S1 ^operator O1942 +)
  9861. Firing rl*prefer*rvt*predict-no*H0*2
  9862. -->
  9863. (S1 ^operator O1940 = 0.9999999999999999)
  9864. Firing rl*prefer*rvt*predict-yes*H0*1
  9865. -->
  9866. (S1 ^operator O1939 = 0.)
  9867. Firing prefer*rvt*predict-yes*H0
  9868. -->
  9869. Firing prefer*rvt*predict-no*H0
  9870. -->
  9871. Firing elaborate*copy-dir-to-output-link
  9872. -->
  9873. (I3 ^dir U +)
  9874. inner elaboration loop at bottom goal.
  9875. Retracting elaborate*copy-see-to-output-link
  9876. -->
  9877. (I3 ^see 1 +)
  9878. Retracting propose*predict-no
  9879. -->
  9880. (O1940 ^name predict-no +)
  9881. (S1 ^operator O1940 +)
  9882. Retracting propose*predict-yes
  9883. -->
  9884. (O1939 ^name predict-yes +)
  9885. (S1 ^operator O1939 +)
  9886. Retracting elaborate*reward*based*on*reward
  9887. -->
  9888. (R973 ^value 1 +)
  9889. (R1 ^reward R973 +)
  9890. Retracting elaborate*copy-dir-to-output-link
  9891. -->
  9892. (I3 ^dir L +)
  9893. Retracting rl*prefer*rvt*predict-no*H0*4*H1*16
  9894. -->
  9895. (S1 ^operator O1940 = -0.2383263875547442)
  9896. Retracting rl*prefer*rvt*predict-no*H0*4
  9897. -->
  9898. (S1 ^operator O1940 = 0.4334972553258731)
  9899. Retracting rl*prefer*rvt*predict-yes*H0*3*H1*17
  9900. -->
  9901. (S1 ^operator O1939 = 0.3930656919649859)
  9902. Retracting rl*prefer*rvt*predict-yes*H0*3
  9903. -->
  9904. (S1 ^operator O1939 = 0.6069223994317926)
  9905. =>WM: (13623: S1 ^operator O1942 +)
  9906. =>WM: (13622: S1 ^operator O1941 +)
  9907. =>WM: (13621: I3 ^dir U)
  9908. =>WM: (13620: O1942 ^name predict-no)
  9909. =>WM: (13619: O1941 ^name predict-yes)
  9910. =>WM: (13618: R974 ^value 1)
  9911. =>WM: (13617: R1 ^reward R974)
  9912. <=WM: (13608: S1 ^operator O1939 +)
  9913. <=WM: (13610: S1 ^operator O1939)
  9914. <=WM: (13609: S1 ^operator O1940 +)
  9915. <=WM: (13607: I3 ^dir L)
  9916. <=WM: (13603: R1 ^reward R973)
  9917. <=WM: (13606: O1940 ^name predict-no)
  9918. <=WM: (13605: O1939 ^name predict-yes)
  9919. <=WM: (13604: R973 ^value 1)
  9920. --- Inner Elaboration Phase, active level 1 (S1) ---
  9921. Firing prefer*rvt*predict-yes*H0
  9922. -->
  9923. Firing rl*prefer*rvt*predict-yes*H0*1
  9924. -->
  9925. (S1 ^operator O1941 = 0.)
  9926. Firing prefer*rvt*predict-no*H0
  9927. -->
  9928. Firing rl*prefer*rvt*predict-no*H0*2
  9929. -->
  9930. (S1 ^operator O1942 = 0.9999999999999999)
  9931. inner elaboration loop at bottom goal.
  9932. Retracting rl*prefer*rvt*predict-no*H0*2
  9933. -->
  9934. (S1 ^operator O1940 = 0.9999999999999999)
  9935. Retracting rl*prefer*rvt*predict-yes*H0*1
  9936. -->
  9937. (S1 ^operator O1939 = 0.)
  9938. --- END Proposal Phase ---
  9939. --- Decision Phase ---
  9940. RL update rl*prefer*rvt*predict-yes*H0*3 0.656143 -0.0492204 0.606922 -> 0.656145 -0.0492204 0.606924(R,m,v=1,0.945946,0.0514801)
  9941. RL update rl*prefer*rvt*predict-yes*H0*3*H1*17 0.343846 0.04922 0.393066 -> 0.343847 0.0492201 0.393067(R,m,v=1,1,0)
  9942. =>WM: (13624: S1 ^operator O1942)
  9943. 971: O: O1942 (predict-no)
  9944. --- END Decision Phase ---
  9945. --- Application Phase ---
  9946. --- Firing Productions (PE) For State At Depth 1 ---
  9947. --- Inner Elaboration Phase, active level 1 (S1) ---
  9948. Firing apply*operator
  9949. -->
  9950. (I3 ^predict-no N971 + :O )
  9951. Firing apply*operator*complete
  9952. -->
  9953. (I3 ^predict-yes N970 - :O )
  9954. inner elaboration loop at bottom goal.
  9955. --- Change Working Memory (PE) ---
  9956. =>WM: (13625: I3 ^predict-no N971)
  9957. <=WM: (13612: N970 ^status complete)
  9958. <=WM: (13611: I3 ^predict-yes N970)
  9959. --- Firing Productions (IE) For State At Depth 1 ---
  9960. --- Inner Elaboration Phase, active level 1 (S1) ---
  9961. Firing monitor*world
  9962. -->
  9963. I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
  9964. --- Change Working Memory (IE) ---
  9965. --- END Application Phase ---
  9966. --- Output Phase ---
  9967. ENV: Agent did: predict-no for direction U in state State-A
  9968. In State-A moving U
  9969. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  9970. predict error 0
  9971. dir: dir isR
  9972. --- END Output Phase ---
  9973. \--- Input Phase ---
  9974. =>WM: (13629: I2 ^dir R)
  9975. =>WM: (13628: I2 ^reward 1)
  9976. =>WM: (13627: I2 ^see 0)
  9977. =>WM: (13626: N971 ^status complete)
  9978. <=WM: (13615: I2 ^dir U)
  9979. <=WM: (13614: I2 ^reward 1)
  9980. <=WM: (13613: I2 ^see 1)
  9981. =>WM: (13630: I2 ^level-1 L1-root)
  9982. <=WM: (13616: I2 ^level-1 L1-root)
  9983. --- END Input Phase ---
  9984. --- Proposal Phase ---
  9985. --- Inner Elaboration Phase, active level 1 (S1) ---
  9986. Firing rl*prefer*rvt*predict-yes*H0*5*H1*18
  9987. -->
  9988. (S1 ^operator O1941 = 0.9322240569345275)
  9989. Firing rl*prefer*rvt*predict-no*H0*6*H1*21
  9990. -->
  9991. (S1 ^operator O1942 = -0.006920940195066783)
  9992. Firing prefer*rvt*predict-no*H0*6*H1
  9993. -->
  9994. Firing prefer*rvt*predict-yes*H0*5*H1
  9995. -->
  9996. Firing elaborate*copy-see-to-output-link
  9997. -->
  9998. (I3 ^see 0 +)
  9999. Firing elaborate*reward*based*on*reward
  10000. -->
  10001. (R975 ^value 1 +)
  10002. (R1 ^reward R975 +)
  10003. Firing propose*predict-yes
  10004. -->
  10005. (O1943 ^name predict-yes +)
  10006. (S1 ^operator O1943 +)
  10007. Firing propose*predict-no
  10008. -->
  10009. (O1944 ^name predict-no +)
  10010. (S1 ^operator O1944 +)
  10011. Firing rl*prefer*rvt*predict-no*H0*6
  10012. -->
  10013. (S1 ^operator O1942 = 0.4643592423920161)
  10014. Firing rl*prefer*rvt*predict-yes*H0*5
  10015. -->
  10016. (S1 ^operator O1941 = 0.06777560354598866)
  10017. Firing prefer*rvt*predict-yes*H0
  10018. -->
  10019. Firing prefer*rvt*predict-no*H0
  10020. -->
  10021. Firing elaborate*copy-dir-to-output-link
  10022. -->
  10023. (I3 ^dir R +)
  10024. inner elaboration loop at bottom goal.
  10025. Retracting elaborate*copy-see-to-output-link
  10026. -->
  10027. (I3 ^see 1 +)
  10028. Retracting propose*predict-no
  10029. -->
  10030. (O1942 ^name predict-no +)
  10031. (S1 ^operator O1942 +)
  10032. Retracting propose*predict-yes
  10033. -->
  10034. (O1941 ^name predict-yes +)
  10035. (S1 ^operator O1941 +)
  10036. Retracting elaborate*reward*based*on*reward
  10037. -->
  10038. (R974 ^value 1 +)
  10039. (R1 ^reward R974 +)
  10040. Retracting elaborate*copy-dir-to-output-link
  10041. -->
  10042. (I3 ^dir U +)
  10043. Retracting rl*prefer*rvt*predict-no*H0*2
  10044. -->
  10045. (S1 ^operator O1942 = 0.9999999999999999)
  10046. Retracting rl*prefer*rvt*predict-yes*H0*1
  10047. -->
  10048. (S1 ^operator O1941 = 0.)
  10049. =>WM: (13638: S1 ^operator O1944 +)
  10050. =>WM: (13637: S1 ^operator O1943 +)
  10051. =>WM: (13636: I3 ^dir R)
  10052. =>WM: (13635: O1944 ^name predict-no)
  10053. =>WM: (13634: O1943 ^name predict-yes)
  10054. =>WM: (13633: R975 ^value 1)
  10055. =>WM: (13632: R1 ^reward R975)
  10056. =>WM: (13631: I3 ^see 0)
  10057. <=WM: (13622: S1 ^operator O1941 +)
  10058. <=WM: (13623: S1 ^operator O1942 +)
  10059. <=WM: (13624: S1 ^operator O1942)
  10060. <=WM: (13621: I3 ^dir U)
  10061. <=WM: (13617: R1 ^reward R974)
  10062. <=WM: (13602: I3 ^see 1)
  10063. <=WM: (13620: O1942 ^name predict-no)
  10064. <=WM: (13619: O1941 ^name predict-yes)
  10065. <=WM: (13618: R974 ^value 1)
  10066. --- Inner Elaboration Phase, active level 1 (S1) ---
  10067. Firing prefer*rvt*predict-yes*H0
  10068. -->
  10069. Firing rl*prefer*rvt*predict-yes*H0*5*H1*18
  10070. -->
  10071. (S1 ^operator O1943 = 0.9322240569345275)
  10072. Firing rl*prefer*rvt*predict-yes*H0*5
  10073. -->
  10074. (S1 ^operator O1943 = 0.06777560354598866)
  10075. Firing prefer*rvt*predict-yes*H0*5*H1
  10076. -->
  10077. Firing prefer*rvt*predict-no*H0
  10078. -->
  10079. Firing rl*prefer*rvt*predict-no*H0*6*H1*21
  10080. -->
  10081. (S1 ^operator O1944 = -0.006920940195066783)
  10082. Firing rl*prefer*rvt*predict-no*H0*6
  10083. -->
  10084. (S1 ^operator O1944 = 0.4643592423920161)
  10085. Firing prefer*rvt*predict-no*H0*6*H1
  10086. -->
  10087. inner elaboration loop at bottom goal.
  10088. Retracting rl*prefer*rvt*predict-no*H0*6
  10089. -->
  10090. (S1 ^operator O1942 = 0.4643592423920161)
  10091. Retracting rl*prefer*rvt*predict-no*H0*6*H1*21
  10092. -->
  10093. (S1 ^operator O1942 = -0.006920940195066783)
  10094. Retracting rl*prefer*rvt*predict-yes*H0*5
  10095. -->
  10096. (S1 ^operator O1941 = 0.06777560354598866)
  10097. Retracting rl*prefer*rvt*predict-yes*H0*5*H1*18
  10098. -->
  10099. (S1 ^operator O1941 = 0.9322240569345275)
  10100. --- END Proposal Phase ---
  10101. --- Decision Phase ---
  10102. RL update rl*prefer*rvt*predict-no*H0*2 1 0 1 -> 1 0 1(R,m,v=1,1,0)
  10103. =>WM: (13639: S1 ^operator O1943)
  10104. 972: O: O1943 (predict-yes)
  10105. --- END Decision Phase ---
  10106. --- Application Phase ---
  10107. --- Firing Productions (PE) For State At Depth 1 ---
  10108. --- Inner Elaboration Phase, active level 1 (S1) ---
  10109. Firing apply*operator
  10110. -->
  10111. (I3 ^predict-yes N972 + :O )
  10112. Firing apply*operator*complete
  10113. -->
  10114. (I3 ^predict-no N971 - :O )
  10115. inner elaboration loop at bottom goal.
  10116. --- Change Working Memory (PE) ---
  10117. =>WM: (13640: I3 ^predict-yes N972)
  10118. <=WM: (13626: N971 ^status complete)
  10119. <=WM: (13625: I3 ^predict-no N971)
  10120. --- Firing Productions (IE) For State At Depth 1 ---
  10121. --- Inner Elaboration Phase, active level 1 (S1) ---
  10122. Firing monitor*world
  10123. -->
  10124. I see 1 and I'm going to do: predict-yes inner elaboration loop at bottom goal.
  10125. --- Change Working Memory (IE) ---
  10126. --- END Application Phase ---
  10127. --- Output Phase ---
  10128. ENV: Agent did: predict-yes for direction R in state State-A
  10129. In State-A moving R
  10130. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  10131. predict error 0
  10132. dir: dir isU
  10133. --- END Output Phase ---
  10134. -/|--- Input Phase ---
  10135. =>WM: (13644: I2 ^dir U)
  10136. =>WM: (13643: I2 ^reward 1)
  10137. =>WM: (13642: I2 ^see 1)
  10138. =>WM: (13641: N972 ^status complete)
  10139. <=WM: (13629: I2 ^dir R)
  10140. <=WM: (13628: I2 ^reward 1)
  10141. <=WM: (13627: I2 ^see 0)
  10142. =>WM: (13645: I2 ^level-1 R1-root)
  10143. <=WM: (13630: I2 ^level-1 L1-root)
  10144. --- END Input Phase ---
  10145. --- Proposal Phase ---
  10146. --- Inner Elaboration Phase, active level 1 (S1) ---
  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*2
  10163. -->
  10164. (S1 ^operator O1944 = 0.9999999999999999)
  10165. Firing rl*prefer*rvt*predict-yes*H0*1
  10166. -->
  10167. (S1 ^operator O1943 = 0.)
  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 U +)
  10175. inner elaboration loop at bottom goal.
  10176. Retracting elaborate*copy-see-to-output-link
  10177. -->
  10178. (I3 ^see 0 +)
  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*6
  10195. -->
  10196. (S1 ^operator O1944 = 0.4643592423920161)
  10197. Retracting rl*prefer*rvt*predict-no*H0*6*H1*21
  10198. -->
  10199. (S1 ^operator O1944 = -0.006920940195066783)
  10200. Retracting rl*prefer*rvt*predict-yes*H0*5
  10201. -->
  10202. (S1 ^operator O1943 = 0.06777560354598866)
  10203. Retracting rl*prefer*rvt*predict-yes*H0*5*H1*18
  10204. -->
  10205. (S1 ^operator O1943 = 0.9322240569345275)
  10206. =>WM: (13653: S1 ^operator O1946 +)
  10207. =>WM: (13652: S1 ^operator O1945 +)
  10208. =>WM: (13651: I3 ^dir U)
  10209. =>WM: (13650: O1946 ^name predict-no)
  10210. =>WM: (13649: O1945 ^name predict-yes)
  10211. =>WM: (13648: R976 ^value 1)
  10212. =>WM: (13647: R1 ^reward R976)
  10213. =>WM: (13646: I3 ^see 1)
  10214. <=WM: (13637: S1 ^operator O1943 +)
  10215. <=WM: (13639: S1 ^operator O1943)
  10216. <=WM: (13638: S1 ^operator O1944 +)
  10217. <=WM: (13636: I3 ^dir R)
  10218. <=WM: (13632: R1 ^reward R975)
  10219. <=WM: (13631: I3 ^see 0)
  10220. <=WM: (13635: O1944 ^name predict-no)
  10221. <=WM: (13634: O1943 ^name predict-yes)
  10222. <=WM: (13633: R975 ^value 1)
  10223. --- Inner Elaboration Phase, active level 1 (S1) ---
  10224. Firing prefer*rvt*predict-yes*H0
  10225. -->
  10226. Firing rl*prefer*rvt*predict-yes*H0*1
  10227. -->
  10228. (S1 ^operator O1945 = 0.)
  10229. Firing prefer*rvt*predict-no*H0
  10230. -->
  10231. Firing rl*prefer*rvt*predict-no*H0*2
  10232. -->
  10233. (S1 ^operator O1946 = 0.9999999999999999)
  10234. inner elaboration loop at bottom goal.
  10235. Retracting rl*prefer*rvt*predict-no*H0*2
  10236. -->
  10237. (S1 ^operator O1944 = 0.9999999999999999)
  10238. Retracting rl*prefer*rvt*predict-yes*H0*1
  10239. -->
  10240. (S1 ^operator O1943 = 0.)
  10241. --- END Proposal Phase ---
  10242. --- Decision Phase ---
  10243. RL update rl*prefer*rvt*predict-yes*H0*5 0.606208 -0.538432 0.0677756 -> 0.606208 -0.538432 0.0677757(R,m,v=1,0.870056,0.113701)
  10244. RL update rl*prefer*rvt*predict-yes*H0*5*H1*18 0.393792 0.538433 0.932224 -> 0.393792 0.538432 0.932224(R,m,v=1,1,0)
  10245. =>WM: (13654: S1 ^operator O1946)
  10246. 973: O: O1946 (predict-no)
  10247. --- END Decision Phase ---
  10248. --- Application Phase ---
  10249. --- Firing Productions (PE) For State At Depth 1 ---
  10250. --- Inner Elaboration Phase, active level 1 (S1) ---
  10251. Firing apply*operator
  10252. -->
  10253. (I3 ^predict-no N973 + :O )
  10254. Firing apply*operator*complete
  10255. -->
  10256. (I3 ^predict-yes N972 - :O )
  10257. inner elaboration loop at bottom goal.
  10258. --- Change Working Memory (PE) ---
  10259. =>WM: (13655: I3 ^predict-no N973)
  10260. <=WM: (13641: N972 ^status complete)
  10261. <=WM: (13640: I3 ^predict-yes N972)
  10262. --- Firing Productions (IE) For State At Depth 1 ---
  10263. --- Inner Elaboration Phase, active level 1 (S1) ---
  10264. Firing monitor*world
  10265. -->
  10266. I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
  10267. --- Change Working Memory (IE) ---
  10268. --- END Application Phase ---
  10269. --- Output Phase ---
  10270. ENV: Agent did: predict-no for direction U in state State-B
  10271. In State-B moving U
  10272. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  10273. predict error 0
  10274. dir: dir isL
  10275. --- END Output Phase ---
  10276. \-/--- Input Phase ---
  10277. =>WM: (13659: I2 ^dir L)
  10278. =>WM: (13658: I2 ^reward 1)
  10279. =>WM: (13657: I2 ^see 0)
  10280. =>WM: (13656: N973 ^status complete)
  10281. <=WM: (13644: I2 ^dir U)
  10282. <=WM: (13643: I2 ^reward 1)
  10283. <=WM: (13642: I2 ^see 1)
  10284. =>WM: (13660: I2 ^level-1 R1-root)
  10285. <=WM: (13645: I2 ^level-1 R1-root)
  10286. --- END Input Phase ---
  10287. --- Proposal Phase ---
  10288. --- Inner Elaboration Phase, active level 1 (S1) ---
  10289. Firing rl*prefer*rvt*predict-no*H0*4*H1*16
  10290. -->
  10291. (S1 ^operator O1946 = -0.2383263875547442)
  10292. Firing rl*prefer*rvt*predict-yes*H0*3*H1*17
  10293. -->
  10294. (S1 ^operator O1945 = 0.3930674782554692)
  10295. Firing prefer*rvt*predict-no*H0*4*H1
  10296. -->
  10297. Firing prefer*rvt*predict-yes*H0*3*H1
  10298. -->
  10299. Firing elaborate*copy-see-to-output-link
  10300. -->
  10301. (I3 ^see 0 +)
  10302. Firing elaborate*reward*based*on*reward
  10303. -->
  10304. (R977 ^value 1 +)
  10305. (R1 ^reward R977 +)
  10306. Firing propose*predict-yes
  10307. -->
  10308. (O1947 ^name predict-yes +)
  10309. (S1 ^operator O1947 +)
  10310. Firing propose*predict-no
  10311. -->
  10312. (O1948 ^name predict-no +)
  10313. (S1 ^operator O1948 +)
  10314. Firing rl*prefer*rvt*predict-no*H0*4
  10315. -->
  10316. (S1 ^operator O1946 = 0.4334972553258731)
  10317. Firing rl*prefer*rvt*predict-yes*H0*3
  10318. -->
  10319. (S1 ^operator O1945 = 0.6069241857222759)
  10320. Firing prefer*rvt*predict-yes*H0
  10321. -->
  10322. Firing prefer*rvt*predict-no*H0
  10323. -->
  10324. Firing elaborate*copy-dir-to-output-link
  10325. -->
  10326. (I3 ^dir L +)
  10327. inner elaboration loop at bottom goal.
  10328. Retracting elaborate*copy-see-to-output-link
  10329. -->
  10330. (I3 ^see 1 +)
  10331. Retracting propose*predict-no
  10332. -->
  10333. (O1946 ^name predict-no +)
  10334. (S1 ^operator O1946 +)
  10335. Retracting propose*predict-yes
  10336. -->
  10337. (O1945 ^name predict-yes +)
  10338. (S1 ^operator O1945 +)
  10339. Retracting elaborate*reward*based*on*reward
  10340. -->
  10341. (R976 ^value 1 +)
  10342. (R1 ^reward R976 +)
  10343. Retracting elaborate*copy-dir-to-output-link
  10344. -->
  10345. (I3 ^dir U +)
  10346. Retracting rl*prefer*rvt*predict-no*H0*2
  10347. -->
  10348. (S1 ^operator O1946 = 0.9999999999999999)
  10349. Retracting rl*prefer*rvt*predict-yes*H0*1
  10350. -->
  10351. (S1 ^operator O1945 = 0.)
  10352. =>WM: (13668: S1 ^operator O1948 +)
  10353. =>WM: (13667: S1 ^operator O1947 +)
  10354. =>WM: (13666: I3 ^dir L)
  10355. =>WM: (13665: O1948 ^name predict-no)
  10356. =>WM: (13664: O1947 ^name predict-yes)
  10357. =>WM: (13663: R977 ^value 1)
  10358. =>WM: (13662: R1 ^reward R977)
  10359. =>WM: (13661: I3 ^see 0)
  10360. <=WM: (13652: S1 ^operator O1945 +)
  10361. <=WM: (13653: S1 ^operator O1946 +)
  10362. <=WM: (13654: S1 ^operator O1946)
  10363. <=WM: (13651: I3 ^dir U)
  10364. <=WM: (13647: R1 ^reward R976)
  10365. <=WM: (13646: I3 ^see 1)
  10366. <=WM: (13650: O1946 ^name predict-no)
  10367. <=WM: (13649: O1945 ^name predict-yes)
  10368. <=WM: (13648: R976 ^value 1)
  10369. --- Inner Elaboration Phase, active level 1 (S1) ---
  10370. Firing prefer*rvt*predict-yes*H0
  10371. -->
  10372. Firing rl*prefer*rvt*predict-yes*H0*3*H1*17
  10373. -->
  10374. (S1 ^operator O1947 = 0.3930674782554692)
  10375. Firing rl*prefer*rvt*predict-yes*H0*3
  10376. -->
  10377. (S1 ^operator O1947 = 0.6069241857222759)
  10378. Firing prefer*rvt*predict-yes*H0*3*H1
  10379. -->
  10380. Firing prefer*rvt*predict-no*H0
  10381. -->
  10382. Firing rl*prefer*rvt*predict-no*H0*4*H1*16
  10383. -->
  10384. (S1 ^operator O1948 = -0.2383263875547442)
  10385. Firing rl*prefer*rvt*predict-no*H0*4
  10386. -->
  10387. (S1 ^operator O1948 = 0.4334972553258731)
  10388. Firing prefer*rvt*predict-no*H0*4*H1
  10389. -->
  10390. inner elaboration loop at bottom goal.
  10391. Retracting rl*prefer*rvt*predict-no*H0*4
  10392. -->
  10393. (S1 ^operator O1946 = 0.4334972553258731)
  10394. Retracting rl*prefer*rvt*predict-no*H0*4*H1*16
  10395. -->
  10396. (S1 ^operator O1946 = -0.2383263875547442)
  10397. Retracting rl*prefer*rvt*predict-yes*H0*3
  10398. -->
  10399. (S1 ^operator O1945 = 0.6069241857222759)
  10400. Retracting rl*prefer*rvt*predict-yes*H0*3*H1*17
  10401. -->
  10402. (S1 ^operator O1945 = 0.3930674782554692)
  10403. --- END Proposal Phase ---
  10404. --- Decision Phase ---
  10405. RL update rl*prefer*rvt*predict-no*H0*2 1 0 1 -> 1 0 1(R,m,v=1,1,0)
  10406. =>WM: (13669: S1 ^operator O1947)
  10407. 974: O: O1947 (predict-yes)
  10408. --- END Decision Phase ---
  10409. --- Application Phase ---
  10410. --- Firing Productions (PE) For State At Depth 1 ---
  10411. --- Inner Elaboration Phase, active level 1 (S1) ---
  10412. Firing apply*operator
  10413. -->
  10414. (I3 ^predict-yes N974 + :O )
  10415. Firing apply*operator*complete
  10416. -->
  10417. (I3 ^predict-no N973 - :O )
  10418. inner elaboration loop at bottom goal.
  10419. --- Change Working Memory (PE) ---
  10420. =>WM: (13670: I3 ^predict-yes N974)
  10421. <=WM: (13656: N973 ^status complete)
  10422. <=WM: (13655: I3 ^predict-no N973)
  10423. --- Firing Productions (IE) For State At Depth 1 ---
  10424. --- Inner Elaboration Phase, active level 1 (S1) ---
  10425. Firing monitor*world
  10426. -->
  10427. I see 1 and I'm going to do: predict-yes inner elaboration loop at bottom goal.
  10428. --- Change Working Memory (IE) ---
  10429. --- END Application Phase ---
  10430. --- Output Phase ---
  10431. ENV: Agent did: predict-yes for direction L in state State-B
  10432. In State-B moving L
  10433. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  10434. predict error 0
  10435. dir: dir isL
  10436. --- END Output Phase ---
  10437. |\---- Input Phase ---
  10438. =>WM: (13674: I2 ^dir L)
  10439. =>WM: (13673: I2 ^reward 1)
  10440. =>WM: (13672: I2 ^see 1)
  10441. =>WM: (13671: N974 ^status complete)
  10442. <=WM: (13659: I2 ^dir L)
  10443. <=WM: (13658: I2 ^reward 1)
  10444. <=WM: (13657: I2 ^see 0)
  10445. =>WM: (13675: I2 ^level-1 L1-root)
  10446. <=WM: (13660: I2 ^level-1 R1-root)
  10447. --- END Input Phase ---
  10448. --- Proposal Phase ---
  10449. --- Inner Elaboration Phase, active level 1 (S1) ---
  10450. Firing rl*prefer*rvt*predict-yes*H0*3*H1*11
  10451. -->
  10452. (S1 ^operator O1947 = -0.03517433757196466)
  10453. Firing rl*prefer*rvt*predict-no*H0*4*H1*10
  10454. -->
  10455. (S1 ^operator O1948 = 0.56650835693627)
  10456. Firing prefer*rvt*predict-no*H0*4*H1
  10457. -->
  10458. Firing prefer*rvt*predict-yes*H0*3*H1
  10459. -->
  10460. Firing elaborate*copy-see-to-output-link
  10461. -->
  10462. (I3 ^see 1 +)
  10463. Firing elaborate*reward*based*on*reward
  10464. -->
  10465. (R978 ^value 1 +)
  10466. (R1 ^reward R978 +)
  10467. Firing propose*predict-yes
  10468. -->
  10469. (O1949 ^name predict-yes +)
  10470. (S1 ^operator O1949 +)
  10471. Firing propose*predict-no
  10472. -->
  10473. (O1950 ^name predict-no +)
  10474. (S1 ^operator O1950 +)
  10475. Firing rl*prefer*rvt*predict-no*H0*4
  10476. -->
  10477. (S1 ^operator O1948 = 0.4334972553258731)
  10478. Firing rl*prefer*rvt*predict-yes*H0*3
  10479. -->
  10480. (S1 ^operator O1947 = 0.6069241857222759)
  10481. Firing prefer*rvt*predict-yes*H0
  10482. -->
  10483. Firing prefer*rvt*predict-no*H0
  10484. -->
  10485. Firing elaborate*copy-dir-to-output-link
  10486. -->
  10487. (I3 ^dir L +)
  10488. inner elaboration loop at bottom goal.
  10489. Retracting elaborate*copy-see-to-output-link
  10490. -->
  10491. (I3 ^see 0 +)
  10492. Retracting propose*predict-no
  10493. -->
  10494. (O1948 ^name predict-no +)
  10495. (S1 ^operator O1948 +)
  10496. Retracting propose*predict-yes
  10497. -->
  10498. (O1947 ^name predict-yes +)
  10499. (S1 ^operator O1947 +)
  10500. Retracting elaborate*reward*based*on*reward
  10501. -->
  10502. (R977 ^value 1 +)
  10503. (R1 ^reward R977 +)
  10504. Retracting elaborate*copy-dir-to-output-link
  10505. -->
  10506. (I3 ^dir L +)
  10507. Retracting rl*prefer*rvt*predict-no*H0*4
  10508. -->
  10509. (S1 ^operator O1948 = 0.4334972553258731)
  10510. Retracting rl*prefer*rvt*predict-no*H0*4*H1*16
  10511. -->
  10512. (S1 ^operator O1948 = -0.2383263875547442)
  10513. Retracting rl*prefer*rvt*predict-yes*H0*3
  10514. -->
  10515. (S1 ^operator O1947 = 0.6069241857222759)
  10516. Retracting rl*prefer*rvt*predict-yes*H0*3*H1*17
  10517. -->
  10518. (S1 ^operator O1947 = 0.3930674782554692)
  10519. =>WM: (13682: S1 ^operator O1950 +)
  10520. =>WM: (13681: S1 ^operator O1949 +)
  10521. =>WM: (13680: O1950 ^name predict-no)
  10522. =>WM: (13679: O1949 ^name predict-yes)
  10523. =>WM: (13678: R978 ^value 1)
  10524. =>WM: (13677: R1 ^reward R978)
  10525. =>WM: (13676: I3 ^see 1)
  10526. <=WM: (13667: S1 ^operator O1947 +)
  10527. <=WM: (13669: S1 ^operator O1947)
  10528. <=WM: (13668: S1 ^operator O1948 +)
  10529. <=WM: (13662: R1 ^reward R977)
  10530. <=WM: (13661: I3 ^see 0)
  10531. <=WM: (13665: O1948 ^name predict-no)
  10532. <=WM: (13664: O1947 ^name predict-yes)
  10533. <=WM: (13663: R977 ^value 1)
  10534. --- Inner Elaboration Phase, active level 1 (S1) ---
  10535. Firing prefer*rvt*predict-yes*H0
  10536. -->
  10537. Firing rl*prefer*rvt*predict-yes*H0*3
  10538. -->
  10539. (S1 ^operator O1949 = 0.6069241857222759)
  10540. Firing prefer*rvt*predict-yes*H0*3*H1
  10541. -->
  10542. Firing rl*prefer*rvt*predict-yes*H0*3*H1*11
  10543. -->
  10544. (S1 ^operator O1949 = -0.03517433757196466)
  10545. Firing prefer*rvt*predict-no*H0
  10546. -->
  10547. Firing rl*prefer*rvt*predict-no*H0*4
  10548. -->
  10549. (S1 ^operator O1950 = 0.4334972553258731)
  10550. Firing prefer*rvt*predict-no*H0*4*H1
  10551. -->
  10552. Firing rl*prefer*rvt*predict-no*H0*4*H1*10
  10553. -->
  10554. (S1 ^operator O1950 = 0.56650835693627)
  10555. inner elaboration loop at bottom goal.
  10556. Retracting rl*prefer*rvt*predict-no*H0*4
  10557. -->
  10558. (S1 ^operator O1948 = 0.4334972553258731)
  10559. Retracting rl*prefer*rvt*predict-no*H0*4*H1*10
  10560. -->
  10561. (S1 ^operator O1948 = 0.56650835693627)
  10562. Retracting rl*prefer*rvt*predict-yes*H0*3
  10563. -->
  10564. (S1 ^operator O1947 = 0.6069241857222759)
  10565. Retracting rl*prefer*rvt*predict-yes*H0*3*H1*11
  10566. -->
  10567. (S1 ^operator O1947 = -0.03517433757196466)
  10568. --- END Proposal Phase ---
  10569. --- Decision Phase ---
  10570. RL update rl*prefer*rvt*predict-yes*H0*3 0.656145 -0.0492204 0.606924 -> 0.656146 -0.0492203 0.606925(R,m,v=1,0.946309,0.0511518)
  10571. RL update rl*prefer*rvt*predict-yes*H0*3*H1*17 0.343847 0.0492201 0.393067 -> 0.343849 0.0492201 0.393069(R,m,v=1,1,0)
  10572. =>WM: (13683: S1 ^operator O1950)
  10573. 975: O: O1950 (predict-no)
  10574. --- END Decision Phase ---
  10575. --- Application Phase ---
  10576. --- Firing Productions (PE) For State At Depth 1 ---
  10577. --- Inner Elaboration Phase, active level 1 (S1) ---
  10578. Firing apply*operator
  10579. -->
  10580. (I3 ^predict-no N975 + :O )
  10581. Firing apply*operator*complete
  10582. -->
  10583. (I3 ^predict-yes N974 - :O )
  10584. inner elaboration loop at bottom goal.
  10585. --- Change Working Memory (PE) ---
  10586. =>WM: (13684: I3 ^predict-no N975)
  10587. <=WM: (13671: N974 ^status complete)
  10588. <=WM: (13670: I3 ^predict-yes N974)
  10589. --- Firing Productions (IE) For State At Depth 1 ---
  10590. --- Inner Elaboration Phase, active level 1 (S1) ---
  10591. Firing monitor*world
  10592. -->
  10593. I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
  10594. --- Change Working Memory (IE) ---
  10595. --- END Application Phase ---
  10596. --- Output Phase ---
  10597. ENV: Agent did: predict-no for direction L in state State-A
  10598. In State-A moving L
  10599. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  10600. predict error 0
  10601. dir: dir isU
  10602. --- END Output Phase ---
  10603. /|\--- Input Phase ---
  10604. =>WM: (13688: I2 ^dir U)
  10605. =>WM: (13687: I2 ^reward 1)
  10606. =>WM: (13686: I2 ^see 0)
  10607. =>WM: (13685: N975 ^status complete)
  10608. <=WM: (13674: I2 ^dir L)
  10609. <=WM: (13673: I2 ^reward 1)
  10610. <=WM: (13672: I2 ^see 1)
  10611. =>WM: (13689: I2 ^level-1 L0-root)
  10612. <=WM: (13675: I2 ^level-1 L1-root)
  10613. --- END Input Phase ---
  10614. --- Proposal Phase ---
  10615. --- Inner Elaboration Phase, active level 1 (S1) ---
  10616. Firing elaborate*copy-see-to-output-link
  10617. -->
  10618. (I3 ^see 0 +)
  10619. Firing elaborate*reward*based*on*reward
  10620. -->
  10621. (R979 ^value 1 +)
  10622. (R1 ^reward R979 +)
  10623. Firing propose*predict-yes
  10624. -->
  10625. (O1951 ^name predict-yes +)
  10626. (S1 ^operator O1951 +)
  10627. Firing propose*predict-no
  10628. -->
  10629. (O1952 ^name predict-no +)
  10630. (S1 ^operator O1952 +)
  10631. Firing rl*prefer*rvt*predict-no*H0*2
  10632. -->
  10633. (S1 ^operator O1950 = 0.9999999999999999)
  10634. Firing rl*prefer*rvt*predict-yes*H0*1
  10635. -->
  10636. (S1 ^operator O1949 = 0.)
  10637. Firing prefer*rvt*predict-yes*H0
  10638. -->
  10639. Firing prefer*rvt*predict-no*H0
  10640. -->
  10641. Firing elaborate*copy-dir-to-output-link
  10642. -->
  10643. (I3 ^dir U +)
  10644. inner elaboration loop at bottom goal.
  10645. Retracting elaborate*copy-see-to-output-link
  10646. -->
  10647. (I3 ^see 1 +)
  10648. Retracting propose*predict-no
  10649. -->
  10650. (O1950 ^name predict-no +)
  10651. (S1 ^operator O1950 +)
  10652. Retracting propose*predict-yes
  10653. -->
  10654. (O1949 ^name predict-yes +)
  10655. (S1 ^operator O1949 +)
  10656. Retracting elaborate*reward*based*on*reward
  10657. -->
  10658. (R978 ^value 1 +)
  10659. (R1 ^reward R978 +)
  10660. Retracting elaborate*copy-dir-to-output-link
  10661. -->
  10662. (I3 ^dir L +)
  10663. Retracting rl*prefer*rvt*predict-no*H0*4*H1*10
  10664. -->
  10665. (S1 ^operator O1950 = 0.56650835693627)
  10666. Retracting rl*prefer*rvt*predict-no*H0*4
  10667. -->
  10668. (S1 ^operator O1950 = 0.4334972553258731)
  10669. Retracting rl*prefer*rvt*predict-yes*H0*3*H1*11
  10670. -->
  10671. (S1 ^operator O1949 = -0.03517433757196466)
  10672. Retracting rl*prefer*rvt*predict-yes*H0*3
  10673. -->
  10674. (S1 ^operator O1949 = 0.6069254361256142)
  10675. =>WM: (13697: S1 ^operator O1952 +)
  10676. =>WM: (13696: S1 ^operator O1951 +)
  10677. =>WM: (13695: I3 ^dir U)
  10678. =>WM: (13694: O1952 ^name predict-no)
  10679. =>WM: (13693: O1951 ^name predict-yes)
  10680. =>WM: (13692: R979 ^value 1)
  10681. =>WM: (13691: R1 ^reward R979)
  10682. =>WM: (13690: I3 ^see 0)
  10683. <=WM: (13681: S1 ^operator O1949 +)
  10684. <=WM: (13682: S1 ^operator O1950 +)
  10685. <=WM: (13683: S1 ^operator O1950)
  10686. <=WM: (13666: I3 ^dir L)
  10687. <=WM: (13677: R1 ^reward R978)
  10688. <=WM: (13676: I3 ^see 1)
  10689. <=WM: (13680: O1950 ^name predict-no)
  10690. <=WM: (13679: O1949 ^name predict-yes)
  10691. <=WM: (13678: R978 ^value 1)
  10692. --- Inner Elaboration Phase, active level 1 (S1) ---
  10693. Firing prefer*rvt*predict-yes*H0
  10694. -->
  10695. Firing rl*prefer*rvt*predict-yes*H0*1
  10696. -->
  10697. (S1 ^operator O1951 = 0.)
  10698. Firing prefer*rvt*predict-no*H0
  10699. -->
  10700. Firing rl*prefer*rvt*predict-no*H0*2
  10701. -->
  10702. (S1 ^operator O1952 = 0.9999999999999999)
  10703. inner elaboration loop at bottom goal.
  10704. Retracting rl*prefer*rvt*predict-no*H0*2
  10705. -->
  10706. (S1 ^operator O1950 = 0.9999999999999999)
  10707. Retracting rl*prefer*rvt*predict-yes*H0*1
  10708. -->
  10709. (S1 ^operator O1949 = 0.)
  10710. --- END Proposal Phase ---
  10711. --- Decision Phase ---
  10712. RL update rl*prefer*rvt*predict-no*H0*4 0.490213 -0.056716 0.433497 -> 0.490212 -0.056716 0.433496(R,m,v=1,0.886076,0.101588)
  10713. RL update rl*prefer*rvt*predict-no*H0*4*H1*10 0.509792 0.056716 0.566508 -> 0.509791 0.056716 0.566508(R,m,v=1,1,0)
  10714. =>WM: (13698: S1 ^operator O1952)
  10715. 976: O: O1952 (predict-no)
  10716. --- END Decision Phase ---
  10717. --- Application Phase ---
  10718. --- Firing Productions (PE) For State At Depth 1 ---
  10719. --- Inner Elaboration Phase, active level 1 (S1) ---
  10720. Firing apply*operator
  10721. -->
  10722. (I3 ^predict-no N976 + :O )
  10723. Firing apply*operator*complete
  10724. -->
  10725. (I3 ^predict-no N975 - :O )
  10726. inner elaboration loop at bottom goal.
  10727. --- Change Working Memory (PE) ---
  10728. =>WM: (13699: I3 ^predict-no N976)
  10729. <=WM: (13685: N975 ^status complete)
  10730. <=WM: (13684: I3 ^predict-no N975)
  10731. --- Firing Productions (IE) For State At Depth 1 ---
  10732. --- Inner Elaboration Phase, active level 1 (S1) ---
  10733. Firing monitor*world
  10734. -->
  10735. I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
  10736. --- Change Working Memory (IE) ---
  10737. --- END Application Phase ---
  10738. --- Output Phase ---
  10739. ENV: Agent did: predict-no for direction U in state State-A
  10740. In State-A moving U
  10741. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  10742. predict error 0
  10743. dir: dir isL
  10744. --- END Output Phase ---
  10745. -/--- Input Phase ---
  10746. =>WM: (13703: I2 ^dir L)
  10747. =>WM: (13702: I2 ^reward 1)
  10748. =>WM: (13701: I2 ^see 0)
  10749. =>WM: (13700: N976 ^status complete)
  10750. <=WM: (13688: I2 ^dir U)
  10751. <=WM: (13687: I2 ^reward 1)
  10752. <=WM: (13686: I2 ^see 0)
  10753. =>WM: (13704: I2 ^level-1 L0-root)
  10754. <=WM: (13689: I2 ^level-1 L0-root)
  10755. --- END Input Phase ---
  10756. --- Proposal Phase ---
  10757. --- Inner Elaboration Phase, active level 1 (S1) ---
  10758. Firing rl*prefer*rvt*predict-yes*H0*3*H1*13
  10759. -->
  10760. (S1 ^operator O1951 = 0.07203)
  10761. Firing rl*prefer*rvt*predict-no*H0*4*H1*12
  10762. -->
  10763. (S1 ^operator O1952 = 0.5664921526005522)
  10764. Firing prefer*rvt*predict-no*H0*4*H1
  10765. -->
  10766. Firing prefer*rvt*predict-yes*H0*3*H1
  10767. -->
  10768. Firing elaborate*copy-see-to-output-link
  10769. -->
  10770. (I3 ^see 0 +)
  10771. Firing elaborate*reward*based*on*reward
  10772. -->
  10773. (R980 ^value 1 +)
  10774. (R1 ^reward R980 +)
  10775. Firing propose*predict-yes
  10776. -->
  10777. (O1953 ^name predict-yes +)
  10778. (S1 ^operator O1953 +)
  10779. Firing propose*predict-no
  10780. -->
  10781. (O1954 ^name predict-no +)
  10782. (S1 ^operator O1954 +)
  10783. Firing rl*prefer*rvt*predict-no*H0*4
  10784. -->
  10785. (S1 ^operator O1952 = 0.4334964134865517)
  10786. Firing rl*prefer*rvt*predict-yes*H0*3
  10787. -->
  10788. (S1 ^operator O1951 = 0.6069254361256142)
  10789. Firing prefer*rvt*predict-yes*H0
  10790. -->
  10791. Firing prefer*rvt*predict-no*H0
  10792. -->
  10793. Firing elaborate*copy-dir-to-output-link
  10794. -->
  10795. (I3 ^dir L +)
  10796. inner elaboration loop at bottom goal.
  10797. Retracting elaborate*copy-see-to-output-link
  10798. -->
  10799. (I3 ^see 0 +)
  10800. Retracting propose*predict-no
  10801. -->
  10802. (O1952 ^name predict-no +)
  10803. (S1 ^operator O1952 +)
  10804. Retracting propose*predict-yes
  10805. -->
  10806. (O1951 ^name predict-yes +)
  10807. (S1 ^operator O1951 +)
  10808. Retracting elaborate*reward*based*on*reward
  10809. -->
  10810. (R979 ^value 1 +)
  10811. (R1 ^reward R979 +)
  10812. Retracting elaborate*copy-dir-to-output-link
  10813. -->
  10814. (I3 ^dir U +)
  10815. Retracting rl*prefer*rvt*predict-no*H0*2
  10816. -->
  10817. (S1 ^operator O1952 = 0.9999999999999999)
  10818. Retracting rl*prefer*rvt*predict-yes*H0*1
  10819. -->
  10820. (S1 ^operator O1951 = 0.)
  10821. =>WM: (13711: S1 ^operator O1954 +)
  10822. =>WM: (13710: S1 ^operator O1953 +)
  10823. =>WM: (13709: I3 ^dir L)
  10824. =>WM: (13708: O1954 ^name predict-no)
  10825. =>WM: (13707: O1953 ^name predict-yes)
  10826. =>WM: (13706: R980 ^value 1)
  10827. =>WM: (13705: R1 ^reward R980)
  10828. <=WM: (13696: S1 ^operator O1951 +)
  10829. <=WM: (13697: S1 ^operator O1952 +)
  10830. <=WM: (13698: S1 ^operator O1952)
  10831. <=WM: (13695: I3 ^dir U)
  10832. <=WM: (13691: R1 ^reward R979)
  10833. <=WM: (13694: O1952 ^name predict-no)
  10834. <=WM: (13693: O1951 ^name predict-yes)
  10835. <=WM: (13692: R979 ^value 1)
  10836. --- Inner Elaboration Phase, active level 1 (S1) ---
  10837. Firing prefer*rvt*predict-yes*H0
  10838. -->
  10839. Firing rl*prefer*rvt*predict-yes*H0*3*H1*13
  10840. -->
  10841. (S1 ^operator O1953 = 0.07203)
  10842. Firing rl*prefer*rvt*predict-yes*H0*3
  10843. -->
  10844. (S1 ^operator O1953 = 0.6069254361256142)
  10845. Firing prefer*rvt*predict-yes*H0*3*H1
  10846. -->
  10847. Firing prefer*rvt*predict-no*H0
  10848. -->
  10849. Firing rl*prefer*rvt*predict-no*H0*4*H1*12
  10850. -->
  10851. (S1 ^operator O1954 = 0.5664921526005522)
  10852. Firing rl*prefer*rvt*predict-no*H0*4
  10853. -->
  10854. (S1 ^operator O1954 = 0.4334964134865517)
  10855. Firing prefer*rvt*predict-no*H0*4*H1
  10856. -->
  10857. inner elaboration loop at bottom goal.
  10858. Retracting rl*prefer*rvt*predict-no*H0*4
  10859. -->
  10860. (S1 ^operator O1952 = 0.4334964134865517)
  10861. Retracting rl*prefer*rvt*predict-no*H0*4*H1*12
  10862. -->
  10863. (S1 ^operator O1952 = 0.5664921526005522)
  10864. Retracting rl*prefer*rvt*predict-yes*H0*3
  10865. -->
  10866. (S1 ^operator O1951 = 0.6069254361256142)
  10867. Retracting rl*prefer*rvt*predict-yes*H0*3*H1*13
  10868. -->
  10869. (S1 ^operator O1951 = 0.07203)
  10870. --- END Proposal Phase ---
  10871. --- Decision Phase ---
  10872. RL update rl*prefer*rvt*predict-no*H0*2 1 0 1 -> 1 0 1(R,m,v=1,1,0)
  10873. =>WM: (13712: S1 ^operator O1954)
  10874. 977: O: O1954 (predict-no)
  10875. --- END Decision Phase ---
  10876. --- Application Phase ---
  10877. --- Firing Productions (PE) For State At Depth 1 ---
  10878. --- Inner Elaboration Phase, active level 1 (S1) ---
  10879. Firing apply*operator
  10880. -->
  10881. (I3 ^predict-no N977 + :O )
  10882. Firing apply*operator*complete
  10883. -->
  10884. (I3 ^predict-no N976 - :O )
  10885. inner elaboration loop at bottom goal.
  10886. --- Change Working Memory (PE) ---
  10887. =>WM: (13713: I3 ^predict-no N977)
  10888. <=WM: (13700: N976 ^status complete)
  10889. <=WM: (13699: I3 ^predict-no N976)
  10890. --- Firing Productions (IE) For State At Depth 1 ---
  10891. --- Inner Elaboration Phase, active level 1 (S1) ---
  10892. Firing monitor*world
  10893. -->
  10894. I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
  10895. --- Change Working Memory (IE) ---
  10896. --- END Application Phase ---
  10897. --- Output Phase ---
  10898. ENV: Agent did: predict-no for direction L in state State-A
  10899. In State-A moving L
  10900. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  10901. predict error 0
  10902. dir: dir isR
  10903. --- END Output Phase ---
  10904. |\---- Input Phase ---
  10905. =>WM: (13717: I2 ^dir R)
  10906. =>WM: (13716: I2 ^reward 1)
  10907. =>WM: (13715: I2 ^see 0)
  10908. =>WM: (13714: N977 ^status complete)
  10909. <=WM: (13703: I2 ^dir L)
  10910. <=WM: (13702: I2 ^reward 1)
  10911. <=WM: (13701: I2 ^see 0)
  10912. =>WM: (13718: I2 ^level-1 L0-root)
  10913. <=WM: (13704: I2 ^level-1 L0-root)
  10914. --- END Input Phase ---
  10915. --- Proposal Phase ---
  10916. --- Inner Elaboration Phase, active level 1 (S1) ---
  10917. Firing rl*prefer*rvt*predict-yes*H0*5*H1*14
  10918. -->
  10919. (S1 ^operator O1953 = 0.9322244609574057)
  10920. Firing rl*prefer*rvt*predict-no*H0*6*H1*19
  10921. -->
  10922. (S1 ^operator O1954 = 0.3)
  10923. Firing prefer*rvt*predict-no*H0*6*H1
  10924. -->
  10925. Firing prefer*rvt*predict-yes*H0*5*H1
  10926. -->
  10927. Firing elaborate*copy-see-to-output-link
  10928. -->
  10929. (I3 ^see 0 +)
  10930. Firing elaborate*reward*based*on*reward
  10931. -->
  10932. (R981 ^value 1 +)
  10933. (R1 ^reward R981 +)
  10934. Firing propose*predict-yes
  10935. -->
  10936. (O1955 ^name predict-yes +)
  10937. (S1 ^operator O1955 +)
  10938. Firing propose*predict-no
  10939. -->
  10940. (O1956 ^name predict-no +)
  10941. (S1 ^operator O1956 +)
  10942. Firing rl*prefer*rvt*predict-no*H0*6
  10943. -->
  10944. (S1 ^operator O1954 = 0.4643592423920161)
  10945. Firing rl*prefer*rvt*predict-yes*H0*5
  10946. -->
  10947. (S1 ^operator O1953 = 0.06777565447391121)
  10948. Firing prefer*rvt*predict-yes*H0
  10949. -->
  10950. Firing prefer*rvt*predict-no*H0
  10951. -->
  10952. Firing elaborate*copy-dir-to-output-link
  10953. -->
  10954. (I3 ^dir R +)
  10955. inner elaboration loop at bottom goal.
  10956. Retracting elaborate*copy-see-to-output-link
  10957. -->
  10958. (I3 ^see 0 +)
  10959. Retracting propose*predict-no
  10960. -->
  10961. (O1954 ^name predict-no +)
  10962. (S1 ^operator O1954 +)
  10963. Retracting propose*predict-yes
  10964. -->
  10965. (O1953 ^name predict-yes +)
  10966. (S1 ^operator O1953 +)
  10967. Retracting elaborate*reward*based*on*reward
  10968. -->
  10969. (R980 ^value 1 +)
  10970. (R1 ^reward R980 +)
  10971. Retracting elaborate*copy-dir-to-output-link
  10972. -->
  10973. (I3 ^dir L +)
  10974. Retracting rl*prefer*rvt*predict-no*H0*4
  10975. -->
  10976. (S1 ^operator O1954 = 0.4334964134865517)
  10977. Retracting rl*prefer*rvt*predict-no*H0*4*H1*12
  10978. -->
  10979. (S1 ^operator O1954 = 0.5664921526005522)
  10980. Retracting rl*prefer*rvt*predict-yes*H0*3
  10981. -->
  10982. (S1 ^operator O1953 = 0.6069254361256142)
  10983. Retracting rl*prefer*rvt*predict-yes*H0*3*H1*13
  10984. -->
  10985. (S1 ^operator O1953 = 0.07203)
  10986. =>WM: (13725: S1 ^operator O1956 +)
  10987. =>WM: (13724: S1 ^operator O1955 +)
  10988. =>WM: (13723: I3 ^dir R)
  10989. =>WM: (13722: O1956 ^name predict-no)
  10990. =>WM: (13721: O1955 ^name predict-yes)
  10991. =>WM: (13720: R981 ^value 1)
  10992. =>WM: (13719: R1 ^reward R981)
  10993. <=WM: (13710: S1 ^operator O1953 +)
  10994. <=WM: (13711: S1 ^operator O1954 +)
  10995. <=WM: (13712: S1 ^operator O1954)
  10996. <=WM: (13709: I3 ^dir L)
  10997. <=WM: (13705: R1 ^reward R980)
  10998. <=WM: (13708: O1954 ^name predict-no)
  10999. <=WM: (13707: O1953 ^name predict-yes)
  11000. <=WM: (13706: R980 ^value 1)
  11001. --- Inner Elaboration Phase, active level 1 (S1) ---
  11002. Firing prefer*rvt*predict-yes*H0
  11003. -->
  11004. Firing rl*prefer*rvt*predict-yes*H0*5*H1*14
  11005. -->
  11006. (S1 ^operator O1955 = 0.9322244609574057)
  11007. Firing rl*prefer*rvt*predict-yes*H0*5
  11008. -->
  11009. (S1 ^operator O1955 = 0.06777565447391121)
  11010. Firing prefer*rvt*predict-yes*H0*5*H1
  11011. -->
  11012. Firing prefer*rvt*predict-no*H0
  11013. -->
  11014. Firing rl*prefer*rvt*predict-no*H0*6*H1*19
  11015. -->
  11016. (S1 ^operator O1956 = 0.3)
  11017. Firing rl*prefer*rvt*predict-no*H0*6
  11018. -->
  11019. (S1 ^operator O1956 = 0.4643592423920161)
  11020. Firing prefer*rvt*predict-no*H0*6*H1
  11021. -->
  11022. inner elaboration loop at bottom goal.
  11023. Retracting rl*prefer*rvt*predict-no*H0*6
  11024. -->
  11025. (S1 ^operator O1954 = 0.4643592423920161)
  11026. Retracting rl*prefer*rvt*predict-no*H0*6*H1*19
  11027. -->
  11028. (S1 ^operator O1954 = 0.3)
  11029. Retracting rl*prefer*rvt*predict-yes*H0*5
  11030. -->
  11031. (S1 ^operator O1953 = 0.06777565447391121)
  11032. Retracting rl*prefer*rvt*predict-yes*H0*5*H1*14
  11033. -->
  11034. (S1 ^operator O1953 = 0.9322244609574057)
  11035. --- END Proposal Phase ---
  11036. --- Decision Phase ---
  11037. RL update rl*prefer*rvt*predict-no*H0*4 0.490212 -0.056716 0.433496 -> 0.490214 -0.056716 0.433498(R,m,v=1,0.886792,0.101027)
  11038. RL update rl*prefer*rvt*predict-no*H0*4*H1*12 0.509776 0.056716 0.566492 -> 0.509778 0.056716 0.566494(R,m,v=1,1,0)
  11039. =>WM: (13726: S1 ^operator O1955)
  11040. 978: O: O1955 (predict-yes)
  11041. --- END Decision Phase ---
  11042. --- Application Phase ---
  11043. --- Firing Productions (PE) For State At Depth 1 ---
  11044. --- Inner Elaboration Phase, active level 1 (S1) ---
  11045. Firing apply*operator
  11046. -->
  11047. (I3 ^predict-yes N978 + :O )
  11048. Firing apply*operator*complete
  11049. -->
  11050. (I3 ^predict-no N977 - :O )
  11051. inner elaboration loop at bottom goal.
  11052. --- Change Working Memory (PE) ---
  11053. =>WM: (13727: I3 ^predict-yes N978)
  11054. <=WM: (13714: N977 ^status complete)
  11055. <=WM: (13713: I3 ^predict-no N977)
  11056. --- Firing Productions (IE) For State At Depth 1 ---
  11057. --- Inner Elaboration Phase, active level 1 (S1) ---
  11058. Firing monitor*world
  11059. -->
  11060. I see 1 and I'm going to do: predict-yes inner elaboration loop at bottom goal.
  11061. --- Change Working Memory (IE) ---
  11062. --- END Application Phase ---
  11063. --- Output Phase ---
  11064. ENV: Agent did: predict-yes for direction R in state State-A
  11065. In State-A moving R
  11066. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  11067. predict error 0
  11068. dir: dir isL
  11069. --- END Output Phase ---
  11070. /|\--- Input Phase ---
  11071. =>WM: (13731: I2 ^dir L)
  11072. =>WM: (13730: I2 ^reward 1)
  11073. =>WM: (13729: I2 ^see 1)
  11074. =>WM: (13728: N978 ^status complete)
  11075. <=WM: (13717: I2 ^dir R)
  11076. <=WM: (13716: I2 ^reward 1)
  11077. <=WM: (13715: I2 ^see 0)
  11078. =>WM: (13732: I2 ^level-1 R1-root)
  11079. <=WM: (13718: I2 ^level-1 L0-root)
  11080. --- END Input Phase ---
  11081. --- Proposal Phase ---
  11082. --- Inner Elaboration Phase, active level 1 (S1) ---
  11083. Firing rl*prefer*rvt*predict-no*H0*4*H1*16
  11084. -->
  11085. (S1 ^operator O1956 = -0.2383263875547442)
  11086. Firing rl*prefer*rvt*predict-yes*H0*3*H1*17
  11087. -->
  11088. (S1 ^operator O1955 = 0.3930687286588074)
  11089. Firing prefer*rvt*predict-no*H0*4*H1
  11090. -->
  11091. Firing prefer*rvt*predict-yes*H0*3*H1
  11092. -->
  11093. Firing elaborate*copy-see-to-output-link
  11094. -->
  11095. (I3 ^see 1 +)
  11096. Firing elaborate*reward*based*on*reward
  11097. -->
  11098. (R982 ^value 1 +)
  11099. (R1 ^reward R982 +)
  11100. Firing propose*predict-yes
  11101. -->
  11102. (O1957 ^name predict-yes +)
  11103. (S1 ^operator O1957 +)
  11104. Firing propose*predict-no
  11105. -->
  11106. (O1958 ^name predict-no +)
  11107. (S1 ^operator O1958 +)
  11108. Firing rl*prefer*rvt*predict-no*H0*4
  11109. -->
  11110. (S1 ^operator O1956 = 0.433498128573486)
  11111. Firing rl*prefer*rvt*predict-yes*H0*3
  11112. -->
  11113. (S1 ^operator O1955 = 0.6069254361256142)
  11114. Firing prefer*rvt*predict-yes*H0
  11115. -->
  11116. Firing prefer*rvt*predict-no*H0
  11117. -->
  11118. Firing elaborate*copy-dir-to-output-link
  11119. -->
  11120. (I3 ^dir L +)
  11121. inner elaboration loop at bottom goal.
  11122. Retracting elaborate*copy-see-to-output-link
  11123. -->
  11124. (I3 ^see 0 +)
  11125. Retracting propose*predict-no
  11126. -->
  11127. (O1956 ^name predict-no +)
  11128. (S1 ^operator O1956 +)
  11129. Retracting propose*predict-yes
  11130. -->
  11131. (O1955 ^name predict-yes +)
  11132. (S1 ^operator O1955 +)
  11133. Retracting elaborate*reward*based*on*reward
  11134. -->
  11135. (R981 ^value 1 +)
  11136. (R1 ^reward R981 +)
  11137. Retracting elaborate*copy-dir-to-output-link
  11138. -->
  11139. (I3 ^dir R +)
  11140. Retracting rl*prefer*rvt*predict-no*H0*6
  11141. -->
  11142. (S1 ^operator O1956 = 0.4643592423920161)
  11143. Retracting rl*prefer*rvt*predict-no*H0*6*H1*19
  11144. -->
  11145. (S1 ^operator O1956 = 0.3)
  11146. Retracting rl*prefer*rvt*predict-yes*H0*5
  11147. -->
  11148. (S1 ^operator O1955 = 0.06777565447391121)
  11149. Retracting rl*prefer*rvt*predict-yes*H0*5*H1*14
  11150. -->
  11151. (S1 ^operator O1955 = 0.9322244609574057)
  11152. =>WM: (13740: S1 ^operator O1958 +)
  11153. =>WM: (13739: S1 ^operator O1957 +)
  11154. =>WM: (13738: I3 ^dir L)
  11155. =>WM: (13737: O1958 ^name predict-no)
  11156. =>WM: (13736: O1957 ^name predict-yes)
  11157. =>WM: (13735: R982 ^value 1)
  11158. =>WM: (13734: R1 ^reward R982)
  11159. =>WM: (13733: I3 ^see 1)
  11160. <=WM: (13724: S1 ^operator O1955 +)
  11161. <=WM: (13726: S1 ^operator O1955)
  11162. <=WM: (13725: S1 ^operator O1956 +)
  11163. <=WM: (13723: I3 ^dir R)
  11164. <=WM: (13719: R1 ^reward R981)
  11165. <=WM: (13690: I3 ^see 0)
  11166. <=WM: (13722: O1956 ^name predict-no)
  11167. <=WM: (13721: O1955 ^name predict-yes)
  11168. <=WM: (13720: R981 ^value 1)
  11169. --- Inner Elaboration Phase, active level 1 (S1) ---
  11170. Firing prefer*rvt*predict-yes*H0
  11171. -->
  11172. Firing rl*prefer*rvt*predict-yes*H0*3
  11173. -->
  11174. (S1 ^operator O1957 = 0.6069254361256142)
  11175. Firing prefer*rvt*predict-yes*H0*3*H1
  11176. -->
  11177. Firing rl*prefer*rvt*predict-yes*H0*3*H1*17
  11178. -->
  11179. (S1 ^operator O1957 = 0.3930687286588074)
  11180. Firing prefer*rvt*predict-no*H0
  11181. -->
  11182. Firing rl*prefer*rvt*predict-no*H0*4
  11183. -->
  11184. (S1 ^operator O1958 = 0.433498128573486)
  11185. Firing prefer*rvt*predict-no*H0*4*H1
  11186. -->
  11187. Firing rl*prefer*rvt*predict-no*H0*4*H1*16
  11188. -->
  11189. (S1 ^operator O1958 = -0.2383263875547442)
  11190. inner elaboration loop at bottom goal.
  11191. Retracting rl*prefer*rvt*predict-no*H0*4
  11192. -->
  11193. (S1 ^operator O1956 = 0.433498128573486)
  11194. Retracting rl*prefer*rvt*predict-no*H0*4*H1*16
  11195. -->
  11196. (S1 ^operator O1956 = -0.2383263875547442)
  11197. Retracting rl*prefer*rvt*predict-yes*H0*3
  11198. -->
  11199. (S1 ^operator O1955 = 0.6069254361256142)
  11200. Retracting rl*prefer*rvt*predict-yes*H0*3*H1*17
  11201. -->
  11202. (S1 ^operator O1955 = 0.3930687286588074)
  11203. --- END Proposal Phase ---
  11204. --- Decision Phase ---
  11205. RL update rl*prefer*rvt*predict-yes*H0*5 0.606208 -0.538432 0.0677757 -> 0.606208 -0.538432 0.0677756(R,m,v=1,0.870787,0.113153)
  11206. RL update rl*prefer*rvt*predict-yes*H0*5*H1*14 0.393792 0.538432 0.932224 -> 0.393792 0.538432 0.932224(R,m,v=1,1,0)
  11207. =>WM: (13741: S1 ^operator O1957)
  11208. 979: O: O1957 (predict-yes)
  11209. --- END Decision Phase ---
  11210. --- Application Phase ---
  11211. --- Firing Productions (PE) For State At Depth 1 ---
  11212. --- Inner Elaboration Phase, active level 1 (S1) ---
  11213. Firing apply*operator
  11214. -->
  11215. (I3 ^predict-yes N979 + :O )
  11216. Firing apply*operator*complete
  11217. -->
  11218. (I3 ^predict-yes N978 - :O )
  11219. inner elaboration loop at bottom goal.
  11220. --- Change Working Memory (PE) ---
  11221. =>WM: (13742: I3 ^predict-yes N979)
  11222. <=WM: (13728: N978 ^status complete)
  11223. <=WM: (13727: I3 ^predict-yes N978)
  11224. --- Firing Productions (IE) For State At Depth 1 ---
  11225. --- Inner Elaboration Phase, active level 1 (S1) ---
  11226. Firing monitor*world
  11227. -->
  11228. I see 1 and I'm going to do: predict-yes inner elaboration loop at bottom goal.
  11229. --- Change Working Memory (IE) ---
  11230. --- END Application Phase ---
  11231. --- Output Phase ---
  11232. ENV: Agent did: predict-yes for direction L in state State-B
  11233. In State-B moving L
  11234. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  11235. predict error 0
  11236. dir: dir isR
  11237. --- END Output Phase ---
  11238. -/|--- Input Phase ---
  11239. =>WM: (13746: I2 ^dir R)
  11240. =>WM: (13745: I2 ^reward 1)
  11241. =>WM: (13744: I2 ^see 1)
  11242. =>WM: (13743: N979 ^status complete)
  11243. <=WM: (13731: I2 ^dir L)
  11244. <=WM: (13730: I2 ^reward 1)
  11245. <=WM: (13729: I2 ^see 1)
  11246. =>WM: (13747: I2 ^level-1 L1-root)
  11247. <=WM: (13732: I2 ^level-1 R1-root)
  11248. --- END Input Phase ---
  11249. --- Proposal Phase ---
  11250. --- Inner Elaboration Phase, active level 1 (S1) ---
  11251. Firing rl*prefer*rvt*predict-yes*H0*5*H1*18
  11252. -->
  11253. (S1 ^operator O1957 = 0.93222410786245)
  11254. Firing rl*prefer*rvt*predict-no*H0*6*H1*21
  11255. -->
  11256. (S1 ^operator O1958 = -0.006920940195066783)
  11257. Firing prefer*rvt*predict-no*H0*6*H1
  11258. -->
  11259. Firing prefer*rvt*predict-yes*H0*5*H1
  11260. -->
  11261. Firing elaborate*copy-see-to-output-link
  11262. -->
  11263. (I3 ^see 1 +)
  11264. Firing elaborate*reward*based*on*reward
  11265. -->
  11266. (R983 ^value 1 +)
  11267. (R1 ^reward R983 +)
  11268. Firing propose*predict-yes
  11269. -->
  11270. (O1959 ^name predict-yes +)
  11271. (S1 ^operator O1959 +)
  11272. Firing propose*predict-no
  11273. -->
  11274. (O1960 ^name predict-no +)
  11275. (S1 ^operator O1960 +)
  11276. Firing rl*prefer*rvt*predict-no*H0*6
  11277. -->
  11278. (S1 ^operator O1958 = 0.4643592423920161)
  11279. Firing rl*prefer*rvt*predict-yes*H0*5
  11280. -->
  11281. (S1 ^operator O1957 = 0.06777563715921375)
  11282. Firing prefer*rvt*predict-yes*H0
  11283. -->
  11284. Firing prefer*rvt*predict-no*H0
  11285. -->
  11286. Firing elaborate*copy-dir-to-output-link
  11287. -->
  11288. (I3 ^dir R +)
  11289. inner elaboration loop at bottom goal.
  11290. Retracting elaborate*copy-see-to-output-link
  11291. -->
  11292. (I3 ^see 1 +)
  11293. Retracting propose*predict-no
  11294. -->
  11295. (O1958 ^name predict-no +)
  11296. (S1 ^operator O1958 +)
  11297. Retracting propose*predict-yes
  11298. -->
  11299. (O1957 ^name predict-yes +)
  11300. (S1 ^operator O1957 +)
  11301. Retracting elaborate*reward*based*on*reward
  11302. -->
  11303. (R982 ^value 1 +)
  11304. (R1 ^reward R982 +)
  11305. Retracting elaborate*copy-dir-to-output-link
  11306. -->
  11307. (I3 ^dir L +)
  11308. Retracting rl*prefer*rvt*predict-no*H0*4*H1*16
  11309. -->
  11310. (S1 ^operator O1958 = -0.2383263875547442)
  11311. Retracting rl*prefer*rvt*predict-no*H0*4
  11312. -->
  11313. (S1 ^operator O1958 = 0.433498128573486)
  11314. Retracting rl*prefer*rvt*predict-yes*H0*3*H1*17
  11315. -->
  11316. (S1 ^operator O1957 = 0.3930687286588074)
  11317. Retracting rl*prefer*rvt*predict-yes*H0*3
  11318. -->
  11319. (S1 ^operator O1957 = 0.6069254361256142)
  11320. =>WM: (13754: S1 ^operator O1960 +)
  11321. =>WM: (13753: S1 ^operator O1959 +)
  11322. =>WM: (13752: I3 ^dir R)
  11323. =>WM: (13751: O1960 ^name predict-no)
  11324. =>WM: (13750: O1959 ^name predict-yes)
  11325. =>WM: (13749: R983 ^value 1)
  11326. =>WM: (13748: R1 ^reward R983)
  11327. <=WM: (13739: S1 ^operator O1957 +)
  11328. <=WM: (13741: S1 ^operator O1957)
  11329. <=WM: (13740: S1 ^operator O1958 +)
  11330. <=WM: (13738: I3 ^dir L)
  11331. <=WM: (13734: R1 ^reward R982)
  11332. <=WM: (13737: O1958 ^name predict-no)
  11333. <=WM: (13736: O1957 ^name predict-yes)
  11334. <=WM: (13735: R982 ^value 1)
  11335. --- Inner Elaboration Phase, active level 1 (S1) ---
  11336. Firing prefer*rvt*predict-yes*H0
  11337. -->
  11338. Firing rl*prefer*rvt*predict-yes*H0*5
  11339. -->
  11340. (S1 ^operator O1959 = 0.06777563715921375)
  11341. Firing prefer*rvt*predict-yes*H0*5*H1
  11342. -->
  11343. Firing rl*prefer*rvt*predict-yes*H0*5*H1*18
  11344. -->
  11345. (S1 ^operator O1959 = 0.93222410786245)
  11346. Firing prefer*rvt*predict-no*H0
  11347. -->
  11348. Firing rl*prefer*rvt*predict-no*H0*6
  11349. -->
  11350. (S1 ^operator O1960 = 0.4643592423920161)
  11351. Firing prefer*rvt*predict-no*H0*6*H1
  11352. -->
  11353. Firing rl*prefer*rvt*predict-no*H0*6*H1*21
  11354. -->
  11355. (S1 ^operator O1960 = -0.006920940195066783)
  11356. inner elaboration loop at bottom goal.
  11357. Retracting rl*prefer*rvt*predict-no*H0*6
  11358. -->
  11359. (S1 ^operator O1958 = 0.4643592423920161)
  11360. Retracting rl*prefer*rvt*predict-no*H0*6*H1*21
  11361. -->
  11362. (S1 ^operator O1958 = -0.006920940195066783)
  11363. Retracting rl*prefer*rvt*predict-yes*H0*5
  11364. -->
  11365. (S1 ^operator O1957 = 0.06777563715921375)
  11366. Retracting rl*prefer*rvt*predict-yes*H0*5*H1*18
  11367. -->
  11368. (S1 ^operator O1957 = 0.93222410786245)
  11369. --- END Proposal Phase ---
  11370. --- Decision Phase ---
  11371. RL update rl*prefer*rvt*predict-yes*H0*3 0.656146 -0.0492203 0.606925 -> 0.656147 -0.0492203 0.606926(R,m,v=1,0.946667,0.0508277)
  11372. RL update rl*prefer*rvt*predict-yes*H0*3*H1*17 0.343849 0.0492201 0.393069 -> 0.343849 0.0492201 0.39307(R,m,v=1,1,0)
  11373. =>WM: (13755: S1 ^operator O1959)
  11374. 980: O: O1959 (predict-yes)
  11375. --- END Decision Phase ---
  11376. --- Application Phase ---
  11377. --- Firing Productions (PE) For State At Depth 1 ---
  11378. --- Inner Elaboration Phase, active level 1 (S1) ---
  11379. Firing apply*operator
  11380. -->
  11381. (I3 ^predict-yes N980 + :O )
  11382. Firing apply*operator*complete
  11383. -->
  11384. (I3 ^predict-yes N979 - :O )
  11385. inner elaboration loop at bottom goal.
  11386. --- Change Working Memory (PE) ---
  11387. =>WM: (13756: I3 ^predict-yes N980)
  11388. <=WM: (13743: N979 ^status complete)
  11389. <=WM: (13742: I3 ^predict-yes N979)
  11390. --- Firing Productions (IE) For State At Depth 1 ---
  11391. --- Inner Elaboration Phase, active level 1 (S1) ---
  11392. Firing monitor*world
  11393. -->
  11394. I see 1 and I'm going to do: predict-yes inner elaboration loop at bottom goal.
  11395. --- Change Working Memory (IE) ---
  11396. --- END Application Phase ---
  11397. --- Output Phase ---
  11398. ENV: Agent did: predict-yes for direction R in state State-A
  11399. In State-A moving R
  11400. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  11401. predict error 0
  11402. dir: dir isR
  11403. --- END Output Phase ---
  11404. \-/--- Input Phase ---
  11405. =>WM: (13760: I2 ^dir R)
  11406. =>WM: (13759: I2 ^reward 1)
  11407. =>WM: (13758: I2 ^see 1)
  11408. =>WM: (13757: N980 ^status complete)
  11409. <=WM: (13746: I2 ^dir R)
  11410. <=WM: (13745: I2 ^reward 1)
  11411. <=WM: (13744: I2 ^see 1)
  11412. =>WM: (13761: I2 ^level-1 R1-root)
  11413. <=WM: (13747: I2 ^level-1 L1-root)
  11414. --- END Input Phase ---
  11415. --- Proposal Phase ---
  11416. --- Inner Elaboration Phase, active level 1 (S1) ---
  11417. Firing rl*prefer*rvt*predict-no*H0*6*H1*20
  11418. -->
  11419. (S1 ^operator O1960 = 0.5356416386505678)
  11420. Firing rl*prefer*rvt*predict-yes*H0*5*H1*15
  11421. -->
  11422. (S1 ^operator O1959 = 0.2653409704952874)
  11423. Firing prefer*rvt*predict-no*H0*6*H1
  11424. -->
  11425. Firing prefer*rvt*predict-yes*H0*5*H1
  11426. -->
  11427. Firing elaborate*copy-see-to-output-link
  11428. -->
  11429. (I3 ^see 1 +)
  11430. Firing elaborate*reward*based*on*reward
  11431. -->
  11432. (R984 ^value 1 +)
  11433. (R1 ^reward R984 +)
  11434. Firing propose*predict-yes
  11435. -->
  11436. (O1961 ^name predict-yes +)
  11437. (S1 ^operator O1961 +)
  11438. Firing propose*predict-no
  11439. -->
  11440. (O1962 ^name predict-no +)
  11441. (S1 ^operator O1962 +)
  11442. Firing rl*prefer*rvt*predict-no*H0*6
  11443. -->
  11444. (S1 ^operator O1960 = 0.4643592423920161)
  11445. Firing rl*prefer*rvt*predict-yes*H0*5
  11446. -->
  11447. (S1 ^operator O1959 = 0.06777563715921375)
  11448. Firing prefer*rvt*predict-yes*H0
  11449. -->
  11450. Firing prefer*rvt*predict-no*H0
  11451. -->
  11452. Firing elaborate*copy-dir-to-output-link
  11453. -->
  11454. (I3 ^dir R +)
  11455. inner elaboration loop at bottom goal.
  11456. Retracting elaborate*copy-see-to-output-link
  11457. -->
  11458. (I3 ^see 1 +)
  11459. Retracting propose*predict-no
  11460. -->
  11461. (O1960 ^name predict-no +)
  11462. (S1 ^operator O1960 +)
  11463. Retracting propose*predict-yes
  11464. -->
  11465. (O1959 ^name predict-yes +)
  11466. (S1 ^operator O1959 +)
  11467. Retracting elaborate*reward*based*on*reward
  11468. -->
  11469. (R983 ^value 1 +)
  11470. (R1 ^reward R983 +)
  11471. Retracting elaborate*copy-dir-to-output-link
  11472. -->
  11473. (I3 ^dir R +)
  11474. Retracting rl*prefer*rvt*predict-no*H0*6*H1*21
  11475. -->
  11476. (S1 ^operator O1960 = -0.006920940195066783)
  11477. Retracting rl*prefer*rvt*predict-no*H0*6
  11478. -->
  11479. (S1 ^operator O1960 = 0.4643592423920161)
  11480. Retracting rl*prefer*rvt*predict-yes*H0*5*H1*18
  11481. -->
  11482. (S1 ^operator O1959 = 0.93222410786245)
  11483. Retracting rl*prefer*rvt*predict-yes*H0*5
  11484. -->
  11485. (S1 ^operator O1959 = 0.06777563715921375)
  11486. =>WM: (13767: S1 ^operator O1962 +)
  11487. =>WM: (13766: S1 ^operator O1961 +)
  11488. =>WM: (13765: O1962 ^name predict-no)
  11489. =>WM: (13764: O1961 ^name predict-yes)
  11490. =>WM: (13763: R984 ^value 1)
  11491. =>WM: (13762: R1 ^reward R984)
  11492. <=WM: (13753: S1 ^operator O1959 +)
  11493. <=WM: (13755: S1 ^operator O1959)
  11494. <=WM: (13754: S1 ^operator O1960 +)
  11495. <=WM: (13748: R1 ^reward R983)
  11496. <=WM: (13751: O1960 ^name predict-no)
  11497. <=WM: (13750: O1959 ^name predict-yes)
  11498. <=WM: (13749: R983 ^value 1)
  11499. --- Inner Elaboration Phase, active level 1 (S1) ---
  11500. Firing prefer*rvt*predict-yes*H0
  11501. -->
  11502. Firing rl*prefer*rvt*predict-yes*H0*5
  11503. -->
  11504. (S1 ^operator O1961 = 0.06777563715921375)
  11505. Firing prefer*rvt*predict-yes*H0*5*H1
  11506. -->
  11507. Firing rl*prefer*rvt*predict-yes*H0*5*H1*15
  11508. -->
  11509. (S1 ^operator O1961 = 0.2653409704952874)
  11510. Firing prefer*rvt*predict-no*H0
  11511. -->
  11512. Firing rl*prefer*rvt*predict-no*H0*6
  11513. -->
  11514. (S1 ^operator O1962 = 0.4643592423920161)
  11515. Firing prefer*rvt*predict-no*H0*6*H1
  11516. -->
  11517. Firing rl*prefer*rvt*predict-no*H0*6*H1*20
  11518. -->
  11519. (S1 ^operator O1962 = 0.5356416386505678)
  11520. inner elaboration loop at bottom goal.
  11521. Retracting rl*prefer*rvt*predict-no*H0*6
  11522. -->
  11523. (S1 ^operator O1960 = 0.4643592423920161)
  11524. Retracting rl*prefer*rvt*predict-no*H0*6*H1*20
  11525. -->
  11526. (S1 ^operator O1960 = 0.5356416386505678)
  11527. Retracting rl*prefer*rvt*predict-yes*H0*5
  11528. -->
  11529. (S1 ^operator O1959 = 0.06777563715921375)
  11530. Retracting rl*prefer*rvt*predict-yes*H0*5*H1*15
  11531. -->
  11532. (S1 ^operator O1959 = 0.2653409704952874)
  11533. --- END Proposal Phase ---
  11534. --- Decision Phase ---
  11535. RL update rl*prefer*rvt*predict-yes*H0*5 0.606208 -0.538432 0.0677756 -> 0.606208 -0.538432 0.0677757(R,m,v=1,0.871508,0.112611)
  11536. RL update rl*prefer*rvt*predict-yes*H0*5*H1*18 0.393792 0.538432 0.932224 -> 0.393792 0.538432 0.932224(R,m,v=1,1,0)
  11537. =>WM: (13768: S1 ^operator O1962)
  11538. 981: O: O1962 (predict-no)
  11539. --- END Decision Phase ---
  11540. --- Application Phase ---
  11541. --- Firing Productions (PE) For State At Depth 1 ---
  11542. --- Inner Elaboration Phase, active level 1 (S1) ---
  11543. Firing apply*operator
  11544. -->
  11545. (I3 ^predict-no N981 + :O )
  11546. Firing apply*operator*complete
  11547. -->
  11548. (I3 ^predict-yes N980 - :O )
  11549. inner elaboration loop at bottom goal.
  11550. --- Change Working Memory (PE) ---
  11551. =>WM: (13769: I3 ^predict-no N981)
  11552. <=WM: (13757: N980 ^status complete)
  11553. <=WM: (13756: I3 ^predict-yes N980)
  11554. --- Firing Productions (IE) For State At Depth 1 ---
  11555. --- Inner Elaboration Phase, active level 1 (S1) ---
  11556. Firing monitor*world
  11557. -->
  11558. I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
  11559. --- Change Working Memory (IE) ---
  11560. --- END Application Phase ---
  11561. --- Output Phase ---
  11562. ENV: Agent did: predict-no for direction R in state State-B
  11563. In State-B moving R
  11564. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  11565. predict error 0
  11566. dir: dir isL
  11567. --- END Output Phase ---
  11568. |--- Input Phase ---
  11569. =>WM: (13773: I2 ^dir L)
  11570. =>WM: (13772: I2 ^reward 1)
  11571. =>WM: (13771: I2 ^see 0)
  11572. =>WM: (13770: N981 ^status complete)
  11573. <=WM: (13760: I2 ^dir R)
  11574. <=WM: (13759: I2 ^reward 1)
  11575. <=WM: (13758: I2 ^see 1)
  11576. =>WM: (13774: I2 ^level-1 R0-root)
  11577. <=WM: (13761: I2 ^level-1 R1-root)
  11578. --- END Input Phase ---
  11579. --- Proposal Phase ---
  11580. --- Inner Elaboration Phase, active level 1 (S1) ---
  11581. Firing rl*prefer*rvt*predict-no*H0*4*H1*8
  11582. -->
  11583. (S1 ^operator O1962 = -0.2450868666562052)
  11584. Firing rl*prefer*rvt*predict-yes*H0*3*H1*9
  11585. -->
  11586. (S1 ^operator O1961 = 0.393091045038772)
  11587. Firing prefer*rvt*predict-no*H0*4*H1
  11588. -->
  11589. Firing prefer*rvt*predict-yes*H0*3*H1
  11590. -->
  11591. Firing elaborate*copy-see-to-output-link
  11592. -->
  11593. (I3 ^see 0 +)
  11594. Firing elaborate*reward*based*on*reward
  11595. -->
  11596. (R985 ^value 1 +)
  11597. (R1 ^reward R985 +)
  11598. Firing propose*predict-yes
  11599. -->
  11600. (O1963 ^name predict-yes +)
  11601. (S1 ^operator O1963 +)
  11602. Firing propose*predict-no
  11603. -->
  11604. (O1964 ^name predict-no +)
  11605. (S1 ^operator O1964 +)
  11606. Firing rl*prefer*rvt*predict-no*H0*4
  11607. -->
  11608. (S1 ^operator O1962 = 0.433498128573486)
  11609. Firing rl*prefer*rvt*predict-yes*H0*3
  11610. -->
  11611. (S1 ^operator O1961 = 0.6069263114079509)
  11612. Firing prefer*rvt*predict-yes*H0
  11613. -->
  11614. Firing prefer*rvt*predict-no*H0
  11615. -->
  11616. Firing elaborate*copy-dir-to-output-link
  11617. -->
  11618. (I3 ^dir L +)
  11619. inner elaboration loop at bottom goal.
  11620. Retracting elaborate*copy-see-to-output-link
  11621. -->
  11622. (I3 ^see 1 +)
  11623. Retracting propose*predict-no
  11624. -->
  11625. (O1962 ^name predict-no +)
  11626. (S1 ^operator O1962 +)
  11627. Retracting propose*predict-yes
  11628. -->
  11629. (O1961 ^name predict-yes +)
  11630. (S1 ^operator O1961 +)
  11631. Retracting elaborate*reward*based*on*reward
  11632. -->
  11633. (R984 ^value 1 +)
  11634. (R1 ^reward R984 +)
  11635. Retracting elaborate*copy-dir-to-output-link
  11636. -->
  11637. (I3 ^dir R +)
  11638. Retracting rl*prefer*rvt*predict-no*H0*6*H1*20
  11639. -->
  11640. (S1 ^operator O1962 = 0.5356416386505678)
  11641. Retracting rl*prefer*rvt*predict-no*H0*6
  11642. -->
  11643. (S1 ^operator O1962 = 0.4643592423920161)
  11644. Retracting rl*prefer*rvt*predict-yes*H0*5*H1*15
  11645. -->
  11646. (S1 ^operator O1961 = 0.2653409704952874)
  11647. Retracting rl*prefer*rvt*predict-yes*H0*5
  11648. -->
  11649. (S1 ^operator O1961 = 0.06777567540596419)
  11650. =>WM: (13782: S1 ^operator O1964 +)
  11651. =>WM: (13781: S1 ^operator O1963 +)
  11652. =>WM: (13780: I3 ^dir L)
  11653. =>WM: (13779: O1964 ^name predict-no)
  11654. =>WM: (13778: O1963 ^name predict-yes)
  11655. =>WM: (13777: R985 ^value 1)
  11656. =>WM: (13776: R1 ^reward R985)
  11657. =>WM: (13775: I3 ^see 0)
  11658. <=WM: (13766: S1 ^operator O1961 +)
  11659. <=WM: (13767: S1 ^operator O1962 +)
  11660. <=WM: (13768: S1 ^operator O1962)
  11661. <=WM: (13752: I3 ^dir R)
  11662. <=WM: (13762: R1 ^reward R984)
  11663. <=WM: (13733: I3 ^see 1)
  11664. <=WM: (13765: O1962 ^name predict-no)
  11665. <=WM: (13764: O1961 ^name predict-yes)
  11666. <=WM: (13763: R984 ^value 1)
  11667. --- Inner Elaboration Phase, active level 1 (S1) ---
  11668. Firing prefer*rvt*predict-yes*H0
  11669. -->
  11670. Firing rl*prefer*rvt*predict-yes*H0*3
  11671. -->
  11672. (S1 ^operator O1963 = 0.6069263114079509)
  11673. Firing prefer*rvt*predict-yes*H0*3*H1
  11674. -->
  11675. Firing rl*prefer*rvt*predict-yes*H0*3*H1*9
  11676. -->
  11677. (S1 ^operator O1963 = 0.393091045038772)
  11678. Firing prefer*rvt*predict-no*H0
  11679. -->
  11680. Firing rl*prefer*rvt*predict-no*H0*4
  11681. -->
  11682. (S1 ^operator O1964 = 0.433498128573486)
  11683. Firing prefer*rvt*predict-no*H0*4*H1
  11684. -->
  11685. Firing rl*prefer*rvt*predict-no*H0*4*H1*8
  11686. -->
  11687. (S1 ^operator O1964 = -0.2450868666562052)
  11688. inner elaboration loop at bottom goal.
  11689. Retracting rl*prefer*rvt*predict-no*H0*4
  11690. -->
  11691. (S1 ^operator O1962 = 0.433498128573486)
  11692. Retracting rl*prefer*rvt*predict-no*H0*4*H1*8
  11693. -->
  11694. (S1 ^operator O1962 = -0.2450868666562052)
  11695. Retracting rl*prefer*rvt*predict-yes*H0*3
  11696. -->
  11697. (S1 ^operator O1961 = 0.6069263114079509)
  11698. Retracting rl*prefer*rvt*predict-yes*H0*3*H1*9
  11699. -->
  11700. (S1 ^operator O1961 = 0.393091045038772)
  11701. --- END Proposal Phase ---
  11702. --- Decision Phase ---
  11703. RL update rl*prefer*rvt*predict-no*H0*6 0.679081 -0.214722 0.464359 -> 0.679081 -0.214722 0.464359(R,m,v=1,0.970588,0.0287156)
  11704. RL update rl*prefer*rvt*predict-no*H0*6*H1*20 0.32092 0.214722 0.535642 -> 0.32092 0.214722 0.535642(R,m,v=1,1,0)
  11705. =>WM: (13783: S1 ^operator O1963)
  11706. 982: O: O1963 (predict-yes)
  11707. --- END Decision Phase ---
  11708. --- Application Phase ---
  11709. --- Firing Productions (PE) For State At Depth 1 ---
  11710. --- Inner Elaboration Phase, active level 1 (S1) ---
  11711. Firing apply*operator
  11712. -->
  11713. (I3 ^predict-yes N982 + :O )
  11714. Firing apply*operator*complete
  11715. -->
  11716. (I3 ^predict-no N981 - :O )
  11717. inner elaboration loop at bottom goal.
  11718. --- Change Working Memory (PE) ---
  11719. =>WM: (13784: I3 ^predict-yes N982)
  11720. <=WM: (13770: N981 ^status complete)
  11721. <=WM: (13769: I3 ^predict-no N981)
  11722. --- Firing Productions (IE) For State At Depth 1 ---
  11723. --- Inner Elaboration Phase, active level 1 (S1) ---
  11724. Firing monitor*world
  11725. -->
  11726. I see 1 and I'm going to do: predict-yes inner elaboration loop at bottom goal.
  11727. --- Change Working Memory (IE) ---
  11728. --- END Application Phase ---
  11729. --- Output Phase ---
  11730. ENV: Agent did: predict-yes for direction L in state State-B
  11731. In State-B moving L
  11732. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  11733. predict error 0
  11734. dir: dir isL
  11735. --- END Output Phase ---
  11736. \-/--- Input Phase ---
  11737. =>WM: (13788: I2 ^dir L)
  11738. =>WM: (13787: I2 ^reward 1)
  11739. =>WM: (13786: I2 ^see 1)
  11740. =>WM: (13785: N982 ^status complete)
  11741. <=WM: (13773: I2 ^dir L)
  11742. <=WM: (13772: I2 ^reward 1)
  11743. <=WM: (13771: I2 ^see 0)
  11744. =>WM: (13789: I2 ^level-1 L1-root)
  11745. <=WM: (13774: I2 ^level-1 R0-root)
  11746. --- END Input Phase ---
  11747. --- Proposal Phase ---
  11748. --- Inner Elaboration Phase, active level 1 (S1) ---
  11749. Firing rl*prefer*rvt*predict-yes*H0*3*H1*11
  11750. -->
  11751. (S1 ^operator O1963 = -0.03517433757196466)
  11752. Firing rl*prefer*rvt*predict-no*H0*4*H1*10
  11753. -->
  11754. (S1 ^operator O1964 = 0.5665075150969485)
  11755. Firing prefer*rvt*predict-no*H0*4*H1
  11756. -->
  11757. Firing prefer*rvt*predict-yes*H0*3*H1
  11758. -->
  11759. Firing elaborate*copy-see-to-output-link
  11760. -->
  11761. (I3 ^see 1 +)
  11762. Firing elaborate*reward*based*on*reward
  11763. -->
  11764. (R986 ^value 1 +)
  11765. (R1 ^reward R986 +)
  11766. Firing propose*predict-yes
  11767. -->
  11768. (O1965 ^name predict-yes +)
  11769. (S1 ^operator O1965 +)
  11770. Firing propose*predict-no
  11771. -->
  11772. (O1966 ^name predict-no +)
  11773. (S1 ^operator O1966 +)
  11774. Firing rl*prefer*rvt*predict-no*H0*4
  11775. -->
  11776. (S1 ^operator O1964 = 0.433498128573486)
  11777. Firing rl*prefer*rvt*predict-yes*H0*3
  11778. -->
  11779. (S1 ^operator O1963 = 0.6069263114079509)
  11780. Firing prefer*rvt*predict-yes*H0
  11781. -->
  11782. Firing prefer*rvt*predict-no*H0
  11783. -->
  11784. Firing elaborate*copy-dir-to-output-link
  11785. -->
  11786. (I3 ^dir L +)
  11787. inner elaboration loop at bottom goal.
  11788. Retracting elaborate*copy-see-to-output-link
  11789. -->
  11790. (I3 ^see 0 +)
  11791. Retracting propose*predict-no
  11792. -->
  11793. (O1964 ^name predict-no +)
  11794. (S1 ^operator O1964 +)
  11795. Retracting propose*predict-yes
  11796. -->
  11797. (O1963 ^name predict-yes +)
  11798. (S1 ^operator O1963 +)
  11799. Retracting elaborate*reward*based*on*reward
  11800. -->
  11801. (R985 ^value 1 +)
  11802. (R1 ^reward R985 +)
  11803. Retracting elaborate*copy-dir-to-output-link
  11804. -->
  11805. (I3 ^dir L +)
  11806. Retracting rl*prefer*rvt*predict-no*H0*4*H1*8
  11807. -->
  11808. (S1 ^operator O1964 = -0.2450868666562052)
  11809. Retracting rl*prefer*rvt*predict-no*H0*4
  11810. -->
  11811. (S1 ^operator O1964 = 0.433498128573486)
  11812. Retracting rl*prefer*rvt*predict-yes*H0*3*H1*9
  11813. -->
  11814. (S1 ^operator O1963 = 0.393091045038772)
  11815. Retracting rl*prefer*rvt*predict-yes*H0*3
  11816. -->
  11817. (S1 ^operator O1963 = 0.6069263114079509)
  11818. =>WM: (13796: S1 ^operator O1966 +)
  11819. =>WM: (13795: S1 ^operator O1965 +)
  11820. =>WM: (13794: O1966 ^name predict-no)
  11821. =>WM: (13793: O1965 ^name predict-yes)
  11822. =>WM: (13792: R986 ^value 1)
  11823. =>WM: (13791: R1 ^reward R986)
  11824. =>WM: (13790: I3 ^see 1)
  11825. <=WM: (13781: S1 ^operator O1963 +)
  11826. <=WM: (13783: S1 ^operator O1963)
  11827. <=WM: (13782: S1 ^operator O1964 +)
  11828. <=WM: (13776: R1 ^reward R985)
  11829. <=WM: (13775: I3 ^see 0)
  11830. <=WM: (13779: O1964 ^name predict-no)
  11831. <=WM: (13778: O1963 ^name predict-yes)
  11832. <=WM: (13777: R985 ^value 1)
  11833. --- Inner Elaboration Phase, active level 1 (S1) ---
  11834. Firing prefer*rvt*predict-yes*H0
  11835. -->
  11836. Firing rl*prefer*rvt*predict-yes*H0*3
  11837. -->
  11838. (S1 ^operator O1965 = 0.6069263114079509)
  11839. Firing prefer*rvt*predict-yes*H0*3*H1
  11840. -->
  11841. Firing rl*prefer*rvt*predict-yes*H0*3*H1*11
  11842. -->
  11843. (S1 ^operator O1965 = -0.03517433757196466)
  11844. Firing prefer*rvt*predict-no*H0
  11845. -->
  11846. Firing rl*prefer*rvt*predict-no*H0*4
  11847. -->
  11848. (S1 ^operator O1966 = 0.433498128573486)
  11849. Firing prefer*rvt*predict-no*H0*4*H1
  11850. -->
  11851. Firing rl*prefer*rvt*predict-no*H0*4*H1*10
  11852. -->
  11853. (S1 ^operator O1966 = 0.5665075150969485)
  11854. inner elaboration loop at bottom goal.
  11855. Retracting rl*prefer*rvt*predict-no*H0*4
  11856. -->
  11857. (S1 ^operator O1964 = 0.433498128573486)
  11858. Retracting rl*prefer*rvt*predict-no*H0*4*H1*10
  11859. -->
  11860. (S1 ^operator O1964 = 0.5665075150969485)
  11861. Retracting rl*prefer*rvt*predict-yes*H0*3
  11862. -->
  11863. (S1 ^operator O1963 = 0.6069263114079509)
  11864. Retracting rl*prefer*rvt*predict-yes*H0*3*H1*11
  11865. -->
  11866. (S1 ^operator O1963 = -0.03517433757196466)
  11867. --- END Proposal Phase ---
  11868. --- Decision Phase ---
  11869. RL update rl*prefer*rvt*predict-yes*H0*3 0.656147 -0.0492203 0.606926 -> 0.656144 -0.0492204 0.606924(R,m,v=1,0.94702,0.0505077)
  11870. RL update rl*prefer*rvt*predict-yes*H0*3*H1*9 0.34387 0.0492209 0.393091 -> 0.343868 0.0492208 0.393088(R,m,v=1,1,0)
  11871. =>WM: (13797: S1 ^operator O1966)
  11872. 983: O: O1966 (predict-no)
  11873. --- END Decision Phase ---
  11874. --- Application Phase ---
  11875. --- Firing Productions (PE) For State At Depth 1 ---
  11876. --- Inner Elaboration Phase, active level 1 (S1) ---
  11877. Firing apply*operator
  11878. -->
  11879. (I3 ^predict-no N983 + :O )
  11880. Firing apply*operator*complete
  11881. -->
  11882. (I3 ^predict-yes N982 - :O )
  11883. inner elaboration loop at bottom goal.
  11884. --- Change Working Memory (PE) ---
  11885. =>WM: (13798: I3 ^predict-no N983)
  11886. <=WM: (13785: N982 ^status complete)
  11887. <=WM: (13784: I3 ^predict-yes N982)
  11888. --- Firing Productions (IE) For State At Depth 1 ---
  11889. --- Inner Elaboration Phase, active level 1 (S1) ---
  11890. Firing monitor*world
  11891. -->
  11892. I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
  11893. --- Change Working Memory (IE) ---
  11894. --- END Application Phase ---
  11895. --- Output Phase ---
  11896. ENV: Agent did: predict-no for direction L in state State-A
  11897. In State-A moving L
  11898. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  11899. predict error 0
  11900. dir: dir isR
  11901. --- END Output Phase ---
  11902. |\---- Input Phase ---
  11903. =>WM: (13802: I2 ^dir R)
  11904. =>WM: (13801: I2 ^reward 1)
  11905. =>WM: (13800: I2 ^see 0)
  11906. =>WM: (13799: N983 ^status complete)
  11907. <=WM: (13788: I2 ^dir L)
  11908. <=WM: (13787: I2 ^reward 1)
  11909. <=WM: (13786: I2 ^see 1)
  11910. =>WM: (13803: I2 ^level-1 L0-root)
  11911. <=WM: (13789: I2 ^level-1 L1-root)
  11912. --- END Input Phase ---
  11913. --- Proposal Phase ---
  11914. --- Inner Elaboration Phase, active level 1 (S1) ---
  11915. Firing rl*prefer*rvt*predict-yes*H0*5*H1*14
  11916. -->
  11917. (S1 ^operator O1965 = 0.9322244436427083)
  11918. Firing rl*prefer*rvt*predict-no*H0*6*H1*19
  11919. -->
  11920. (S1 ^operator O1966 = 0.3)
  11921. Firing prefer*rvt*predict-no*H0*6*H1
  11922. -->
  11923. Firing prefer*rvt*predict-yes*H0*5*H1
  11924. -->
  11925. Firing elaborate*copy-see-to-output-link
  11926. -->
  11927. (I3 ^see 0 +)
  11928. Firing elaborate*reward*based*on*reward
  11929. -->
  11930. (R987 ^value 1 +)
  11931. (R1 ^reward R987 +)
  11932. Firing propose*predict-yes
  11933. -->
  11934. (O1967 ^name predict-yes +)
  11935. (S1 ^operator O1967 +)
  11936. Firing propose*predict-no
  11937. -->
  11938. (O1968 ^name predict-no +)
  11939. (S1 ^operator O1968 +)
  11940. Firing rl*prefer*rvt*predict-no*H0*6
  11941. -->
  11942. (S1 ^operator O1966 = 0.4643591102356286)
  11943. Firing rl*prefer*rvt*predict-yes*H0*5
  11944. -->
  11945. (S1 ^operator O1965 = 0.06777567540596419)
  11946. Firing prefer*rvt*predict-yes*H0
  11947. -->
  11948. Firing prefer*rvt*predict-no*H0
  11949. -->
  11950. Firing elaborate*copy-dir-to-output-link
  11951. -->
  11952. (I3 ^dir R +)
  11953. inner elaboration loop at bottom goal.
  11954. Retracting elaborate*copy-see-to-output-link
  11955. -->
  11956. (I3 ^see 1 +)
  11957. Retracting propose*predict-no
  11958. -->
  11959. (O1966 ^name predict-no +)
  11960. (S1 ^operator O1966 +)
  11961. Retracting propose*predict-yes
  11962. -->
  11963. (O1965 ^name predict-yes +)
  11964. (S1 ^operator O1965 +)
  11965. Retracting elaborate*reward*based*on*reward
  11966. -->
  11967. (R986 ^value 1 +)
  11968. (R1 ^reward R986 +)
  11969. Retracting elaborate*copy-dir-to-output-link
  11970. -->
  11971. (I3 ^dir L +)
  11972. Retracting rl*prefer*rvt*predict-no*H0*4*H1*10
  11973. -->
  11974. (S1 ^operator O1966 = 0.5665075150969485)
  11975. Retracting rl*prefer*rvt*predict-no*H0*4
  11976. -->
  11977. (S1 ^operator O1966 = 0.433498128573486)
  11978. Retracting rl*prefer*rvt*predict-yes*H0*3*H1*11
  11979. -->
  11980. (S1 ^operator O1965 = -0.03517433757196466)
  11981. Retracting rl*prefer*rvt*predict-yes*H0*3
  11982. -->
  11983. (S1 ^operator O1965 = 0.6069237079409425)
  11984. =>WM: (13811: S1 ^operator O1968 +)
  11985. =>WM: (13810: S1 ^operator O1967 +)
  11986. =>WM: (13809: I3 ^dir R)
  11987. =>WM: (13808: O1968 ^name predict-no)
  11988. =>WM: (13807: O1967 ^name predict-yes)
  11989. =>WM: (13806: R987 ^value 1)
  11990. =>WM: (13805: R1 ^reward R987)
  11991. =>WM: (13804: I3 ^see 0)
  11992. <=WM: (13795: S1 ^operator O1965 +)
  11993. <=WM: (13796: S1 ^operator O1966 +)
  11994. <=WM: (13797: S1 ^operator O1966)
  11995. <=WM: (13780: I3 ^dir L)
  11996. <=WM: (13791: R1 ^reward R986)
  11997. <=WM: (13790: I3 ^see 1)
  11998. <=WM: (13794: O1966 ^name predict-no)
  11999. <=WM: (13793: O1965 ^name predict-yes)
  12000. <=WM: (13792: R986 ^value 1)
  12001. --- Inner Elaboration Phase, active level 1 (S1) ---
  12002. Firing prefer*rvt*predict-yes*H0
  12003. -->
  12004. Firing rl*prefer*rvt*predict-yes*H0*5
  12005. -->
  12006. (S1 ^operator O1967 = 0.06777567540596419)
  12007. Firing prefer*rvt*predict-yes*H0*5*H1
  12008. -->
  12009. Firing rl*prefer*rvt*predict-yes*H0*5*H1*14
  12010. -->
  12011. (S1 ^operator O1967 = 0.9322244436427083)
  12012. Firing prefer*rvt*predict-no*H0
  12013. -->
  12014. Firing rl*prefer*rvt*predict-no*H0*6
  12015. -->
  12016. (S1 ^operator O1968 = 0.4643591102356286)
  12017. Firing prefer*rvt*predict-no*H0*6*H1
  12018. -->
  12019. Firing rl*prefer*rvt*predict-no*H0*6*H1*19
  12020. -->
  12021. (S1 ^operator O1968 = 0.3)
  12022. inner elaboration loop at bottom goal.
  12023. Retracting rl*prefer*rvt*predict-no*H0*6
  12024. -->
  12025. (S1 ^operator O1966 = 0.4643591102356286)
  12026. Retracting rl*prefer*rvt*predict-no*H0*6*H1*19
  12027. -->
  12028. (S1 ^operator O1966 = 0.3)
  12029. Retracting rl*prefer*rvt*predict-yes*H0*5
  12030. -->
  12031. (S1 ^operator O1965 = 0.06777567540596419)
  12032. Retracting rl*prefer*rvt*predict-yes*H0*5*H1*14
  12033. -->
  12034. (S1 ^operator O1965 = 0.9322244436427083)
  12035. --- END Proposal Phase ---
  12036. --- Decision Phase ---
  12037. RL update rl*prefer*rvt*predict-no*H0*4 0.490214 -0.056716 0.433498 -> 0.490213 -0.056716 0.433497(R,m,v=1,0.8875,0.100472)
  12038. RL update rl*prefer*rvt*predict-no*H0*4*H1*10 0.509791 0.056716 0.566508 -> 0.509791 0.056716 0.566507(R,m,v=1,1,0)
  12039. =>WM: (13812: S1 ^operator O1967)
  12040. 984: O: O1967 (predict-yes)
  12041. --- END Decision Phase ---
  12042. --- Application Phase ---
  12043. --- Firing Productions (PE) For State At Depth 1 ---
  12044. --- Inner Elaboration Phase, active level 1 (S1) ---
  12045. Firing apply*operator
  12046. -->
  12047. (I3 ^predict-yes N984 + :O )
  12048. Firing apply*operator*complete
  12049. -->
  12050. (I3 ^predict-no N983 - :O )
  12051. inner elaboration loop at bottom goal.
  12052. --- Change Working Memory (PE) ---
  12053. =>WM: (13813: I3 ^predict-yes N984)
  12054. <=WM: (13799: N983 ^status complete)
  12055. <=WM: (13798: I3 ^predict-no N983)
  12056. --- Firing Productions (IE) For State At Depth 1 ---
  12057. --- Inner Elaboration Phase, active level 1 (S1) ---
  12058. Firing monitor*world
  12059. -->
  12060. I see 1 and I'm going to do: predict-yes inner elaboration loop at bottom goal.
  12061. --- Change Working Memory (IE) ---
  12062. --- END Application Phase ---
  12063. --- Output Phase ---
  12064. ENV: Agent did: predict-yes for direction R in state State-A
  12065. In State-A moving R
  12066. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  12067. predict error 0
  12068. dir: dir isU
  12069. --- END Output Phase ---
  12070. /|\--- Input Phase ---
  12071. =>WM: (13817: I2 ^dir U)
  12072. =>WM: (13816: I2 ^reward 1)
  12073. =>WM: (13815: I2 ^see 1)
  12074. =>WM: (13814: N984 ^status complete)
  12075. <=WM: (13802: I2 ^dir R)
  12076. <=WM: (13801: I2 ^reward 1)
  12077. <=WM: (13800: I2 ^see 0)
  12078. =>WM: (13818: I2 ^level-1 R1-root)
  12079. <=WM: (13803: I2 ^level-1 L0-root)
  12080. --- END Input Phase ---
  12081. --- Proposal Phase ---
  12082. --- Inner Elaboration Phase, active level 1 (S1) ---
  12083. Firing elaborate*copy-see-to-output-link
  12084. -->
  12085. (I3 ^see 1 +)
  12086. Firing elaborate*reward*based*on*reward
  12087. -->
  12088. (R988 ^value 1 +)
  12089. (R1 ^reward R988 +)
  12090. Firing propose*predict-yes
  12091. -->
  12092. (O1969 ^name predict-yes +)
  12093. (S1 ^operator O1969 +)
  12094. Firing propose*predict-no
  12095. -->
  12096. (O1970 ^name predict-no +)
  12097. (S1 ^operator O1970 +)
  12098. Firing rl*prefer*rvt*predict-no*H0*2
  12099. -->
  12100. (S1 ^operator O1968 = 0.9999999999999999)
  12101. Firing rl*prefer*rvt*predict-yes*H0*1
  12102. -->
  12103. (S1 ^operator O1967 = 0.)
  12104. Firing prefer*rvt*predict-yes*H0
  12105. -->
  12106. Firing prefer*rvt*predict-no*H0
  12107. -->
  12108. Firing elaborate*copy-dir-to-output-link
  12109. -->
  12110. (I3 ^dir U +)
  12111. inner elaboration loop at bottom goal.
  12112. Retracting elaborate*copy-see-to-output-link
  12113. -->
  12114. (I3 ^see 0 +)
  12115. Retracting propose*predict-no
  12116. -->
  12117. (O1968 ^name predict-no +)
  12118. (S1 ^operator O1968 +)
  12119. Retracting propose*predict-yes
  12120. -->
  12121. (O1967 ^name predict-yes +)
  12122. (S1 ^operator O1967 +)
  12123. Retracting elaborate*reward*based*on*reward
  12124. -->
  12125. (R987 ^value 1 +)
  12126. (R1 ^reward R987 +)
  12127. Retracting elaborate*copy-dir-to-output-link
  12128. -->
  12129. (I3 ^dir R +)
  12130. Retracting rl*prefer*rvt*predict-no*H0*6*H1*19
  12131. -->
  12132. (S1 ^operator O1968 = 0.3)
  12133. Retracting rl*prefer*rvt*predict-no*H0*6
  12134. -->
  12135. (S1 ^operator O1968 = 0.4643591102356286)
  12136. Retracting rl*prefer*rvt*predict-yes*H0*5*H1*14
  12137. -->
  12138. (S1 ^operator O1967 = 0.9322244436427083)
  12139. Retracting rl*prefer*rvt*predict-yes*H0*5
  12140. -->
  12141. (S1 ^operator O1967 = 0.06777567540596419)
  12142. =>WM: (13826: S1 ^operator O1970 +)
  12143. =>WM: (13825: S1 ^operator O1969 +)
  12144. =>WM: (13824: I3 ^dir U)
  12145. =>WM: (13823: O1970 ^name predict-no)
  12146. =>WM: (13822: O1969 ^name predict-yes)
  12147. =>WM: (13821: R988 ^value 1)
  12148. =>WM: (13820: R1 ^reward R988)
  12149. =>WM: (13819: I3 ^see 1)
  12150. <=WM: (13810: S1 ^operator O1967 +)
  12151. <=WM: (13812: S1 ^operator O1967)
  12152. <=WM: (13811: S1 ^operator O1968 +)
  12153. <=WM: (13809: I3 ^dir R)
  12154. <=WM: (13805: R1 ^reward R987)
  12155. <=WM: (13804: I3 ^see 0)
  12156. <=WM: (13808: O1968 ^name predict-no)
  12157. <=WM: (13807: O1967 ^name predict-yes)
  12158. <=WM: (13806: R987 ^value 1)
  12159. --- Inner Elaboration Phase, active level 1 (S1) ---
  12160. Firing prefer*rvt*predict-yes*H0
  12161. -->
  12162. Firing rl*prefer*rvt*predict-yes*H0*1
  12163. -->
  12164. (S1 ^operator O1969 = 0.)
  12165. Firing prefer*rvt*predict-no*H0
  12166. -->
  12167. Firing rl*prefer*rvt*predict-no*H0*2
  12168. -->
  12169. (S1 ^operator O1970 = 0.9999999999999999)
  12170. inner elaboration loop at bottom goal.
  12171. Retracting rl*prefer*rvt*predict-no*H0*2
  12172. -->
  12173. (S1 ^operator O1968 = 0.9999999999999999)
  12174. Retracting rl*prefer*rvt*predict-yes*H0*1
  12175. -->
  12176. (S1 ^operator O1967 = 0.)
  12177. --- END Proposal Phase ---
  12178. --- Decision Phase ---
  12179. RL update rl*prefer*rvt*predict-yes*H0*5 0.606208 -0.538432 0.0677757 -> 0.606208 -0.538432 0.0677757(R,m,v=1,0.872222,0.112073)
  12180. RL update rl*prefer*rvt*predict-yes*H0*5*H1*14 0.393792 0.538432 0.932224 -> 0.393792 0.538432 0.932224(R,m,v=1,1,0)
  12181. =>WM: (13827: S1 ^operator O1970)
  12182. 985: O: O1970 (predict-no)
  12183. --- END Decision Phase ---
  12184. --- Application Phase ---
  12185. --- Firing Productions (PE) For State At Depth 1 ---
  12186. --- Inner Elaboration Phase, active level 1 (S1) ---
  12187. Firing apply*operator
  12188. -->
  12189. (I3 ^predict-no N985 + :O )
  12190. Firing apply*operator*complete
  12191. -->
  12192. (I3 ^predict-yes N984 - :O )
  12193. inner elaboration loop at bottom goal.
  12194. --- Change Working Memory (PE) ---
  12195. =>WM: (13828: I3 ^predict-no N985)
  12196. <=WM: (13814: N984 ^status complete)
  12197. <=WM: (13813: I3 ^predict-yes N984)
  12198. --- Firing Productions (IE) For State At Depth 1 ---
  12199. --- Inner Elaboration Phase, active level 1 (S1) ---
  12200. Firing monitor*world
  12201. -->
  12202. I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
  12203. --- Change Working Memory (IE) ---
  12204. --- END Application Phase ---
  12205. --- Output Phase ---
  12206. ENV: Agent did: predict-no for direction U in state State-B
  12207. In State-B moving U
  12208. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  12209. predict error 0
  12210. dir: dir isL
  12211. --- END Output Phase ---
  12212. -/--- Input Phase ---
  12213. =>WM: (13832: I2 ^dir L)
  12214. =>WM: (13831: I2 ^reward 1)
  12215. =>WM: (13830: I2 ^see 0)
  12216. =>WM: (13829: N985 ^status complete)
  12217. <=WM: (13817: I2 ^dir U)
  12218. <=WM: (13816: I2 ^reward 1)
  12219. <=WM: (13815: I2 ^see 1)
  12220. =>WM: (13833: I2 ^level-1 R1-root)
  12221. <=WM: (13818: I2 ^level-1 R1-root)
  12222. --- END Input Phase ---
  12223. --- Proposal Phase ---
  12224. --- Inner Elaboration Phase, active level 1 (S1) ---
  12225. Firing rl*prefer*rvt*predict-no*H0*4*H1*16
  12226. -->
  12227. (S1 ^operator O1970 = -0.2383263875547442)
  12228. Firing rl*prefer*rvt*predict-yes*H0*3*H1*17
  12229. -->
  12230. (S1 ^operator O1969 = 0.3930696039411442)
  12231. Firing prefer*rvt*predict-no*H0*4*H1
  12232. -->
  12233. Firing prefer*rvt*predict-yes*H0*3*H1
  12234. -->
  12235. Firing elaborate*copy-see-to-output-link
  12236. -->
  12237. (I3 ^see 0 +)
  12238. Firing elaborate*reward*based*on*reward
  12239. -->
  12240. (R989 ^value 1 +)
  12241. (R1 ^reward R989 +)
  12242. Firing propose*predict-yes
  12243. -->
  12244. (O1971 ^name predict-yes +)
  12245. (S1 ^operator O1971 +)
  12246. Firing propose*predict-no
  12247. -->
  12248. (O1972 ^name predict-no +)
  12249. (S1 ^operator O1972 +)
  12250. Firing rl*prefer*rvt*predict-no*H0*4
  12251. -->
  12252. (S1 ^operator O1970 = 0.4334972820229208)
  12253. Firing rl*prefer*rvt*predict-yes*H0*3
  12254. -->
  12255. (S1 ^operator O1969 = 0.6069237079409425)
  12256. Firing prefer*rvt*predict-yes*H0
  12257. -->
  12258. Firing prefer*rvt*predict-no*H0
  12259. -->
  12260. Firing elaborate*copy-dir-to-output-link
  12261. -->
  12262. (I3 ^dir L +)
  12263. inner elaboration loop at bottom goal.
  12264. Retracting elaborate*copy-see-to-output-link
  12265. -->
  12266. (I3 ^see 1 +)
  12267. Retracting propose*predict-no
  12268. -->
  12269. (O1970 ^name predict-no +)
  12270. (S1 ^operator O1970 +)
  12271. Retracting propose*predict-yes
  12272. -->
  12273. (O1969 ^name predict-yes +)
  12274. (S1 ^operator O1969 +)
  12275. Retracting elaborate*reward*based*on*reward
  12276. -->
  12277. (R988 ^value 1 +)
  12278. (R1 ^reward R988 +)
  12279. Retracting elaborate*copy-dir-to-output-link
  12280. -->
  12281. (I3 ^dir U +)
  12282. Retracting rl*prefer*rvt*predict-no*H0*2
  12283. -->
  12284. (S1 ^operator O1970 = 0.9999999999999999)
  12285. Retracting rl*prefer*rvt*predict-yes*H0*1
  12286. -->
  12287. (S1 ^operator O1969 = 0.)
  12288. =>WM: (13841: S1 ^operator O1972 +)
  12289. =>WM: (13840: S1 ^operator O1971 +)
  12290. =>WM: (13839: I3 ^dir L)
  12291. =>WM: (13838: O1972 ^name predict-no)
  12292. =>WM: (13837: O1971 ^name predict-yes)
  12293. =>WM: (13836: R989 ^value 1)
  12294. =>WM: (13835: R1 ^reward R989)
  12295. =>WM: (13834: I3 ^see 0)
  12296. <=WM: (13825: S1 ^operator O1969 +)
  12297. <=WM: (13826: S1 ^operator O1970 +)
  12298. <=WM: (13827: S1 ^operator O1970)
  12299. <=WM: (13824: I3 ^dir U)
  12300. <=WM: (13820: R1 ^reward R988)
  12301. <=WM: (13819: I3 ^see 1)
  12302. <=WM: (13823: O1970 ^name predict-no)
  12303. <=WM: (13822: O1969 ^name predict-yes)
  12304. <=WM: (13821: R988 ^value 1)
  12305. --- Inner Elaboration Phase, active level 1 (S1) ---
  12306. Firing prefer*rvt*predict-yes*H0
  12307. -->
  12308. Firing rl*prefer*rvt*predict-yes*H0*3*H1*17
  12309. -->
  12310. (S1 ^operator O1971 = 0.3930696039411442)
  12311. Firing rl*prefer*rvt*predict-yes*H0*3
  12312. -->
  12313. (S1 ^operator O1971 = 0.6069237079409425)
  12314. Firing prefer*rvt*predict-yes*H0*3*H1
  12315. -->
  12316. Firing prefer*rvt*predict-no*H0
  12317. -->
  12318. Firing rl*prefer*rvt*predict-no*H0*4*H1*16
  12319. -->
  12320. (S1 ^operator O1972 = -0.2383263875547442)
  12321. Firing rl*prefer*rvt*predict-no*H0*4
  12322. -->
  12323. (S1 ^operator O1972 = 0.4334972820229208)
  12324. Firing prefer*rvt*predict-no*H0*4*H1
  12325. -->
  12326. inner elaboration loop at bottom goal.
  12327. Retracting rl*prefer*rvt*predict-no*H0*4
  12328. -->
  12329. (S1 ^operator O1970 = 0.4334972820229208)
  12330. Retracting rl*prefer*rvt*predict-no*H0*4*H1*16
  12331. -->
  12332. (S1 ^operator O1970 = -0.2383263875547442)
  12333. Retracting rl*prefer*rvt*predict-yes*H0*3
  12334. -->
  12335. (S1 ^operator O1969 = 0.6069237079409425)
  12336. Retracting rl*prefer*rvt*predict-yes*H0*3*H1*17
  12337. -->
  12338. (S1 ^operator O1969 = 0.3930696039411442)
  12339. --- END Proposal Phase ---
  12340. --- Decision Phase ---
  12341. RL update rl*prefer*rvt*predict-no*H0*2 1 0 1 -> 1 0 1(R,m,v=1,1,0)
  12342. =>WM: (13842: S1 ^operator O1971)
  12343. 986: O: O1971 (predict-yes)
  12344. --- END Decision Phase ---
  12345. --- Application Phase ---
  12346. --- Firing Productions (PE) For State At Depth 1 ---
  12347. --- Inner Elaboration Phase, active level 1 (S1) ---
  12348. Firing apply*operator
  12349. -->
  12350. (I3 ^predict-yes N986 + :O )
  12351. Firing apply*operator*complete
  12352. -->
  12353. (I3 ^predict-no N985 - :O )
  12354. inner elaboration loop at bottom goal.
  12355. --- Change Working Memory (PE) ---
  12356. =>WM: (13843: I3 ^predict-yes N986)
  12357. <=WM: (13829: N985 ^status complete)
  12358. <=WM: (13828: I3 ^predict-no N985)
  12359. --- Firing Productions (IE) For State At Depth 1 ---
  12360. --- Inner Elaboration Phase, active level 1 (S1) ---
  12361. Firing monitor*world
  12362. -->
  12363. I see 1 and I'm going to do: predict-yes inner elaboration loop at bottom goal.
  12364. --- Change Working Memory (IE) ---
  12365. --- END Application Phase ---
  12366. --- Output Phase ---
  12367. ENV: Agent did: predict-yes for direction L in state State-B
  12368. In State-B moving L
  12369. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  12370. predict error 0
  12371. dir: dir isL
  12372. --- END Output Phase ---
  12373. |\-/--- Input Phase ---
  12374. =>WM: (13847: I2 ^dir L)
  12375. =>WM: (13846: I2 ^reward 1)
  12376. =>WM: (13845: I2 ^see 1)
  12377. =>WM: (13844: N986 ^status complete)
  12378. <=WM: (13832: I2 ^dir L)
  12379. <=WM: (13831: I2 ^reward 1)
  12380. <=WM: (13830: I2 ^see 0)
  12381. =>WM: (13848: I2 ^level-1 L1-root)
  12382. <=WM: (13833: I2 ^level-1 R1-root)
  12383. --- END Input Phase ---
  12384. --- Proposal Phase ---
  12385. --- Inner Elaboration Phase, active level 1 (S1) ---
  12386. Firing rl*prefer*rvt*predict-yes*H0*3*H1*11
  12387. -->
  12388. (S1 ^operator O1971 = -0.03517433757196466)
  12389. Firing rl*prefer*rvt*predict-no*H0*4*H1*10
  12390. -->
  12391. (S1 ^operator O1972 = 0.5665066685463833)
  12392. Firing prefer*rvt*predict-no*H0*4*H1
  12393. -->
  12394. Firing prefer*rvt*predict-yes*H0*3*H1
  12395. -->
  12396. Firing elaborate*copy-see-to-output-link
  12397. -->
  12398. (I3 ^see 1 +)
  12399. Firing elaborate*reward*based*on*reward
  12400. -->
  12401. (R990 ^value 1 +)
  12402. (R1 ^reward R990 +)
  12403. Firing propose*predict-yes
  12404. -->
  12405. (O1973 ^name predict-yes +)
  12406. (S1 ^operator O1973 +)
  12407. Firing propose*predict-no
  12408. -->
  12409. (O1974 ^name predict-no +)
  12410. (S1 ^operator O1974 +)
  12411. Firing rl*prefer*rvt*predict-no*H0*4
  12412. -->
  12413. (S1 ^operator O1972 = 0.4334972820229208)
  12414. Firing rl*prefer*rvt*predict-yes*H0*3
  12415. -->
  12416. (S1 ^operator O1971 = 0.6069237079409425)
  12417. Firing prefer*rvt*predict-yes*H0
  12418. -->
  12419. Firing prefer*rvt*predict-no*H0
  12420. -->
  12421. Firing elaborate*copy-dir-to-output-link
  12422. -->
  12423. (I3 ^dir L +)
  12424. inner elaboration loop at bottom goal.
  12425. Retracting elaborate*copy-see-to-output-link
  12426. -->
  12427. (I3 ^see 0 +)
  12428. Retracting propose*predict-no
  12429. -->
  12430. (O1972 ^name predict-no +)
  12431. (S1 ^operator O1972 +)
  12432. Retracting propose*predict-yes
  12433. -->
  12434. (O1971 ^name predict-yes +)
  12435. (S1 ^operator O1971 +)
  12436. Retracting elaborate*reward*based*on*reward
  12437. -->
  12438. (R989 ^value 1 +)
  12439. (R1 ^reward R989 +)
  12440. Retracting elaborate*copy-dir-to-output-link
  12441. -->
  12442. (I3 ^dir L +)
  12443. Retracting rl*prefer*rvt*predict-no*H0*4
  12444. -->
  12445. (S1 ^operator O1972 = 0.4334972820229208)
  12446. Retracting rl*prefer*rvt*predict-no*H0*4*H1*16
  12447. -->
  12448. (S1 ^operator O1972 = -0.2383263875547442)
  12449. Retracting rl*prefer*rvt*predict-yes*H0*3
  12450. -->
  12451. (S1 ^operator O1971 = 0.6069237079409425)
  12452. Retracting rl*prefer*rvt*predict-yes*H0*3*H1*17
  12453. -->
  12454. (S1 ^operator O1971 = 0.3930696039411442)
  12455. =>WM: (13855: S1 ^operator O1974 +)
  12456. =>WM: (13854: S1 ^operator O1973 +)
  12457. =>WM: (13853: O1974 ^name predict-no)
  12458. =>WM: (13852: O1973 ^name predict-yes)
  12459. =>WM: (13851: R990 ^value 1)
  12460. =>WM: (13850: R1 ^reward R990)
  12461. =>WM: (13849: I3 ^see 1)
  12462. <=WM: (13840: S1 ^operator O1971 +)
  12463. <=WM: (13842: S1 ^operator O1971)
  12464. <=WM: (13841: S1 ^operator O1972 +)
  12465. <=WM: (13835: R1 ^reward R989)
  12466. <=WM: (13834: I3 ^see 0)
  12467. <=WM: (13838: O1972 ^name predict-no)
  12468. <=WM: (13837: O1971 ^name predict-yes)
  12469. <=WM: (13836: R989 ^value 1)
  12470. --- Inner Elaboration Phase, active level 1 (S1) ---
  12471. Firing prefer*rvt*predict-yes*H0
  12472. -->
  12473. Firing rl*prefer*rvt*predict-yes*H0*3
  12474. -->
  12475. (S1 ^operator O1973 = 0.6069237079409425)
  12476. Firing prefer*rvt*predict-yes*H0*3*H1
  12477. -->
  12478. Firing rl*prefer*rvt*predict-yes*H0*3*H1*11
  12479. -->
  12480. (S1 ^operator O1973 = -0.03517433757196466)
  12481. Firing prefer*rvt*predict-no*H0
  12482. -->
  12483. Firing rl*prefer*rvt*predict-no*H0*4
  12484. -->
  12485. (S1 ^operator O1974 = 0.4334972820229208)
  12486. Firing prefer*rvt*predict-no*H0*4*H1
  12487. -->
  12488. Firing rl*prefer*rvt*predict-no*H0*4*H1*10
  12489. -->
  12490. (S1 ^operator O1974 = 0.5665066685463833)
  12491. inner elaboration loop at bottom goal.
  12492. Retracting rl*prefer*rvt*predict-no*H0*4
  12493. -->
  12494. (S1 ^operator O1972 = 0.4334972820229208)
  12495. Retracting rl*prefer*rvt*predict-no*H0*4*H1*10
  12496. -->
  12497. (S1 ^operator O1972 = 0.5665066685463833)
  12498. Retracting rl*prefer*rvt*predict-yes*H0*3
  12499. -->
  12500. (S1 ^operator O1971 = 0.6069237079409425)
  12501. Retracting rl*prefer*rvt*predict-yes*H0*3*H1*11
  12502. -->
  12503. (S1 ^operator O1971 = -0.03517433757196466)
  12504. --- END Proposal Phase ---
  12505. --- Decision Phase ---
  12506. RL update rl*prefer*rvt*predict-yes*H0*3 0.656144 -0.0492204 0.606924 -> 0.656145 -0.0492204 0.606925(R,m,v=1,0.947368,0.0501917)
  12507. RL update rl*prefer*rvt*predict-yes*H0*3*H1*17 0.343849 0.0492201 0.39307 -> 0.34385 0.0492202 0.393071(R,m,v=1,1,0)
  12508. =>WM: (13856: S1 ^operator O1974)
  12509. 987: O: O1974 (predict-no)
  12510. --- END Decision Phase ---
  12511. --- Application Phase ---
  12512. --- Firing Productions (PE) For State At Depth 1 ---
  12513. --- Inner Elaboration Phase, active level 1 (S1) ---
  12514. Firing apply*operator
  12515. -->
  12516. (I3 ^predict-no N987 + :O )
  12517. Firing apply*operator*complete
  12518. -->
  12519. (I3 ^predict-yes N986 - :O )
  12520. inner elaboration loop at bottom goal.
  12521. --- Change Working Memory (PE) ---
  12522. =>WM: (13857: I3 ^predict-no N987)
  12523. <=WM: (13844: N986 ^status complete)
  12524. <=WM: (13843: I3 ^predict-yes N986)
  12525. --- Firing Productions (IE) For State At Depth 1 ---
  12526. --- Inner Elaboration Phase, active level 1 (S1) ---
  12527. Firing monitor*world
  12528. -->
  12529. I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
  12530. --- Change Working Memory (IE) ---
  12531. --- END Application Phase ---
  12532. --- Output Phase ---
  12533. ENV: Agent did: predict-no for direction L in state State-A
  12534. In State-A moving L
  12535. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  12536. predict error 0
  12537. dir: dir isR
  12538. --- END Output Phase ---
  12539. |\---- Input Phase ---
  12540. =>WM: (13861: I2 ^dir R)
  12541. =>WM: (13860: I2 ^reward 1)
  12542. =>WM: (13859: I2 ^see 0)
  12543. =>WM: (13858: N987 ^status complete)
  12544. <=WM: (13847: I2 ^dir L)
  12545. <=WM: (13846: I2 ^reward 1)
  12546. <=WM: (13845: I2 ^see 1)
  12547. =>WM: (13862: I2 ^level-1 L0-root)
  12548. <=WM: (13848: I2 ^level-1 L1-root)
  12549. --- END Input Phase ---
  12550. --- Proposal Phase ---
  12551. --- Inner Elaboration Phase, active level 1 (S1) ---
  12552. Firing rl*prefer*rvt*predict-yes*H0*5*H1*14
  12553. -->
  12554. (S1 ^operator O1973 = 0.9322244257854073)
  12555. Firing rl*prefer*rvt*predict-no*H0*6*H1*19
  12556. -->
  12557. (S1 ^operator O1974 = 0.3)
  12558. Firing prefer*rvt*predict-no*H0*6*H1
  12559. -->
  12560. Firing prefer*rvt*predict-yes*H0*5*H1
  12561. -->
  12562. Firing elaborate*copy-see-to-output-link
  12563. -->
  12564. (I3 ^see 0 +)
  12565. Firing elaborate*reward*based*on*reward
  12566. -->
  12567. (R991 ^value 1 +)
  12568. (R1 ^reward R991 +)
  12569. Firing propose*predict-yes
  12570. -->
  12571. (O1975 ^name predict-yes +)
  12572. (S1 ^operator O1975 +)
  12573. Firing propose*predict-no
  12574. -->
  12575. (O1976 ^name predict-no +)
  12576. (S1 ^operator O1976 +)
  12577. Firing rl*prefer*rvt*predict-no*H0*6
  12578. -->
  12579. (S1 ^operator O1974 = 0.4643591102356286)
  12580. Firing rl*prefer*rvt*predict-yes*H0*5
  12581. -->
  12582. (S1 ^operator O1973 = 0.06777565754866333)
  12583. Firing prefer*rvt*predict-yes*H0
  12584. -->
  12585. Firing prefer*rvt*predict-no*H0
  12586. -->
  12587. Firing elaborate*copy-dir-to-output-link
  12588. -->
  12589. (I3 ^dir R +)
  12590. inner elaboration loop at bottom goal.
  12591. Retracting elaborate*copy-see-to-output-link
  12592. -->
  12593. (I3 ^see 1 +)
  12594. Retracting propose*predict-no
  12595. -->
  12596. (O1974 ^name predict-no +)
  12597. (S1 ^operator O1974 +)
  12598. Retracting propose*predict-yes
  12599. -->
  12600. (O1973 ^name predict-yes +)
  12601. (S1 ^operator O1973 +)
  12602. Retracting elaborate*reward*based*on*reward
  12603. -->
  12604. (R990 ^value 1 +)
  12605. (R1 ^reward R990 +)
  12606. Retracting elaborate*copy-dir-to-output-link
  12607. -->
  12608. (I3 ^dir L +)
  12609. Retracting rl*prefer*rvt*predict-no*H0*4*H1*10
  12610. -->
  12611. (S1 ^operator O1974 = 0.5665066685463833)
  12612. Retracting rl*prefer*rvt*predict-no*H0*4
  12613. -->
  12614. (S1 ^operator O1974 = 0.4334972820229208)
  12615. Retracting rl*prefer*rvt*predict-yes*H0*3*H1*11
  12616. -->
  12617. (S1 ^operator O1973 = -0.03517433757196466)
  12618. Retracting rl*prefer*rvt*predict-yes*H0*3
  12619. -->
  12620. (S1 ^operator O1973 = 0.6069247111586296)
  12621. =>WM: (13870: S1 ^operator O1976 +)
  12622. =>WM: (13869: S1 ^operator O1975 +)
  12623. =>WM: (13868: I3 ^dir R)
  12624. =>WM: (13867: O1976 ^name predict-no)
  12625. =>WM: (13866: O1975 ^name predict-yes)
  12626. =>WM: (13865: R991 ^value 1)
  12627. =>WM: (13864: R1 ^reward R991)
  12628. =>WM: (13863: I3 ^see 0)
  12629. <=WM: (13854: S1 ^operator O1973 +)
  12630. <=WM: (13855: S1 ^operator O1974 +)
  12631. <=WM: (13856: S1 ^operator O1974)
  12632. <=WM: (13839: I3 ^dir L)
  12633. <=WM: (13850: R1 ^reward R990)
  12634. <=WM: (13849: I3 ^see 1)
  12635. <=WM: (13853: O1974 ^name predict-no)
  12636. <=WM: (13852: O1973 ^name predict-yes)
  12637. <=WM: (13851: R990 ^value 1)
  12638. --- Inner Elaboration Phase, active level 1 (S1) ---
  12639. Firing prefer*rvt*predict-yes*H0
  12640. -->
  12641. Firing rl*prefer*rvt*predict-yes*H0*5
  12642. -->
  12643. (S1 ^operator O1975 = 0.06777565754866333)
  12644. Firing prefer*rvt*predict-yes*H0*5*H1
  12645. -->
  12646. Firing rl*prefer*rvt*predict-yes*H0*5*H1*14
  12647. -->
  12648. (S1 ^operator O1975 = 0.9322244257854073)
  12649. Firing prefer*rvt*predict-no*H0
  12650. -->
  12651. Firing rl*prefer*rvt*predict-no*H0*6
  12652. -->
  12653. (S1 ^operator O1976 = 0.4643591102356286)
  12654. Firing prefer*rvt*predict-no*H0*6*H1
  12655. -->
  12656. Firing rl*prefer*rvt*predict-no*H0*6*H1*19
  12657. -->
  12658. (S1 ^operator O1976 = 0.3)
  12659. inner elaboration loop at bottom goal.
  12660. Retracting rl*prefer*rvt*predict-no*H0*6
  12661. -->
  12662. (S1 ^operator O1974 = 0.4643591102356286)
  12663. Retracting rl*prefer*rvt*predict-no*H0*6*H1*19
  12664. -->
  12665. (S1 ^operator O1974 = 0.3)
  12666. Retracting rl*prefer*rvt*predict-yes*H0*5
  12667. -->
  12668. (S1 ^operator O1973 = 0.06777565754866333)
  12669. Retracting rl*prefer*rvt*predict-yes*H0*5*H1*14
  12670. -->
  12671. (S1 ^operator O1973 = 0.9322244257854073)
  12672. --- END Proposal Phase ---
  12673. --- Decision Phase ---
  12674. RL update rl*prefer*rvt*predict-no*H0*4 0.490213 -0.056716 0.433497 -> 0.490213 -0.056716 0.433497(R,m,v=1,0.888199,0.0999224)
  12675. RL update rl*prefer*rvt*predict-no*H0*4*H1*10 0.509791 0.056716 0.566507 -> 0.50979 0.056716 0.566506(R,m,v=1,1,0)
  12676. =>WM: (13871: S1 ^operator O1975)
  12677. 988: O: O1975 (predict-yes)
  12678. --- END Decision Phase ---
  12679. --- Application Phase ---
  12680. --- Firing Productions (PE) For State At Depth 1 ---
  12681. --- Inner Elaboration Phase, active level 1 (S1) ---
  12682. Firing apply*operator
  12683. -->
  12684. (I3 ^predict-yes N988 + :O )
  12685. Firing apply*operator*complete
  12686. -->
  12687. (I3 ^predict-no N987 - :O )
  12688. inner elaboration loop at bottom goal.
  12689. --- Change Working Memory (PE) ---
  12690. =>WM: (13872: I3 ^predict-yes N988)
  12691. <=WM: (13858: N987 ^status complete)
  12692. <=WM: (13857: I3 ^predict-no N987)
  12693. --- Firing Productions (IE) For State At Depth 1 ---
  12694. --- Inner Elaboration Phase, active level 1 (S1) ---
  12695. Firing monitor*world
  12696. -->
  12697. I see 1 and I'm going to do: predict-yes inner elaboration loop at bottom goal.
  12698. --- Change Working Memory (IE) ---
  12699. --- END Application Phase ---
  12700. --- Output Phase ---
  12701. ENV: Agent did: predict-yes for direction R in state State-A
  12702. In State-A moving R
  12703. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  12704. predict error 0
  12705. dir: dir isR
  12706. --- END Output Phase ---
  12707. /|\--- Input Phase ---
  12708. =>WM: (13876: I2 ^dir R)
  12709. =>WM: (13875: I2 ^reward 1)
  12710. =>WM: (13874: I2 ^see 1)
  12711. =>WM: (13873: N988 ^status complete)
  12712. <=WM: (13861: I2 ^dir R)
  12713. <=WM: (13860: I2 ^reward 1)
  12714. <=WM: (13859: I2 ^see 0)
  12715. =>WM: (13877: I2 ^level-1 R1-root)
  12716. <=WM: (13862: I2 ^level-1 L0-root)
  12717. --- END Input Phase ---
  12718. --- Proposal Phase ---
  12719. --- Inner Elaboration Phase, active level 1 (S1) ---
  12720. Firing rl*prefer*rvt*predict-no*H0*6*H1*20
  12721. -->
  12722. (S1 ^operator O1976 = 0.5356415064941802)
  12723. Firing rl*prefer*rvt*predict-yes*H0*5*H1*15
  12724. -->
  12725. (S1 ^operator O1975 = 0.2653409704952874)
  12726. Firing prefer*rvt*predict-no*H0*6*H1
  12727. -->
  12728. Firing prefer*rvt*predict-yes*H0*5*H1
  12729. -->
  12730. Firing elaborate*copy-see-to-output-link
  12731. -->
  12732. (I3 ^see 1 +)
  12733. Firing elaborate*reward*based*on*reward
  12734. -->
  12735. (R992 ^value 1 +)
  12736. (R1 ^reward R992 +)
  12737. Firing propose*predict-yes
  12738. -->
  12739. (O1977 ^name predict-yes +)
  12740. (S1 ^operator O1977 +)
  12741. Firing propose*predict-no
  12742. -->
  12743. (O1978 ^name predict-no +)
  12744. (S1 ^operator O1978 +)
  12745. Firing rl*prefer*rvt*predict-no*H0*6
  12746. -->
  12747. (S1 ^operator O1976 = 0.4643591102356286)
  12748. Firing rl*prefer*rvt*predict-yes*H0*5
  12749. -->
  12750. (S1 ^operator O1975 = 0.06777565754866333)
  12751. Firing prefer*rvt*predict-yes*H0
  12752. -->
  12753. Firing prefer*rvt*predict-no*H0
  12754. -->
  12755. Firing elaborate*copy-dir-to-output-link
  12756. -->
  12757. (I3 ^dir R +)
  12758. inner elaboration loop at bottom goal.
  12759. Retracting elaborate*copy-see-to-output-link
  12760. -->
  12761. (I3 ^see 0 +)
  12762. Retracting propose*predict-no
  12763. -->
  12764. (O1976 ^name predict-no +)
  12765. (S1 ^operator O1976 +)
  12766. Retracting propose*predict-yes
  12767. -->
  12768. (O1975 ^name predict-yes +)
  12769. (S1 ^operator O1975 +)
  12770. Retracting elaborate*reward*based*on*reward
  12771. -->
  12772. (R991 ^value 1 +)
  12773. (R1 ^reward R991 +)
  12774. Retracting elaborate*copy-dir-to-output-link
  12775. -->
  12776. (I3 ^dir R +)
  12777. Retracting rl*prefer*rvt*predict-no*H0*6*H1*19
  12778. -->
  12779. (S1 ^operator O1976 = 0.3)
  12780. Retracting rl*prefer*rvt*predict-no*H0*6
  12781. -->
  12782. (S1 ^operator O1976 = 0.4643591102356286)
  12783. Retracting rl*prefer*rvt*predict-yes*H0*5*H1*14
  12784. -->
  12785. (S1 ^operator O1975 = 0.9322244257854073)
  12786. Retracting rl*prefer*rvt*predict-yes*H0*5
  12787. -->
  12788. (S1 ^operator O1975 = 0.06777565754866333)
  12789. =>WM: (13884: S1 ^operator O1978 +)
  12790. =>WM: (13883: S1 ^operator O1977 +)
  12791. =>WM: (13882: O1978 ^name predict-no)
  12792. =>WM: (13881: O1977 ^name predict-yes)
  12793. =>WM: (13880: R992 ^value 1)
  12794. =>WM: (13879: R1 ^reward R992)
  12795. =>WM: (13878: I3 ^see 1)
  12796. <=WM: (13869: S1 ^operator O1975 +)
  12797. <=WM: (13871: S1 ^operator O1975)
  12798. <=WM: (13870: S1 ^operator O1976 +)
  12799. <=WM: (13864: R1 ^reward R991)
  12800. <=WM: (13863: I3 ^see 0)
  12801. <=WM: (13867: O1976 ^name predict-no)
  12802. <=WM: (13866: O1975 ^name predict-yes)
  12803. <=WM: (13865: R991 ^value 1)
  12804. --- Inner Elaboration Phase, active level 1 (S1) ---
  12805. Firing prefer*rvt*predict-yes*H0
  12806. -->
  12807. Firing rl*prefer*rvt*predict-yes*H0*5
  12808. -->
  12809. (S1 ^operator O1977 = 0.06777565754866333)
  12810. Firing prefer*rvt*predict-yes*H0*5*H1
  12811. -->
  12812. Firing rl*prefer*rvt*predict-yes*H0*5*H1*15
  12813. -->
  12814. (S1 ^operator O1977 = 0.2653409704952874)
  12815. Firing prefer*rvt*predict-no*H0
  12816. -->
  12817. Firing rl*prefer*rvt*predict-no*H0*6
  12818. -->
  12819. (S1 ^operator O1978 = 0.4643591102356286)
  12820. Firing prefer*rvt*predict-no*H0*6*H1
  12821. -->
  12822. Firing rl*prefer*rvt*predict-no*H0*6*H1*20
  12823. -->
  12824. (S1 ^operator O1978 = 0.5356415064941802)
  12825. inner elaboration loop at bottom goal.
  12826. Retracting rl*prefer*rvt*predict-no*H0*6
  12827. -->
  12828. (S1 ^operator O1976 = 0.4643591102356286)
  12829. Retracting rl*prefer*rvt*predict-no*H0*6*H1*20
  12830. -->
  12831. (S1 ^operator O1976 = 0.5356415064941802)
  12832. Retracting rl*prefer*rvt*predict-yes*H0*5
  12833. -->
  12834. (S1 ^operator O1975 = 0.06777565754866333)
  12835. Retracting rl*prefer*rvt*predict-yes*H0*5*H1*15
  12836. -->
  12837. (S1 ^operator O1975 = 0.2653409704952874)
  12838. --- END Proposal Phase ---
  12839. --- Decision Phase ---
  12840. RL update rl*prefer*rvt*predict-yes*H0*5 0.606208 -0.538432 0.0677757 -> 0.606208 -0.538432 0.0677756(R,m,v=1,0.872928,0.111541)
  12841. RL update rl*prefer*rvt*predict-yes*H0*5*H1*14 0.393792 0.538432 0.932224 -> 0.393792 0.538432 0.932224(R,m,v=1,1,0)
  12842. =>WM: (13885: S1 ^operator O1978)
  12843. 989: O: O1978 (predict-no)
  12844. --- END Decision Phase ---
  12845. --- Application Phase ---
  12846. --- Firing Productions (PE) For State At Depth 1 ---
  12847. --- Inner Elaboration Phase, active level 1 (S1) ---
  12848. Firing apply*operator
  12849. -->
  12850. (I3 ^predict-no N989 + :O )
  12851. Firing apply*operator*complete
  12852. -->
  12853. (I3 ^predict-yes N988 - :O )
  12854. inner elaboration loop at bottom goal.
  12855. --- Change Working Memory (PE) ---
  12856. =>WM: (13886: I3 ^predict-no N989)
  12857. <=WM: (13873: N988 ^status complete)
  12858. <=WM: (13872: I3 ^predict-yes N988)
  12859. --- Firing Productions (IE) For State At Depth 1 ---
  12860. --- Inner Elaboration Phase, active level 1 (S1) ---
  12861. Firing monitor*world
  12862. -->
  12863. I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
  12864. --- Change Working Memory (IE) ---
  12865. --- END Application Phase ---
  12866. --- Output Phase ---
  12867. ENV: Agent did: predict-no for direction R in state State-B
  12868. In State-B moving R
  12869. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  12870. predict error 0
  12871. dir: dir isU
  12872. --- END Output Phase ---
  12873. -/--- Input Phase ---
  12874. =>WM: (13890: I2 ^dir U)
  12875. =>WM: (13889: I2 ^reward 1)
  12876. =>WM: (13888: I2 ^see 0)
  12877. =>WM: (13887: N989 ^status complete)
  12878. <=WM: (13876: I2 ^dir R)
  12879. <=WM: (13875: I2 ^reward 1)
  12880. <=WM: (13874: I2 ^see 1)
  12881. =>WM: (13891: I2 ^level-1 R0-root)
  12882. <=WM: (13877: I2 ^level-1 R1-root)
  12883. --- END Input Phase ---
  12884. --- Proposal Phase ---
  12885. --- Inner Elaboration Phase, active level 1 (S1) ---
  12886. Firing elaborate*copy-see-to-output-link
  12887. -->
  12888. (I3 ^see 0 +)
  12889. Firing elaborate*reward*based*on*reward
  12890. -->
  12891. (R993 ^value 1 +)
  12892. (R1 ^reward R993 +)
  12893. Firing propose*predict-yes
  12894. -->
  12895. (O1979 ^name predict-yes +)
  12896. (S1 ^operator O1979 +)
  12897. Firing propose*predict-no
  12898. -->
  12899. (O1980 ^name predict-no +)
  12900. (S1 ^operator O1980 +)
  12901. Firing rl*prefer*rvt*predict-no*H0*2
  12902. -->
  12903. (S1 ^operator O1978 = 0.9999999999999999)
  12904. Firing rl*prefer*rvt*predict-yes*H0*1
  12905. -->
  12906. (S1 ^operator O1977 = 0.)
  12907. Firing prefer*rvt*predict-yes*H0
  12908. -->
  12909. Firing prefer*rvt*predict-no*H0
  12910. -->
  12911. Firing elaborate*copy-dir-to-output-link
  12912. -->
  12913. (I3 ^dir U +)
  12914. inner elaboration loop at bottom goal.
  12915. Retracting elaborate*copy-see-to-output-link
  12916. -->
  12917. (I3 ^see 1 +)
  12918. Retracting propose*predict-no
  12919. -->
  12920. (O1978 ^name predict-no +)
  12921. (S1 ^operator O1978 +)
  12922. Retracting propose*predict-yes
  12923. -->
  12924. (O1977 ^name predict-yes +)
  12925. (S1 ^operator O1977 +)
  12926. Retracting elaborate*reward*based*on*reward
  12927. -->
  12928. (R992 ^value 1 +)
  12929. (R1 ^reward R992 +)
  12930. Retracting elaborate*copy-dir-to-output-link
  12931. -->
  12932. (I3 ^dir R +)
  12933. Retracting rl*prefer*rvt*predict-no*H0*6*H1*20
  12934. -->
  12935. (S1 ^operator O1978 = 0.5356415064941802)
  12936. Retracting rl*prefer*rvt*predict-no*H0*6
  12937. -->
  12938. (S1 ^operator O1978 = 0.4643591102356286)
  12939. Retracting rl*prefer*rvt*predict-yes*H0*5*H1*15
  12940. -->
  12941. (S1 ^operator O1977 = 0.2653409704952874)
  12942. Retracting rl*prefer*rvt*predict-yes*H0*5
  12943. -->
  12944. (S1 ^operator O1977 = 0.06777564504855271)
  12945. =>WM: (13899: S1 ^operator O1980 +)
  12946. =>WM: (13898: S1 ^operator O1979 +)
  12947. =>WM: (13897: I3 ^dir U)
  12948. =>WM: (13896: O1980 ^name predict-no)
  12949. =>WM: (13895: O1979 ^name predict-yes)
  12950. =>WM: (13894: R993 ^value 1)
  12951. =>WM: (13893: R1 ^reward R993)
  12952. =>WM: (13892: I3 ^see 0)
  12953. <=WM: (13883: S1 ^operator O1977 +)
  12954. <=WM: (13884: S1 ^operator O1978 +)
  12955. <=WM: (13885: S1 ^operator O1978)
  12956. <=WM: (13868: I3 ^dir R)
  12957. <=WM: (13879: R1 ^reward R992)
  12958. <=WM: (13878: I3 ^see 1)
  12959. <=WM: (13882: O1978 ^name predict-no)
  12960. <=WM: (13881: O1977 ^name predict-yes)
  12961. <=WM: (13880: R992 ^value 1)
  12962. --- Inner Elaboration Phase, active level 1 (S1) ---
  12963. Firing prefer*rvt*predict-yes*H0
  12964. -->
  12965. Firing rl*prefer*rvt*predict-yes*H0*1
  12966. -->
  12967. (S1 ^operator O1979 = 0.)
  12968. Firing prefer*rvt*predict-no*H0
  12969. -->
  12970. Firing rl*prefer*rvt*predict-no*H0*2
  12971. -->
  12972. (S1 ^operator O1980 = 0.9999999999999999)
  12973. inner elaboration loop at bottom goal.
  12974. Retracting rl*prefer*rvt*predict-no*H0*2
  12975. -->
  12976. (S1 ^operator O1978 = 0.9999999999999999)
  12977. Retracting rl*prefer*rvt*predict-yes*H0*1
  12978. -->
  12979. (S1 ^operator O1977 = 0.)
  12980. --- END Proposal Phase ---
  12981. --- Decision Phase ---
  12982. RL update rl*prefer*rvt*predict-no*H0*6 0.679081 -0.214722 0.464359 -> 0.679081 -0.214722 0.464359(R,m,v=1,0.97076,0.0285518)
  12983. RL update rl*prefer*rvt*predict-no*H0*6*H1*20 0.32092 0.214722 0.535642 -> 0.32092 0.214722 0.535641(R,m,v=1,1,0)
  12984. =>WM: (13900: S1 ^operator O1980)
  12985. 990: O: O1980 (predict-no)
  12986. --- END Decision Phase ---
  12987. --- Application Phase ---
  12988. --- Firing Productions (PE) For State At Depth 1 ---
  12989. --- Inner Elaboration Phase, active level 1 (S1) ---
  12990. Firing apply*operator
  12991. -->
  12992. (I3 ^predict-no N990 + :O )
  12993. Firing apply*operator*complete
  12994. -->
  12995. (I3 ^predict-no N989 - :O )
  12996. inner elaboration loop at bottom goal.
  12997. --- Change Working Memory (PE) ---
  12998. =>WM: (13901: I3 ^predict-no N990)
  12999. <=WM: (13887: N989 ^status complete)
  13000. <=WM: (13886: I3 ^predict-no N989)
  13001. --- Firing Productions (IE) For State At Depth 1 ---
  13002. --- Inner Elaboration Phase, active level 1 (S1) ---
  13003. Firing monitor*world
  13004. -->
  13005. I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
  13006. --- Change Working Memory (IE) ---
  13007. --- END Application Phase ---
  13008. --- Output Phase ---
  13009. ENV: Agent did: predict-no for direction U in state State-B
  13010. In State-B moving U
  13011. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  13012. predict error 0
  13013. dir: dir isR
  13014. --- END Output Phase ---
  13015. |\---- Input Phase ---
  13016. =>WM: (13905: I2 ^dir R)
  13017. =>WM: (13904: I2 ^reward 1)
  13018. =>WM: (13903: I2 ^see 0)
  13019. =>WM: (13902: N990 ^status complete)
  13020. <=WM: (13890: I2 ^dir U)
  13021. <=WM: (13889: I2 ^reward 1)
  13022. <=WM: (13888: I2 ^see 0)
  13023. =>WM: (13906: I2 ^level-1 R0-root)
  13024. <=WM: (13891: I2 ^level-1 R0-root)
  13025. --- END Input Phase ---
  13026. --- Proposal Phase ---
  13027. --- Inner Elaboration Phase, active level 1 (S1) ---
  13028. Firing rl*prefer*rvt*predict-no*H0*6*H1*22
  13029. -->
  13030. (S1 ^operator O1980 = 0.5356385439365152)
  13031. Firing rl*prefer*rvt*predict-yes*H0*5*H1*7
  13032. -->
  13033. (S1 ^operator O1979 = 0.0787273604177588)
  13034. Firing prefer*rvt*predict-no*H0*6*H1
  13035. -->
  13036. Firing prefer*rvt*predict-yes*H0*5*H1
  13037. -->
  13038. Firing elaborate*copy-see-to-output-link
  13039. -->
  13040. (I3 ^see 0 +)
  13041. Firing elaborate*reward*based*on*reward
  13042. -->
  13043. (R994 ^value 1 +)
  13044. (R1 ^reward R994 +)
  13045. Firing propose*predict-yes
  13046. -->
  13047. (O1981 ^name predict-yes +)
  13048. (S1 ^operator O1981 +)
  13049. Firing propose*predict-no
  13050. -->
  13051. (O1982 ^name predict-no +)
  13052. (S1 ^operator O1982 +)
  13053. Firing rl*prefer*rvt*predict-no*H0*6
  13054. -->
  13055. (S1 ^operator O1980 = 0.4643590177261572)
  13056. Firing rl*prefer*rvt*predict-yes*H0*5
  13057. -->
  13058. (S1 ^operator O1979 = 0.06777564504855271)
  13059. Firing prefer*rvt*predict-yes*H0
  13060. -->
  13061. Firing prefer*rvt*predict-no*H0
  13062. -->
  13063. Firing elaborate*copy-dir-to-output-link
  13064. -->
  13065. (I3 ^dir R +)
  13066. inner elaboration loop at bottom goal.
  13067. Retracting elaborate*copy-see-to-output-link
  13068. -->
  13069. (I3 ^see 0 +)
  13070. Retracting propose*predict-no
  13071. -->
  13072. (O1980 ^name predict-no +)
  13073. (S1 ^operator O1980 +)
  13074. Retracting propose*predict-yes
  13075. -->
  13076. (O1979 ^name predict-yes +)
  13077. (S1 ^operator O1979 +)
  13078. Retracting elaborate*reward*based*on*reward
  13079. -->
  13080. (R993 ^value 1 +)
  13081. (R1 ^reward R993 +)
  13082. Retracting elaborate*copy-dir-to-output-link
  13083. -->
  13084. (I3 ^dir U +)
  13085. Retracting rl*prefer*rvt*predict-no*H0*2
  13086. -->
  13087. (S1 ^operator O1980 = 0.9999999999999999)
  13088. Retracting rl*prefer*rvt*predict-yes*H0*1
  13089. -->
  13090. (S1 ^operator O1979 = 0.)
  13091. =>WM: (13913: S1 ^operator O1982 +)
  13092. =>WM: (13912: S1 ^operator O1981 +)
  13093. =>WM: (13911: I3 ^dir R)
  13094. =>WM: (13910: O1982 ^name predict-no)
  13095. =>WM: (13909: O1981 ^name predict-yes)
  13096. =>WM: (13908: R994 ^value 1)
  13097. =>WM: (13907: R1 ^reward R994)
  13098. <=WM: (13898: S1 ^operator O1979 +)
  13099. <=WM: (13899: S1 ^operator O1980 +)
  13100. <=WM: (13900: S1 ^operator O1980)
  13101. <=WM: (13897: I3 ^dir U)
  13102. <=WM: (13893: R1 ^reward R993)
  13103. <=WM: (13896: O1980 ^name predict-no)
  13104. <=WM: (13895: O1979 ^name predict-yes)
  13105. <=WM: (13894: R993 ^value 1)
  13106. --- Inner Elaboration Phase, active level 1 (S1) ---
  13107. Firing prefer*rvt*predict-yes*H0
  13108. -->
  13109. Firing rl*prefer*rvt*predict-yes*H0*5*H1*7
  13110. -->
  13111. (S1 ^operator O1981 = 0.0787273604177588)
  13112. Firing rl*prefer*rvt*predict-yes*H0*5
  13113. -->
  13114. (S1 ^operator O1981 = 0.06777564504855271)
  13115. Firing prefer*rvt*predict-yes*H0*5*H1
  13116. -->
  13117. Firing prefer*rvt*predict-no*H0
  13118. -->
  13119. Firing rl*prefer*rvt*predict-no*H0*6*H1*22
  13120. -->
  13121. (S1 ^operator O1982 = 0.5356385439365152)
  13122. Firing rl*prefer*rvt*predict-no*H0*6
  13123. -->
  13124. (S1 ^operator O1982 = 0.4643590177261572)
  13125. Firing prefer*rvt*predict-no*H0*6*H1
  13126. -->
  13127. inner elaboration loop at bottom goal.
  13128. Retracting rl*prefer*rvt*predict-no*H0*6
  13129. -->
  13130. (S1 ^operator O1980 = 0.4643590177261572)
  13131. Retracting rl*prefer*rvt*predict-no*H0*6*H1*22
  13132. -->
  13133. (S1 ^operator O1980 = 0.5356385439365152)
  13134. Retracting rl*prefer*rvt*predict-yes*H0*5
  13135. -->
  13136. (S1 ^operator O1979 = 0.06777564504855271)
  13137. Retracting rl*prefer*rvt*predict-yes*H0*5*H1*7
  13138. -->
  13139. (S1 ^operator O1979 = 0.0787273604177588)
  13140. --- END Proposal Phase ---
  13141. --- Decision Phase ---
  13142. RL update rl*prefer*rvt*predict-no*H0*2 1 0 1 -> 1 0 1(R,m,v=1,1,0)
  13143. =>WM: (13914: S1 ^operator O1982)
  13144. 991: O: O1982 (predict-no)
  13145. --- END Decision Phase ---
  13146. --- Application Phase ---
  13147. --- Firing Productions (PE) For State At Depth 1 ---
  13148. --- Inner Elaboration Phase, active level 1 (S1) ---
  13149. Firing apply*operator
  13150. -->
  13151. (I3 ^predict-no N991 + :O )
  13152. Firing apply*operator*complete
  13153. -->
  13154. (I3 ^predict-no N990 - :O )
  13155. inner elaboration loop at bottom goal.
  13156. --- Change Working Memory (PE) ---
  13157. =>WM: (13915: I3 ^predict-no N991)
  13158. <=WM: (13902: N990 ^status complete)
  13159. <=WM: (13901: I3 ^predict-no N990)
  13160. --- Firing Productions (IE) For State At Depth 1 ---
  13161. --- Inner Elaboration Phase, active level 1 (S1) ---
  13162. Firing monitor*world
  13163. -->
  13164. I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
  13165. --- Change Working Memory (IE) ---
  13166. --- END Application Phase ---
  13167. --- Output Phase ---
  13168. ENV: Agent did: predict-no for direction R in state State-B
  13169. In State-B moving R
  13170. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  13171. predict error 0
  13172. dir: dir isU
  13173. --- END Output Phase ---
  13174. /--- Input Phase ---
  13175. =>WM: (13919: I2 ^dir U)
  13176. =>WM: (13918: I2 ^reward 1)
  13177. =>WM: (13917: I2 ^see 0)
  13178. =>WM: (13916: N991 ^status complete)
  13179. <=WM: (13905: I2 ^dir R)
  13180. <=WM: (13904: I2 ^reward 1)
  13181. <=WM: (13903: I2 ^see 0)
  13182. =>WM: (13920: I2 ^level-1 R0-root)
  13183. <=WM: (13906: I2 ^level-1 R0-root)
  13184. --- END Input Phase ---
  13185. --- Proposal Phase ---
  13186. --- Inner Elaboration Phase, active level 1 (S1) ---
  13187. Firing elaborate*copy-see-to-output-link
  13188. -->
  13189. (I3 ^see 0 +)
  13190. Firing elaborate*reward*based*on*reward
  13191. -->
  13192. (R995 ^value 1 +)
  13193. (R1 ^reward R995 +)
  13194. Firing propose*predict-yes
  13195. -->
  13196. (O1983 ^name predict-yes +)
  13197. (S1 ^operator O1983 +)
  13198. Firing propose*predict-no
  13199. -->
  13200. (O1984 ^name predict-no +)
  13201. (S1 ^operator O1984 +)
  13202. Firing rl*prefer*rvt*predict-no*H0*2
  13203. -->
  13204. (S1 ^operator O1982 = 0.9999999999999999)
  13205. Firing rl*prefer*rvt*predict-yes*H0*1
  13206. -->
  13207. (S1 ^operator O1981 = 0.)
  13208. Firing prefer*rvt*predict-yes*H0
  13209. -->
  13210. Firing prefer*rvt*predict-no*H0
  13211. -->
  13212. Firing elaborate*copy-dir-to-output-link
  13213. -->
  13214. (I3 ^dir U +)
  13215. inner elaboration loop at bottom goal.
  13216. Retracting elaborate*copy-see-to-output-link
  13217. -->
  13218. (I3 ^see 0 +)
  13219. Retracting propose*predict-no
  13220. -->
  13221. (O1982 ^name predict-no +)
  13222. (S1 ^operator O1982 +)
  13223. Retracting propose*predict-yes
  13224. -->
  13225. (O1981 ^name predict-yes +)
  13226. (S1 ^operator O1981 +)
  13227. Retracting elaborate*reward*based*on*reward
  13228. -->
  13229. (R994 ^value 1 +)
  13230. (R1 ^reward R994 +)
  13231. Retracting elaborate*copy-dir-to-output-link
  13232. -->
  13233. (I3 ^dir R +)
  13234. Retracting rl*prefer*rvt*predict-no*H0*6
  13235. -->
  13236. (S1 ^operator O1982 = 0.4643590177261572)
  13237. Retracting rl*prefer*rvt*predict-no*H0*6*H1*22
  13238. -->
  13239. (S1 ^operator O1982 = 0.5356385439365152)
  13240. Retracting rl*prefer*rvt*predict-yes*H0*5
  13241. -->
  13242. (S1 ^operator O1981 = 0.06777564504855271)
  13243. Retracting rl*prefer*rvt*predict-yes*H0*5*H1*7
  13244. -->
  13245. (S1 ^operator O1981 = 0.0787273604177588)
  13246. =>WM: (13927: S1 ^operator O1984 +)
  13247. =>WM: (13926: S1 ^operator O1983 +)
  13248. =>WM: (13925: I3 ^dir U)
  13249. =>WM: (13924: O1984 ^name predict-no)
  13250. =>WM: (13923: O1983 ^name predict-yes)
  13251. =>WM: (13922: R995 ^value 1)
  13252. =>WM: (13921: R1 ^reward R995)
  13253. <=WM: (13912: S1 ^operator O1981 +)
  13254. <=WM: (13913: S1 ^operator O1982 +)
  13255. <=WM: (13914: S1 ^operator O1982)
  13256. <=WM: (13911: I3 ^dir R)
  13257. <=WM: (13907: R1 ^reward R994)
  13258. <=WM: (13910: O1982 ^name predict-no)
  13259. <=WM: (13909: O1981 ^name predict-yes)
  13260. <=WM: (13908: R994 ^value 1)
  13261. --- Inner Elaboration Phase, active level 1 (S1) ---
  13262. Firing prefer*rvt*predict-yes*H0
  13263. -->
  13264. Firing rl*prefer*rvt*predict-yes*H0*1
  13265. -->
  13266. (S1 ^operator O1983 = 0.)
  13267. Firing prefer*rvt*predict-no*H0
  13268. -->
  13269. Firing rl*prefer*rvt*predict-no*H0*2
  13270. -->
  13271. (S1 ^operator O1984 = 0.9999999999999999)
  13272. inner elaboration loop at bottom goal.
  13273. Retracting rl*prefer*rvt*predict-no*H0*2
  13274. -->
  13275. (S1 ^operator O1982 = 0.9999999999999999)
  13276. Retracting rl*prefer*rvt*predict-yes*H0*1
  13277. -->
  13278. (S1 ^operator O1981 = 0.)
  13279. --- END Proposal Phase ---
  13280. --- Decision Phase ---
  13281. RL update rl*prefer*rvt*predict-no*H0*6 0.679081 -0.214722 0.464359 -> 0.679081 -0.214722 0.464359(R,m,v=1,0.97093,0.0283898)
  13282. RL update rl*prefer*rvt*predict-no*H0*6*H1*22 0.320916 0.214722 0.535639 -> 0.320917 0.214722 0.535639(R,m,v=1,1,0)
  13283. =>WM: (13928: S1 ^operator O1984)
  13284. 992: O: O1984 (predict-no)
  13285. --- END Decision Phase ---
  13286. --- Application Phase ---
  13287. --- Firing Productions (PE) For State At Depth 1 ---
  13288. --- Inner Elaboration Phase, active level 1 (S1) ---
  13289. Firing apply*operator
  13290. -->
  13291. (I3 ^predict-no N992 + :O )
  13292. Firing apply*operator*complete
  13293. -->
  13294. (I3 ^predict-no N991 - :O )
  13295. inner elaboration loop at bottom goal.
  13296. --- Change Working Memory (PE) ---
  13297. =>WM: (13929: I3 ^predict-no N992)
  13298. <=WM: (13916: N991 ^status complete)
  13299. <=WM: (13915: I3 ^predict-no N991)
  13300. --- Firing Productions (IE) For State At Depth 1 ---
  13301. --- Inner Elaboration Phase, active level 1 (S1) ---
  13302. Firing monitor*world
  13303. -->
  13304. I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
  13305. --- Change Working Memory (IE) ---
  13306. --- END Application Phase ---
  13307. --- Output Phase ---
  13308. ENV: Agent did: predict-no for direction U in state State-B
  13309. In State-B moving U
  13310. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  13311. predict error 0
  13312. dir: dir isL
  13313. --- END Output Phase ---
  13314. |\---- Input Phase ---
  13315. =>WM: (13933: I2 ^dir L)
  13316. =>WM: (13932: I2 ^reward 1)
  13317. =>WM: (13931: I2 ^see 0)
  13318. =>WM: (13930: N992 ^status complete)
  13319. <=WM: (13919: I2 ^dir U)
  13320. <=WM: (13918: I2 ^reward 1)
  13321. <=WM: (13917: I2 ^see 0)
  13322. =>WM: (13934: I2 ^level-1 R0-root)
  13323. <=WM: (13920: I2 ^level-1 R0-root)
  13324. --- END Input Phase ---
  13325. --- Proposal Phase ---
  13326. --- Inner Elaboration Phase, active level 1 (S1) ---
  13327. Firing rl*prefer*rvt*predict-no*H0*4*H1*8
  13328. -->
  13329. (S1 ^operator O1984 = -0.2450868666562052)
  13330. Firing rl*prefer*rvt*predict-yes*H0*3*H1*9
  13331. -->
  13332. (S1 ^operator O1983 = 0.3930884415717635)
  13333. Firing prefer*rvt*predict-no*H0*4*H1
  13334. -->
  13335. Firing prefer*rvt*predict-yes*H0*3*H1
  13336. -->
  13337. Firing elaborate*copy-see-to-output-link
  13338. -->
  13339. (I3 ^see 0 +)
  13340. Firing elaborate*reward*based*on*reward
  13341. -->
  13342. (R996 ^value 1 +)
  13343. (R1 ^reward R996 +)
  13344. Firing propose*predict-yes
  13345. -->
  13346. (O1985 ^name predict-yes +)
  13347. (S1 ^operator O1985 +)
  13348. Firing propose*predict-no
  13349. -->
  13350. (O1986 ^name predict-no +)
  13351. (S1 ^operator O1986 +)
  13352. Firing rl*prefer*rvt*predict-no*H0*4
  13353. -->
  13354. (S1 ^operator O1984 = 0.4334966894375252)
  13355. Firing rl*prefer*rvt*predict-yes*H0*3
  13356. -->
  13357. (S1 ^operator O1983 = 0.6069247111586296)
  13358. Firing prefer*rvt*predict-yes*H0
  13359. -->
  13360. Firing prefer*rvt*predict-no*H0
  13361. -->
  13362. Firing elaborate*copy-dir-to-output-link
  13363. -->
  13364. (I3 ^dir L +)
  13365. inner elaboration loop at bottom goal.
  13366. Retracting elaborate*copy-see-to-output-link
  13367. -->
  13368. (I3 ^see 0 +)
  13369. Retracting propose*predict-no
  13370. -->
  13371. (O1984 ^name predict-no +)
  13372. (S1 ^operator O1984 +)
  13373. Retracting propose*predict-yes
  13374. -->
  13375. (O1983 ^name predict-yes +)
  13376. (S1 ^operator O1983 +)
  13377. Retracting elaborate*reward*based*on*reward
  13378. -->
  13379. (R995 ^value 1 +)
  13380. (R1 ^reward R995 +)
  13381. Retracting elaborate*copy-dir-to-output-link
  13382. -->
  13383. (I3 ^dir U +)
  13384. Retracting rl*prefer*rvt*predict-no*H0*2
  13385. -->
  13386. (S1 ^operator O1984 = 0.9999999999999999)
  13387. Retracting rl*prefer*rvt*predict-yes*H0*1
  13388. -->
  13389. (S1 ^operator O1983 = 0.)
  13390. =>WM: (13941: S1 ^operator O1986 +)
  13391. =>WM: (13940: S1 ^operator O1985 +)
  13392. =>WM: (13939: I3 ^dir L)
  13393. =>WM: (13938: O1986 ^name predict-no)
  13394. =>WM: (13937: O1985 ^name predict-yes)
  13395. =>WM: (13936: R996 ^value 1)
  13396. =>WM: (13935: R1 ^reward R996)
  13397. <=WM: (13926: S1 ^operator O1983 +)
  13398. <=WM: (13927: S1 ^operator O1984 +)
  13399. <=WM: (13928: S1 ^operator O1984)
  13400. <=WM: (13925: I3 ^dir U)
  13401. <=WM: (13921: R1 ^reward R995)
  13402. <=WM: (13924: O1984 ^name predict-no)
  13403. <=WM: (13923: O1983 ^name predict-yes)
  13404. <=WM: (13922: R995 ^value 1)
  13405. --- Inner Elaboration Phase, active level 1 (S1) ---
  13406. Firing prefer*rvt*predict-yes*H0
  13407. -->
  13408. Firing rl*prefer*rvt*predict-yes*H0*3*H1*9
  13409. -->
  13410. (S1 ^operator O1985 = 0.3930884415717635)
  13411. Firing rl*prefer*rvt*predict-yes*H0*3
  13412. -->
  13413. (S1 ^operator O1985 = 0.6069247111586296)
  13414. Firing prefer*rvt*predict-yes*H0*3*H1
  13415. -->
  13416. Firing prefer*rvt*predict-no*H0
  13417. -->
  13418. Firing rl*prefer*rvt*predict-no*H0*4*H1*8
  13419. -->
  13420. (S1 ^operator O1986 = -0.2450868666562052)
  13421. Firing rl*prefer*rvt*predict-no*H0*4
  13422. -->
  13423. (S1 ^operator O1986 = 0.4334966894375252)
  13424. Firing prefer*rvt*predict-no*H0*4*H1
  13425. -->
  13426. inner elaboration loop at bottom goal.
  13427. Retracting rl*prefer*rvt*predict-no*H0*4
  13428. -->
  13429. (S1 ^operator O1984 = 0.4334966894375252)
  13430. Retracting rl*prefer*rvt*predict-no*H0*4*H1*8
  13431. -->
  13432. (S1 ^operator O1984 = -0.2450868666562052)
  13433. Retracting rl*prefer*rvt*predict-yes*H0*3
  13434. -->
  13435. (S1 ^operator O1983 = 0.6069247111586296)
  13436. Retracting rl*prefer*rvt*predict-yes*H0*3*H1*9
  13437. -->
  13438. (S1 ^operator O1983 = 0.3930884415717635)
  13439. --- END Proposal Phase ---
  13440. --- Decision Phase ---
  13441. RL update rl*prefer*rvt*predict-no*H0*2 1 0 1 -> 1 0 1(R,m,v=1,1,0)
  13442. =>WM: (13942: S1 ^operator O1985)
  13443. 993: O: O1985 (predict-yes)
  13444. --- END Decision Phase ---
  13445. --- Application Phase ---
  13446. --- Firing Productions (PE) For State At Depth 1 ---
  13447. --- Inner Elaboration Phase, active level 1 (S1) ---
  13448. Firing apply*operator
  13449. -->
  13450. (I3 ^predict-yes N993 + :O )
  13451. Firing apply*operator*complete
  13452. -->
  13453. (I3 ^predict-no N992 - :O )
  13454. inner elaboration loop at bottom goal.
  13455. --- Change Working Memory (PE) ---
  13456. =>WM: (13943: I3 ^predict-yes N993)
  13457. <=WM: (13930: N992 ^status complete)
  13458. <=WM: (13929: I3 ^predict-no N992)
  13459. --- Firing Productions (IE) For State At Depth 1 ---
  13460. --- Inner Elaboration Phase, active level 1 (S1) ---
  13461. Firing monitor*world
  13462. -->
  13463. I see 1 and I'm going to do: predict-yes inner elaboration loop at bottom goal.
  13464. --- Change Working Memory (IE) ---
  13465. --- END Application Phase ---
  13466. --- Output Phase ---
  13467. ENV: Agent did: predict-yes for direction L in state State-B
  13468. In State-B moving L
  13469. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  13470. predict error 0
  13471. dir: dir isU
  13472. --- END Output Phase ---
  13473. /|\--- Input Phase ---
  13474. =>WM: (13947: I2 ^dir U)
  13475. =>WM: (13946: I2 ^reward 1)
  13476. =>WM: (13945: I2 ^see 1)
  13477. =>WM: (13944: N993 ^status complete)
  13478. <=WM: (13933: I2 ^dir L)
  13479. <=WM: (13932: I2 ^reward 1)
  13480. <=WM: (13931: I2 ^see 0)
  13481. =>WM: (13948: I2 ^level-1 L1-root)
  13482. <=WM: (13934: I2 ^level-1 R0-root)
  13483. --- END Input Phase ---
  13484. --- Proposal Phase ---
  13485. --- Inner Elaboration Phase, active level 1 (S1) ---
  13486. Firing elaborate*copy-see-to-output-link
  13487. -->
  13488. (I3 ^see 1 +)
  13489. Firing elaborate*reward*based*on*reward
  13490. -->
  13491. (R997 ^value 1 +)
  13492. (R1 ^reward R997 +)
  13493. Firing propose*predict-yes
  13494. -->
  13495. (O1987 ^name predict-yes +)
  13496. (S1 ^operator O1987 +)
  13497. Firing propose*predict-no
  13498. -->
  13499. (O1988 ^name predict-no +)
  13500. (S1 ^operator O1988 +)
  13501. Firing rl*prefer*rvt*predict-no*H0*2
  13502. -->
  13503. (S1 ^operator O1986 = 0.9999999999999999)
  13504. Firing rl*prefer*rvt*predict-yes*H0*1
  13505. -->
  13506. (S1 ^operator O1985 = 0.)
  13507. Firing prefer*rvt*predict-yes*H0
  13508. -->
  13509. Firing prefer*rvt*predict-no*H0
  13510. -->
  13511. Firing elaborate*copy-dir-to-output-link
  13512. -->
  13513. (I3 ^dir U +)
  13514. inner elaboration loop at bottom goal.
  13515. Retracting elaborate*copy-see-to-output-link
  13516. -->
  13517. (I3 ^see 0 +)
  13518. Retracting propose*predict-no
  13519. -->
  13520. (O1986 ^name predict-no +)
  13521. (S1 ^operator O1986 +)
  13522. Retracting propose*predict-yes
  13523. -->
  13524. (O1985 ^name predict-yes +)
  13525. (S1 ^operator O1985 +)
  13526. Retracting elaborate*reward*based*on*reward
  13527. -->
  13528. (R996 ^value 1 +)
  13529. (R1 ^reward R996 +)
  13530. Retracting elaborate*copy-dir-to-output-link
  13531. -->
  13532. (I3 ^dir L +)
  13533. Retracting rl*prefer*rvt*predict-no*H0*4
  13534. -->
  13535. (S1 ^operator O1986 = 0.4334966894375252)
  13536. Retracting rl*prefer*rvt*predict-no*H0*4*H1*8
  13537. -->
  13538. (S1 ^operator O1986 = -0.2450868666562052)
  13539. Retracting rl*prefer*rvt*predict-yes*H0*3
  13540. -->
  13541. (S1 ^operator O1985 = 0.6069247111586296)
  13542. Retracting rl*prefer*rvt*predict-yes*H0*3*H1*9
  13543. -->
  13544. (S1 ^operator O1985 = 0.3930884415717635)
  13545. =>WM: (13956: S1 ^operator O1988 +)
  13546. =>WM: (13955: S1 ^operator O1987 +)
  13547. =>WM: (13954: I3 ^dir U)
  13548. =>WM: (13953: O1988 ^name predict-no)
  13549. =>WM: (13952: O1987 ^name predict-yes)
  13550. =>WM: (13951: R997 ^value 1)
  13551. =>WM: (13950: R1 ^reward R997)
  13552. =>WM: (13949: I3 ^see 1)
  13553. <=WM: (13940: S1 ^operator O1985 +)
  13554. <=WM: (13942: S1 ^operator O1985)
  13555. <=WM: (13941: S1 ^operator O1986 +)
  13556. <=WM: (13939: I3 ^dir L)
  13557. <=WM: (13935: R1 ^reward R996)
  13558. <=WM: (13892: I3 ^see 0)
  13559. <=WM: (13938: O1986 ^name predict-no)
  13560. <=WM: (13937: O1985 ^name predict-yes)
  13561. <=WM: (13936: R996 ^value 1)
  13562. --- Inner Elaboration Phase, active level 1 (S1) ---
  13563. Firing prefer*rvt*predict-yes*H0
  13564. -->
  13565. Firing rl*prefer*rvt*predict-yes*H0*1
  13566. -->
  13567. (S1 ^operator O1987 = 0.)
  13568. Firing prefer*rvt*predict-no*H0
  13569. -->
  13570. Firing rl*prefer*rvt*predict-no*H0*2
  13571. -->
  13572. (S1 ^operator O1988 = 0.9999999999999999)
  13573. inner elaboration loop at bottom goal.
  13574. Retracting rl*prefer*rvt*predict-no*H0*2
  13575. -->
  13576. (S1 ^operator O1986 = 0.9999999999999999)
  13577. Retracting rl*prefer*rvt*predict-yes*H0*1
  13578. -->
  13579. (S1 ^operator O1985 = 0.)
  13580. --- END Proposal Phase ---
  13581. --- Decision Phase ---
  13582. RL update rl*prefer*rvt*predict-yes*H0*3 0.656145 -0.0492204 0.606925 -> 0.656143 -0.0492204 0.606923(R,m,v=1,0.947712,0.0498796)
  13583. RL update rl*prefer*rvt*predict-yes*H0*3*H1*9 0.343868 0.0492208 0.393088 -> 0.343866 0.0492208 0.393086(R,m,v=1,1,0)
  13584. =>WM: (13957: S1 ^operator O1988)
  13585. 994: O: O1988 (predict-no)
  13586. --- END Decision Phase ---
  13587. --- Application Phase ---
  13588. --- Firing Productions (PE) For State At Depth 1 ---
  13589. --- Inner Elaboration Phase, active level 1 (S1) ---
  13590. Firing apply*operator
  13591. -->
  13592. (I3 ^predict-no N994 + :O )
  13593. Firing apply*operator*complete
  13594. -->
  13595. (I3 ^predict-yes N993 - :O )
  13596. inner elaboration loop at bottom goal.
  13597. --- Change Working Memory (PE) ---
  13598. =>WM: (13958: I3 ^predict-no N994)
  13599. <=WM: (13944: N993 ^status complete)
  13600. <=WM: (13943: I3 ^predict-yes N993)
  13601. --- Firing Productions (IE) For State At Depth 1 ---
  13602. --- Inner Elaboration Phase, active level 1 (S1) ---
  13603. Firing monitor*world
  13604. -->
  13605. I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
  13606. --- Change Working Memory (IE) ---
  13607. --- END Application Phase ---
  13608. --- Output Phase ---
  13609. ENV: Agent did: predict-no for direction U in state State-A
  13610. In State-A moving U
  13611. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  13612. predict error 0
  13613. dir: dir isL
  13614. --- END Output Phase ---
  13615. -/|--- Input Phase ---
  13616. =>WM: (13962: I2 ^dir L)
  13617. =>WM: (13961: I2 ^reward 1)
  13618. =>WM: (13960: I2 ^see 0)
  13619. =>WM: (13959: N994 ^status complete)
  13620. <=WM: (13947: I2 ^dir U)
  13621. <=WM: (13946: I2 ^reward 1)
  13622. <=WM: (13945: I2 ^see 1)
  13623. =>WM: (13963: I2 ^level-1 L1-root)
  13624. <=WM: (13948: I2 ^level-1 L1-root)
  13625. --- END Input Phase ---
  13626. --- Proposal Phase ---
  13627. --- Inner Elaboration Phase, active level 1 (S1) ---
  13628. Firing rl*prefer*rvt*predict-yes*H0*3*H1*11
  13629. -->
  13630. (S1 ^operator O1987 = -0.03517433757196466)
  13631. Firing rl*prefer*rvt*predict-no*H0*4*H1*10
  13632. -->
  13633. (S1 ^operator O1988 = 0.5665060759609877)
  13634. Firing prefer*rvt*predict-no*H0*4*H1
  13635. -->
  13636. Firing prefer*rvt*predict-yes*H0*3*H1
  13637. -->
  13638. Firing elaborate*copy-see-to-output-link
  13639. -->
  13640. (I3 ^see 0 +)
  13641. Firing elaborate*reward*based*on*reward
  13642. -->
  13643. (R998 ^value 1 +)
  13644. (R1 ^reward R998 +)
  13645. Firing propose*predict-yes
  13646. -->
  13647. (O1989 ^name predict-yes +)
  13648. (S1 ^operator O1989 +)
  13649. Firing propose*predict-no
  13650. -->
  13651. (O1990 ^name predict-no +)
  13652. (S1 ^operator O1990 +)
  13653. Firing rl*prefer*rvt*predict-no*H0*4
  13654. -->
  13655. (S1 ^operator O1988 = 0.4334966894375252)
  13656. Firing rl*prefer*rvt*predict-yes*H0*3
  13657. -->
  13658. (S1 ^operator O1987 = 0.6069227382490706)
  13659. Firing prefer*rvt*predict-yes*H0
  13660. -->
  13661. Firing prefer*rvt*predict-no*H0
  13662. -->
  13663. Firing elaborate*copy-dir-to-output-link
  13664. -->
  13665. (I3 ^dir L +)
  13666. inner elaboration loop at bottom goal.
  13667. Retracting elaborate*copy-see-to-output-link
  13668. -->
  13669. (I3 ^see 1 +)
  13670. Retracting propose*predict-no
  13671. -->
  13672. (O1988 ^name predict-no +)
  13673. (S1 ^operator O1988 +)
  13674. Retracting propose*predict-yes
  13675. -->
  13676. (O1987 ^name predict-yes +)
  13677. (S1 ^operator O1987 +)
  13678. Retracting elaborate*reward*based*on*reward
  13679. -->
  13680. (R997 ^value 1 +)
  13681. (R1 ^reward R997 +)
  13682. Retracting elaborate*copy-dir-to-output-link
  13683. -->
  13684. (I3 ^dir U +)
  13685. Retracting rl*prefer*rvt*predict-no*H0*2
  13686. -->
  13687. (S1 ^operator O1988 = 0.9999999999999999)
  13688. Retracting rl*prefer*rvt*predict-yes*H0*1
  13689. -->
  13690. (S1 ^operator O1987 = 0.)
  13691. =>WM: (13971: S1 ^operator O1990 +)
  13692. =>WM: (13970: S1 ^operator O1989 +)
  13693. =>WM: (13969: I3 ^dir L)
  13694. =>WM: (13968: O1990 ^name predict-no)
  13695. =>WM: (13967: O1989 ^name predict-yes)
  13696. =>WM: (13966: R998 ^value 1)
  13697. =>WM: (13965: R1 ^reward R998)
  13698. =>WM: (13964: I3 ^see 0)
  13699. <=WM: (13955: S1 ^operator O1987 +)
  13700. <=WM: (13956: S1 ^operator O1988 +)
  13701. <=WM: (13957: S1 ^operator O1988)
  13702. <=WM: (13954: I3 ^dir U)
  13703. <=WM: (13950: R1 ^reward R997)
  13704. <=WM: (13949: I3 ^see 1)
  13705. <=WM: (13953: O1988 ^name predict-no)
  13706. <=WM: (13952: O1987 ^name predict-yes)
  13707. <=WM: (13951: R997 ^value 1)
  13708. --- Inner Elaboration Phase, active level 1 (S1) ---
  13709. Firing prefer*rvt*predict-yes*H0
  13710. -->
  13711. Firing rl*prefer*rvt*predict-yes*H0*3*H1*11
  13712. -->
  13713. (S1 ^operator O1989 = -0.03517433757196466)
  13714. Firing rl*prefer*rvt*predict-yes*H0*3
  13715. -->
  13716. (S1 ^operator O1989 = 0.6069227382490706)
  13717. Firing prefer*rvt*predict-yes*H0*3*H1
  13718. -->
  13719. Firing prefer*rvt*predict-no*H0
  13720. -->
  13721. Firing rl*prefer*rvt*predict-no*H0*4*H1*10
  13722. -->
  13723. (S1 ^operator O1990 = 0.5665060759609877)
  13724. Firing rl*prefer*rvt*predict-no*H0*4
  13725. -->
  13726. (S1 ^operator O1990 = 0.4334966894375252)
  13727. Firing prefer*rvt*predict-no*H0*4*H1
  13728. -->
  13729. inner elaboration loop at bottom goal.
  13730. Retracting rl*prefer*rvt*predict-no*H0*4
  13731. -->
  13732. (S1 ^operator O1988 = 0.4334966894375252)
  13733. Retracting rl*prefer*rvt*predict-no*H0*4*H1*10
  13734. -->
  13735. (S1 ^operator O1988 = 0.5665060759609877)
  13736. Retracting rl*prefer*rvt*predict-yes*H0*3
  13737. -->
  13738. (S1 ^operator O1987 = 0.6069227382490706)
  13739. Retracting rl*prefer*rvt*predict-yes*H0*3*H1*11
  13740. -->
  13741. (S1 ^operator O1987 = -0.03517433757196466)
  13742. --- END Proposal Phase ---
  13743. --- Decision Phase ---
  13744. RL update rl*prefer*rvt*predict-no*H0*2 1 0 1 -> 1 0 1(R,m,v=1,1,0)
  13745. =>WM: (13972: S1 ^operator O1990)
  13746. 995: O: O1990 (predict-no)
  13747. --- END Decision Phase ---
  13748. --- Application Phase ---
  13749. --- Firing Productions (PE) For State At Depth 1 ---
  13750. --- Inner Elaboration Phase, active level 1 (S1) ---
  13751. Firing apply*operator
  13752. -->
  13753. (I3 ^predict-no N995 + :O )
  13754. Firing apply*operator*complete
  13755. -->
  13756. (I3 ^predict-no N994 - :O )
  13757. inner elaboration loop at bottom goal.
  13758. --- Change Working Memory (PE) ---
  13759. =>WM: (13973: I3 ^predict-no N995)
  13760. <=WM: (13959: N994 ^status complete)
  13761. <=WM: (13958: I3 ^predict-no N994)
  13762. --- Firing Productions (IE) For State At Depth 1 ---
  13763. --- Inner Elaboration Phase, active level 1 (S1) ---
  13764. Firing monitor*world
  13765. -->
  13766. I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
  13767. --- Change Working Memory (IE) ---
  13768. --- END Application Phase ---
  13769. --- Output Phase ---
  13770. ENV: Agent did: predict-no for direction L in state State-A
  13771. In State-A moving L
  13772. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  13773. predict error 0
  13774. dir: dir isL
  13775. --- END Output Phase ---
  13776. \-/--- Input Phase ---
  13777. =>WM: (13977: I2 ^dir L)
  13778. =>WM: (13976: I2 ^reward 1)
  13779. =>WM: (13975: I2 ^see 0)
  13780. =>WM: (13974: N995 ^status complete)
  13781. <=WM: (13962: I2 ^dir L)
  13782. <=WM: (13961: I2 ^reward 1)
  13783. <=WM: (13960: I2 ^see 0)
  13784. =>WM: (13978: I2 ^level-1 L0-root)
  13785. <=WM: (13963: I2 ^level-1 L1-root)
  13786. --- END Input Phase ---
  13787. --- Proposal Phase ---
  13788. --- Inner Elaboration Phase, active level 1 (S1) ---
  13789. Firing rl*prefer*rvt*predict-yes*H0*3*H1*13
  13790. -->
  13791. (S1 ^operator O1989 = 0.07203)
  13792. Firing rl*prefer*rvt*predict-no*H0*4*H1*12
  13793. -->
  13794. (S1 ^operator O1990 = 0.5664938676874867)
  13795. Firing prefer*rvt*predict-no*H0*4*H1
  13796. -->
  13797. Firing prefer*rvt*predict-yes*H0*3*H1
  13798. -->
  13799. Firing elaborate*copy-see-to-output-link
  13800. -->
  13801. (I3 ^see 0 +)
  13802. Firing elaborate*reward*based*on*reward
  13803. -->
  13804. (R999 ^value 1 +)
  13805. (R1 ^reward R999 +)
  13806. Firing propose*predict-yes
  13807. -->
  13808. (O1991 ^name predict-yes +)
  13809. (S1 ^operator O1991 +)
  13810. Firing propose*predict-no
  13811. -->
  13812. (O1992 ^name predict-no +)
  13813. (S1 ^operator O1992 +)
  13814. Firing rl*prefer*rvt*predict-no*H0*4
  13815. -->
  13816. (S1 ^operator O1990 = 0.4334966894375252)
  13817. Firing rl*prefer*rvt*predict-yes*H0*3
  13818. -->
  13819. (S1 ^operator O1989 = 0.6069227382490706)
  13820. Firing prefer*rvt*predict-yes*H0
  13821. -->
  13822. Firing prefer*rvt*predict-no*H0
  13823. -->
  13824. Firing elaborate*copy-dir-to-output-link
  13825. -->
  13826. (I3 ^dir L +)
  13827. inner elaboration loop at bottom goal.
  13828. Retracting elaborate*copy-see-to-output-link
  13829. -->
  13830. (I3 ^see 0 +)
  13831. Retracting propose*predict-no
  13832. -->
  13833. (O1990 ^name predict-no +)
  13834. (S1 ^operator O1990 +)
  13835. Retracting propose*predict-yes
  13836. -->
  13837. (O1989 ^name predict-yes +)
  13838. (S1 ^operator O1989 +)
  13839. Retracting elaborate*reward*based*on*reward
  13840. -->
  13841. (R998 ^value 1 +)
  13842. (R1 ^reward R998 +)
  13843. Retracting elaborate*copy-dir-to-output-link
  13844. -->
  13845. (I3 ^dir L +)
  13846. Retracting rl*prefer*rvt*predict-no*H0*4
  13847. -->
  13848. (S1 ^operator O1990 = 0.4334966894375252)
  13849. Retracting rl*prefer*rvt*predict-no*H0*4*H1*10
  13850. -->
  13851. (S1 ^operator O1990 = 0.5665060759609877)
  13852. Retracting rl*prefer*rvt*predict-yes*H0*3
  13853. -->
  13854. (S1 ^operator O1989 = 0.6069227382490706)
  13855. Retracting rl*prefer*rvt*predict-yes*H0*3*H1*11
  13856. -->
  13857. (S1 ^operator O1989 = -0.03517433757196466)
  13858. =>WM: (13984: S1 ^operator O1992 +)
  13859. =>WM: (13983: S1 ^operator O1991 +)
  13860. =>WM: (13982: O1992 ^name predict-no)
  13861. =>WM: (13981: O1991 ^name predict-yes)
  13862. =>WM: (13980: R999 ^value 1)
  13863. =>WM: (13979: R1 ^reward R999)
  13864. <=WM: (13970: S1 ^operator O1989 +)
  13865. <=WM: (13971: S1 ^operator O1990 +)
  13866. <=WM: (13972: S1 ^operator O1990)
  13867. <=WM: (13965: R1 ^reward R998)
  13868. <=WM: (13968: O1990 ^name predict-no)
  13869. <=WM: (13967: O1989 ^name predict-yes)
  13870. <=WM: (13966: R998 ^value 1)
  13871. --- Inner Elaboration Phase, active level 1 (S1) ---
  13872. Firing prefer*rvt*predict-yes*H0
  13873. -->
  13874. Firing rl*prefer*rvt*predict-yes*H0*3
  13875. -->
  13876. (S1 ^operator O1991 = 0.6069227382490706)
  13877. Firing prefer*rvt*predict-yes*H0*3*H1
  13878. -->
  13879. Firing rl*prefer*rvt*predict-yes*H0*3*H1*13
  13880. -->
  13881. (S1 ^operator O1991 = 0.07203)
  13882. Firing prefer*rvt*predict-no*H0
  13883. -->
  13884. Firing rl*prefer*rvt*predict-no*H0*4
  13885. -->
  13886. (S1 ^operator O1992 = 0.4334966894375252)
  13887. Firing prefer*rvt*predict-no*H0*4*H1
  13888. -->
  13889. Firing rl*prefer*rvt*predict-no*H0*4*H1*12
  13890. -->
  13891. (S1 ^operator O1992 = 0.5664938676874867)
  13892. inner elaboration loop at bottom goal.
  13893. Retracting rl*prefer*rvt*predict-no*H0*4
  13894. -->
  13895. (S1 ^operator O1990 = 0.4334966894375252)
  13896. Retracting rl*prefer*rvt*predict-no*H0*4*H1*12
  13897. -->
  13898. (S1 ^operator O1990 = 0.5664938676874867)
  13899. Retracting rl*prefer*rvt*predict-yes*H0*3
  13900. -->
  13901. (S1 ^operator O1989 = 0.6069227382490706)
  13902. Retracting rl*prefer*rvt*predict-yes*H0*3*H1*13
  13903. -->
  13904. (S1 ^operator O1989 = 0.07203)
  13905. --- END Proposal Phase ---
  13906. --- Decision Phase ---
  13907. RL update rl*prefer*rvt*predict-no*H0*4 0.490213 -0.056716 0.433497 -> 0.490212 -0.056716 0.433496(R,m,v=1,0.888889,0.0993789)
  13908. RL update rl*prefer*rvt*predict-no*H0*4*H1*10 0.50979 0.056716 0.566506 -> 0.50979 0.056716 0.566506(R,m,v=1,1,0)
  13909. =>WM: (13985: S1 ^operator O1992)
  13910. 996: O: O1992 (predict-no)
  13911. --- END Decision Phase ---
  13912. --- Application Phase ---
  13913. --- Firing Productions (PE) For State At Depth 1 ---
  13914. --- Inner Elaboration Phase, active level 1 (S1) ---
  13915. Firing apply*operator
  13916. -->
  13917. (I3 ^predict-no N996 + :O )
  13918. Firing apply*operator*complete
  13919. -->
  13920. (I3 ^predict-no N995 - :O )
  13921. inner elaboration loop at bottom goal.
  13922. --- Change Working Memory (PE) ---
  13923. =>WM: (13986: I3 ^predict-no N996)
  13924. <=WM: (13974: N995 ^status complete)
  13925. <=WM: (13973: I3 ^predict-no N995)
  13926. --- Firing Productions (IE) For State At Depth 1 ---
  13927. --- Inner Elaboration Phase, active level 1 (S1) ---
  13928. Firing monitor*world
  13929. -->
  13930. I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
  13931. --- Change Working Memory (IE) ---
  13932. --- END Application Phase ---
  13933. --- Output Phase ---
  13934. ENV: Agent did: predict-no for direction L in state State-A
  13935. In State-A moving L
  13936. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  13937. predict error 0
  13938. dir: dir isL
  13939. --- END Output Phase ---
  13940. |\-/--- Input Phase ---
  13941. =>WM: (13990: I2 ^dir L)
  13942. =>WM: (13989: I2 ^reward 1)
  13943. =>WM: (13988: I2 ^see 0)
  13944. =>WM: (13987: N996 ^status complete)
  13945. <=WM: (13977: I2 ^dir L)
  13946. <=WM: (13976: I2 ^reward 1)
  13947. <=WM: (13975: I2 ^see 0)
  13948. =>WM: (13991: I2 ^level-1 L0-root)
  13949. <=WM: (13978: I2 ^level-1 L0-root)
  13950. --- END Input Phase ---
  13951. --- Proposal Phase ---
  13952. --- Inner Elaboration Phase, active level 1 (S1) ---
  13953. Firing rl*prefer*rvt*predict-yes*H0*3*H1*13
  13954. -->
  13955. (S1 ^operator O1991 = 0.07203)
  13956. Firing rl*prefer*rvt*predict-no*H0*4*H1*12
  13957. -->
  13958. (S1 ^operator O1992 = 0.5664938676874867)
  13959. Firing prefer*rvt*predict-no*H0*4*H1
  13960. -->
  13961. Firing prefer*rvt*predict-yes*H0*3*H1
  13962. -->
  13963. Firing elaborate*copy-see-to-output-link
  13964. -->
  13965. (I3 ^see 0 +)
  13966. Firing elaborate*reward*based*on*reward
  13967. -->
  13968. (R1000 ^value 1 +)
  13969. (R1 ^reward R1000 +)
  13970. Firing propose*predict-yes
  13971. -->
  13972. (O1993 ^name predict-yes +)
  13973. (S1 ^operator O1993 +)
  13974. Firing propose*predict-no
  13975. -->
  13976. (O1994 ^name predict-no +)
  13977. (S1 ^operator O1994 +)
  13978. Firing rl*prefer*rvt*predict-no*H0*4
  13979. -->
  13980. (S1 ^operator O1992 = 0.4334962746277483)
  13981. Firing rl*prefer*rvt*predict-yes*H0*3
  13982. -->
  13983. (S1 ^operator O1991 = 0.6069227382490706)
  13984. Firing prefer*rvt*predict-yes*H0
  13985. -->
  13986. Firing prefer*rvt*predict-no*H0
  13987. -->
  13988. Firing elaborate*copy-dir-to-output-link
  13989. -->
  13990. (I3 ^dir L +)
  13991. inner elaboration loop at bottom goal.
  13992. Retracting elaborate*copy-see-to-output-link
  13993. -->
  13994. (I3 ^see 0 +)
  13995. Retracting propose*predict-no
  13996. -->
  13997. (O1992 ^name predict-no +)
  13998. (S1 ^operator O1992 +)
  13999. Retracting propose*predict-yes
  14000. -->
  14001. (O1991 ^name predict-yes +)
  14002. (S1 ^operator O1991 +)
  14003. Retracting elaborate*reward*based*on*reward
  14004. -->
  14005. (R999 ^value 1 +)
  14006. (R1 ^reward R999 +)
  14007. Retracting elaborate*copy-dir-to-output-link
  14008. -->
  14009. (I3 ^dir L +)
  14010. Retracting rl*prefer*rvt*predict-no*H0*4*H1*12
  14011. -->
  14012. (S1 ^operator O1992 = 0.5664938676874867)
  14013. Retracting rl*prefer*rvt*predict-no*H0*4
  14014. -->
  14015. (S1 ^operator O1992 = 0.4334962746277483)
  14016. Retracting rl*prefer*rvt*predict-yes*H0*3*H1*13
  14017. -->
  14018. (S1 ^operator O1991 = 0.07203)
  14019. Retracting rl*prefer*rvt*predict-yes*H0*3
  14020. -->
  14021. (S1 ^operator O1991 = 0.6069227382490706)
  14022. =>WM: (13997: S1 ^operator O1994 +)
  14023. =>WM: (13996: S1 ^operator O1993 +)
  14024. =>WM: (13995: O1994 ^name predict-no)
  14025. =>WM: (13994: O1993 ^name predict-yes)
  14026. =>WM: (13993: R1000 ^value 1)
  14027. =>WM: (13992: R1 ^reward R1000)
  14028. <=WM: (13983: S1 ^operator O1991 +)
  14029. <=WM: (13984: S1 ^operator O1992 +)
  14030. <=WM: (13985: S1 ^operator O1992)
  14031. <=WM: (13979: R1 ^reward R999)
  14032. <=WM: (13982: O1992 ^name predict-no)
  14033. <=WM: (13981: O1991 ^name predict-yes)
  14034. <=WM: (13980: R999 ^value 1)
  14035. --- Inner Elaboration Phase, active level 1 (S1) ---
  14036. Firing prefer*rvt*predict-yes*H0
  14037. -->
  14038. Firing rl*prefer*rvt*predict-yes*H0*3
  14039. -->
  14040. (S1 ^operator O1993 = 0.6069227382490706)
  14041. Firing prefer*rvt*predict-yes*H0*3*H1
  14042. -->
  14043. Firing rl*prefer*rvt*predict-yes*H0*3*H1*13
  14044. -->
  14045. (S1 ^operator O1993 = 0.07203)
  14046. Firing prefer*rvt*predict-no*H0
  14047. -->
  14048. Firing rl*prefer*rvt*predict-no*H0*4
  14049. -->
  14050. (S1 ^operator O1994 = 0.4334962746277483)
  14051. Firing prefer*rvt*predict-no*H0*4*H1
  14052. -->
  14053. Firing rl*prefer*rvt*predict-no*H0*4*H1*12
  14054. -->
  14055. (S1 ^operator O1994 = 0.5664938676874867)
  14056. inner elaboration loop at bottom goal.
  14057. Retracting rl*prefer*rvt*predict-no*H0*4
  14058. -->
  14059. (S1 ^operator O1992 = 0.4334962746277483)
  14060. Retracting rl*prefer*rvt*predict-no*H0*4*H1*12
  14061. -->
  14062. (S1 ^operator O1992 = 0.5664938676874867)
  14063. Retracting rl*prefer*rvt*predict-yes*H0*3
  14064. -->
  14065. (S1 ^operator O1991 = 0.6069227382490706)
  14066. Retracting rl*prefer*rvt*predict-yes*H0*3*H1*13
  14067. -->
  14068. (S1 ^operator O1991 = 0.07203)
  14069. --- END Proposal Phase ---
  14070. --- Decision Phase ---
  14071. RL update rl*prefer*rvt*predict-no*H0*4 0.490212 -0.056716 0.433496 -> 0.490214 -0.056716 0.433498(R,m,v=1,0.889571,0.0988412)
  14072. RL update rl*prefer*rvt*predict-no*H0*4*H1*12 0.509778 0.056716 0.566494 -> 0.509779 0.056716 0.566495(R,m,v=1,1,0)
  14073. =>WM: (13998: S1 ^operator O1994)
  14074. 997: O: O1994 (predict-no)
  14075. --- END Decision Phase ---
  14076. --- Application Phase ---
  14077. --- Firing Productions (PE) For State At Depth 1 ---
  14078. --- Inner Elaboration Phase, active level 1 (S1) ---
  14079. Firing apply*operator
  14080. -->
  14081. (I3 ^predict-no N997 + :O )
  14082. Firing apply*operator*complete
  14083. -->
  14084. (I3 ^predict-no N996 - :O )
  14085. inner elaboration loop at bottom goal.
  14086. --- Change Working Memory (PE) ---
  14087. =>WM: (13999: I3 ^predict-no N997)
  14088. <=WM: (13987: N996 ^status complete)
  14089. <=WM: (13986: I3 ^predict-no N996)
  14090. --- Firing Productions (IE) For State At Depth 1 ---
  14091. --- Inner Elaboration Phase, active level 1 (S1) ---
  14092. Firing monitor*world
  14093. -->
  14094. I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
  14095. --- Change Working Memory (IE) ---
  14096. --- END Application Phase ---
  14097. --- Output Phase ---
  14098. ENV: Agent did: predict-no for direction L in state State-A
  14099. In State-A moving L
  14100. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  14101. predict error 0
  14102. dir: dir isU
  14103. --- END Output Phase ---
  14104. |\---- Input Phase ---
  14105. =>WM: (14003: I2 ^dir U)
  14106. =>WM: (14002: I2 ^reward 1)
  14107. =>WM: (14001: I2 ^see 0)
  14108. =>WM: (14000: N997 ^status complete)
  14109. <=WM: (13990: I2 ^dir L)
  14110. <=WM: (13989: I2 ^reward 1)
  14111. <=WM: (13988: I2 ^see 0)
  14112. =>WM: (14004: I2 ^level-1 L0-root)
  14113. <=WM: (13991: I2 ^level-1 L0-root)
  14114. --- END Input Phase ---
  14115. --- Proposal Phase ---
  14116. --- Inner Elaboration Phase, active level 1 (S1) ---
  14117. Firing elaborate*copy-see-to-output-link
  14118. -->
  14119. (I3 ^see 0 +)
  14120. Firing elaborate*reward*based*on*reward
  14121. -->
  14122. (R1001 ^value 1 +)
  14123. (R1 ^reward R1001 +)
  14124. Firing propose*predict-yes
  14125. -->
  14126. (O1995 ^name predict-yes +)
  14127. (S1 ^operator O1995 +)
  14128. Firing propose*predict-no
  14129. -->
  14130. (O1996 ^name predict-no +)
  14131. (S1 ^operator O1996 +)
  14132. Firing rl*prefer*rvt*predict-no*H0*2
  14133. -->
  14134. (S1 ^operator O1994 = 0.9999999999999999)
  14135. Firing rl*prefer*rvt*predict-yes*H0*1
  14136. -->
  14137. (S1 ^operator O1993 = 0.)
  14138. Firing prefer*rvt*predict-yes*H0
  14139. -->
  14140. Firing prefer*rvt*predict-no*H0
  14141. -->
  14142. Firing elaborate*copy-dir-to-output-link
  14143. -->
  14144. (I3 ^dir U +)
  14145. inner elaboration loop at bottom goal.
  14146. Retracting elaborate*copy-see-to-output-link
  14147. -->
  14148. (I3 ^see 0 +)
  14149. Retracting propose*predict-no
  14150. -->
  14151. (O1994 ^name predict-no +)
  14152. (S1 ^operator O1994 +)
  14153. Retracting propose*predict-yes
  14154. -->
  14155. (O1993 ^name predict-yes +)
  14156. (S1 ^operator O1993 +)
  14157. Retracting elaborate*reward*based*on*reward
  14158. -->
  14159. (R1000 ^value 1 +)
  14160. (R1 ^reward R1000 +)
  14161. Retracting elaborate*copy-dir-to-output-link
  14162. -->
  14163. (I3 ^dir L +)
  14164. Retracting rl*prefer*rvt*predict-no*H0*4*H1*12
  14165. -->
  14166. (S1 ^operator O1994 = 0.5664953463402014)
  14167. Retracting rl*prefer*rvt*predict-no*H0*4
  14168. -->
  14169. (S1 ^operator O1994 = 0.433497753280463)
  14170. Retracting rl*prefer*rvt*predict-yes*H0*3*H1*13
  14171. -->
  14172. (S1 ^operator O1993 = 0.07203)
  14173. Retracting rl*prefer*rvt*predict-yes*H0*3
  14174. -->
  14175. (S1 ^operator O1993 = 0.6069227382490706)
  14176. =>WM: (14011: S1 ^operator O1996 +)
  14177. =>WM: (14010: S1 ^operator O1995 +)
  14178. =>WM: (14009: I3 ^dir U)
  14179. =>WM: (14008: O1996 ^name predict-no)
  14180. =>WM: (14007: O1995 ^name predict-yes)
  14181. =>WM: (14006: R1001 ^value 1)
  14182. =>WM: (14005: R1 ^reward R1001)
  14183. <=WM: (13996: S1 ^operator O1993 +)
  14184. <=WM: (13997: S1 ^operator O1994 +)
  14185. <=WM: (13998: S1 ^operator O1994)
  14186. <=WM: (13969: I3 ^dir L)
  14187. <=WM: (13992: R1 ^reward R1000)
  14188. <=WM: (13995: O1994 ^name predict-no)
  14189. <=WM: (13994: O1993 ^name predict-yes)
  14190. <=WM: (13993: R1000 ^value 1)
  14191. --- Inner Elaboration Phase, active level 1 (S1) ---
  14192. Firing prefer*rvt*predict-yes*H0
  14193. -->
  14194. Firing rl*prefer*rvt*predict-yes*H0*1
  14195. -->
  14196. (S1 ^operator O1995 = 0.)
  14197. Firing prefer*rvt*predict-no*H0
  14198. -->
  14199. Firing rl*prefer*rvt*predict-no*H0*2
  14200. -->
  14201. (S1 ^operator O1996 = 0.9999999999999999)
  14202. inner elaboration loop at bottom goal.
  14203. Retracting rl*prefer*rvt*predict-no*H0*2
  14204. -->
  14205. (S1 ^operator O1994 = 0.9999999999999999)
  14206. Retracting rl*prefer*rvt*predict-yes*H0*1
  14207. -->
  14208. (S1 ^operator O1993 = 0.)
  14209. --- END Proposal Phase ---
  14210. --- Decision Phase ---
  14211. RL update rl*prefer*rvt*predict-no*H0*4 0.490214 -0.056716 0.433498 -> 0.490215 -0.056716 0.433499(R,m,v=1,0.890244,0.0983091)
  14212. RL update rl*prefer*rvt*predict-no*H0*4*H1*12 0.509779 0.056716 0.566495 -> 0.50978 0.056716 0.566496(R,m,v=1,1,0)
  14213. =>WM: (14012: S1 ^operator O1996)
  14214. 998: O: O1996 (predict-no)
  14215. --- END Decision Phase ---
  14216. --- Application Phase ---
  14217. --- Firing Productions (PE) For State At Depth 1 ---
  14218. --- Inner Elaboration Phase, active level 1 (S1) ---
  14219. Firing apply*operator
  14220. -->
  14221. (I3 ^predict-no N998 + :O )
  14222. Firing apply*operator*complete
  14223. -->
  14224. (I3 ^predict-no N997 - :O )
  14225. inner elaboration loop at bottom goal.
  14226. --- Change Working Memory (PE) ---
  14227. =>WM: (14013: I3 ^predict-no N998)
  14228. <=WM: (14000: N997 ^status complete)
  14229. <=WM: (13999: I3 ^predict-no N997)
  14230. --- Firing Productions (IE) For State At Depth 1 ---
  14231. --- Inner Elaboration Phase, active level 1 (S1) ---
  14232. Firing monitor*world
  14233. -->
  14234. I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
  14235. --- Change Working Memory (IE) ---
  14236. --- END Application Phase ---
  14237. --- Output Phase ---
  14238. ENV: Agent did: predict-no for direction U in state State-A
  14239. In State-A moving U
  14240. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  14241. predict error 0
  14242. dir: dir isR
  14243. --- END Output Phase ---
  14244. /|\--- Input Phase ---
  14245. =>WM: (14017: I2 ^dir R)
  14246. =>WM: (14016: I2 ^reward 1)
  14247. =>WM: (14015: I2 ^see 0)
  14248. =>WM: (14014: N998 ^status complete)
  14249. <=WM: (14003: I2 ^dir U)
  14250. <=WM: (14002: I2 ^reward 1)
  14251. <=WM: (14001: I2 ^see 0)
  14252. =>WM: (14018: I2 ^level-1 L0-root)
  14253. <=WM: (14004: I2 ^level-1 L0-root)
  14254. --- END Input Phase ---
  14255. --- Proposal Phase ---
  14256. --- Inner Elaboration Phase, active level 1 (S1) ---
  14257. Firing rl*prefer*rvt*predict-yes*H0*5*H1*14
  14258. -->
  14259. (S1 ^operator O1995 = 0.9322244132852968)
  14260. Firing rl*prefer*rvt*predict-no*H0*6*H1*19
  14261. -->
  14262. (S1 ^operator O1996 = 0.3)
  14263. Firing prefer*rvt*predict-no*H0*6*H1
  14264. -->
  14265. Firing prefer*rvt*predict-yes*H0*5*H1
  14266. -->
  14267. Firing elaborate*copy-see-to-output-link
  14268. -->
  14269. (I3 ^see 0 +)
  14270. Firing elaborate*reward*based*on*reward
  14271. -->
  14272. (R1002 ^value 1 +)
  14273. (R1 ^reward R1002 +)
  14274. Firing propose*predict-yes
  14275. -->
  14276. (O1997 ^name predict-yes +)
  14277. (S1 ^operator O1997 +)
  14278. Firing propose*predict-no
  14279. -->
  14280. (O1998 ^name predict-no +)
  14281. (S1 ^operator O1998 +)
  14282. Firing rl*prefer*rvt*predict-no*H0*6
  14283. -->
  14284. (S1 ^operator O1996 = 0.4643593834767564)
  14285. Firing rl*prefer*rvt*predict-yes*H0*5
  14286. -->
  14287. (S1 ^operator O1995 = 0.06777564504855271)
  14288. Firing prefer*rvt*predict-yes*H0
  14289. -->
  14290. Firing prefer*rvt*predict-no*H0
  14291. -->
  14292. Firing elaborate*copy-dir-to-output-link
  14293. -->
  14294. (I3 ^dir R +)
  14295. inner elaboration loop at bottom goal.
  14296. Retracting elaborate*copy-see-to-output-link
  14297. -->
  14298. (I3 ^see 0 +)
  14299. Retracting propose*predict-no
  14300. -->
  14301. (O1996 ^name predict-no +)
  14302. (S1 ^operator O1996 +)
  14303. Retracting propose*predict-yes
  14304. -->
  14305. (O1995 ^name predict-yes +)
  14306. (S1 ^operator O1995 +)
  14307. Retracting elaborate*reward*based*on*reward
  14308. -->
  14309. (R1001 ^value 1 +)
  14310. (R1 ^reward R1001 +)
  14311. Retracting elaborate*copy-dir-to-output-link
  14312. -->
  14313. (I3 ^dir U +)
  14314. Retracting rl*prefer*rvt*predict-no*H0*2
  14315. -->
  14316. (S1 ^operator O1996 = 0.9999999999999999)
  14317. Retracting rl*prefer*rvt*predict-yes*H0*1
  14318. -->
  14319. (S1 ^operator O1995 = 0.)
  14320. =>WM: (14025: S1 ^operator O1998 +)
  14321. =>WM: (14024: S1 ^operator O1997 +)
  14322. =>WM: (14023: I3 ^dir R)
  14323. =>WM: (14022: O1998 ^name predict-no)
  14324. =>WM: (14021: O1997 ^name predict-yes)
  14325. =>WM: (14020: R1002 ^value 1)
  14326. =>WM: (14019: R1 ^reward R1002)
  14327. <=WM: (14010: S1 ^operator O1995 +)
  14328. <=WM: (14011: S1 ^operator O1996 +)
  14329. <=WM: (14012: S1 ^operator O1996)
  14330. <=WM: (14009: I3 ^dir U)
  14331. <=WM: (14005: R1 ^reward R1001)
  14332. <=WM: (14008: O1996 ^name predict-no)
  14333. <=WM: (14007: O1995 ^name predict-yes)
  14334. <=WM: (14006: R1001 ^value 1)
  14335. --- Inner Elaboration Phase, active level 1 (S1) ---
  14336. Firing prefer*rvt*predict-yes*H0
  14337. -->
  14338. Firing rl*prefer*rvt*predict-yes*H0*5*H1*14
  14339. -->
  14340. (S1 ^operator O1997 = 0.9322244132852968)
  14341. Firing rl*prefer*rvt*predict-yes*H0*5
  14342. -->
  14343. (S1 ^operator O1997 = 0.06777564504855271)
  14344. Firing prefer*rvt*predict-yes*H0*5*H1
  14345. -->
  14346. Firing prefer*rvt*predict-no*H0
  14347. -->
  14348. Firing rl*prefer*rvt*predict-no*H0*6*H1*19
  14349. -->
  14350. (S1 ^operator O1998 = 0.3)
  14351. Firing rl*prefer*rvt*predict-no*H0*6
  14352. -->
  14353. (S1 ^operator O1998 = 0.4643593834767564)
  14354. Firing prefer*rvt*predict-no*H0*6*H1
  14355. -->
  14356. inner elaboration loop at bottom goal.
  14357. Retracting rl*prefer*rvt*predict-no*H0*6
  14358. -->
  14359. (S1 ^operator O1996 = 0.4643593834767564)
  14360. Retracting rl*prefer*rvt*predict-no*H0*6*H1*19
  14361. -->
  14362. (S1 ^operator O1996 = 0.3)
  14363. Retracting rl*prefer*rvt*predict-yes*H0*5
  14364. -->
  14365. (S1 ^operator O1995 = 0.06777564504855271)
  14366. Retracting rl*prefer*rvt*predict-yes*H0*5*H1*14
  14367. -->
  14368. (S1 ^operator O1995 = 0.9322244132852968)
  14369. --- END Proposal Phase ---
  14370. --- Decision Phase ---
  14371. RL update rl*prefer*rvt*predict-no*H0*2 1 0 1 -> 1 0 1(R,m,v=1,1,0)
  14372. =>WM: (14026: S1 ^operator O1997)
  14373. 999: O: O1997 (predict-yes)
  14374. --- END Decision Phase ---
  14375. --- Application Phase ---
  14376. --- Firing Productions (PE) For State At Depth 1 ---
  14377. --- Inner Elaboration Phase, active level 1 (S1) ---
  14378. Firing apply*operator
  14379. -->
  14380. (I3 ^predict-yes N999 + :O )
  14381. Firing apply*operator*complete
  14382. -->
  14383. (I3 ^predict-no N998 - :O )
  14384. inner elaboration loop at bottom goal.
  14385. --- Change Working Memory (PE) ---
  14386. =>WM: (14027: I3 ^predict-yes N999)
  14387. <=WM: (14014: N998 ^status complete)
  14388. <=WM: (14013: I3 ^predict-no N998)
  14389. --- Firing Productions (IE) For State At Depth 1 ---
  14390. --- Inner Elaboration Phase, active level 1 (S1) ---
  14391. Firing monitor*world
  14392. -->
  14393. I see 1 and I'm going to do: predict-yes inner elaboration loop at bottom goal.
  14394. --- Change Working Memory (IE) ---
  14395. --- END Application Phase ---
  14396. --- Output Phase ---
  14397. ENV: Agent did: predict-yes for direction R in state State-A
  14398. In State-A moving R
  14399. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  14400. predict error 0
  14401. dir: dir isU
  14402. --- END Output Phase ---
  14403. -/|--- Input Phase ---
  14404. =>WM: (14031: I2 ^dir U)
  14405. =>WM: (14030: I2 ^reward 1)
  14406. =>WM: (14029: I2 ^see 1)
  14407. =>WM: (14028: N999 ^status complete)
  14408. <=WM: (14017: I2 ^dir R)
  14409. <=WM: (14016: I2 ^reward 1)
  14410. <=WM: (14015: I2 ^see 0)
  14411. =>WM: (14032: I2 ^level-1 R1-root)
  14412. <=WM: (14018: I2 ^level-1 L0-root)
  14413. --- END Input Phase ---
  14414. --- Proposal Phase ---
  14415. --- Inner Elaboration Phase, active level 1 (S1) ---
  14416. Firing elaborate*copy-see-to-output-link
  14417. -->
  14418. (I3 ^see 1 +)
  14419. Firing elaborate*reward*based*on*reward
  14420. -->
  14421. (R1003 ^value 1 +)
  14422. (R1 ^reward R1003 +)
  14423. Firing propose*predict-yes
  14424. -->
  14425. (O1999 ^name predict-yes +)
  14426. (S1 ^operator O1999 +)
  14427. Firing propose*predict-no
  14428. -->
  14429. (O2000 ^name predict-no +)
  14430. (S1 ^operator O2000 +)
  14431. Firing rl*prefer*rvt*predict-no*H0*2
  14432. -->
  14433. (S1 ^operator O1998 = 0.9999999999999999)
  14434. Firing rl*prefer*rvt*predict-yes*H0*1
  14435. -->
  14436. (S1 ^operator O1997 = 0.)
  14437. Firing prefer*rvt*predict-yes*H0
  14438. -->
  14439. Firing prefer*rvt*predict-no*H0
  14440. -->
  14441. Firing elaborate*copy-dir-to-output-link
  14442. -->
  14443. (I3 ^dir U +)
  14444. inner elaboration loop at bottom goal.
  14445. Retracting elaborate*copy-see-to-output-link
  14446. -->
  14447. (I3 ^see 0 +)
  14448. Retracting propose*predict-no
  14449. -->
  14450. (O1998 ^name predict-no +)
  14451. (S1 ^operator O1998 +)
  14452. Retracting propose*predict-yes
  14453. -->
  14454. (O1997 ^name predict-yes +)
  14455. (S1 ^operator O1997 +)
  14456. Retracting elaborate*reward*based*on*reward
  14457. -->
  14458. (R1002 ^value 1 +)
  14459. (R1 ^reward R1002 +)
  14460. Retracting elaborate*copy-dir-to-output-link
  14461. -->
  14462. (I3 ^dir R +)
  14463. Retracting rl*prefer*rvt*predict-no*H0*6
  14464. -->
  14465. (S1 ^operator O1998 = 0.4643593834767564)
  14466. Retracting rl*prefer*rvt*predict-no*H0*6*H1*19
  14467. -->
  14468. (S1 ^operator O1998 = 0.3)
  14469. Retracting rl*prefer*rvt*predict-yes*H0*5
  14470. -->
  14471. (S1 ^operator O1997 = 0.06777564504855271)
  14472. Retracting rl*prefer*rvt*predict-yes*H0*5*H1*14
  14473. -->
  14474. (S1 ^operator O1997 = 0.9322244132852968)
  14475. =>WM: (14040: S1 ^operator O2000 +)
  14476. =>WM: (14039: S1 ^operator O1999 +)
  14477. =>WM: (14038: I3 ^dir U)
  14478. =>WM: (14037: O2000 ^name predict-no)
  14479. =>WM: (14036: O1999 ^name predict-yes)
  14480. =>WM: (14035: R1003 ^value 1)
  14481. =>WM: (14034: R1 ^reward R1003)
  14482. =>WM: (14033: I3 ^see 1)
  14483. <=WM: (14024: S1 ^operator O1997 +)
  14484. <=WM: (14026: S1 ^operator O1997)
  14485. <=WM: (14025: S1 ^operator O1998 +)
  14486. <=WM: (14023: I3 ^dir R)
  14487. <=WM: (14019: R1 ^reward R1002)
  14488. <=WM: (13964: I3 ^see 0)
  14489. <=WM: (14022: O1998 ^name predict-no)
  14490. <=WM: (14021: O1997 ^name predict-yes)
  14491. <=WM: (14020: R1002 ^value 1)
  14492. --- Inner Elaboration Phase, active level 1 (S1) ---
  14493. Firing prefer*rvt*predict-yes*H0
  14494. -->
  14495. Firing rl*prefer*rvt*predict-yes*H0*1
  14496. -->
  14497. (S1 ^operator O1999 = 0.)
  14498. Firing prefer*rvt*predict-no*H0
  14499. -->
  14500. Firing rl*prefer*rvt*predict-no*H0*2
  14501. -->
  14502. (S1 ^operator O2000 = 0.9999999999999999)
  14503. inner elaboration loop at bottom goal.
  14504. Retracting rl*prefer*rvt*predict-no*H0*2
  14505. -->
  14506. (S1 ^operator O1998 = 0.9999999999999999)
  14507. Retracting rl*prefer*rvt*predict-yes*H0*1
  14508. -->
  14509. (S1 ^operator O1997 = 0.)
  14510. --- END Proposal Phase ---
  14511. --- Decision Phase ---
  14512. RL update rl*prefer*rvt*predict-yes*H0*5 0.606208 -0.538432 0.0677756 -> 0.606208 -0.538432 0.0677756(R,m,v=1,0.873626,0.111013)
  14513. RL update rl*prefer*rvt*predict-yes*H0*5*H1*14 0.393792 0.538432 0.932224 -> 0.393792 0.538432 0.932224(R,m,v=1,1,0)
  14514. =>WM: (14041: S1 ^operator O2000)
  14515. 1000: O: O2000 (predict-no)
  14516. --- END Decision Phase ---
  14517. --- Application Phase ---
  14518. --- Firing Productions (PE) For State At Depth 1 ---
  14519. --- Inner Elaboration Phase, active level 1 (S1) ---
  14520. Firing apply*operator
  14521. -->
  14522. (I3 ^predict-no N1000 + :O )
  14523. Firing apply*operator*complete
  14524. -->
  14525. (I3 ^predict-yes N999 - :O )
  14526. inner elaboration loop at bottom goal.
  14527. --- Change Working Memory (PE) ---
  14528. =>WM: (14042: I3 ^predict-no N1000)
  14529. <=WM: (14028: N999 ^status complete)
  14530. <=WM: (14027: I3 ^predict-yes N999)
  14531. --- Firing Productions (IE) For State At Depth 1 ---
  14532. --- Inner Elaboration Phase, active level 1 (S1) ---
  14533. Firing monitor*world
  14534. -->
  14535. I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
  14536. --- Change Working Memory (IE) ---
  14537. --- END Application Phase ---
  14538. --- Output Phase ---
  14539. ENV: Agent did: predict-no for direction U in state State-B
  14540. In State-B moving U
  14541. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  14542. predict error 0
  14543. dir: dir isU
  14544. --- END Output Phase ---
  14545. \-/|\-/|\-/--- Input Phase ---
  14546. =>WM: (14046: I2 ^dir U)
  14547. =>WM: (14045: I2 ^reward 1)
  14548. =>WM: (14044: I2 ^see 0)
  14549. =>WM: (14043: N1000 ^status complete)
  14550. <=WM: (14031: I2 ^dir U)
  14551. <=WM: (14030: I2 ^reward 1)
  14552. <=WM: (14029: I2 ^see 1)
  14553. =>WM: (14047: I2 ^level-1 R1-root)
  14554. <=WM: (14032: I2 ^level-1 R1-root)
  14555. --- END Input Phase ---
  14556. --- Proposal Phase ---
  14557. --- Inner Elaboration Phase, active level 1 (S1) ---
  14558. Firing elaborate*copy-see-to-output-link
  14559. -->
  14560. (I3 ^see 0 +)
  14561. Firing elaborate*reward*based*on*reward
  14562. -->
  14563. (R1004 ^value 1 +)
  14564. (R1 ^reward R1004 +)
  14565. Firing propose*predict-yes
  14566. -->
  14567. (O2001 ^name predict-yes +)
  14568. (S1 ^operator O2001 +)
  14569. Firing propose*predict-no
  14570. -->
  14571. (O2002 ^name predict-no +)
  14572. (S1 ^operator O2002 +)
  14573. Firing rl*prefer*rvt*predict-no*H0*2
  14574. -->
  14575. (S1 ^operator O2000 = 0.9999999999999999)
  14576. Firing rl*prefer*rvt*predict-yes*H0*1
  14577. -->
  14578. (S1 ^operator O1999 = 0.)
  14579. Firing prefer*rvt*predict-yes*H0
  14580. -->
  14581. Firing prefer*rvt*predict-no*H0
  14582. -->
  14583. Firing elaborate*copy-dir-to-output-link
  14584. -->
  14585. (I3 ^dir U +)
  14586. inner elaboration loop at bottom goal.
  14587. Retracting elaborate*copy-see-to-output-link
  14588. -->
  14589. (I3 ^see 1 +)
  14590. Retracting propose*predict-no
  14591. -->
  14592. (O2000 ^name predict-no +)
  14593. (S1 ^operator O2000 +)
  14594. Retracting propose*predict-yes
  14595. -->
  14596. (O1999 ^name predict-yes +)
  14597. (S1 ^operator O1999 +)
  14598. Retracting elaborate*reward*based*on*reward
  14599. -->
  14600. (R1003 ^value 1 +)
  14601. (R1 ^reward R1003 +)
  14602. Retracting elaborate*copy-dir-to-output-link
  14603. -->
  14604. (I3 ^dir U +)
  14605. Retracting rl*prefer*rvt*predict-no*H0*2
  14606. -->
  14607. (S1 ^operator O2000 = 0.9999999999999999)
  14608. Retracting rl*prefer*rvt*predict-yes*H0*1
  14609. -->
  14610. (S1 ^operator O1999 = 0.)
  14611. =>WM: (14054: S1 ^operator O2002 +)
  14612. =>WM: (14053: S1 ^operator O2001 +)
  14613. =>WM: (14052: O2002 ^name predict-no)
  14614. =>WM: (14051: O2001 ^name predict-yes)
  14615. =>WM: (14050: R1004 ^value 1)
  14616. =>WM: (14049: R1 ^reward R1004)
  14617. =>WM: (14048: I3 ^see 0)
  14618. <=WM: (14039: S1 ^operator O1999 +)
  14619. <=WM: (14040: S1 ^operator O2000 +)
  14620. <=WM: (14041: S1 ^operator O2000)
  14621. <=WM: (14034: R1 ^reward R1003)
  14622. <=WM: (14033: I3 ^see 1)
  14623. <=WM: (14037: O2000 ^name predict-no)
  14624. <=WM: (14036: O1999 ^name predict-yes)
  14625. <=WM: (14035: R1003 ^value 1)
  14626. --- Inner Elaboration Phase, active level 1 (S1) ---
  14627. Firing prefer*rvt*predict-yes*H0
  14628. -->
  14629. Firing rl*prefer*rvt*predict-yes*H0*1
  14630. -->
  14631. (S1 ^operator O2001 = 0.)
  14632. Firing prefer*rvt*predict-no*H0
  14633. -->
  14634. Firing rl*prefer*rvt*predict-no*H0*2
  14635. -->
  14636. (S1 ^operator O2002 = 0.9999999999999999)
  14637. inner elaboration loop at bottom goal.
  14638. Retracting rl*prefer*rvt*predict-no*H0*2
  14639. -->
  14640. (S1 ^operator O2000 = 0.9999999999999999)
  14641. Retracting rl*prefer*rvt*predict-yes*H0*1
  14642. -->
  14643. (S1 ^operator O1999 = 0.)
  14644. --- END Proposal Phase ---
  14645. --- Decision Phase ---
  14646. RL update rl*prefer*rvt*predict-no*H0*2 1 0 1 -> 1 0 1(R,m,v=1,1,0)
  14647. =>WM: (14055: S1 ^operator O2002)
  14648. 1001: O: O2002 (predict-no)
  14649. --- END Decision Phase ---
  14650. --- Application Phase ---
  14651. --- Firing Productions (PE) For State At Depth 1 ---
  14652. --- Inner Elaboration Phase, active level 1 (S1) ---
  14653. Firing apply*operator
  14654. -->
  14655. (I3 ^predict-no N1001 + :O )
  14656. Firing apply*operator*complete
  14657. -->
  14658. (I3 ^predict-no N1000 - :O )
  14659. inner elaboration loop at bottom goal.
  14660. --- Change Working Memory (PE) ---
  14661. =>WM: (14056: I3 ^predict-no N1001)
  14662. <=WM: (14043: N1000 ^status complete)
  14663. <=WM: (14042: I3 ^predict-no N1000)
  14664. --- Firing Productions (IE) For State At Depth 1 ---
  14665. --- Inner Elaboration Phase, active level 1 (S1) ---
  14666. Firing monitor*world
  14667. -->
  14668. I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
  14669. --- Change Working Memory (IE) ---
  14670. --- END Application Phase ---
  14671. --- Output Phase ---
  14672. ENV: Agent did: predict-no for direction U in state State-B
  14673. In State-B moving U
  14674. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  14675. predict error 0
  14676. dir: dir isU
  14677. --- END Output Phase ---
  14678. |--- Input Phase ---
  14679. =>WM: (14060: I2 ^dir U)
  14680. =>WM: (14059: I2 ^reward 1)
  14681. =>WM: (14058: I2 ^see 0)
  14682. =>WM: (14057: N1001 ^status complete)
  14683. <=WM: (14046: I2 ^dir U)
  14684. <=WM: (14045: I2 ^reward 1)
  14685. <=WM: (14044: I2 ^see 0)
  14686. =>WM: (14061: I2 ^level-1 R1-root)
  14687. <=WM: (14047: I2 ^level-1 R1-root)
  14688. --- END Input Phase ---
  14689. --- Proposal Phase ---
  14690. --- Inner Elaboration Phase, active level 1 (S1) ---
  14691. Firing elaborate*copy-see-to-output-link
  14692. -->
  14693. (I3 ^see 0 +)
  14694. Firing elaborate*reward*based*on*reward
  14695. -->
  14696. (R1005 ^value 1 +)
  14697. (R1 ^reward R1005 +)
  14698. Firing propose*predict-yes
  14699. -->
  14700. (O2003 ^name predict-yes +)
  14701. (S1 ^operator O2003 +)
  14702. Firing propose*predict-no
  14703. -->
  14704. (O2004 ^name predict-no +)
  14705. (S1 ^operator O2004 +)
  14706. Firing rl*prefer*rvt*predict-no*H0*2
  14707. -->
  14708. (S1 ^operator O2002 = 0.9999999999999999)
  14709. Firing rl*prefer*rvt*predict-yes*H0*1
  14710. -->
  14711. (S1 ^operator O2001 = 0.)
  14712. Firing prefer*rvt*predict-yes*H0
  14713. -->
  14714. Firing prefer*rvt*predict-no*H0
  14715. -->
  14716. Firing elaborate*copy-dir-to-output-link
  14717. -->
  14718. (I3 ^dir U +)
  14719. inner elaboration loop at bottom goal.
  14720. Retracting elaborate*copy-see-to-output-link
  14721. -->
  14722. (I3 ^see 0 +)
  14723. Retracting propose*predict-no
  14724. -->
  14725. (O2002 ^name predict-no +)
  14726. (S1 ^operator O2002 +)
  14727. Retracting propose*predict-yes
  14728. -->
  14729. (O2001 ^name predict-yes +)
  14730. (S1 ^operator O2001 +)
  14731. Retracting elaborate*reward*based*on*reward
  14732. -->
  14733. (R1004 ^value 1 +)
  14734. (R1 ^reward R1004 +)
  14735. Retracting elaborate*copy-dir-to-output-link
  14736. -->
  14737. (I3 ^dir U +)
  14738. Retracting rl*prefer*rvt*predict-no*H0*2
  14739. -->
  14740. (S1 ^operator O2002 = 0.9999999999999999)
  14741. Retracting rl*prefer*rvt*predict-yes*H0*1
  14742. -->
  14743. (S1 ^operator O2001 = 0.)
  14744. =>WM: (14067: S1 ^operator O2004 +)
  14745. =>WM: (14066: S1 ^operator O2003 +)
  14746. =>WM: (14065: O2004 ^name predict-no)
  14747. =>WM: (14064: O2003 ^name predict-yes)
  14748. =>WM: (14063: R1005 ^value 1)
  14749. =>WM: (14062: R1 ^reward R1005)
  14750. <=WM: (14053: S1 ^operator O2001 +)
  14751. <=WM: (14054: S1 ^operator O2002 +)
  14752. <=WM: (14055: S1 ^operator O2002)
  14753. <=WM: (14049: R1 ^reward R1004)
  14754. <=WM: (14052: O2002 ^name predict-no)
  14755. <=WM: (14051: O2001 ^name predict-yes)
  14756. <=WM: (14050: R1004 ^value 1)
  14757. --- Inner Elaboration Phase, active level 1 (S1) ---
  14758. Firing prefer*rvt*predict-yes*H0
  14759. -->
  14760. Firing rl*prefer*rvt*predict-yes*H0*1
  14761. -->
  14762. (S1 ^operator O2003 = 0.)
  14763. Firing prefer*rvt*predict-no*H0
  14764. -->
  14765. Firing rl*prefer*rvt*predict-no*H0*2
  14766. -->
  14767. (S1 ^operator O2004 = 0.9999999999999999)
  14768. inner elaboration loop at bottom goal.
  14769. Retracting rl*prefer*rvt*predict-no*H0*2
  14770. -->
  14771. (S1 ^operator O2002 = 0.9999999999999999)
  14772. Retracting rl*prefer*rvt*predict-yes*H0*1
  14773. -->
  14774. (S1 ^operator O2001 = 0.)
  14775. --- END Proposal Phase ---
  14776. --- Decision Phase ---
  14777. RL update rl*prefer*rvt*predict-no*H0*2 1 0 1 -> 1 0 1(R,m,v=1,1,0)
  14778. =>WM: (14068: S1 ^operator O2004)
  14779. 1002: O: O2004 (predict-no)
  14780. --- END Decision Phase ---
  14781. --- Application Phase ---
  14782. --- Firing Productions (PE) For State At Depth 1 ---
  14783. --- Inner Elaboration Phase, active level 1 (S1) ---
  14784. Firing apply*operator
  14785. -->
  14786. (I3 ^predict-no N1002 + :O )
  14787. Firing apply*operator*complete
  14788. -->
  14789. (I3 ^predict-no N1001 - :O )
  14790. inner elaboration loop at bottom goal.
  14791. --- Change Working Memory (PE) ---
  14792. =>WM: (14069: I3 ^predict-no N1002)
  14793. <=WM: (14057: N1001 ^status complete)
  14794. <=WM: (14056: I3 ^predict-no N1001)
  14795. --- Firing Productions (IE) For State At Depth 1 ---
  14796. --- Inner Elaboration Phase, active level 1 (S1) ---
  14797. Firing monitor*world
  14798. -->
  14799. I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
  14800. --- Change Working Memory (IE) ---
  14801. --- END Application Phase ---
  14802. --- Output Phase ---
  14803. ENV: Agent did: predict-no for direction U in state State-B
  14804. In State-B moving U
  14805. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  14806. predict error 0
  14807. dir: dir isR
  14808. --- END Output Phase ---
  14809. \-/--- Input Phase ---
  14810. =>WM: (14073: I2 ^dir R)
  14811. =>WM: (14072: I2 ^reward 1)
  14812. =>WM: (14071: I2 ^see 0)
  14813. =>WM: (14070: N1002 ^status complete)
  14814. <=WM: (14060: I2 ^dir U)
  14815. <=WM: (14059: I2 ^reward 1)
  14816. <=WM: (14058: I2 ^see 0)
  14817. =>WM: (14074: I2 ^level-1 R1-root)
  14818. <=WM: (14061: I2 ^level-1 R1-root)
  14819. --- END Input Phase ---
  14820. --- Proposal Phase ---
  14821. --- Inner Elaboration Phase, active level 1 (S1) ---
  14822. Firing rl*prefer*rvt*predict-no*H0*6*H1*20
  14823. -->
  14824. (S1 ^operator O2004 = 0.5356414139847089)
  14825. Firing rl*prefer*rvt*predict-yes*H0*5*H1*15
  14826. -->
  14827. (S1 ^operator O2003 = 0.2653409704952874)
  14828. Firing prefer*rvt*predict-no*H0*6*H1
  14829. -->
  14830. Firing prefer*rvt*predict-yes*H0*5*H1
  14831. -->
  14832. Firing elaborate*copy-see-to-output-link
  14833. -->
  14834. (I3 ^see 0 +)
  14835. Firing elaborate*reward*based*on*reward
  14836. -->
  14837. (R1006 ^value 1 +)
  14838. (R1 ^reward R1006 +)
  14839. Firing propose*predict-yes
  14840. -->
  14841. (O2005 ^name predict-yes +)
  14842. (S1 ^operator O2005 +)
  14843. Firing propose*predict-no
  14844. -->
  14845. (O2006 ^name predict-no +)
  14846. (S1 ^operator O2006 +)
  14847. Firing rl*prefer*rvt*predict-no*H0*6
  14848. -->
  14849. (S1 ^operator O2004 = 0.4643593834767564)
  14850. Firing rl*prefer*rvt*predict-yes*H0*5
  14851. -->
  14852. (S1 ^operator O2003 = 0.06777563629847527)
  14853. Firing prefer*rvt*predict-yes*H0
  14854. -->
  14855. Firing prefer*rvt*predict-no*H0
  14856. -->
  14857. Firing elaborate*copy-dir-to-output-link
  14858. -->
  14859. (I3 ^dir R +)
  14860. inner elaboration loop at bottom goal.
  14861. Retracting elaborate*copy-see-to-output-link
  14862. -->
  14863. (I3 ^see 0 +)
  14864. Retracting propose*predict-no
  14865. -->
  14866. (O2004 ^name predict-no +)
  14867. (S1 ^operator O2004 +)
  14868. Retracting propose*predict-yes
  14869. -->
  14870. (O2003 ^name predict-yes +)
  14871. (S1 ^operator O2003 +)
  14872. Retracting elaborate*reward*based*on*reward
  14873. -->
  14874. (R1005 ^value 1 +)
  14875. (R1 ^reward R1005 +)
  14876. Retracting elaborate*copy-dir-to-output-link
  14877. -->
  14878. (I3 ^dir U +)
  14879. Retracting rl*prefer*rvt*predict-no*H0*2
  14880. -->
  14881. (S1 ^operator O2004 = 0.9999999999999999)
  14882. Retracting rl*prefer*rvt*predict-yes*H0*1
  14883. -->
  14884. (S1 ^operator O2003 = 0.)
  14885. =>WM: (14081: S1 ^operator O2006 +)
  14886. =>WM: (14080: S1 ^operator O2005 +)
  14887. =>WM: (14079: I3 ^dir R)
  14888. =>WM: (14078: O2006 ^name predict-no)
  14889. =>WM: (14077: O2005 ^name predict-yes)
  14890. =>WM: (14076: R1006 ^value 1)
  14891. =>WM: (14075: R1 ^reward R1006)
  14892. <=WM: (14066: S1 ^operator O2003 +)
  14893. <=WM: (14067: S1 ^operator O2004 +)
  14894. <=WM: (14068: S1 ^operator O2004)
  14895. <=WM: (14038: I3 ^dir U)
  14896. <=WM: (14062: R1 ^reward R1005)
  14897. <=WM: (14065: O2004 ^name predict-no)
  14898. <=WM: (14064: O2003 ^name predict-yes)
  14899. <=WM: (14063: R1005 ^value 1)
  14900. --- Inner Elaboration Phase, active level 1 (S1) ---
  14901. Firing prefer*rvt*predict-yes*H0
  14902. -->
  14903. Firing rl*prefer*rvt*predict-yes*H0*5*H1*15
  14904. -->
  14905. (S1 ^operator O2005 = 0.2653409704952874)
  14906. Firing rl*prefer*rvt*predict-yes*H0*5
  14907. -->
  14908. (S1 ^operator O2005 = 0.06777563629847527)
  14909. Firing prefer*rvt*predict-yes*H0*5*H1
  14910. -->
  14911. Firing prefer*rvt*predict-no*H0
  14912. -->
  14913. Firing rl*prefer*rvt*predict-no*H0*6*H1*20
  14914. -->
  14915. (S1 ^operator O2006 = 0.5356414139847089)
  14916. Firing rl*prefer*rvt*predict-no*H0*6
  14917. -->
  14918. (S1 ^operator O2006 = 0.4643593834767564)
  14919. Firing prefer*rvt*predict-no*H0*6*H1
  14920. -->
  14921. inner elaboration loop at bottom goal.
  14922. Retracting rl*prefer*rvt*predict-no*H0*6
  14923. -->
  14924. (S1 ^operator O2004 = 0.4643593834767564)
  14925. Retracting rl*prefer*rvt*predict-no*H0*6*H1*20
  14926. -->
  14927. (S1 ^operator O2004 = 0.5356414139847089)
  14928. Retracting rl*prefer*rvt*predict-yes*H0*5
  14929. -->
  14930. (S1 ^operator O2003 = 0.06777563629847527)
  14931. Retracting rl*prefer*rvt*predict-yes*H0*5*H1*15
  14932. -->
  14933. (S1 ^operator O2003 = 0.2653409704952874)
  14934. --- END Proposal Phase ---
  14935. --- Decision Phase ---
  14936. RL update rl*prefer*rvt*predict-no*H0*2 1 0 1 -> 1 0 1(R,m,v=1,1,0)
  14937. =>WM: (14082: S1 ^operator O2006)
  14938. 1003: O: O2006 (predict-no)
  14939. --- END Decision Phase ---
  14940. --- Application Phase ---
  14941. --- Firing Productions (PE) For State At Depth 1 ---
  14942. --- Inner Elaboration Phase, active level 1 (S1) ---
  14943. Firing apply*operator
  14944. -->
  14945. (I3 ^predict-no N1003 + :O )
  14946. Firing apply*operator*complete
  14947. -->
  14948. (I3 ^predict-no N1002 - :O )
  14949. inner elaboration loop at bottom goal.
  14950. --- Change Working Memory (PE) ---
  14951. =>WM: (14083: I3 ^predict-no N1003)
  14952. <=WM: (14070: N1002 ^status complete)
  14953. <=WM: (14069: I3 ^predict-no N1002)
  14954. --- Firing Productions (IE) For State At Depth 1 ---
  14955. --- Inner Elaboration Phase, active level 1 (S1) ---
  14956. Firing monitor*world
  14957. -->
  14958. I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
  14959. --- Change Working Memory (IE) ---
  14960. --- END Application Phase ---
  14961. --- Output Phase ---
  14962. ENV: Agent did: predict-no for direction R in state State-B
  14963. In State-B moving R
  14964. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  14965. predict error 0
  14966. dir: dir isR
  14967. --- END Output Phase ---
  14968. |\---- Input Phase ---
  14969. =>WM: (14087: I2 ^dir R)
  14970. =>WM: (14086: I2 ^reward 1)
  14971. =>WM: (14085: I2 ^see 0)
  14972. =>WM: (14084: N1003 ^status complete)
  14973. <=WM: (14073: I2 ^dir R)
  14974. <=WM: (14072: I2 ^reward 1)
  14975. <=WM: (14071: I2 ^see 0)
  14976. =>WM: (14088: I2 ^level-1 R0-root)
  14977. <=WM: (14074: I2 ^level-1 R1-root)
  14978. --- END Input Phase ---
  14979. --- Proposal Phase ---
  14980. --- Inner Elaboration Phase, active level 1 (S1) ---
  14981. Firing rl*prefer*rvt*predict-no*H0*6*H1*22
  14982. -->
  14983. (S1 ^operator O2006 = 0.5356389096871144)
  14984. Firing rl*prefer*rvt*predict-yes*H0*5*H1*7
  14985. -->
  14986. (S1 ^operator O2005 = 0.0787273604177588)
  14987. Firing prefer*rvt*predict-no*H0*6*H1
  14988. -->
  14989. Firing prefer*rvt*predict-yes*H0*5*H1
  14990. -->
  14991. Firing elaborate*copy-see-to-output-link
  14992. -->
  14993. (I3 ^see 0 +)
  14994. Firing elaborate*reward*based*on*reward
  14995. -->
  14996. (R1007 ^value 1 +)
  14997. (R1 ^reward R1007 +)
  14998. Firing propose*predict-yes
  14999. -->
  15000. (O2007 ^name predict-yes +)
  15001. (S1 ^operator O2007 +)
  15002. Firing propose*predict-no
  15003. -->
  15004. (O2008 ^name predict-no +)
  15005. (S1 ^operator O2008 +)
  15006. Firing rl*prefer*rvt*predict-no*H0*6
  15007. -->
  15008. (S1 ^operator O2006 = 0.4643593834767564)
  15009. Firing rl*prefer*rvt*predict-yes*H0*5
  15010. -->
  15011. (S1 ^operator O2005 = 0.06777563629847527)
  15012. Firing prefer*rvt*predict-yes*H0
  15013. -->
  15014. Firing prefer*rvt*predict-no*H0
  15015. -->
  15016. Firing elaborate*copy-dir-to-output-link
  15017. -->
  15018. (I3 ^dir R +)
  15019. inner elaboration loop at bottom goal.
  15020. Retracting elaborate*copy-see-to-output-link
  15021. -->
  15022. (I3 ^see 0 +)
  15023. Retracting propose*predict-no
  15024. -->
  15025. (O2006 ^name predict-no +)
  15026. (S1 ^operator O2006 +)
  15027. Retracting propose*predict-yes
  15028. -->
  15029. (O2005 ^name predict-yes +)
  15030. (S1 ^operator O2005 +)
  15031. Retracting elaborate*reward*based*on*reward
  15032. -->
  15033. (R1006 ^value 1 +)
  15034. (R1 ^reward R1006 +)
  15035. Retracting elaborate*copy-dir-to-output-link
  15036. -->
  15037. (I3 ^dir R +)
  15038. Retracting rl*prefer*rvt*predict-no*H0*6
  15039. -->
  15040. (S1 ^operator O2006 = 0.4643593834767564)
  15041. Retracting rl*prefer*rvt*predict-no*H0*6*H1*20
  15042. -->
  15043. (S1 ^operator O2006 = 0.5356414139847089)
  15044. Retracting rl*prefer*rvt*predict-yes*H0*5
  15045. -->
  15046. (S1 ^operator O2005 = 0.06777563629847527)
  15047. Retracting rl*prefer*rvt*predict-yes*H0*5*H1*15
  15048. -->
  15049. (S1 ^operator O2005 = 0.2653409704952874)
  15050. =>WM: (14094: S1 ^operator O2008 +)
  15051. =>WM: (14093: S1 ^operator O2007 +)
  15052. =>WM: (14092: O2008 ^name predict-no)
  15053. =>WM: (14091: O2007 ^name predict-yes)
  15054. =>WM: (14090: R1007 ^value 1)
  15055. =>WM: (14089: R1 ^reward R1007)
  15056. <=WM: (14080: S1 ^operator O2005 +)
  15057. <=WM: (14081: S1 ^operator O2006 +)
  15058. <=WM: (14082: S1 ^operator O2006)
  15059. <=WM: (14075: R1 ^reward R1006)
  15060. <=WM: (14078: O2006 ^name predict-no)
  15061. <=WM: (14077: O2005 ^name predict-yes)
  15062. <=WM: (14076: R1006 ^value 1)
  15063. --- Inner Elaboration Phase, active level 1 (S1) ---
  15064. Firing prefer*rvt*predict-yes*H0
  15065. -->
  15066. Firing rl*prefer*rvt*predict-yes*H0*5
  15067. -->
  15068. (S1 ^operator O2007 = 0.06777563629847527)
  15069. Firing prefer*rvt*predict-yes*H0*5*H1
  15070. -->
  15071. Firing rl*prefer*rvt*predict-yes*H0*5*H1*7
  15072. -->
  15073. (S1 ^operator O2007 = 0.0787273604177588)
  15074. Firing prefer*rvt*predict-no*H0
  15075. -->
  15076. Firing rl*prefer*rvt*predict-no*H0*6
  15077. -->
  15078. (S1 ^operator O2008 = 0.4643593834767564)
  15079. Firing prefer*rvt*predict-no*H0*6*H1
  15080. -->
  15081. Firing rl*prefer*rvt*predict-no*H0*6*H1*22
  15082. -->
  15083. (S1 ^operator O2008 = 0.5356389096871144)
  15084. inner elaboration loop at bottom goal.
  15085. Retracting rl*prefer*rvt*predict-no*H0*6
  15086. -->
  15087. (S1 ^operator O2006 = 0.4643593834767564)
  15088. Retracting rl*prefer*rvt*predict-no*H0*6*H1*22
  15089. -->
  15090. (S1 ^operator O2006 = 0.5356389096871144)
  15091. Retracting rl*prefer*rvt*predict-yes*H0*5
  15092. -->
  15093. (S1 ^operator O2005 = 0.06777563629847527)
  15094. Retracting rl*prefer*rvt*predict-yes*H0*5*H1*7
  15095. -->
  15096. (S1 ^operator O2005 = 0.0787273604177588)
  15097. --- END Proposal Phase ---
  15098. --- Decision Phase ---
  15099. RL update rl*prefer*rvt*predict-no*H0*6 0.679081 -0.214722 0.464359 -> 0.679081 -0.214722 0.464359(R,m,v=1,0.971098,0.0282296)
  15100. RL update rl*prefer*rvt*predict-no*H0*6*H1*20 0.32092 0.214722 0.535641 -> 0.32092 0.214722 0.535641(R,m,v=1,1,0)
  15101. =>WM: (14095: S1 ^operator O2008)
  15102. 1004: O: O2008 (predict-no)
  15103. --- END Decision Phase ---
  15104. --- Application Phase ---
  15105. --- Firing Productions (PE) For State At Depth 1 ---
  15106. --- Inner Elaboration Phase, active level 1 (S1) ---
  15107. Firing apply*operator
  15108. -->
  15109. (I3 ^predict-no N1004 + :O )
  15110. Firing apply*operator*complete
  15111. -->
  15112. (I3 ^predict-no N1003 - :O )
  15113. inner elaboration loop at bottom goal.
  15114. --- Change Working Memory (PE) ---
  15115. =>WM: (14096: I3 ^predict-no N1004)
  15116. <=WM: (14084: N1003 ^status complete)
  15117. <=WM: (14083: I3 ^predict-no N1003)
  15118. --- Firing Productions (IE) For State At Depth 1 ---
  15119. --- Inner Elaboration Phase, active level 1 (S1) ---
  15120. Firing monitor*world
  15121. -->
  15122. I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
  15123. --- Change Working Memory (IE) ---
  15124. --- END Application Phase ---
  15125. --- Output Phase ---
  15126. ENV: Agent did: predict-no for direction R in state State-B
  15127. In State-B moving R
  15128. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  15129. predict error 0
  15130. dir: dir isU
  15131. --- END Output Phase ---
  15132. /|\--- Input Phase ---
  15133. =>WM: (14100: I2 ^dir U)
  15134. =>WM: (14099: I2 ^reward 1)
  15135. =>WM: (14098: I2 ^see 0)
  15136. =>WM: (14097: N1004 ^status complete)
  15137. <=WM: (14087: I2 ^dir R)
  15138. <=WM: (14086: I2 ^reward 1)
  15139. <=WM: (14085: I2 ^see 0)
  15140. =>WM: (14101: I2 ^level-1 R0-root)
  15141. <=WM: (14088: I2 ^level-1 R0-root)
  15142. --- END Input Phase ---
  15143. --- Proposal Phase ---
  15144. --- Inner Elaboration Phase, active level 1 (S1) ---
  15145. Firing elaborate*copy-see-to-output-link
  15146. -->
  15147. (I3 ^see 0 +)
  15148. Firing elaborate*reward*based*on*reward
  15149. -->
  15150. (R1008 ^value 1 +)
  15151. (R1 ^reward R1008 +)
  15152. Firing propose*predict-yes
  15153. -->
  15154. (O2009 ^name predict-yes +)
  15155. (S1 ^operator O2009 +)
  15156. Firing propose*predict-no
  15157. -->
  15158. (O2010 ^name predict-no +)
  15159. (S1 ^operator O2010 +)
  15160. Firing rl*prefer*rvt*predict-no*H0*2
  15161. -->
  15162. (S1 ^operator O2008 = 0.9999999999999999)
  15163. Firing rl*prefer*rvt*predict-yes*H0*1
  15164. -->
  15165. (S1 ^operator O2007 = 0.)
  15166. Firing prefer*rvt*predict-yes*H0
  15167. -->
  15168. Firing prefer*rvt*predict-no*H0
  15169. -->
  15170. Firing elaborate*copy-dir-to-output-link
  15171. -->
  15172. (I3 ^dir U +)
  15173. inner elaboration loop at bottom goal.
  15174. Retracting elaborate*copy-see-to-output-link
  15175. -->
  15176. (I3 ^see 0 +)
  15177. Retracting propose*predict-no
  15178. -->
  15179. (O2008 ^name predict-no +)
  15180. (S1 ^operator O2008 +)
  15181. Retracting propose*predict-yes
  15182. -->
  15183. (O2007 ^name predict-yes +)
  15184. (S1 ^operator O2007 +)
  15185. Retracting elaborate*reward*based*on*reward
  15186. -->
  15187. (R1007 ^value 1 +)
  15188. (R1 ^reward R1007 +)
  15189. Retracting elaborate*copy-dir-to-output-link
  15190. -->
  15191. (I3 ^dir R +)
  15192. Retracting rl*prefer*rvt*predict-no*H0*6*H1*22
  15193. -->
  15194. (S1 ^operator O2008 = 0.5356389096871144)
  15195. Retracting rl*prefer*rvt*predict-no*H0*6
  15196. -->
  15197. (S1 ^operator O2008 = 0.4643592638575366)
  15198. Retracting rl*prefer*rvt*predict-yes*H0*5*H1*7
  15199. -->
  15200. (S1 ^operator O2007 = 0.0787273604177588)
  15201. Retracting rl*prefer*rvt*predict-yes*H0*5
  15202. -->
  15203. (S1 ^operator O2007 = 0.06777563629847527)
  15204. =>WM: (14108: S1 ^operator O2010 +)
  15205. =>WM: (14107: S1 ^operator O2009 +)
  15206. =>WM: (14106: I3 ^dir U)
  15207. =>WM: (14105: O2010 ^name predict-no)
  15208. =>WM: (14104: O2009 ^name predict-yes)
  15209. =>WM: (14103: R1008 ^value 1)
  15210. =>WM: (14102: R1 ^reward R1008)
  15211. <=WM: (14093: S1 ^operator O2007 +)
  15212. <=WM: (14094: S1 ^operator O2008 +)
  15213. <=WM: (14095: S1 ^operator O2008)
  15214. <=WM: (14079: I3 ^dir R)
  15215. <=WM: (14089: R1 ^reward R1007)
  15216. <=WM: (14092: O2008 ^name predict-no)
  15217. <=WM: (14091: O2007 ^name predict-yes)
  15218. <=WM: (14090: R1007 ^value 1)
  15219. --- Inner Elaboration Phase, active level 1 (S1) ---
  15220. Firing prefer*rvt*predict-yes*H0
  15221. -->
  15222. Firing rl*prefer*rvt*predict-yes*H0*1
  15223. -->
  15224. (S1 ^operator O2009 = 0.)
  15225. Firing prefer*rvt*predict-no*H0
  15226. -->
  15227. Firing rl*prefer*rvt*predict-no*H0*2
  15228. -->
  15229. (S1 ^operator O2010 = 0.9999999999999999)
  15230. inner elaboration loop at bottom goal.
  15231. Retracting rl*prefer*rvt*predict-no*H0*2
  15232. -->
  15233. (S1 ^operator O2008 = 0.9999999999999999)
  15234. Retracting rl*prefer*rvt*predict-yes*H0*1
  15235. -->
  15236. (S1 ^operator O2007 = 0.)
  15237. --- END Proposal Phase ---
  15238. --- Decision Phase ---
  15239. RL update rl*prefer*rvt*predict-no*H0*6 0.679081 -0.214722 0.464359 -> 0.679081 -0.214722 0.46436(R,m,v=1,0.971264,0.0280712)
  15240. RL update rl*prefer*rvt*predict-no*H0*6*H1*22 0.320917 0.214722 0.535639 -> 0.320917 0.214722 0.535639(R,m,v=1,1,0)
  15241. =>WM: (14109: S1 ^operator O2010)
  15242. 1005: O: O2010 (predict-no)
  15243. --- END Decision Phase ---
  15244. --- Application Phase ---
  15245. --- Firing Productions (PE) For State At Depth 1 ---
  15246. --- Inner Elaboration Phase, active level 1 (S1) ---
  15247. Firing apply*operator
  15248. -->
  15249. (I3 ^predict-no N1005 + :O )
  15250. Firing apply*operator*complete
  15251. -->
  15252. (I3 ^predict-no N1004 - :O )
  15253. inner elaboration loop at bottom goal.
  15254. --- Change Working Memory (PE) ---
  15255. =>WM: (14110: I3 ^predict-no N1005)
  15256. <=WM: (14097: N1004 ^status complete)
  15257. <=WM: (14096: I3 ^predict-no N1004)
  15258. --- Firing Productions (IE) For State At Depth 1 ---
  15259. --- Inner Elaboration Phase, active level 1 (S1) ---
  15260. Firing monitor*world
  15261. -->
  15262. I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
  15263. --- Change Working Memory (IE) ---
  15264. --- END Application Phase ---
  15265. --- Output Phase ---
  15266. ENV: Agent did: predict-no for direction U in state State-B
  15267. In State-B moving U
  15268. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  15269. predict error 0
  15270. dir: dir isU
  15271. --- END Output Phase ---
  15272. -/|--- Input Phase ---
  15273. =>WM: (14114: I2 ^dir U)
  15274. =>WM: (14113: I2 ^reward 1)
  15275. =>WM: (14112: I2 ^see 0)
  15276. =>WM: (14111: N1005 ^status complete)
  15277. <=WM: (14100: I2 ^dir U)
  15278. <=WM: (14099: I2 ^reward 1)
  15279. <=WM: (14098: I2 ^see 0)
  15280. =>WM: (14115: I2 ^level-1 R0-root)
  15281. <=WM: (14101: I2 ^level-1 R0-root)
  15282. --- END Input Phase ---
  15283. --- Proposal Phase ---
  15284. --- Inner Elaboration Phase, active level 1 (S1) ---
  15285. Firing elaborate*copy-see-to-output-link
  15286. -->
  15287. (I3 ^see 0 +)
  15288. Firing elaborate*reward*based*on*reward
  15289. -->
  15290. (R1009 ^value 1 +)
  15291. (R1 ^reward R1009 +)
  15292. Firing propose*predict-yes
  15293. -->
  15294. (O2011 ^name predict-yes +)
  15295. (S1 ^operator O2011 +)
  15296. Firing propose*predict-no
  15297. -->
  15298. (O2012 ^name predict-no +)
  15299. (S1 ^operator O2012 +)
  15300. Firing rl*prefer*rvt*predict-no*H0*2
  15301. -->
  15302. (S1 ^operator O2010 = 0.9999999999999999)
  15303. Firing rl*prefer*rvt*predict-yes*H0*1
  15304. -->
  15305. (S1 ^operator O2009 = 0.)
  15306. Firing prefer*rvt*predict-yes*H0
  15307. -->
  15308. Firing prefer*rvt*predict-no*H0
  15309. -->
  15310. Firing elaborate*copy-dir-to-output-link
  15311. -->
  15312. (I3 ^dir U +)
  15313. inner elaboration loop at bottom goal.
  15314. Retracting elaborate*copy-see-to-output-link
  15315. -->
  15316. (I3 ^see 0 +)
  15317. Retracting propose*predict-no
  15318. -->
  15319. (O2010 ^name predict-no +)
  15320. (S1 ^operator O2010 +)
  15321. Retracting propose*predict-yes
  15322. -->
  15323. (O2009 ^name predict-yes +)
  15324. (S1 ^operator O2009 +)
  15325. Retracting elaborate*reward*based*on*reward
  15326. -->
  15327. (R1008 ^value 1 +)
  15328. (R1 ^reward R1008 +)
  15329. Retracting elaborate*copy-dir-to-output-link
  15330. -->
  15331. (I3 ^dir U +)
  15332. Retracting rl*prefer*rvt*predict-no*H0*2
  15333. -->
  15334. (S1 ^operator O2010 = 0.9999999999999999)
  15335. Retracting rl*prefer*rvt*predict-yes*H0*1
  15336. -->
  15337. (S1 ^operator O2009 = 0.)
  15338. =>WM: (14121: S1 ^operator O2012 +)
  15339. =>WM: (14120: S1 ^operator O2011 +)
  15340. =>WM: (14119: O2012 ^name predict-no)
  15341. =>WM: (14118: O2011 ^name predict-yes)
  15342. =>WM: (14117: R1009 ^value 1)
  15343. =>WM: (14116: R1 ^reward R1009)
  15344. <=WM: (14107: S1 ^operator O2009 +)
  15345. <=WM: (14108: S1 ^operator O2010 +)
  15346. <=WM: (14109: S1 ^operator O2010)
  15347. <=WM: (14102: R1 ^reward R1008)
  15348. <=WM: (14105: O2010 ^name predict-no)
  15349. <=WM: (14104: O2009 ^name predict-yes)
  15350. <=WM: (14103: R1008 ^value 1)
  15351. --- Inner Elaboration Phase, active level 1 (S1) ---
  15352. Firing prefer*rvt*predict-yes*H0
  15353. -->
  15354. Firing rl*prefer*rvt*predict-yes*H0*1
  15355. -->
  15356. (S1 ^operator O2011 = 0.)
  15357. Firing prefer*rvt*predict-no*H0
  15358. -->
  15359. Firing rl*prefer*rvt*predict-no*H0*2
  15360. -->
  15361. (S1 ^operator O2012 = 0.9999999999999999)
  15362. inner elaboration loop at bottom goal.
  15363. Retracting rl*prefer*rvt*predict-no*H0*2
  15364. -->
  15365. (S1 ^operator O2010 = 0.9999999999999999)
  15366. Retracting rl*prefer*rvt*predict-yes*H0*1
  15367. -->
  15368. (S1 ^operator O2009 = 0.)
  15369. --- END Proposal Phase ---
  15370. --- Decision Phase ---
  15371. RL update rl*prefer*rvt*predict-no*H0*2 1 0 1 -> 1 0 1(R,m,v=1,1,0)
  15372. =>WM: (14122: S1 ^operator O2012)
  15373. 1006: O: O2012 (predict-no)
  15374. --- END Decision Phase ---
  15375. --- Application Phase ---
  15376. --- Firing Productions (PE) For State At Depth 1 ---
  15377. --- Inner Elaboration Phase, active level 1 (S1) ---
  15378. Firing apply*operator
  15379. -->
  15380. (I3 ^predict-no N1006 + :O )
  15381. Firing apply*operator*complete
  15382. -->
  15383. (I3 ^predict-no N1005 - :O )
  15384. inner elaboration loop at bottom goal.
  15385. --- Change Working Memory (PE) ---
  15386. =>WM: (14123: I3 ^predict-no N1006)
  15387. <=WM: (14111: N1005 ^status complete)
  15388. <=WM: (14110: I3 ^predict-no N1005)
  15389. --- Firing Productions (IE) For State At Depth 1 ---
  15390. --- Inner Elaboration Phase, active level 1 (S1) ---
  15391. Firing monitor*world
  15392. -->
  15393. I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
  15394. --- Change Working Memory (IE) ---
  15395. --- END Application Phase ---
  15396. --- Output Phase ---
  15397. ENV: Agent did: predict-no for direction U in state State-B
  15398. In State-B moving U
  15399. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  15400. predict error 0
  15401. dir: dir isL
  15402. --- END Output Phase ---
  15403. \-/--- Input Phase ---
  15404. =>WM: (14127: I2 ^dir L)
  15405. =>WM: (14126: I2 ^reward 1)
  15406. =>WM: (14125: I2 ^see 0)
  15407. =>WM: (14124: N1006 ^status complete)
  15408. <=WM: (14114: I2 ^dir U)
  15409. <=WM: (14113: I2 ^reward 1)
  15410. <=WM: (14112: I2 ^see 0)
  15411. =>WM: (14128: I2 ^level-1 R0-root)
  15412. <=WM: (14115: I2 ^level-1 R0-root)
  15413. --- END Input Phase ---
  15414. --- Proposal Phase ---
  15415. --- Inner Elaboration Phase, active level 1 (S1) ---
  15416. Firing rl*prefer*rvt*predict-no*H0*4*H1*8
  15417. -->
  15418. (S1 ^operator O2012 = -0.2450868666562052)
  15419. Firing rl*prefer*rvt*predict-yes*H0*3*H1*9
  15420. -->
  15421. (S1 ^operator O2011 = 0.3930864686622045)
  15422. Firing prefer*rvt*predict-no*H0*4*H1
  15423. -->
  15424. Firing prefer*rvt*predict-yes*H0*3*H1
  15425. -->
  15426. Firing elaborate*copy-see-to-output-link
  15427. -->
  15428. (I3 ^see 0 +)
  15429. Firing elaborate*reward*based*on*reward
  15430. -->
  15431. (R1010 ^value 1 +)
  15432. (R1 ^reward R1010 +)
  15433. Firing propose*predict-yes
  15434. -->
  15435. (O2013 ^name predict-yes +)
  15436. (S1 ^operator O2013 +)
  15437. Firing propose*predict-no
  15438. -->
  15439. (O2014 ^name predict-no +)
  15440. (S1 ^operator O2014 +)
  15441. Firing rl*prefer*rvt*predict-no*H0*4
  15442. -->
  15443. (S1 ^operator O2012 = 0.4334987883373633)
  15444. Firing rl*prefer*rvt*predict-yes*H0*3
  15445. -->
  15446. (S1 ^operator O2011 = 0.6069227382490706)
  15447. Firing prefer*rvt*predict-yes*H0
  15448. -->
  15449. Firing prefer*rvt*predict-no*H0
  15450. -->
  15451. Firing elaborate*copy-dir-to-output-link
  15452. -->
  15453. (I3 ^dir L +)
  15454. inner elaboration loop at bottom goal.
  15455. Retracting elaborate*copy-see-to-output-link
  15456. -->
  15457. (I3 ^see 0 +)
  15458. Retracting propose*predict-no
  15459. -->
  15460. (O2012 ^name predict-no +)
  15461. (S1 ^operator O2012 +)
  15462. Retracting propose*predict-yes
  15463. -->
  15464. (O2011 ^name predict-yes +)
  15465. (S1 ^operator O2011 +)
  15466. Retracting elaborate*reward*based*on*reward
  15467. -->
  15468. (R1009 ^value 1 +)
  15469. (R1 ^reward R1009 +)
  15470. Retracting elaborate*copy-dir-to-output-link
  15471. -->
  15472. (I3 ^dir U +)
  15473. Retracting rl*prefer*rvt*predict-no*H0*2
  15474. -->
  15475. (S1 ^operator O2012 = 0.9999999999999999)
  15476. Retracting rl*prefer*rvt*predict-yes*H0*1
  15477. -->
  15478. (S1 ^operator O2011 = 0.)
  15479. =>WM: (14135: S1 ^operator O2014 +)
  15480. =>WM: (14134: S1 ^operator O2013 +)
  15481. =>WM: (14133: I3 ^dir L)
  15482. =>WM: (14132: O2014 ^name predict-no)
  15483. =>WM: (14131: O2013 ^name predict-yes)
  15484. =>WM: (14130: R1010 ^value 1)
  15485. =>WM: (14129: R1 ^reward R1010)
  15486. <=WM: (14120: S1 ^operator O2011 +)
  15487. <=WM: (14121: S1 ^operator O2012 +)
  15488. <=WM: (14122: S1 ^operator O2012)
  15489. <=WM: (14106: I3 ^dir U)
  15490. <=WM: (14116: R1 ^reward R1009)
  15491. <=WM: (14119: O2012 ^name predict-no)
  15492. <=WM: (14118: O2011 ^name predict-yes)
  15493. <=WM: (14117: R1009 ^value 1)
  15494. --- Inner Elaboration Phase, active level 1 (S1) ---
  15495. Firing prefer*rvt*predict-yes*H0
  15496. -->
  15497. Firing rl*prefer*rvt*predict-yes*H0*3*H1*9
  15498. -->
  15499. (S1 ^operator O2013 = 0.3930864686622045)
  15500. Firing rl*prefer*rvt*predict-yes*H0*3
  15501. -->
  15502. (S1 ^operator O2013 = 0.6069227382490706)
  15503. Firing prefer*rvt*predict-yes*H0*3*H1
  15504. -->
  15505. Firing prefer*rvt*predict-no*H0
  15506. -->
  15507. Firing rl*prefer*rvt*predict-no*H0*4*H1*8
  15508. -->
  15509. (S1 ^operator O2014 = -0.2450868666562052)
  15510. Firing rl*prefer*rvt*predict-no*H0*4
  15511. -->
  15512. (S1 ^operator O2014 = 0.4334987883373633)
  15513. Firing prefer*rvt*predict-no*H0*4*H1
  15514. -->
  15515. inner elaboration loop at bottom goal.
  15516. Retracting rl*prefer*rvt*predict-no*H0*4
  15517. -->
  15518. (S1 ^operator O2012 = 0.4334987883373633)
  15519. Retracting rl*prefer*rvt*predict-no*H0*4*H1*8
  15520. -->
  15521. (S1 ^operator O2012 = -0.2450868666562052)
  15522. Retracting rl*prefer*rvt*predict-yes*H0*3
  15523. -->
  15524. (S1 ^operator O2011 = 0.6069227382490706)
  15525. Retracting rl*prefer*rvt*predict-yes*H0*3*H1*9
  15526. -->
  15527. (S1 ^operator O2011 = 0.3930864686622045)
  15528. --- END Proposal Phase ---
  15529. --- Decision Phase ---
  15530. RL update rl*prefer*rvt*predict-no*H0*2 1 0 1 -> 1 0 1(R,m,v=1,1,0)
  15531. =>WM: (14136: S1 ^operator O2013)
  15532. 1007: O: O2013 (predict-yes)
  15533. --- END Decision Phase ---
  15534. --- Application Phase ---
  15535. --- Firing Productions (PE) For State At Depth 1 ---
  15536. --- Inner Elaboration Phase, active level 1 (S1) ---
  15537. Firing apply*operator
  15538. -->
  15539. (I3 ^predict-yes N1007 + :O )
  15540. Firing apply*operator*complete
  15541. -->
  15542. (I3 ^predict-no N1006 - :O )
  15543. inner elaboration loop at bottom goal.
  15544. --- Change Working Memory (PE) ---
  15545. =>WM: (14137: I3 ^predict-yes N1007)
  15546. <=WM: (14124: N1006 ^status complete)
  15547. <=WM: (14123: I3 ^predict-no N1006)
  15548. --- Firing Productions (IE) For State At Depth 1 ---
  15549. --- Inner Elaboration Phase, active level 1 (S1) ---
  15550. Firing monitor*world
  15551. -->
  15552. I see 1 and I'm going to do: predict-yes inner elaboration loop at bottom goal.
  15553. --- Change Working Memory (IE) ---
  15554. --- END Application Phase ---
  15555. --- Output Phase ---
  15556. ENV: Agent did: predict-yes for direction L in state State-B
  15557. In State-B moving L
  15558. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  15559. predict error 0
  15560. dir: dir isR
  15561. --- END Output Phase ---
  15562. |\---- Input Phase ---
  15563. =>WM: (14141: I2 ^dir R)
  15564. =>WM: (14140: I2 ^reward 1)
  15565. =>WM: (14139: I2 ^see 1)
  15566. =>WM: (14138: N1007 ^status complete)
  15567. <=WM: (14127: I2 ^dir L)
  15568. <=WM: (14126: I2 ^reward 1)
  15569. <=WM: (14125: I2 ^see 0)
  15570. =>WM: (14142: I2 ^level-1 L1-root)
  15571. <=WM: (14128: I2 ^level-1 R0-root)
  15572. --- END Input Phase ---
  15573. --- Proposal Phase ---
  15574. --- Inner Elaboration Phase, active level 1 (S1) ---
  15575. Firing rl*prefer*rvt*predict-yes*H0*5*H1*18
  15576. -->
  15577. (S1 ^operator O2013 = 0.9322241461092005)
  15578. Firing rl*prefer*rvt*predict-no*H0*6*H1*21
  15579. -->
  15580. (S1 ^operator O2014 = -0.006920940195066783)
  15581. Firing prefer*rvt*predict-no*H0*6*H1
  15582. -->
  15583. Firing prefer*rvt*predict-yes*H0*5*H1
  15584. -->
  15585. Firing elaborate*copy-see-to-output-link
  15586. -->
  15587. (I3 ^see 1 +)
  15588. Firing elaborate*reward*based*on*reward
  15589. -->
  15590. (R1011 ^value 1 +)
  15591. (R1 ^reward R1011 +)
  15592. Firing propose*predict-yes
  15593. -->
  15594. (O2015 ^name predict-yes +)
  15595. (S1 ^operator O2015 +)
  15596. Firing propose*predict-no
  15597. -->
  15598. (O2016 ^name predict-no +)
  15599. (S1 ^operator O2016 +)
  15600. Firing rl*prefer*rvt*predict-no*H0*6
  15601. -->
  15602. (S1 ^operator O2014 = 0.4643595378258389)
  15603. Firing rl*prefer*rvt*predict-yes*H0*5
  15604. -->
  15605. (S1 ^operator O2013 = 0.06777563629847527)
  15606. Firing prefer*rvt*predict-yes*H0
  15607. -->
  15608. Firing prefer*rvt*predict-no*H0
  15609. -->
  15610. Firing elaborate*copy-dir-to-output-link
  15611. -->
  15612. (I3 ^dir R +)
  15613. inner elaboration loop at bottom goal.
  15614. Retracting elaborate*copy-see-to-output-link
  15615. -->
  15616. (I3 ^see 0 +)
  15617. Retracting propose*predict-no
  15618. -->
  15619. (O2014 ^name predict-no +)
  15620. (S1 ^operator O2014 +)
  15621. Retracting propose*predict-yes
  15622. -->
  15623. (O2013 ^name predict-yes +)
  15624. (S1 ^operator O2013 +)
  15625. Retracting elaborate*reward*based*on*reward
  15626. -->
  15627. (R1010 ^value 1 +)
  15628. (R1 ^reward R1010 +)
  15629. Retracting elaborate*copy-dir-to-output-link
  15630. -->
  15631. (I3 ^dir L +)
  15632. Retracting rl*prefer*rvt*predict-no*H0*4
  15633. -->
  15634. (S1 ^operator O2014 = 0.4334987883373633)
  15635. Retracting rl*prefer*rvt*predict-no*H0*4*H1*8
  15636. -->
  15637. (S1 ^operator O2014 = -0.2450868666562052)
  15638. Retracting rl*prefer*rvt*predict-yes*H0*3
  15639. -->
  15640. (S1 ^operator O2013 = 0.6069227382490706)
  15641. Retracting rl*prefer*rvt*predict-yes*H0*3*H1*9
  15642. -->
  15643. (S1 ^operator O2013 = 0.3930864686622045)
  15644. =>WM: (14150: S1 ^operator O2016 +)
  15645. =>WM: (14149: S1 ^operator O2015 +)
  15646. =>WM: (14148: I3 ^dir R)
  15647. =>WM: (14147: O2016 ^name predict-no)
  15648. =>WM: (14146: O2015 ^name predict-yes)
  15649. =>WM: (14145: R1011 ^value 1)
  15650. =>WM: (14144: R1 ^reward R1011)
  15651. =>WM: (14143: I3 ^see 1)
  15652. <=WM: (14134: S1 ^operator O2013 +)
  15653. <=WM: (14136: S1 ^operator O2013)
  15654. <=WM: (14135: S1 ^operator O2014 +)
  15655. <=WM: (14133: I3 ^dir L)
  15656. <=WM: (14129: R1 ^reward R1010)
  15657. <=WM: (14048: I3 ^see 0)
  15658. <=WM: (14132: O2014 ^name predict-no)
  15659. <=WM: (14131: O2013 ^name predict-yes)
  15660. <=WM: (14130: R1010 ^value 1)
  15661. --- Inner Elaboration Phase, active level 1 (S1) ---
  15662. Firing prefer*rvt*predict-yes*H0
  15663. -->
  15664. Firing rl*prefer*rvt*predict-yes*H0*5
  15665. -->
  15666. (S1 ^operator O2015 = 0.06777563629847527)
  15667. Firing prefer*rvt*predict-yes*H0*5*H1
  15668. -->
  15669. Firing rl*prefer*rvt*predict-yes*H0*5*H1*18
  15670. -->
  15671. (S1 ^operator O2015 = 0.9322241461092005)
  15672. Firing prefer*rvt*predict-no*H0
  15673. -->
  15674. Firing rl*prefer*rvt*predict-no*H0*6
  15675. -->
  15676. (S1 ^operator O2016 = 0.4643595378258389)
  15677. Firing prefer*rvt*predict-no*H0*6*H1
  15678. -->
  15679. Firing rl*prefer*rvt*predict-no*H0*6*H1*21
  15680. -->
  15681. (S1 ^operator O2016 = -0.006920940195066783)
  15682. inner elaboration loop at bottom goal.
  15683. Retracting rl*prefer*rvt*predict-no*H0*6
  15684. -->
  15685. (S1 ^operator O2014 = 0.4643595378258389)
  15686. Retracting rl*prefer*rvt*predict-no*H0*6*H1*21
  15687. -->
  15688. (S1 ^operator O2014 = -0.006920940195066783)
  15689. Retracting rl*prefer*rvt*predict-yes*H0*5
  15690. -->
  15691. (S1 ^operator O2013