PageRenderTime 140ms CodeModel.GetById 18ms RepoModel.GetById 1ms app.codeStats 0ms

/flipv2/20121113-091142-2.5K-ReLST-asneeded_epochs_50_5runs_noalphadecay/stdout-flip-2.5K_3.txt

https://bitbucket.org/evan13579b/soar-ziggurat
Plain Text | 16412 lines | 15689 code | 723 blank | 0 comment | 0 complexity | 117951999a9c01c4172ea6893d520a0c MD5 | raw file
Possible License(s): BSD-3-Clause
  1. Seeding... 3
  2. dir: dir isL
  3. Python-Soar Flip environment.
  4. To accept commands from an external sml process, you'll need to
  5. type 'slave <log file> <n decisons>' at the prompt...
  6. sourcing 'flip_predict.soar'
  7. ***********
  8. Total: 11 productions sourced.
  9. seeding Soar with 3 ...
  10. soar> Entering slave mode:
  11. - log file 'rl-slave-2.5K_3.log'....
  12. - will exit slave mode after 2500 decisions
  13. waiting for commands from an externally connected sml process...
  14. -/|sleeping...
  15. \sleeping...
  16. -sleeping...
  17. /sleeping...
  18. |sleeping...
  19. \-/|\-/|\-sleeping...
  20. /|\-/|\sleeping...
  21. -1: O: O2 (predict-no)
  22. I see 0 and I'm going to do: predict-no
  23. ENV: Agent did: predict-no for direction L in state State-A
  24. In State-A moving L
  25. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  26. predict error 0
  27. dir: dir isR
  28. rule alias: '*'
  29. rule alias: '*'
  30. /|\-/|\2: O: O3 (predict-yes)
  31. I see 1 and I'm going to do: predict-yes
  32. ENV: Agent did: predict-yes for direction R in state State-A
  33. In State-A moving R
  34. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  35. predict error 0
  36. dir: dir isR
  37. -/|3: O: O6 (predict-no)
  38. I see 1 and I'm going to do: predict-no
  39. ENV: Agent did: predict-no for direction R in state State-B
  40. In State-B moving R
  41. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  42. predict error 0
  43. dir: dir isR
  44. \-/4: O: O7 (predict-yes)
  45. I see 1 and I'm going to do: predict-yes
  46. ENV: Agent did: predict-yes for direction R in state State-B
  47. In State-B moving R
  48. ENV: (next state, see, prediction correct?) = (State-B, 0, False)
  49. predict error 1
  50. dir: dir isR
  51. |\5: O: O9 (predict-yes)
  52. I see 0 and I'm going to do: predict-yes
  53. ENV: Agent did: predict-yes for direction R in state State-B
  54. In State-B moving R
  55. ENV: (next state, see, prediction correct?) = (State-B, 0, False)
  56. predict error 1
  57. dir: dir isL
  58. -/|6: O: O12 (predict-no)
  59. I see 0 and I'm going to do: predict-no
  60. ENV: Agent did: predict-no for direction L in state State-B
  61. In State-B moving L
  62. ENV: (next state, see, prediction correct?) = (State-A, 1, False)
  63. predict error 1
  64. dir: dir isL
  65. \-/|7: O: O14 (predict-no)
  66. I see 0 and I'm going to do: predict-no
  67. ENV: Agent did: predict-no for direction L in state State-A
  68. In State-A moving L
  69. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  70. predict error 0
  71. dir: dir isU
  72. \-8: O: O15 (predict-yes)
  73. I see 1 and I'm going to do: predict-yes
  74. ENV: Agent did: predict-yes for direction U in state State-A
  75. In State-A moving U
  76. ENV: (next state, see, prediction correct?) = (State-A, 0, False)
  77. predict error 1
  78. dir: dir isL
  79. /|9: O: O18 (predict-no)
  80. I see 0 and I'm going to do: predict-no
  81. ENV: Agent did: predict-no for direction L in state State-A
  82. In State-A moving L
  83. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  84. predict error 0
  85. dir: dir isL
  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 L in state State-A
  89. In State-A moving L
  90. ENV: (next state, see, prediction correct?) = (State-A, 0, False)
  91. predict error 1
  92. dir: dir isU
  93. |11: O: O22 (predict-no)
  94. I see 0 and I'm going to do: predict-no
  95. ENV: Agent did: predict-no for direction U in state State-A
  96. In State-A moving U
  97. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  98. predict error 0
  99. dir: dir isR
  100. rule alias: '*'
  101. rule alias: '*'
  102. rule alias: '*'
  103. rule alias: '*'
  104. \12: O: O24 (predict-no)
  105. I see 1 and I'm going to do: predict-no
  106. ENV: Agent did: predict-no for direction R in state State-A
  107. In State-A moving R
  108. ENV: (next state, see, prediction correct?) = (State-B, 1, False)
  109. predict error 1
  110. dir: dir isU
  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 U in state State-B
  114. In State-B moving U
  115. ENV: (next state, see, prediction correct?) = (State-B, 0, False)
  116. predict error 1
  117. dir: dir isR
  118. \14: O: O28 (predict-no)
  119. I see 0 and I'm going to do: predict-no
  120. ENV: Agent did: predict-no for direction R in state State-B
  121. In State-B moving R
  122. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  123. predict error 0
  124. dir: dir isR
  125. -/15: O: O30 (predict-no)
  126. I see 1 and I'm going to do: predict-no
  127. ENV: Agent did: predict-no for direction R in state State-B
  128. In State-B moving R
  129. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  130. predict error 0
  131. dir: dir isL
  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 L in state State-B
  135. In State-B moving L
  136. ENV: (next state, see, prediction correct?) = (State-A, 1, False)
  137. predict error 1
  138. dir: dir isR
  139. /|17: O: O33 (predict-yes)
  140. I see 0 and I'm going to do: predict-yes
  141. ENV: Agent did: predict-yes for direction R in state State-A
  142. In State-A moving R
  143. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  144. predict error 0
  145. dir: dir isU
  146. \-/18: O: O36 (predict-no)
  147. I see 1 and I'm going to do: predict-no
  148. ENV: Agent did: predict-no for direction U in state State-B
  149. In State-B moving U
  150. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  151. predict error 0
  152. dir: dir isR
  153. |\-19: O: O38 (predict-no)
  154. I see 1 and I'm going to do: predict-no
  155. ENV: Agent did: predict-no for direction R in state State-B
  156. In State-B moving R
  157. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  158. predict error 0
  159. dir: dir isU
  160. /|\20: O: O40 (predict-no)
  161. I see 1 and I'm going to do: predict-no
  162. ENV: Agent did: predict-no for direction U in state State-B
  163. In State-B moving U
  164. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  165. predict error 0
  166. dir: dir isU
  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 U in state State-B
  170. In State-B moving U
  171. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  172. predict error 0
  173. dir: dir isL
  174. |22: O: O44 (predict-no)
  175. I see 1 and I'm going to do: predict-no
  176. ENV: Agent did: predict-no for direction L in state State-B
  177. In State-B moving L
  178. ENV: (next state, see, prediction correct?) = (State-A, 1, False)
  179. predict error 1
  180. dir: dir isU
  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 U in state State-A
  184. In State-A moving U
  185. ENV: (next state, see, prediction correct?) = (State-A, 0, False)
  186. predict error 1
  187. dir: dir isR
  188. /|\-24: O: O48 (predict-no)
  189. I see 0 and I'm going to do: predict-no
  190. ENV: Agent did: predict-no for direction R in state State-A
  191. In State-A moving R
  192. ENV: (next state, see, prediction correct?) = (State-B, 1, False)
  193. predict error 1
  194. dir: dir isL
  195. /|\25: O: O50 (predict-no)
  196. I see 0 and I'm going to do: predict-no
  197. ENV: Agent did: predict-no for direction L in state State-B
  198. In State-B moving L
  199. ENV: (next state, see, prediction correct?) = (State-A, 1, False)
  200. predict error 1
  201. dir: dir isL
  202. -/|26: O: O52 (predict-no)
  203. I see 0 and I'm going to do: predict-no
  204. ENV: Agent did: predict-no for direction L in state State-A
  205. In State-A moving L
  206. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  207. predict error 0
  208. dir: dir isU
  209. \-/27: O: O54 (predict-no)
  210. I see 1 and I'm going to do: predict-no
  211. ENV: Agent did: predict-no for direction U in state State-A
  212. In State-A moving U
  213. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  214. predict error 0
  215. dir: dir isR
  216. |\28: O: O56 (predict-no)
  217. I see 1 and I'm going to do: predict-no
  218. ENV: Agent did: predict-no for direction R in state State-A
  219. In State-A moving R
  220. ENV: (next state, see, prediction correct?) = (State-B, 1, False)
  221. predict error 1
  222. dir: dir isU
  223. -/|29: O: O58 (predict-no)
  224. I see 0 and I'm going to do: predict-no
  225. ENV: Agent did: predict-no for direction U in state State-B
  226. In State-B moving U
  227. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  228. predict error 0
  229. dir: dir isU
  230. \-30: O: O60 (predict-no)
  231. I see 1 and I'm going to do: predict-no
  232. ENV: Agent did: predict-no for direction U in state State-B
  233. In State-B moving U
  234. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  235. predict error 0
  236. dir: dir isU
  237. /31: O: O62 (predict-no)
  238. I see 1 and I'm going to do: predict-no
  239. ENV: Agent did: predict-no for direction U in state State-B
  240. In State-B moving U
  241. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  242. predict error 0
  243. dir: dir isU
  244. |32: O: O64 (predict-no)
  245. I see 1 and I'm going to do: predict-no
  246. ENV: Agent did: predict-no for direction U in state State-B
  247. In State-B moving U
  248. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  249. predict error 0
  250. dir: dir isR
  251. \-/33: O: O66 (predict-no)
  252. I see 1 and I'm going to do: predict-no
  253. ENV: Agent did: predict-no for direction R in state State-B
  254. In State-B moving R
  255. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  256. predict error 0
  257. dir: dir isU
  258. |\-34: O: O68 (predict-no)
  259. I see 1 and I'm going to do: predict-no
  260. ENV: Agent did: predict-no for direction U in state State-B
  261. In State-B moving U
  262. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  263. predict error 0
  264. dir: dir isR
  265. /|\35: O: O70 (predict-no)
  266. I see 1 and I'm going to do: predict-no
  267. ENV: Agent did: predict-no for direction R in state State-B
  268. In State-B moving R
  269. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  270. predict error 0
  271. dir: dir isU
  272. -/|36: O: O72 (predict-no)
  273. I see 1 and I'm going to do: predict-no
  274. ENV: Agent did: predict-no for direction U in state State-B
  275. In State-B moving U
  276. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  277. predict error 0
  278. dir: dir isU
  279. \37: O: O74 (predict-no)
  280. I see 1 and I'm going to do: predict-no
  281. ENV: Agent did: predict-no for direction U in state State-B
  282. In State-B moving U
  283. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  284. predict error 0
  285. dir: dir isL
  286. -/38: O: O76 (predict-no)
  287. I see 1 and I'm going to do: predict-no
  288. ENV: Agent did: predict-no for direction L in state State-B
  289. In State-B moving L
  290. ENV: (next state, see, prediction correct?) = (State-A, 1, False)
  291. predict error 1
  292. dir: dir isL
  293. |\-39: O: O78 (predict-no)
  294. I see 0 and I'm going to do: predict-no
  295. ENV: Agent did: predict-no for direction L in state State-A
  296. In State-A moving L
  297. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  298. predict error 0
  299. dir: dir isL
  300. /|40: O: O80 (predict-no)
  301. I see 1 and I'm going to do: predict-no
  302. ENV: Agent did: predict-no for direction L in state State-A
  303. In State-A moving L
  304. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  305. predict error 0
  306. dir: dir isU
  307. \-41: O: O82 (predict-no)
  308. I see 1 and I'm going to do: predict-no
  309. ENV: Agent did: predict-no for direction U in state State-A
  310. In State-A moving U
  311. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  312. predict error 0
  313. dir: dir isR
  314. /42: O: O84 (predict-no)
  315. I see 1 and I'm going to do: predict-no
  316. ENV: Agent did: predict-no for direction R in state State-A
  317. In State-A moving R
  318. ENV: (next state, see, prediction correct?) = (State-B, 1, False)
  319. predict error 1
  320. dir: dir isR
  321. |\-43: O: O86 (predict-no)
  322. I see 0 and I'm going to do: predict-no
  323. ENV: Agent did: predict-no for direction R in state State-B
  324. In State-B moving R
  325. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  326. predict error 0
  327. dir: dir isL
  328. /|\44: O: O88 (predict-no)
  329. I see 1 and I'm going to do: predict-no
  330. ENV: Agent did: predict-no for direction L in state State-B
  331. In State-B moving L
  332. ENV: (next state, see, prediction correct?) = (State-A, 1, False)
  333. predict error 1
  334. dir: dir isR
  335. -/45: O: O90 (predict-no)
  336. I see 0 and I'm going to do: predict-no
  337. ENV: Agent did: predict-no for direction R in state State-A
  338. In State-A moving R
  339. ENV: (next state, see, prediction correct?) = (State-B, 1, False)
  340. predict error 1
  341. dir: dir isR
  342. |\-46: O: O92 (predict-no)
  343. I see 0 and I'm going to do: predict-no
  344. ENV: Agent did: predict-no for direction R in state State-B
  345. In State-B moving R
  346. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  347. predict error 0
  348. dir: dir isR
  349. /|\47: O: O94 (predict-no)
  350. I see 1 and I'm going to do: predict-no
  351. ENV: Agent did: predict-no for direction R in state State-B
  352. In State-B moving R
  353. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  354. predict error 0
  355. dir: dir isR
  356. -/48: O: O96 (predict-no)
  357. I see 1 and I'm going to do: predict-no
  358. ENV: Agent did: predict-no for direction R in state State-B
  359. In State-B moving R
  360. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  361. predict error 0
  362. dir: dir isR
  363. |\-49: O: O98 (predict-no)
  364. I see 1 and I'm going to do: predict-no
  365. ENV: Agent did: predict-no for direction R in state State-B
  366. In State-B moving R
  367. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  368. predict error 0
  369. dir: dir isU
  370. /50: O: O100 (predict-no)
  371. I see 1 and I'm going to do: predict-no
  372. ENV: Agent did: predict-no for direction U in state State-B
  373. In State-B moving U
  374. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  375. predict error 0
  376. dir: dir isU
  377. |\-/|\sleeping...
  378. -51: O: O102 (predict-no)
  379. I see 1 and I'm going to do: predict-no
  380. ENV: Agent did: predict-no for direction U in state State-B
  381. In State-B moving U
  382. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  383. predict error 0
  384. dir: dir isU
  385. /52: O: O104 (predict-no)
  386. I see 1 and I'm going to do: predict-no
  387. ENV: Agent did: predict-no for direction U in state State-B
  388. In State-B moving U
  389. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  390. predict error 0
  391. dir: dir isU
  392. |\53: O: O106 (predict-no)
  393. I see 1 and I'm going to do: predict-no
  394. ENV: Agent did: predict-no for direction U in state State-B
  395. In State-B moving U
  396. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  397. predict error 0
  398. dir: dir isU
  399. -/54: O: O108 (predict-no)
  400. I see 1 and I'm going to do: predict-no
  401. ENV: Agent did: predict-no for direction U in state State-B
  402. In State-B moving U
  403. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  404. predict error 0
  405. dir: dir isU
  406. |\55: O: O110 (predict-no)
  407. I see 1 and I'm going to do: predict-no
  408. ENV: Agent did: predict-no for direction U in state State-B
  409. In State-B moving U
  410. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  411. predict error 0
  412. dir: dir isL
  413. -/|56: O: O112 (predict-no)
  414. I see 1 and I'm going to do: predict-no
  415. ENV: Agent did: predict-no for direction L in state State-B
  416. In State-B moving L
  417. ENV: (next state, see, prediction correct?) = (State-A, 1, False)
  418. predict error 1
  419. dir: dir isU
  420. \-57: O: O114 (predict-no)
  421. I see 0 and I'm going to do: predict-no
  422. ENV: Agent did: predict-no for direction U in state State-A
  423. In State-A moving U
  424. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  425. predict error 0
  426. dir: dir isU
  427. /|\58: O: O116 (predict-no)
  428. I see 1 and I'm going to do: predict-no
  429. ENV: Agent did: predict-no for direction U in state State-A
  430. In State-A moving U
  431. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  432. predict error 0
  433. dir: dir isU
  434. -/59: O: O118 (predict-no)
  435. I see 1 and I'm going to do: predict-no
  436. ENV: Agent did: predict-no for direction U in state State-A
  437. In State-A moving U
  438. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  439. predict error 0
  440. dir: dir isR
  441. |\60: O: O119 (predict-yes)
  442. I see 1 and I'm going to do: predict-yes
  443. ENV: Agent did: predict-yes for direction R in state State-A
  444. In State-A moving R
  445. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  446. predict error 0
  447. dir: dir isU
  448. -/61: O: O122 (predict-no)
  449. I see 1 and I'm going to do: predict-no
  450. ENV: Agent did: predict-no for direction U in state State-B
  451. In State-B moving U
  452. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  453. predict error 0
  454. dir: dir isL
  455. rule alias: '*'
  456. rule alias: '*'
  457. rule alias: '*'
  458. |62: O: O124 (predict-no)
  459. I see 1 and I'm going to do: predict-no
  460. ENV: Agent did: predict-no for direction L in state State-B
  461. In State-B moving L
  462. ENV: (next state, see, prediction correct?) = (State-A, 1, False)
  463. predict error 1
  464. dir: dir isU
  465. \-63: O: O126 (predict-no)
  466. I see 0 and I'm going to do: predict-no
  467. ENV: Agent did: predict-no for direction U in state State-A
  468. In State-A moving U
  469. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  470. predict error 0
  471. dir: dir isR
  472. /|\64: O: O128 (predict-no)
  473. I see 1 and I'm going to do: predict-no
  474. ENV: Agent did: predict-no for direction R in state State-A
  475. In State-A moving R
  476. ENV: (next state, see, prediction correct?) = (State-B, 1, False)
  477. predict error 1
  478. dir: dir isL
  479. -/|65: O: O130 (predict-no)
  480. I see 0 and I'm going to do: predict-no
  481. ENV: Agent did: predict-no for direction L in state State-B
  482. In State-B moving L
  483. ENV: (next state, see, prediction correct?) = (State-A, 1, False)
  484. predict error 1
  485. dir: dir isL
  486. \-/66: O: O132 (predict-no)
  487. I see 0 and I'm going to do: predict-no
  488. ENV: Agent did: predict-no for direction L in state State-A
  489. In State-A moving L
  490. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  491. predict error 0
  492. dir: dir isU
  493. |\-67: O: O134 (predict-no)
  494. I see 1 and I'm going to do: predict-no
  495. ENV: Agent did: predict-no for direction U in state State-A
  496. In State-A moving U
  497. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  498. predict error 0
  499. dir: dir isU
  500. /|\68: O: O136 (predict-no)
  501. I see 1 and I'm going to do: predict-no
  502. ENV: Agent did: predict-no for direction U in state State-A
  503. In State-A moving U
  504. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  505. predict error 0
  506. dir: dir isL
  507. -69: O: O138 (predict-no)
  508. I see 1 and I'm going to do: predict-no
  509. ENV: Agent did: predict-no for direction L in state State-A
  510. In State-A moving L
  511. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  512. predict error 0
  513. dir: dir isU
  514. /|\70: O: O140 (predict-no)
  515. I see 1 and I'm going to do: predict-no
  516. ENV: Agent did: predict-no for direction U in state State-A
  517. In State-A moving U
  518. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  519. predict error 0
  520. dir: dir isR
  521. -/71: O: O142 (predict-no)
  522. I see 1 and I'm going to do: predict-no
  523. ENV: Agent did: predict-no for direction R in state State-A
  524. In State-A moving R
  525. ENV: (next state, see, prediction correct?) = (State-B, 1, False)
  526. predict error 1
  527. dir: dir isL
  528. rule alias: '*'
  529. rule alias: '*'
  530. rule alias: '*'
  531. rule alias: '*'
  532. rule alias: '*'
  533. |72: O: O144 (predict-no)
  534. I see 0 and I'm going to do: predict-no
  535. ENV: Agent did: predict-no for direction L in state State-B
  536. In State-B moving L
  537. ENV: (next state, see, prediction correct?) = (State-A, 1, False)
  538. predict error 1
  539. dir: dir isL
  540. \-/|73: O: O146 (predict-no)
  541. I see 0 and I'm going to do: predict-no
  542. ENV: Agent did: predict-no for direction L in state State-A
  543. In State-A moving L
  544. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  545. predict error 0
  546. dir: dir isU
  547. \-/74: O: O148 (predict-no)
  548. I see 1 and I'm going to do: predict-no
  549. ENV: Agent did: predict-no for direction U in state State-A
  550. In State-A moving U
  551. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  552. predict error 0
  553. dir: dir isU
  554. |\75: O: O150 (predict-no)
  555. I see 1 and I'm going to do: predict-no
  556. ENV: Agent did: predict-no for direction U in state State-A
  557. In State-A moving U
  558. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  559. predict error 0
  560. dir: dir isL
  561. -/76: O: O152 (predict-no)
  562. I see 1 and I'm going to do: predict-no
  563. ENV: Agent did: predict-no for direction L in state State-A
  564. In State-A moving L
  565. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  566. predict error 0
  567. dir: dir isR
  568. |\-77: O: O154 (predict-no)
  569. I see 1 and I'm going to do: predict-no
  570. ENV: Agent did: predict-no for direction R in state State-A
  571. In State-A moving R
  572. ENV: (next state, see, prediction correct?) = (State-B, 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-B
  578. In State-B moving L
  579. ENV: (next state, see, prediction correct?) = (State-A, 1, False)
  580. predict error 1
  581. dir: dir isU
  582. -/|79: O: O158 (predict-no)
  583. I see 0 and I'm going to do: predict-no
  584. ENV: Agent did: predict-no for direction U in state State-A
  585. In State-A moving U
  586. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  587. predict error 0
  588. dir: dir isL
  589. \-/80: O: O159 (predict-yes)
  590. I see 1 and I'm going to do: predict-yes
  591. ENV: Agent did: predict-yes for direction L in state State-A
  592. In State-A moving L
  593. ENV: (next state, see, prediction correct?) = (State-A, 0, False)
  594. predict error 1
  595. dir: dir isU
  596. |\-81: O: O162 (predict-no)
  597. I see 0 and I'm going to do: predict-no
  598. ENV: Agent did: predict-no for direction U in state State-A
  599. In State-A moving U
  600. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  601. predict error 0
  602. dir: dir isU
  603. /82: O: O163 (predict-yes)
  604. I see 1 and I'm going to do: predict-yes
  605. ENV: Agent did: predict-yes for direction U in state State-A
  606. In State-A moving U
  607. ENV: (next state, see, prediction correct?) = (State-A, 0, False)
  608. predict error 1
  609. dir: dir isR
  610. |\-83: O: O165 (predict-yes)
  611. I see 0 and I'm going to do: predict-yes
  612. ENV: Agent did: predict-yes for direction R in state State-A
  613. In State-A moving R
  614. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  615. predict error 0
  616. dir: dir isU
  617. /|\84: O: O168 (predict-no)
  618. I see 1 and I'm going to do: predict-no
  619. ENV: Agent did: predict-no for direction U in state State-B
  620. In State-B moving U
  621. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  622. predict error 0
  623. dir: dir isL
  624. -/85: O: O170 (predict-no)
  625. I see 1 and I'm going to do: predict-no
  626. ENV: Agent did: predict-no for direction L in state State-B
  627. In State-B moving L
  628. ENV: (next state, see, prediction correct?) = (State-A, 1, False)
  629. predict error 1
  630. dir: dir isL
  631. |\-86: O: O172 (predict-no)
  632. I see 0 and I'm going to do: predict-no
  633. ENV: Agent did: predict-no for direction L in state State-A
  634. In State-A moving L
  635. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  636. predict error 0
  637. dir: dir isR
  638. /|\87: O: O173 (predict-yes)
  639. I see 1 and I'm going to do: predict-yes
  640. ENV: Agent did: predict-yes for direction R in state State-A
  641. In State-A moving R
  642. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  643. predict error 0
  644. dir: dir isL
  645. -/|88: O: O176 (predict-no)
  646. I see 1 and I'm going to do: predict-no
  647. ENV: Agent did: predict-no for direction L in state State-B
  648. In State-B moving L
  649. ENV: (next state, see, prediction correct?) = (State-A, 1, False)
  650. predict error 1
  651. dir: dir isL
  652. \-/89: O: O178 (predict-no)
  653. I see 0 and I'm going to do: predict-no
  654. ENV: Agent did: predict-no for direction L in state State-A
  655. In State-A moving L
  656. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  657. predict error 0
  658. dir: dir isR
  659. |\-90: O: O179 (predict-yes)
  660. I see 1 and I'm going to do: predict-yes
  661. ENV: Agent did: predict-yes for direction R in state State-A
  662. In State-A moving R
  663. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  664. predict error 0
  665. dir: dir isR
  666. /|91: O: O182 (predict-no)
  667. I see 1 and I'm going to do: predict-no
  668. ENV: Agent did: predict-no for direction R in state State-B
  669. In State-B moving R
  670. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  671. predict error 0
  672. dir: dir isL
  673. rule alias: '*'
  674. rule alias: '*'
  675. \92: O: O184 (predict-no)
  676. I see 1 and I'm going to do: predict-no
  677. ENV: Agent did: predict-no for direction L in state State-B
  678. In State-B moving L
  679. ENV: (next state, see, prediction correct?) = (State-A, 1, False)
  680. predict error 1
  681. dir: dir isL
  682. -/|93: O: O186 (predict-no)
  683. I see 0 and I'm going to do: predict-no
  684. ENV: Agent did: predict-no for direction L in state State-A
  685. In State-A moving L
  686. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  687. predict error 0
  688. dir: dir isU
  689. \-94: O: O188 (predict-no)
  690. I see 1 and I'm going to do: predict-no
  691. ENV: Agent did: predict-no for direction U in state State-A
  692. In State-A moving U
  693. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  694. predict error 0
  695. dir: dir isL
  696. /|95: O: O190 (predict-no)
  697. I see 1 and I'm going to do: predict-no
  698. ENV: Agent did: predict-no for direction L in state State-A
  699. In State-A moving L
  700. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  701. predict error 0
  702. dir: dir isU
  703. \-96: O: O192 (predict-no)
  704. I see 1 and I'm going to do: predict-no
  705. ENV: Agent did: predict-no for direction U in state State-A
  706. In State-A moving U
  707. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  708. predict error 0
  709. dir: dir isU
  710. /|97: O: O194 (predict-no)
  711. I see 1 and I'm going to do: predict-no
  712. ENV: Agent did: predict-no for direction U in state State-A
  713. In State-A moving U
  714. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  715. predict error 0
  716. dir: dir isR
  717. \-98: O: O195 (predict-yes)
  718. I see 1 and I'm going to do: predict-yes
  719. ENV: Agent did: predict-yes for direction R in state State-A
  720. In State-A moving R
  721. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  722. predict error 0
  723. dir: dir isR
  724. /|\99: O: O198 (predict-no)
  725. I see 1 and I'm going to do: predict-no
  726. ENV: Agent did: predict-no for direction R in state State-B
  727. In State-B moving R
  728. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  729. predict error 0
  730. dir: dir isR
  731. -/100: O: O200 (predict-no)
  732. I see 1 and I'm going to do: predict-no
  733. ENV: Agent did: predict-no for direction R in state State-B
  734. In State-B moving R
  735. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  736. predict error 0
  737. dir: dir isR
  738. |\101: O: O202 (predict-no)
  739. I see 1 and I'm going to do: predict-no
  740. ENV: Agent did: predict-no for direction R in state State-B
  741. In State-B moving R
  742. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  743. predict error 0
  744. dir: dir isR
  745. rule alias: '*'
  746. rule alias: '*'
  747. -/102: O: O204 (predict-no)
  748. I see 1 and I'm going to do: predict-no
  749. ENV: Agent did: predict-no for direction R in state State-B
  750. In State-B moving R
  751. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  752. predict error 0
  753. dir: dir isR
  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 R in state State-B
  757. In State-B moving R
  758. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  759. predict error 0
  760. dir: dir isR
  761. /|\104: O: O208 (predict-no)
  762. I see 1 and I'm going to do: predict-no
  763. ENV: Agent did: predict-no for direction R in state State-B
  764. In State-B moving R
  765. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  766. predict error 0
  767. dir: dir isU
  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 U in state State-B
  771. In State-B moving U
  772. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  773. predict error 0
  774. dir: dir isR
  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 R in state State-B
  778. In State-B moving R
  779. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  780. predict error 0
  781. dir: dir isR
  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 R in state State-B
  785. In State-B moving R
  786. ENV: (next state, see, prediction correct?) = (State-B, 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-B
  792. In State-B moving U
  793. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  794. predict error 0
  795. dir: dir isL
  796. -/|109: O: O217 (predict-yes)
  797. I see 1 and I'm going to do: predict-yes
  798. ENV: Agent did: predict-yes for direction L in state State-B
  799. In State-B moving L
  800. ENV: (next state, see, prediction correct?) = (State-A, 1, 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 isR
  817. /112: O: O223 (predict-yes)
  818. I see 1 and I'm going to do: predict-yes
  819. ENV: Agent did: predict-yes for direction R in state State-A
  820. In State-A moving R
  821. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  822. predict error 0
  823. dir: dir isR
  824. |\-113: O: O226 (predict-no)
  825. I see 1 and I'm going to do: predict-no
  826. ENV: Agent did: predict-no for direction R in state State-B
  827. In State-B moving R
  828. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  829. predict error 0
  830. dir: dir isL
  831. /|\114: O: O227 (predict-yes)
  832. I see 1 and I'm going to do: predict-yes
  833. ENV: Agent did: predict-yes for direction L in state State-B
  834. In State-B moving L
  835. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  836. predict error 0
  837. dir: dir isR
  838. -/|115: O: O230 (predict-no)
  839. I see 1 and I'm going to do: predict-no
  840. ENV: Agent did: predict-no for direction R in state State-A
  841. In State-A moving R
  842. ENV: (next state, see, prediction correct?) = (State-B, 1, False)
  843. predict error 1
  844. dir: dir isR
  845. \-/116: O: O232 (predict-no)
  846. I see 0 and I'm going to do: predict-no
  847. ENV: Agent did: predict-no for direction R in state State-B
  848. In State-B moving R
  849. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  850. predict error 0
  851. dir: dir isL
  852. |\117: O: O233 (predict-yes)
  853. I see 1 and I'm going to do: predict-yes
  854. ENV: Agent did: predict-yes for direction L in state State-B
  855. In State-B moving L
  856. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  857. predict error 0
  858. dir: dir isR
  859. -/|118: O: O235 (predict-yes)
  860. I see 1 and I'm going to do: predict-yes
  861. ENV: Agent did: predict-yes for direction R in state State-A
  862. In State-A moving R
  863. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  864. predict error 0
  865. dir: dir isR
  866. \-119: O: O238 (predict-no)
  867. I see 1 and I'm going to do: predict-no
  868. ENV: Agent did: predict-no for direction R in state State-B
  869. In State-B moving R
  870. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  871. predict error 0
  872. dir: dir isL
  873. /|\-120: O: O239 (predict-yes)
  874. I see 1 and I'm going to do: predict-yes
  875. ENV: Agent did: predict-yes for direction L in state State-B
  876. In State-B moving L
  877. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  878. predict error 0
  879. dir: dir isR
  880. /|121: O: O241 (predict-yes)
  881. I see 1 and I'm going to do: predict-yes
  882. ENV: Agent did: predict-yes for direction R in state State-A
  883. In State-A moving R
  884. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  885. predict error 0
  886. dir: dir isR
  887. rule alias: '*'
  888. \122: O: O244 (predict-no)
  889. I see 1 and I'm going to do: predict-no
  890. ENV: Agent did: predict-no for direction R in state State-B
  891. In State-B moving R
  892. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  893. predict error 0
  894. dir: dir isU
  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 U in state State-B
  898. In State-B moving U
  899. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  900. predict error 0
  901. dir: dir isR
  902. \-124: O: O248 (predict-no)
  903. I see 1 and I'm going to do: predict-no
  904. ENV: Agent did: predict-no for direction R in state State-B
  905. In State-B moving R
  906. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  907. predict error 0
  908. dir: dir isU
  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 U in state State-B
  912. In State-B moving U
  913. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  914. predict error 0
  915. dir: dir isU
  916. -/126: O: O252 (predict-no)
  917. I see 1 and I'm going to do: predict-no
  918. ENV: Agent did: predict-no for direction U in state State-B
  919. In State-B moving U
  920. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  921. predict error 0
  922. dir: dir isL
  923. |\-127: O: O253 (predict-yes)
  924. I see 1 and I'm going to do: predict-yes
  925. ENV: Agent did: predict-yes for direction L in state State-B
  926. In State-B moving L
  927. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  928. predict error 0
  929. dir: dir isL
  930. /|128: O: O256 (predict-no)
  931. I see 1 and I'm going to do: predict-no
  932. ENV: Agent did: predict-no for direction L in state State-A
  933. In State-A moving L
  934. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  935. predict error 0
  936. dir: dir isU
  937. \-129: O: O257 (predict-yes)
  938. I see 1 and I'm going to do: predict-yes
  939. ENV: Agent did: predict-yes for direction U in state State-A
  940. In State-A moving U
  941. ENV: (next state, see, prediction correct?) = (State-A, 0, False)
  942. predict error 1
  943. dir: dir isU
  944. /|130: O: O259 (predict-yes)
  945. I see 0 and I'm going to do: predict-yes
  946. ENV: Agent did: predict-yes for direction U in state State-A
  947. In State-A moving U
  948. ENV: (next state, see, prediction correct?) = (State-A, 0, False)
  949. predict error 1
  950. dir: dir isL
  951. \-131: O: O262 (predict-no)
  952. I see 0 and I'm going to do: predict-no
  953. ENV: Agent did: predict-no for direction L in state State-A
  954. In State-A moving L
  955. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  956. predict error 0
  957. dir: dir isR
  958. rule alias: '*'
  959. rule alias: '*'
  960. /132: O: O263 (predict-yes)
  961. I see 1 and I'm going to do: predict-yes
  962. ENV: Agent did: predict-yes for direction R in state State-A
  963. In State-A moving R
  964. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  965. predict error 0
  966. dir: dir isR
  967. |\-133: O: O266 (predict-no)
  968. I see 1 and I'm going to do: predict-no
  969. ENV: Agent did: predict-no for direction R in state State-B
  970. In State-B moving R
  971. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  972. predict error 0
  973. dir: dir isL
  974. /|\-sleeping...
  975. /134: O: O267 (predict-yes)
  976. I see 1 and I'm going to do: predict-yes
  977. ENV: Agent did: predict-yes for direction L in state State-B
  978. In State-B moving L
  979. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  980. predict error 0
  981. dir: dir isR
  982. |\-135: O: O269 (predict-yes)
  983. I see 1 and I'm going to do: predict-yes
  984. ENV: Agent did: predict-yes for direction R in state State-A
  985. In State-A moving R
  986. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  987. predict error 0
  988. dir: dir isL
  989. /|\136: O: O271 (predict-yes)
  990. I see 1 and I'm going to do: predict-yes
  991. ENV: Agent did: predict-yes for direction L in state State-B
  992. In State-B moving L
  993. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  994. predict error 0
  995. dir: dir isR
  996. -/137: O: O273 (predict-yes)
  997. I see 1 and I'm going to do: predict-yes
  998. ENV: Agent did: predict-yes for direction R in state State-A
  999. In State-A moving R
  1000. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  1001. predict error 0
  1002. dir: dir isR
  1003. |\138: O: O276 (predict-no)
  1004. I see 1 and I'm going to do: predict-no
  1005. ENV: Agent did: predict-no for direction R in state State-B
  1006. In State-B moving R
  1007. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  1008. predict error 0
  1009. dir: dir isL
  1010. -/|139: O: O277 (predict-yes)
  1011. I see 1 and I'm going to do: predict-yes
  1012. ENV: Agent did: predict-yes for direction L in state State-B
  1013. In State-B moving L
  1014. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  1015. predict error 0
  1016. dir: dir isR
  1017. \-/140: O: O279 (predict-yes)
  1018. I see 1 and I'm going to do: predict-yes
  1019. ENV: Agent did: predict-yes for direction R in state State-A
  1020. In State-A moving R
  1021. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  1022. predict error 0
  1023. dir: dir isU
  1024. |\141: O: O282 (predict-no)
  1025. I see 1 and I'm going to do: predict-no
  1026. ENV: Agent did: predict-no for direction U in state State-B
  1027. In State-B moving U
  1028. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  1029. predict error 0
  1030. dir: dir isL
  1031. rule alias: '*'
  1032. -142: O: O283 (predict-yes)
  1033. I see 1 and I'm going to do: predict-yes
  1034. ENV: Agent did: predict-yes for direction L in state State-B
  1035. In State-B moving L
  1036. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  1037. predict error 0
  1038. dir: dir isR
  1039. /|\143: O: O285 (predict-yes)
  1040. I see 1 and I'm going to do: predict-yes
  1041. ENV: Agent did: predict-yes for direction R in state State-A
  1042. In State-A moving R
  1043. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  1044. predict error 0
  1045. dir: dir isU
  1046. -/144: O: O288 (predict-no)
  1047. I see 1 and I'm going to do: predict-no
  1048. ENV: Agent did: predict-no for direction U in state State-B
  1049. In State-B moving U
  1050. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  1051. predict error 0
  1052. dir: dir isL
  1053. |\-145: O: O289 (predict-yes)
  1054. I see 1 and I'm going to do: predict-yes
  1055. ENV: Agent did: predict-yes for direction L in state State-B
  1056. In State-B moving L
  1057. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  1058. predict error 0
  1059. dir: dir isL
  1060. /146: O: O292 (predict-no)
  1061. I see 1 and I'm going to do: predict-no
  1062. ENV: Agent did: predict-no for direction L in state State-A
  1063. In State-A moving L
  1064. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  1065. predict error 0
  1066. dir: dir isU
  1067. |147: O: O294 (predict-no)
  1068. I see 1 and I'm going to do: predict-no
  1069. ENV: Agent did: predict-no for direction U in state State-A
  1070. In State-A moving U
  1071. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  1072. predict error 0
  1073. dir: dir isL
  1074. \-/148: O: O296 (predict-no)
  1075. I see 1 and I'm going to do: predict-no
  1076. ENV: Agent did: predict-no for direction L in state State-A
  1077. In State-A moving L
  1078. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  1079. predict error 0
  1080. dir: dir isL
  1081. |\149: O: O298 (predict-no)
  1082. I see 1 and I'm going to do: predict-no
  1083. ENV: Agent did: predict-no for direction L in state State-A
  1084. In State-A moving L
  1085. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  1086. predict error 0
  1087. dir: dir isR
  1088. -/150: O: O299 (predict-yes)
  1089. I see 1 and I'm going to do: predict-yes
  1090. ENV: Agent did: predict-yes for direction R in state State-A
  1091. In State-A moving R
  1092. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  1093. predict error 0
  1094. dir: dir isU
  1095. |\-151: O: O302 (predict-no)
  1096. I see 1 and I'm going to do: predict-no
  1097. ENV: Agent did: predict-no for direction U in state State-B
  1098. In State-B moving U
  1099. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  1100. predict error 0
  1101. dir: dir isL
  1102. /152: O: O303 (predict-yes)
  1103. I see 1 and I'm going to do: predict-yes
  1104. ENV: Agent did: predict-yes for direction L in state State-B
  1105. In State-B moving L
  1106. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  1107. predict error 0
  1108. dir: dir isL
  1109. |\153: O: O306 (predict-no)
  1110. I see 1 and I'm going to do: predict-no
  1111. ENV: Agent did: predict-no for direction L in state State-A
  1112. In State-A moving L
  1113. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  1114. predict error 0
  1115. dir: dir isR
  1116. -/|154: O: O307 (predict-yes)
  1117. I see 1 and I'm going to do: predict-yes
  1118. ENV: Agent did: predict-yes for direction R in state State-A
  1119. In State-A moving R
  1120. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  1121. predict error 0
  1122. dir: dir isU
  1123. \-/155: O: O310 (predict-no)
  1124. I see 1 and I'm going to do: predict-no
  1125. ENV: Agent did: predict-no for direction U in state State-B
  1126. In State-B moving U
  1127. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  1128. predict error 0
  1129. dir: dir isR
  1130. |\156: O: O312 (predict-no)
  1131. I see 1 and I'm going to do: predict-no
  1132. ENV: Agent did: predict-no for direction R in state State-B
  1133. In State-B moving R
  1134. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  1135. predict error 0
  1136. dir: dir isU
  1137. -/|157: O: O314 (predict-no)
  1138. I see 1 and I'm going to do: predict-no
  1139. ENV: Agent did: predict-no for direction U in state State-B
  1140. In State-B moving U
  1141. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  1142. predict error 0
  1143. dir: dir isL
  1144. \-/158: O: O315 (predict-yes)
  1145. I see 1 and I'm going to do: predict-yes
  1146. ENV: Agent did: predict-yes for direction L in state State-B
  1147. In State-B moving L
  1148. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  1149. predict error 0
  1150. dir: dir isR
  1151. |\-159: O: O317 (predict-yes)
  1152. I see 1 and I'm going to do: predict-yes
  1153. ENV: Agent did: predict-yes for direction R in state State-A
  1154. In State-A moving R
  1155. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  1156. predict error 0
  1157. dir: dir isR
  1158. /|\160: O: O320 (predict-no)
  1159. I see 1 and I'm going to do: predict-no
  1160. ENV: Agent did: predict-no for direction R in state State-B
  1161. In State-B moving R
  1162. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  1163. predict error 0
  1164. dir: dir isU
  1165. -/161: O: O322 (predict-no)
  1166. I see 1 and I'm going to do: predict-no
  1167. ENV: Agent did: predict-no for direction U in state State-B
  1168. In State-B moving U
  1169. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  1170. predict error 0
  1171. dir: dir isR
  1172. |162: O: O324 (predict-no)
  1173. I see 1 and I'm going to do: predict-no
  1174. ENV: Agent did: predict-no for direction R in state State-B
  1175. In State-B moving R
  1176. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  1177. predict error 0
  1178. dir: dir isL
  1179. \-163: O: O325 (predict-yes)
  1180. I see 1 and I'm going to do: predict-yes
  1181. ENV: Agent did: predict-yes for direction L in state State-B
  1182. In State-B moving L
  1183. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  1184. predict error 0
  1185. dir: dir isL
  1186. /|164: O: O328 (predict-no)
  1187. I see 1 and I'm going to do: predict-no
  1188. ENV: Agent did: predict-no for direction L in state State-A
  1189. In State-A moving L
  1190. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  1191. predict error 0
  1192. dir: dir isR
  1193. \-/165: O: O329 (predict-yes)
  1194. I see 1 and I'm going to do: predict-yes
  1195. ENV: Agent did: predict-yes for direction R in state State-A
  1196. In State-A moving R
  1197. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  1198. predict error 0
  1199. dir: dir isL
  1200. |\-/166: O: O331 (predict-yes)
  1201. I see 1 and I'm going to do: predict-yes
  1202. ENV: Agent did: predict-yes for direction L in state State-B
  1203. In State-B moving L
  1204. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  1205. predict error 0
  1206. dir: dir isU
  1207. |\-167: O: O334 (predict-no)
  1208. I see 1 and I'm going to do: predict-no
  1209. ENV: Agent did: predict-no for direction U in state State-A
  1210. In State-A moving U
  1211. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  1212. predict error 0
  1213. dir: dir isU
  1214. /|\168: O: O336 (predict-no)
  1215. I see 1 and I'm going to do: predict-no
  1216. ENV: Agent did: predict-no for direction U in state State-A
  1217. In State-A moving U
  1218. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  1219. predict error 0
  1220. dir: dir isL
  1221. -/|169: O: O338 (predict-no)
  1222. I see 1 and I'm going to do: predict-no
  1223. ENV: Agent did: predict-no for direction L in state State-A
  1224. In State-A moving L
  1225. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  1226. predict error 0
  1227. dir: dir isL
  1228. \-/170: O: O340 (predict-no)
  1229. I see 1 and I'm going to do: predict-no
  1230. ENV: Agent did: predict-no for direction L in state State-A
  1231. In State-A moving L
  1232. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  1233. predict error 0
  1234. dir: dir isU
  1235. |\-171: O: O342 (predict-no)
  1236. I see 1 and I'm going to do: predict-no
  1237. ENV: Agent did: predict-no for direction U in state State-A
  1238. In State-A moving U
  1239. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  1240. predict error 0
  1241. dir: dir isR
  1242. /172: O: O343 (predict-yes)
  1243. I see 1 and I'm going to do: predict-yes
  1244. ENV: Agent did: predict-yes for direction R in state State-A
  1245. In State-A moving R
  1246. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  1247. predict error 0
  1248. dir: dir isU
  1249. |\-173: O: O346 (predict-no)
  1250. I see 1 and I'm going to do: predict-no
  1251. ENV: Agent did: predict-no for direction U in state State-B
  1252. In State-B moving U
  1253. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  1254. predict error 0
  1255. dir: dir isR
  1256. /|\174: O: O347 (predict-yes)
  1257. I see 1 and I'm going to do: predict-yes
  1258. ENV: Agent did: predict-yes for direction R in state State-B
  1259. In State-B moving R
  1260. ENV: (next state, see, prediction correct?) = (State-B, 0, False)
  1261. predict error 1
  1262. dir: dir isL
  1263. -/|175: O: O349 (predict-yes)
  1264. I see 0 and I'm going to do: predict-yes
  1265. ENV: Agent did: predict-yes for direction L in state State-B
  1266. In State-B moving L
  1267. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  1268. predict error 0
  1269. dir: dir isL
  1270. \-/176: O: O352 (predict-no)
  1271. I see 1 and I'm going to do: predict-no
  1272. ENV: Agent did: predict-no for direction L in state State-A
  1273. In State-A moving L
  1274. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  1275. predict error 0
  1276. dir: dir isU
  1277. |\177: O: O354 (predict-no)
  1278. I see 1 and I'm going to do: predict-no
  1279. ENV: Agent did: predict-no for direction U in state State-A
  1280. In State-A moving U
  1281. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  1282. predict error 0
  1283. dir: dir isL
  1284. -/|\178: O: O356 (predict-no)
  1285. I see 1 and I'm going to do: predict-no
  1286. ENV: Agent did: predict-no for direction L in state State-A
  1287. In State-A moving L
  1288. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  1289. predict error 0
  1290. dir: dir isR
  1291. -/179: O: O357 (predict-yes)
  1292. I see 1 and I'm going to do: predict-yes
  1293. ENV: Agent did: predict-yes for direction R in state State-A
  1294. In State-A moving R
  1295. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  1296. predict error 0
  1297. dir: dir isR
  1298. |\-180: O: O360 (predict-no)
  1299. I see 1 and I'm going to do: predict-no
  1300. ENV: Agent did: predict-no for direction R in state State-B
  1301. In State-B moving R
  1302. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  1303. predict error 0
  1304. dir: dir isR
  1305. /181: O: O362 (predict-no)
  1306. I see 1 and I'm going to do: predict-no
  1307. ENV: Agent did: predict-no for direction R in state State-B
  1308. In State-B moving R
  1309. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  1310. predict error 0
  1311. dir: dir isR
  1312. |182: O: O364 (predict-no)
  1313. I see 1 and I'm going to do: predict-no
  1314. ENV: Agent did: predict-no for direction R in state State-B
  1315. In State-B moving R
  1316. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  1317. predict error 0
  1318. dir: dir isU
  1319. \-/183: O: O366 (predict-no)
  1320. I see 1 and I'm going to do: predict-no
  1321. ENV: Agent did: predict-no for direction U in state State-B
  1322. In State-B moving U
  1323. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  1324. predict error 0
  1325. dir: dir isL
  1326. |\-184: O: O367 (predict-yes)
  1327. I see 1 and I'm going to do: predict-yes
  1328. ENV: Agent did: predict-yes for direction L in state State-B
  1329. In State-B moving L
  1330. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  1331. predict error 0
  1332. dir: dir isL
  1333. /|185: O: O370 (predict-no)
  1334. I see 1 and I'm going to do: predict-no
  1335. ENV: Agent did: predict-no for direction L in state State-A
  1336. In State-A moving L
  1337. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  1338. predict error 0
  1339. dir: dir isU
  1340. \-/186: O: O372 (predict-no)
  1341. I see 1 and I'm going to do: predict-no
  1342. ENV: Agent did: predict-no for direction U in state State-A
  1343. In State-A moving U
  1344. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  1345. predict error 0
  1346. dir: dir isU
  1347. |\187: O: O374 (predict-no)
  1348. I see 1 and I'm going to do: predict-no
  1349. ENV: Agent did: predict-no for direction U in state State-A
  1350. In State-A moving U
  1351. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  1352. predict error 0
  1353. dir: dir isU
  1354. -/|188: O: O375 (predict-yes)
  1355. I see 1 and I'm going to do: predict-yes
  1356. ENV: Agent did: predict-yes for direction U in state State-A
  1357. In State-A moving U
  1358. ENV: (next state, see, prediction correct?) = (State-A, 0, False)
  1359. predict error 1
  1360. dir: dir isR
  1361. \-189: O: O377 (predict-yes)
  1362. I see 0 and I'm going to do: predict-yes
  1363. ENV: Agent did: predict-yes for direction R in state State-A
  1364. In State-A moving R
  1365. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  1366. predict error 0
  1367. dir: dir isU
  1368. /|190: O: O380 (predict-no)
  1369. I see 1 and I'm going to do: predict-no
  1370. ENV: Agent did: predict-no for direction U in state State-B
  1371. In State-B moving U
  1372. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  1373. predict error 0
  1374. dir: dir isU
  1375. \-/191: O: O382 (predict-no)
  1376. I see 1 and I'm going to do: predict-no
  1377. ENV: Agent did: predict-no for direction U in state State-B
  1378. In State-B moving U
  1379. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  1380. predict error 0
  1381. dir: dir isL
  1382. |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 isU
  1389. \-/193: O: O386 (predict-no)
  1390. I see 1 and I'm going to do: predict-no
  1391. ENV: Agent did: predict-no for direction U in state State-A
  1392. In State-A moving U
  1393. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  1394. predict error 0
  1395. dir: dir isU
  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 U in state State-A
  1399. In State-A moving U
  1400. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  1401. predict error 0
  1402. dir: dir isR
  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 R in state State-A
  1406. In State-A moving R
  1407. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  1408. predict error 0
  1409. dir: dir isR
  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 R in state State-B
  1413. In State-B moving R
  1414. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  1415. predict error 0
  1416. dir: dir isL
  1417. /|\197: O: O393 (predict-yes)
  1418. I see 1 and I'm going to do: predict-yes
  1419. ENV: Agent did: predict-yes for direction L in state State-B
  1420. In State-B moving L
  1421. ENV: (next state, see, prediction correct?) = (State-A, 1, 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 isL
  1431. \-199: O: O397 (predict-yes)
  1432. I see 1 and I'm going to do: predict-yes
  1433. ENV: Agent did: predict-yes for direction L in state State-B
  1434. In State-B moving L
  1435. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  1436. predict error 0
  1437. dir: dir isL
  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 L in state State-A
  1441. In State-A moving L
  1442. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  1443. predict error 0
  1444. dir: dir isR
  1445. -/|201: O: O401 (predict-yes)
  1446. I see 1 and I'm going to do: predict-yes
  1447. ENV: Agent did: predict-yes for direction R in state State-A
  1448. In State-A moving R
  1449. ENV: (next state, see, prediction correct?) = (State-B, 1, 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 isL
  1466. \-/204: O: O408 (predict-no)
  1467. I see 1 and I'm going to do: predict-no
  1468. ENV: Agent did: predict-no for direction L in state State-A
  1469. In State-A moving L
  1470. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  1471. predict error 0
  1472. dir: dir isU
  1473. |\-205: O: O410 (predict-no)
  1474. I see 1 and I'm going to do: predict-no
  1475. ENV: Agent did: predict-no for direction U in state State-A
  1476. In State-A moving U
  1477. ENV: (next state, see, prediction correct?) = (State-A, 0, 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 isU
  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 U in state State-A
  1490. In State-A moving U
  1491. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  1492. predict error 0
  1493. dir: dir isU
  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 U in state State-A
  1497. In State-A moving U
  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 isR
  1508. \-/210: O: O419 (predict-yes)
  1509. I see 1 and I'm going to do: predict-yes
  1510. ENV: Agent did: predict-yes for direction R in state State-A
  1511. In State-A moving R
  1512. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  1513. predict error 0
  1514. dir: dir isL
  1515. |\-211: O: O421 (predict-yes)
  1516. I see 1 and I'm going to do: predict-yes
  1517. ENV: Agent did: predict-yes for direction L in state State-B
  1518. In State-B moving L
  1519. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  1520. predict error 0
  1521. dir: dir isU
  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 U in state State-A
  1525. In State-A moving U
  1526. ENV: (next state, see, prediction correct?) = (State-A, 0, False)
  1527. predict error 1
  1528. dir: dir isL
  1529. |\213: O: O425 (predict-yes)
  1530. I see 0 and I'm going to do: predict-yes
  1531. ENV: Agent did: predict-yes for direction L in state State-A
  1532. In State-A moving L
  1533. ENV: (next state, see, prediction correct?) = (State-A, 0, False)
  1534. predict error 1
  1535. dir: dir isL
  1536. -/|214: O: O428 (predict-no)
  1537. I see 0 and I'm going to do: predict-no
  1538. ENV: Agent did: predict-no for direction L in state State-A
  1539. In State-A moving L
  1540. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  1541. predict error 0
  1542. dir: dir isR
  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 R in state State-A
  1546. In State-A moving R
  1547. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  1548. predict error 0
  1549. dir: dir isR
  1550. |\-/216: O: O432 (predict-no)
  1551. I see 1 and I'm going to do: predict-no
  1552. ENV: Agent did: predict-no for direction R in state State-B
  1553. In State-B moving R
  1554. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  1555. predict error 0
  1556. dir: dir isR
  1557. |\217: O: O434 (predict-no)
  1558. I see 1 and I'm going to do: predict-no
  1559. ENV: Agent did: predict-no for direction R in state State-B
  1560. In State-B moving R
  1561. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  1562. predict error 0
  1563. dir: dir isU
  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 U in state State-B
  1567. In State-B moving U
  1568. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  1569. predict error 0
  1570. dir: dir isR
  1571. |\-219: O: O438 (predict-no)
  1572. I see 1 and I'm going to do: predict-no
  1573. ENV: Agent did: predict-no for direction R in state State-B
  1574. In State-B moving R
  1575. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  1576. predict error 0
  1577. dir: dir isR
  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 R in state State-B
  1581. In State-B moving R
  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 isR
  1599. /|\223: O: O445 (predict-yes)
  1600. I see 1 and I'm going to do: predict-yes
  1601. ENV: Agent did: predict-yes for direction R in state State-A
  1602. In State-A moving R
  1603. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  1604. predict error 0
  1605. dir: dir isU
  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 U in state State-B
  1609. In State-B moving U
  1610. ENV: (next state, see, prediction correct?) = (State-B, 0, False)
  1611. predict error 1
  1612. dir: dir isR
  1613. \-/225: O: O450 (predict-no)
  1614. I see 0 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 isL
  1620. |\-/226: O: O451 (predict-yes)
  1621. I see 1 and I'm going to do: predict-yes
  1622. ENV: Agent did: predict-yes for direction L in state State-B
  1623. In State-B moving L
  1624. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  1625. predict error 0
  1626. dir: dir isR
  1627. |\-/sleeping...
  1628. |227: O: O453 (predict-yes)
  1629. I see 1 and I'm going to do: predict-yes
  1630. ENV: Agent did: predict-yes for direction R in state State-A
  1631. In State-A moving R
  1632. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  1633. predict error 0
  1634. dir: dir isU
  1635. \-/228: O: O456 (predict-no)
  1636. I see 1 and I'm going to do: predict-no
  1637. ENV: Agent did: predict-no for direction U in state State-B
  1638. In State-B moving U
  1639. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  1640. predict error 0
  1641. dir: dir isL
  1642. |\-229: O: O457 (predict-yes)
  1643. I see 1 and I'm going to do: predict-yes
  1644. ENV: Agent did: predict-yes for direction L in state State-B
  1645. In State-B moving L
  1646. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  1647. predict error 0
  1648. dir: dir isU
  1649. /|230: O: O459 (predict-yes)
  1650. I see 1 and I'm going to do: predict-yes
  1651. ENV: Agent did: predict-yes for direction U in state State-A
  1652. In State-A moving U
  1653. ENV: (next state, see, prediction correct?) = (State-A, 0, False)
  1654. predict error 1
  1655. dir: dir isU
  1656. \231: O: O462 (predict-no)
  1657. I see 0 and I'm going to do: predict-no
  1658. ENV: Agent did: predict-no for direction U in state State-A
  1659. In State-A moving U
  1660. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  1661. predict error 0
  1662. dir: dir isU
  1663. -232: O: O464 (predict-no)
  1664. I see 1 and I'm going to do: predict-no
  1665. ENV: Agent did: predict-no for direction U in state State-A
  1666. In State-A moving U
  1667. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  1668. predict error 0
  1669. dir: dir isU
  1670. /|233: O: O466 (predict-no)
  1671. I see 1 and I'm going to do: predict-no
  1672. ENV: Agent did: predict-no for direction U in state State-A
  1673. In State-A moving U
  1674. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  1675. predict error 0
  1676. dir: dir isL
  1677. \-/|234: O: O468 (predict-no)
  1678. I see 1 and I'm going to do: predict-no
  1679. ENV: Agent did: predict-no for direction L in state State-A
  1680. In State-A moving L
  1681. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  1682. predict error 0
  1683. dir: dir isR
  1684. \-/235: O: O469 (predict-yes)
  1685. I see 1 and I'm going to do: predict-yes
  1686. ENV: Agent did: predict-yes for direction R in state State-A
  1687. In State-A moving R
  1688. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  1689. predict error 0
  1690. dir: dir isU
  1691. |\-236: O: O472 (predict-no)
  1692. I see 1 and I'm going to do: predict-no
  1693. ENV: Agent did: predict-no for direction U in state State-B
  1694. In State-B moving U
  1695. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  1696. predict error 0
  1697. dir: dir isL
  1698. /|237: O: O474 (predict-no)
  1699. I see 1 and I'm going to do: predict-no
  1700. ENV: Agent did: predict-no for direction L in state State-B
  1701. In State-B moving L
  1702. ENV: (next state, see, prediction correct?) = (State-A, 1, False)
  1703. predict error 1
  1704. dir: dir isL
  1705. \-/238: O: O476 (predict-no)
  1706. I see 0 and I'm going to do: predict-no
  1707. ENV: Agent did: predict-no for direction L in state State-A
  1708. In State-A moving L
  1709. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  1710. predict error 0
  1711. dir: dir isL
  1712. |\-239: O: O478 (predict-no)
  1713. I see 1 and I'm going to do: predict-no
  1714. ENV: Agent did: predict-no for direction L in state State-A
  1715. In State-A moving L
  1716. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  1717. predict error 0
  1718. dir: dir isR
  1719. /|\240: O: O479 (predict-yes)
  1720. I see 1 and I'm going to do: predict-yes
  1721. ENV: Agent did: predict-yes for direction R in state State-A
  1722. In State-A moving R
  1723. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  1724. predict error 0
  1725. dir: dir isR
  1726. -/|241: O: O482 (predict-no)
  1727. I see 1 and I'm going to do: predict-no
  1728. ENV: Agent did: predict-no for direction R in state State-B
  1729. In State-B moving R
  1730. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  1731. predict error 0
  1732. dir: dir isR
  1733. \242: O: O484 (predict-no)
  1734. I see 1 and I'm going to do: predict-no
  1735. ENV: Agent did: predict-no for direction R in state State-B
  1736. In State-B moving R
  1737. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  1738. predict error 0
  1739. dir: dir isU
  1740. -/|243: O: O486 (predict-no)
  1741. I see 1 and I'm going to do: predict-no
  1742. ENV: Agent did: predict-no for direction U in state State-B
  1743. In State-B moving U
  1744. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  1745. predict error 0
  1746. dir: dir isL
  1747. \-244: O: O487 (predict-yes)
  1748. I see 1 and I'm going to do: predict-yes
  1749. ENV: Agent did: predict-yes for direction L in state State-B
  1750. In State-B moving L
  1751. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  1752. predict error 0
  1753. dir: dir isL
  1754. /|245: O: O490 (predict-no)
  1755. I see 1 and I'm going to do: predict-no
  1756. ENV: Agent did: predict-no for direction L in state State-A
  1757. In State-A moving L
  1758. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  1759. predict error 0
  1760. dir: dir isL
  1761. \-246: O: O492 (predict-no)
  1762. I see 1 and I'm going to do: predict-no
  1763. ENV: Agent did: predict-no for direction L in state State-A
  1764. In State-A moving L
  1765. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  1766. predict error 0
  1767. dir: dir isL
  1768. /|\-247: O: O494 (predict-no)
  1769. I see 1 and I'm going to do: predict-no
  1770. ENV: Agent did: predict-no for direction L in state State-A
  1771. In State-A moving L
  1772. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  1773. predict error 0
  1774. dir: dir isL
  1775. /|\248: O: O496 (predict-no)
  1776. I see 1 and I'm going to do: predict-no
  1777. ENV: Agent did: predict-no for direction L in state State-A
  1778. In State-A moving L
  1779. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  1780. predict error 0
  1781. dir: dir isU
  1782. -/|249: O: O498 (predict-no)
  1783. I see 1 and I'm going to do: predict-no
  1784. ENV: Agent did: predict-no for direction U in state State-A
  1785. In State-A moving U
  1786. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  1787. predict error 0
  1788. dir: dir isU
  1789. \-/250: O: O500 (predict-no)
  1790. I see 1 and I'm going to do: predict-no
  1791. ENV: Agent did: predict-no for direction U in state State-A
  1792. In State-A moving U
  1793. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  1794. predict error 0
  1795. dir: dir isL
  1796. |\-251: O: O502 (predict-no)
  1797. I see 1 and I'm going to do: predict-no
  1798. ENV: Agent did: predict-no for direction L in state State-A
  1799. In State-A moving L
  1800. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  1801. predict error 0
  1802. dir: dir isR
  1803. /252: O: O503 (predict-yes)
  1804. I see 1 and I'm going to do: predict-yes
  1805. ENV: Agent did: predict-yes for direction R in state State-A
  1806. In State-A moving R
  1807. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  1808. predict error 0
  1809. dir: dir isL
  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 L in state State-B
  1813. In State-B moving L
  1814. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  1815. predict error 0
  1816. dir: dir isL
  1817. /|254: O: O508 (predict-no)
  1818. I see 1 and I'm going to do: predict-no
  1819. ENV: Agent did: predict-no for direction L in state State-A
  1820. In State-A moving L
  1821. ENV: (next state, see, prediction correct?) = (State-A, 0, 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 isR
  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 R in state State-B
  1834. In State-B moving R
  1835. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  1836. predict error 0
  1837. dir: dir isR
  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 R in state State-B
  1841. In State-B moving R
  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 isL
  1852. |\-259: O: O517 (predict-yes)
  1853. I see 1 and I'm going to do: predict-yes
  1854. ENV: Agent did: predict-yes for direction L in state State-B
  1855. In State-B moving L
  1856. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  1857. predict error 0
  1858. dir: dir isL
  1859. /|260: O: O520 (predict-no)
  1860. I see 1 and I'm going to do: predict-no
  1861. ENV: Agent did: predict-no for direction L in state State-A
  1862. In State-A moving L
  1863. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  1864. predict error 0
  1865. dir: dir isL
  1866. \-/261: O: O522 (predict-no)
  1867. I see 1 and I'm going to do: predict-no
  1868. ENV: Agent did: predict-no for direction L in state State-A
  1869. In State-A moving L
  1870. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  1871. predict error 0
  1872. dir: dir isR
  1873. |262: O: O523 (predict-yes)
  1874. I see 1 and I'm going to do: predict-yes
  1875. ENV: Agent did: predict-yes for direction R in state State-A
  1876. In State-A moving R
  1877. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  1878. predict error 0
  1879. dir: dir isU
  1880. \-/263: O: O526 (predict-no)
  1881. I see 1 and I'm going to do: predict-no
  1882. ENV: Agent did: predict-no for direction U in state State-B
  1883. In State-B moving U
  1884. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  1885. predict error 0
  1886. dir: dir isR
  1887. |\-264: O: O528 (predict-no)
  1888. I see 1 and I'm going to do: predict-no
  1889. ENV: Agent did: predict-no for direction R in state State-B
  1890. In State-B moving R
  1891. ENV: (next state, see, prediction correct?) = (State-B, 0, 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 isR
  1908. |\267: O: O533 (predict-yes)
  1909. I see 1 and I'm going to do: predict-yes
  1910. ENV: Agent did: predict-yes for direction R in state State-A
  1911. In State-A moving R
  1912. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  1913. predict error 0
  1914. dir: dir isR
  1915. -/268: O: O536 (predict-no)
  1916. I see 1 and I'm going to do: predict-no
  1917. ENV: Agent did: predict-no for direction R in state State-B
  1918. In State-B moving R
  1919. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  1920. predict error 0
  1921. dir: dir isU
  1922. |\269: O: O538 (predict-no)
  1923. I see 1 and I'm going to do: predict-no
  1924. ENV: Agent did: predict-no for direction U in state State-B
  1925. In State-B moving U
  1926. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  1927. predict error 0
  1928. dir: dir isR
  1929. -/|270: O: O540 (predict-no)
  1930. I see 1 and I'm going to do: predict-no
  1931. ENV: Agent did: predict-no for direction R in state State-B
  1932. In State-B moving R
  1933. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  1934. predict error 0
  1935. dir: dir isU
  1936. \-/271: O: O542 (predict-no)
  1937. I see 1 and I'm going to do: predict-no
  1938. ENV: Agent did: predict-no for direction U in state State-B
  1939. In State-B moving U
  1940. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  1941. predict error 0
  1942. dir: dir isR
  1943. |272: O: O544 (predict-no)
  1944. I see 1 and I'm going to do: predict-no
  1945. ENV: Agent did: predict-no for direction R in state State-B
  1946. In State-B moving R
  1947. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  1948. predict error 0
  1949. dir: dir isR
  1950. \-/273: O: O546 (predict-no)
  1951. I see 1 and I'm going to do: predict-no
  1952. ENV: Agent did: predict-no for direction R in state State-B
  1953. In State-B moving R
  1954. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  1955. predict error 0
  1956. dir: dir isR
  1957. |\-274: O: O548 (predict-no)
  1958. I see 1 and I'm going to do: predict-no
  1959. ENV: Agent did: predict-no for direction R in state State-B
  1960. In State-B moving R
  1961. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  1962. predict error 0
  1963. dir: dir isR
  1964. /|275: O: O550 (predict-no)
  1965. I see 1 and I'm going to do: predict-no
  1966. ENV: Agent did: predict-no for direction R in state State-B
  1967. In State-B moving R
  1968. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  1969. predict error 0
  1970. dir: dir isU
  1971. \-/276: O: O552 (predict-no)
  1972. I see 1 and I'm going to do: predict-no
  1973. ENV: Agent did: predict-no for direction U in state State-B
  1974. In State-B moving U
  1975. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  1976. predict error 0
  1977. dir: dir isR
  1978. |\-/277: O: O554 (predict-no)
  1979. I see 1 and I'm going to do: predict-no
  1980. ENV: Agent did: predict-no for direction R in state State-B
  1981. In State-B moving R
  1982. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  1983. predict error 0
  1984. dir: dir isU
  1985. |\-278: O: O556 (predict-no)
  1986. I see 1 and I'm going to do: predict-no
  1987. ENV: Agent did: predict-no for direction U in state State-B
  1988. In State-B moving U
  1989. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  1990. predict error 0
  1991. dir: dir isR
  1992. /|\279: O: O558 (predict-no)
  1993. I see 1 and I'm going to do: predict-no
  1994. ENV: Agent did: predict-no for direction R in state State-B
  1995. In State-B moving R
  1996. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  1997. predict error 0
  1998. dir: dir isL
  1999. -/280: O: O560 (predict-no)
  2000. I see 1 and I'm going to do: predict-no
  2001. ENV: Agent did: predict-no for direction L in state State-B
  2002. In State-B moving L
  2003. ENV: (next state, see, prediction correct?) = (State-A, 1, False)
  2004. predict error 1
  2005. dir: dir isR
  2006. |\281: O: O561 (predict-yes)
  2007. I see 0 and I'm going to do: predict-yes
  2008. ENV: Agent did: predict-yes for direction R in state State-A
  2009. In State-A moving R
  2010. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  2011. predict error 0
  2012. dir: dir isU
  2013. -282: O: O564 (predict-no)
  2014. I see 1 and I'm going to do: predict-no
  2015. ENV: Agent did: predict-no for direction U in state State-B
  2016. In State-B moving U
  2017. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2018. predict error 0
  2019. dir: dir isL
  2020. /|\283: O: O565 (predict-yes)
  2021. I see 1 and I'm going to do: predict-yes
  2022. ENV: Agent did: predict-yes for direction L in state State-B
  2023. In State-B moving L
  2024. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  2025. predict error 0
  2026. dir: dir isR
  2027. -/284: O: O567 (predict-yes)
  2028. I see 1 and I'm going to do: predict-yes
  2029. ENV: Agent did: predict-yes for direction R in state State-A
  2030. In State-A moving R
  2031. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  2032. predict error 0
  2033. dir: dir isR
  2034. |\285: O: O570 (predict-no)
  2035. I see 1 and I'm going to do: predict-no
  2036. ENV: Agent did: predict-no for direction R in state State-B
  2037. In State-B moving R
  2038. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2039. predict error 0
  2040. dir: dir isU
  2041. -/|286: O: O572 (predict-no)
  2042. I see 1 and I'm going to do: predict-no
  2043. ENV: Agent did: predict-no for direction U in state State-B
  2044. In State-B moving U
  2045. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2046. predict error 0
  2047. dir: dir isU
  2048. \-/287: O: O574 (predict-no)
  2049. I see 1 and I'm going to do: predict-no
  2050. ENV: Agent did: predict-no for direction U in state State-B
  2051. In State-B moving U
  2052. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2053. predict error 0
  2054. dir: dir isR
  2055. |\288: O: O576 (predict-no)
  2056. I see 1 and I'm going to do: predict-no
  2057. ENV: Agent did: predict-no for direction R in state State-B
  2058. In State-B moving R
  2059. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2060. predict error 0
  2061. dir: dir isU
  2062. -/289: O: O578 (predict-no)
  2063. I see 1 and I'm going to do: predict-no
  2064. ENV: Agent did: predict-no for direction U in state State-B
  2065. In State-B moving U
  2066. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2067. predict error 0
  2068. dir: dir isU
  2069. |\290: O: O580 (predict-no)
  2070. I see 1 and I'm going to do: predict-no
  2071. ENV: Agent did: predict-no for direction U in state State-B
  2072. In State-B moving U
  2073. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2074. predict error 0
  2075. dir: dir isL
  2076. -/|291: O: O581 (predict-yes)
  2077. I see 1 and I'm going to do: predict-yes
  2078. ENV: Agent did: predict-yes for direction L in state State-B
  2079. In State-B moving L
  2080. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  2081. predict error 0
  2082. dir: dir isR
  2083. \292: O: O583 (predict-yes)
  2084. I see 1 and I'm going to do: predict-yes
  2085. ENV: Agent did: predict-yes for direction R in state State-A
  2086. In State-A moving R
  2087. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  2088. predict error 0
  2089. dir: dir isL
  2090. -/|293: O: O585 (predict-yes)
  2091. I see 1 and I'm going to do: predict-yes
  2092. ENV: Agent did: predict-yes for direction L in state State-B
  2093. In State-B moving L
  2094. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  2095. predict error 0
  2096. dir: dir isU
  2097. \-/|294: O: O588 (predict-no)
  2098. I see 1 and I'm going to do: predict-no
  2099. ENV: Agent did: predict-no for direction U in state State-A
  2100. In State-A moving U
  2101. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  2102. predict error 0
  2103. dir: dir isR
  2104. \-/295: O: O589 (predict-yes)
  2105. I see 1 and I'm going to do: predict-yes
  2106. ENV: Agent did: predict-yes for direction R in state State-A
  2107. In State-A moving R
  2108. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  2109. predict error 0
  2110. dir: dir isU
  2111. |296: O: O591 (predict-yes)
  2112. I see 1 and I'm going to do: predict-yes
  2113. ENV: Agent did: predict-yes for direction U in state State-B
  2114. In State-B moving U
  2115. ENV: (next state, see, prediction correct?) = (State-B, 0, False)
  2116. predict error 1
  2117. dir: dir isU
  2118. \297: O: O594 (predict-no)
  2119. I see 0 and I'm going to do: predict-no
  2120. ENV: Agent did: predict-no for direction U in state State-B
  2121. In State-B moving U
  2122. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2123. predict error 0
  2124. dir: dir isU
  2125. -/|298: O: O596 (predict-no)
  2126. I see 1 and I'm going to do: predict-no
  2127. ENV: Agent did: predict-no for direction U in state State-B
  2128. In State-B moving U
  2129. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2130. predict error 0
  2131. dir: dir isU
  2132. \-/299: O: O598 (predict-no)
  2133. I see 1 and I'm going to do: predict-no
  2134. ENV: Agent did: predict-no for direction U in state State-B
  2135. In State-B moving U
  2136. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2137. predict error 0
  2138. dir: dir isR
  2139. |\-300: O: O600 (predict-no)
  2140. I see 1 and I'm going to do: predict-no
  2141. ENV: Agent did: predict-no for direction R in state State-B
  2142. In State-B moving R
  2143. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2144. predict error 0
  2145. dir: dir isL
  2146. /|\-/301: O: O601 (predict-yes)
  2147. I see 1 and I'm going to do: predict-yes
  2148. ENV: Agent did: predict-yes for direction L in state State-B
  2149. In State-B moving L
  2150. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  2151. predict error 0
  2152. dir: dir isR
  2153. |302: O: O603 (predict-yes)
  2154. I see 1 and I'm going to do: predict-yes
  2155. ENV: Agent did: predict-yes for direction R in state State-A
  2156. In State-A moving R
  2157. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  2158. predict error 0
  2159. dir: dir isL
  2160. \-/303: O: O605 (predict-yes)
  2161. I see 1 and I'm going to do: predict-yes
  2162. ENV: Agent did: predict-yes for direction L in state State-B
  2163. In State-B moving L
  2164. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  2165. predict error 0
  2166. dir: dir isL
  2167. |\304: O: O608 (predict-no)
  2168. I see 1 and I'm going to do: predict-no
  2169. ENV: Agent did: predict-no for direction L in state State-A
  2170. In State-A moving L
  2171. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  2172. predict error 0
  2173. dir: dir isU
  2174. -/|305: O: O610 (predict-no)
  2175. I see 1 and I'm going to do: predict-no
  2176. ENV: Agent did: predict-no for direction U in state State-A
  2177. In State-A moving U
  2178. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  2179. predict error 0
  2180. dir: dir isL
  2181. \-/306: O: O612 (predict-no)
  2182. I see 1 and I'm going to do: predict-no
  2183. ENV: Agent did: predict-no for direction L in state State-A
  2184. In State-A moving L
  2185. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  2186. predict error 0
  2187. dir: dir isL
  2188. |\307: O: O614 (predict-no)
  2189. I see 1 and I'm going to do: predict-no
  2190. ENV: Agent did: predict-no for direction L in state State-A
  2191. In State-A moving L
  2192. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  2193. predict error 0
  2194. dir: dir isL
  2195. -/|308: O: O616 (predict-no)
  2196. I see 1 and I'm going to do: predict-no
  2197. ENV: Agent did: predict-no for direction L in state State-A
  2198. In State-A moving L
  2199. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  2200. predict error 0
  2201. dir: dir isU
  2202. \-/309: O: O618 (predict-no)
  2203. I see 1 and I'm going to do: predict-no
  2204. ENV: Agent did: predict-no for direction U in state State-A
  2205. In State-A moving U
  2206. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  2207. predict error 0
  2208. dir: dir isL
  2209. |\310: O: O620 (predict-no)
  2210. I see 1 and I'm going to do: predict-no
  2211. ENV: Agent did: predict-no for direction L in state State-A
  2212. In State-A moving L
  2213. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  2214. predict error 0
  2215. dir: dir isL
  2216. -/|311: O: O622 (predict-no)
  2217. I see 1 and I'm going to do: predict-no
  2218. ENV: Agent did: predict-no for direction L in state State-A
  2219. In State-A moving L
  2220. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  2221. predict error 0
  2222. dir: dir isU
  2223. \312: O: O624 (predict-no)
  2224. I see 1 and I'm going to do: predict-no
  2225. ENV: Agent did: predict-no for direction U in state State-A
  2226. In State-A moving U
  2227. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  2228. predict error 0
  2229. dir: dir isL
  2230. -/|313: O: O626 (predict-no)
  2231. I see 1 and I'm going to do: predict-no
  2232. ENV: Agent did: predict-no for direction L in state State-A
  2233. In State-A moving L
  2234. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  2235. predict error 0
  2236. dir: dir isU
  2237. \-/314: O: O628 (predict-no)
  2238. I see 1 and I'm going to do: predict-no
  2239. ENV: Agent did: predict-no for direction U in state State-A
  2240. In State-A moving U
  2241. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  2242. predict error 0
  2243. dir: dir isU
  2244. |\-315: O: O630 (predict-no)
  2245. I see 1 and I'm going to do: predict-no
  2246. ENV: Agent did: predict-no for direction U in state State-A
  2247. In State-A moving U
  2248. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  2249. predict error 0
  2250. dir: dir isU
  2251. /|\316: O: O632 (predict-no)
  2252. I see 1 and I'm going to do: predict-no
  2253. ENV: Agent did: predict-no for direction U in state State-A
  2254. In State-A moving U
  2255. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  2256. predict error 0
  2257. dir: dir isU
  2258. -/|317: O: O634 (predict-no)
  2259. I see 1 and I'm going to do: predict-no
  2260. ENV: Agent did: predict-no for direction U in state State-A
  2261. In State-A moving U
  2262. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  2263. predict error 0
  2264. dir: dir isR
  2265. \-/318: O: O635 (predict-yes)
  2266. I see 1 and I'm going to do: predict-yes
  2267. ENV: Agent did: predict-yes for direction R in state State-A
  2268. In State-A moving R
  2269. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  2270. predict error 0
  2271. dir: dir isU
  2272. |\-319: O: O638 (predict-no)
  2273. I see 1 and I'm going to do: predict-no
  2274. ENV: Agent did: predict-no for direction U in state State-B
  2275. In State-B moving U
  2276. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2277. predict error 0
  2278. dir: dir isL
  2279. /|\320: O: O639 (predict-yes)
  2280. I see 1 and I'm going to do: predict-yes
  2281. ENV: Agent did: predict-yes for direction L in state State-B
  2282. In State-B moving L
  2283. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  2284. predict error 0
  2285. dir: dir isU
  2286. -321: O: O642 (predict-no)
  2287. I see 1 and I'm going to do: predict-no
  2288. ENV: Agent did: predict-no for direction U in state State-A
  2289. In State-A moving U
  2290. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  2291. predict error 0
  2292. dir: dir isR
  2293. /322: O: O643 (predict-yes)
  2294. I see 1 and I'm going to do: predict-yes
  2295. ENV: Agent did: predict-yes for direction R in state State-A
  2296. In State-A moving R
  2297. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  2298. predict error 0
  2299. dir: dir isU
  2300. |\-323: O: O646 (predict-no)
  2301. I see 1 and I'm going to do: predict-no
  2302. ENV: Agent did: predict-no for direction U in state State-B
  2303. In State-B moving U
  2304. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2305. predict error 0
  2306. dir: dir isL
  2307. /|\324: O: O647 (predict-yes)
  2308. I see 1 and I'm going to do: predict-yes
  2309. ENV: Agent did: predict-yes for direction L in state State-B
  2310. In State-B moving L
  2311. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  2312. predict error 0
  2313. dir: dir isU
  2314. -/325: O: O650 (predict-no)
  2315. I see 1 and I'm going to do: predict-no
  2316. ENV: Agent did: predict-no for direction U in state State-A
  2317. In State-A moving U
  2318. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  2319. predict error 0
  2320. dir: dir isU
  2321. |\326: O: O652 (predict-no)
  2322. I see 1 and I'm going to do: predict-no
  2323. ENV: Agent did: predict-no for direction U in state State-A
  2324. In State-A moving U
  2325. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  2326. predict error 0
  2327. dir: dir isL
  2328. -/327: O: O654 (predict-no)
  2329. I see 1 and I'm going to do: predict-no
  2330. ENV: Agent did: predict-no for direction L in state State-A
  2331. In State-A moving L
  2332. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  2333. predict error 0
  2334. dir: dir isL
  2335. |\-/sleeping...
  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 L in state State-A
  2339. In State-A moving L
  2340. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  2341. predict error 0
  2342. dir: dir isR
  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 R in state State-A
  2346. In State-A moving R
  2347. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  2348. predict error 0
  2349. dir: dir isU
  2350. /|\330: O: O660 (predict-no)
  2351. I see 1 and I'm going to do: predict-no
  2352. ENV: Agent did: predict-no for direction U in state State-B
  2353. In State-B moving U
  2354. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2355. predict error 0
  2356. dir: dir isL
  2357. -/331: O: O661 (predict-yes)
  2358. I see 1 and I'm going to do: predict-yes
  2359. ENV: Agent did: predict-yes for direction L in state State-B
  2360. In State-B moving L
  2361. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  2362. predict error 0
  2363. dir: dir isL
  2364. |332: O: O664 (predict-no)
  2365. I see 1 and I'm going to do: predict-no
  2366. ENV: Agent did: predict-no for direction L in state State-A
  2367. In State-A moving L
  2368. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  2369. predict error 0
  2370. dir: dir isL
  2371. \-/333: O: O666 (predict-no)
  2372. I see 1 and I'm going to do: predict-no
  2373. ENV: Agent did: predict-no for direction L in state State-A
  2374. In State-A moving L
  2375. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  2376. predict error 0
  2377. dir: dir isR
  2378. |\-334: O: O667 (predict-yes)
  2379. I see 1 and I'm going to do: predict-yes
  2380. ENV: Agent did: predict-yes for direction R in state State-A
  2381. In State-A moving R
  2382. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  2383. predict error 0
  2384. dir: dir isU
  2385. /|335: O: O669 (predict-yes)
  2386. I see 1 and I'm going to do: predict-yes
  2387. ENV: Agent did: predict-yes for direction U in state State-B
  2388. In State-B moving U
  2389. ENV: (next state, see, prediction correct?) = (State-B, 0, False)
  2390. predict error 1
  2391. dir: dir isR
  2392. \-/336: O: O672 (predict-no)
  2393. I see 0 and I'm going to do: predict-no
  2394. ENV: Agent did: predict-no for direction R in state State-B
  2395. In State-B moving R
  2396. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2397. predict error 0
  2398. dir: dir isR
  2399. |\-337: O: O674 (predict-no)
  2400. I see 1 and I'm going to do: predict-no
  2401. ENV: Agent did: predict-no for direction R in state State-B
  2402. In State-B moving R
  2403. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2404. predict error 0
  2405. dir: dir isR
  2406. /|\338: O: O676 (predict-no)
  2407. I see 1 and I'm going to do: predict-no
  2408. ENV: Agent did: predict-no for direction R in state State-B
  2409. In State-B moving R
  2410. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2411. predict error 0
  2412. dir: dir isR
  2413. -/339: O: O678 (predict-no)
  2414. I see 1 and I'm going to do: predict-no
  2415. ENV: Agent did: predict-no for direction R in state State-B
  2416. In State-B moving R
  2417. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2418. predict error 0
  2419. dir: dir isR
  2420. |\-340: O: O679 (predict-yes)
  2421. I see 1 and I'm going to do: predict-yes
  2422. ENV: Agent did: predict-yes for direction R in state State-B
  2423. In State-B moving R
  2424. ENV: (next state, see, prediction correct?) = (State-B, 0, False)
  2425. predict error 1
  2426. dir: dir isL
  2427. /|341: O: O681 (predict-yes)
  2428. I see 0 and I'm going to do: predict-yes
  2429. ENV: Agent did: predict-yes for direction L in state State-B
  2430. In State-B moving L
  2431. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  2432. predict error 0
  2433. dir: dir isR
  2434. \342: O: O683 (predict-yes)
  2435. I see 1 and I'm going to do: predict-yes
  2436. ENV: Agent did: predict-yes for direction R in state State-A
  2437. In State-A moving R
  2438. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  2439. predict error 0
  2440. dir: dir isU
  2441. -/|343: O: O686 (predict-no)
  2442. I see 1 and I'm going to do: predict-no
  2443. ENV: Agent did: predict-no for direction U in state State-B
  2444. In State-B moving U
  2445. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2446. predict error 0
  2447. dir: dir isR
  2448. \-/344: O: O687 (predict-yes)
  2449. I see 1 and I'm going to do: predict-yes
  2450. ENV: Agent did: predict-yes for direction R in state State-B
  2451. In State-B moving R
  2452. ENV: (next state, see, prediction correct?) = (State-B, 0, False)
  2453. predict error 1
  2454. dir: dir isU
  2455. |\-345: O: O690 (predict-no)
  2456. I see 0 and I'm going to do: predict-no
  2457. ENV: Agent did: predict-no for direction U in state State-B
  2458. In State-B moving U
  2459. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2460. predict error 0
  2461. dir: dir isL
  2462. /|346: O: O691 (predict-yes)
  2463. I see 1 and I'm going to do: predict-yes
  2464. ENV: Agent did: predict-yes for direction L in state State-B
  2465. In State-B moving L
  2466. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  2467. predict error 0
  2468. dir: dir isU
  2469. \-/347: O: O694 (predict-no)
  2470. I see 1 and I'm going to do: predict-no
  2471. ENV: Agent did: predict-no for direction U in state State-A
  2472. In State-A moving U
  2473. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  2474. predict error 0
  2475. dir: dir isU
  2476. |\-348: O: O696 (predict-no)
  2477. I see 1 and I'm going to do: predict-no
  2478. ENV: Agent did: predict-no for direction U in state State-A
  2479. In State-A moving U
  2480. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  2481. predict error 0
  2482. dir: dir isU
  2483. /|\349: O: O698 (predict-no)
  2484. I see 1 and I'm going to do: predict-no
  2485. ENV: Agent did: predict-no for direction U in state State-A
  2486. In State-A moving U
  2487. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  2488. predict error 0
  2489. dir: dir isR
  2490. -/|350: O: O699 (predict-yes)
  2491. I see 1 and I'm going to do: predict-yes
  2492. ENV: Agent did: predict-yes for direction R in state State-A
  2493. In State-A moving R
  2494. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  2495. predict error 0
  2496. dir: dir isR
  2497. \-/351: O: O702 (predict-no)
  2498. I see 1 and I'm going to do: predict-no
  2499. ENV: Agent did: predict-no for direction R in state State-B
  2500. In State-B moving R
  2501. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2502. predict error 0
  2503. dir: dir isR
  2504. |352: O: O704 (predict-no)
  2505. I see 1 and I'm going to do: predict-no
  2506. ENV: Agent did: predict-no for direction R in state State-B
  2507. In State-B moving R
  2508. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2509. predict error 0
  2510. dir: dir isU
  2511. \-353: O: O706 (predict-no)
  2512. I see 1 and I'm going to do: predict-no
  2513. ENV: Agent did: predict-no for direction U in state State-B
  2514. In State-B moving U
  2515. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2516. predict error 0
  2517. dir: dir isL
  2518. /|\354: O: O707 (predict-yes)
  2519. I see 1 and I'm going to do: predict-yes
  2520. ENV: Agent did: predict-yes for direction L in state State-B
  2521. In State-B moving L
  2522. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  2523. predict error 0
  2524. dir: dir isL
  2525. -/|355: O: O710 (predict-no)
  2526. I see 1 and I'm going to do: predict-no
  2527. ENV: Agent did: predict-no for direction L in state State-A
  2528. In State-A moving L
  2529. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  2530. predict error 0
  2531. dir: dir isU
  2532. \-/356: O: O712 (predict-no)
  2533. I see 1 and I'm going to do: predict-no
  2534. ENV: Agent did: predict-no for direction U in state State-A
  2535. In State-A moving U
  2536. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  2537. predict error 0
  2538. dir: dir isU
  2539. |\-357: O: O714 (predict-no)
  2540. I see 1 and I'm going to do: predict-no
  2541. ENV: Agent did: predict-no for direction U in state State-A
  2542. In State-A moving U
  2543. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  2544. predict error 0
  2545. dir: dir isR
  2546. /|\358: O: O715 (predict-yes)
  2547. I see 1 and I'm going to do: predict-yes
  2548. ENV: Agent did: predict-yes for direction R in state State-A
  2549. In State-A moving R
  2550. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  2551. predict error 0
  2552. dir: dir isR
  2553. -/|359: O: O718 (predict-no)
  2554. I see 1 and I'm going to do: predict-no
  2555. ENV: Agent did: predict-no for direction R in state State-B
  2556. In State-B moving R
  2557. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2558. predict error 0
  2559. dir: dir isU
  2560. \-/360: O: O720 (predict-no)
  2561. I see 1 and I'm going to do: predict-no
  2562. ENV: Agent did: predict-no for direction U in state State-B
  2563. In State-B moving U
  2564. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2565. predict error 0
  2566. dir: dir isL
  2567. |\361: O: O721 (predict-yes)
  2568. I see 1 and I'm going to do: predict-yes
  2569. ENV: Agent did: predict-yes for direction L in state State-B
  2570. In State-B moving L
  2571. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  2572. predict error 0
  2573. dir: dir isL
  2574. -362: O: O724 (predict-no)
  2575. I see 1 and I'm going to do: predict-no
  2576. ENV: Agent did: predict-no for direction L in state State-A
  2577. In State-A moving L
  2578. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  2579. predict error 0
  2580. dir: dir isL
  2581. /|\363: O: O726 (predict-no)
  2582. I see 1 and I'm going to do: predict-no
  2583. ENV: Agent did: predict-no for direction L in state State-A
  2584. In State-A moving L
  2585. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  2586. predict error 0
  2587. dir: dir isR
  2588. -/|364: O: O727 (predict-yes)
  2589. I see 1 and I'm going to do: predict-yes
  2590. ENV: Agent did: predict-yes for direction R in state State-A
  2591. In State-A moving R
  2592. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  2593. predict error 0
  2594. dir: dir isL
  2595. \-/365: O: O729 (predict-yes)
  2596. I see 1 and I'm going to do: predict-yes
  2597. ENV: Agent did: predict-yes for direction L in state State-B
  2598. In State-B moving L
  2599. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  2600. predict error 0
  2601. dir: dir isL
  2602. |366: O: O732 (predict-no)
  2603. I see 1 and I'm going to do: predict-no
  2604. ENV: Agent did: predict-no for direction L in state State-A
  2605. In State-A moving L
  2606. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  2607. predict error 0
  2608. dir: dir isU
  2609. \-/367: O: O734 (predict-no)
  2610. I see 1 and I'm going to do: predict-no
  2611. ENV: Agent did: predict-no for direction U in state State-A
  2612. In State-A moving U
  2613. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  2614. predict error 0
  2615. dir: dir isU
  2616. |\-368: O: O735 (predict-yes)
  2617. I see 1 and I'm going to do: predict-yes
  2618. ENV: Agent did: predict-yes for direction U in state State-A
  2619. In State-A moving U
  2620. ENV: (next state, see, prediction correct?) = (State-A, 0, False)
  2621. predict error 1
  2622. dir: dir isL
  2623. /|\369: O: O738 (predict-no)
  2624. I see 0 and I'm going to do: predict-no
  2625. ENV: Agent did: predict-no for direction L in state State-A
  2626. In State-A moving L
  2627. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  2628. predict error 0
  2629. dir: dir isU
  2630. -/|370: O: O740 (predict-no)
  2631. I see 1 and I'm going to do: predict-no
  2632. ENV: Agent did: predict-no for direction U in state State-A
  2633. In State-A moving U
  2634. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  2635. predict error 0
  2636. dir: dir isR
  2637. \-371: O: O741 (predict-yes)
  2638. I see 1 and I'm going to do: predict-yes
  2639. ENV: Agent did: predict-yes for direction R in state State-A
  2640. In State-A moving R
  2641. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  2642. predict error 0
  2643. dir: dir isU
  2644. /372: O: O744 (predict-no)
  2645. I see 1 and I'm going to do: predict-no
  2646. ENV: Agent did: predict-no for direction U in state State-B
  2647. In State-B moving U
  2648. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2649. predict error 0
  2650. dir: dir isR
  2651. |\-373: O: O745 (predict-yes)
  2652. I see 1 and I'm going to do: predict-yes
  2653. ENV: Agent did: predict-yes for direction R in state State-B
  2654. In State-B moving R
  2655. ENV: (next state, see, prediction correct?) = (State-B, 0, False)
  2656. predict error 1
  2657. dir: dir isL
  2658. /|374: O: O747 (predict-yes)
  2659. I see 0 and I'm going to do: predict-yes
  2660. ENV: Agent did: predict-yes for direction L in state State-B
  2661. In State-B moving L
  2662. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  2663. predict error 0
  2664. dir: dir isL
  2665. \-/375: O: O750 (predict-no)
  2666. I see 1 and I'm going to do: predict-no
  2667. ENV: Agent did: predict-no for direction L in state State-A
  2668. In State-A moving L
  2669. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  2670. predict error 0
  2671. dir: dir isL
  2672. |\-376: O: O752 (predict-no)
  2673. I see 1 and I'm going to do: predict-no
  2674. ENV: Agent did: predict-no for direction L in state State-A
  2675. In State-A moving L
  2676. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  2677. predict error 0
  2678. dir: dir isR
  2679. /|\377: O: O753 (predict-yes)
  2680. I see 1 and I'm going to do: predict-yes
  2681. ENV: Agent did: predict-yes for direction R in state State-A
  2682. In State-A moving R
  2683. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  2684. predict error 0
  2685. dir: dir isR
  2686. -/|378: O: O756 (predict-no)
  2687. I see 1 and I'm going to do: predict-no
  2688. ENV: Agent did: predict-no for direction R in state State-B
  2689. In State-B moving R
  2690. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2691. predict error 0
  2692. dir: dir isL
  2693. \-/379: O: O757 (predict-yes)
  2694. I see 1 and I'm going to do: predict-yes
  2695. ENV: Agent did: predict-yes for direction L in state State-B
  2696. In State-B moving L
  2697. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  2698. predict error 0
  2699. dir: dir isR
  2700. |\380: O: O759 (predict-yes)
  2701. I see 1 and I'm going to do: predict-yes
  2702. ENV: Agent did: predict-yes for direction R in state State-A
  2703. In State-A moving R
  2704. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  2705. predict error 0
  2706. dir: dir isL
  2707. -/381: O: O761 (predict-yes)
  2708. I see 1 and I'm going to do: predict-yes
  2709. ENV: Agent did: predict-yes for direction L in state State-B
  2710. In State-B moving L
  2711. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  2712. predict error 0
  2713. dir: dir isU
  2714. |382: O: O764 (predict-no)
  2715. I see 1 and I'm going to do: predict-no
  2716. ENV: Agent did: predict-no for direction U in state State-A
  2717. In State-A moving U
  2718. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  2719. predict error 0
  2720. dir: dir isL
  2721. \-383: O: O766 (predict-no)
  2722. I see 1 and I'm going to do: predict-no
  2723. ENV: Agent did: predict-no for direction L in state State-A
  2724. In State-A moving L
  2725. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  2726. predict error 0
  2727. dir: dir isU
  2728. /|384: O: O768 (predict-no)
  2729. I see 1 and I'm going to do: predict-no
  2730. ENV: Agent did: predict-no for direction U in state State-A
  2731. In State-A moving U
  2732. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  2733. predict error 0
  2734. dir: dir isR
  2735. \-385: O: O769 (predict-yes)
  2736. I see 1 and I'm going to do: predict-yes
  2737. ENV: Agent did: predict-yes for direction R in state State-A
  2738. In State-A moving R
  2739. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  2740. predict error 0
  2741. dir: dir isR
  2742. /|386: O: O772 (predict-no)
  2743. I see 1 and I'm going to do: predict-no
  2744. ENV: Agent did: predict-no for direction R in state State-B
  2745. In State-B moving R
  2746. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2747. predict error 0
  2748. dir: dir isR
  2749. \-387: O: O774 (predict-no)
  2750. I see 1 and I'm going to do: predict-no
  2751. ENV: Agent did: predict-no for direction R in state State-B
  2752. In State-B moving R
  2753. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2754. predict error 0
  2755. dir: dir isU
  2756. /|\-388: O: O776 (predict-no)
  2757. I see 1 and I'm going to do: predict-no
  2758. ENV: Agent did: predict-no for direction U in state State-B
  2759. In State-B moving U
  2760. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2761. predict error 0
  2762. dir: dir isU
  2763. /|\389: O: O778 (predict-no)
  2764. I see 1 and I'm going to do: predict-no
  2765. ENV: Agent did: predict-no for direction U in state State-B
  2766. In State-B moving U
  2767. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2768. predict error 0
  2769. dir: dir isR
  2770. -/|390: O: O780 (predict-no)
  2771. I see 1 and I'm going to do: predict-no
  2772. ENV: Agent did: predict-no for direction R in state State-B
  2773. In State-B moving R
  2774. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2775. predict error 0
  2776. dir: dir isR
  2777. \-391: O: O782 (predict-no)
  2778. I see 1 and I'm going to do: predict-no
  2779. ENV: Agent did: predict-no for direction R in state State-B
  2780. In State-B moving R
  2781. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2782. predict error 0
  2783. dir: dir isU
  2784. /392: O: O784 (predict-no)
  2785. I see 1 and I'm going to do: predict-no
  2786. ENV: Agent did: predict-no for direction U in state State-B
  2787. In State-B moving U
  2788. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2789. predict error 0
  2790. dir: dir isU
  2791. |\393: O: O786 (predict-no)
  2792. I see 1 and I'm going to do: predict-no
  2793. ENV: Agent did: predict-no for direction U in state State-B
  2794. In State-B moving U
  2795. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2796. predict error 0
  2797. dir: dir isR
  2798. -/394: O: O788 (predict-no)
  2799. I see 1 and I'm going to do: predict-no
  2800. ENV: Agent did: predict-no for direction R in state State-B
  2801. In State-B moving R
  2802. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2803. predict error 0
  2804. dir: dir isU
  2805. |\-395: O: O790 (predict-no)
  2806. I see 1 and I'm going to do: predict-no
  2807. ENV: Agent did: predict-no for direction U in state State-B
  2808. In State-B moving U
  2809. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2810. predict error 0
  2811. dir: dir isU
  2812. /|396: O: O792 (predict-no)
  2813. I see 1 and I'm going to do: predict-no
  2814. ENV: Agent did: predict-no for direction U in state State-B
  2815. In State-B moving U
  2816. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2817. predict error 0
  2818. dir: dir isR
  2819. \-/397: O: O794 (predict-no)
  2820. I see 1 and I'm going to do: predict-no
  2821. ENV: Agent did: predict-no for direction R in state State-B
  2822. In State-B moving R
  2823. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2824. predict error 0
  2825. dir: dir isL
  2826. |\-398: O: O795 (predict-yes)
  2827. I see 1 and I'm going to do: predict-yes
  2828. ENV: Agent did: predict-yes for direction L in state State-B
  2829. In State-B moving L
  2830. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  2831. predict error 0
  2832. dir: dir isL
  2833. /|399: O: O798 (predict-no)
  2834. I see 1 and I'm going to do: predict-no
  2835. ENV: Agent did: predict-no for direction L in state State-A
  2836. In State-A moving L
  2837. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  2838. predict error 0
  2839. dir: dir isU
  2840. \-/400: O: O800 (predict-no)
  2841. I see 1 and I'm going to do: predict-no
  2842. ENV: Agent did: predict-no for direction U in state State-A
  2843. In State-A moving U
  2844. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  2845. predict error 0
  2846. dir: dir isU
  2847. |\-401: O: O802 (predict-no)
  2848. I see 1 and I'm going to do: predict-no
  2849. ENV: Agent did: predict-no for direction U in state State-A
  2850. In State-A moving U
  2851. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  2852. predict error 0
  2853. dir: dir isU
  2854. /402: O: O804 (predict-no)
  2855. I see 1 and I'm going to do: predict-no
  2856. ENV: Agent did: predict-no for direction U in state State-A
  2857. In State-A moving U
  2858. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  2859. predict error 0
  2860. dir: dir isU
  2861. |\-403: O: O806 (predict-no)
  2862. I see 1 and I'm going to do: predict-no
  2863. ENV: Agent did: predict-no for direction U in state State-A
  2864. In State-A moving U
  2865. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  2866. predict error 0
  2867. dir: dir isL
  2868. /|\404: O: O808 (predict-no)
  2869. I see 1 and I'm going to do: predict-no
  2870. ENV: Agent did: predict-no for direction L in state State-A
  2871. In State-A moving L
  2872. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  2873. predict error 0
  2874. dir: dir isL
  2875. -/|405: O: O810 (predict-no)
  2876. I see 1 and I'm going to do: predict-no
  2877. ENV: Agent did: predict-no for direction L in state State-A
  2878. In State-A moving L
  2879. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  2880. predict error 0
  2881. dir: dir isL
  2882. \-/406: O: O812 (predict-no)
  2883. I see 1 and I'm going to do: predict-no
  2884. ENV: Agent did: predict-no for direction L in state State-A
  2885. In State-A moving L
  2886. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  2887. predict error 0
  2888. dir: dir isL
  2889. |\-407: O: O814 (predict-no)
  2890. I see 1 and I'm going to do: predict-no
  2891. ENV: Agent did: predict-no for direction L in state State-A
  2892. In State-A moving L
  2893. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  2894. predict error 0
  2895. dir: dir isU
  2896. /|\408: O: O816 (predict-no)
  2897. I see 1 and I'm going to do: predict-no
  2898. ENV: Agent did: predict-no for direction U in state State-A
  2899. In State-A moving U
  2900. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  2901. predict error 0
  2902. dir: dir isU
  2903. -/|409: O: O818 (predict-no)
  2904. I see 1 and I'm going to do: predict-no
  2905. ENV: Agent did: predict-no for direction U in state State-A
  2906. In State-A moving U
  2907. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  2908. predict error 0
  2909. dir: dir isU
  2910. \-/410: O: O820 (predict-no)
  2911. I see 1 and I'm going to do: predict-no
  2912. ENV: Agent did: predict-no for direction U in state State-A
  2913. In State-A moving U
  2914. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  2915. predict error 0
  2916. dir: dir isL
  2917. |\411: O: O822 (predict-no)
  2918. I see 1 and I'm going to do: predict-no
  2919. ENV: Agent did: predict-no for direction L in state State-A
  2920. In State-A moving L
  2921. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  2922. predict error 0
  2923. dir: dir isU
  2924. -412: O: O824 (predict-no)
  2925. I see 1 and I'm going to do: predict-no
  2926. ENV: Agent did: predict-no for direction U in state State-A
  2927. In State-A moving U
  2928. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  2929. predict error 0
  2930. dir: dir isL
  2931. /|413: O: O826 (predict-no)
  2932. I see 1 and I'm going to do: predict-no
  2933. ENV: Agent did: predict-no for direction L in state State-A
  2934. In State-A moving L
  2935. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  2936. predict error 0
  2937. dir: dir isR
  2938. \-/414: O: O827 (predict-yes)
  2939. I see 1 and I'm going to do: predict-yes
  2940. ENV: Agent did: predict-yes for direction R in state State-A
  2941. In State-A moving R
  2942. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  2943. predict error 0
  2944. dir: dir isU
  2945. |\-415: O: O829 (predict-yes)
  2946. I see 1 and I'm going to do: predict-yes
  2947. ENV: Agent did: predict-yes for direction U in state State-B
  2948. In State-B moving U
  2949. ENV: (next state, see, prediction correct?) = (State-B, 0, False)
  2950. predict error 1
  2951. dir: dir isL
  2952. /|416: O: O831 (predict-yes)
  2953. I see 0 and I'm going to do: predict-yes
  2954. ENV: Agent did: predict-yes for direction L in state State-B
  2955. In State-B moving L
  2956. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  2957. predict error 0
  2958. dir: dir isL
  2959. \-417: O: O834 (predict-no)
  2960. I see 1 and I'm going to do: predict-no
  2961. ENV: Agent did: predict-no for direction L in state State-A
  2962. In State-A moving L
  2963. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  2964. predict error 0
  2965. dir: dir isU
  2966. /|\418: O: O835 (predict-yes)
  2967. I see 1 and I'm going to do: predict-yes
  2968. ENV: Agent did: predict-yes for direction U in state State-A
  2969. In State-A moving U
  2970. ENV: (next state, see, prediction correct?) = (State-A, 0, False)
  2971. predict error 1
  2972. dir: dir isL
  2973. -/419: O: O838 (predict-no)
  2974. I see 0 and I'm going to do: predict-no
  2975. ENV: Agent did: predict-no for direction L in state State-A
  2976. In State-A moving L
  2977. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  2978. predict error 0
  2979. dir: dir isR
  2980. |\-420: O: O839 (predict-yes)
  2981. I see 1 and I'm going to do: predict-yes
  2982. ENV: Agent did: predict-yes for direction R in state State-A
  2983. In State-A moving R
  2984. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  2985. predict error 0
  2986. dir: dir isR
  2987. /421: O: O842 (predict-no)
  2988. I see 1 and I'm going to do: predict-no
  2989. ENV: Agent did: predict-no for direction R in state State-B
  2990. In State-B moving R
  2991. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2992. predict error 0
  2993. dir: dir isU
  2994. |422: O: O844 (predict-no)
  2995. I see 1 and I'm going to do: predict-no
  2996. ENV: Agent did: predict-no for direction U in state State-B
  2997. In State-B moving U
  2998. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2999. predict error 0
  3000. dir: dir isL
  3001. \-423: O: O845 (predict-yes)
  3002. I see 1 and I'm going to do: predict-yes
  3003. ENV: Agent did: predict-yes for direction L in state State-B
  3004. In State-B moving L
  3005. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  3006. predict error 0
  3007. dir: dir isR
  3008. /424: O: O847 (predict-yes)
  3009. I see 1 and I'm going to do: predict-yes
  3010. ENV: Agent did: predict-yes for direction R in state State-A
  3011. In State-A moving R
  3012. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  3013. predict error 0
  3014. dir: dir isR
  3015. |\-425: O: O850 (predict-no)
  3016. I see 1 and I'm going to do: predict-no
  3017. ENV: Agent did: predict-no for direction R in state State-B
  3018. In State-B moving R
  3019. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3020. predict error 0
  3021. dir: dir isR
  3022. /|426: O: O852 (predict-no)
  3023. I see 1 and I'm going to do: predict-no
  3024. ENV: Agent did: predict-no for direction R in state State-B
  3025. In State-B moving R
  3026. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3027. predict error 0
  3028. dir: dir isL
  3029. \-/427: O: O853 (predict-yes)
  3030. I see 1 and I'm going to do: predict-yes
  3031. ENV: Agent did: predict-yes for direction L in state State-B
  3032. In State-B moving L
  3033. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  3034. predict error 0
  3035. dir: dir isR
  3036. |\-428: O: O855 (predict-yes)
  3037. I see 1 and I'm going to do: predict-yes
  3038. ENV: Agent did: predict-yes for direction R in state State-A
  3039. In State-A moving R
  3040. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  3041. predict error 0
  3042. dir: dir isU
  3043. /|\429: O: O858 (predict-no)
  3044. I see 1 and I'm going to do: predict-no
  3045. ENV: Agent did: predict-no for direction U in state State-B
  3046. In State-B moving U
  3047. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3048. predict error 0
  3049. dir: dir isR
  3050. -/430: O: O860 (predict-no)
  3051. I see 1 and I'm going to do: predict-no
  3052. ENV: Agent did: predict-no for direction R in state State-B
  3053. In State-B moving R
  3054. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3055. predict error 0
  3056. dir: dir isR
  3057. |\431: O: O862 (predict-no)
  3058. I see 1 and I'm going to do: predict-no
  3059. ENV: Agent did: predict-no for direction R in state State-B
  3060. In State-B moving R
  3061. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3062. predict error 0
  3063. dir: dir isL
  3064. -432: O: O863 (predict-yes)
  3065. I see 1 and I'm going to do: predict-yes
  3066. ENV: Agent did: predict-yes for direction L in state State-B
  3067. In State-B moving L
  3068. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  3069. predict error 0
  3070. dir: dir isL
  3071. /|\433: O: O866 (predict-no)
  3072. I see 1 and I'm going to do: predict-no
  3073. ENV: Agent did: predict-no for direction L in state State-A
  3074. In State-A moving L
  3075. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3076. predict error 0
  3077. dir: dir isR
  3078. -/434: O: O867 (predict-yes)
  3079. I see 1 and I'm going to do: predict-yes
  3080. ENV: Agent did: predict-yes for direction R in state State-A
  3081. In State-A moving R
  3082. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  3083. predict error 0
  3084. dir: dir isL
  3085. |\-435: O: O869 (predict-yes)
  3086. I see 1 and I'm going to do: predict-yes
  3087. ENV: Agent did: predict-yes for direction L in state State-B
  3088. In State-B moving L
  3089. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  3090. predict error 0
  3091. dir: dir isU
  3092. /|\436: O: O872 (predict-no)
  3093. I see 1 and I'm going to do: predict-no
  3094. ENV: Agent did: predict-no for direction U in state State-A
  3095. In State-A moving U
  3096. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3097. predict error 0
  3098. dir: dir isU
  3099. -/|437: O: O874 (predict-no)
  3100. I see 1 and I'm going to do: predict-no
  3101. ENV: Agent did: predict-no for direction U in state State-A
  3102. In State-A moving U
  3103. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3104. predict error 0
  3105. dir: dir isL
  3106. \-/438: O: O876 (predict-no)
  3107. I see 1 and I'm going to do: predict-no
  3108. ENV: Agent did: predict-no for direction L in state State-A
  3109. In State-A moving L
  3110. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3111. predict error 0
  3112. dir: dir isU
  3113. |\-439: O: O878 (predict-no)
  3114. I see 1 and I'm going to do: predict-no
  3115. ENV: Agent did: predict-no for direction U in state State-A
  3116. In State-A moving U
  3117. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3118. predict error 0
  3119. dir: dir isR
  3120. /|\440: O: O879 (predict-yes)
  3121. I see 1 and I'm going to do: predict-yes
  3122. ENV: Agent did: predict-yes for direction R in state State-A
  3123. In State-A moving R
  3124. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  3125. predict error 0
  3126. dir: dir isU
  3127. -/|441: O: O882 (predict-no)
  3128. I see 1 and I'm going to do: predict-no
  3129. ENV: Agent did: predict-no for direction U in state State-B
  3130. In State-B moving U
  3131. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3132. predict error 0
  3133. dir: dir isU
  3134. \442: O: O884 (predict-no)
  3135. I see 1 and I'm going to do: predict-no
  3136. ENV: Agent did: predict-no for direction U in state State-B
  3137. In State-B moving U
  3138. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3139. predict error 0
  3140. dir: dir isL
  3141. -/|443: O: O885 (predict-yes)
  3142. I see 1 and I'm going to do: predict-yes
  3143. ENV: Agent did: predict-yes for direction L in state State-B
  3144. In State-B moving L
  3145. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  3146. predict error 0
  3147. dir: dir isU
  3148. \-444: O: O888 (predict-no)
  3149. I see 1 and I'm going to do: predict-no
  3150. ENV: Agent did: predict-no for direction U in state State-A
  3151. In State-A moving U
  3152. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3153. predict error 0
  3154. dir: dir isR
  3155. /445: O: O889 (predict-yes)
  3156. I see 1 and I'm going to do: predict-yes
  3157. ENV: Agent did: predict-yes for direction R in state State-A
  3158. In State-A moving R
  3159. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  3160. predict error 0
  3161. dir: dir isU
  3162. |\-446: O: O892 (predict-no)
  3163. I see 1 and I'm going to do: predict-no
  3164. ENV: Agent did: predict-no for direction U in state State-B
  3165. In State-B moving U
  3166. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3167. predict error 0
  3168. dir: dir isL
  3169. /|447: O: O893 (predict-yes)
  3170. I see 1 and I'm going to do: predict-yes
  3171. ENV: Agent did: predict-yes for direction L in state State-B
  3172. In State-B moving L
  3173. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  3174. predict error 0
  3175. dir: dir isU
  3176. \-/448: O: O896 (predict-no)
  3177. I see 1 and I'm going to do: predict-no
  3178. ENV: Agent did: predict-no for direction U in state State-A
  3179. In State-A moving U
  3180. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3181. predict error 0
  3182. dir: dir isU
  3183. |\-449: O: O898 (predict-no)
  3184. I see 1 and I'm going to do: predict-no
  3185. ENV: Agent did: predict-no for direction U in state State-A
  3186. In State-A moving U
  3187. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3188. predict error 0
  3189. dir: dir isU
  3190. /|\450: O: O900 (predict-no)
  3191. I see 1 and I'm going to do: predict-no
  3192. ENV: Agent did: predict-no for direction U in state State-A
  3193. In State-A moving U
  3194. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3195. predict error 0
  3196. dir: dir isR
  3197. -451: O: O901 (predict-yes)
  3198. I see 1 and I'm going to do: predict-yes
  3199. ENV: Agent did: predict-yes for direction R in state State-A
  3200. In State-A moving R
  3201. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  3202. predict error 0
  3203. dir: dir isL
  3204. /452: O: O903 (predict-yes)
  3205. I see 1 and I'm going to do: predict-yes
  3206. ENV: Agent did: predict-yes for direction L in state State-B
  3207. In State-B moving L
  3208. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  3209. predict error 0
  3210. dir: dir isR
  3211. |\-/sleeping...
  3212. |453: O: O905 (predict-yes)
  3213. I see 1 and I'm going to do: predict-yes
  3214. ENV: Agent did: predict-yes for direction R in state State-A
  3215. In State-A moving R
  3216. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  3217. predict error 0
  3218. dir: dir isR
  3219. \-/454: O: O908 (predict-no)
  3220. I see 1 and I'm going to do: predict-no
  3221. ENV: Agent did: predict-no for direction R in state State-B
  3222. In State-B moving R
  3223. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3224. predict error 0
  3225. dir: dir isU
  3226. |\-455: O: O910 (predict-no)
  3227. I see 1 and I'm going to do: predict-no
  3228. ENV: Agent did: predict-no for direction U in state State-B
  3229. In State-B moving U
  3230. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3231. predict error 0
  3232. dir: dir isU
  3233. /|\456: O: O912 (predict-no)
  3234. I see 1 and I'm going to do: predict-no
  3235. ENV: Agent did: predict-no for direction U in state State-B
  3236. In State-B moving U
  3237. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3238. predict error 0
  3239. dir: dir isR
  3240. -/|457: O: O914 (predict-no)
  3241. I see 1 and I'm going to do: predict-no
  3242. ENV: Agent did: predict-no for direction R in state State-B
  3243. In State-B moving R
  3244. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3245. predict error 0
  3246. dir: dir isL
  3247. \458: O: O915 (predict-yes)
  3248. I see 1 and I'm going to do: predict-yes
  3249. ENV: Agent did: predict-yes for direction L in state State-B
  3250. In State-B moving L
  3251. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  3252. predict error 0
  3253. dir: dir isR
  3254. -/459: O: O917 (predict-yes)
  3255. I see 1 and I'm going to do: predict-yes
  3256. ENV: Agent did: predict-yes for direction R in state State-A
  3257. In State-A moving R
  3258. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  3259. predict error 0
  3260. dir: dir isR
  3261. |\-460: O: O920 (predict-no)
  3262. I see 1 and I'm going to do: predict-no
  3263. ENV: Agent did: predict-no for direction R in state State-B
  3264. In State-B moving R
  3265. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3266. predict error 0
  3267. dir: dir isL
  3268. /|\461: O: O921 (predict-yes)
  3269. I see 1 and I'm going to do: predict-yes
  3270. ENV: Agent did: predict-yes for direction L in state State-B
  3271. In State-B moving L
  3272. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  3273. predict error 0
  3274. dir: dir isU
  3275. -462: O: O924 (predict-no)
  3276. I see 1 and I'm going to do: predict-no
  3277. ENV: Agent did: predict-no for direction U in state State-A
  3278. In State-A moving U
  3279. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3280. predict error 0
  3281. dir: dir isR
  3282. /|463: O: O925 (predict-yes)
  3283. I see 1 and I'm going to do: predict-yes
  3284. ENV: Agent did: predict-yes for direction R in state State-A
  3285. In State-A moving R
  3286. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  3287. predict error 0
  3288. dir: dir isL
  3289. \464: O: O927 (predict-yes)
  3290. I see 1 and I'm going to do: predict-yes
  3291. ENV: Agent did: predict-yes for direction L in state State-B
  3292. In State-B moving L
  3293. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  3294. predict error 0
  3295. dir: dir isU
  3296. -/465: O: O930 (predict-no)
  3297. I see 1 and I'm going to do: predict-no
  3298. ENV: Agent did: predict-no for direction U in state State-A
  3299. In State-A moving U
  3300. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3301. predict error 0
  3302. dir: dir isL
  3303. |\-466: O: O932 (predict-no)
  3304. I see 1 and I'm going to do: predict-no
  3305. ENV: Agent did: predict-no for direction L in state State-A
  3306. In State-A moving L
  3307. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3308. predict error 0
  3309. dir: dir isL
  3310. /|\-467: O: O934 (predict-no)
  3311. I see 1 and I'm going to do: predict-no
  3312. ENV: Agent did: predict-no for direction L in state State-A
  3313. In State-A moving L
  3314. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3315. predict error 0
  3316. dir: dir isU
  3317. /|\468: O: O936 (predict-no)
  3318. I see 1 and I'm going to do: predict-no
  3319. ENV: Agent did: predict-no for direction U in state State-A
  3320. In State-A moving U
  3321. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3322. predict error 0
  3323. dir: dir isR
  3324. -/469: O: O937 (predict-yes)
  3325. I see 1 and I'm going to do: predict-yes
  3326. ENV: Agent did: predict-yes for direction R in state State-A
  3327. In State-A moving R
  3328. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  3329. predict error 0
  3330. dir: dir isR
  3331. |\470: O: O940 (predict-no)
  3332. I see 1 and I'm going to do: predict-no
  3333. ENV: Agent did: predict-no for direction R in state State-B
  3334. In State-B moving R
  3335. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3336. predict error 0
  3337. dir: dir isR
  3338. -/|\471: O: O942 (predict-no)
  3339. I see 1 and I'm going to do: predict-no
  3340. ENV: Agent did: predict-no for direction R in state State-B
  3341. In State-B moving R
  3342. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3343. predict error 0
  3344. dir: dir isR
  3345. -472: O: O944 (predict-no)
  3346. I see 1 and I'm going to do: predict-no
  3347. ENV: Agent did: predict-no for direction R in state State-B
  3348. In State-B moving R
  3349. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3350. predict error 0
  3351. dir: dir isL
  3352. /|473: O: O945 (predict-yes)
  3353. I see 1 and I'm going to do: predict-yes
  3354. ENV: Agent did: predict-yes for direction L in state State-B
  3355. In State-B moving L
  3356. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  3357. predict error 0
  3358. dir: dir isL
  3359. \-/474: O: O948 (predict-no)
  3360. I see 1 and I'm going to do: predict-no
  3361. ENV: Agent did: predict-no for direction L in state State-A
  3362. In State-A moving L
  3363. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3364. predict error 0
  3365. dir: dir isL
  3366. |\-475: O: O950 (predict-no)
  3367. I see 1 and I'm going to do: predict-no
  3368. ENV: Agent did: predict-no for direction L in state State-A
  3369. In State-A moving L
  3370. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3371. predict error 0
  3372. dir: dir isU
  3373. /|\476: O: O952 (predict-no)
  3374. I see 1 and I'm going to do: predict-no
  3375. ENV: Agent did: predict-no for direction U in state State-A
  3376. In State-A moving U
  3377. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3378. predict error 0
  3379. dir: dir isU
  3380. -/|477: O: O954 (predict-no)
  3381. I see 1 and I'm going to do: predict-no
  3382. ENV: Agent did: predict-no for direction U in state State-A
  3383. In State-A moving U
  3384. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3385. predict error 0
  3386. dir: dir isR
  3387. \-478: O: O955 (predict-yes)
  3388. I see 1 and I'm going to do: predict-yes
  3389. ENV: Agent did: predict-yes for direction R in state State-A
  3390. In State-A moving R
  3391. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  3392. predict error 0
  3393. dir: dir isU
  3394. /|479: O: O958 (predict-no)
  3395. I see 1 and I'm going to do: predict-no
  3396. ENV: Agent did: predict-no for direction U in state State-B
  3397. In State-B moving U
  3398. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3399. predict error 0
  3400. dir: dir isR
  3401. \-/480: O: O960 (predict-no)
  3402. I see 1 and I'm going to do: predict-no
  3403. ENV: Agent did: predict-no for direction R in state State-B
  3404. In State-B moving R
  3405. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3406. predict error 0
  3407. dir: dir isL
  3408. |\-481: O: O961 (predict-yes)
  3409. I see 1 and I'm going to do: predict-yes
  3410. ENV: Agent did: predict-yes for direction L in state State-B
  3411. In State-B moving L
  3412. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  3413. predict error 0
  3414. dir: dir isR
  3415. /482: O: O963 (predict-yes)
  3416. I see 1 and I'm going to do: predict-yes
  3417. ENV: Agent did: predict-yes for direction R in state State-A
  3418. In State-A moving R
  3419. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  3420. predict error 0
  3421. dir: dir isU
  3422. |\-483: O: O966 (predict-no)
  3423. I see 1 and I'm going to do: predict-no
  3424. ENV: Agent did: predict-no for direction U in state State-B
  3425. In State-B moving U
  3426. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3427. predict error 0
  3428. dir: dir isL
  3429. /|\484: O: O967 (predict-yes)
  3430. I see 1 and I'm going to do: predict-yes
  3431. ENV: Agent did: predict-yes for direction L in state State-B
  3432. In State-B moving L
  3433. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  3434. predict error 0
  3435. dir: dir isR
  3436. -/485: O: O969 (predict-yes)
  3437. I see 1 and I'm going to do: predict-yes
  3438. ENV: Agent did: predict-yes for direction R in state State-A
  3439. In State-A moving R
  3440. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  3441. predict error 0
  3442. dir: dir isL
  3443. |\-486: O: O971 (predict-yes)
  3444. I see 1 and I'm going to do: predict-yes
  3445. ENV: Agent did: predict-yes for direction L in state State-B
  3446. In State-B moving L
  3447. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  3448. predict error 0
  3449. dir: dir isU
  3450. /|\487: O: O974 (predict-no)
  3451. I see 1 and I'm going to do: predict-no
  3452. ENV: Agent did: predict-no for direction U in state State-A
  3453. In State-A moving U
  3454. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3455. predict error 0
  3456. dir: dir isR
  3457. -/488: O: O975 (predict-yes)
  3458. I see 1 and I'm going to do: predict-yes
  3459. ENV: Agent did: predict-yes for direction R in state State-A
  3460. In State-A moving R
  3461. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  3462. predict error 0
  3463. dir: dir isL
  3464. |489: O: O977 (predict-yes)
  3465. I see 1 and I'm going to do: predict-yes
  3466. ENV: Agent did: predict-yes for direction L in state State-B
  3467. In State-B moving L
  3468. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  3469. predict error 0
  3470. dir: dir isR
  3471. \-/490: O: O979 (predict-yes)
  3472. I see 1 and I'm going to do: predict-yes
  3473. ENV: Agent did: predict-yes for direction R in state State-A
  3474. In State-A moving R
  3475. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  3476. predict error 0
  3477. dir: dir isR
  3478. |491: O: O982 (predict-no)
  3479. I see 1 and I'm going to do: predict-no
  3480. ENV: Agent did: predict-no for direction R in state State-B
  3481. In State-B moving R
  3482. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3483. predict error 0
  3484. dir: dir isU
  3485. \492: O: O984 (predict-no)
  3486. I see 1 and I'm going to do: predict-no
  3487. ENV: Agent did: predict-no for direction U in state State-B
  3488. In State-B moving U
  3489. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3490. predict error 0
  3491. dir: dir isR
  3492. -/|493: O: O986 (predict-no)
  3493. I see 1 and I'm going to do: predict-no
  3494. ENV: Agent did: predict-no for direction R in state State-B
  3495. In State-B moving R
  3496. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3497. predict error 0
  3498. dir: dir isU
  3499. \-/494: O: O988 (predict-no)
  3500. I see 1 and I'm going to do: predict-no
  3501. ENV: Agent did: predict-no for direction U in state State-B
  3502. In State-B moving U
  3503. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3504. predict error 0
  3505. dir: dir isL
  3506. |\-495: O: O989 (predict-yes)
  3507. I see 1 and I'm going to do: predict-yes
  3508. ENV: Agent did: predict-yes for direction L in state State-B
  3509. In State-B moving L
  3510. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  3511. predict error 0
  3512. dir: dir isL
  3513. /|\496: O: O992 (predict-no)
  3514. I see 1 and I'm going to do: predict-no
  3515. ENV: Agent did: predict-no for direction L in state State-A
  3516. In State-A moving L
  3517. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3518. predict error 0
  3519. dir: dir isL
  3520. -/|497: O: O994 (predict-no)
  3521. I see 1 and I'm going to do: predict-no
  3522. ENV: Agent did: predict-no for direction L in state State-A
  3523. In State-A moving L
  3524. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3525. predict error 0
  3526. dir: dir isL
  3527. \-/498: O: O996 (predict-no)
  3528. I see 1 and I'm going to do: predict-no
  3529. ENV: Agent did: predict-no for direction L in state State-A
  3530. In State-A moving L
  3531. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3532. predict error 0
  3533. dir: dir isU
  3534. |\-/499: O: O998 (predict-no)
  3535. I see 1 and I'm going to do: predict-no
  3536. ENV: Agent did: predict-no for direction U in state State-A
  3537. In State-A moving U
  3538. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3539. predict error 0
  3540. dir: dir isU
  3541. |\500: O: O1000 (predict-no)
  3542. I see 1 and I'm going to do: predict-no
  3543. ENV: Agent did: predict-no for direction U in state State-A
  3544. In State-A moving U
  3545. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3546. predict error 0
  3547. dir: dir isL
  3548. -/|\501: O: O1002 (predict-no)
  3549. I see 1 and I'm going to do: predict-no
  3550. ENV: Agent did: predict-no for direction L in state State-A
  3551. In State-A moving L
  3552. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3553. predict error 0
  3554. dir: dir isL
  3555. -502: O: O1004 (predict-no)
  3556. I see 1 and I'm going to do: predict-no
  3557. ENV: Agent did: predict-no for direction L in state State-A
  3558. In State-A moving L
  3559. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3560. predict error 0
  3561. dir: dir isR
  3562. /|\-503: O: O1005 (predict-yes)
  3563. I see 1 and I'm going to do: predict-yes
  3564. ENV: Agent did: predict-yes for direction R in state State-A
  3565. In State-A moving R
  3566. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  3567. predict error 0
  3568. dir: dir isU
  3569. /|504: O: O1008 (predict-no)
  3570. I see 1 and I'm going to do: predict-no
  3571. ENV: Agent did: predict-no for direction U in state State-B
  3572. In State-B moving U
  3573. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3574. predict error 0
  3575. dir: dir isU
  3576. \-505: O: O1010 (predict-no)
  3577. I see 1 and I'm going to do: predict-no
  3578. ENV: Agent did: predict-no for direction U in state State-B
  3579. In State-B moving U
  3580. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3581. predict error 0
  3582. dir: dir isU
  3583. /|\506: O: O1012 (predict-no)
  3584. I see 1 and I'm going to do: predict-no
  3585. ENV: Agent did: predict-no for direction U in state State-B
  3586. In State-B moving U
  3587. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3588. predict error 0
  3589. dir: dir isR
  3590. -/|507: O: O1014 (predict-no)
  3591. I see 1 and I'm going to do: predict-no
  3592. ENV: Agent did: predict-no for direction R in state State-B
  3593. In State-B moving R
  3594. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3595. predict error 0
  3596. dir: dir isL
  3597. \-/508: O: O1015 (predict-yes)
  3598. I see 1 and I'm going to do: predict-yes
  3599. ENV: Agent did: predict-yes for direction L in state State-B
  3600. In State-B moving L
  3601. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  3602. predict error 0
  3603. dir: dir isR
  3604. |\-509: O: O1017 (predict-yes)
  3605. I see 1 and I'm going to do: predict-yes
  3606. ENV: Agent did: predict-yes for direction R in state State-A
  3607. In State-A moving R
  3608. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  3609. predict error 0
  3610. dir: dir isL
  3611. /|\510: O: O1019 (predict-yes)
  3612. I see 1 and I'm going to do: predict-yes
  3613. ENV: Agent did: predict-yes for direction L in state State-B
  3614. In State-B moving L
  3615. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  3616. predict error 0
  3617. dir: dir isR
  3618. -/|511: O: O1021 (predict-yes)
  3619. I see 1 and I'm going to do: predict-yes
  3620. ENV: Agent did: predict-yes for direction R in state State-A
  3621. In State-A moving R
  3622. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  3623. predict error 0
  3624. dir: dir isR
  3625. \512: O: O1024 (predict-no)
  3626. I see 1 and I'm going to do: predict-no
  3627. ENV: Agent did: predict-no for direction R in state State-B
  3628. In State-B moving R
  3629. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3630. predict error 0
  3631. dir: dir isL
  3632. -/513: O: O1025 (predict-yes)
  3633. I see 1 and I'm going to do: predict-yes
  3634. ENV: Agent did: predict-yes for direction L in state State-B
  3635. In State-B moving L
  3636. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  3637. predict error 0
  3638. dir: dir isL
  3639. |\-514: O: O1028 (predict-no)
  3640. I see 1 and I'm going to do: predict-no
  3641. ENV: Agent did: predict-no for direction L in state State-A
  3642. In State-A moving L
  3643. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3644. predict error 0
  3645. dir: dir isU
  3646. /|\515: O: O1030 (predict-no)
  3647. I see 1 and I'm going to do: predict-no
  3648. ENV: Agent did: predict-no for direction U in state State-A
  3649. In State-A moving U
  3650. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3651. predict error 0
  3652. dir: dir isL
  3653. -/|516: O: O1032 (predict-no)
  3654. I see 1 and I'm going to do: predict-no
  3655. ENV: Agent did: predict-no for direction L in state State-A
  3656. In State-A moving L
  3657. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3658. predict error 0
  3659. dir: dir isU
  3660. \-517: O: O1034 (predict-no)
  3661. I see 1 and I'm going to do: predict-no
  3662. ENV: Agent did: predict-no for direction U in state State-A
  3663. In State-A moving U
  3664. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3665. predict error 0
  3666. dir: dir isU
  3667. /|\518: O: O1036 (predict-no)
  3668. I see 1 and I'm going to do: predict-no
  3669. ENV: Agent did: predict-no for direction U in state State-A
  3670. In State-A moving U
  3671. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3672. predict error 0
  3673. dir: dir isU
  3674. -/519: O: O1038 (predict-no)
  3675. I see 1 and I'm going to do: predict-no
  3676. ENV: Agent did: predict-no for direction U in state State-A
  3677. In State-A moving U
  3678. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3679. predict error 0
  3680. dir: dir isR
  3681. |\520: O: O1039 (predict-yes)
  3682. I see 1 and I'm going to do: predict-yes
  3683. ENV: Agent did: predict-yes for direction R in state State-A
  3684. In State-A moving R
  3685. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  3686. predict error 0
  3687. dir: dir isR
  3688. -/|521: O: O1042 (predict-no)
  3689. I see 1 and I'm going to do: predict-no
  3690. ENV: Agent did: predict-no for direction R in state State-B
  3691. In State-B moving R
  3692. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3693. predict error 0
  3694. dir: dir isR
  3695. \522: O: O1044 (predict-no)
  3696. I see 1 and I'm going to do: predict-no
  3697. ENV: Agent did: predict-no for direction R in state State-B
  3698. In State-B moving R
  3699. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3700. predict error 0
  3701. dir: dir isR
  3702. -/523: O: O1046 (predict-no)
  3703. I see 1 and I'm going to do: predict-no
  3704. ENV: Agent did: predict-no for direction R in state State-B
  3705. In State-B moving R
  3706. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3707. predict error 0
  3708. dir: dir isU
  3709. |\-524: O: O1048 (predict-no)
  3710. I see 1 and I'm going to do: predict-no
  3711. ENV: Agent did: predict-no for direction U in state State-B
  3712. In State-B moving U
  3713. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3714. predict error 0
  3715. dir: dir isU
  3716. /|\525: O: O1050 (predict-no)
  3717. I see 1 and I'm going to do: predict-no
  3718. ENV: Agent did: predict-no for direction U in state State-B
  3719. In State-B moving U
  3720. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3721. predict error 0
  3722. dir: dir isL
  3723. -/|526: O: O1051 (predict-yes)
  3724. I see 1 and I'm going to do: predict-yes
  3725. ENV: Agent did: predict-yes for direction L in state State-B
  3726. In State-B moving L
  3727. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  3728. predict error 0
  3729. dir: dir isU
  3730. \-/527: O: O1054 (predict-no)
  3731. I see 1 and I'm going to do: predict-no
  3732. ENV: Agent did: predict-no for direction U in state State-A
  3733. In State-A moving U
  3734. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3735. predict error 0
  3736. dir: dir isR
  3737. |\528: O: O1055 (predict-yes)
  3738. I see 1 and I'm going to do: predict-yes
  3739. ENV: Agent did: predict-yes for direction R in state State-A
  3740. In State-A moving R
  3741. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  3742. predict error 0
  3743. dir: dir isR
  3744. -529: O: O1058 (predict-no)
  3745. I see 1 and I'm going to do: predict-no
  3746. ENV: Agent did: predict-no for direction R in state State-B
  3747. In State-B moving R
  3748. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3749. predict error 0
  3750. dir: dir isU
  3751. /|530: O: O1060 (predict-no)
  3752. I see 1 and I'm going to do: predict-no
  3753. ENV: Agent did: predict-no for direction U in state State-B
  3754. In State-B moving U
  3755. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3756. predict error 0
  3757. dir: dir isL
  3758. \-/531: O: O1061 (predict-yes)
  3759. I see 1 and I'm going to do: predict-yes
  3760. ENV: Agent did: predict-yes for direction L in state State-B
  3761. In State-B moving L
  3762. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  3763. predict error 0
  3764. dir: dir isU
  3765. |532: O: O1064 (predict-no)
  3766. I see 1 and I'm going to do: predict-no
  3767. ENV: Agent did: predict-no for direction U in state State-A
  3768. In State-A moving U
  3769. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3770. predict error 0
  3771. dir: dir isR
  3772. \-/533: O: O1065 (predict-yes)
  3773. I see 1 and I'm going to do: predict-yes
  3774. ENV: Agent did: predict-yes for direction R in state State-A
  3775. In State-A moving R
  3776. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  3777. predict error 0
  3778. dir: dir isR
  3779. |\-534: O: O1068 (predict-no)
  3780. I see 1 and I'm going to do: predict-no
  3781. ENV: Agent did: predict-no for direction R in state State-B
  3782. In State-B moving R
  3783. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3784. predict error 0
  3785. dir: dir isR
  3786. /|\535: O: O1070 (predict-no)
  3787. I see 1 and I'm going to do: predict-no
  3788. ENV: Agent did: predict-no for direction R in state State-B
  3789. In State-B moving R
  3790. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3791. predict error 0
  3792. dir: dir isR
  3793. -/|536: O: O1072 (predict-no)
  3794. I see 1 and I'm going to do: predict-no
  3795. ENV: Agent did: predict-no for direction R in state State-B
  3796. In State-B moving R
  3797. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3798. predict error 0
  3799. dir: dir isL
  3800. \-537: O: O1073 (predict-yes)
  3801. I see 1 and I'm going to do: predict-yes
  3802. ENV: Agent did: predict-yes for direction L in state State-B
  3803. In State-B moving L
  3804. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  3805. predict error 0
  3806. dir: dir isR
  3807. /|\538: O: O1075 (predict-yes)
  3808. I see 1 and I'm going to do: predict-yes
  3809. ENV: Agent did: predict-yes for direction R in state State-A
  3810. In State-A moving R
  3811. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  3812. predict error 0
  3813. dir: dir isL
  3814. -539: O: O1077 (predict-yes)
  3815. I see 1 and I'm going to do: predict-yes
  3816. ENV: Agent did: predict-yes for direction L in state State-B
  3817. In State-B moving L
  3818. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  3819. predict error 0
  3820. dir: dir isR
  3821. /|\540: O: O1079 (predict-yes)
  3822. I see 1 and I'm going to do: predict-yes
  3823. ENV: Agent did: predict-yes for direction R in state State-A
  3824. In State-A moving R
  3825. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  3826. predict error 0
  3827. dir: dir isR
  3828. -/541: O: O1082 (predict-no)
  3829. I see 1 and I'm going to do: predict-no
  3830. ENV: Agent did: predict-no for direction R in state State-B
  3831. In State-B moving R
  3832. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3833. predict error 0
  3834. dir: dir isR
  3835. |542: O: O1084 (predict-no)
  3836. I see 1 and I'm going to do: predict-no
  3837. ENV: Agent did: predict-no for direction R in state State-B
  3838. In State-B moving R
  3839. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3840. predict error 0
  3841. dir: dir isR
  3842. \-543: O: O1086 (predict-no)
  3843. I see 1 and I'm going to do: predict-no
  3844. ENV: Agent did: predict-no for direction R in state State-B
  3845. In State-B moving R
  3846. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3847. predict error 0
  3848. dir: dir isU
  3849. /544: O: O1088 (predict-no)
  3850. I see 1 and I'm going to do: predict-no
  3851. ENV: Agent did: predict-no for direction U in state State-B
  3852. In State-B moving U
  3853. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3854. predict error 0
  3855. dir: dir isU
  3856. |\545: O: O1090 (predict-no)
  3857. I see 1 and I'm going to do: predict-no
  3858. ENV: Agent did: predict-no for direction U in state State-B
  3859. In State-B moving U
  3860. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3861. predict error 0
  3862. dir: dir isL
  3863. -/|546: O: O1091 (predict-yes)
  3864. I see 1 and I'm going to do: predict-yes
  3865. ENV: Agent did: predict-yes for direction L in state State-B
  3866. In State-B moving L
  3867. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  3868. predict error 0
  3869. dir: dir isU
  3870. \-/547: O: O1094 (predict-no)
  3871. I see 1 and I'm going to do: predict-no
  3872. ENV: Agent did: predict-no for direction U in state State-A
  3873. In State-A moving U
  3874. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3875. predict error 0
  3876. dir: dir isR
  3877. |\-548: O: O1095 (predict-yes)
  3878. I see 1 and I'm going to do: predict-yes
  3879. ENV: Agent did: predict-yes for direction R in state State-A
  3880. In State-A moving R
  3881. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  3882. predict error 0
  3883. dir: dir isL
  3884. /|\549: O: O1097 (predict-yes)
  3885. I see 1 and I'm going to do: predict-yes
  3886. ENV: Agent did: predict-yes for direction L in state State-B
  3887. In State-B moving L
  3888. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  3889. predict error 0
  3890. dir: dir isR
  3891. -/|550: O: O1099 (predict-yes)
  3892. I see 1 and I'm going to do: predict-yes
  3893. ENV: Agent did: predict-yes for direction R in state State-A
  3894. In State-A moving R
  3895. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  3896. predict error 0
  3897. dir: dir isL
  3898. \-/551: O: O1101 (predict-yes)
  3899. I see 1 and I'm going to do: predict-yes
  3900. ENV: Agent did: predict-yes for direction L in state State-B
  3901. In State-B moving L
  3902. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  3903. predict error 0
  3904. dir: dir isL
  3905. |552: O: O1104 (predict-no)
  3906. I see 1 and I'm going to do: predict-no
  3907. ENV: Agent did: predict-no for direction L in state State-A
  3908. In State-A moving L
  3909. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3910. predict error 0
  3911. dir: dir isR
  3912. \-553: O: O1105 (predict-yes)
  3913. I see 1 and I'm going to do: predict-yes
  3914. ENV: Agent did: predict-yes for direction R in state State-A
  3915. In State-A moving R
  3916. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  3917. predict error 0
  3918. dir: dir isU
  3919. /|\554: O: O1108 (predict-no)
  3920. I see 1 and I'm going to do: predict-no
  3921. ENV: Agent did: predict-no for direction U in state State-B
  3922. In State-B moving U
  3923. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3924. predict error 0
  3925. dir: dir isL
  3926. -555: O: O1109 (predict-yes)
  3927. I see 1 and I'm going to do: predict-yes
  3928. ENV: Agent did: predict-yes for direction L in state State-B
  3929. In State-B moving L
  3930. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  3931. predict error 0
  3932. dir: dir isU
  3933. /|\556: O: O1112 (predict-no)
  3934. I see 1 and I'm going to do: predict-no
  3935. ENV: Agent did: predict-no for direction U in state State-A
  3936. In State-A moving U
  3937. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3938. predict error 0
  3939. dir: dir isU
  3940. -/|557: O: O1114 (predict-no)
  3941. I see 1 and I'm going to do: predict-no
  3942. ENV: Agent did: predict-no for direction U in state State-A
  3943. In State-A moving U
  3944. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3945. predict error 0
  3946. dir: dir isL
  3947. \-/558: O: O1116 (predict-no)
  3948. I see 1 and I'm going to do: predict-no
  3949. ENV: Agent did: predict-no for direction L in state State-A
  3950. In State-A moving L
  3951. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3952. predict error 0
  3953. dir: dir isU
  3954. |\-559: O: O1118 (predict-no)
  3955. I see 1 and I'm going to do: predict-no
  3956. ENV: Agent did: predict-no for direction U in state State-A
  3957. In State-A moving U
  3958. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3959. predict error 0
  3960. dir: dir isR
  3961. /|\560: O: O1119 (predict-yes)
  3962. I see 1 and I'm going to do: predict-yes
  3963. ENV: Agent did: predict-yes for direction R in state State-A
  3964. In State-A moving R
  3965. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  3966. predict error 0
  3967. dir: dir isU
  3968. -/|\561: O: O1122 (predict-no)
  3969. I see 1 and I'm going to do: predict-no
  3970. ENV: Agent did: predict-no for direction U in state State-B
  3971. In State-B moving U
  3972. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3973. predict error 0
  3974. dir: dir isU
  3975. -562: O: O1124 (predict-no)
  3976. I see 1 and I'm going to do: predict-no
  3977. ENV: Agent did: predict-no for direction U in state State-B
  3978. In State-B moving U
  3979. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3980. predict error 0
  3981. dir: dir isU
  3982. /|563: O: O1126 (predict-no)
  3983. I see 1 and I'm going to do: predict-no
  3984. ENV: Agent did: predict-no for direction U in state State-B
  3985. In State-B moving U
  3986. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3987. predict error 0
  3988. dir: dir isR
  3989. \-/564: O: O1128 (predict-no)
  3990. I see 1 and I'm going to do: predict-no
  3991. ENV: Agent did: predict-no for direction R in state State-B
  3992. In State-B moving R
  3993. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3994. predict error 0
  3995. dir: dir isU
  3996. |\565: O: O1130 (predict-no)
  3997. I see 1 and I'm going to do: predict-no
  3998. ENV: Agent did: predict-no for direction U in state State-B
  3999. In State-B moving U
  4000. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4001. predict error 0
  4002. dir: dir isU
  4003. -/|566: O: O1132 (predict-no)
  4004. I see 1 and I'm going to do: predict-no
  4005. ENV: Agent did: predict-no for direction U in state State-B
  4006. In State-B moving U
  4007. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4008. predict error 0
  4009. dir: dir isU
  4010. \-/567: O: O1134 (predict-no)
  4011. I see 1 and I'm going to do: predict-no
  4012. ENV: Agent did: predict-no for direction U in state State-B
  4013. In State-B moving U
  4014. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4015. predict error 0
  4016. dir: dir isR
  4017. |\-568: O: O1136 (predict-no)
  4018. I see 1 and I'm going to do: predict-no
  4019. ENV: Agent did: predict-no for direction R in state State-B
  4020. In State-B moving R
  4021. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4022. predict error 0
  4023. dir: dir isU
  4024. /|\569: O: O1138 (predict-no)
  4025. I see 1 and I'm going to do: predict-no
  4026. ENV: Agent did: predict-no for direction U in state State-B
  4027. In State-B moving U
  4028. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4029. predict error 0
  4030. dir: dir isR
  4031. -/|570: O: O1140 (predict-no)
  4032. I see 1 and I'm going to do: predict-no
  4033. ENV: Agent did: predict-no for direction R in state State-B
  4034. In State-B moving R
  4035. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4036. predict error 0
  4037. dir: dir isL
  4038. \571: O: O1141 (predict-yes)
  4039. I see 1 and I'm going to do: predict-yes
  4040. ENV: Agent did: predict-yes for direction L in state State-B
  4041. In State-B moving L
  4042. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  4043. predict error 0
  4044. dir: dir isL
  4045. -572: O: O1144 (predict-no)
  4046. I see 1 and I'm going to do: predict-no
  4047. ENV: Agent did: predict-no for direction L in state State-A
  4048. In State-A moving L
  4049. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4050. predict error 0
  4051. dir: dir isL
  4052. /|\573: O: O1146 (predict-no)
  4053. I see 1 and I'm going to do: predict-no
  4054. ENV: Agent did: predict-no for direction L in state State-A
  4055. In State-A moving L
  4056. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4057. predict error 0
  4058. dir: dir isL
  4059. -/|574: O: O1148 (predict-no)
  4060. I see 1 and I'm going to do: predict-no
  4061. ENV: Agent did: predict-no for direction L in state State-A
  4062. In State-A moving L
  4063. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4064. predict error 0
  4065. dir: dir isL
  4066. \-/575: O: O1150 (predict-no)
  4067. I see 1 and I'm going to do: predict-no
  4068. ENV: Agent did: predict-no for direction L in state State-A
  4069. In State-A moving L
  4070. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4071. predict error 0
  4072. dir: dir isR
  4073. |\-576: O: O1151 (predict-yes)
  4074. I see 1 and I'm going to do: predict-yes
  4075. ENV: Agent did: predict-yes for direction R in state State-A
  4076. In State-A moving R
  4077. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  4078. predict error 0
  4079. dir: dir isU
  4080. /|\577: O: O1154 (predict-no)
  4081. I see 1 and I'm going to do: predict-no
  4082. ENV: Agent did: predict-no for direction U in state State-B
  4083. In State-B moving U
  4084. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4085. predict error 0
  4086. dir: dir isR
  4087. -/578: O: O1156 (predict-no)
  4088. I see 1 and I'm going to do: predict-no
  4089. ENV: Agent did: predict-no for direction R in state State-B
  4090. In State-B moving R
  4091. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4092. predict error 0
  4093. dir: dir isR
  4094. |\-579: O: O1158 (predict-no)
  4095. I see 1 and I'm going to do: predict-no
  4096. ENV: Agent did: predict-no for direction R in state State-B
  4097. In State-B moving R
  4098. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4099. predict error 0
  4100. dir: dir isR
  4101. /|\580: O: O1160 (predict-no)
  4102. I see 1 and I'm going to do: predict-no
  4103. ENV: Agent did: predict-no for direction R in state State-B
  4104. In State-B moving R
  4105. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4106. predict error 0
  4107. dir: dir isL
  4108. -/581: O: O1161 (predict-yes)
  4109. I see 1 and I'm going to do: predict-yes
  4110. ENV: Agent did: predict-yes for direction L in state State-B
  4111. In State-B moving L
  4112. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  4113. predict error 0
  4114. dir: dir isR
  4115. |582: O: O1163 (predict-yes)
  4116. I see 1 and I'm going to do: predict-yes
  4117. ENV: Agent did: predict-yes for direction R in state State-A
  4118. In State-A moving R
  4119. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  4120. predict error 0
  4121. dir: dir isU
  4122. \-583: O: O1166 (predict-no)
  4123. I see 1 and I'm going to do: predict-no
  4124. ENV: Agent did: predict-no for direction U in state State-B
  4125. In State-B moving U
  4126. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4127. predict error 0
  4128. dir: dir isR
  4129. /|\584: O: O1168 (predict-no)
  4130. I see 1 and I'm going to do: predict-no
  4131. ENV: Agent did: predict-no for direction R in state State-B
  4132. In State-B moving R
  4133. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4134. predict error 0
  4135. dir: dir isL
  4136. -/|\585: O: O1169 (predict-yes)
  4137. I see 1 and I'm going to do: predict-yes
  4138. ENV: Agent did: predict-yes for direction L in state State-B
  4139. In State-B moving L
  4140. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  4141. predict error 0
  4142. dir: dir isU
  4143. -/|586: O: O1172 (predict-no)
  4144. I see 1 and I'm going to do: predict-no
  4145. ENV: Agent did: predict-no for direction U in state State-A
  4146. In State-A moving U
  4147. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4148. predict error 0
  4149. dir: dir isU
  4150. \-/587: O: O1174 (predict-no)
  4151. I see 1 and I'm going to do: predict-no
  4152. ENV: Agent did: predict-no for direction U in state State-A
  4153. In State-A moving U
  4154. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4155. predict error 0
  4156. dir: dir isR
  4157. |\-588: O: O1175 (predict-yes)
  4158. I see 1 and I'm going to do: predict-yes
  4159. ENV: Agent did: predict-yes for direction R in state State-A
  4160. In State-A moving R
  4161. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  4162. predict error 0
  4163. dir: dir isR
  4164. /|\589: O: O1178 (predict-no)
  4165. I see 1 and I'm going to do: predict-no
  4166. ENV: Agent did: predict-no for direction R in state State-B
  4167. In State-B moving R
  4168. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4169. predict error 0
  4170. dir: dir isR
  4171. -/|590: O: O1180 (predict-no)
  4172. I see 1 and I'm going to do: predict-no
  4173. ENV: Agent did: predict-no for direction R in state State-B
  4174. In State-B moving R
  4175. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4176. predict error 0
  4177. dir: dir isR
  4178. \-591: O: O1182 (predict-no)
  4179. I see 1 and I'm going to do: predict-no
  4180. ENV: Agent did: predict-no for direction R in state State-B
  4181. In State-B moving R
  4182. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4183. predict error 0
  4184. dir: dir isL
  4185. /592: O: O1183 (predict-yes)
  4186. I see 1 and I'm going to do: predict-yes
  4187. ENV: Agent did: predict-yes for direction L in state State-B
  4188. In State-B moving L
  4189. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  4190. predict error 0
  4191. dir: dir isL
  4192. |\-593: O: O1186 (predict-no)
  4193. I see 1 and I'm going to do: predict-no
  4194. ENV: Agent did: predict-no for direction L in state State-A
  4195. In State-A moving L
  4196. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4197. predict error 0
  4198. dir: dir isL
  4199. /|\-594: O: O1188 (predict-no)
  4200. I see 1 and I'm going to do: predict-no
  4201. ENV: Agent did: predict-no for direction L in state State-A
  4202. In State-A moving L
  4203. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4204. predict error 0
  4205. dir: dir isU
  4206. /|595: O: O1190 (predict-no)
  4207. I see 1 and I'm going to do: predict-no
  4208. ENV: Agent did: predict-no for direction U in state State-A
  4209. In State-A moving U
  4210. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4211. predict error 0
  4212. dir: dir isL
  4213. \-/596: O: O1192 (predict-no)
  4214. I see 1 and I'm going to do: predict-no
  4215. ENV: Agent did: predict-no for direction L in state State-A
  4216. In State-A moving L
  4217. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4218. predict error 0
  4219. dir: dir isR
  4220. |\-597: O: O1193 (predict-yes)
  4221. I see 1 and I'm going to do: predict-yes
  4222. ENV: Agent did: predict-yes for direction R in state State-A
  4223. In State-A moving R
  4224. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  4225. predict error 0
  4226. dir: dir isL
  4227. /|\598: O: O1195 (predict-yes)
  4228. I see 1 and I'm going to do: predict-yes
  4229. ENV: Agent did: predict-yes for direction L in state State-B
  4230. In State-B moving L
  4231. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  4232. predict error 0
  4233. dir: dir isL
  4234. -/|599: O: O1198 (predict-no)
  4235. I see 1 and I'm going to do: predict-no
  4236. ENV: Agent did: predict-no for direction L in state State-A
  4237. In State-A moving L
  4238. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4239. predict error 0
  4240. dir: dir isL
  4241. \-600: O: O1200 (predict-no)
  4242. I see 1 and I'm going to do: predict-no
  4243. ENV: Agent did: predict-no for direction L in state State-A
  4244. In State-A moving L
  4245. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4246. predict error 0
  4247. dir: dir isR
  4248. /|\601: O: O1201 (predict-yes)
  4249. I see 1 and I'm going to do: predict-yes
  4250. ENV: Agent did: predict-yes for direction R in state State-A
  4251. In State-A moving R
  4252. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  4253. predict error 0
  4254. dir: dir isL
  4255. -602: O: O1203 (predict-yes)
  4256. I see 1 and I'm going to do: predict-yes
  4257. ENV: Agent did: predict-yes for direction L in state State-B
  4258. In State-B moving L
  4259. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  4260. predict error 0
  4261. dir: dir isL
  4262. /|\-603: O: O1206 (predict-no)
  4263. I see 1 and I'm going to do: predict-no
  4264. ENV: Agent did: predict-no for direction L in state State-A
  4265. In State-A moving L
  4266. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4267. predict error 0
  4268. dir: dir isL
  4269. /|604: O: O1208 (predict-no)
  4270. I see 1 and I'm going to do: predict-no
  4271. ENV: Agent did: predict-no for direction L in state State-A
  4272. In State-A moving L
  4273. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4274. predict error 0
  4275. dir: dir isL
  4276. \-/605: O: O1210 (predict-no)
  4277. I see 1 and I'm going to do: predict-no
  4278. ENV: Agent did: predict-no for direction L in state State-A
  4279. In State-A moving L
  4280. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4281. predict error 0
  4282. dir: dir isR
  4283. |\-/606: O: O1211 (predict-yes)
  4284. I see 1 and I'm going to do: predict-yes
  4285. ENV: Agent did: predict-yes for direction R in state State-A
  4286. In State-A moving R
  4287. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  4288. predict error 0
  4289. dir: dir isL
  4290. |\607: O: O1213 (predict-yes)
  4291. I see 1 and I'm going to do: predict-yes
  4292. ENV: Agent did: predict-yes for direction L in state State-B
  4293. In State-B moving L
  4294. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  4295. predict error 0
  4296. dir: dir isL
  4297. -/|608: O: O1216 (predict-no)
  4298. I see 1 and I'm going to do: predict-no
  4299. ENV: Agent did: predict-no for direction L in state State-A
  4300. In State-A moving L
  4301. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4302. predict error 0
  4303. dir: dir isR
  4304. \-/609: O: O1217 (predict-yes)
  4305. I see 1 and I'm going to do: predict-yes
  4306. ENV: Agent did: predict-yes for direction R in state State-A
  4307. In State-A moving R
  4308. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  4309. predict error 0
  4310. dir: dir isR
  4311. |\610: O: O1220 (predict-no)
  4312. I see 1 and I'm going to do: predict-no
  4313. ENV: Agent did: predict-no for direction R in state State-B
  4314. In State-B moving R
  4315. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4316. predict error 0
  4317. dir: dir isU
  4318. -/|611: O: O1222 (predict-no)
  4319. I see 1 and I'm going to do: predict-no
  4320. ENV: Agent did: predict-no for direction U in state State-B
  4321. In State-B moving U
  4322. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4323. predict error 0
  4324. dir: dir isL
  4325. \612: O: O1223 (predict-yes)
  4326. I see 1 and I'm going to do: predict-yes
  4327. ENV: Agent did: predict-yes for direction L in state State-B
  4328. In State-B moving L
  4329. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  4330. predict error 0
  4331. dir: dir isR
  4332. -/|613: O: O1225 (predict-yes)
  4333. I see 1 and I'm going to do: predict-yes
  4334. ENV: Agent did: predict-yes for direction R in state State-A
  4335. In State-A moving R
  4336. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  4337. predict error 0
  4338. dir: dir isR
  4339. \-/614: O: O1228 (predict-no)
  4340. I see 1 and I'm going to do: predict-no
  4341. ENV: Agent did: predict-no for direction R in state State-B
  4342. In State-B moving R
  4343. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4344. predict error 0
  4345. dir: dir isL
  4346. |\-615: O: O1229 (predict-yes)
  4347. I see 1 and I'm going to do: predict-yes
  4348. ENV: Agent did: predict-yes for direction L in state State-B
  4349. In State-B moving L
  4350. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  4351. predict error 0
  4352. dir: dir isU
  4353. /|\616: O: O1232 (predict-no)
  4354. I see 1 and I'm going to do: predict-no
  4355. ENV: Agent did: predict-no for direction U in state State-A
  4356. In State-A moving U
  4357. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4358. predict error 0
  4359. dir: dir isL
  4360. -/|617: O: O1234 (predict-no)
  4361. I see 1 and I'm going to do: predict-no
  4362. ENV: Agent did: predict-no for direction L in state State-A
  4363. In State-A moving L
  4364. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4365. predict error 0
  4366. dir: dir isL
  4367. \-618: O: O1236 (predict-no)
  4368. I see 1 and I'm going to do: predict-no
  4369. ENV: Agent did: predict-no for direction L in state State-A
  4370. In State-A moving L
  4371. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4372. predict error 0
  4373. dir: dir isR
  4374. /|619: O: O1237 (predict-yes)
  4375. I see 1 and I'm going to do: predict-yes
  4376. ENV: Agent did: predict-yes for direction R in state State-A
  4377. In State-A moving R
  4378. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  4379. predict error 0
  4380. dir: dir isL
  4381. \-/620: O: O1239 (predict-yes)
  4382. I see 1 and I'm going to do: predict-yes
  4383. ENV: Agent did: predict-yes for direction L in state State-B
  4384. In State-B moving L
  4385. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  4386. predict error 0
  4387. dir: dir isR
  4388. |\-621: O: O1241 (predict-yes)
  4389. I see 1 and I'm going to do: predict-yes
  4390. ENV: Agent did: predict-yes for direction R in state State-A
  4391. In State-A moving R
  4392. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  4393. predict error 0
  4394. dir: dir isR
  4395. /622: O: O1244 (predict-no)
  4396. I see 1 and I'm going to do: predict-no
  4397. ENV: Agent did: predict-no for direction R in state State-B
  4398. In State-B moving R
  4399. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4400. predict error 0
  4401. dir: dir isL
  4402. |\623: O: O1245 (predict-yes)
  4403. I see 1 and I'm going to do: predict-yes
  4404. ENV: Agent did: predict-yes for direction L in state State-B
  4405. In State-B moving L
  4406. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  4407. predict error 0
  4408. dir: dir isL
  4409. -/624: O: O1248 (predict-no)
  4410. I see 1 and I'm going to do: predict-no
  4411. ENV: Agent did: predict-no for direction L in state State-A
  4412. In State-A moving L
  4413. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4414. predict error 0
  4415. dir: dir isU
  4416. |\625: O: O1250 (predict-no)
  4417. I see 1 and I'm going to do: predict-no
  4418. ENV: Agent did: predict-no for direction U in state State-A
  4419. In State-A moving U
  4420. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4421. predict error 0
  4422. dir: dir isL
  4423. -/|626: O: O1252 (predict-no)
  4424. I see 1 and I'm going to do: predict-no
  4425. ENV: Agent did: predict-no for direction L in state State-A
  4426. In State-A moving L
  4427. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4428. predict error 0
  4429. dir: dir isU
  4430. \-627: O: O1254 (predict-no)
  4431. I see 1 and I'm going to do: predict-no
  4432. ENV: Agent did: predict-no for direction U in state State-A
  4433. In State-A moving U
  4434. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4435. predict error 0
  4436. dir: dir isR
  4437. /|\628: O: O1255 (predict-yes)
  4438. I see 1 and I'm going to do: predict-yes
  4439. ENV: Agent did: predict-yes for direction R in state State-A
  4440. In State-A moving R
  4441. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  4442. predict error 0
  4443. dir: dir isU
  4444. -/|\629: O: O1258 (predict-no)
  4445. I see 1 and I'm going to do: predict-no
  4446. ENV: Agent did: predict-no for direction U in state State-B
  4447. In State-B moving U
  4448. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4449. predict error 0
  4450. dir: dir isL
  4451. -/630: O: O1259 (predict-yes)
  4452. I see 1 and I'm going to do: predict-yes
  4453. ENV: Agent did: predict-yes for direction L in state State-B
  4454. In State-B moving L
  4455. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  4456. predict error 0
  4457. dir: dir isL
  4458. |\631: O: O1262 (predict-no)
  4459. I see 1 and I'm going to do: predict-no
  4460. ENV: Agent did: predict-no for direction L in state State-A
  4461. In State-A moving L
  4462. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4463. predict error 0
  4464. dir: dir isL
  4465. -632: O: O1264 (predict-no)
  4466. I see 1 and I'm going to do: predict-no
  4467. ENV: Agent did: predict-no for direction L in state State-A
  4468. In State-A moving L
  4469. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4470. predict error 0
  4471. dir: dir isU
  4472. /|\633: O: O1266 (predict-no)
  4473. I see 1 and I'm going to do: predict-no
  4474. ENV: Agent did: predict-no for direction U in state State-A
  4475. In State-A moving U
  4476. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4477. predict error 0
  4478. dir: dir isR
  4479. -/|\634: O: O1267 (predict-yes)
  4480. I see 1 and I'm going to do: predict-yes
  4481. ENV: Agent did: predict-yes for direction R in state State-A
  4482. In State-A moving R
  4483. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  4484. predict error 0
  4485. dir: dir isR
  4486. -/|\635: O: O1270 (predict-no)
  4487. I see 1 and I'm going to do: predict-no
  4488. ENV: Agent did: predict-no for direction R in state State-B
  4489. In State-B moving R
  4490. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4491. predict error 0
  4492. dir: dir isL
  4493. -/636: O: O1271 (predict-yes)
  4494. I see 1 and I'm going to do: predict-yes
  4495. ENV: Agent did: predict-yes for direction L in state State-B
  4496. In State-B moving L
  4497. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  4498. predict error 0
  4499. dir: dir isU
  4500. |\-637: O: O1274 (predict-no)
  4501. I see 1 and I'm going to do: predict-no
  4502. ENV: Agent did: predict-no for direction U in state State-A
  4503. In State-A moving U
  4504. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4505. predict error 0
  4506. dir: dir isU
  4507. /|638: O: O1276 (predict-no)
  4508. I see 1 and I'm going to do: predict-no
  4509. ENV: Agent did: predict-no for direction U in state State-A
  4510. In State-A moving U
  4511. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4512. predict error 0
  4513. dir: dir isR
  4514. \-/639: O: O1277 (predict-yes)
  4515. I see 1 and I'm going to do: predict-yes
  4516. ENV: Agent did: predict-yes for direction R in state State-A
  4517. In State-A moving R
  4518. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  4519. predict error 0
  4520. dir: dir isL
  4521. |\-640: O: O1279 (predict-yes)
  4522. I see 1 and I'm going to do: predict-yes
  4523. ENV: Agent did: predict-yes for direction L in state State-B
  4524. In State-B moving L
  4525. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  4526. predict error 0
  4527. dir: dir isL
  4528. /|\641: O: O1282 (predict-no)
  4529. I see 1 and I'm going to do: predict-no
  4530. ENV: Agent did: predict-no for direction L in state State-A
  4531. In State-A moving L
  4532. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4533. predict error 0
  4534. dir: dir isL
  4535. -642: O: O1284 (predict-no)
  4536. I see 1 and I'm going to do: predict-no
  4537. ENV: Agent did: predict-no for direction L in state State-A
  4538. In State-A moving L
  4539. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4540. predict error 0
  4541. dir: dir isL
  4542. /|\643: O: O1286 (predict-no)
  4543. I see 1 and I'm going to do: predict-no
  4544. ENV: Agent did: predict-no for direction L in state State-A
  4545. In State-A moving L
  4546. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4547. predict error 0
  4548. dir: dir isL
  4549. -/644: O: O1288 (predict-no)
  4550. I see 1 and I'm going to do: predict-no
  4551. ENV: Agent did: predict-no for direction L in state State-A
  4552. In State-A moving L
  4553. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4554. predict error 0
  4555. dir: dir isL
  4556. |\-645: O: O1290 (predict-no)
  4557. I see 1 and I'm going to do: predict-no
  4558. ENV: Agent did: predict-no for direction L in state State-A
  4559. In State-A moving L
  4560. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4561. predict error 0
  4562. dir: dir isR
  4563. /|\646: O: O1291 (predict-yes)
  4564. I see 1 and I'm going to do: predict-yes
  4565. ENV: Agent did: predict-yes for direction R in state State-A
  4566. In State-A moving R
  4567. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  4568. predict error 0
  4569. dir: dir isU
  4570. -/|647: O: O1294 (predict-no)
  4571. I see 1 and I'm going to do: predict-no
  4572. ENV: Agent did: predict-no for direction U in state State-B
  4573. In State-B moving U
  4574. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4575. predict error 0
  4576. dir: dir isL
  4577. \-/648: O: O1295 (predict-yes)
  4578. I see 1 and I'm going to do: predict-yes
  4579. ENV: Agent did: predict-yes for direction L in state State-B
  4580. In State-B moving L
  4581. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  4582. predict error 0
  4583. dir: dir isU
  4584. |\-649: O: O1298 (predict-no)
  4585. I see 1 and I'm going to do: predict-no
  4586. ENV: Agent did: predict-no for direction U in state State-A
  4587. In State-A moving U
  4588. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4589. predict error 0
  4590. dir: dir isR
  4591. /|\650: O: O1299 (predict-yes)
  4592. I see 1 and I'm going to do: predict-yes
  4593. ENV: Agent did: predict-yes for direction R in state State-A
  4594. In State-A moving R
  4595. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  4596. predict error 0
  4597. dir: dir isU
  4598. -/|651: O: O1302 (predict-no)
  4599. I see 1 and I'm going to do: predict-no
  4600. ENV: Agent did: predict-no for direction U in state State-B
  4601. In State-B moving U
  4602. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4603. predict error 0
  4604. dir: dir isU
  4605. \652: O: O1304 (predict-no)
  4606. I see 1 and I'm going to do: predict-no
  4607. ENV: Agent did: predict-no for direction U in state State-B
  4608. In State-B moving U
  4609. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4610. predict error 0
  4611. dir: dir isU
  4612. -/653: O: O1306 (predict-no)
  4613. I see 1 and I'm going to do: predict-no
  4614. ENV: Agent did: predict-no for direction U in state State-B
  4615. In State-B moving U
  4616. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4617. predict error 0
  4618. dir: dir isL
  4619. |\654: O: O1307 (predict-yes)
  4620. I see 1 and I'm going to do: predict-yes
  4621. ENV: Agent did: predict-yes for direction L in state State-B
  4622. In State-B moving L
  4623. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  4624. predict error 0
  4625. dir: dir isL
  4626. -/655: O: O1310 (predict-no)
  4627. I see 1 and I'm going to do: predict-no
  4628. ENV: Agent did: predict-no for direction L in state State-A
  4629. In State-A moving L
  4630. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4631. predict error 0
  4632. dir: dir isR
  4633. |656: O: O1311 (predict-yes)
  4634. I see 1 and I'm going to do: predict-yes
  4635. ENV: Agent did: predict-yes for direction R in state State-A
  4636. In State-A moving R
  4637. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  4638. predict error 0
  4639. dir: dir isU
  4640. \-/657: O: O1314 (predict-no)
  4641. I see 1 and I'm going to do: predict-no
  4642. ENV: Agent did: predict-no for direction U in state State-B
  4643. In State-B moving U
  4644. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4645. predict error 0
  4646. dir: dir isL
  4647. |\-658: O: O1315 (predict-yes)
  4648. I see 1 and I'm going to do: predict-yes
  4649. ENV: Agent did: predict-yes for direction L in state State-B
  4650. In State-B moving L
  4651. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  4652. predict error 0
  4653. dir: dir isL
  4654. /|\659: O: O1318 (predict-no)
  4655. I see 1 and I'm going to do: predict-no
  4656. ENV: Agent did: predict-no for direction L in state State-A
  4657. In State-A moving L
  4658. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4659. predict error 0
  4660. dir: dir isU
  4661. -/|660: O: O1320 (predict-no)
  4662. I see 1 and I'm going to do: predict-no
  4663. ENV: Agent did: predict-no for direction U in state State-A
  4664. In State-A moving U
  4665. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4666. predict error 0
  4667. dir: dir isL
  4668. \-/661: O: O1322 (predict-no)
  4669. I see 1 and I'm going to do: predict-no
  4670. ENV: Agent did: predict-no for direction L in state State-A
  4671. In State-A moving L
  4672. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4673. predict error 0
  4674. dir: dir isR
  4675. |662: O: O1323 (predict-yes)
  4676. I see 1 and I'm going to do: predict-yes
  4677. ENV: Agent did: predict-yes for direction R in state State-A
  4678. In State-A moving R
  4679. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  4680. predict error 0
  4681. dir: dir isR
  4682. \-/663: O: O1326 (predict-no)
  4683. I see 1 and I'm going to do: predict-no
  4684. ENV: Agent did: predict-no for direction R in state State-B
  4685. In State-B moving R
  4686. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4687. predict error 0
  4688. dir: dir isU
  4689. |664: O: O1328 (predict-no)
  4690. I see 1 and I'm going to do: predict-no
  4691. ENV: Agent did: predict-no for direction U in state State-B
  4692. In State-B moving U
  4693. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4694. predict error 0
  4695. dir: dir isU
  4696. \-/665: O: O1330 (predict-no)
  4697. I see 1 and I'm going to do: predict-no
  4698. ENV: Agent did: predict-no for direction U in state State-B
  4699. In State-B moving U
  4700. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4701. predict error 0
  4702. dir: dir isL
  4703. |666: O: O1331 (predict-yes)
  4704. I see 1 and I'm going to do: predict-yes
  4705. ENV: Agent did: predict-yes for direction L in state State-B
  4706. In State-B moving L
  4707. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  4708. predict error 0
  4709. dir: dir isU
  4710. \-/667: O: O1334 (predict-no)
  4711. I see 1 and I'm going to do: predict-no
  4712. ENV: Agent did: predict-no for direction U in state State-A
  4713. In State-A moving U
  4714. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4715. predict error 0
  4716. dir: dir isU
  4717. |\668: O: O1336 (predict-no)
  4718. I see 1 and I'm going to do: predict-no
  4719. ENV: Agent did: predict-no for direction U in state State-A
  4720. In State-A moving U
  4721. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4722. predict error 0
  4723. dir: dir isU
  4724. -669: O: O1338 (predict-no)
  4725. I see 1 and I'm going to do: predict-no
  4726. ENV: Agent did: predict-no for direction U in state State-A
  4727. In State-A moving U
  4728. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4729. predict error 0
  4730. dir: dir isR
  4731. /|\670: O: O1339 (predict-yes)
  4732. I see 1 and I'm going to do: predict-yes
  4733. ENV: Agent did: predict-yes for direction R in state State-A
  4734. In State-A moving R
  4735. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  4736. predict error 0
  4737. dir: dir isU
  4738. -/|671: O: O1342 (predict-no)
  4739. I see 1 and I'm going to do: predict-no
  4740. ENV: Agent did: predict-no for direction U in state State-B
  4741. In State-B moving U
  4742. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4743. predict error 0
  4744. dir: dir isR
  4745. \672: O: O1344 (predict-no)
  4746. I see 1 and I'm going to do: predict-no
  4747. ENV: Agent did: predict-no for direction R in state State-B
  4748. In State-B moving R
  4749. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4750. predict error 0
  4751. dir: dir isR
  4752. -/|673: O: O1346 (predict-no)
  4753. I see 1 and I'm going to do: predict-no
  4754. ENV: Agent did: predict-no for direction R in state State-B
  4755. In State-B moving R
  4756. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4757. predict error 0
  4758. dir: dir isL
  4759. \-/674: O: O1347 (predict-yes)
  4760. I see 1 and I'm going to do: predict-yes
  4761. ENV: Agent did: predict-yes for direction L in state State-B
  4762. In State-B moving L
  4763. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  4764. predict error 0
  4765. dir: dir isU
  4766. |\-675: O: O1350 (predict-no)
  4767. I see 1 and I'm going to do: predict-no
  4768. ENV: Agent did: predict-no for direction U in state State-A
  4769. In State-A moving U
  4770. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4771. predict error 0
  4772. dir: dir isR
  4773. /|\676: O: O1351 (predict-yes)
  4774. I see 1 and I'm going to do: predict-yes
  4775. ENV: Agent did: predict-yes for direction R in state State-A
  4776. In State-A moving R
  4777. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  4778. predict error 0
  4779. dir: dir isL
  4780. -/|\677: O: O1353 (predict-yes)
  4781. I see 1 and I'm going to do: predict-yes
  4782. ENV: Agent did: predict-yes for direction L in state State-B
  4783. In State-B moving L
  4784. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  4785. predict error 0
  4786. dir: dir isL
  4787. -/678: O: O1356 (predict-no)
  4788. I see 1 and I'm going to do: predict-no
  4789. ENV: Agent did: predict-no for direction L in state State-A
  4790. In State-A moving L
  4791. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4792. predict error 0
  4793. dir: dir isU
  4794. |\-679: O: O1358 (predict-no)
  4795. I see 1 and I'm going to do: predict-no
  4796. ENV: Agent did: predict-no for direction U in state State-A
  4797. In State-A moving U
  4798. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4799. predict error 0
  4800. dir: dir isR
  4801. /|\680: O: O1359 (predict-yes)
  4802. I see 1 and I'm going to do: predict-yes
  4803. ENV: Agent did: predict-yes for direction R in state State-A
  4804. In State-A moving R
  4805. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  4806. predict error 0
  4807. dir: dir isU
  4808. -/|681: O: O1362 (predict-no)
  4809. I see 1 and I'm going to do: predict-no
  4810. ENV: Agent did: predict-no for direction U in state State-B
  4811. In State-B moving U
  4812. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4813. predict error 0
  4814. dir: dir isR
  4815. \682: O: O1364 (predict-no)
  4816. I see 1 and I'm going to do: predict-no
  4817. ENV: Agent did: predict-no for direction R in state State-B
  4818. In State-B moving R
  4819. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4820. predict error 0
  4821. dir: dir isR
  4822. -/|683: O: O1366 (predict-no)
  4823. I see 1 and I'm going to do: predict-no
  4824. ENV: Agent did: predict-no for direction R in state State-B
  4825. In State-B moving R
  4826. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4827. predict error 0
  4828. dir: dir isL
  4829. \-/684: O: O1367 (predict-yes)
  4830. I see 1 and I'm going to do: predict-yes
  4831. ENV: Agent did: predict-yes for direction L in state State-B
  4832. In State-B moving L
  4833. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  4834. predict error 0
  4835. dir: dir isU
  4836. |\-685: O: O1370 (predict-no)
  4837. I see 1 and I'm going to do: predict-no
  4838. ENV: Agent did: predict-no for direction U in state State-A
  4839. In State-A moving U
  4840. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4841. predict error 0
  4842. dir: dir isL
  4843. /|\686: O: O1372 (predict-no)
  4844. I see 1 and I'm going to do: predict-no
  4845. ENV: Agent did: predict-no for direction L in state State-A
  4846. In State-A moving L
  4847. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4848. predict error 0
  4849. dir: dir isR
  4850. -/|687: O: O1373 (predict-yes)
  4851. I see 1 and I'm going to do: predict-yes
  4852. ENV: Agent did: predict-yes for direction R in state State-A
  4853. In State-A moving R
  4854. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  4855. predict error 0
  4856. dir: dir isU
  4857. \-688: O: O1376 (predict-no)
  4858. I see 1 and I'm going to do: predict-no
  4859. ENV: Agent did: predict-no for direction U in state State-B
  4860. In State-B moving U
  4861. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4862. predict error 0
  4863. dir: dir isU
  4864. /|689: O: O1378 (predict-no)
  4865. I see 1 and I'm going to do: predict-no
  4866. ENV: Agent did: predict-no for direction U in state State-B
  4867. In State-B moving U
  4868. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4869. predict error 0
  4870. dir: dir isL
  4871. \-/690: O: O1379 (predict-yes)
  4872. I see 1 and I'm going to do: predict-yes
  4873. ENV: Agent did: predict-yes for direction L in state State-B
  4874. In State-B moving L
  4875. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  4876. predict error 0
  4877. dir: dir isL
  4878. |\-/691: O: O1382 (predict-no)
  4879. I see 1 and I'm going to do: predict-no
  4880. ENV: Agent did: predict-no for direction L in state State-A
  4881. In State-A moving L
  4882. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4883. predict error 0
  4884. dir: dir isU
  4885. |692: O: O1384 (predict-no)
  4886. I see 1 and I'm going to do: predict-no
  4887. ENV: Agent did: predict-no for direction U in state State-A
  4888. In State-A moving U
  4889. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4890. predict error 0
  4891. dir: dir isR
  4892. \-693: O: O1385 (predict-yes)
  4893. I see 1 and I'm going to do: predict-yes
  4894. ENV: Agent did: predict-yes for direction R in state State-A
  4895. In State-A moving R
  4896. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  4897. predict error 0
  4898. dir: dir isU
  4899. /|694: O: O1388 (predict-no)
  4900. I see 1 and I'm going to do: predict-no
  4901. ENV: Agent did: predict-no for direction U in state State-B
  4902. In State-B moving U
  4903. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4904. predict error 0
  4905. dir: dir isU
  4906. \-695: O: O1390 (predict-no)
  4907. I see 1 and I'm going to do: predict-no
  4908. ENV: Agent did: predict-no for direction U in state State-B
  4909. In State-B moving U
  4910. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4911. predict error 0
  4912. dir: dir isR
  4913. /|\696: O: O1392 (predict-no)
  4914. I see 1 and I'm going to do: predict-no
  4915. ENV: Agent did: predict-no for direction R in state State-B
  4916. In State-B moving R
  4917. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4918. predict error 0
  4919. dir: dir isU
  4920. -/|697: O: O1394 (predict-no)
  4921. I see 1 and I'm going to do: predict-no
  4922. ENV: Agent did: predict-no for direction U in state State-B
  4923. In State-B moving U
  4924. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4925. predict error 0
  4926. dir: dir isU
  4927. \-/698: O: O1396 (predict-no)
  4928. I see 1 and I'm going to do: predict-no
  4929. ENV: Agent did: predict-no for direction U in state State-B
  4930. In State-B moving U
  4931. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4932. predict error 0
  4933. dir: dir isR
  4934. |\-/699: O: O1398 (predict-no)
  4935. I see 1 and I'm going to do: predict-no
  4936. ENV: Agent did: predict-no for direction R in state State-B
  4937. In State-B moving R
  4938. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4939. predict error 0
  4940. dir: dir isR
  4941. |\-700: O: O1400 (predict-no)
  4942. I see 1 and I'm going to do: predict-no
  4943. ENV: Agent did: predict-no for direction R in state State-B
  4944. In State-B moving R
  4945. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4946. predict error 0
  4947. dir: dir isL
  4948. /|701: O: O1401 (predict-yes)
  4949. I see 1 and I'm going to do: predict-yes
  4950. ENV: Agent did: predict-yes for direction L in state State-B
  4951. In State-B moving L
  4952. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  4953. predict error 0
  4954. dir: dir isR
  4955. \702: O: O1403 (predict-yes)
  4956. I see 1 and I'm going to do: predict-yes
  4957. ENV: Agent did: predict-yes for direction R in state State-A
  4958. In State-A moving R
  4959. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  4960. predict error 0
  4961. dir: dir isU
  4962. -/|703: O: O1406 (predict-no)
  4963. I see 1 and I'm going to do: predict-no
  4964. ENV: Agent did: predict-no for direction U in state State-B
  4965. In State-B moving U
  4966. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4967. predict error 0
  4968. dir: dir isL
  4969. \-/704: O: O1407 (predict-yes)
  4970. I see 1 and I'm going to do: predict-yes
  4971. ENV: Agent did: predict-yes for direction L in state State-B
  4972. In State-B moving L
  4973. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  4974. predict error 0
  4975. dir: dir isR
  4976. |\705: O: O1409 (predict-yes)
  4977. I see 1 and I'm going to do: predict-yes
  4978. ENV: Agent did: predict-yes for direction R in state State-A
  4979. In State-A moving R
  4980. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  4981. predict error 0
  4982. dir: dir isL
  4983. -/706: O: O1411 (predict-yes)
  4984. I see 1 and I'm going to do: predict-yes
  4985. ENV: Agent did: predict-yes for direction L in state State-B
  4986. In State-B moving L
  4987. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  4988. predict error 0
  4989. dir: dir isL
  4990. |\-707: O: O1414 (predict-no)
  4991. I see 1 and I'm going to do: predict-no
  4992. ENV: Agent did: predict-no for direction L in state State-A
  4993. In State-A moving L
  4994. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4995. predict error 0
  4996. dir: dir isR
  4997. /|708: O: O1415 (predict-yes)
  4998. I see 1 and I'm going to do: predict-yes
  4999. ENV: Agent did: predict-yes for direction R in state State-A
  5000. In State-A moving R
  5001. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  5002. predict error 0
  5003. dir: dir isL
  5004. \-/709: O: O1417 (predict-yes)
  5005. I see 1 and I'm going to do: predict-yes
  5006. ENV: Agent did: predict-yes for direction L in state State-B
  5007. In State-B moving L
  5008. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  5009. predict error 0
  5010. dir: dir isL
  5011. |\-710: O: O1420 (predict-no)
  5012. I see 1 and I'm going to do: predict-no
  5013. ENV: Agent did: predict-no for direction L in state State-A
  5014. In State-A moving L
  5015. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  5016. predict error 0
  5017. dir: dir isL
  5018. /|\711: O: O1422 (predict-no)
  5019. I see 1 and I'm going to do: predict-no
  5020. ENV: Agent did: predict-no for direction L in state State-A
  5021. In State-A moving L
  5022. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  5023. predict error 0
  5024. dir: dir isR
  5025. -712: O: O1423 (predict-yes)
  5026. I see 1 and I'm going to do: predict-yes
  5027. ENV: Agent did: predict-yes for direction R in state State-A
  5028. In State-A moving R
  5029. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  5030. predict error 0
  5031. dir: dir isR
  5032. /|713: O: O1426 (predict-no)
  5033. I see 1 and I'm going to do: predict-no
  5034. ENV: Agent did: predict-no for direction R in state State-B
  5035. In State-B moving R
  5036. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5037. predict error 0
  5038. dir: dir isL
  5039. \-/714: O: O1427 (predict-yes)
  5040. I see 1 and I'm going to do: predict-yes
  5041. ENV: Agent did: predict-yes for direction L in state State-B
  5042. In State-B moving L
  5043. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  5044. predict error 0
  5045. dir: dir isL
  5046. |\-715: O: O1430 (predict-no)
  5047. I see 1 and I'm going to do: predict-no
  5048. ENV: Agent did: predict-no for direction L in state State-A
  5049. In State-A moving L
  5050. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  5051. predict error 0
  5052. dir: dir isU
  5053. /|716: O: O1432 (predict-no)
  5054. I see 1 and I'm going to do: predict-no
  5055. ENV: Agent did: predict-no for direction U in state State-A
  5056. In State-A moving U
  5057. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  5058. predict error 0
  5059. dir: dir isL
  5060. \-717: O: O1434 (predict-no)
  5061. I see 1 and I'm going to do: predict-no
  5062. ENV: Agent did: predict-no for direction L in state State-A
  5063. In State-A moving L
  5064. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  5065. predict error 0
  5066. dir: dir isR
  5067. /|\-718: O: O1435 (predict-yes)
  5068. I see 1 and I'm going to do: predict-yes
  5069. ENV: Agent did: predict-yes for direction R in state State-A
  5070. In State-A moving R
  5071. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  5072. predict error 0
  5073. dir: dir isR
  5074. /|\719: O: O1438 (predict-no)
  5075. I see 1 and I'm going to do: predict-no
  5076. ENV: Agent did: predict-no for direction R in state State-B
  5077. In State-B moving R
  5078. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5079. predict error 0
  5080. dir: dir isU
  5081. -/720: O: O1440 (predict-no)
  5082. I see 1 and I'm going to do: predict-no
  5083. ENV: Agent did: predict-no for direction U in state State-B
  5084. In State-B moving U
  5085. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5086. predict error 0
  5087. dir: dir isR
  5088. |\-721: O: O1442 (predict-no)
  5089. I see 1 and I'm going to do: predict-no
  5090. ENV: Agent did: predict-no for direction R in state State-B
  5091. In State-B moving R
  5092. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5093. predict error 0
  5094. dir: dir isU
  5095. /722: O: O1444 (predict-no)
  5096. I see 1 and I'm going to do: predict-no
  5097. ENV: Agent did: predict-no for direction U in state State-B
  5098. In State-B moving U
  5099. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5100. predict error 0
  5101. dir: dir isR
  5102. |\723: O: O1446 (predict-no)
  5103. I see 1 and I'm going to do: predict-no
  5104. ENV: Agent did: predict-no for direction R in state State-B
  5105. In State-B moving R
  5106. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5107. predict error 0
  5108. dir: dir isL
  5109. -/724: O: O1447 (predict-yes)
  5110. I see 1 and I'm going to do: predict-yes
  5111. ENV: Agent did: predict-yes for direction L in state State-B
  5112. In State-B moving L
  5113. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  5114. predict error 0
  5115. dir: dir isL
  5116. |\-725: O: O1450 (predict-no)
  5117. I see 1 and I'm going to do: predict-no
  5118. ENV: Agent did: predict-no for direction L in state State-A
  5119. In State-A moving L
  5120. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  5121. predict error 0
  5122. dir: dir isL
  5123. /|726: O: O1452 (predict-no)
  5124. I see 1 and I'm going to do: predict-no
  5125. ENV: Agent did: predict-no for direction L in state State-A
  5126. In State-A moving L
  5127. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  5128. predict error 0
  5129. dir: dir isU
  5130. \-/727: O: O1454 (predict-no)
  5131. I see 1 and I'm going to do: predict-no
  5132. ENV: Agent did: predict-no for direction U in state State-A
  5133. In State-A moving U
  5134. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  5135. predict error 0
  5136. dir: dir isL
  5137. |\-/728: O: O1456 (predict-no)
  5138. I see 1 and I'm going to do: predict-no
  5139. ENV: Agent did: predict-no for direction L in state State-A
  5140. In State-A moving L
  5141. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  5142. predict error 0
  5143. dir: dir isL
  5144. |\729: O: O1458 (predict-no)
  5145. I see 1 and I'm going to do: predict-no
  5146. ENV: Agent did: predict-no for direction L in state State-A
  5147. In State-A moving L
  5148. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  5149. predict error 0
  5150. dir: dir isU
  5151. -/|730: O: O1460 (predict-no)
  5152. I see 1 and I'm going to do: predict-no
  5153. ENV: Agent did: predict-no for direction U in state State-A
  5154. In State-A moving U
  5155. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  5156. predict error 0
  5157. dir: dir isL
  5158. \-731: O: O1462 (predict-no)
  5159. I see 1 and I'm going to do: predict-no
  5160. ENV: Agent did: predict-no for direction L in state State-A
  5161. In State-A moving L
  5162. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  5163. predict error 0
  5164. dir: dir isU
  5165. /732: O: O1464 (predict-no)
  5166. I see 1 and I'm going to do: predict-no
  5167. ENV: Agent did: predict-no for direction U in state State-A
  5168. In State-A moving U
  5169. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  5170. predict error 0
  5171. dir: dir isL
  5172. |\733: O: O1466 (predict-no)
  5173. I see 1 and I'm going to do: predict-no
  5174. ENV: Agent did: predict-no for direction L in state State-A
  5175. In State-A moving L
  5176. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  5177. predict error 0
  5178. dir: dir isR
  5179. -/734: O: O1467 (predict-yes)
  5180. I see 1 and I'm going to do: predict-yes
  5181. ENV: Agent did: predict-yes for direction R in state State-A
  5182. In State-A moving R
  5183. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  5184. predict error 0
  5185. dir: dir isL
  5186. |\-735: O: O1469 (predict-yes)
  5187. I see 1 and I'm going to do: predict-yes
  5188. ENV: Agent did: predict-yes for direction L in state State-B
  5189. In State-B moving L
  5190. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  5191. predict error 0
  5192. dir: dir isU
  5193. /|\736: O: O1472 (predict-no)
  5194. I see 1 and I'm going to do: predict-no
  5195. ENV: Agent did: predict-no for direction U in state State-A
  5196. In State-A moving U
  5197. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  5198. predict error 0
  5199. dir: dir isR
  5200. -737: O: O1473 (predict-yes)
  5201. I see 1 and I'm going to do: predict-yes
  5202. ENV: Agent did: predict-yes for direction R in state State-A
  5203. In State-A moving R
  5204. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  5205. predict error 0
  5206. dir: dir isR
  5207. /|\738: O: O1476 (predict-no)
  5208. I see 1 and I'm going to do: predict-no
  5209. ENV: Agent did: predict-no for direction R in state State-B
  5210. In State-B moving R
  5211. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5212. predict error 0
  5213. dir: dir isU
  5214. -/|739: O: O1478 (predict-no)
  5215. I see 1 and I'm going to do: predict-no
  5216. ENV: Agent did: predict-no for direction U in state State-B
  5217. In State-B moving U
  5218. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5219. predict error 0
  5220. dir: dir isU
  5221. \-740: O: O1480 (predict-no)
  5222. I see 1 and I'm going to do: predict-no
  5223. ENV: Agent did: predict-no for direction U in state State-B
  5224. In State-B moving U
  5225. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5226. predict error 0
  5227. dir: dir isR
  5228. /|741: O: O1482 (predict-no)
  5229. I see 1 and I'm going to do: predict-no
  5230. ENV: Agent did: predict-no for direction R in state State-B
  5231. In State-B moving R
  5232. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5233. predict error 0
  5234. dir: dir isR
  5235. \742: O: O1484 (predict-no)
  5236. I see 1 and I'm going to do: predict-no
  5237. ENV: Agent did: predict-no for direction R in state State-B
  5238. In State-B moving R
  5239. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5240. predict error 0
  5241. dir: dir isR
  5242. -/743: O: O1486 (predict-no)
  5243. I see 1 and I'm going to do: predict-no
  5244. ENV: Agent did: predict-no for direction R in state State-B
  5245. In State-B moving R
  5246. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5247. predict error 0
  5248. dir: dir isL
  5249. |\744: O: O1487 (predict-yes)
  5250. I see 1 and I'm going to do: predict-yes
  5251. ENV: Agent did: predict-yes for direction L in state State-B
  5252. In State-B moving L
  5253. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  5254. predict error 0
  5255. dir: dir isU
  5256. -/|745: O: O1490 (predict-no)
  5257. I see 1 and I'm going to do: predict-no
  5258. ENV: Agent did: predict-no for direction U in state State-A
  5259. In State-A moving U
  5260. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  5261. predict error 0
  5262. dir: dir isR
  5263. \-746: O: O1491 (predict-yes)
  5264. I see 1 and I'm going to do: predict-yes
  5265. ENV: Agent did: predict-yes for direction R in state State-A
  5266. In State-A moving R
  5267. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  5268. predict error 0
  5269. dir: dir isU
  5270. /|\747: O: O1494 (predict-no)
  5271. I see 1 and I'm going to do: predict-no
  5272. ENV: Agent did: predict-no for direction U in state State-B
  5273. In State-B moving U
  5274. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5275. predict error 0
  5276. dir: dir isL
  5277. -/|748: O: O1495 (predict-yes)
  5278. I see 1 and I'm going to do: predict-yes
  5279. ENV: Agent did: predict-yes for direction L in state State-B
  5280. In State-B moving L
  5281. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  5282. predict error 0
  5283. dir: dir isR
  5284. \-/749: O: O1497 (predict-yes)
  5285. I see 1 and I'm going to do: predict-yes
  5286. ENV: Agent did: predict-yes for direction R in state State-A
  5287. In State-A moving R
  5288. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  5289. predict error 0
  5290. dir: dir isR
  5291. |\-750: O: O1500 (predict-no)
  5292. I see 1 and I'm going to do: predict-no
  5293. ENV: Agent did: predict-no for direction R in state State-B
  5294. In State-B moving R
  5295. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5296. predict error 0
  5297. dir: dir isU
  5298. /|\751: O: O1502 (predict-no)
  5299. I see 1 and I'm going to do: predict-no
  5300. ENV: Agent did: predict-no for direction U in state State-B
  5301. In State-B moving U
  5302. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5303. predict error 0
  5304. dir: dir isL
  5305. -752: O: O1503 (predict-yes)
  5306. I see 1 and I'm going to do: predict-yes
  5307. ENV: Agent did: predict-yes for direction L in state State-B
  5308. In State-B moving L
  5309. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  5310. predict error 0
  5311. dir: dir isR
  5312. /|\753: O: O1505 (predict-yes)
  5313. I see 1 and I'm going to do: predict-yes
  5314. ENV: Agent did: predict-yes for direction R in state State-A
  5315. In State-A moving R
  5316. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  5317. predict error 0
  5318. dir: dir isR
  5319. -/|754: O: O1508 (predict-no)
  5320. I see 1 and I'm going to do: predict-no
  5321. ENV: Agent did: predict-no for direction R in state State-B
  5322. In State-B moving R
  5323. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5324. predict error 0
  5325. dir: dir isL
  5326. \-755: O: O1509 (predict-yes)
  5327. I see 1 and I'm going to do: predict-yes
  5328. ENV: Agent did: predict-yes for direction L in state State-B
  5329. In State-B moving L
  5330. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  5331. predict error 0
  5332. dir: dir isR
  5333. /|\756: O: O1511 (predict-yes)
  5334. I see 1 and I'm going to do: predict-yes
  5335. ENV: Agent did: predict-yes for direction R in state State-A
  5336. In State-A moving R
  5337. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  5338. predict error 0
  5339. dir: dir isU
  5340. -/|757: O: O1514 (predict-no)
  5341. I see 1 and I'm going to do: predict-no
  5342. ENV: Agent did: predict-no for direction U in state State-B
  5343. In State-B moving U
  5344. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5345. predict error 0
  5346. dir: dir isR
  5347. \-/|758: O: O1516 (predict-no)
  5348. I see 1 and I'm going to do: predict-no
  5349. ENV: Agent did: predict-no for direction R in state State-B
  5350. In State-B moving R
  5351. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5352. predict error 0
  5353. dir: dir isR
  5354. \-/759: O: O1518 (predict-no)
  5355. I see 1 and I'm going to do: predict-no
  5356. ENV: Agent did: predict-no for direction R in state State-B
  5357. In State-B moving R
  5358. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5359. predict error 0
  5360. dir: dir isR
  5361. |\760: O: O1520 (predict-no)
  5362. I see 1 and I'm going to do: predict-no
  5363. ENV: Agent did: predict-no for direction R in state State-B
  5364. In State-B moving R
  5365. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5366. predict error 0
  5367. dir: dir isL
  5368. -/|761: O: O1521 (predict-yes)
  5369. I see 1 and I'm going to do: predict-yes
  5370. ENV: Agent did: predict-yes for direction L in state State-B
  5371. In State-B moving L
  5372. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  5373. predict error 0
  5374. dir: dir isR
  5375. \762: O: O1523 (predict-yes)
  5376. I see 1 and I'm going to do: predict-yes
  5377. ENV: Agent did: predict-yes for direction R in state State-A
  5378. In State-A moving R
  5379. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  5380. predict error 0
  5381. dir: dir isU
  5382. -/|\763: O: O1526 (predict-no)
  5383. I see 1 and I'm going to do: predict-no
  5384. ENV: Agent did: predict-no for direction U in state State-B
  5385. In State-B moving U
  5386. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5387. predict error 0
  5388. dir: dir isR
  5389. -/|764: O: O1528 (predict-no)
  5390. I see 1 and I'm going to do: predict-no
  5391. ENV: Agent did: predict-no for direction R in state State-B
  5392. In State-B moving R
  5393. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5394. predict error 0
  5395. dir: dir isR
  5396. \-/765: O: O1530 (predict-no)
  5397. I see 1 and I'm going to do: predict-no
  5398. ENV: Agent did: predict-no for direction R in state State-B
  5399. In State-B moving R
  5400. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5401. predict error 0
  5402. dir: dir isL
  5403. |\-766: O: O1531 (predict-yes)
  5404. I see 1 and I'm going to do: predict-yes
  5405. ENV: Agent did: predict-yes for direction L in state State-B
  5406. In State-B moving L
  5407. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  5408. predict error 0
  5409. dir: dir isL
  5410. /|767: O: O1534 (predict-no)
  5411. I see 1 and I'm going to do: predict-no
  5412. ENV: Agent did: predict-no for direction L in state State-A
  5413. In State-A moving L
  5414. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  5415. predict error 0
  5416. dir: dir isL
  5417. \-/768: O: O1536 (predict-no)
  5418. I see 1 and I'm going to do: predict-no
  5419. ENV: Agent did: predict-no for direction L in state State-A
  5420. In State-A moving L
  5421. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  5422. predict error 0
  5423. dir: dir isU
  5424. |\769: O: O1538 (predict-no)
  5425. I see 1 and I'm going to do: predict-no
  5426. ENV: Agent did: predict-no for direction U in state State-A
  5427. In State-A moving U
  5428. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  5429. predict error 0
  5430. dir: dir isU
  5431. -/770: O: O1540 (predict-no)
  5432. I see 1 and I'm going to do: predict-no
  5433. ENV: Agent did: predict-no for direction U in state State-A
  5434. In State-A moving U
  5435. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  5436. predict error 0
  5437. dir: dir isU
  5438. |\-771: O: O1542 (predict-no)
  5439. I see 1 and I'm going to do: predict-no
  5440. ENV: Agent did: predict-no for direction U in state State-A
  5441. In State-A moving U
  5442. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  5443. predict error 0
  5444. dir: dir isU
  5445. /772: O: O1544 (predict-no)
  5446. I see 1 and I'm going to do: predict-no
  5447. ENV: Agent did: predict-no for direction U in state State-A
  5448. In State-A moving U
  5449. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  5450. predict error 0
  5451. dir: dir isR
  5452. |\-773: O: O1545 (predict-yes)
  5453. I see 1 and I'm going to do: predict-yes
  5454. ENV: Agent did: predict-yes for direction R in state State-A
  5455. In State-A moving R
  5456. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  5457. predict error 0
  5458. dir: dir isU
  5459. /|\774: O: O1548 (predict-no)
  5460. I see 1 and I'm going to do: predict-no
  5461. ENV: Agent did: predict-no for direction U in state State-B
  5462. In State-B moving U
  5463. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5464. predict error 0
  5465. dir: dir isR
  5466. -/|775: O: O1550 (predict-no)
  5467. I see 1 and I'm going to do: predict-no
  5468. ENV: Agent did: predict-no for direction R in state State-B
  5469. In State-B moving R
  5470. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5471. predict error 0
  5472. dir: dir isR
  5473. \-/776: O: O1552 (predict-no)
  5474. I see 1 and I'm going to do: predict-no
  5475. ENV: Agent did: predict-no for direction R in state State-B
  5476. In State-B moving R
  5477. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5478. predict error 0
  5479. dir: dir isU
  5480. |\-777: O: O1554 (predict-no)
  5481. I see 1 and I'm going to do: predict-no
  5482. ENV: Agent did: predict-no for direction U in state State-B
  5483. In State-B moving U
  5484. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5485. predict error 0
  5486. dir: dir isU
  5487. /|\778: O: O1556 (predict-no)
  5488. I see 1 and I'm going to do: predict-no
  5489. ENV: Agent did: predict-no for direction U in state State-B
  5490. In State-B moving U
  5491. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5492. predict error 0
  5493. dir: dir isU
  5494. -/779: O: O1558 (predict-no)
  5495. I see 1 and I'm going to do: predict-no
  5496. ENV: Agent did: predict-no for direction U in state State-B
  5497. In State-B moving U
  5498. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5499. predict error 0
  5500. dir: dir isR
  5501. |\780: O: O1560 (predict-no)
  5502. I see 1 and I'm going to do: predict-no
  5503. ENV: Agent did: predict-no for direction R in state State-B
  5504. In State-B moving R
  5505. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5506. predict error 0
  5507. dir: dir isU
  5508. -/|\781: O: O1562 (predict-no)
  5509. I see 1 and I'm going to do: predict-no
  5510. ENV: Agent did: predict-no for direction U in state State-B
  5511. In State-B moving U
  5512. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5513. predict error 0
  5514. dir: dir isR
  5515. -782: O: O1564 (predict-no)
  5516. I see 1 and I'm going to do: predict-no
  5517. ENV: Agent did: predict-no for direction R in state State-B
  5518. In State-B moving R
  5519. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5520. predict error 0
  5521. dir: dir isU
  5522. /783: O: O1566 (predict-no)
  5523. I see 1 and I'm going to do: predict-no
  5524. ENV: Agent did: predict-no for direction U in state State-B
  5525. In State-B moving U
  5526. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5527. predict error 0
  5528. dir: dir isU
  5529. |\-784: O: O1568 (predict-no)
  5530. I see 1 and I'm going to do: predict-no
  5531. ENV: Agent did: predict-no for direction U in state State-B
  5532. In State-B moving U
  5533. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5534. predict error 0
  5535. dir: dir isL
  5536. /|\785: O: O1569 (predict-yes)
  5537. I see 1 and I'm going to do: predict-yes
  5538. ENV: Agent did: predict-yes for direction L in state State-B
  5539. In State-B moving L
  5540. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  5541. predict error 0
  5542. dir: dir isU
  5543. -/|\786: O: O1572 (predict-no)
  5544. I see 1 and I'm going to do: predict-no
  5545. ENV: Agent did: predict-no for direction U in state State-A
  5546. In State-A moving U
  5547. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  5548. predict error 0
  5549. dir: dir isL
  5550. -/|787: O: O1574 (predict-no)
  5551. I see 1 and I'm going to do: predict-no
  5552. ENV: Agent did: predict-no for direction L in state State-A
  5553. In State-A moving L
  5554. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  5555. predict error 0
  5556. dir: dir isL
  5557. \-788: O: O1576 (predict-no)
  5558. I see 1 and I'm going to do: predict-no
  5559. ENV: Agent did: predict-no for direction L in state State-A
  5560. In State-A moving L
  5561. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  5562. predict error 0
  5563. dir: dir isU
  5564. /|\789: O: O1578 (predict-no)
  5565. I see 1 and I'm going to do: predict-no
  5566. ENV: Agent did: predict-no for direction U in state State-A
  5567. In State-A moving U
  5568. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  5569. predict error 0
  5570. dir: dir isL
  5571. -/|790: O: O1580 (predict-no)
  5572. I see 1 and I'm going to do: predict-no
  5573. ENV: Agent did: predict-no for direction L in state State-A
  5574. In State-A moving L
  5575. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  5576. predict error 0
  5577. dir: dir isR
  5578. \-791: O: O1581 (predict-yes)
  5579. I see 1 and I'm going to do: predict-yes
  5580. ENV: Agent did: predict-yes for direction R in state State-A
  5581. In State-A moving R
  5582. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  5583. predict error 0
  5584. dir: dir isR
  5585. /792: O: O1584 (predict-no)
  5586. I see 1 and I'm going to do: predict-no
  5587. ENV: Agent did: predict-no for direction R in state State-B
  5588. In State-B moving R
  5589. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5590. predict error 0
  5591. dir: dir isL
  5592. |\793: O: O1585 (predict-yes)
  5593. I see 1 and I'm going to do: predict-yes
  5594. ENV: Agent did: predict-yes for direction L in state State-B
  5595. In State-B moving L
  5596. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  5597. predict error 0
  5598. dir: dir isU
  5599. -/|794: O: O1588 (predict-no)
  5600. I see 1 and I'm going to do: predict-no
  5601. ENV: Agent did: predict-no for direction U in state State-A
  5602. In State-A moving U
  5603. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  5604. predict error 0
  5605. dir: dir isL
  5606. \-/795: O: O1590 (predict-no)
  5607. I see 1 and I'm going to do: predict-no
  5608. ENV: Agent did: predict-no for direction L in state State-A
  5609. In State-A moving L
  5610. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  5611. predict error 0
  5612. dir: dir isR
  5613. |\796: O: O1591 (predict-yes)
  5614. I see 1 and I'm going to do: predict-yes
  5615. ENV: Agent did: predict-yes for direction R in state State-A
  5616. In State-A moving R
  5617. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  5618. predict error 0
  5619. dir: dir isR
  5620. -/|797: O: O1594 (predict-no)
  5621. I see 1 and I'm going to do: predict-no
  5622. ENV: Agent did: predict-no for direction R in state State-B
  5623. In State-B moving R
  5624. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5625. predict error 0
  5626. dir: dir isU
  5627. \-/798: O: O1596 (predict-no)
  5628. I see 1 and I'm going to do: predict-no
  5629. ENV: Agent did: predict-no for direction U in state State-B
  5630. In State-B moving U
  5631. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5632. predict error 0
  5633. dir: dir isU
  5634. |\799: O: O1598 (predict-no)
  5635. I see 1 and I'm going to do: predict-no
  5636. ENV: Agent did: predict-no for direction U in state State-B
  5637. In State-B moving U
  5638. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5639. predict error 0
  5640. dir: dir isL
  5641. -/|800: O: O1599 (predict-yes)
  5642. I see 1 and I'm going to do: predict-yes
  5643. ENV: Agent did: predict-yes for direction L in state State-B
  5644. In State-B moving L
  5645. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  5646. predict error 0
  5647. dir: dir isL
  5648. \-/801: O: O1602 (predict-no)
  5649. I see 1 and I'm going to do: predict-no
  5650. ENV: Agent did: predict-no for direction L in state State-A
  5651. In State-A moving L
  5652. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  5653. predict error 0
  5654. dir: dir isL
  5655. |802: O: O1604 (predict-no)
  5656. I see 1 and I'm going to do: predict-no
  5657. ENV: Agent did: predict-no for direction L in state State-A
  5658. In State-A moving L
  5659. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  5660. predict error 0
  5661. dir: dir isR
  5662. \-/803: O: O1605 (predict-yes)
  5663. I see 1 and I'm going to do: predict-yes
  5664. ENV: Agent did: predict-yes for direction R in state State-A
  5665. In State-A moving R
  5666. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  5667. predict error 0
  5668. dir: dir isL
  5669. |\-804: O: O1607 (predict-yes)
  5670. I see 1 and I'm going to do: predict-yes
  5671. ENV: Agent did: predict-yes for direction L in state State-B
  5672. In State-B moving L
  5673. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  5674. predict error 0
  5675. dir: dir isL
  5676. /|\805: O: O1610 (predict-no)
  5677. I see 1 and I'm going to do: predict-no
  5678. ENV: Agent did: predict-no for direction L in state State-A
  5679. In State-A moving L
  5680. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  5681. predict error 0
  5682. dir: dir isU
  5683. -/806: O: O1612 (predict-no)
  5684. I see 1 and I'm going to do: predict-no
  5685. ENV: Agent did: predict-no for direction U in state State-A
  5686. In State-A moving U
  5687. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  5688. predict error 0
  5689. dir: dir isU
  5690. |\-807: O: O1614 (predict-no)
  5691. I see 1 and I'm going to do: predict-no
  5692. ENV: Agent did: predict-no for direction U in state State-A
  5693. In State-A moving U
  5694. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  5695. predict error 0
  5696. dir: dir isU
  5697. /|\808: O: O1616 (predict-no)
  5698. I see 1 and I'm going to do: predict-no
  5699. ENV: Agent did: predict-no for direction U in state State-A
  5700. In State-A moving U
  5701. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  5702. predict error 0
  5703. dir: dir isU
  5704. -/|809: O: O1618 (predict-no)
  5705. I see 1 and I'm going to do: predict-no
  5706. ENV: Agent did: predict-no for direction U in state State-A
  5707. In State-A moving U
  5708. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  5709. predict error 0
  5710. dir: dir isU
  5711. \-/810: O: O1620 (predict-no)
  5712. I see 1 and I'm going to do: predict-no
  5713. ENV: Agent did: predict-no for direction U in state State-A
  5714. In State-A moving U
  5715. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  5716. predict error 0
  5717. dir: dir isR
  5718. |\811: O: O1621 (predict-yes)
  5719. I see 1 and I'm going to do: predict-yes
  5720. ENV: Agent did: predict-yes for direction R in state State-A
  5721. In State-A moving R
  5722. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  5723. predict error 0
  5724. dir: dir isL
  5725. -812: O: O1623 (predict-yes)
  5726. I see 1 and I'm going to do: predict-yes
  5727. ENV: Agent did: predict-yes for direction L in state State-B
  5728. In State-B moving L
  5729. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  5730. predict error 0
  5731. dir: dir isL
  5732. /|\813: O: O1626 (predict-no)
  5733. I see 1 and I'm going to do: predict-no
  5734. ENV: Agent did: predict-no for direction L in state State-A
  5735. In State-A moving L
  5736. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  5737. predict error 0
  5738. dir: dir isR
  5739. -/|814: O: O1627 (predict-yes)
  5740. I see 1 and I'm going to do: predict-yes
  5741. ENV: Agent did: predict-yes for direction R in state State-A
  5742. In State-A moving R
  5743. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  5744. predict error 0
  5745. dir: dir isR
  5746. \-815: O: O1630 (predict-no)
  5747. I see 1 and I'm going to do: predict-no
  5748. ENV: Agent did: predict-no for direction R in state State-B
  5749. In State-B moving R
  5750. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5751. predict error 0
  5752. dir: dir isR
  5753. /|\816: O: O1632 (predict-no)
  5754. I see 1 and I'm going to do: predict-no
  5755. ENV: Agent did: predict-no for direction R in state State-B
  5756. In State-B moving R
  5757. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5758. predict error 0
  5759. dir: dir isR
  5760. -/817: O: O1634 (predict-no)
  5761. I see 1 and I'm going to do: predict-no
  5762. ENV: Agent did: predict-no for direction R in state State-B
  5763. In State-B moving R
  5764. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5765. predict error 0
  5766. dir: dir isU
  5767. |\-818: O: O1636 (predict-no)
  5768. I see 1 and I'm going to do: predict-no
  5769. ENV: Agent did: predict-no for direction U in state State-B
  5770. In State-B moving U
  5771. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5772. predict error 0
  5773. dir: dir isL
  5774. /|819: O: O1637 (predict-yes)
  5775. I see 1 and I'm going to do: predict-yes
  5776. ENV: Agent did: predict-yes for direction L in state State-B
  5777. In State-B moving L
  5778. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  5779. predict error 0
  5780. dir: dir isR
  5781. \820: O: O1639 (predict-yes)
  5782. I see 1 and I'm going to do: predict-yes
  5783. ENV: Agent did: predict-yes for direction R in state State-A
  5784. In State-A moving R
  5785. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  5786. predict error 0
  5787. dir: dir isU
  5788. -/|821: O: O1642 (predict-no)
  5789. I see 1 and I'm going to do: predict-no
  5790. ENV: Agent did: predict-no for direction U in state State-B
  5791. In State-B moving U
  5792. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5793. predict error 0
  5794. dir: dir isU
  5795. \822: O: O1644 (predict-no)
  5796. I see 1 and I'm going to do: predict-no
  5797. ENV: Agent did: predict-no for direction U in state State-B
  5798. In State-B moving U
  5799. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5800. predict error 0
  5801. dir: dir isL
  5802. -/|823: O: O1645 (predict-yes)
  5803. I see 1 and I'm going to do: predict-yes
  5804. ENV: Agent did: predict-yes for direction L in state State-B
  5805. In State-B moving L
  5806. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  5807. predict error 0
  5808. dir: dir isL
  5809. \-824: O: O1648 (predict-no)
  5810. I see 1 and I'm going to do: predict-no
  5811. ENV: Agent did: predict-no for direction L in state State-A
  5812. In State-A moving L
  5813. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  5814. predict error 0
  5815. dir: dir isU
  5816. /|\-825: O: O1650 (predict-no)
  5817. I see 1 and I'm going to do: predict-no
  5818. ENV: Agent did: predict-no for direction U in state State-A
  5819. In State-A moving U
  5820. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  5821. predict error 0
  5822. dir: dir isL
  5823. /|826: O: O1652 (predict-no)
  5824. I see 1 and I'm going to do: predict-no
  5825. ENV: Agent did: predict-no for direction L in state State-A
  5826. In State-A moving L
  5827. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  5828. predict error 0
  5829. dir: dir isL
  5830. \-/827: O: O1654 (predict-no)
  5831. I see 1 and I'm going to do: predict-no
  5832. ENV: Agent did: predict-no for direction L in state State-A
  5833. In State-A moving L
  5834. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  5835. predict error 0
  5836. dir: dir isR
  5837. |\-828: O: O1655 (predict-yes)
  5838. I see 1 and I'm going to do: predict-yes
  5839. ENV: Agent did: predict-yes for direction R in state State-A
  5840. In State-A moving R
  5841. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  5842. predict error 0
  5843. dir: dir isR
  5844. /|829: O: O1658 (predict-no)
  5845. I see 1 and I'm going to do: predict-no
  5846. ENV: Agent did: predict-no for direction R in state State-B
  5847. In State-B moving R
  5848. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5849. predict error 0
  5850. dir: dir isL
  5851. \-/830: O: O1659 (predict-yes)
  5852. I see 1 and I'm going to do: predict-yes
  5853. ENV: Agent did: predict-yes for direction L in state State-B
  5854. In State-B moving L
  5855. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  5856. predict error 0
  5857. dir: dir isL
  5858. |\-831: O: O1662 (predict-no)
  5859. I see 1 and I'm going to do: predict-no
  5860. ENV: Agent did: predict-no for direction L in state State-A
  5861. In State-A moving L
  5862. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  5863. predict error 0
  5864. dir: dir isL
  5865. /832: O: O1664 (predict-no)
  5866. I see 1 and I'm going to do: predict-no
  5867. ENV: Agent did: predict-no for direction L in state State-A
  5868. In State-A moving L
  5869. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  5870. predict error 0
  5871. dir: dir isU
  5872. |833: O: O1666 (predict-no)
  5873. I see 1 and I'm going to do: predict-no
  5874. ENV: Agent did: predict-no for direction U in state State-A
  5875. In State-A moving U
  5876. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  5877. predict error 0
  5878. dir: dir isR
  5879. \-/834: O: O1667 (predict-yes)
  5880. I see 1 and I'm going to do: predict-yes
  5881. ENV: Agent did: predict-yes for direction R in state State-A
  5882. In State-A moving R
  5883. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  5884. predict error 0
  5885. dir: dir isU
  5886. |\-835: O: O1670 (predict-no)
  5887. I see 1 and I'm going to do: predict-no
  5888. ENV: Agent did: predict-no for direction U in state State-B
  5889. In State-B moving U
  5890. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5891. predict error 0
  5892. dir: dir isU
  5893. /|\836: O: O1672 (predict-no)
  5894. I see 1 and I'm going to do: predict-no
  5895. ENV: Agent did: predict-no for direction U in state State-B
  5896. In State-B moving U
  5897. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5898. predict error 0
  5899. dir: dir isU
  5900. -/|837: O: O1674 (predict-no)
  5901. I see 1 and I'm going to do: predict-no
  5902. ENV: Agent did: predict-no for direction U in state State-B
  5903. In State-B moving U
  5904. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5905. predict error 0
  5906. dir: dir isL
  5907. \-838: O: O1675 (predict-yes)
  5908. I see 1 and I'm going to do: predict-yes
  5909. ENV: Agent did: predict-yes for direction L in state State-B
  5910. In State-B moving L
  5911. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  5912. predict error 0
  5913. dir: dir isL
  5914. /|\839: O: O1678 (predict-no)
  5915. I see 1 and I'm going to do: predict-no
  5916. ENV: Agent did: predict-no for direction L in state State-A
  5917. In State-A moving L
  5918. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  5919. predict error 0
  5920. dir: dir isL
  5921. -/|\840: O: O1680 (predict-no)
  5922. I see 1 and I'm going to do: predict-no
  5923. ENV: Agent did: predict-no for direction L in state State-A
  5924. In State-A moving L
  5925. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  5926. predict error 0
  5927. dir: dir isR
  5928. -/|841: O: O1681 (predict-yes)
  5929. I see 1 and I'm going to do: predict-yes
  5930. ENV: Agent did: predict-yes for direction R in state State-A
  5931. In State-A moving R
  5932. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  5933. predict error 0
  5934. dir: dir isR
  5935. \842: O: O1684 (predict-no)
  5936. I see 1 and I'm going to do: predict-no
  5937. ENV: Agent did: predict-no for direction R in state State-B
  5938. In State-B moving R
  5939. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5940. predict error 0
  5941. dir: dir isL
  5942. -/843: O: O1685 (predict-yes)
  5943. I see 1 and I'm going to do: predict-yes
  5944. ENV: Agent did: predict-yes for direction L in state State-B
  5945. In State-B moving L
  5946. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  5947. predict error 0
  5948. dir: dir isR
  5949. |\-844: O: O1687 (predict-yes)
  5950. I see 1 and I'm going to do: predict-yes
  5951. ENV: Agent did: predict-yes for direction R in state State-A
  5952. In State-A moving R
  5953. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  5954. predict error 0
  5955. dir: dir isL
  5956. /|\845: O: O1689 (predict-yes)
  5957. I see 1 and I'm going to do: predict-yes
  5958. ENV: Agent did: predict-yes for direction L in state State-B
  5959. In State-B moving L
  5960. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  5961. predict error 0
  5962. dir: dir isL
  5963. -/|846: O: O1692 (predict-no)
  5964. I see 1 and I'm going to do: predict-no
  5965. ENV: Agent did: predict-no for direction L in state State-A
  5966. In State-A moving L
  5967. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  5968. predict error 0
  5969. dir: dir isL
  5970. \-847: O: O1694 (predict-no)
  5971. I see 1 and I'm going to do: predict-no
  5972. ENV: Agent did: predict-no for direction L in state State-A
  5973. In State-A moving L
  5974. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  5975. predict error 0
  5976. dir: dir isU
  5977. /|\848: O: O1696 (predict-no)
  5978. I see 1 and I'm going to do: predict-no
  5979. ENV: Agent did: predict-no for direction U in state State-A
  5980. In State-A moving U
  5981. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  5982. predict error 0
  5983. dir: dir isR
  5984. -/849: O: O1697 (predict-yes)
  5985. I see 1 and I'm going to do: predict-yes
  5986. ENV: Agent did: predict-yes for direction R in state State-A
  5987. In State-A moving R
  5988. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  5989. predict error 0
  5990. dir: dir isL
  5991. |\-/850: O: O1699 (predict-yes)
  5992. I see 1 and I'm going to do: predict-yes
  5993. ENV: Agent did: predict-yes for direction L in state State-B
  5994. In State-B moving L
  5995. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  5996. predict error 0
  5997. dir: dir isL
  5998. |\-851: O: O1702 (predict-no)
  5999. I see 1 and I'm going to do: predict-no
  6000. ENV: Agent did: predict-no for direction L in state State-A
  6001. In State-A moving L
  6002. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  6003. predict error 0
  6004. dir: dir isR
  6005. /852: O: O1703 (predict-yes)
  6006. I see 1 and I'm going to do: predict-yes
  6007. ENV: Agent did: predict-yes for direction R in state State-A
  6008. In State-A moving R
  6009. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  6010. predict error 0
  6011. dir: dir isR
  6012. |\853: O: O1706 (predict-no)
  6013. I see 1 and I'm going to do: predict-no
  6014. ENV: Agent did: predict-no for direction R in state State-B
  6015. In State-B moving R
  6016. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  6017. predict error 0
  6018. dir: dir isU
  6019. -/|854: O: O1708 (predict-no)
  6020. I see 1 and I'm going to do: predict-no
  6021. ENV: Agent did: predict-no for direction U in state State-B
  6022. In State-B moving U
  6023. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  6024. predict error 0
  6025. dir: dir isU
  6026. \-/855: O: O1710 (predict-no)
  6027. I see 1 and I'm going to do: predict-no
  6028. ENV: Agent did: predict-no for direction U in state State-B
  6029. In State-B moving U
  6030. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  6031. predict error 0
  6032. dir: dir isU
  6033. |\-856: O: O1712 (predict-no)
  6034. I see 1 and I'm going to do: predict-no
  6035. ENV: Agent did: predict-no for direction U in state State-B
  6036. In State-B moving U
  6037. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  6038. predict error 0
  6039. dir: dir isL
  6040. /|\857: O: O1713 (predict-yes)
  6041. I see 1 and I'm going to do: predict-yes
  6042. ENV: Agent did: predict-yes for direction L in state State-B
  6043. In State-B moving L
  6044. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  6045. predict error 0
  6046. dir: dir isL
  6047. -/858: O: O1716 (predict-no)
  6048. I see 1 and I'm going to do: predict-no
  6049. ENV: Agent did: predict-no for direction L in state State-A
  6050. In State-A moving L
  6051. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  6052. predict error 0
  6053. dir: dir isU
  6054. |\-859: O: O1718 (predict-no)
  6055. I see 1 and I'm going to do: predict-no
  6056. ENV: Agent did: predict-no for direction U in state State-A
  6057. In State-A moving U
  6058. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  6059. predict error 0
  6060. dir: dir isU
  6061. /|\860: O: O1720 (predict-no)
  6062. I see 1 and I'm going to do: predict-no
  6063. ENV: Agent did: predict-no for direction U in state State-A
  6064. In State-A moving U
  6065. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  6066. predict error 0
  6067. dir: dir isR
  6068. -/|861: O: O1721 (predict-yes)
  6069. I see 1 and I'm going to do: predict-yes
  6070. ENV: Agent did: predict-yes for direction R in state State-A
  6071. In State-A moving R
  6072. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  6073. predict error 0
  6074. dir: dir isU
  6075. \862: O: O1724 (predict-no)
  6076. I see 1 and I'm going to do: predict-no
  6077. ENV: Agent did: predict-no for direction U in state State-B
  6078. In State-B moving U
  6079. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  6080. predict error 0
  6081. dir: dir isR
  6082. -/|863: O: O1726 (predict-no)
  6083. I see 1 and I'm going to do: predict-no
  6084. ENV: Agent did: predict-no for direction R in state State-B
  6085. In State-B moving R
  6086. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  6087. predict error 0
  6088. dir: dir isL
  6089. \-/864: O: O1727 (predict-yes)
  6090. I see 1 and I'm going to do: predict-yes
  6091. ENV: Agent did: predict-yes for direction L in state State-B
  6092. In State-B moving L
  6093. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  6094. predict error 0
  6095. dir: dir isL
  6096. |\-865: O: O1730 (predict-no)
  6097. I see 1 and I'm going to do: predict-no
  6098. ENV: Agent did: predict-no for direction L in state State-A
  6099. In State-A moving L
  6100. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  6101. predict error 0
  6102. dir: dir isL
  6103. /|866: O: O1732 (predict-no)
  6104. I see 1 and I'm going to do: predict-no
  6105. ENV: Agent did: predict-no for direction L in state State-A
  6106. In State-A moving L
  6107. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  6108. predict error 0
  6109. dir: dir isR
  6110. \-867: O: O1733 (predict-yes)
  6111. I see 1 and I'm going to do: predict-yes
  6112. ENV: Agent did: predict-yes for direction R in state State-A
  6113. In State-A moving R
  6114. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  6115. predict error 0
  6116. dir: dir isU
  6117. /|\868: O: O1736 (predict-no)
  6118. I see 1 and I'm going to do: predict-no
  6119. ENV: Agent did: predict-no for direction U in state State-B
  6120. In State-B moving U
  6121. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  6122. predict error 0
  6123. dir: dir isU
  6124. -/|869: O: O1738 (predict-no)
  6125. I see 1 and I'm going to do: predict-no
  6126. ENV: Agent did: predict-no for direction U in state State-B
  6127. In State-B moving U
  6128. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  6129. predict error 0
  6130. dir: dir isR
  6131. \-870: O: O1740 (predict-no)
  6132. I see 1 and I'm going to do: predict-no
  6133. ENV: Agent did: predict-no for direction R in state State-B
  6134. In State-B moving R
  6135. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  6136. predict error 0
  6137. dir: dir isR
  6138. /|\871: O: O1742 (predict-no)
  6139. I see 1 and I'm going to do: predict-no
  6140. ENV: Agent did: predict-no for direction R in state State-B
  6141. In State-B moving R
  6142. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  6143. predict error 0
  6144. dir: dir isU
  6145. -872: O: O1744 (predict-no)
  6146. I see 1 and I'm going to do: predict-no
  6147. ENV: Agent did: predict-no for direction U in state State-B
  6148. In State-B moving U
  6149. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  6150. predict error 0
  6151. dir: dir isU
  6152. /|873: O: O1746 (predict-no)
  6153. I see 1 and I'm going to do: predict-no
  6154. ENV: Agent did: predict-no for direction U in state State-B
  6155. In State-B moving U
  6156. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  6157. predict error 0
  6158. dir: dir isR
  6159. \-/874: O: O1748 (predict-no)
  6160. I see 1 and I'm going to do: predict-no
  6161. ENV: Agent did: predict-no for direction R in state State-B
  6162. In State-B moving R
  6163. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  6164. predict error 0
  6165. dir: dir isR
  6166. |\-875: O: O1750 (predict-no)
  6167. I see 1 and I'm going to do: predict-no
  6168. ENV: Agent did: predict-no for direction R in state State-B
  6169. In State-B moving R
  6170. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  6171. predict error 0
  6172. dir: dir isR
  6173. /|\876: O: O1752 (predict-no)
  6174. I see 1 and I'm going to do: predict-no
  6175. ENV: Agent did: predict-no for direction R in state State-B
  6176. In State-B moving R
  6177. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  6178. predict error 0
  6179. dir: dir isL
  6180. -/|877: O: O1753 (predict-yes)
  6181. I see 1 and I'm going to do: predict-yes
  6182. ENV: Agent did: predict-yes for direction L in state State-B
  6183. In State-B moving L
  6184. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  6185. predict error 0
  6186. dir: dir isL
  6187. \-/878: O: O1756 (predict-no)
  6188. I see 1 and I'm going to do: predict-no
  6189. ENV: Agent did: predict-no for direction L in state State-A
  6190. In State-A moving L
  6191. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  6192. predict error 0
  6193. dir: dir isU
  6194. |\-879: O: O1758 (predict-no)
  6195. I see 1 and I'm going to do: predict-no
  6196. ENV: Agent did: predict-no for direction U in state State-A
  6197. In State-A moving U
  6198. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  6199. predict error 0
  6200. dir: dir isU
  6201. /|880: O: O1760 (predict-no)
  6202. I see 1 and I'm going to do: predict-no
  6203. ENV: Agent did: predict-no for direction U in state State-A
  6204. In State-A moving U
  6205. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  6206. predict error 0
  6207. dir: dir isR
  6208. \-881: O: O1761 (predict-yes)
  6209. I see 1 and I'm going to do: predict-yes
  6210. ENV: Agent did: predict-yes for direction R in state State-A
  6211. In State-A moving R
  6212. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  6213. predict error 0
  6214. dir: dir isR
  6215. /882: O: O1764 (predict-no)
  6216. I see 1 and I'm going to do: predict-no
  6217. ENV: Agent did: predict-no for direction R in state State-B
  6218. In State-B moving R
  6219. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  6220. predict error 0
  6221. dir: dir isR
  6222. |\-883: O: O1766 (predict-no)
  6223. I see 1 and I'm going to do: predict-no
  6224. ENV: Agent did: predict-no for direction R in state State-B
  6225. In State-B moving R
  6226. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  6227. predict error 0
  6228. dir: dir isR
  6229. /|\884: O: O1768 (predict-no)
  6230. I see 1 and I'm going to do: predict-no
  6231. ENV: Agent did: predict-no for direction R in state State-B
  6232. In State-B moving R
  6233. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  6234. predict error 0
  6235. dir: dir isU
  6236. -/|885: O: O1770 (predict-no)
  6237. I see 1 and I'm going to do: predict-no
  6238. ENV: Agent did: predict-no for direction U in state State-B
  6239. In State-B moving U
  6240. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  6241. predict error 0
  6242. dir: dir isR
  6243. \-886: O: O1772 (predict-no)
  6244. I see 1 and I'm going to do: predict-no
  6245. ENV: Agent did: predict-no for direction R in state State-B
  6246. In State-B moving R
  6247. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  6248. predict error 0
  6249. dir: dir isU
  6250. /|887: O: O1774 (predict-no)
  6251. I see 1 and I'm going to do: predict-no
  6252. ENV: Agent did: predict-no for direction U in state State-B
  6253. In State-B moving U
  6254. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  6255. predict error 0
  6256. dir: dir isL
  6257. \-/888: O: O1775 (predict-yes)
  6258. I see 1 and I'm going to do: predict-yes
  6259. ENV: Agent did: predict-yes for direction L in state State-B
  6260. In State-B moving L
  6261. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  6262. predict error 0
  6263. dir: dir isL
  6264. |\-889: O: O1778 (predict-no)
  6265. I see 1 and I'm going to do: predict-no
  6266. ENV: Agent did: predict-no for direction L in state State-A
  6267. In State-A moving L
  6268. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  6269. predict error 0
  6270. dir: dir isR
  6271. /|\890: O: O1779 (predict-yes)
  6272. I see 1 and I'm going to do: predict-yes
  6273. ENV: Agent did: predict-yes for direction R in state State-A
  6274. In State-A moving R
  6275. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  6276. predict error 0
  6277. dir: dir isR
  6278. -/|891: O: O1782 (predict-no)
  6279. I see 1 and I'm going to do: predict-no
  6280. ENV: Agent did: predict-no for direction R in state State-B
  6281. In State-B moving R
  6282. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  6283. predict error 0
  6284. dir: dir isU
  6285. \892: O: O1784 (predict-no)
  6286. I see 1 and I'm going to do: predict-no
  6287. ENV: Agent did: predict-no for direction U in state State-B
  6288. In State-B moving U
  6289. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  6290. predict error 0
  6291. dir: dir isU
  6292. -/|893: O: O1786 (predict-no)
  6293. I see 1 and I'm going to do: predict-no
  6294. ENV: Agent did: predict-no for direction U in state State-B
  6295. In State-B moving U
  6296. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  6297. predict error 0
  6298. dir: dir isU
  6299. \-/894: O: O1788 (predict-no)
  6300. I see 1 and I'm going to do: predict-no
  6301. ENV: Agent did: predict-no for direction U in state State-B
  6302. In State-B moving U
  6303. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  6304. predict error 0
  6305. dir: dir isR
  6306. |\895: O: O1790 (predict-no)
  6307. I see 1 and I'm going to do: predict-no
  6308. ENV: Agent did: predict-no for direction R in state State-B
  6309. In State-B moving R
  6310. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  6311. predict error 0
  6312. dir: dir isL
  6313. -/|896: O: O1791 (predict-yes)
  6314. I see 1 and I'm going to do: predict-yes
  6315. ENV: Agent did: predict-yes for direction L in state State-B
  6316. In State-B moving L
  6317. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  6318. predict error 0
  6319. dir: dir isR
  6320. \-897: O: O1793 (predict-yes)
  6321. I see 1 and I'm going to do: predict-yes
  6322. ENV: Agent did: predict-yes for direction R in state State-A
  6323. In State-A moving R
  6324. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  6325. predict error 0
  6326. dir: dir isR
  6327. /|\898: O: O1796 (predict-no)
  6328. I see 1 and I'm going to do: predict-no
  6329. ENV: Agent did: predict-no for direction R in state State-B
  6330. In State-B moving R
  6331. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  6332. predict error 0
  6333. dir: dir isR
  6334. -/|899: O: O1798 (predict-no)
  6335. I see 1 and I'm going to do: predict-no
  6336. ENV: Agent did: predict-no for direction R in state State-B
  6337. In State-B moving R
  6338. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  6339. predict error 0
  6340. dir: dir isL
  6341. \-/900: O: O1799 (predict-yes)
  6342. I see 1 and I'm going to do: predict-yes
  6343. ENV: Agent did: predict-yes for direction L in state State-B
  6344. In State-B moving L
  6345. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  6346. predict error 0
  6347. dir: dir isU
  6348. |\-901: O: O1802 (predict-no)
  6349. I see 1 and I'm going to do: predict-no
  6350. ENV: Agent did: predict-no for direction U in state State-A
  6351. In State-A moving U
  6352. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  6353. predict error 0
  6354. dir: dir isU
  6355. /902: O: O1804 (predict-no)
  6356. I see 1 and I'm going to do: predict-no
  6357. ENV: Agent did: predict-no for direction U in state State-A
  6358. In State-A moving U
  6359. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  6360. predict error 0
  6361. dir: dir isL
  6362. |\-903: O: O1806 (predict-no)
  6363. I see 1 and I'm going to do: predict-no
  6364. ENV: Agent did: predict-no for direction L in state State-A
  6365. In State-A moving L
  6366. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  6367. predict error 0
  6368. dir: dir isU
  6369. /|904: O: O1808 (predict-no)
  6370. I see 1 and I'm going to do: predict-no
  6371. ENV: Agent did: predict-no for direction U in state State-A
  6372. In State-A moving U
  6373. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  6374. predict error 0
  6375. dir: dir isR
  6376. \-/905: O: O1809 (predict-yes)
  6377. I see 1 and I'm going to do: predict-yes
  6378. ENV: Agent did: predict-yes for direction R in state State-A
  6379. In State-A moving R
  6380. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  6381. predict error 0
  6382. dir: dir isR
  6383. |\906: O: O1812 (predict-no)
  6384. I see 1 and I'm going to do: predict-no
  6385. ENV: Agent did: predict-no for direction R in state State-B
  6386. In State-B moving R
  6387. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  6388. predict error 0
  6389. dir: dir isU
  6390. -/|907: O: O1814 (predict-no)
  6391. I see 1 and I'm going to do: predict-no
  6392. ENV: Agent did: predict-no for direction U in state State-B
  6393. In State-B moving U
  6394. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  6395. predict error 0
  6396. dir: dir isU
  6397. \-/908: O: O1816 (predict-no)
  6398. I see 1 and I'm going to do: predict-no
  6399. ENV: Agent did: predict-no for direction U in state State-B
  6400. In State-B moving U
  6401. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  6402. predict error 0
  6403. dir: dir isR
  6404. |\909: O: O1818 (predict-no)
  6405. I see 1 and I'm going to do: predict-no
  6406. ENV: Agent did: predict-no for direction R in state State-B
  6407. In State-B moving R
  6408. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  6409. predict error 0
  6410. dir: dir isL
  6411. -/|910: O: O1819 (predict-yes)
  6412. I see 1 and I'm going to do: predict-yes
  6413. ENV: Agent did: predict-yes for direction L in state State-B
  6414. In State-B moving L
  6415. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  6416. predict error 0
  6417. dir: dir isU
  6418. \-/911: O: O1822 (predict-no)
  6419. I see 1 and I'm going to do: predict-no
  6420. ENV: Agent did: predict-no for direction U in state State-A
  6421. In State-A moving U
  6422. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  6423. predict error 0
  6424. dir: dir isL
  6425. |912: O: O1824 (predict-no)
  6426. I see 1 and I'm going to do: predict-no
  6427. ENV: Agent did: predict-no for direction L in state State-A
  6428. In State-A moving L
  6429. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  6430. predict error 0
  6431. dir: dir isR
  6432. \-913: O: O1825 (predict-yes)
  6433. I see 1 and I'm going to do: predict-yes
  6434. ENV: Agent did: predict-yes for direction R in state State-A
  6435. In State-A moving R
  6436. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  6437. predict error 0
  6438. dir: dir isU
  6439. /|914: O: O1828 (predict-no)
  6440. I see 1 and I'm going to do: predict-no
  6441. ENV: Agent did: predict-no for direction U in state State-B
  6442. In State-B moving U
  6443. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  6444. predict error 0
  6445. dir: dir isL
  6446. \-/915: O: O1829 (predict-yes)
  6447. I see 1 and I'm going to do: predict-yes
  6448. ENV: Agent did: predict-yes for direction L in state State-B
  6449. In State-B moving L
  6450. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  6451. predict error 0
  6452. dir: dir isL
  6453. |\916: O: O1832 (predict-no)
  6454. I see 1 and I'm going to do: predict-no
  6455. ENV: Agent did: predict-no for direction L in state State-A
  6456. In State-A moving L
  6457. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  6458. predict error 0
  6459. dir: dir isU
  6460. -/|\917: O: O1834 (predict-no)
  6461. I see 1 and I'm going to do: predict-no
  6462. ENV: Agent did: predict-no for direction U in state State-A
  6463. In State-A moving U
  6464. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  6465. predict error 0
  6466. dir: dir isU
  6467. -/918: O: O1836 (predict-no)
  6468. I see 1 and I'm going to do: predict-no
  6469. ENV: Agent did: predict-no for direction U in state State-A
  6470. In State-A moving U
  6471. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  6472. predict error 0
  6473. dir: dir isL
  6474. |919: O: O1838 (predict-no)
  6475. I see 1 and I'm going to do: predict-no
  6476. ENV: Agent did: predict-no for direction L in state State-A
  6477. In State-A moving L
  6478. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  6479. predict error 0
  6480. dir: dir isR
  6481. \-/920: O: O1839 (predict-yes)
  6482. I see 1 and I'm going to do: predict-yes
  6483. ENV: Agent did: predict-yes for direction R in state State-A
  6484. In State-A moving R
  6485. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  6486. predict error 0
  6487. dir: dir isL
  6488. |\-921: O: O1841 (predict-yes)
  6489. I see 1 and I'm going to do: predict-yes
  6490. ENV: Agent did: predict-yes for direction L in state State-B
  6491. In State-B moving L
  6492. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  6493. predict error 0
  6494. dir: dir isL
  6495. /922: O: O1844 (predict-no)
  6496. I see 1 and I'm going to do: predict-no
  6497. ENV: Agent did: predict-no for direction L in state State-A
  6498. In State-A moving L
  6499. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  6500. predict error 0
  6501. dir: dir isL
  6502. |\923: O: O1846 (predict-no)
  6503. I see 1 and I'm going to do: predict-no
  6504. ENV: Agent did: predict-no for direction L in state State-A
  6505. In State-A moving L
  6506. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  6507. predict error 0
  6508. dir: dir isU
  6509. -/|924: O: O1848 (predict-no)
  6510. I see 1 and I'm going to do: predict-no
  6511. ENV: Agent did: predict-no for direction U in state State-A
  6512. In State-A moving U
  6513. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  6514. predict error 0
  6515. dir: dir isL
  6516. \-/925: O: O1850 (predict-no)
  6517. I see 1 and I'm going to do: predict-no
  6518. ENV: Agent did: predict-no for direction L in state State-A
  6519. In State-A moving L
  6520. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  6521. predict error 0
  6522. dir: dir isL
  6523. |\926: O: O1852 (predict-no)
  6524. I see 1 and I'm going to do: predict-no
  6525. ENV: Agent did: predict-no for direction L in state State-A
  6526. In State-A moving L
  6527. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  6528. predict error 0
  6529. dir: dir isL
  6530. -/|927: O: O1854 (predict-no)
  6531. I see 1 and I'm going to do: predict-no
  6532. ENV: Agent did: predict-no for direction L in state State-A
  6533. In State-A moving L
  6534. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  6535. predict error 0
  6536. dir: dir isL
  6537. \-/928: O: O1856 (predict-no)
  6538. I see 1 and I'm going to do: predict-no
  6539. ENV: Agent did: predict-no for direction L in state State-A
  6540. In State-A moving L
  6541. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  6542. predict error 0
  6543. dir: dir isR
  6544. |\-929: O: O1857 (predict-yes)
  6545. I see 1 and I'm going to do: predict-yes
  6546. ENV: Agent did: predict-yes for direction R in state State-A
  6547. In State-A moving R
  6548. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  6549. predict error 0
  6550. dir: dir isU
  6551. /|\930: O: O1860 (predict-no)
  6552. I see 1 and I'm going to do: predict-no
  6553. ENV: Agent did: predict-no for direction U in state State-B
  6554. In State-B moving U
  6555. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  6556. predict error 0
  6557. dir: dir isU
  6558. -/|931: O: O1862 (predict-no)
  6559. I see 1 and I'm going to do: predict-no
  6560. ENV: Agent did: predict-no for direction U in state State-B
  6561. In State-B moving U
  6562. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  6563. predict error 0
  6564. dir: dir isR
  6565. \932: O: O1864 (predict-no)
  6566. I see 1 and I'm going to do: predict-no
  6567. ENV: Agent did: predict-no for direction R in state State-B
  6568. In State-B moving R
  6569. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  6570. predict error 0
  6571. dir: dir isU
  6572. -/933: O: O1866 (predict-no)
  6573. I see 1 and I'm going to do: predict-no
  6574. ENV: Agent did: predict-no for direction U in state State-B
  6575. In State-B moving U
  6576. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  6577. predict error 0
  6578. dir: dir isL
  6579. |\934: O: O1867 (predict-yes)
  6580. I see 1 and I'm going to do: predict-yes
  6581. ENV: Agent did: predict-yes for direction L in state State-B
  6582. In State-B moving L
  6583. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  6584. predict error 0
  6585. dir: dir isL
  6586. -/|935: O: O1870 (predict-no)
  6587. I see 1 and I'm going to do: predict-no
  6588. ENV: Agent did: predict-no for direction L in state State-A
  6589. In State-A moving L
  6590. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  6591. predict error 0
  6592. dir: dir isU
  6593. \-/936: O: O1872 (predict-no)
  6594. I see 1 and I'm going to do: predict-no
  6595. ENV: Agent did: predict-no for direction U in state State-A
  6596. In State-A moving U
  6597. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  6598. predict error 0
  6599. dir: dir isL
  6600. |\937: O: O1874 (predict-no)
  6601. I see 1 and I'm going to do: predict-no
  6602. ENV: Agent did: predict-no for direction L in state State-A
  6603. In State-A moving L
  6604. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  6605. predict error 0
  6606. dir: dir isL
  6607. -/938: O: O1876 (predict-no)
  6608. I see 1 and I'm going to do: predict-no
  6609. ENV: Agent did: predict-no for direction L in state State-A
  6610. In State-A moving L
  6611. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  6612. predict error 0
  6613. dir: dir isR
  6614. |\939: O: O1877 (predict-yes)
  6615. I see 1 and I'm going to do: predict-yes
  6616. ENV: Agent did: predict-yes for direction R in state State-A
  6617. In State-A moving R
  6618. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  6619. predict error 0
  6620. dir: dir isL
  6621. -/940: O: O1879 (predict-yes)
  6622. I see 1 and I'm going to do: predict-yes
  6623. ENV: Agent did: predict-yes for direction L in state State-B
  6624. In State-B moving L
  6625. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  6626. predict error 0
  6627. dir: dir isR
  6628. |\-941: O: O1881 (predict-yes)
  6629. I see 1 and I'm going to do: predict-yes
  6630. ENV: Agent did: predict-yes for direction R in state State-A
  6631. In State-A moving R
  6632. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  6633. predict error 0
  6634. dir: dir isL
  6635. /942: O: O1883 (predict-yes)
  6636. I see 1 and I'm going to do: predict-yes
  6637. ENV: Agent did: predict-yes for direction L in state State-B
  6638. In State-B moving L
  6639. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  6640. predict error 0
  6641. dir: dir isL
  6642. |\-943: O: O1886 (predict-no)
  6643. I see 1 and I'm going to do: predict-no
  6644. ENV: Agent did: predict-no for direction L in state State-A
  6645. In State-A moving L
  6646. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  6647. predict error 0
  6648. dir: dir isU
  6649. /|\944: O: O1888 (predict-no)
  6650. I see 1 and I'm going to do: predict-no
  6651. ENV: Agent did: predict-no for direction U in state State-A
  6652. In State-A moving U
  6653. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  6654. predict error 0
  6655. dir: dir isL
  6656. -/945: O: O1890 (predict-no)
  6657. I see 1 and I'm going to do: predict-no
  6658. ENV: Agent did: predict-no for direction L in state State-A
  6659. In State-A moving L
  6660. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  6661. predict error 0
  6662. dir: dir isU
  6663. |\-946: O: O1892 (predict-no)
  6664. I see 1 and I'm going to do: predict-no
  6665. ENV: Agent did: predict-no for direction U in state State-A
  6666. In State-A moving U
  6667. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  6668. predict error 0
  6669. dir: dir isL
  6670. /|947: O: O1894 (predict-no)
  6671. I see 1 and I'm going to do: predict-no
  6672. ENV: Agent did: predict-no for direction L in state State-A
  6673. In State-A moving L
  6674. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  6675. predict error 0
  6676. dir: dir isU
  6677. \948: O: O1896 (predict-no)
  6678. I see 1 and I'm going to do: predict-no
  6679. ENV: Agent did: predict-no for direction U in state State-A
  6680. In State-A moving U
  6681. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  6682. predict error 0
  6683. dir: dir isU
  6684. -/|949: O: O1898 (predict-no)
  6685. I see 1 and I'm going to do: predict-no
  6686. ENV: Agent did: predict-no for direction U in state State-A
  6687. In State-A moving U
  6688. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  6689. predict error 0
  6690. dir: dir isR
  6691. \-/950: O: O1899 (predict-yes)
  6692. I see 1 and I'm going to do: predict-yes
  6693. ENV: Agent did: predict-yes for direction R in state State-A
  6694. In State-A moving R
  6695. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  6696. predict error 0
  6697. dir: dir isL
  6698. |\-/|\-/|--- Input Phase ---
  6699. =>WM: (13351: I2 ^dir L)
  6700. =>WM: (13350: I2 ^reward 1)
  6701. =>WM: (13349: I2 ^see 1)
  6702. =>WM: (13348: N950 ^status complete)
  6703. <=WM: (13337: I2 ^dir R)
  6704. <=WM: (13336: I2 ^reward 1)
  6705. <=WM: (13335: I2 ^see 0)
  6706. =>WM: (13352: I2 ^level-1 R1-root)
  6707. <=WM: (13338: I2 ^level-1 L0-root)
  6708. --- END Input Phase ---
  6709. --- Proposal Phase ---
  6710. --- Inner Elaboration Phase, active level 1 (S1) ---
  6711. Firing rl*prefer*rvt*predict-yes*H0*1*H1*22
  6712. -->
  6713. (S1 ^operator O1899 = 0.4768760547163575)
  6714. Firing rl*prefer*rvt*predict-no*H0*2*H1*10
  6715. -->
  6716. (S1 ^operator O1900 = -0.01194930198035649)
  6717. Firing prefer*rvt*predict-no*H0*2*H1
  6718. -->
  6719. Firing prefer*rvt*predict-yes*H0*1*H1
  6720. -->
  6721. Firing elaborate*copy-see-to-output-link
  6722. -->
  6723. (I3 ^see 1 +)
  6724. Firing elaborate*reward*based*on*reward
  6725. -->
  6726. (R954 ^value 1 +)
  6727. (R1 ^reward R954 +)
  6728. Firing propose*predict-yes
  6729. -->
  6730. (O1901 ^name predict-yes +)
  6731. (S1 ^operator O1901 +)
  6732. Firing propose*predict-no
  6733. -->
  6734. (O1902 ^name predict-no +)
  6735. (S1 ^operator O1902 +)
  6736. Firing rl*prefer*rvt*predict-no*H0*2
  6737. -->
  6738. (S1 ^operator O1900 = 0.2550132695707557)
  6739. Firing rl*prefer*rvt*predict-yes*H0*1
  6740. -->
  6741. (S1 ^operator O1899 = 0.5231202597544767)
  6742. Firing prefer*rvt*predict-yes*H0
  6743. -->
  6744. Firing prefer*rvt*predict-no*H0
  6745. -->
  6746. Firing elaborate*copy-dir-to-output-link
  6747. -->
  6748. (I3 ^dir L +)
  6749. inner elaboration loop at bottom goal.
  6750. Retracting elaborate*copy-see-to-output-link
  6751. -->
  6752. (I3 ^see 0 +)
  6753. Retracting propose*predict-no
  6754. -->
  6755. (O1900 ^name predict-no +)
  6756. (S1 ^operator O1900 +)
  6757. Retracting propose*predict-yes
  6758. -->
  6759. (O1899 ^name predict-yes +)
  6760. (S1 ^operator O1899 +)
  6761. Retracting elaborate*reward*based*on*reward
  6762. -->
  6763. (R953 ^value 1 +)
  6764. (R1 ^reward R953 +)
  6765. Retracting elaborate*copy-dir-to-output-link
  6766. -->
  6767. (I3 ^dir R +)
  6768. Retracting rl*prefer*rvt*predict-no*H0*4
  6769. -->
  6770. (S1 ^operator O1900 = 0.1269768259493387)
  6771. Retracting rl*prefer*rvt*predict-no*H0*4*H1*13
  6772. -->
  6773. (S1 ^operator O1900 = 0.4910065094545203)
  6774. Retracting rl*prefer*rvt*predict-yes*H0*3
  6775. -->
  6776. (S1 ^operator O1899 = 0.3829293116822346)
  6777. Retracting rl*prefer*rvt*predict-yes*H0*3*H1*14
  6778. -->
  6779. (S1 ^operator O1899 = 0.6170848495907595)
  6780. =>WM: (13360: S1 ^operator O1902 +)
  6781. =>WM: (13359: S1 ^operator O1901 +)
  6782. =>WM: (13358: I3 ^dir L)
  6783. =>WM: (13357: O1902 ^name predict-no)
  6784. =>WM: (13356: O1901 ^name predict-yes)
  6785. =>WM: (13355: R954 ^value 1)
  6786. =>WM: (13354: R1 ^reward R954)
  6787. =>WM: (13353: I3 ^see 1)
  6788. <=WM: (13344: S1 ^operator O1899 +)
  6789. <=WM: (13346: S1 ^operator O1899)
  6790. <=WM: (13345: S1 ^operator O1900 +)
  6791. <=WM: (13343: I3 ^dir R)
  6792. <=WM: (13339: R1 ^reward R953)
  6793. <=WM: (13255: I3 ^see 0)
  6794. <=WM: (13342: O1900 ^name predict-no)
  6795. <=WM: (13341: O1899 ^name predict-yes)
  6796. <=WM: (13340: R953 ^value 1)
  6797. --- Inner Elaboration Phase, active level 1 (S1) ---
  6798. Firing prefer*rvt*predict-yes*H0
  6799. -->
  6800. Firing rl*prefer*rvt*predict-yes*H0*1
  6801. -->
  6802. (S1 ^operator O1901 = 0.5231202597544767)
  6803. Firing prefer*rvt*predict-yes*H0*1*H1
  6804. -->
  6805. Firing rl*prefer*rvt*predict-yes*H0*1*H1*22
  6806. -->
  6807. (S1 ^operator O1901 = 0.4768760547163575)
  6808. Firing prefer*rvt*predict-no*H0
  6809. -->
  6810. Firing rl*prefer*rvt*predict-no*H0*2
  6811. -->
  6812. (S1 ^operator O1902 = 0.2550132695707557)
  6813. Firing prefer*rvt*predict-no*H0*2*H1
  6814. -->
  6815. Firing rl*prefer*rvt*predict-no*H0*2*H1*10
  6816. -->
  6817. (S1 ^operator O1902 = -0.01194930198035649)
  6818. inner elaboration loop at bottom goal.
  6819. Retracting rl*prefer*rvt*predict-no*H0*2
  6820. -->
  6821. (S1 ^operator O1900 = 0.2550132695707557)
  6822. Retracting rl*prefer*rvt*predict-no*H0*2*H1*10
  6823. -->
  6824. (S1 ^operator O1900 = -0.01194930198035649)
  6825. Retracting rl*prefer*rvt*predict-yes*H0*1
  6826. -->
  6827. (S1 ^operator O1899 = 0.5231202597544767)
  6828. Retracting rl*prefer*rvt*predict-yes*H0*1*H1*22
  6829. -->
  6830. (S1 ^operator O1899 = 0.4768760547163575)
  6831. --- END Proposal Phase ---
  6832. --- Decision Phase ---
  6833. RL update rl*prefer*rvt*predict-yes*H0*3 0.673123 -0.290194 0.382929 -> 0.673122 -0.290194 0.382927(R,m,v=1,0.958904,0.0396788)
  6834. RL update rl*prefer*rvt*predict-yes*H0*3*H1*14 0.326889 0.290195 0.617085 -> 0.326888 0.290195 0.617083(R,m,v=1,1,0)
  6835. =>WM: (13361: S1 ^operator O1901)
  6836. 951: O: O1901 (predict-yes)
  6837. --- END Decision Phase ---
  6838. --- Application Phase ---
  6839. --- Firing Productions (PE) For State At Depth 1 ---
  6840. --- Inner Elaboration Phase, active level 1 (S1) ---
  6841. Firing apply*operator
  6842. -->
  6843. (I3 ^predict-yes N951 + :O )
  6844. Firing apply*operator*complete
  6845. -->
  6846. (I3 ^predict-yes N950 - :O )
  6847. inner elaboration loop at bottom goal.
  6848. --- Change Working Memory (PE) ---
  6849. =>WM: (13362: I3 ^predict-yes N951)
  6850. <=WM: (13348: N950 ^status complete)
  6851. <=WM: (13347: I3 ^predict-yes N950)
  6852. --- Firing Productions (IE) For State At Depth 1 ---
  6853. --- Inner Elaboration Phase, active level 1 (S1) ---
  6854. Firing monitor*world
  6855. -->
  6856. I see 1 and I'm going to do: predict-yes inner elaboration loop at bottom goal.
  6857. --- Change Working Memory (IE) ---
  6858. --- END Application Phase ---
  6859. --- Output Phase ---
  6860. ENV: Agent did: predict-yes for direction L in state State-B
  6861. In State-B moving L
  6862. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  6863. predict error 0
  6864. dir: dir isL
  6865. --- END Output Phase ---
  6866. \--- Input Phase ---
  6867. =>WM: (13366: I2 ^dir L)
  6868. =>WM: (13365: I2 ^reward 1)
  6869. =>WM: (13364: I2 ^see 1)
  6870. =>WM: (13363: N951 ^status complete)
  6871. <=WM: (13351: I2 ^dir L)
  6872. <=WM: (13350: I2 ^reward 1)
  6873. <=WM: (13349: I2 ^see 1)
  6874. =>WM: (13367: I2 ^level-1 L1-root)
  6875. <=WM: (13352: I2 ^level-1 R1-root)
  6876. --- END Input Phase ---
  6877. --- Proposal Phase ---
  6878. --- Inner Elaboration Phase, active level 1 (S1) ---
  6879. Firing rl*prefer*rvt*predict-yes*H0*1*H1*20
  6880. -->
  6881. (S1 ^operator O1901 = 0.1693592933936033)
  6882. Firing rl*prefer*rvt*predict-no*H0*2*H1*11
  6883. -->
  6884. (S1 ^operator O1902 = 0.7449862034212327)
  6885. Firing prefer*rvt*predict-no*H0*2*H1
  6886. -->
  6887. Firing prefer*rvt*predict-yes*H0*1*H1
  6888. -->
  6889. Firing elaborate*copy-see-to-output-link
  6890. -->
  6891. (I3 ^see 1 +)
  6892. Firing elaborate*reward*based*on*reward
  6893. -->
  6894. (R955 ^value 1 +)
  6895. (R1 ^reward R955 +)
  6896. Firing propose*predict-yes
  6897. -->
  6898. (O1903 ^name predict-yes +)
  6899. (S1 ^operator O1903 +)
  6900. Firing propose*predict-no
  6901. -->
  6902. (O1904 ^name predict-no +)
  6903. (S1 ^operator O1904 +)
  6904. Firing rl*prefer*rvt*predict-no*H0*2
  6905. -->
  6906. (S1 ^operator O1902 = 0.2550132695707557)
  6907. Firing rl*prefer*rvt*predict-yes*H0*1
  6908. -->
  6909. (S1 ^operator O1901 = 0.5231202597544767)
  6910. Firing prefer*rvt*predict-yes*H0
  6911. -->
  6912. Firing prefer*rvt*predict-no*H0
  6913. -->
  6914. Firing elaborate*copy-dir-to-output-link
  6915. -->
  6916. (I3 ^dir L +)
  6917. inner elaboration loop at bottom goal.
  6918. Retracting elaborate*copy-see-to-output-link
  6919. -->
  6920. (I3 ^see 1 +)
  6921. Retracting propose*predict-no
  6922. -->
  6923. (O1902 ^name predict-no +)
  6924. (S1 ^operator O1902 +)
  6925. Retracting propose*predict-yes
  6926. -->
  6927. (O1901 ^name predict-yes +)
  6928. (S1 ^operator O1901 +)
  6929. Retracting elaborate*reward*based*on*reward
  6930. -->
  6931. (R954 ^value 1 +)
  6932. (R1 ^reward R954 +)
  6933. Retracting elaborate*copy-dir-to-output-link
  6934. -->
  6935. (I3 ^dir L +)
  6936. Retracting rl*prefer*rvt*predict-no*H0*2*H1*10
  6937. -->
  6938. (S1 ^operator O1902 = -0.01194930198035649)
  6939. Retracting rl*prefer*rvt*predict-no*H0*2
  6940. -->
  6941. (S1 ^operator O1902 = 0.2550132695707557)
  6942. Retracting rl*prefer*rvt*predict-yes*H0*1*H1*22
  6943. -->
  6944. (S1 ^operator O1901 = 0.4768760547163575)
  6945. Retracting rl*prefer*rvt*predict-yes*H0*1
  6946. -->
  6947. (S1 ^operator O1901 = 0.5231202597544767)
  6948. =>WM: (13373: S1 ^operator O1904 +)
  6949. =>WM: (13372: S1 ^operator O1903 +)
  6950. =>WM: (13371: O1904 ^name predict-no)
  6951. =>WM: (13370: O1903 ^name predict-yes)
  6952. =>WM: (13369: R955 ^value 1)
  6953. =>WM: (13368: R1 ^reward R955)
  6954. <=WM: (13359: S1 ^operator O1901 +)
  6955. <=WM: (13361: S1 ^operator O1901)
  6956. <=WM: (13360: S1 ^operator O1902 +)
  6957. <=WM: (13354: R1 ^reward R954)
  6958. <=WM: (13357: O1902 ^name predict-no)
  6959. <=WM: (13356: O1901 ^name predict-yes)
  6960. <=WM: (13355: R954 ^value 1)
  6961. --- Inner Elaboration Phase, active level 1 (S1) ---
  6962. Firing prefer*rvt*predict-yes*H0
  6963. -->
  6964. Firing rl*prefer*rvt*predict-yes*H0*1
  6965. -->
  6966. (S1 ^operator O1903 = 0.5231202597544767)
  6967. Firing prefer*rvt*predict-yes*H0*1*H1
  6968. -->
  6969. Firing rl*prefer*rvt*predict-yes*H0*1*H1*20
  6970. -->
  6971. (S1 ^operator O1903 = 0.1693592933936033)
  6972. Firing prefer*rvt*predict-no*H0
  6973. -->
  6974. Firing rl*prefer*rvt*predict-no*H0*2
  6975. -->
  6976. (S1 ^operator O1904 = 0.2550132695707557)
  6977. Firing prefer*rvt*predict-no*H0*2*H1
  6978. -->
  6979. Firing rl*prefer*rvt*predict-no*H0*2*H1*11
  6980. -->
  6981. (S1 ^operator O1904 = 0.7449862034212327)
  6982. inner elaboration loop at bottom goal.
  6983. Retracting rl*prefer*rvt*predict-no*H0*2
  6984. -->
  6985. (S1 ^operator O1902 = 0.2550132695707557)
  6986. Retracting rl*prefer*rvt*predict-no*H0*2*H1*11
  6987. -->
  6988. (S1 ^operator O1902 = 0.7449862034212327)
  6989. Retracting rl*prefer*rvt*predict-yes*H0*1
  6990. -->
  6991. (S1 ^operator O1901 = 0.5231202597544767)
  6992. Retracting rl*prefer*rvt*predict-yes*H0*1*H1*20
  6993. -->
  6994. (S1 ^operator O1901 = 0.1693592933936033)
  6995. --- END Proposal Phase ---
  6996. --- Decision Phase ---
  6997. RL update rl*prefer*rvt*predict-yes*H0*1 0.72796 -0.20484 0.52312 -> 0.727961 -0.20484 0.523121(R,m,v=1,0.977941,0.021732)
  6998. RL update rl*prefer*rvt*predict-yes*H0*1*H1*22 0.272035 0.204841 0.476876 -> 0.272036 0.204841 0.476877(R,m,v=1,1,0)
  6999. =>WM: (13374: S1 ^operator O1904)
  7000. 952: O: O1904 (predict-no)
  7001. --- END Decision Phase ---
  7002. --- Application Phase ---
  7003. --- Firing Productions (PE) For State At Depth 1 ---
  7004. --- Inner Elaboration Phase, active level 1 (S1) ---
  7005. Firing apply*operator
  7006. -->
  7007. (I3 ^predict-no N952 + :O )
  7008. Firing apply*operator*complete
  7009. -->
  7010. (I3 ^predict-yes N951 - :O )
  7011. inner elaboration loop at bottom goal.
  7012. --- Change Working Memory (PE) ---
  7013. =>WM: (13375: I3 ^predict-no N952)
  7014. <=WM: (13363: N951 ^status complete)
  7015. <=WM: (13362: I3 ^predict-yes N951)
  7016. --- Firing Productions (IE) For State At Depth 1 ---
  7017. --- Inner Elaboration Phase, active level 1 (S1) ---
  7018. Firing monitor*world
  7019. -->
  7020. I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
  7021. --- Change Working Memory (IE) ---
  7022. --- END Application Phase ---
  7023. --- Output Phase ---
  7024. ENV: Agent did: predict-no for direction L in state State-A
  7025. In State-A moving L
  7026. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  7027. predict error 0
  7028. dir: dir isU
  7029. --- END Output Phase ---
  7030. -/|\--- Input Phase ---
  7031. =>WM: (13379: I2 ^dir U)
  7032. =>WM: (13378: I2 ^reward 1)
  7033. =>WM: (13377: I2 ^see 0)
  7034. =>WM: (13376: N952 ^status complete)
  7035. <=WM: (13366: I2 ^dir L)
  7036. <=WM: (13365: I2 ^reward 1)
  7037. <=WM: (13364: I2 ^see 1)
  7038. =>WM: (13380: I2 ^level-1 L0-root)
  7039. <=WM: (13367: I2 ^level-1 L1-root)
  7040. --- END Input Phase ---
  7041. --- Proposal Phase ---
  7042. --- Inner Elaboration Phase, active level 1 (S1) ---
  7043. Firing elaborate*copy-see-to-output-link
  7044. -->
  7045. (I3 ^see 0 +)
  7046. Firing elaborate*reward*based*on*reward
  7047. -->
  7048. (R956 ^value 1 +)
  7049. (R1 ^reward R956 +)
  7050. Firing propose*predict-yes
  7051. -->
  7052. (O1905 ^name predict-yes +)
  7053. (S1 ^operator O1905 +)
  7054. Firing propose*predict-no
  7055. -->
  7056. (O1906 ^name predict-no +)
  7057. (S1 ^operator O1906 +)
  7058. Firing rl*prefer*rvt*predict-no*H0*6
  7059. -->
  7060. (S1 ^operator O1904 = 0.9999999999999999)
  7061. Firing rl*prefer*rvt*predict-yes*H0*5
  7062. -->
  7063. (S1 ^operator O1903 = 0.)
  7064. Firing prefer*rvt*predict-yes*H0
  7065. -->
  7066. Firing prefer*rvt*predict-no*H0
  7067. -->
  7068. Firing elaborate*copy-dir-to-output-link
  7069. -->
  7070. (I3 ^dir U +)
  7071. inner elaboration loop at bottom goal.
  7072. Retracting elaborate*copy-see-to-output-link
  7073. -->
  7074. (I3 ^see 1 +)
  7075. Retracting propose*predict-no
  7076. -->
  7077. (O1904 ^name predict-no +)
  7078. (S1 ^operator O1904 +)
  7079. Retracting propose*predict-yes
  7080. -->
  7081. (O1903 ^name predict-yes +)
  7082. (S1 ^operator O1903 +)
  7083. Retracting elaborate*reward*based*on*reward
  7084. -->
  7085. (R955 ^value 1 +)
  7086. (R1 ^reward R955 +)
  7087. Retracting elaborate*copy-dir-to-output-link
  7088. -->
  7089. (I3 ^dir L +)
  7090. Retracting rl*prefer*rvt*predict-no*H0*2*H1*11
  7091. -->
  7092. (S1 ^operator O1904 = 0.7449862034212327)
  7093. Retracting rl*prefer*rvt*predict-no*H0*2
  7094. -->
  7095. (S1 ^operator O1904 = 0.2550132695707557)
  7096. Retracting rl*prefer*rvt*predict-yes*H0*1*H1*20
  7097. -->
  7098. (S1 ^operator O1903 = 0.1693592933936033)
  7099. Retracting rl*prefer*rvt*predict-yes*H0*1
  7100. -->
  7101. (S1 ^operator O1903 = 0.5231208125838516)
  7102. =>WM: (13388: S1 ^operator O1906 +)
  7103. =>WM: (13387: S1 ^operator O1905 +)
  7104. =>WM: (13386: I3 ^dir U)
  7105. =>WM: (13385: O1906 ^name predict-no)
  7106. =>WM: (13384: O1905 ^name predict-yes)
  7107. =>WM: (13383: R956 ^value 1)
  7108. =>WM: (13382: R1 ^reward R956)
  7109. =>WM: (13381: I3 ^see 0)
  7110. <=WM: (13372: S1 ^operator O1903 +)
  7111. <=WM: (13373: S1 ^operator O1904 +)
  7112. <=WM: (13374: S1 ^operator O1904)
  7113. <=WM: (13358: I3 ^dir L)
  7114. <=WM: (13368: R1 ^reward R955)
  7115. <=WM: (13353: I3 ^see 1)
  7116. <=WM: (13371: O1904 ^name predict-no)
  7117. <=WM: (13370: O1903 ^name predict-yes)
  7118. <=WM: (13369: R955 ^value 1)
  7119. --- Inner Elaboration Phase, active level 1 (S1) ---
  7120. Firing prefer*rvt*predict-yes*H0
  7121. -->
  7122. Firing rl*prefer*rvt*predict-yes*H0*5
  7123. -->
  7124. (S1 ^operator O1905 = 0.)
  7125. Firing prefer*rvt*predict-no*H0
  7126. -->
  7127. Firing rl*prefer*rvt*predict-no*H0*6
  7128. -->
  7129. (S1 ^operator O1906 = 0.9999999999999999)
  7130. inner elaboration loop at bottom goal.
  7131. Retracting rl*prefer*rvt*predict-no*H0*6
  7132. -->
  7133. (S1 ^operator O1904 = 0.9999999999999999)
  7134. Retracting rl*prefer*rvt*predict-yes*H0*5
  7135. -->
  7136. (S1 ^operator O1903 = 0.)
  7137. --- END Proposal Phase ---
  7138. --- Decision Phase ---
  7139. RL update rl*prefer*rvt*predict-no*H0*2 0.631495 -0.376482 0.255013 -> 0.631495 -0.376482 0.255013(R,m,v=1,0.913043,0.0798289)
  7140. RL update rl*prefer*rvt*predict-no*H0*2*H1*11 0.368505 0.376481 0.744986 -> 0.368505 0.376482 0.744986(R,m,v=1,1,0)
  7141. =>WM: (13389: S1 ^operator O1906)
  7142. 953: O: O1906 (predict-no)
  7143. --- END Decision Phase ---
  7144. --- Application Phase ---
  7145. --- Firing Productions (PE) For State At Depth 1 ---
  7146. --- Inner Elaboration Phase, active level 1 (S1) ---
  7147. Firing apply*operator
  7148. -->
  7149. (I3 ^predict-no N953 + :O )
  7150. Firing apply*operator*complete
  7151. -->
  7152. (I3 ^predict-no N952 - :O )
  7153. inner elaboration loop at bottom goal.
  7154. --- Change Working Memory (PE) ---
  7155. =>WM: (13390: I3 ^predict-no N953)
  7156. <=WM: (13376: N952 ^status complete)
  7157. <=WM: (13375: I3 ^predict-no N952)
  7158. --- Firing Productions (IE) For State At Depth 1 ---
  7159. --- Inner Elaboration Phase, active level 1 (S1) ---
  7160. Firing monitor*world
  7161. -->
  7162. I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
  7163. --- Change Working Memory (IE) ---
  7164. --- END Application Phase ---
  7165. --- Output Phase ---
  7166. ENV: Agent did: predict-no for direction U in state State-A
  7167. In State-A moving U
  7168. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  7169. predict error 0
  7170. dir: dir isL
  7171. --- END Output Phase ---
  7172. -/|--- Input Phase ---
  7173. =>WM: (13394: I2 ^dir L)
  7174. =>WM: (13393: I2 ^reward 1)
  7175. =>WM: (13392: I2 ^see 0)
  7176. =>WM: (13391: N953 ^status complete)
  7177. <=WM: (13379: I2 ^dir U)
  7178. <=WM: (13378: I2 ^reward 1)
  7179. <=WM: (13377: I2 ^see 0)
  7180. =>WM: (13395: I2 ^level-1 L0-root)
  7181. <=WM: (13380: I2 ^level-1 L0-root)
  7182. --- END Input Phase ---
  7183. --- Proposal Phase ---
  7184. --- Inner Elaboration Phase, active level 1 (S1) ---
  7185. Firing rl*prefer*rvt*predict-yes*H0*1*H1*21
  7186. -->
  7187. (S1 ^operator O1905 = 0.3)
  7188. Firing rl*prefer*rvt*predict-no*H0*2*H1*12
  7189. -->
  7190. (S1 ^operator O1906 = 0.7449868594607382)
  7191. Firing prefer*rvt*predict-no*H0*2*H1
  7192. -->
  7193. Firing prefer*rvt*predict-yes*H0*1*H1
  7194. -->
  7195. Firing elaborate*copy-see-to-output-link
  7196. -->
  7197. (I3 ^see 0 +)
  7198. Firing elaborate*reward*based*on*reward
  7199. -->
  7200. (R957 ^value 1 +)
  7201. (R1 ^reward R957 +)
  7202. Firing propose*predict-yes
  7203. -->
  7204. (O1907 ^name predict-yes +)
  7205. (S1 ^operator O1907 +)
  7206. Firing propose*predict-no
  7207. -->
  7208. (O1908 ^name predict-no +)
  7209. (S1 ^operator O1908 +)
  7210. Firing rl*prefer*rvt*predict-no*H0*2
  7211. -->
  7212. (S1 ^operator O1906 = 0.2550133486219575)
  7213. Firing rl*prefer*rvt*predict-yes*H0*1
  7214. -->
  7215. (S1 ^operator O1905 = 0.5231208125838516)
  7216. Firing prefer*rvt*predict-yes*H0
  7217. -->
  7218. Firing prefer*rvt*predict-no*H0
  7219. -->
  7220. Firing elaborate*copy-dir-to-output-link
  7221. -->
  7222. (I3 ^dir L +)
  7223. inner elaboration loop at bottom goal.
  7224. Retracting elaborate*copy-see-to-output-link
  7225. -->
  7226. (I3 ^see 0 +)
  7227. Retracting propose*predict-no
  7228. -->
  7229. (O1906 ^name predict-no +)
  7230. (S1 ^operator O1906 +)
  7231. Retracting propose*predict-yes
  7232. -->
  7233. (O1905 ^name predict-yes +)
  7234. (S1 ^operator O1905 +)
  7235. Retracting elaborate*reward*based*on*reward
  7236. -->
  7237. (R956 ^value 1 +)
  7238. (R1 ^reward R956 +)
  7239. Retracting elaborate*copy-dir-to-output-link
  7240. -->
  7241. (I3 ^dir U +)
  7242. Retracting rl*prefer*rvt*predict-no*H0*6
  7243. -->
  7244. (S1 ^operator O1906 = 0.9999999999999999)
  7245. Retracting rl*prefer*rvt*predict-yes*H0*5
  7246. -->
  7247. (S1 ^operator O1905 = 0.)
  7248. =>WM: (13402: S1 ^operator O1908 +)
  7249. =>WM: (13401: S1 ^operator O1907 +)
  7250. =>WM: (13400: I3 ^dir L)
  7251. =>WM: (13399: O1908 ^name predict-no)
  7252. =>WM: (13398: O1907 ^name predict-yes)
  7253. =>WM: (13397: R957 ^value 1)
  7254. =>WM: (13396: R1 ^reward R957)
  7255. <=WM: (13387: S1 ^operator O1905 +)
  7256. <=WM: (13388: S1 ^operator O1906 +)
  7257. <=WM: (13389: S1 ^operator O1906)
  7258. <=WM: (13386: I3 ^dir U)
  7259. <=WM: (13382: R1 ^reward R956)
  7260. <=WM: (13385: O1906 ^name predict-no)
  7261. <=WM: (13384: O1905 ^name predict-yes)
  7262. <=WM: (13383: R956 ^value 1)
  7263. --- Inner Elaboration Phase, active level 1 (S1) ---
  7264. Firing prefer*rvt*predict-yes*H0
  7265. -->
  7266. Firing rl*prefer*rvt*predict-yes*H0*1*H1*21
  7267. -->
  7268. (S1 ^operator O1907 = 0.3)
  7269. Firing rl*prefer*rvt*predict-yes*H0*1
  7270. -->
  7271. (S1 ^operator O1907 = 0.5231208125838516)
  7272. Firing prefer*rvt*predict-yes*H0*1*H1
  7273. -->
  7274. Firing prefer*rvt*predict-no*H0
  7275. -->
  7276. Firing rl*prefer*rvt*predict-no*H0*2*H1*12
  7277. -->
  7278. (S1 ^operator O1908 = 0.7449868594607382)
  7279. Firing rl*prefer*rvt*predict-no*H0*2
  7280. -->
  7281. (S1 ^operator O1908 = 0.2550133486219575)
  7282. Firing prefer*rvt*predict-no*H0*2*H1
  7283. -->
  7284. inner elaboration loop at bottom goal.
  7285. Retracting rl*prefer*rvt*predict-no*H0*2
  7286. -->
  7287. (S1 ^operator O1906 = 0.2550133486219575)
  7288. Retracting rl*prefer*rvt*predict-no*H0*2*H1*12
  7289. -->
  7290. (S1 ^operator O1906 = 0.7449868594607382)
  7291. Retracting rl*prefer*rvt*predict-yes*H0*1
  7292. -->
  7293. (S1 ^operator O1905 = 0.5231208125838516)
  7294. Retracting rl*prefer*rvt*predict-yes*H0*1*H1*21
  7295. -->
  7296. (S1 ^operator O1905 = 0.3)
  7297. --- END Proposal Phase ---
  7298. --- Decision Phase ---
  7299. RL update rl*prefer*rvt*predict-no*H0*6 1 0 1 -> 1 0 1(R,m,v=1,1,0)
  7300. =>WM: (13403: 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-no N953 - :O )
  7312. inner elaboration loop at bottom goal.
  7313. --- Change Working Memory (PE) ---
  7314. =>WM: (13404: I3 ^predict-no N954)
  7315. <=WM: (13391: N953 ^status complete)
  7316. <=WM: (13390: I3 ^predict-no 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 L in state State-A
  7326. In State-A moving L
  7327. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  7328. predict error 0
  7329. dir: dir isL
  7330. --- END Output Phase ---
  7331. \-/--- Input Phase ---
  7332. =>WM: (13408: I2 ^dir L)
  7333. =>WM: (13407: I2 ^reward 1)
  7334. =>WM: (13406: I2 ^see 0)
  7335. =>WM: (13405: N954 ^status complete)
  7336. <=WM: (13394: I2 ^dir L)
  7337. <=WM: (13393: I2 ^reward 1)
  7338. <=WM: (13392: I2 ^see 0)
  7339. =>WM: (13409: I2 ^level-1 L0-root)
  7340. <=WM: (13395: I2 ^level-1 L0-root)
  7341. --- END Input Phase ---
  7342. --- Proposal Phase ---
  7343. --- Inner Elaboration Phase, active level 1 (S1) ---
  7344. Firing rl*prefer*rvt*predict-yes*H0*1*H1*21
  7345. -->
  7346. (S1 ^operator O1907 = 0.3)
  7347. Firing rl*prefer*rvt*predict-no*H0*2*H1*12
  7348. -->
  7349. (S1 ^operator O1908 = 0.7449868594607382)
  7350. Firing prefer*rvt*predict-no*H0*2*H1
  7351. -->
  7352. Firing prefer*rvt*predict-yes*H0*1*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*2
  7370. -->
  7371. (S1 ^operator O1908 = 0.2550133486219575)
  7372. Firing rl*prefer*rvt*predict-yes*H0*1
  7373. -->
  7374. (S1 ^operator O1907 = 0.5231208125838516)
  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 0 +)
  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 L +)
  7401. Retracting rl*prefer*rvt*predict-no*H0*2
  7402. -->
  7403. (S1 ^operator O1908 = 0.2550133486219575)
  7404. Retracting rl*prefer*rvt*predict-no*H0*2*H1*12
  7405. -->
  7406. (S1 ^operator O1908 = 0.7449868594607382)
  7407. Retracting rl*prefer*rvt*predict-yes*H0*1
  7408. -->
  7409. (S1 ^operator O1907 = 0.5231208125838516)
  7410. Retracting rl*prefer*rvt*predict-yes*H0*1*H1*21
  7411. -->
  7412. (S1 ^operator O1907 = 0.3)
  7413. =>WM: (13415: S1 ^operator O1910 +)
  7414. =>WM: (13414: S1 ^operator O1909 +)
  7415. =>WM: (13413: O1910 ^name predict-no)
  7416. =>WM: (13412: O1909 ^name predict-yes)
  7417. =>WM: (13411: R958 ^value 1)
  7418. =>WM: (13410: R1 ^reward R958)
  7419. <=WM: (13401: S1 ^operator O1907 +)
  7420. <=WM: (13402: S1 ^operator O1908 +)
  7421. <=WM: (13403: S1 ^operator O1908)
  7422. <=WM: (13396: R1 ^reward R957)
  7423. <=WM: (13399: O1908 ^name predict-no)
  7424. <=WM: (13398: O1907 ^name predict-yes)
  7425. <=WM: (13397: R957 ^value 1)
  7426. --- Inner Elaboration Phase, active level 1 (S1) ---
  7427. Firing prefer*rvt*predict-yes*H0
  7428. -->
  7429. Firing rl*prefer*rvt*predict-yes*H0*1*H1*21
  7430. -->
  7431. (S1 ^operator O1909 = 0.3)
  7432. Firing rl*prefer*rvt*predict-yes*H0*1
  7433. -->
  7434. (S1 ^operator O1909 = 0.5231208125838516)
  7435. Firing prefer*rvt*predict-yes*H0*1*H1
  7436. -->
  7437. Firing prefer*rvt*predict-no*H0
  7438. -->
  7439. Firing rl*prefer*rvt*predict-no*H0*2*H1*12
  7440. -->
  7441. (S1 ^operator O1910 = 0.7449868594607382)
  7442. Firing rl*prefer*rvt*predict-no*H0*2
  7443. -->
  7444. (S1 ^operator O1910 = 0.2550133486219575)
  7445. Firing prefer*rvt*predict-no*H0*2*H1
  7446. -->
  7447. inner elaboration loop at bottom goal.
  7448. Retracting rl*prefer*rvt*predict-no*H0*2
  7449. -->
  7450. (S1 ^operator O1908 = 0.2550133486219575)
  7451. Retracting rl*prefer*rvt*predict-no*H0*2*H1*12
  7452. -->
  7453. (S1 ^operator O1908 = 0.7449868594607382)
  7454. Retracting rl*prefer*rvt*predict-yes*H0*1
  7455. -->
  7456. (S1 ^operator O1907 = 0.5231208125838516)
  7457. Retracting rl*prefer*rvt*predict-yes*H0*1*H1*21
  7458. -->
  7459. (S1 ^operator O1907 = 0.3)
  7460. --- END Proposal Phase ---
  7461. --- Decision Phase ---
  7462. RL update rl*prefer*rvt*predict-no*H0*2 0.631495 -0.376482 0.255013 -> 0.631495 -0.376482 0.255013(R,m,v=1,0.913514,0.079436)
  7463. RL update rl*prefer*rvt*predict-no*H0*2*H1*12 0.368505 0.376482 0.744987 -> 0.368505 0.376482 0.744987(R,m,v=1,1,0)
  7464. =>WM: (13416: S1 ^operator O1910)
  7465. 955: O: O1910 (predict-no)
  7466. --- END Decision Phase ---
  7467. --- Application Phase ---
  7468. --- Firing Productions (PE) For State At Depth 1 ---
  7469. --- Inner Elaboration Phase, active level 1 (S1) ---
  7470. Firing apply*operator
  7471. -->
  7472. (I3 ^predict-no N955 + :O )
  7473. Firing apply*operator*complete
  7474. -->
  7475. (I3 ^predict-no N954 - :O )
  7476. inner elaboration loop at bottom goal.
  7477. --- Change Working Memory (PE) ---
  7478. =>WM: (13417: I3 ^predict-no N955)
  7479. <=WM: (13405: N954 ^status complete)
  7480. <=WM: (13404: I3 ^predict-no N954)
  7481. --- Firing Productions (IE) For State At Depth 1 ---
  7482. --- Inner Elaboration Phase, active level 1 (S1) ---
  7483. Firing monitor*world
  7484. -->
  7485. I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
  7486. --- Change Working Memory (IE) ---
  7487. --- END Application Phase ---
  7488. --- Output Phase ---
  7489. ENV: Agent did: predict-no for direction L in state State-A
  7490. In State-A moving L
  7491. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  7492. predict error 0
  7493. dir: dir isU
  7494. --- END Output Phase ---
  7495. |\---- Input Phase ---
  7496. =>WM: (13421: I2 ^dir U)
  7497. =>WM: (13420: I2 ^reward 1)
  7498. =>WM: (13419: I2 ^see 0)
  7499. =>WM: (13418: N955 ^status complete)
  7500. <=WM: (13408: I2 ^dir L)
  7501. <=WM: (13407: I2 ^reward 1)
  7502. <=WM: (13406: I2 ^see 0)
  7503. =>WM: (13422: I2 ^level-1 L0-root)
  7504. <=WM: (13409: I2 ^level-1 L0-root)
  7505. --- END Input Phase ---
  7506. --- Proposal Phase ---
  7507. --- Inner Elaboration Phase, active level 1 (S1) ---
  7508. Firing elaborate*copy-see-to-output-link
  7509. -->
  7510. (I3 ^see 0 +)
  7511. Firing elaborate*reward*based*on*reward
  7512. -->
  7513. (R959 ^value 1 +)
  7514. (R1 ^reward R959 +)
  7515. Firing propose*predict-yes
  7516. -->
  7517. (O1911 ^name predict-yes +)
  7518. (S1 ^operator O1911 +)
  7519. Firing propose*predict-no
  7520. -->
  7521. (O1912 ^name predict-no +)
  7522. (S1 ^operator O1912 +)
  7523. Firing rl*prefer*rvt*predict-no*H0*6
  7524. -->
  7525. (S1 ^operator O1910 = 0.9999999999999999)
  7526. Firing rl*prefer*rvt*predict-yes*H0*5
  7527. -->
  7528. (S1 ^operator O1909 = 0.)
  7529. Firing prefer*rvt*predict-yes*H0
  7530. -->
  7531. Firing prefer*rvt*predict-no*H0
  7532. -->
  7533. Firing elaborate*copy-dir-to-output-link
  7534. -->
  7535. (I3 ^dir U +)
  7536. inner elaboration loop at bottom goal.
  7537. Retracting elaborate*copy-see-to-output-link
  7538. -->
  7539. (I3 ^see 0 +)
  7540. Retracting propose*predict-no
  7541. -->
  7542. (O1910 ^name predict-no +)
  7543. (S1 ^operator O1910 +)
  7544. Retracting propose*predict-yes
  7545. -->
  7546. (O1909 ^name predict-yes +)
  7547. (S1 ^operator O1909 +)
  7548. Retracting elaborate*reward*based*on*reward
  7549. -->
  7550. (R958 ^value 1 +)
  7551. (R1 ^reward R958 +)
  7552. Retracting elaborate*copy-dir-to-output-link
  7553. -->
  7554. (I3 ^dir L +)
  7555. Retracting rl*prefer*rvt*predict-no*H0*2
  7556. -->
  7557. (S1 ^operator O1910 = 0.2550133174095531)
  7558. Retracting rl*prefer*rvt*predict-no*H0*2*H1*12
  7559. -->
  7560. (S1 ^operator O1910 = 0.7449868282483338)
  7561. Retracting rl*prefer*rvt*predict-yes*H0*1
  7562. -->
  7563. (S1 ^operator O1909 = 0.5231208125838516)
  7564. Retracting rl*prefer*rvt*predict-yes*H0*1*H1*21
  7565. -->
  7566. (S1 ^operator O1909 = 0.3)
  7567. =>WM: (13429: S1 ^operator O1912 +)
  7568. =>WM: (13428: S1 ^operator O1911 +)
  7569. =>WM: (13427: I3 ^dir U)
  7570. =>WM: (13426: O1912 ^name predict-no)
  7571. =>WM: (13425: O1911 ^name predict-yes)
  7572. =>WM: (13424: R959 ^value 1)
  7573. =>WM: (13423: R1 ^reward R959)
  7574. <=WM: (13414: S1 ^operator O1909 +)
  7575. <=WM: (13415: S1 ^operator O1910 +)
  7576. <=WM: (13416: S1 ^operator O1910)
  7577. <=WM: (13400: I3 ^dir L)
  7578. <=WM: (13410: R1 ^reward R958)
  7579. <=WM: (13413: O1910 ^name predict-no)
  7580. <=WM: (13412: O1909 ^name predict-yes)
  7581. <=WM: (13411: R958 ^value 1)
  7582. --- Inner Elaboration Phase, active level 1 (S1) ---
  7583. Firing prefer*rvt*predict-yes*H0
  7584. -->
  7585. Firing rl*prefer*rvt*predict-yes*H0*5
  7586. -->
  7587. (S1 ^operator O1911 = 0.)
  7588. Firing prefer*rvt*predict-no*H0
  7589. -->
  7590. Firing rl*prefer*rvt*predict-no*H0*6
  7591. -->
  7592. (S1 ^operator O1912 = 0.9999999999999999)
  7593. inner elaboration loop at bottom goal.
  7594. Retracting rl*prefer*rvt*predict-no*H0*6
  7595. -->
  7596. (S1 ^operator O1910 = 0.9999999999999999)
  7597. Retracting rl*prefer*rvt*predict-yes*H0*5
  7598. -->
  7599. (S1 ^operator O1909 = 0.)
  7600. --- END Proposal Phase ---
  7601. --- Decision Phase ---
  7602. RL update rl*prefer*rvt*predict-no*H0*2 0.631495 -0.376482 0.255013 -> 0.631495 -0.376482 0.255013(R,m,v=1,0.913978,0.0790468)
  7603. RL update rl*prefer*rvt*predict-no*H0*2*H1*12 0.368505 0.376482 0.744987 -> 0.368505 0.376482 0.744987(R,m,v=1,1,0)
  7604. =>WM: (13430: S1 ^operator O1912)
  7605. 956: O: O1912 (predict-no)
  7606. --- END Decision Phase ---
  7607. --- Application Phase ---
  7608. --- Firing Productions (PE) For State At Depth 1 ---
  7609. --- Inner Elaboration Phase, active level 1 (S1) ---
  7610. Firing apply*operator
  7611. -->
  7612. (I3 ^predict-no N956 + :O )
  7613. Firing apply*operator*complete
  7614. -->
  7615. (I3 ^predict-no N955 - :O )
  7616. inner elaboration loop at bottom goal.
  7617. --- Change Working Memory (PE) ---
  7618. =>WM: (13431: I3 ^predict-no N956)
  7619. <=WM: (13418: N955 ^status complete)
  7620. <=WM: (13417: I3 ^predict-no N955)
  7621. --- Firing Productions (IE) For State At Depth 1 ---
  7622. --- Inner Elaboration Phase, active level 1 (S1) ---
  7623. Firing monitor*world
  7624. -->
  7625. I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
  7626. --- Change Working Memory (IE) ---
  7627. --- END Application Phase ---
  7628. --- Output Phase ---
  7629. ENV: Agent did: predict-no for direction U in state State-A
  7630. In State-A moving U
  7631. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  7632. predict error 0
  7633. dir: dir isU
  7634. --- END Output Phase ---
  7635. /|\--- Input Phase ---
  7636. =>WM: (13435: I2 ^dir U)
  7637. =>WM: (13434: I2 ^reward 1)
  7638. =>WM: (13433: I2 ^see 0)
  7639. =>WM: (13432: N956 ^status complete)
  7640. <=WM: (13421: I2 ^dir U)
  7641. <=WM: (13420: I2 ^reward 1)
  7642. <=WM: (13419: I2 ^see 0)
  7643. =>WM: (13436: I2 ^level-1 L0-root)
  7644. <=WM: (13422: I2 ^level-1 L0-root)
  7645. --- END Input Phase ---
  7646. --- Proposal Phase ---
  7647. --- Inner Elaboration Phase, active level 1 (S1) ---
  7648. Firing elaborate*copy-see-to-output-link
  7649. -->
  7650. (I3 ^see 0 +)
  7651. Firing elaborate*reward*based*on*reward
  7652. -->
  7653. (R960 ^value 1 +)
  7654. (R1 ^reward R960 +)
  7655. Firing propose*predict-yes
  7656. -->
  7657. (O1913 ^name predict-yes +)
  7658. (S1 ^operator O1913 +)
  7659. Firing propose*predict-no
  7660. -->
  7661. (O1914 ^name predict-no +)
  7662. (S1 ^operator O1914 +)
  7663. Firing rl*prefer*rvt*predict-no*H0*6
  7664. -->
  7665. (S1 ^operator O1912 = 0.9999999999999999)
  7666. Firing rl*prefer*rvt*predict-yes*H0*5
  7667. -->
  7668. (S1 ^operator O1911 = 0.)
  7669. Firing prefer*rvt*predict-yes*H0
  7670. -->
  7671. Firing prefer*rvt*predict-no*H0
  7672. -->
  7673. Firing elaborate*copy-dir-to-output-link
  7674. -->
  7675. (I3 ^dir U +)
  7676. inner elaboration loop at bottom goal.
  7677. Retracting elaborate*copy-see-to-output-link
  7678. -->
  7679. (I3 ^see 0 +)
  7680. Retracting propose*predict-no
  7681. -->
  7682. (O1912 ^name predict-no +)
  7683. (S1 ^operator O1912 +)
  7684. Retracting propose*predict-yes
  7685. -->
  7686. (O1911 ^name predict-yes +)
  7687. (S1 ^operator O1911 +)
  7688. Retracting elaborate*reward*based*on*reward
  7689. -->
  7690. (R959 ^value 1 +)
  7691. (R1 ^reward R959 +)
  7692. Retracting elaborate*copy-dir-to-output-link
  7693. -->
  7694. (I3 ^dir U +)
  7695. Retracting rl*prefer*rvt*predict-no*H0*6
  7696. -->
  7697. (S1 ^operator O1912 = 0.9999999999999999)
  7698. Retracting rl*prefer*rvt*predict-yes*H0*5
  7699. -->
  7700. (S1 ^operator O1911 = 0.)
  7701. =>WM: (13442: S1 ^operator O1914 +)
  7702. =>WM: (13441: S1 ^operator O1913 +)
  7703. =>WM: (13440: O1914 ^name predict-no)
  7704. =>WM: (13439: O1913 ^name predict-yes)
  7705. =>WM: (13438: R960 ^value 1)
  7706. =>WM: (13437: R1 ^reward R960)
  7707. <=WM: (13428: S1 ^operator O1911 +)
  7708. <=WM: (13429: S1 ^operator O1912 +)
  7709. <=WM: (13430: S1 ^operator O1912)
  7710. <=WM: (13423: R1 ^reward R959)
  7711. <=WM: (13426: O1912 ^name predict-no)
  7712. <=WM: (13425: O1911 ^name predict-yes)
  7713. <=WM: (13424: R959 ^value 1)
  7714. --- Inner Elaboration Phase, active level 1 (S1) ---
  7715. Firing prefer*rvt*predict-yes*H0
  7716. -->
  7717. Firing rl*prefer*rvt*predict-yes*H0*5
  7718. -->
  7719. (S1 ^operator O1913 = 0.)
  7720. Firing prefer*rvt*predict-no*H0
  7721. -->
  7722. Firing rl*prefer*rvt*predict-no*H0*6
  7723. -->
  7724. (S1 ^operator O1914 = 0.9999999999999999)
  7725. inner elaboration loop at bottom goal.
  7726. Retracting rl*prefer*rvt*predict-no*H0*6
  7727. -->
  7728. (S1 ^operator O1912 = 0.9999999999999999)
  7729. Retracting rl*prefer*rvt*predict-yes*H0*5
  7730. -->
  7731. (S1 ^operator O1911 = 0.)
  7732. --- END Proposal Phase ---
  7733. --- Decision Phase ---
  7734. RL update rl*prefer*rvt*predict-no*H0*6 1 0 1 -> 1 0 1(R,m,v=1,1,0)
  7735. =>WM: (13443: S1 ^operator O1914)
  7736. 957: O: O1914 (predict-no)
  7737. --- END Decision Phase ---
  7738. --- Application Phase ---
  7739. --- Firing Productions (PE) For State At Depth 1 ---
  7740. --- Inner Elaboration Phase, active level 1 (S1) ---
  7741. Firing apply*operator
  7742. -->
  7743. (I3 ^predict-no N957 + :O )
  7744. Firing apply*operator*complete
  7745. -->
  7746. (I3 ^predict-no N956 - :O )
  7747. inner elaboration loop at bottom goal.
  7748. --- Change Working Memory (PE) ---
  7749. =>WM: (13444: I3 ^predict-no N957)
  7750. <=WM: (13432: N956 ^status complete)
  7751. <=WM: (13431: I3 ^predict-no N956)
  7752. --- Firing Productions (IE) For State At Depth 1 ---
  7753. --- Inner Elaboration Phase, active level 1 (S1) ---
  7754. Firing monitor*world
  7755. -->
  7756. I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
  7757. --- Change Working Memory (IE) ---
  7758. --- END Application Phase ---
  7759. --- Output Phase ---
  7760. ENV: Agent did: predict-no for direction U in state State-A
  7761. In State-A moving U
  7762. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  7763. predict error 0
  7764. dir: dir isL
  7765. --- END Output Phase ---
  7766. -/|--- Input Phase ---
  7767. =>WM: (13448: I2 ^dir L)
  7768. =>WM: (13447: I2 ^reward 1)
  7769. =>WM: (13446: I2 ^see 0)
  7770. =>WM: (13445: N957 ^status complete)
  7771. <=WM: (13435: I2 ^dir U)
  7772. <=WM: (13434: I2 ^reward 1)
  7773. <=WM: (13433: I2 ^see 0)
  7774. =>WM: (13449: I2 ^level-1 L0-root)
  7775. <=WM: (13436: I2 ^level-1 L0-root)
  7776. --- END Input Phase ---
  7777. --- Proposal Phase ---
  7778. --- Inner Elaboration Phase, active level 1 (S1) ---
  7779. Firing rl*prefer*rvt*predict-yes*H0*1*H1*21
  7780. -->
  7781. (S1 ^operator O1913 = 0.3)
  7782. Firing rl*prefer*rvt*predict-no*H0*2*H1*12
  7783. -->
  7784. (S1 ^operator O1914 = 0.7449868063996508)
  7785. Firing prefer*rvt*predict-no*H0*2*H1
  7786. -->
  7787. Firing prefer*rvt*predict-yes*H0*1*H1
  7788. -->
  7789. Firing elaborate*copy-see-to-output-link
  7790. -->
  7791. (I3 ^see 0 +)
  7792. Firing elaborate*reward*based*on*reward
  7793. -->
  7794. (R961 ^value 1 +)
  7795. (R1 ^reward R961 +)
  7796. Firing propose*predict-yes
  7797. -->
  7798. (O1915 ^name predict-yes +)
  7799. (S1 ^operator O1915 +)
  7800. Firing propose*predict-no
  7801. -->
  7802. (O1916 ^name predict-no +)
  7803. (S1 ^operator O1916 +)
  7804. Firing rl*prefer*rvt*predict-no*H0*2
  7805. -->
  7806. (S1 ^operator O1914 = 0.2550132955608701)
  7807. Firing rl*prefer*rvt*predict-yes*H0*1
  7808. -->
  7809. (S1 ^operator O1913 = 0.5231208125838516)
  7810. Firing prefer*rvt*predict-yes*H0
  7811. -->
  7812. Firing prefer*rvt*predict-no*H0
  7813. -->
  7814. Firing elaborate*copy-dir-to-output-link
  7815. -->
  7816. (I3 ^dir L +)
  7817. inner elaboration loop at bottom goal.
  7818. Retracting elaborate*copy-see-to-output-link
  7819. -->
  7820. (I3 ^see 0 +)
  7821. Retracting propose*predict-no
  7822. -->
  7823. (O1914 ^name predict-no +)
  7824. (S1 ^operator O1914 +)
  7825. Retracting propose*predict-yes
  7826. -->
  7827. (O1913 ^name predict-yes +)
  7828. (S1 ^operator O1913 +)
  7829. Retracting elaborate*reward*based*on*reward
  7830. -->
  7831. (R960 ^value 1 +)
  7832. (R1 ^reward R960 +)
  7833. Retracting elaborate*copy-dir-to-output-link
  7834. -->
  7835. (I3 ^dir U +)
  7836. Retracting rl*prefer*rvt*predict-no*H0*6
  7837. -->
  7838. (S1 ^operator O1914 = 0.9999999999999999)
  7839. Retracting rl*prefer*rvt*predict-yes*H0*5
  7840. -->
  7841. (S1 ^operator O1913 = 0.)
  7842. =>WM: (13456: S1 ^operator O1916 +)
  7843. =>WM: (13455: S1 ^operator O1915 +)
  7844. =>WM: (13454: I3 ^dir L)
  7845. =>WM: (13453: O1916 ^name predict-no)
  7846. =>WM: (13452: O1915 ^name predict-yes)
  7847. =>WM: (13451: R961 ^value 1)
  7848. =>WM: (13450: R1 ^reward R961)
  7849. <=WM: (13441: S1 ^operator O1913 +)
  7850. <=WM: (13442: S1 ^operator O1914 +)
  7851. <=WM: (13443: S1 ^operator O1914)
  7852. <=WM: (13427: I3 ^dir U)
  7853. <=WM: (13437: R1 ^reward R960)
  7854. <=WM: (13440: O1914 ^name predict-no)
  7855. <=WM: (13439: O1913 ^name predict-yes)
  7856. <=WM: (13438: R960 ^value 1)
  7857. --- Inner Elaboration Phase, active level 1 (S1) ---
  7858. Firing prefer*rvt*predict-yes*H0
  7859. -->
  7860. Firing rl*prefer*rvt*predict-yes*H0*1*H1*21
  7861. -->
  7862. (S1 ^operator O1915 = 0.3)
  7863. Firing rl*prefer*rvt*predict-yes*H0*1
  7864. -->
  7865. (S1 ^operator O1915 = 0.5231208125838516)
  7866. Firing prefer*rvt*predict-yes*H0*1*H1
  7867. -->
  7868. Firing prefer*rvt*predict-no*H0
  7869. -->
  7870. Firing rl*prefer*rvt*predict-no*H0*2*H1*12
  7871. -->
  7872. (S1 ^operator O1916 = 0.7449868063996508)
  7873. Firing rl*prefer*rvt*predict-no*H0*2
  7874. -->
  7875. (S1 ^operator O1916 = 0.2550132955608701)
  7876. Firing prefer*rvt*predict-no*H0*2*H1
  7877. -->
  7878. inner elaboration loop at bottom goal.
  7879. Retracting rl*prefer*rvt*predict-no*H0*2
  7880. -->
  7881. (S1 ^operator O1914 = 0.2550132955608701)
  7882. Retracting rl*prefer*rvt*predict-no*H0*2*H1*12
  7883. -->
  7884. (S1 ^operator O1914 = 0.7449868063996508)
  7885. Retracting rl*prefer*rvt*predict-yes*H0*1
  7886. -->
  7887. (S1 ^operator O1913 = 0.5231208125838516)
  7888. Retracting rl*prefer*rvt*predict-yes*H0*1*H1*21
  7889. -->
  7890. (S1 ^operator O1913 = 0.3)
  7891. --- END Proposal Phase ---
  7892. --- Decision Phase ---
  7893. RL update rl*prefer*rvt*predict-no*H0*6 1 0 1 -> 1 0 1(R,m,v=1,1,0)
  7894. =>WM: (13457: S1 ^operator O1916)
  7895. 958: O: O1916 (predict-no)
  7896. --- END Decision Phase ---
  7897. --- Application Phase ---
  7898. --- Firing Productions (PE) For State At Depth 1 ---
  7899. --- Inner Elaboration Phase, active level 1 (S1) ---
  7900. Firing apply*operator
  7901. -->
  7902. (I3 ^predict-no N958 + :O )
  7903. Firing apply*operator*complete
  7904. -->
  7905. (I3 ^predict-no N957 - :O )
  7906. inner elaboration loop at bottom goal.
  7907. --- Change Working Memory (PE) ---
  7908. =>WM: (13458: I3 ^predict-no N958)
  7909. <=WM: (13445: N957 ^status complete)
  7910. <=WM: (13444: I3 ^predict-no N957)
  7911. --- Firing Productions (IE) For State At Depth 1 ---
  7912. --- Inner Elaboration Phase, active level 1 (S1) ---
  7913. Firing monitor*world
  7914. -->
  7915. I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
  7916. --- Change Working Memory (IE) ---
  7917. --- END Application Phase ---
  7918. --- Output Phase ---
  7919. ENV: Agent did: predict-no for direction L in state State-A
  7920. In State-A moving L
  7921. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  7922. predict error 0
  7923. dir: dir isU
  7924. --- END Output Phase ---
  7925. \-/--- Input Phase ---
  7926. =>WM: (13462: I2 ^dir U)
  7927. =>WM: (13461: I2 ^reward 1)
  7928. =>WM: (13460: I2 ^see 0)
  7929. =>WM: (13459: N958 ^status complete)
  7930. <=WM: (13448: I2 ^dir L)
  7931. <=WM: (13447: I2 ^reward 1)
  7932. <=WM: (13446: I2 ^see 0)
  7933. =>WM: (13463: I2 ^level-1 L0-root)
  7934. <=WM: (13449: I2 ^level-1 L0-root)
  7935. --- END Input Phase ---
  7936. --- Proposal Phase ---
  7937. --- Inner Elaboration Phase, active level 1 (S1) ---
  7938. Firing elaborate*copy-see-to-output-link
  7939. -->
  7940. (I3 ^see 0 +)
  7941. Firing elaborate*reward*based*on*reward
  7942. -->
  7943. (R962 ^value 1 +)
  7944. (R1 ^reward R962 +)
  7945. Firing propose*predict-yes
  7946. -->
  7947. (O1917 ^name predict-yes +)
  7948. (S1 ^operator O1917 +)
  7949. Firing propose*predict-no
  7950. -->
  7951. (O1918 ^name predict-no +)
  7952. (S1 ^operator O1918 +)
  7953. Firing rl*prefer*rvt*predict-no*H0*6
  7954. -->
  7955. (S1 ^operator O1916 = 0.9999999999999999)
  7956. Firing rl*prefer*rvt*predict-yes*H0*5
  7957. -->
  7958. (S1 ^operator O1915 = 0.)
  7959. Firing prefer*rvt*predict-yes*H0
  7960. -->
  7961. Firing prefer*rvt*predict-no*H0
  7962. -->
  7963. Firing elaborate*copy-dir-to-output-link
  7964. -->
  7965. (I3 ^dir U +)
  7966. inner elaboration loop at bottom goal.
  7967. Retracting elaborate*copy-see-to-output-link
  7968. -->
  7969. (I3 ^see 0 +)
  7970. Retracting propose*predict-no
  7971. -->
  7972. (O1916 ^name predict-no +)
  7973. (S1 ^operator O1916 +)
  7974. Retracting propose*predict-yes
  7975. -->
  7976. (O1915 ^name predict-yes +)
  7977. (S1 ^operator O1915 +)
  7978. Retracting elaborate*reward*based*on*reward
  7979. -->
  7980. (R961 ^value 1 +)
  7981. (R1 ^reward R961 +)
  7982. Retracting elaborate*copy-dir-to-output-link
  7983. -->
  7984. (I3 ^dir L +)
  7985. Retracting rl*prefer*rvt*predict-no*H0*2
  7986. -->
  7987. (S1 ^operator O1916 = 0.2550132955608701)
  7988. Retracting rl*prefer*rvt*predict-no*H0*2*H1*12
  7989. -->
  7990. (S1 ^operator O1916 = 0.7449868063996508)
  7991. Retracting rl*prefer*rvt*predict-yes*H0*1
  7992. -->
  7993. (S1 ^operator O1915 = 0.5231208125838516)
  7994. Retracting rl*prefer*rvt*predict-yes*H0*1*H1*21
  7995. -->
  7996. (S1 ^operator O1915 = 0.3)
  7997. =>WM: (13470: S1 ^operator O1918 +)
  7998. =>WM: (13469: S1 ^operator O1917 +)
  7999. =>WM: (13468: I3 ^dir U)
  8000. =>WM: (13467: O1918 ^name predict-no)
  8001. =>WM: (13466: O1917 ^name predict-yes)
  8002. =>WM: (13465: R962 ^value 1)
  8003. =>WM: (13464: R1 ^reward R962)
  8004. <=WM: (13455: S1 ^operator O1915 +)
  8005. <=WM: (13456: S1 ^operator O1916 +)
  8006. <=WM: (13457: S1 ^operator O1916)
  8007. <=WM: (13454: I3 ^dir L)
  8008. <=WM: (13450: R1 ^reward R961)
  8009. <=WM: (13453: O1916 ^name predict-no)
  8010. <=WM: (13452: O1915 ^name predict-yes)
  8011. <=WM: (13451: R961 ^value 1)
  8012. --- Inner Elaboration Phase, active level 1 (S1) ---
  8013. Firing prefer*rvt*predict-yes*H0
  8014. -->
  8015. Firing rl*prefer*rvt*predict-yes*H0*5
  8016. -->
  8017. (S1 ^operator O1917 = 0.)
  8018. Firing prefer*rvt*predict-no*H0
  8019. -->
  8020. Firing rl*prefer*rvt*predict-no*H0*6
  8021. -->
  8022. (S1 ^operator O1918 = 0.9999999999999999)
  8023. inner elaboration loop at bottom goal.
  8024. Retracting rl*prefer*rvt*predict-no*H0*6
  8025. -->
  8026. (S1 ^operator O1916 = 0.9999999999999999)
  8027. Retracting rl*prefer*rvt*predict-yes*H0*5
  8028. -->
  8029. (S1 ^operator O1915 = 0.)
  8030. --- END Proposal Phase ---
  8031. --- Decision Phase ---
  8032. RL update rl*prefer*rvt*predict-no*H0*2 0.631495 -0.376482 0.255013 -> 0.631495 -0.376482 0.255013(R,m,v=1,0.914439,0.0786614)
  8033. RL update rl*prefer*rvt*predict-no*H0*2*H1*12 0.368505 0.376482 0.744987 -> 0.368505 0.376482 0.744987(R,m,v=1,1,0)
  8034. =>WM: (13471: S1 ^operator O1918)
  8035. 959: O: O1918 (predict-no)
  8036. --- END Decision Phase ---
  8037. --- Application Phase ---
  8038. --- Firing Productions (PE) For State At Depth 1 ---
  8039. --- Inner Elaboration Phase, active level 1 (S1) ---
  8040. Firing apply*operator
  8041. -->
  8042. (I3 ^predict-no N959 + :O )
  8043. Firing apply*operator*complete
  8044. -->
  8045. (I3 ^predict-no N958 - :O )
  8046. inner elaboration loop at bottom goal.
  8047. --- Change Working Memory (PE) ---
  8048. =>WM: (13472: I3 ^predict-no N959)
  8049. <=WM: (13459: N958 ^status complete)
  8050. <=WM: (13458: I3 ^predict-no N958)
  8051. --- Firing Productions (IE) For State At Depth 1 ---
  8052. --- Inner Elaboration Phase, active level 1 (S1) ---
  8053. Firing monitor*world
  8054. -->
  8055. I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
  8056. --- Change Working Memory (IE) ---
  8057. --- END Application Phase ---
  8058. --- Output Phase ---
  8059. ENV: Agent did: predict-no for direction U in state State-A
  8060. In State-A moving U
  8061. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  8062. predict error 0
  8063. dir: dir isR
  8064. --- END Output Phase ---
  8065. |\---- Input Phase ---
  8066. =>WM: (13476: I2 ^dir R)
  8067. =>WM: (13475: I2 ^reward 1)
  8068. =>WM: (13474: I2 ^see 0)
  8069. =>WM: (13473: N959 ^status complete)
  8070. <=WM: (13462: I2 ^dir U)
  8071. <=WM: (13461: I2 ^reward 1)
  8072. <=WM: (13460: I2 ^see 0)
  8073. =>WM: (13477: I2 ^level-1 L0-root)
  8074. <=WM: (13463: I2 ^level-1 L0-root)
  8075. --- END Input Phase ---
  8076. --- Proposal Phase ---
  8077. --- Inner Elaboration Phase, active level 1 (S1) ---
  8078. Firing rl*prefer*rvt*predict-yes*H0*3*H1*14
  8079. -->
  8080. (S1 ^operator O1917 = 0.6170827253998104)
  8081. Firing rl*prefer*rvt*predict-no*H0*4*H1*13
  8082. -->
  8083. (S1 ^operator O1918 = 0.4910065094545203)
  8084. Firing prefer*rvt*predict-no*H0*4*H1
  8085. -->
  8086. Firing prefer*rvt*predict-yes*H0*3*H1
  8087. -->
  8088. Firing elaborate*copy-see-to-output-link
  8089. -->
  8090. (I3 ^see 0 +)
  8091. Firing elaborate*reward*based*on*reward
  8092. -->
  8093. (R963 ^value 1 +)
  8094. (R1 ^reward R963 +)
  8095. Firing propose*predict-yes
  8096. -->
  8097. (O1919 ^name predict-yes +)
  8098. (S1 ^operator O1919 +)
  8099. Firing propose*predict-no
  8100. -->
  8101. (O1920 ^name predict-no +)
  8102. (S1 ^operator O1920 +)
  8103. Firing rl*prefer*rvt*predict-no*H0*4
  8104. -->
  8105. (S1 ^operator O1918 = 0.1269768259493387)
  8106. Firing rl*prefer*rvt*predict-yes*H0*3
  8107. -->
  8108. (S1 ^operator O1917 = 0.3829271874912855)
  8109. Firing prefer*rvt*predict-yes*H0
  8110. -->
  8111. Firing prefer*rvt*predict-no*H0
  8112. -->
  8113. Firing elaborate*copy-dir-to-output-link
  8114. -->
  8115. (I3 ^dir R +)
  8116. inner elaboration loop at bottom goal.
  8117. Retracting elaborate*copy-see-to-output-link
  8118. -->
  8119. (I3 ^see 0 +)
  8120. Retracting propose*predict-no
  8121. -->
  8122. (O1918 ^name predict-no +)
  8123. (S1 ^operator O1918 +)
  8124. Retracting propose*predict-yes
  8125. -->
  8126. (O1917 ^name predict-yes +)
  8127. (S1 ^operator O1917 +)
  8128. Retracting elaborate*reward*based*on*reward
  8129. -->
  8130. (R962 ^value 1 +)
  8131. (R1 ^reward R962 +)
  8132. Retracting elaborate*copy-dir-to-output-link
  8133. -->
  8134. (I3 ^dir U +)
  8135. Retracting rl*prefer*rvt*predict-no*H0*6
  8136. -->
  8137. (S1 ^operator O1918 = 0.9999999999999999)
  8138. Retracting rl*prefer*rvt*predict-yes*H0*5
  8139. -->
  8140. (S1 ^operator O1917 = 0.)
  8141. =>WM: (13484: S1 ^operator O1920 +)
  8142. =>WM: (13483: S1 ^operator O1919 +)
  8143. =>WM: (13482: I3 ^dir R)
  8144. =>WM: (13481: O1920 ^name predict-no)
  8145. =>WM: (13480: O1919 ^name predict-yes)
  8146. =>WM: (13479: R963 ^value 1)
  8147. =>WM: (13478: R1 ^reward R963)
  8148. <=WM: (13469: S1 ^operator O1917 +)
  8149. <=WM: (13470: S1 ^operator O1918 +)
  8150. <=WM: (13471: S1 ^operator O1918)
  8151. <=WM: (13468: I3 ^dir U)
  8152. <=WM: (13464: R1 ^reward R962)
  8153. <=WM: (13467: O1918 ^name predict-no)
  8154. <=WM: (13466: O1917 ^name predict-yes)
  8155. <=WM: (13465: R962 ^value 1)
  8156. --- Inner Elaboration Phase, active level 1 (S1) ---
  8157. Firing prefer*rvt*predict-yes*H0
  8158. -->
  8159. Firing rl*prefer*rvt*predict-yes*H0*3*H1*14
  8160. -->
  8161. (S1 ^operator O1919 = 0.6170827253998104)
  8162. Firing rl*prefer*rvt*predict-yes*H0*3
  8163. -->
  8164. (S1 ^operator O1919 = 0.3829271874912855)
  8165. Firing prefer*rvt*predict-yes*H0*3*H1
  8166. -->
  8167. Firing prefer*rvt*predict-no*H0
  8168. -->
  8169. Firing rl*prefer*rvt*predict-no*H0*4*H1*13
  8170. -->
  8171. (S1 ^operator O1920 = 0.4910065094545203)
  8172. Firing rl*prefer*rvt*predict-no*H0*4
  8173. -->
  8174. (S1 ^operator O1920 = 0.1269768259493387)
  8175. Firing prefer*rvt*predict-no*H0*4*H1
  8176. -->
  8177. inner elaboration loop at bottom goal.
  8178. Retracting rl*prefer*rvt*predict-no*H0*4
  8179. -->
  8180. (S1 ^operator O1918 = 0.1269768259493387)
  8181. Retracting rl*prefer*rvt*predict-no*H0*4*H1*13
  8182. -->
  8183. (S1 ^operator O1918 = 0.4910065094545203)
  8184. Retracting rl*prefer*rvt*predict-yes*H0*3
  8185. -->
  8186. (S1 ^operator O1917 = 0.3829271874912855)
  8187. Retracting rl*prefer*rvt*predict-yes*H0*3*H1*14
  8188. -->
  8189. (S1 ^operator O1917 = 0.6170827253998104)
  8190. --- END Proposal Phase ---
  8191. --- Decision Phase ---
  8192. RL update rl*prefer*rvt*predict-no*H0*6 1 0 1 -> 1 0 1(R,m,v=1,1,0)
  8193. =>WM: (13485: S1 ^operator O1919)
  8194. 960: O: O1919 (predict-yes)
  8195. --- END Decision Phase ---
  8196. --- Application Phase ---
  8197. --- Firing Productions (PE) For State At Depth 1 ---
  8198. --- Inner Elaboration Phase, active level 1 (S1) ---
  8199. Firing apply*operator
  8200. -->
  8201. (I3 ^predict-yes N960 + :O )
  8202. Firing apply*operator*complete
  8203. -->
  8204. (I3 ^predict-no N959 - :O )
  8205. inner elaboration loop at bottom goal.
  8206. --- Change Working Memory (PE) ---
  8207. =>WM: (13486: I3 ^predict-yes N960)
  8208. <=WM: (13473: N959 ^status complete)
  8209. <=WM: (13472: I3 ^predict-no N959)
  8210. --- Firing Productions (IE) For State At Depth 1 ---
  8211. --- Inner Elaboration Phase, active level 1 (S1) ---
  8212. Firing monitor*world
  8213. -->
  8214. I see 1 and I'm going to do: predict-yes inner elaboration loop at bottom goal.
  8215. --- Change Working Memory (IE) ---
  8216. --- END Application Phase ---
  8217. --- Output Phase ---
  8218. ENV: Agent did: predict-yes for direction R in state State-A
  8219. In State-A moving R
  8220. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  8221. predict error 0
  8222. dir: dir isR
  8223. --- END Output Phase ---
  8224. /|\--- Input Phase ---
  8225. =>WM: (13490: I2 ^dir R)
  8226. =>WM: (13489: I2 ^reward 1)
  8227. =>WM: (13488: I2 ^see 1)
  8228. =>WM: (13487: N960 ^status complete)
  8229. <=WM: (13476: I2 ^dir R)
  8230. <=WM: (13475: I2 ^reward 1)
  8231. <=WM: (13474: I2 ^see 0)
  8232. =>WM: (13491: I2 ^level-1 R1-root)
  8233. <=WM: (13477: I2 ^level-1 L0-root)
  8234. --- END Input Phase ---
  8235. --- Proposal Phase ---
  8236. --- Inner Elaboration Phase, active level 1 (S1) ---
  8237. Firing rl*prefer*rvt*predict-yes*H0*3*H1*16
  8238. -->
  8239. (S1 ^operator O1919 = 0.08783148430849691)
  8240. Firing rl*prefer*rvt*predict-no*H0*4*H1*15
  8241. -->
  8242. (S1 ^operator O1920 = 0.873023493232603)
  8243. Firing prefer*rvt*predict-no*H0*4*H1
  8244. -->
  8245. Firing prefer*rvt*predict-yes*H0*3*H1
  8246. -->
  8247. Firing elaborate*copy-see-to-output-link
  8248. -->
  8249. (I3 ^see 1 +)
  8250. Firing elaborate*reward*based*on*reward
  8251. -->
  8252. (R964 ^value 1 +)
  8253. (R1 ^reward R964 +)
  8254. Firing propose*predict-yes
  8255. -->
  8256. (O1921 ^name predict-yes +)
  8257. (S1 ^operator O1921 +)
  8258. Firing propose*predict-no
  8259. -->
  8260. (O1922 ^name predict-no +)
  8261. (S1 ^operator O1922 +)
  8262. Firing rl*prefer*rvt*predict-no*H0*4
  8263. -->
  8264. (S1 ^operator O1920 = 0.1269768259493387)
  8265. Firing rl*prefer*rvt*predict-yes*H0*3
  8266. -->
  8267. (S1 ^operator O1919 = 0.3829271874912855)
  8268. Firing prefer*rvt*predict-yes*H0
  8269. -->
  8270. Firing prefer*rvt*predict-no*H0
  8271. -->
  8272. Firing elaborate*copy-dir-to-output-link
  8273. -->
  8274. (I3 ^dir R +)
  8275. inner elaboration loop at bottom goal.
  8276. Retracting elaborate*copy-see-to-output-link
  8277. -->
  8278. (I3 ^see 0 +)
  8279. Retracting propose*predict-no
  8280. -->
  8281. (O1920 ^name predict-no +)
  8282. (S1 ^operator O1920 +)
  8283. Retracting propose*predict-yes
  8284. -->
  8285. (O1919 ^name predict-yes +)
  8286. (S1 ^operator O1919 +)
  8287. Retracting elaborate*reward*based*on*reward
  8288. -->
  8289. (R963 ^value 1 +)
  8290. (R1 ^reward R963 +)
  8291. Retracting elaborate*copy-dir-to-output-link
  8292. -->
  8293. (I3 ^dir R +)
  8294. Retracting rl*prefer*rvt*predict-no*H0*4
  8295. -->
  8296. (S1 ^operator O1920 = 0.1269768259493387)
  8297. Retracting rl*prefer*rvt*predict-no*H0*4*H1*13
  8298. -->
  8299. (S1 ^operator O1920 = 0.4910065094545203)
  8300. Retracting rl*prefer*rvt*predict-yes*H0*3
  8301. -->
  8302. (S1 ^operator O1919 = 0.3829271874912855)
  8303. Retracting rl*prefer*rvt*predict-yes*H0*3*H1*14
  8304. -->
  8305. (S1 ^operator O1919 = 0.6170827253998104)
  8306. =>WM: (13498: S1 ^operator O1922 +)
  8307. =>WM: (13497: S1 ^operator O1921 +)
  8308. =>WM: (13496: O1922 ^name predict-no)
  8309. =>WM: (13495: O1921 ^name predict-yes)
  8310. =>WM: (13494: R964 ^value 1)
  8311. =>WM: (13493: R1 ^reward R964)
  8312. =>WM: (13492: I3 ^see 1)
  8313. <=WM: (13483: S1 ^operator O1919 +)
  8314. <=WM: (13485: S1 ^operator O1919)
  8315. <=WM: (13484: S1 ^operator O1920 +)
  8316. <=WM: (13478: R1 ^reward R963)
  8317. <=WM: (13381: I3 ^see 0)
  8318. <=WM: (13481: O1920 ^name predict-no)
  8319. <=WM: (13480: O1919 ^name predict-yes)
  8320. <=WM: (13479: R963 ^value 1)
  8321. --- Inner Elaboration Phase, active level 1 (S1) ---
  8322. Firing prefer*rvt*predict-yes*H0
  8323. -->
  8324. Firing rl*prefer*rvt*predict-yes*H0*3
  8325. -->
  8326. (S1 ^operator O1921 = 0.3829271874912855)
  8327. Firing prefer*rvt*predict-yes*H0*3*H1
  8328. -->
  8329. Firing rl*prefer*rvt*predict-yes*H0*3*H1*16
  8330. -->
  8331. (S1 ^operator O1921 = 0.08783148430849691)
  8332. Firing prefer*rvt*predict-no*H0
  8333. -->
  8334. Firing rl*prefer*rvt*predict-no*H0*4
  8335. -->
  8336. (S1 ^operator O1922 = 0.1269768259493387)
  8337. Firing prefer*rvt*predict-no*H0*4*H1
  8338. -->
  8339. Firing rl*prefer*rvt*predict-no*H0*4*H1*15
  8340. -->
  8341. (S1 ^operator O1922 = 0.873023493232603)
  8342. inner elaboration loop at bottom goal.
  8343. Retracting rl*prefer*rvt*predict-no*H0*4
  8344. -->
  8345. (S1 ^operator O1920 = 0.1269768259493387)
  8346. Retracting rl*prefer*rvt*predict-no*H0*4*H1*15
  8347. -->
  8348. (S1 ^operator O1920 = 0.873023493232603)
  8349. Retracting rl*prefer*rvt*predict-yes*H0*3
  8350. -->
  8351. (S1 ^operator O1919 = 0.3829271874912855)
  8352. Retracting rl*prefer*rvt*predict-yes*H0*3*H1*16
  8353. -->
  8354. (S1 ^operator O1919 = 0.08783148430849691)
  8355. --- END Proposal Phase ---
  8356. --- Decision Phase ---
  8357. RL update rl*prefer*rvt*predict-yes*H0*3 0.673122 -0.290194 0.382927 -> 0.67312 -0.290194 0.382926(R,m,v=1,0.959184,0.0394185)
  8358. RL update rl*prefer*rvt*predict-yes*H0*3*H1*14 0.326888 0.290195 0.617083 -> 0.326886 0.290195 0.617081(R,m,v=1,1,0)
  8359. =>WM: (13499: S1 ^operator O1922)
  8360. 961: O: O1922 (predict-no)
  8361. --- END Decision Phase ---
  8362. --- Application Phase ---
  8363. --- Firing Productions (PE) For State At Depth 1 ---
  8364. --- Inner Elaboration Phase, active level 1 (S1) ---
  8365. Firing apply*operator
  8366. -->
  8367. (I3 ^predict-no N961 + :O )
  8368. Firing apply*operator*complete
  8369. -->
  8370. (I3 ^predict-yes N960 - :O )
  8371. inner elaboration loop at bottom goal.
  8372. --- Change Working Memory (PE) ---
  8373. =>WM: (13500: I3 ^predict-no N961)
  8374. <=WM: (13487: N960 ^status complete)
  8375. <=WM: (13486: I3 ^predict-yes N960)
  8376. --- Firing Productions (IE) For State At Depth 1 ---
  8377. --- Inner Elaboration Phase, active level 1 (S1) ---
  8378. Firing monitor*world
  8379. -->
  8380. I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
  8381. --- Change Working Memory (IE) ---
  8382. --- END Application Phase ---
  8383. --- Output Phase ---
  8384. ENV: Agent did: predict-no for direction R in state State-B
  8385. In State-B moving R
  8386. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  8387. predict error 0
  8388. dir: dir isL
  8389. --- END Output Phase ---
  8390. ---- Input Phase ---
  8391. =>WM: (13504: I2 ^dir L)
  8392. =>WM: (13503: I2 ^reward 1)
  8393. =>WM: (13502: I2 ^see 0)
  8394. =>WM: (13501: N961 ^status complete)
  8395. <=WM: (13490: I2 ^dir R)
  8396. <=WM: (13489: I2 ^reward 1)
  8397. <=WM: (13488: I2 ^see 1)
  8398. =>WM: (13505: I2 ^level-1 R0-root)
  8399. <=WM: (13491: I2 ^level-1 R1-root)
  8400. --- END Input Phase ---
  8401. --- Proposal Phase ---
  8402. --- Inner Elaboration Phase, active level 1 (S1) ---
  8403. Firing rl*prefer*rvt*predict-yes*H0*1*H1*19
  8404. -->
  8405. (S1 ^operator O1921 = 0.4768849116445159)
  8406. Firing rl*prefer*rvt*predict-no*H0*2*H1*7
  8407. -->
  8408. (S1 ^operator O1922 = 0.1700769046561409)
  8409. Firing prefer*rvt*predict-no*H0*2*H1
  8410. -->
  8411. Firing prefer*rvt*predict-yes*H0*1*H1
  8412. -->
  8413. Firing elaborate*copy-see-to-output-link
  8414. -->
  8415. (I3 ^see 0 +)
  8416. Firing elaborate*reward*based*on*reward
  8417. -->
  8418. (R965 ^value 1 +)
  8419. (R1 ^reward R965 +)
  8420. Firing propose*predict-yes
  8421. -->
  8422. (O1923 ^name predict-yes +)
  8423. (S1 ^operator O1923 +)
  8424. Firing propose*predict-no
  8425. -->
  8426. (O1924 ^name predict-no +)
  8427. (S1 ^operator O1924 +)
  8428. Firing rl*prefer*rvt*predict-no*H0*2
  8429. -->
  8430. (S1 ^operator O1922 = 0.255013280266792)
  8431. Firing rl*prefer*rvt*predict-yes*H0*1
  8432. -->
  8433. (S1 ^operator O1921 = 0.5231208125838516)
  8434. Firing prefer*rvt*predict-yes*H0
  8435. -->
  8436. Firing prefer*rvt*predict-no*H0
  8437. -->
  8438. Firing elaborate*copy-dir-to-output-link
  8439. -->
  8440. (I3 ^dir L +)
  8441. inner elaboration loop at bottom goal.
  8442. Retracting elaborate*copy-see-to-output-link
  8443. -->
  8444. (I3 ^see 1 +)
  8445. Retracting propose*predict-no
  8446. -->
  8447. (O1922 ^name predict-no +)
  8448. (S1 ^operator O1922 +)
  8449. Retracting propose*predict-yes
  8450. -->
  8451. (O1921 ^name predict-yes +)
  8452. (S1 ^operator O1921 +)
  8453. Retracting elaborate*reward*based*on*reward
  8454. -->
  8455. (R964 ^value 1 +)
  8456. (R1 ^reward R964 +)
  8457. Retracting elaborate*copy-dir-to-output-link
  8458. -->
  8459. (I3 ^dir R +)
  8460. Retracting rl*prefer*rvt*predict-no*H0*4*H1*15
  8461. -->
  8462. (S1 ^operator O1922 = 0.873023493232603)
  8463. Retracting rl*prefer*rvt*predict-no*H0*4
  8464. -->
  8465. (S1 ^operator O1922 = 0.1269768259493387)
  8466. Retracting rl*prefer*rvt*predict-yes*H0*3*H1*16
  8467. -->
  8468. (S1 ^operator O1921 = 0.08783148430849691)
  8469. Retracting rl*prefer*rvt*predict-yes*H0*3
  8470. -->
  8471. (S1 ^operator O1921 = 0.3829257005576211)
  8472. =>WM: (13513: S1 ^operator O1924 +)
  8473. =>WM: (13512: S1 ^operator O1923 +)
  8474. =>WM: (13511: I3 ^dir L)
  8475. =>WM: (13510: O1924 ^name predict-no)
  8476. =>WM: (13509: O1923 ^name predict-yes)
  8477. =>WM: (13508: R965 ^value 1)
  8478. =>WM: (13507: R1 ^reward R965)
  8479. =>WM: (13506: I3 ^see 0)
  8480. <=WM: (13497: S1 ^operator O1921 +)
  8481. <=WM: (13498: S1 ^operator O1922 +)
  8482. <=WM: (13499: S1 ^operator O1922)
  8483. <=WM: (13482: I3 ^dir R)
  8484. <=WM: (13493: R1 ^reward R964)
  8485. <=WM: (13492: I3 ^see 1)
  8486. <=WM: (13496: O1922 ^name predict-no)
  8487. <=WM: (13495: O1921 ^name predict-yes)
  8488. <=WM: (13494: R964 ^value 1)
  8489. --- Inner Elaboration Phase, active level 1 (S1) ---
  8490. Firing prefer*rvt*predict-yes*H0
  8491. -->
  8492. Firing rl*prefer*rvt*predict-yes*H0*1
  8493. -->
  8494. (S1 ^operator O1923 = 0.5231208125838516)
  8495. Firing prefer*rvt*predict-yes*H0*1*H1
  8496. -->
  8497. Firing rl*prefer*rvt*predict-yes*H0*1*H1*19
  8498. -->
  8499. (S1 ^operator O1923 = 0.4768849116445159)
  8500. Firing prefer*rvt*predict-no*H0
  8501. -->
  8502. Firing rl*prefer*rvt*predict-no*H0*2
  8503. -->
  8504. (S1 ^operator O1924 = 0.255013280266792)
  8505. Firing prefer*rvt*predict-no*H0*2*H1
  8506. -->
  8507. Firing rl*prefer*rvt*predict-no*H0*2*H1*7
  8508. -->
  8509. (S1 ^operator O1924 = 0.1700769046561409)
  8510. inner elaboration loop at bottom goal.
  8511. Retracting rl*prefer*rvt*predict-no*H0*2
  8512. -->
  8513. (S1 ^operator O1922 = 0.255013280266792)
  8514. Retracting rl*prefer*rvt*predict-no*H0*2*H1*7
  8515. -->
  8516. (S1 ^operator O1922 = 0.1700769046561409)
  8517. Retracting rl*prefer*rvt*predict-yes*H0*1
  8518. -->
  8519. (S1 ^operator O1921 = 0.5231208125838516)
  8520. Retracting rl*prefer*rvt*predict-yes*H0*1*H1*19
  8521. -->
  8522. (S1 ^operator O1921 = 0.4768849116445159)
  8523. --- END Proposal Phase ---
  8524. --- Decision Phase ---
  8525. RL update rl*prefer*rvt*predict-no*H0*4 0.814714 -0.687737 0.126977 -> 0.814714 -0.687737 0.126977(R,m,v=1,0.947674,0.0498776)
  8526. RL update rl*prefer*rvt*predict-no*H0*4*H1*15 0.185286 0.687737 0.873023 -> 0.185286 0.687737 0.873023(R,m,v=1,1,0)
  8527. =>WM: (13514: S1 ^operator O1923)
  8528. 962: O: O1923 (predict-yes)
  8529. --- END Decision Phase ---
  8530. --- Application Phase ---
  8531. --- Firing Productions (PE) For State At Depth 1 ---
  8532. --- Inner Elaboration Phase, active level 1 (S1) ---
  8533. Firing apply*operator
  8534. -->
  8535. (I3 ^predict-yes N962 + :O )
  8536. Firing apply*operator*complete
  8537. -->
  8538. (I3 ^predict-no N961 - :O )
  8539. inner elaboration loop at bottom goal.
  8540. --- Change Working Memory (PE) ---
  8541. =>WM: (13515: I3 ^predict-yes N962)
  8542. <=WM: (13501: N961 ^status complete)
  8543. <=WM: (13500: I3 ^predict-no N961)
  8544. --- Firing Productions (IE) For State At Depth 1 ---
  8545. --- Inner Elaboration Phase, active level 1 (S1) ---
  8546. Firing monitor*world
  8547. -->
  8548. I see 1 and I'm going to do: predict-yes inner elaboration loop at bottom goal.
  8549. --- Change Working Memory (IE) ---
  8550. --- END Application Phase ---
  8551. --- Output Phase ---
  8552. ENV: Agent did: predict-yes for direction L in state State-B
  8553. In State-B moving L
  8554. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  8555. predict error 0
  8556. dir: dir isR
  8557. --- END Output Phase ---
  8558. /|\--- Input Phase ---
  8559. =>WM: (13519: I2 ^dir R)
  8560. =>WM: (13518: I2 ^reward 1)
  8561. =>WM: (13517: I2 ^see 1)
  8562. =>WM: (13516: N962 ^status complete)
  8563. <=WM: (13504: I2 ^dir L)
  8564. <=WM: (13503: I2 ^reward 1)
  8565. <=WM: (13502: I2 ^see 0)
  8566. =>WM: (13520: I2 ^level-1 L1-root)
  8567. <=WM: (13505: I2 ^level-1 R0-root)
  8568. --- END Input Phase ---
  8569. --- Proposal Phase ---
  8570. --- Inner Elaboration Phase, active level 1 (S1) ---
  8571. Firing rl*prefer*rvt*predict-yes*H0*3*H1*9
  8572. -->
  8573. (S1 ^operator O1923 = 0.6170188666021243)
  8574. Firing rl*prefer*rvt*predict-no*H0*4*H1*8
  8575. -->
  8576. (S1 ^operator O1924 = 0.4901349546100854)
  8577. Firing prefer*rvt*predict-no*H0*4*H1
  8578. -->
  8579. Firing prefer*rvt*predict-yes*H0*3*H1
  8580. -->
  8581. Firing elaborate*copy-see-to-output-link
  8582. -->
  8583. (I3 ^see 1 +)
  8584. Firing elaborate*reward*based*on*reward
  8585. -->
  8586. (R966 ^value 1 +)
  8587. (R1 ^reward R966 +)
  8588. Firing propose*predict-yes
  8589. -->
  8590. (O1925 ^name predict-yes +)
  8591. (S1 ^operator O1925 +)
  8592. Firing propose*predict-no
  8593. -->
  8594. (O1926 ^name predict-no +)
  8595. (S1 ^operator O1926 +)
  8596. Firing rl*prefer*rvt*predict-no*H0*4
  8597. -->
  8598. (S1 ^operator O1924 = 0.1269767780720474)
  8599. Firing rl*prefer*rvt*predict-yes*H0*3
  8600. -->
  8601. (S1 ^operator O1923 = 0.3829257005576211)
  8602. Firing prefer*rvt*predict-yes*H0
  8603. -->
  8604. Firing prefer*rvt*predict-no*H0
  8605. -->
  8606. Firing elaborate*copy-dir-to-output-link
  8607. -->
  8608. (I3 ^dir R +)
  8609. inner elaboration loop at bottom goal.
  8610. Retracting elaborate*copy-see-to-output-link
  8611. -->
  8612. (I3 ^see 0 +)
  8613. Retracting propose*predict-no
  8614. -->
  8615. (O1924 ^name predict-no +)
  8616. (S1 ^operator O1924 +)
  8617. Retracting propose*predict-yes
  8618. -->
  8619. (O1923 ^name predict-yes +)
  8620. (S1 ^operator O1923 +)
  8621. Retracting elaborate*reward*based*on*reward
  8622. -->
  8623. (R965 ^value 1 +)
  8624. (R1 ^reward R965 +)
  8625. Retracting elaborate*copy-dir-to-output-link
  8626. -->
  8627. (I3 ^dir L +)
  8628. Retracting rl*prefer*rvt*predict-no*H0*2*H1*7
  8629. -->
  8630. (S1 ^operator O1924 = 0.1700769046561409)
  8631. Retracting rl*prefer*rvt*predict-no*H0*2
  8632. -->
  8633. (S1 ^operator O1924 = 0.255013280266792)
  8634. Retracting rl*prefer*rvt*predict-yes*H0*1*H1*19
  8635. -->
  8636. (S1 ^operator O1923 = 0.4768849116445159)
  8637. Retracting rl*prefer*rvt*predict-yes*H0*1
  8638. -->
  8639. (S1 ^operator O1923 = 0.5231208125838516)
  8640. =>WM: (13528: S1 ^operator O1926 +)
  8641. =>WM: (13527: S1 ^operator O1925 +)
  8642. =>WM: (13526: I3 ^dir R)
  8643. =>WM: (13525: O1926 ^name predict-no)
  8644. =>WM: (13524: O1925 ^name predict-yes)
  8645. =>WM: (13523: R966 ^value 1)
  8646. =>WM: (13522: R1 ^reward R966)
  8647. =>WM: (13521: I3 ^see 1)
  8648. <=WM: (13512: S1 ^operator O1923 +)
  8649. <=WM: (13514: S1 ^operator O1923)
  8650. <=WM: (13513: S1 ^operator O1924 +)
  8651. <=WM: (13511: I3 ^dir L)
  8652. <=WM: (13507: R1 ^reward R965)
  8653. <=WM: (13506: I3 ^see 0)
  8654. <=WM: (13510: O1924 ^name predict-no)
  8655. <=WM: (13509: O1923 ^name predict-yes)
  8656. <=WM: (13508: R965 ^value 1)
  8657. --- Inner Elaboration Phase, active level 1 (S1) ---
  8658. Firing prefer*rvt*predict-yes*H0
  8659. -->
  8660. Firing rl*prefer*rvt*predict-yes*H0*3
  8661. -->
  8662. (S1 ^operator O1925 = 0.3829257005576211)
  8663. Firing prefer*rvt*predict-yes*H0*3*H1
  8664. -->
  8665. Firing rl*prefer*rvt*predict-yes*H0*3*H1*9
  8666. -->
  8667. (S1 ^operator O1925 = 0.6170188666021243)
  8668. Firing prefer*rvt*predict-no*H0
  8669. -->
  8670. Firing rl*prefer*rvt*predict-no*H0*4
  8671. -->
  8672. (S1 ^operator O1926 = 0.1269767780720474)
  8673. Firing prefer*rvt*predict-no*H0*4*H1
  8674. -->
  8675. Firing rl*prefer*rvt*predict-no*H0*4*H1*8
  8676. -->
  8677. (S1 ^operator O1926 = 0.4901349546100854)
  8678. inner elaboration loop at bottom goal.
  8679. Retracting rl*prefer*rvt*predict-no*H0*4
  8680. -->
  8681. (S1 ^operator O1924 = 0.1269767780720474)
  8682. Retracting rl*prefer*rvt*predict-no*H0*4*H1*8
  8683. -->
  8684. (S1 ^operator O1924 = 0.4901349546100854)
  8685. Retracting rl*prefer*rvt*predict-yes*H0*3
  8686. -->
  8687. (S1 ^operator O1923 = 0.3829257005576211)
  8688. Retracting rl*prefer*rvt*predict-yes*H0*3*H1*9
  8689. -->
  8690. (S1 ^operator O1923 = 0.6170188666021243)
  8691. --- END Proposal Phase ---
  8692. --- Decision Phase ---
  8693. RL update rl*prefer*rvt*predict-yes*H0*1 0.727961 -0.20484 0.523121 -> 0.72796 -0.20484 0.52312(R,m,v=1,0.978102,0.0215758)
  8694. RL update rl*prefer*rvt*predict-yes*H0*1*H1*19 0.272047 0.204838 0.476885 -> 0.272045 0.204839 0.476884(R,m,v=1,1,0)
  8695. =>WM: (13529: S1 ^operator O1925)
  8696. 963: O: O1925 (predict-yes)
  8697. --- END Decision Phase ---
  8698. --- Application Phase ---
  8699. --- Firing Productions (PE) For State At Depth 1 ---
  8700. --- Inner Elaboration Phase, active level 1 (S1) ---
  8701. Firing apply*operator
  8702. -->
  8703. (I3 ^predict-yes N963 + :O )
  8704. Firing apply*operator*complete
  8705. -->
  8706. (I3 ^predict-yes N962 - :O )
  8707. inner elaboration loop at bottom goal.
  8708. --- Change Working Memory (PE) ---
  8709. =>WM: (13530: I3 ^predict-yes N963)
  8710. <=WM: (13516: N962 ^status complete)
  8711. <=WM: (13515: I3 ^predict-yes N962)
  8712. --- Firing Productions (IE) For State At Depth 1 ---
  8713. --- Inner Elaboration Phase, active level 1 (S1) ---
  8714. Firing monitor*world
  8715. -->
  8716. I see 1 and I'm going to do: predict-yes inner elaboration loop at bottom goal.
  8717. --- Change Working Memory (IE) ---
  8718. --- END Application Phase ---
  8719. --- Output Phase ---
  8720. ENV: Agent did: predict-yes for direction R in state State-A
  8721. In State-A moving R
  8722. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  8723. predict error 0
  8724. dir: dir isU
  8725. --- END Output Phase ---
  8726. -/--- Input Phase ---
  8727. =>WM: (13534: I2 ^dir U)
  8728. =>WM: (13533: I2 ^reward 1)
  8729. =>WM: (13532: I2 ^see 1)
  8730. =>WM: (13531: N963 ^status complete)
  8731. <=WM: (13519: I2 ^dir R)
  8732. <=WM: (13518: I2 ^reward 1)
  8733. <=WM: (13517: I2 ^see 1)
  8734. =>WM: (13535: I2 ^level-1 R1-root)
  8735. <=WM: (13520: I2 ^level-1 L1-root)
  8736. --- END Input Phase ---
  8737. --- Proposal Phase ---
  8738. --- Inner Elaboration Phase, active level 1 (S1) ---
  8739. Firing elaborate*copy-see-to-output-link
  8740. -->
  8741. (I3 ^see 1 +)
  8742. Firing elaborate*reward*based*on*reward
  8743. -->
  8744. (R967 ^value 1 +)
  8745. (R1 ^reward R967 +)
  8746. Firing propose*predict-yes
  8747. -->
  8748. (O1927 ^name predict-yes +)
  8749. (S1 ^operator O1927 +)
  8750. Firing propose*predict-no
  8751. -->
  8752. (O1928 ^name predict-no +)
  8753. (S1 ^operator O1928 +)
  8754. Firing rl*prefer*rvt*predict-no*H0*6
  8755. -->
  8756. (S1 ^operator O1926 = 0.9999999999999999)
  8757. Firing rl*prefer*rvt*predict-yes*H0*5
  8758. -->
  8759. (S1 ^operator O1925 = 0.)
  8760. Firing prefer*rvt*predict-yes*H0
  8761. -->
  8762. Firing prefer*rvt*predict-no*H0
  8763. -->
  8764. Firing elaborate*copy-dir-to-output-link
  8765. -->
  8766. (I3 ^dir U +)
  8767. inner elaboration loop at bottom goal.
  8768. Retracting elaborate*copy-see-to-output-link
  8769. -->
  8770. (I3 ^see 1 +)
  8771. Retracting propose*predict-no
  8772. -->
  8773. (O1926 ^name predict-no +)
  8774. (S1 ^operator O1926 +)
  8775. Retracting propose*predict-yes
  8776. -->
  8777. (O1925 ^name predict-yes +)
  8778. (S1 ^operator O1925 +)
  8779. Retracting elaborate*reward*based*on*reward
  8780. -->
  8781. (R966 ^value 1 +)
  8782. (R1 ^reward R966 +)
  8783. Retracting elaborate*copy-dir-to-output-link
  8784. -->
  8785. (I3 ^dir R +)
  8786. Retracting rl*prefer*rvt*predict-no*H0*4*H1*8
  8787. -->
  8788. (S1 ^operator O1926 = 0.4901349546100854)
  8789. Retracting rl*prefer*rvt*predict-no*H0*4
  8790. -->
  8791. (S1 ^operator O1926 = 0.1269767780720474)
  8792. Retracting rl*prefer*rvt*predict-yes*H0*3*H1*9
  8793. -->
  8794. (S1 ^operator O1925 = 0.6170188666021243)
  8795. Retracting rl*prefer*rvt*predict-yes*H0*3
  8796. -->
  8797. (S1 ^operator O1925 = 0.3829257005576211)
  8798. =>WM: (13542: S1 ^operator O1928 +)
  8799. =>WM: (13541: S1 ^operator O1927 +)
  8800. =>WM: (13540: I3 ^dir U)
  8801. =>WM: (13539: O1928 ^name predict-no)
  8802. =>WM: (13538: O1927 ^name predict-yes)
  8803. =>WM: (13537: R967 ^value 1)
  8804. =>WM: (13536: R1 ^reward R967)
  8805. <=WM: (13527: S1 ^operator O1925 +)
  8806. <=WM: (13529: S1 ^operator O1925)
  8807. <=WM: (13528: S1 ^operator O1926 +)
  8808. <=WM: (13526: I3 ^dir R)
  8809. <=WM: (13522: R1 ^reward R966)
  8810. <=WM: (13525: O1926 ^name predict-no)
  8811. <=WM: (13524: O1925 ^name predict-yes)
  8812. <=WM: (13523: R966 ^value 1)
  8813. --- Inner Elaboration Phase, active level 1 (S1) ---
  8814. Firing prefer*rvt*predict-yes*H0
  8815. -->
  8816. Firing rl*prefer*rvt*predict-yes*H0*5
  8817. -->
  8818. (S1 ^operator O1927 = 0.)
  8819. Firing prefer*rvt*predict-no*H0
  8820. -->
  8821. Firing rl*prefer*rvt*predict-no*H0*6
  8822. -->
  8823. (S1 ^operator O1928 = 0.9999999999999999)
  8824. inner elaboration loop at bottom goal.
  8825. Retracting rl*prefer*rvt*predict-no*H0*6
  8826. -->
  8827. (S1 ^operator O1926 = 0.9999999999999999)
  8828. Retracting rl*prefer*rvt*predict-yes*H0*5
  8829. -->
  8830. (S1 ^operator O1925 = 0.)
  8831. --- END Proposal Phase ---
  8832. --- Decision Phase ---
  8833. RL update rl*prefer*rvt*predict-yes*H0*3 0.67312 -0.290194 0.382926 -> 0.673128 -0.290194 0.382934(R,m,v=1,0.959459,0.0391616)
  8834. RL update rl*prefer*rvt*predict-yes*H0*3*H1*9 0.326829 0.29019 0.617019 -> 0.326837 0.29019 0.617027(R,m,v=1,1,0)
  8835. =>WM: (13543: S1 ^operator O1928)
  8836. 964: O: O1928 (predict-no)
  8837. --- END Decision Phase ---
  8838. --- Application Phase ---
  8839. --- Firing Productions (PE) For State At Depth 1 ---
  8840. --- Inner Elaboration Phase, active level 1 (S1) ---
  8841. Firing apply*operator
  8842. -->
  8843. (I3 ^predict-no N964 + :O )
  8844. Firing apply*operator*complete
  8845. -->
  8846. (I3 ^predict-yes N963 - :O )
  8847. inner elaboration loop at bottom goal.
  8848. --- Change Working Memory (PE) ---
  8849. =>WM: (13544: I3 ^predict-no N964)
  8850. <=WM: (13531: N963 ^status complete)
  8851. <=WM: (13530: I3 ^predict-yes N963)
  8852. --- Firing Productions (IE) For State At Depth 1 ---
  8853. --- Inner Elaboration Phase, active level 1 (S1) ---
  8854. Firing monitor*world
  8855. -->
  8856. I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
  8857. --- Change Working Memory (IE) ---
  8858. --- END Application Phase ---
  8859. --- Output Phase ---
  8860. ENV: Agent did: predict-no for direction U in state State-B
  8861. In State-B moving U
  8862. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  8863. predict error 0
  8864. dir: dir isL
  8865. --- END Output Phase ---
  8866. |\---- Input Phase ---
  8867. =>WM: (13548: I2 ^dir L)
  8868. =>WM: (13547: I2 ^reward 1)
  8869. =>WM: (13546: I2 ^see 0)
  8870. =>WM: (13545: N964 ^status complete)
  8871. <=WM: (13534: I2 ^dir U)
  8872. <=WM: (13533: I2 ^reward 1)
  8873. <=WM: (13532: I2 ^see 1)
  8874. =>WM: (13549: I2 ^level-1 R1-root)
  8875. <=WM: (13535: I2 ^level-1 R1-root)
  8876. --- END Input Phase ---
  8877. --- Proposal Phase ---
  8878. --- Inner Elaboration Phase, active level 1 (S1) ---
  8879. Firing rl*prefer*rvt*predict-yes*H0*1*H1*22
  8880. -->
  8881. (S1 ^operator O1927 = 0.4768766075457324)
  8882. Firing rl*prefer*rvt*predict-no*H0*2*H1*10
  8883. -->
  8884. (S1 ^operator O1928 = -0.01194930198035649)
  8885. Firing prefer*rvt*predict-no*H0*2*H1
  8886. -->
  8887. Firing prefer*rvt*predict-yes*H0*1*H1
  8888. -->
  8889. Firing elaborate*copy-see-to-output-link
  8890. -->
  8891. (I3 ^see 0 +)
  8892. Firing elaborate*reward*based*on*reward
  8893. -->
  8894. (R968 ^value 1 +)
  8895. (R1 ^reward R968 +)
  8896. Firing propose*predict-yes
  8897. -->
  8898. (O1929 ^name predict-yes +)
  8899. (S1 ^operator O1929 +)
  8900. Firing propose*predict-no
  8901. -->
  8902. (O1930 ^name predict-no +)
  8903. (S1 ^operator O1930 +)
  8904. Firing rl*prefer*rvt*predict-no*H0*2
  8905. -->
  8906. (S1 ^operator O1928 = 0.255013280266792)
  8907. Firing rl*prefer*rvt*predict-yes*H0*1
  8908. -->
  8909. (S1 ^operator O1927 = 0.5231199539495964)
  8910. Firing prefer*rvt*predict-yes*H0
  8911. -->
  8912. Firing prefer*rvt*predict-no*H0
  8913. -->
  8914. Firing elaborate*copy-dir-to-output-link
  8915. -->
  8916. (I3 ^dir L +)
  8917. inner elaboration loop at bottom goal.
  8918. Retracting elaborate*copy-see-to-output-link
  8919. -->
  8920. (I3 ^see 1 +)
  8921. Retracting propose*predict-no
  8922. -->
  8923. (O1928 ^name predict-no +)
  8924. (S1 ^operator O1928 +)
  8925. Retracting propose*predict-yes
  8926. -->
  8927. (O1927 ^name predict-yes +)
  8928. (S1 ^operator O1927 +)
  8929. Retracting elaborate*reward*based*on*reward
  8930. -->
  8931. (R967 ^value 1 +)
  8932. (R1 ^reward R967 +)
  8933. Retracting elaborate*copy-dir-to-output-link
  8934. -->
  8935. (I3 ^dir U +)
  8936. Retracting rl*prefer*rvt*predict-no*H0*6
  8937. -->
  8938. (S1 ^operator O1928 = 0.9999999999999999)
  8939. Retracting rl*prefer*rvt*predict-yes*H0*5
  8940. -->
  8941. (S1 ^operator O1927 = 0.)
  8942. =>WM: (13557: S1 ^operator O1930 +)
  8943. =>WM: (13556: S1 ^operator O1929 +)
  8944. =>WM: (13555: I3 ^dir L)
  8945. =>WM: (13554: O1930 ^name predict-no)
  8946. =>WM: (13553: O1929 ^name predict-yes)
  8947. =>WM: (13552: R968 ^value 1)
  8948. =>WM: (13551: R1 ^reward R968)
  8949. =>WM: (13550: I3 ^see 0)
  8950. <=WM: (13541: S1 ^operator O1927 +)
  8951. <=WM: (13542: S1 ^operator O1928 +)
  8952. <=WM: (13543: S1 ^operator O1928)
  8953. <=WM: (13540: I3 ^dir U)
  8954. <=WM: (13536: R1 ^reward R967)
  8955. <=WM: (13521: I3 ^see 1)
  8956. <=WM: (13539: O1928 ^name predict-no)
  8957. <=WM: (13538: O1927 ^name predict-yes)
  8958. <=WM: (13537: R967 ^value 1)
  8959. --- Inner Elaboration Phase, active level 1 (S1) ---
  8960. Firing prefer*rvt*predict-yes*H0
  8961. -->
  8962. Firing rl*prefer*rvt*predict-yes*H0*1*H1*22
  8963. -->
  8964. (S1 ^operator O1929 = 0.4768766075457324)
  8965. Firing rl*prefer*rvt*predict-yes*H0*1
  8966. -->
  8967. (S1 ^operator O1929 = 0.5231199539495964)
  8968. Firing prefer*rvt*predict-yes*H0*1*H1
  8969. -->
  8970. Firing prefer*rvt*predict-no*H0
  8971. -->
  8972. Firing rl*prefer*rvt*predict-no*H0*2*H1*10
  8973. -->
  8974. (S1 ^operator O1930 = -0.01194930198035649)
  8975. Firing rl*prefer*rvt*predict-no*H0*2
  8976. -->
  8977. (S1 ^operator O1930 = 0.255013280266792)
  8978. Firing prefer*rvt*predict-no*H0*2*H1
  8979. -->
  8980. inner elaboration loop at bottom goal.
  8981. Retracting rl*prefer*rvt*predict-no*H0*2
  8982. -->
  8983. (S1 ^operator O1928 = 0.255013280266792)
  8984. Retracting rl*prefer*rvt*predict-no*H0*2*H1*10
  8985. -->
  8986. (S1 ^operator O1928 = -0.01194930198035649)
  8987. Retracting rl*prefer*rvt*predict-yes*H0*1
  8988. -->
  8989. (S1 ^operator O1927 = 0.5231199539495964)
  8990. Retracting rl*prefer*rvt*predict-yes*H0*1*H1*22
  8991. -->
  8992. (S1 ^operator O1927 = 0.4768766075457324)
  8993. --- END Proposal Phase ---
  8994. --- Decision Phase ---
  8995. RL update rl*prefer*rvt*predict-no*H0*6 1 0 1 -> 1 0 1(R,m,v=1,1,0)
  8996. =>WM: (13558: S1 ^operator O1929)
  8997. 965: O: O1929 (predict-yes)
  8998. --- END Decision Phase ---
  8999. --- Application Phase ---
  9000. --- Firing Productions (PE) For State At Depth 1 ---
  9001. --- Inner Elaboration Phase, active level 1 (S1) ---
  9002. Firing apply*operator
  9003. -->
  9004. (I3 ^predict-yes N965 + :O )
  9005. Firing apply*operator*complete
  9006. -->
  9007. (I3 ^predict-no N964 - :O )
  9008. inner elaboration loop at bottom goal.
  9009. --- Change Working Memory (PE) ---
  9010. =>WM: (13559: I3 ^predict-yes N965)
  9011. <=WM: (13545: N964 ^status complete)
  9012. <=WM: (13544: I3 ^predict-no N964)
  9013. --- Firing Productions (IE) For State At Depth 1 ---
  9014. --- Inner Elaboration Phase, active level 1 (S1) ---
  9015. Firing monitor*world
  9016. -->
  9017. I see 1 and I'm going to do: predict-yes inner elaboration loop at bottom goal.
  9018. --- Change Working Memory (IE) ---
  9019. --- END Application Phase ---
  9020. --- Output Phase ---
  9021. ENV: Agent did: predict-yes for direction L in state State-B
  9022. In State-B moving L
  9023. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  9024. predict error 0
  9025. dir: dir isL
  9026. --- END Output Phase ---
  9027. /|\--- Input Phase ---
  9028. =>WM: (13563: I2 ^dir L)
  9029. =>WM: (13562: I2 ^reward 1)
  9030. =>WM: (13561: I2 ^see 1)
  9031. =>WM: (13560: N965 ^status complete)
  9032. <=WM: (13548: I2 ^dir L)
  9033. <=WM: (13547: I2 ^reward 1)
  9034. <=WM: (13546: I2 ^see 0)
  9035. =>WM: (13564: I2 ^level-1 L1-root)
  9036. <=WM: (13549: I2 ^level-1 R1-root)
  9037. --- END Input Phase ---
  9038. --- Proposal Phase ---
  9039. --- Inner Elaboration Phase, active level 1 (S1) ---
  9040. Firing rl*prefer*rvt*predict-yes*H0*1*H1*20
  9041. -->
  9042. (S1 ^operator O1929 = 0.1693592933936033)
  9043. Firing rl*prefer*rvt*predict-no*H0*2*H1*11
  9044. -->
  9045. (S1 ^operator O1930 = 0.7449862824724345)
  9046. Firing prefer*rvt*predict-no*H0*2*H1
  9047. -->
  9048. Firing prefer*rvt*predict-yes*H0*1*H1
  9049. -->
  9050. Firing elaborate*copy-see-to-output-link
  9051. -->
  9052. (I3 ^see 1 +)
  9053. Firing elaborate*reward*based*on*reward
  9054. -->
  9055. (R969 ^value 1 +)
  9056. (R1 ^reward R969 +)
  9057. Firing propose*predict-yes
  9058. -->
  9059. (O1931 ^name predict-yes +)
  9060. (S1 ^operator O1931 +)
  9061. Firing propose*predict-no
  9062. -->
  9063. (O1932 ^name predict-no +)
  9064. (S1 ^operator O1932 +)
  9065. Firing rl*prefer*rvt*predict-no*H0*2
  9066. -->
  9067. (S1 ^operator O1930 = 0.255013280266792)
  9068. Firing rl*prefer*rvt*predict-yes*H0*1
  9069. -->
  9070. (S1 ^operator O1929 = 0.5231199539495964)
  9071. Firing prefer*rvt*predict-yes*H0
  9072. -->
  9073. Firing prefer*rvt*predict-no*H0
  9074. -->
  9075. Firing elaborate*copy-dir-to-output-link
  9076. -->
  9077. (I3 ^dir L +)
  9078. inner elaboration loop at bottom goal.
  9079. Retracting elaborate*copy-see-to-output-link
  9080. -->
  9081. (I3 ^see 0 +)
  9082. Retracting propose*predict-no
  9083. -->
  9084. (O1930 ^name predict-no +)
  9085. (S1 ^operator O1930 +)
  9086. Retracting propose*predict-yes
  9087. -->
  9088. (O1929 ^name predict-yes +)
  9089. (S1 ^operator O1929 +)
  9090. Retracting elaborate*reward*based*on*reward
  9091. -->
  9092. (R968 ^value 1 +)
  9093. (R1 ^reward R968 +)
  9094. Retracting elaborate*copy-dir-to-output-link
  9095. -->
  9096. (I3 ^dir L +)
  9097. Retracting rl*prefer*rvt*predict-no*H0*2
  9098. -->
  9099. (S1 ^operator O1930 = 0.255013280266792)
  9100. Retracting rl*prefer*rvt*predict-no*H0*2*H1*10
  9101. -->
  9102. (S1 ^operator O1930 = -0.01194930198035649)
  9103. Retracting rl*prefer*rvt*predict-yes*H0*1
  9104. -->
  9105. (S1 ^operator O1929 = 0.5231199539495964)
  9106. Retracting rl*prefer*rvt*predict-yes*H0*1*H1*22
  9107. -->
  9108. (S1 ^operator O1929 = 0.4768766075457324)
  9109. =>WM: (13571: S1 ^operator O1932 +)
  9110. =>WM: (13570: S1 ^operator O1931 +)
  9111. =>WM: (13569: O1932 ^name predict-no)
  9112. =>WM: (13568: O1931 ^name predict-yes)
  9113. =>WM: (13567: R969 ^value 1)
  9114. =>WM: (13566: R1 ^reward R969)
  9115. =>WM: (13565: I3 ^see 1)
  9116. <=WM: (13556: S1 ^operator O1929 +)
  9117. <=WM: (13558: S1 ^operator O1929)
  9118. <=WM: (13557: S1 ^operator O1930 +)
  9119. <=WM: (13551: R1 ^reward R968)
  9120. <=WM: (13550: I3 ^see 0)
  9121. <=WM: (13554: O1930 ^name predict-no)
  9122. <=WM: (13553: O1929 ^name predict-yes)
  9123. <=WM: (13552: R968 ^value 1)
  9124. --- Inner Elaboration Phase, active level 1 (S1) ---
  9125. Firing prefer*rvt*predict-yes*H0
  9126. -->
  9127. Firing rl*prefer*rvt*predict-yes*H0*1
  9128. -->
  9129. (S1 ^operator O1931 = 0.5231199539495964)
  9130. Firing prefer*rvt*predict-yes*H0*1*H1
  9131. -->
  9132. Firing rl*prefer*rvt*predict-yes*H0*1*H1*20
  9133. -->
  9134. (S1 ^operator O1931 = 0.1693592933936033)
  9135. Firing prefer*rvt*predict-no*H0
  9136. -->
  9137. Firing rl*prefer*rvt*predict-no*H0*2
  9138. -->
  9139. (S1 ^operator O1932 = 0.255013280266792)
  9140. Firing prefer*rvt*predict-no*H0*2*H1
  9141. -->
  9142. Firing rl*prefer*rvt*predict-no*H0*2*H1*11
  9143. -->
  9144. (S1 ^operator O1932 = 0.7449862824724345)
  9145. inner elaboration loop at bottom goal.
  9146. Retracting rl*prefer*rvt*predict-no*H0*2
  9147. -->
  9148. (S1 ^operator O1930 = 0.255013280266792)
  9149. Retracting rl*prefer*rvt*predict-no*H0*2*H1*11
  9150. -->
  9151. (S1 ^operator O1930 = 0.7449862824724345)
  9152. Retracting rl*prefer*rvt*predict-yes*H0*1
  9153. -->
  9154. (S1 ^operator O1929 = 0.5231199539495964)
  9155. Retracting rl*prefer*rvt*predict-yes*H0*1*H1*20
  9156. -->
  9157. (S1 ^operator O1929 = 0.1693592933936033)
  9158. --- END Proposal Phase ---
  9159. --- Decision Phase ---
  9160. RL update rl*prefer*rvt*predict-yes*H0*1 0.72796 -0.20484 0.52312 -> 0.727961 -0.20484 0.52312(R,m,v=1,0.978261,0.0214218)
  9161. RL update rl*prefer*rvt*predict-yes*H0*1*H1*22 0.272036 0.204841 0.476877 -> 0.272036 0.204841 0.476877(R,m,v=1,1,0)
  9162. =>WM: (13572: S1 ^operator O1932)
  9163. 966: O: O1932 (predict-no)
  9164. --- END Decision Phase ---
  9165. --- Application Phase ---
  9166. --- Firing Productions (PE) For State At Depth 1 ---
  9167. --- Inner Elaboration Phase, active level 1 (S1) ---
  9168. Firing apply*operator
  9169. -->
  9170. (I3 ^predict-no N966 + :O )
  9171. Firing apply*operator*complete
  9172. -->
  9173. (I3 ^predict-yes N965 - :O )
  9174. inner elaboration loop at bottom goal.
  9175. --- Change Working Memory (PE) ---
  9176. =>WM: (13573: I3 ^predict-no N966)
  9177. <=WM: (13560: N965 ^status complete)
  9178. <=WM: (13559: I3 ^predict-yes N965)
  9179. --- Firing Productions (IE) For State At Depth 1 ---
  9180. --- Inner Elaboration Phase, active level 1 (S1) ---
  9181. Firing monitor*world
  9182. -->
  9183. I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
  9184. --- Change Working Memory (IE) ---
  9185. --- END Application Phase ---
  9186. --- Output Phase ---
  9187. ENV: Agent did: predict-no for direction L in state State-A
  9188. In State-A moving L
  9189. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  9190. predict error 0
  9191. dir: dir isL
  9192. --- END Output Phase ---
  9193. ---- Input Phase ---
  9194. =>WM: (13577: I2 ^dir L)
  9195. =>WM: (13576: I2 ^reward 1)
  9196. =>WM: (13575: I2 ^see 0)
  9197. =>WM: (13574: N966 ^status complete)
  9198. <=WM: (13563: I2 ^dir L)
  9199. <=WM: (13562: I2 ^reward 1)
  9200. <=WM: (13561: I2 ^see 1)
  9201. =>WM: (13578: I2 ^level-1 L0-root)
  9202. <=WM: (13564: I2 ^level-1 L1-root)
  9203. --- END Input Phase ---
  9204. --- Proposal Phase ---
  9205. --- Inner Elaboration Phase, active level 1 (S1) ---
  9206. Firing rl*prefer*rvt*predict-yes*H0*1*H1*21
  9207. -->
  9208. (S1 ^operator O1931 = 0.3)
  9209. Firing rl*prefer*rvt*predict-no*H0*2*H1*12
  9210. -->
  9211. (S1 ^operator O1932 = 0.7449867911055725)
  9212. Firing prefer*rvt*predict-no*H0*2*H1
  9213. -->
  9214. Firing prefer*rvt*predict-yes*H0*1*H1
  9215. -->
  9216. Firing elaborate*copy-see-to-output-link
  9217. -->
  9218. (I3 ^see 0 +)
  9219. Firing elaborate*reward*based*on*reward
  9220. -->
  9221. (R970 ^value 1 +)
  9222. (R1 ^reward R970 +)
  9223. Firing propose*predict-yes
  9224. -->
  9225. (O1933 ^name predict-yes +)
  9226. (S1 ^operator O1933 +)
  9227. Firing propose*predict-no
  9228. -->
  9229. (O1934 ^name predict-no +)
  9230. (S1 ^operator O1934 +)
  9231. Firing rl*prefer*rvt*predict-no*H0*2
  9232. -->
  9233. (S1 ^operator O1932 = 0.255013280266792)
  9234. Firing rl*prefer*rvt*predict-yes*H0*1
  9235. -->
  9236. (S1 ^operator O1931 = 0.5231204697252971)
  9237. Firing prefer*rvt*predict-yes*H0
  9238. -->
  9239. Firing prefer*rvt*predict-no*H0
  9240. -->
  9241. Firing elaborate*copy-dir-to-output-link
  9242. -->
  9243. (I3 ^dir L +)
  9244. inner elaboration loop at bottom goal.
  9245. Retracting elaborate*copy-see-to-output-link
  9246. -->
  9247. (I3 ^see 1 +)
  9248. Retracting propose*predict-no
  9249. -->
  9250. (O1932 ^name predict-no +)
  9251. (S1 ^operator O1932 +)
  9252. Retracting propose*predict-yes
  9253. -->
  9254. (O1931 ^name predict-yes +)
  9255. (S1 ^operator O1931 +)
  9256. Retracting elaborate*reward*based*on*reward
  9257. -->
  9258. (R969 ^value 1 +)
  9259. (R1 ^reward R969 +)
  9260. Retracting elaborate*copy-dir-to-output-link
  9261. -->
  9262. (I3 ^dir L +)
  9263. Retracting rl*prefer*rvt*predict-no*H0*2*H1*11
  9264. -->
  9265. (S1 ^operator O1932 = 0.7449862824724345)
  9266. Retracting rl*prefer*rvt*predict-no*H0*2
  9267. -->
  9268. (S1 ^operator O1932 = 0.255013280266792)
  9269. Retracting rl*prefer*rvt*predict-yes*H0*1*H1*20
  9270. -->
  9271. (S1 ^operator O1931 = 0.1693592933936033)
  9272. Retracting rl*prefer*rvt*predict-yes*H0*1
  9273. -->
  9274. (S1 ^operator O1931 = 0.5231204697252971)
  9275. =>WM: (13585: S1 ^operator O1934 +)
  9276. =>WM: (13584: S1 ^operator O1933 +)
  9277. =>WM: (13583: O1934 ^name predict-no)
  9278. =>WM: (13582: O1933 ^name predict-yes)
  9279. =>WM: (13581: R970 ^value 1)
  9280. =>WM: (13580: R1 ^reward R970)
  9281. =>WM: (13579: I3 ^see 0)
  9282. <=WM: (13570: S1 ^operator O1931 +)
  9283. <=WM: (13571: S1 ^operator O1932 +)
  9284. <=WM: (13572: S1 ^operator O1932)
  9285. <=WM: (13566: R1 ^reward R969)
  9286. <=WM: (13565: I3 ^see 1)
  9287. <=WM: (13569: O1932 ^name predict-no)
  9288. <=WM: (13568: O1931 ^name predict-yes)
  9289. <=WM: (13567: R969 ^value 1)
  9290. --- Inner Elaboration Phase, active level 1 (S1) ---
  9291. Firing prefer*rvt*predict-yes*H0
  9292. -->
  9293. Firing rl*prefer*rvt*predict-yes*H0*1
  9294. -->
  9295. (S1 ^operator O1933 = 0.5231204697252971)
  9296. Firing prefer*rvt*predict-yes*H0*1*H1
  9297. -->
  9298. Firing rl*prefer*rvt*predict-yes*H0*1*H1*21
  9299. -->
  9300. (S1 ^operator O1933 = 0.3)
  9301. Firing prefer*rvt*predict-no*H0
  9302. -->
  9303. Firing rl*prefer*rvt*predict-no*H0*2
  9304. -->
  9305. (S1 ^operator O1934 = 0.255013280266792)
  9306. Firing prefer*rvt*predict-no*H0*2*H1
  9307. -->
  9308. Firing rl*prefer*rvt*predict-no*H0*2*H1*12
  9309. -->
  9310. (S1 ^operator O1934 = 0.7449867911055725)
  9311. inner elaboration loop at bottom goal.
  9312. Retracting rl*prefer*rvt*predict-no*H0*2
  9313. -->
  9314. (S1 ^operator O1932 = 0.255013280266792)
  9315. Retracting rl*prefer*rvt*predict-no*H0*2*H1*12
  9316. -->
  9317. (S1 ^operator O1932 = 0.7449867911055725)
  9318. Retracting rl*prefer*rvt*predict-yes*H0*1
  9319. -->
  9320. (S1 ^operator O1931 = 0.5231204697252971)
  9321. Retracting rl*prefer*rvt*predict-yes*H0*1*H1*21
  9322. -->
  9323. (S1 ^operator O1931 = 0.3)
  9324. --- END Proposal Phase ---
  9325. --- Decision Phase ---
  9326. RL update rl*prefer*rvt*predict-no*H0*2 0.631495 -0.376482 0.255013 -> 0.631495 -0.376482 0.255013(R,m,v=1,0.914894,0.0782797)
  9327. RL update rl*prefer*rvt*predict-no*H0*2*H1*11 0.368505 0.376482 0.744986 -> 0.368505 0.376482 0.744986(R,m,v=1,1,0)
  9328. =>WM: (13586: S1 ^operator O1934)
  9329. 967: O: O1934 (predict-no)
  9330. --- END Decision Phase ---
  9331. --- Application Phase ---
  9332. --- Firing Productions (PE) For State At Depth 1 ---
  9333. --- Inner Elaboration Phase, active level 1 (S1) ---
  9334. Firing apply*operator
  9335. -->
  9336. (I3 ^predict-no N967 + :O )
  9337. Firing apply*operator*complete
  9338. -->
  9339. (I3 ^predict-no N966 - :O )
  9340. inner elaboration loop at bottom goal.
  9341. --- Change Working Memory (PE) ---
  9342. =>WM: (13587: I3 ^predict-no N967)
  9343. <=WM: (13574: N966 ^status complete)
  9344. <=WM: (13573: I3 ^predict-no N966)
  9345. --- Firing Productions (IE) For State At Depth 1 ---
  9346. --- Inner Elaboration Phase, active level 1 (S1) ---
  9347. Firing monitor*world
  9348. -->
  9349. I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
  9350. --- Change Working Memory (IE) ---
  9351. --- END Application Phase ---
  9352. --- Output Phase ---
  9353. ENV: Agent did: predict-no for direction L in state State-A
  9354. In State-A moving L
  9355. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  9356. predict error 0
  9357. dir: dir isL
  9358. --- END Output Phase ---
  9359. /|\--- Input Phase ---
  9360. =>WM: (13591: I2 ^dir L)
  9361. =>WM: (13590: I2 ^reward 1)
  9362. =>WM: (13589: I2 ^see 0)
  9363. =>WM: (13588: N967 ^status complete)
  9364. <=WM: (13577: I2 ^dir L)
  9365. <=WM: (13576: I2 ^reward 1)
  9366. <=WM: (13575: I2 ^see 0)
  9367. =>WM: (13592: I2 ^level-1 L0-root)
  9368. <=WM: (13578: I2 ^level-1 L0-root)
  9369. --- END Input Phase ---
  9370. --- Proposal Phase ---
  9371. --- Inner Elaboration Phase, active level 1 (S1) ---
  9372. Firing rl*prefer*rvt*predict-yes*H0*1*H1*21
  9373. -->
  9374. (S1 ^operator O1933 = 0.3)
  9375. Firing rl*prefer*rvt*predict-no*H0*2*H1*12
  9376. -->
  9377. (S1 ^operator O1934 = 0.7449867911055725)
  9378. Firing prefer*rvt*predict-no*H0*2*H1
  9379. -->
  9380. Firing prefer*rvt*predict-yes*H0*1*H1
  9381. -->
  9382. Firing elaborate*copy-see-to-output-link
  9383. -->
  9384. (I3 ^see 0 +)
  9385. Firing elaborate*reward*based*on*reward
  9386. -->
  9387. (R971 ^value 1 +)
  9388. (R1 ^reward R971 +)
  9389. Firing propose*predict-yes
  9390. -->
  9391. (O1935 ^name predict-yes +)
  9392. (S1 ^operator O1935 +)
  9393. Firing propose*predict-no
  9394. -->
  9395. (O1936 ^name predict-no +)
  9396. (S1 ^operator O1936 +)
  9397. Firing rl*prefer*rvt*predict-no*H0*2
  9398. -->
  9399. (S1 ^operator O1934 = 0.255013345855908)
  9400. Firing rl*prefer*rvt*predict-yes*H0*1
  9401. -->
  9402. (S1 ^operator O1933 = 0.5231204697252971)
  9403. Firing prefer*rvt*predict-yes*H0
  9404. -->
  9405. Firing prefer*rvt*predict-no*H0
  9406. -->
  9407. Firing elaborate*copy-dir-to-output-link
  9408. -->
  9409. (I3 ^dir L +)
  9410. inner elaboration loop at bottom goal.
  9411. Retracting elaborate*copy-see-to-output-link
  9412. -->
  9413. (I3 ^see 0 +)
  9414. Retracting propose*predict-no
  9415. -->
  9416. (O1934 ^name predict-no +)
  9417. (S1 ^operator O1934 +)
  9418. Retracting propose*predict-yes
  9419. -->
  9420. (O1933 ^name predict-yes +)
  9421. (S1 ^operator O1933 +)
  9422. Retracting elaborate*reward*based*on*reward
  9423. -->
  9424. (R970 ^value 1 +)
  9425. (R1 ^reward R970 +)
  9426. Retracting elaborate*copy-dir-to-output-link
  9427. -->
  9428. (I3 ^dir L +)
  9429. Retracting rl*prefer*rvt*predict-no*H0*2*H1*12
  9430. -->
  9431. (S1 ^operator O1934 = 0.7449867911055725)
  9432. Retracting rl*prefer*rvt*predict-no*H0*2
  9433. -->
  9434. (S1 ^operator O1934 = 0.255013345855908)
  9435. Retracting rl*prefer*rvt*predict-yes*H0*1*H1*21
  9436. -->
  9437. (S1 ^operator O1933 = 0.3)
  9438. Retracting rl*prefer*rvt*predict-yes*H0*1
  9439. -->
  9440. (S1 ^operator O1933 = 0.5231204697252971)
  9441. =>WM: (13598: S1 ^operator O1936 +)
  9442. =>WM: (13597: S1 ^operator O1935 +)
  9443. =>WM: (13596: O1936 ^name predict-no)
  9444. =>WM: (13595: O1935 ^name predict-yes)
  9445. =>WM: (13594: R971 ^value 1)
  9446. =>WM: (13593: R1 ^reward R971)
  9447. <=WM: (13584: S1 ^operator O1933 +)
  9448. <=WM: (13585: S1 ^operator O1934 +)
  9449. <=WM: (13586: S1 ^operator O1934)
  9450. <=WM: (13580: R1 ^reward R970)
  9451. <=WM: (13583: O1934 ^name predict-no)
  9452. <=WM: (13582: O1933 ^name predict-yes)
  9453. <=WM: (13581: R970 ^value 1)
  9454. --- Inner Elaboration Phase, active level 1 (S1) ---
  9455. Firing prefer*rvt*predict-yes*H0
  9456. -->
  9457. Firing rl*prefer*rvt*predict-yes*H0*1
  9458. -->
  9459. (S1 ^operator O1935 = 0.5231204697252971)
  9460. Firing prefer*rvt*predict-yes*H0*1*H1
  9461. -->
  9462. Firing rl*prefer*rvt*predict-yes*H0*1*H1*21
  9463. -->
  9464. (S1 ^operator O1935 = 0.3)
  9465. Firing prefer*rvt*predict-no*H0
  9466. -->
  9467. Firing rl*prefer*rvt*predict-no*H0*2
  9468. -->
  9469. (S1 ^operator O1936 = 0.255013345855908)
  9470. Firing prefer*rvt*predict-no*H0*2*H1
  9471. -->
  9472. Firing rl*prefer*rvt*predict-no*H0*2*H1*12
  9473. -->
  9474. (S1 ^operator O1936 = 0.7449867911055725)
  9475. inner elaboration loop at bottom goal.
  9476. Retracting rl*prefer*rvt*predict-no*H0*2
  9477. -->
  9478. (S1 ^operator O1934 = 0.255013345855908)
  9479. Retracting rl*prefer*rvt*predict-no*H0*2*H1*12
  9480. -->
  9481. (S1 ^operator O1934 = 0.7449867911055725)
  9482. Retracting rl*prefer*rvt*predict-yes*H0*1
  9483. -->
  9484. (S1 ^operator O1933 = 0.5231204697252971)
  9485. Retracting rl*prefer*rvt*predict-yes*H0*1*H1*21
  9486. -->
  9487. (S1 ^operator O1933 = 0.3)
  9488. --- END Proposal Phase ---
  9489. --- Decision Phase ---
  9490. RL update rl*prefer*rvt*predict-no*H0*2 0.631495 -0.376482 0.255013 -> 0.631495 -0.376482 0.255013(R,m,v=1,0.915344,0.0779016)
  9491. RL update rl*prefer*rvt*predict-no*H0*2*H1*12 0.368505 0.376482 0.744987 -> 0.368505 0.376482 0.744987(R,m,v=1,1,0)
  9492. =>WM: (13599: S1 ^operator O1936)
  9493. 968: O: O1936 (predict-no)
  9494. --- END Decision Phase ---
  9495. --- Application Phase ---
  9496. --- Firing Productions (PE) For State At Depth 1 ---
  9497. --- Inner Elaboration Phase, active level 1 (S1) ---
  9498. Firing apply*operator
  9499. -->
  9500. (I3 ^predict-no N968 + :O )
  9501. Firing apply*operator*complete
  9502. -->
  9503. (I3 ^predict-no N967 - :O )
  9504. inner elaboration loop at bottom goal.
  9505. --- Change Working Memory (PE) ---
  9506. =>WM: (13600: I3 ^predict-no N968)
  9507. <=WM: (13588: N967 ^status complete)
  9508. <=WM: (13587: I3 ^predict-no N967)
  9509. --- Firing Productions (IE) For State At Depth 1 ---
  9510. --- Inner Elaboration Phase, active level 1 (S1) ---
  9511. Firing monitor*world
  9512. -->
  9513. I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
  9514. --- Change Working Memory (IE) ---
  9515. --- END Application Phase ---
  9516. --- Output Phase ---
  9517. ENV: Agent did: predict-no for direction L in state State-A
  9518. In State-A moving L
  9519. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  9520. predict error 0
  9521. dir: dir isR
  9522. --- END Output Phase ---
  9523. -/--- Input Phase ---
  9524. =>WM: (13604: I2 ^dir R)
  9525. =>WM: (13603: I2 ^reward 1)
  9526. =>WM: (13602: I2 ^see 0)
  9527. =>WM: (13601: N968 ^status complete)
  9528. <=WM: (13591: I2 ^dir L)
  9529. <=WM: (13590: I2 ^reward 1)
  9530. <=WM: (13589: I2 ^see 0)
  9531. =>WM: (13605: I2 ^level-1 L0-root)
  9532. <=WM: (13592: I2 ^level-1 L0-root)
  9533. --- END Input Phase ---
  9534. --- Proposal Phase ---
  9535. --- Inner Elaboration Phase, active level 1 (S1) ---
  9536. Firing rl*prefer*rvt*predict-yes*H0*3*H1*14
  9537. -->
  9538. (S1 ^operator O1935 = 0.6170812384661459)
  9539. Firing rl*prefer*rvt*predict-no*H0*4*H1*13
  9540. -->
  9541. (S1 ^operator O1936 = 0.4910065094545203)
  9542. Firing prefer*rvt*predict-no*H0*4*H1
  9543. -->
  9544. Firing prefer*rvt*predict-yes*H0*3*H1
  9545. -->
  9546. Firing elaborate*copy-see-to-output-link
  9547. -->
  9548. (I3 ^see 0 +)
  9549. Firing elaborate*reward*based*on*reward
  9550. -->
  9551. (R972 ^value 1 +)
  9552. (R1 ^reward R972 +)
  9553. Firing propose*predict-yes
  9554. -->
  9555. (O1937 ^name predict-yes +)
  9556. (S1 ^operator O1937 +)
  9557. Firing propose*predict-no
  9558. -->
  9559. (O1938 ^name predict-no +)
  9560. (S1 ^operator O1938 +)
  9561. Firing rl*prefer*rvt*predict-no*H0*4
  9562. -->
  9563. (S1 ^operator O1936 = 0.1269767780720474)
  9564. Firing rl*prefer*rvt*predict-yes*H0*3
  9565. -->
  9566. (S1 ^operator O1935 = 0.3829340154836592)
  9567. Firing prefer*rvt*predict-yes*H0
  9568. -->
  9569. Firing prefer*rvt*predict-no*H0
  9570. -->
  9571. Firing elaborate*copy-dir-to-output-link
  9572. -->
  9573. (I3 ^dir R +)
  9574. inner elaboration loop at bottom goal.
  9575. Retracting elaborate*copy-see-to-output-link
  9576. -->
  9577. (I3 ^see 0 +)
  9578. Retracting propose*predict-no
  9579. -->
  9580. (O1936 ^name predict-no +)
  9581. (S1 ^operator O1936 +)
  9582. Retracting propose*predict-yes
  9583. -->
  9584. (O1935 ^name predict-yes +)
  9585. (S1 ^operator O1935 +)
  9586. Retracting elaborate*reward*based*on*reward
  9587. -->
  9588. (R971 ^value 1 +)
  9589. (R1 ^reward R971 +)
  9590. Retracting elaborate*copy-dir-to-output-link
  9591. -->
  9592. (I3 ^dir L +)
  9593. Retracting rl*prefer*rvt*predict-no*H0*2*H1*12
  9594. -->
  9595. (S1 ^operator O1936 = 0.7449867705613504)
  9596. Retracting rl*prefer*rvt*predict-no*H0*2
  9597. -->
  9598. (S1 ^operator O1936 = 0.255013325311686)
  9599. Retracting rl*prefer*rvt*predict-yes*H0*1*H1*21
  9600. -->
  9601. (S1 ^operator O1935 = 0.3)
  9602. Retracting rl*prefer*rvt*predict-yes*H0*1
  9603. -->
  9604. (S1 ^operator O1935 = 0.5231204697252971)
  9605. =>WM: (13612: S1 ^operator O1938 +)
  9606. =>WM: (13611: S1 ^operator O1937 +)
  9607. =>WM: (13610: I3 ^dir R)
  9608. =>WM: (13609: O1938 ^name predict-no)
  9609. =>WM: (13608: O1937 ^name predict-yes)
  9610. =>WM: (13607: R972 ^value 1)
  9611. =>WM: (13606: R1 ^reward R972)
  9612. <=WM: (13597: S1 ^operator O1935 +)
  9613. <=WM: (13598: S1 ^operator O1936 +)
  9614. <=WM: (13599: S1 ^operator O1936)
  9615. <=WM: (13555: I3 ^dir L)
  9616. <=WM: (13593: R1 ^reward R971)
  9617. <=WM: (13596: O1936 ^name predict-no)
  9618. <=WM: (13595: O1935 ^name predict-yes)
  9619. <=WM: (13594: R971 ^value 1)
  9620. --- Inner Elaboration Phase, active level 1 (S1) ---
  9621. Firing prefer*rvt*predict-yes*H0
  9622. -->
  9623. Firing rl*prefer*rvt*predict-yes*H0*3*H1*14
  9624. -->
  9625. (S1 ^operator O1937 = 0.6170812384661459)
  9626. Firing rl*prefer*rvt*predict-yes*H0*3
  9627. -->
  9628. (S1 ^operator O1937 = 0.3829340154836592)
  9629. Firing prefer*rvt*predict-yes*H0*3*H1
  9630. -->
  9631. Firing prefer*rvt*predict-no*H0
  9632. -->
  9633. Firing rl*prefer*rvt*predict-no*H0*4*H1*13
  9634. -->
  9635. (S1 ^operator O1938 = 0.4910065094545203)
  9636. Firing rl*prefer*rvt*predict-no*H0*4
  9637. -->
  9638. (S1 ^operator O1938 = 0.1269767780720474)
  9639. Firing prefer*rvt*predict-no*H0*4*H1
  9640. -->
  9641. inner elaboration loop at bottom goal.
  9642. Retracting rl*prefer*rvt*predict-no*H0*4
  9643. -->
  9644. (S1 ^operator O1936 = 0.1269767780720474)
  9645. Retracting rl*prefer*rvt*predict-no*H0*4*H1*13
  9646. -->
  9647. (S1 ^operator O1936 = 0.4910065094545203)
  9648. Retracting rl*prefer*rvt*predict-yes*H0*3
  9649. -->
  9650. (S1 ^operator O1935 = 0.3829340154836592)
  9651. Retracting rl*prefer*rvt*predict-yes*H0*3*H1*14
  9652. -->
  9653. (S1 ^operator O1935 = 0.6170812384661459)
  9654. --- END Proposal Phase ---
  9655. --- Decision Phase ---
  9656. RL update rl*prefer*rvt*predict-no*H0*2 0.631495 -0.376482 0.255013 -> 0.631495 -0.376482 0.255013(R,m,v=1,0.915789,0.0775272)
  9657. RL update rl*prefer*rvt*predict-no*H0*2*H1*12 0.368505 0.376482 0.744987 -> 0.368505 0.376482 0.744987(R,m,v=1,1,0)
  9658. =>WM: (13613: S1 ^operator O1937)
  9659. 969: O: O1937 (predict-yes)
  9660. --- END Decision Phase ---
  9661. --- Application Phase ---
  9662. --- Firing Productions (PE) For State At Depth 1 ---
  9663. --- Inner Elaboration Phase, active level 1 (S1) ---
  9664. Firing apply*operator
  9665. -->
  9666. (I3 ^predict-yes N969 + :O )
  9667. Firing apply*operator*complete
  9668. -->
  9669. (I3 ^predict-no N968 - :O )
  9670. inner elaboration loop at bottom goal.
  9671. --- Change Working Memory (PE) ---
  9672. =>WM: (13614: I3 ^predict-yes N969)
  9673. <=WM: (13601: N968 ^status complete)
  9674. <=WM: (13600: I3 ^predict-no N968)
  9675. --- Firing Productions (IE) For State At Depth 1 ---
  9676. --- Inner Elaboration Phase, active level 1 (S1) ---
  9677. Firing monitor*world
  9678. -->
  9679. I see 1 and I'm going to do: predict-yes inner elaboration loop at bottom goal.
  9680. --- Change Working Memory (IE) ---
  9681. --- END Application Phase ---
  9682. --- Output Phase ---
  9683. ENV: Agent did: predict-yes for direction R in state State-A
  9684. In State-A moving R
  9685. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  9686. predict error 0
  9687. dir: dir isU
  9688. --- END Output Phase ---
  9689. |\---- Input Phase ---
  9690. =>WM: (13618: I2 ^dir U)
  9691. =>WM: (13617: I2 ^reward 1)
  9692. =>WM: (13616: I2 ^see 1)
  9693. =>WM: (13615: N969 ^status complete)
  9694. <=WM: (13604: I2 ^dir R)
  9695. <=WM: (13603: I2 ^reward 1)
  9696. <=WM: (13602: I2 ^see 0)
  9697. =>WM: (13619: I2 ^level-1 R1-root)
  9698. <=WM: (13605: I2 ^level-1 L0-root)
  9699. --- END Input Phase ---
  9700. --- Proposal Phase ---
  9701. --- Inner Elaboration Phase, active level 1 (S1) ---
  9702. Firing elaborate*copy-see-to-output-link
  9703. -->
  9704. (I3 ^see 1 +)
  9705. Firing elaborate*reward*based*on*reward
  9706. -->
  9707. (R973 ^value 1 +)
  9708. (R1 ^reward R973 +)
  9709. Firing propose*predict-yes
  9710. -->
  9711. (O1939 ^name predict-yes +)
  9712. (S1 ^operator O1939 +)
  9713. Firing propose*predict-no
  9714. -->
  9715. (O1940 ^name predict-no +)
  9716. (S1 ^operator O1940 +)
  9717. Firing rl*prefer*rvt*predict-no*H0*6
  9718. -->
  9719. (S1 ^operator O1938 = 0.9999999999999999)
  9720. Firing rl*prefer*rvt*predict-yes*H0*5
  9721. -->
  9722. (S1 ^operator O1937 = 0.)
  9723. Firing prefer*rvt*predict-yes*H0
  9724. -->
  9725. Firing prefer*rvt*predict-no*H0
  9726. -->
  9727. Firing elaborate*copy-dir-to-output-link
  9728. -->
  9729. (I3 ^dir U +)
  9730. inner elaboration loop at bottom goal.
  9731. Retracting elaborate*copy-see-to-output-link
  9732. -->
  9733. (I3 ^see 0 +)
  9734. Retracting propose*predict-no
  9735. -->
  9736. (O1938 ^name predict-no +)
  9737. (S1 ^operator O1938 +)
  9738. Retracting propose*predict-yes
  9739. -->
  9740. (O1937 ^name predict-yes +)
  9741. (S1 ^operator O1937 +)
  9742. Retracting elaborate*reward*based*on*reward
  9743. -->
  9744. (R972 ^value 1 +)
  9745. (R1 ^reward R972 +)
  9746. Retracting elaborate*copy-dir-to-output-link
  9747. -->
  9748. (I3 ^dir R +)
  9749. Retracting rl*prefer*rvt*predict-no*H0*4
  9750. -->
  9751. (S1 ^operator O1938 = 0.1269767780720474)
  9752. Retracting rl*prefer*rvt*predict-no*H0*4*H1*13
  9753. -->
  9754. (S1 ^operator O1938 = 0.4910065094545203)
  9755. Retracting rl*prefer*rvt*predict-yes*H0*3
  9756. -->
  9757. (S1 ^operator O1937 = 0.3829340154836592)
  9758. Retracting rl*prefer*rvt*predict-yes*H0*3*H1*14
  9759. -->
  9760. (S1 ^operator O1937 = 0.6170812384661459)
  9761. =>WM: (13627: S1 ^operator O1940 +)
  9762. =>WM: (13626: S1 ^operator O1939 +)
  9763. =>WM: (13625: I3 ^dir U)
  9764. =>WM: (13624: O1940 ^name predict-no)
  9765. =>WM: (13623: O1939 ^name predict-yes)
  9766. =>WM: (13622: R973 ^value 1)
  9767. =>WM: (13621: R1 ^reward R973)
  9768. =>WM: (13620: I3 ^see 1)
  9769. <=WM: (13611: S1 ^operator O1937 +)
  9770. <=WM: (13613: S1 ^operator O1937)
  9771. <=WM: (13612: S1 ^operator O1938 +)
  9772. <=WM: (13610: I3 ^dir R)
  9773. <=WM: (13606: R1 ^reward R972)
  9774. <=WM: (13579: I3 ^see 0)
  9775. <=WM: (13609: O1938 ^name predict-no)
  9776. <=WM: (13608: O1937 ^name predict-yes)
  9777. <=WM: (13607: R972 ^value 1)
  9778. --- Inner Elaboration Phase, active level 1 (S1) ---
  9779. Firing prefer*rvt*predict-yes*H0
  9780. -->
  9781. Firing rl*prefer*rvt*predict-yes*H0*5
  9782. -->
  9783. (S1 ^operator O1939 = 0.)
  9784. Firing prefer*rvt*predict-no*H0
  9785. -->
  9786. Firing rl*prefer*rvt*predict-no*H0*6
  9787. -->
  9788. (S1 ^operator O1940 = 0.9999999999999999)
  9789. inner elaboration loop at bottom goal.
  9790. Retracting rl*prefer*rvt*predict-no*H0*6
  9791. -->
  9792. (S1 ^operator O1938 = 0.9999999999999999)
  9793. Retracting rl*prefer*rvt*predict-yes*H0*5
  9794. -->
  9795. (S1 ^operator O1937 = 0.)
  9796. --- END Proposal Phase ---
  9797. --- Decision Phase ---
  9798. RL update rl*prefer*rvt*predict-yes*H0*3 0.673128 -0.290194 0.382934 -> 0.673126 -0.290194 0.382932(R,m,v=1,0.959732,0.038908)
  9799. RL update rl*prefer*rvt*predict-yes*H0*3*H1*14 0.326886 0.290195 0.617081 -> 0.326884 0.290195 0.617079(R,m,v=1,1,0)
  9800. =>WM: (13628: S1 ^operator O1940)
  9801. 970: O: O1940 (predict-no)
  9802. --- END Decision Phase ---
  9803. --- Application Phase ---
  9804. --- Firing Productions (PE) For State At Depth 1 ---
  9805. --- Inner Elaboration Phase, active level 1 (S1) ---
  9806. Firing apply*operator
  9807. -->
  9808. (I3 ^predict-no N970 + :O )
  9809. Firing apply*operator*complete
  9810. -->
  9811. (I3 ^predict-yes N969 - :O )
  9812. inner elaboration loop at bottom goal.
  9813. --- Change Working Memory (PE) ---
  9814. =>WM: (13629: I3 ^predict-no N970)
  9815. <=WM: (13615: N969 ^status complete)
  9816. <=WM: (13614: I3 ^predict-yes N969)
  9817. --- Firing Productions (IE) For State At Depth 1 ---
  9818. --- Inner Elaboration Phase, active level 1 (S1) ---
  9819. Firing monitor*world
  9820. -->
  9821. I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
  9822. --- Change Working Memory (IE) ---
  9823. --- END Application Phase ---
  9824. --- Output Phase ---
  9825. ENV: Agent did: predict-no for direction U in state State-B
  9826. In State-B moving U
  9827. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  9828. predict error 0
  9829. dir: dir isL
  9830. --- END Output Phase ---
  9831. /|--- Input Phase ---
  9832. =>WM: (13633: I2 ^dir L)
  9833. =>WM: (13632: I2 ^reward 1)
  9834. =>WM: (13631: I2 ^see 0)
  9835. =>WM: (13630: N970 ^status complete)
  9836. <=WM: (13618: I2 ^dir U)
  9837. <=WM: (13617: I2 ^reward 1)
  9838. <=WM: (13616: I2 ^see 1)
  9839. =>WM: (13634: I2 ^level-1 R1-root)
  9840. <=WM: (13619: I2 ^level-1 R1-root)
  9841. --- END Input Phase ---
  9842. --- Proposal Phase ---
  9843. --- Inner Elaboration Phase, active level 1 (S1) ---
  9844. Firing rl*prefer*rvt*predict-yes*H0*1*H1*22
  9845. -->
  9846. (S1 ^operator O1939 = 0.4768771233214331)
  9847. Firing rl*prefer*rvt*predict-no*H0*2*H1*10
  9848. -->
  9849. (S1 ^operator O1940 = -0.01194930198035649)
  9850. Firing prefer*rvt*predict-no*H0*2*H1
  9851. -->
  9852. Firing prefer*rvt*predict-yes*H0*1*H1
  9853. -->
  9854. Firing elaborate*copy-see-to-output-link
  9855. -->
  9856. (I3 ^see 0 +)
  9857. Firing elaborate*reward*based*on*reward
  9858. -->
  9859. (R974 ^value 1 +)
  9860. (R1 ^reward R974 +)
  9861. Firing propose*predict-yes
  9862. -->
  9863. (O1941 ^name predict-yes +)
  9864. (S1 ^operator O1941 +)
  9865. Firing propose*predict-no
  9866. -->
  9867. (O1942 ^name predict-no +)
  9868. (S1 ^operator O1942 +)
  9869. Firing rl*prefer*rvt*predict-no*H0*2
  9870. -->
  9871. (S1 ^operator O1940 = 0.2550133109307305)
  9872. Firing rl*prefer*rvt*predict-yes*H0*1
  9873. -->
  9874. (S1 ^operator O1939 = 0.5231204697252971)
  9875. Firing prefer*rvt*predict-yes*H0
  9876. -->
  9877. Firing prefer*rvt*predict-no*H0
  9878. -->
  9879. Firing elaborate*copy-dir-to-output-link
  9880. -->
  9881. (I3 ^dir L +)
  9882. inner elaboration loop at bottom goal.
  9883. Retracting elaborate*copy-see-to-output-link
  9884. -->
  9885. (I3 ^see 1 +)
  9886. Retracting propose*predict-no
  9887. -->
  9888. (O1940 ^name predict-no +)
  9889. (S1 ^operator O1940 +)
  9890. Retracting propose*predict-yes
  9891. -->
  9892. (O1939 ^name predict-yes +)
  9893. (S1 ^operator O1939 +)
  9894. Retracting elaborate*reward*based*on*reward
  9895. -->
  9896. (R973 ^value 1 +)
  9897. (R1 ^reward R973 +)
  9898. Retracting elaborate*copy-dir-to-output-link
  9899. -->
  9900. (I3 ^dir U +)
  9901. Retracting rl*prefer*rvt*predict-no*H0*6
  9902. -->
  9903. (S1 ^operator O1940 = 0.9999999999999999)
  9904. Retracting rl*prefer*rvt*predict-yes*H0*5
  9905. -->
  9906. (S1 ^operator O1939 = 0.)
  9907. =>WM: (13642: S1 ^operator O1942 +)
  9908. =>WM: (13641: S1 ^operator O1941 +)
  9909. =>WM: (13640: I3 ^dir L)
  9910. =>WM: (13639: O1942 ^name predict-no)
  9911. =>WM: (13638: O1941 ^name predict-yes)
  9912. =>WM: (13637: R974 ^value 1)
  9913. =>WM: (13636: R1 ^reward R974)
  9914. =>WM: (13635: I3 ^see 0)
  9915. <=WM: (13626: S1 ^operator O1939 +)
  9916. <=WM: (13627: S1 ^operator O1940 +)
  9917. <=WM: (13628: S1 ^operator O1940)
  9918. <=WM: (13625: I3 ^dir U)
  9919. <=WM: (13621: R1 ^reward R973)
  9920. <=WM: (13620: I3 ^see 1)
  9921. <=WM: (13624: O1940 ^name predict-no)
  9922. <=WM: (13623: O1939 ^name predict-yes)
  9923. <=WM: (13622: R973 ^value 1)
  9924. --- Inner Elaboration Phase, active level 1 (S1) ---
  9925. Firing prefer*rvt*predict-yes*H0
  9926. -->
  9927. Firing rl*prefer*rvt*predict-yes*H0*1*H1*22
  9928. -->
  9929. (S1 ^operator O1941 = 0.4768771233214331)
  9930. Firing rl*prefer*rvt*predict-yes*H0*1
  9931. -->
  9932. (S1 ^operator O1941 = 0.5231204697252971)
  9933. Firing prefer*rvt*predict-yes*H0*1*H1
  9934. -->
  9935. Firing prefer*rvt*predict-no*H0
  9936. -->
  9937. Firing rl*prefer*rvt*predict-no*H0*2*H1*10
  9938. -->
  9939. (S1 ^operator O1942 = -0.01194930198035649)
  9940. Firing rl*prefer*rvt*predict-no*H0*2
  9941. -->
  9942. (S1 ^operator O1942 = 0.2550133109307305)
  9943. Firing prefer*rvt*predict-no*H0*2*H1
  9944. -->
  9945. inner elaboration loop at bottom goal.
  9946. Retracting rl*prefer*rvt*predict-no*H0*2
  9947. -->
  9948. (S1 ^operator O1940 = 0.2550133109307305)
  9949. Retracting rl*prefer*rvt*predict-no*H0*2*H1*10
  9950. -->
  9951. (S1 ^operator O1940 = -0.01194930198035649)
  9952. Retracting rl*prefer*rvt*predict-yes*H0*1
  9953. -->
  9954. (S1 ^operator O1939 = 0.5231204697252971)
  9955. Retracting rl*prefer*rvt*predict-yes*H0*1*H1*22
  9956. -->
  9957. (S1 ^operator O1939 = 0.4768771233214331)
  9958. --- END Proposal Phase ---
  9959. --- Decision Phase ---
  9960. RL update rl*prefer*rvt*predict-no*H0*6 1 0 1 -> 1 0 1(R,m,v=1,1,0)
  9961. =>WM: (13643: S1 ^operator O1941)
  9962. 971: O: O1941 (predict-yes)
  9963. --- END Decision Phase ---
  9964. --- Application Phase ---
  9965. --- Firing Productions (PE) For State At Depth 1 ---
  9966. --- Inner Elaboration Phase, active level 1 (S1) ---
  9967. Firing apply*operator
  9968. -->
  9969. (I3 ^predict-yes N971 + :O )
  9970. Firing apply*operator*complete
  9971. -->
  9972. (I3 ^predict-no N970 - :O )
  9973. inner elaboration loop at bottom goal.
  9974. --- Change Working Memory (PE) ---
  9975. =>WM: (13644: I3 ^predict-yes N971)
  9976. <=WM: (13630: N970 ^status complete)
  9977. <=WM: (13629: I3 ^predict-no N970)
  9978. --- Firing Productions (IE) For State At Depth 1 ---
  9979. --- Inner Elaboration Phase, active level 1 (S1) ---
  9980. Firing monitor*world
  9981. -->
  9982. I see 1 and I'm going to do: predict-yes inner elaboration loop at bottom goal.
  9983. --- Change Working Memory (IE) ---
  9984. --- END Application Phase ---
  9985. --- Output Phase ---
  9986. ENV: Agent did: predict-yes for direction L in state State-B
  9987. In State-B moving L
  9988. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  9989. predict error 0
  9990. dir: dir isL
  9991. --- END Output Phase ---
  9992. \--- Input Phase ---
  9993. =>WM: (13648: I2 ^dir L)
  9994. =>WM: (13647: I2 ^reward 1)
  9995. =>WM: (13646: I2 ^see 1)
  9996. =>WM: (13645: N971 ^status complete)
  9997. <=WM: (13633: I2 ^dir L)
  9998. <=WM: (13632: I2 ^reward 1)
  9999. <=WM: (13631: I2 ^see 0)
  10000. =>WM: (13649: I2 ^level-1 L1-root)
  10001. <=WM: (13634: I2 ^level-1 R1-root)
  10002. --- END Input Phase ---
  10003. --- Proposal Phase ---
  10004. --- Inner Elaboration Phase, active level 1 (S1) ---
  10005. Firing rl*prefer*rvt*predict-yes*H0*1*H1*20
  10006. -->
  10007. (S1 ^operator O1941 = 0.1693592933936033)
  10008. Firing rl*prefer*rvt*predict-no*H0*2*H1*11
  10009. -->
  10010. (S1 ^operator O1942 = 0.7449863480615504)
  10011. Firing prefer*rvt*predict-no*H0*2*H1
  10012. -->
  10013. Firing prefer*rvt*predict-yes*H0*1*H1
  10014. -->
  10015. Firing elaborate*copy-see-to-output-link
  10016. -->
  10017. (I3 ^see 1 +)
  10018. Firing elaborate*reward*based*on*reward
  10019. -->
  10020. (R975 ^value 1 +)
  10021. (R1 ^reward R975 +)
  10022. Firing propose*predict-yes
  10023. -->
  10024. (O1943 ^name predict-yes +)
  10025. (S1 ^operator O1943 +)
  10026. Firing propose*predict-no
  10027. -->
  10028. (O1944 ^name predict-no +)
  10029. (S1 ^operator O1944 +)
  10030. Firing rl*prefer*rvt*predict-no*H0*2
  10031. -->
  10032. (S1 ^operator O1942 = 0.2550133109307305)
  10033. Firing rl*prefer*rvt*predict-yes*H0*1
  10034. -->
  10035. (S1 ^operator O1941 = 0.5231204697252971)
  10036. Firing prefer*rvt*predict-yes*H0
  10037. -->
  10038. Firing prefer*rvt*predict-no*H0
  10039. -->
  10040. Firing elaborate*copy-dir-to-output-link
  10041. -->
  10042. (I3 ^dir L +)
  10043. inner elaboration loop at bottom goal.
  10044. Retracting elaborate*copy-see-to-output-link
  10045. -->
  10046. (I3 ^see 0 +)
  10047. Retracting propose*predict-no
  10048. -->
  10049. (O1942 ^name predict-no +)
  10050. (S1 ^operator O1942 +)
  10051. Retracting propose*predict-yes
  10052. -->
  10053. (O1941 ^name predict-yes +)
  10054. (S1 ^operator O1941 +)
  10055. Retracting elaborate*reward*based*on*reward
  10056. -->
  10057. (R974 ^value 1 +)
  10058. (R1 ^reward R974 +)
  10059. Retracting elaborate*copy-dir-to-output-link
  10060. -->
  10061. (I3 ^dir L +)
  10062. Retracting rl*prefer*rvt*predict-no*H0*2
  10063. -->
  10064. (S1 ^operator O1942 = 0.2550133109307305)
  10065. Retracting rl*prefer*rvt*predict-no*H0*2*H1*10
  10066. -->
  10067. (S1 ^operator O1942 = -0.01194930198035649)
  10068. Retracting rl*prefer*rvt*predict-yes*H0*1
  10069. -->
  10070. (S1 ^operator O1941 = 0.5231204697252971)
  10071. Retracting rl*prefer*rvt*predict-yes*H0*1*H1*22
  10072. -->
  10073. (S1 ^operator O1941 = 0.4768771233214331)
  10074. =>WM: (13656: S1 ^operator O1944 +)
  10075. =>WM: (13655: S1 ^operator O1943 +)
  10076. =>WM: (13654: O1944 ^name predict-no)
  10077. =>WM: (13653: O1943 ^name predict-yes)
  10078. =>WM: (13652: R975 ^value 1)
  10079. =>WM: (13651: R1 ^reward R975)
  10080. =>WM: (13650: I3 ^see 1)
  10081. <=WM: (13641: S1 ^operator O1941 +)
  10082. <=WM: (13643: S1 ^operator O1941)
  10083. <=WM: (13642: S1 ^operator O1942 +)
  10084. <=WM: (13636: R1 ^reward R974)
  10085. <=WM: (13635: I3 ^see 0)
  10086. <=WM: (13639: O1942 ^name predict-no)
  10087. <=WM: (13638: O1941 ^name predict-yes)
  10088. <=WM: (13637: R974 ^value 1)
  10089. --- Inner Elaboration Phase, active level 1 (S1) ---
  10090. Firing prefer*rvt*predict-yes*H0
  10091. -->
  10092. Firing rl*prefer*rvt*predict-yes*H0*1
  10093. -->
  10094. (S1 ^operator O1943 = 0.5231204697252971)
  10095. Firing prefer*rvt*predict-yes*H0*1*H1
  10096. -->
  10097. Firing rl*prefer*rvt*predict-yes*H0*1*H1*20
  10098. -->
  10099. (S1 ^operator O1943 = 0.1693592933936033)
  10100. Firing prefer*rvt*predict-no*H0
  10101. -->
  10102. Firing rl*prefer*rvt*predict-no*H0*2
  10103. -->
  10104. (S1 ^operator O1944 = 0.2550133109307305)
  10105. Firing prefer*rvt*predict-no*H0*2*H1
  10106. -->
  10107. Firing rl*prefer*rvt*predict-no*H0*2*H1*11
  10108. -->
  10109. (S1 ^operator O1944 = 0.7449863480615504)
  10110. inner elaboration loop at bottom goal.
  10111. Retracting rl*prefer*rvt*predict-no*H0*2
  10112. -->
  10113. (S1 ^operator O1942 = 0.2550133109307305)
  10114. Retracting rl*prefer*rvt*predict-no*H0*2*H1*11
  10115. -->
  10116. (S1 ^operator O1942 = 0.7449863480615504)
  10117. Retracting rl*prefer*rvt*predict-yes*H0*1
  10118. -->
  10119. (S1 ^operator O1941 = 0.5231204697252971)
  10120. Retracting rl*prefer*rvt*predict-yes*H0*1*H1*20
  10121. -->
  10122. (S1 ^operator O1941 = 0.1693592933936033)
  10123. --- END Proposal Phase ---
  10124. --- Decision Phase ---
  10125. RL update rl*prefer*rvt*predict-yes*H0*1 0.727961 -0.20484 0.52312 -> 0.727961 -0.20484 0.523121(R,m,v=1,0.978417,0.0212699)
  10126. RL update rl*prefer*rvt*predict-yes*H0*1*H1*22 0.272036 0.204841 0.476877 -> 0.272037 0.204841 0.476877(R,m,v=1,1,0)
  10127. =>WM: (13657: S1 ^operator O1944)
  10128. 972: O: O1944 (predict-no)
  10129. --- END Decision Phase ---
  10130. --- Application Phase ---
  10131. --- Firing Productions (PE) For State At Depth 1 ---
  10132. --- Inner Elaboration Phase, active level 1 (S1) ---
  10133. Firing apply*operator
  10134. -->
  10135. (I3 ^predict-no N972 + :O )
  10136. Firing apply*operator*complete
  10137. -->
  10138. (I3 ^predict-yes N971 - :O )
  10139. inner elaboration loop at bottom goal.
  10140. --- Change Working Memory (PE) ---
  10141. =>WM: (13658: I3 ^predict-no N972)
  10142. <=WM: (13645: N971 ^status complete)
  10143. <=WM: (13644: I3 ^predict-yes N971)
  10144. --- Firing Productions (IE) For State At Depth 1 ---
  10145. --- Inner Elaboration Phase, active level 1 (S1) ---
  10146. Firing monitor*world
  10147. -->
  10148. I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
  10149. --- Change Working Memory (IE) ---
  10150. --- END Application Phase ---
  10151. --- Output Phase ---
  10152. ENV: Agent did: predict-no for direction L in state State-A
  10153. In State-A moving L
  10154. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  10155. predict error 0
  10156. dir: dir isU
  10157. --- END Output Phase ---
  10158. -/--- Input Phase ---
  10159. =>WM: (13662: I2 ^dir U)
  10160. =>WM: (13661: I2 ^reward 1)
  10161. =>WM: (13660: I2 ^see 0)
  10162. =>WM: (13659: N972 ^status complete)
  10163. <=WM: (13648: I2 ^dir L)
  10164. <=WM: (13647: I2 ^reward 1)
  10165. <=WM: (13646: I2 ^see 1)
  10166. =>WM: (13663: I2 ^level-1 L0-root)
  10167. <=WM: (13649: I2 ^level-1 L1-root)
  10168. --- END Input Phase ---
  10169. --- Proposal Phase ---
  10170. --- Inner Elaboration Phase, active level 1 (S1) ---
  10171. Firing elaborate*copy-see-to-output-link
  10172. -->
  10173. (I3 ^see 0 +)
  10174. Firing elaborate*reward*based*on*reward
  10175. -->
  10176. (R976 ^value 1 +)
  10177. (R1 ^reward R976 +)
  10178. Firing propose*predict-yes
  10179. -->
  10180. (O1945 ^name predict-yes +)
  10181. (S1 ^operator O1945 +)
  10182. Firing propose*predict-no
  10183. -->
  10184. (O1946 ^name predict-no +)
  10185. (S1 ^operator O1946 +)
  10186. Firing rl*prefer*rvt*predict-no*H0*6
  10187. -->
  10188. (S1 ^operator O1944 = 0.9999999999999999)
  10189. Firing rl*prefer*rvt*predict-yes*H0*5
  10190. -->
  10191. (S1 ^operator O1943 = 0.)
  10192. Firing prefer*rvt*predict-yes*H0
  10193. -->
  10194. Firing prefer*rvt*predict-no*H0
  10195. -->
  10196. Firing elaborate*copy-dir-to-output-link
  10197. -->
  10198. (I3 ^dir U +)
  10199. inner elaboration loop at bottom goal.
  10200. Retracting elaborate*copy-see-to-output-link
  10201. -->
  10202. (I3 ^see 1 +)
  10203. Retracting propose*predict-no
  10204. -->
  10205. (O1944 ^name predict-no +)
  10206. (S1 ^operator O1944 +)
  10207. Retracting propose*predict-yes
  10208. -->
  10209. (O1943 ^name predict-yes +)
  10210. (S1 ^operator O1943 +)
  10211. Retracting elaborate*reward*based*on*reward
  10212. -->
  10213. (R975 ^value 1 +)
  10214. (R1 ^reward R975 +)
  10215. Retracting elaborate*copy-dir-to-output-link
  10216. -->
  10217. (I3 ^dir L +)
  10218. Retracting rl*prefer*rvt*predict-no*H0*2*H1*11
  10219. -->
  10220. (S1 ^operator O1944 = 0.7449863480615504)
  10221. Retracting rl*prefer*rvt*predict-no*H0*2
  10222. -->
  10223. (S1 ^operator O1944 = 0.2550133109307305)
  10224. Retracting rl*prefer*rvt*predict-yes*H0*1*H1*20
  10225. -->
  10226. (S1 ^operator O1943 = 0.1693592933936033)
  10227. Retracting rl*prefer*rvt*predict-yes*H0*1
  10228. -->
  10229. (S1 ^operator O1943 = 0.5231208307682875)
  10230. =>WM: (13671: S1 ^operator O1946 +)
  10231. =>WM: (13670: S1 ^operator O1945 +)
  10232. =>WM: (13669: I3 ^dir U)
  10233. =>WM: (13668: O1946 ^name predict-no)
  10234. =>WM: (13667: O1945 ^name predict-yes)
  10235. =>WM: (13666: R976 ^value 1)
  10236. =>WM: (13665: R1 ^reward R976)
  10237. =>WM: (13664: I3 ^see 0)
  10238. <=WM: (13655: S1 ^operator O1943 +)
  10239. <=WM: (13656: S1 ^operator O1944 +)
  10240. <=WM: (13657: S1 ^operator O1944)
  10241. <=WM: (13640: I3 ^dir L)
  10242. <=WM: (13651: R1 ^reward R975)
  10243. <=WM: (13650: I3 ^see 1)
  10244. <=WM: (13654: O1944 ^name predict-no)
  10245. <=WM: (13653: O1943 ^name predict-yes)
  10246. <=WM: (13652: R975 ^value 1)
  10247. --- Inner Elaboration Phase, active level 1 (S1) ---
  10248. Firing prefer*rvt*predict-yes*H0
  10249. -->
  10250. Firing rl*prefer*rvt*predict-yes*H0*5
  10251. -->
  10252. (S1 ^operator O1945 = 0.)
  10253. Firing prefer*rvt*predict-no*H0
  10254. -->
  10255. Firing rl*prefer*rvt*predict-no*H0*6
  10256. -->
  10257. (S1 ^operator O1946 = 0.9999999999999999)
  10258. inner elaboration loop at bottom goal.
  10259. Retracting rl*prefer*rvt*predict-no*H0*6
  10260. -->
  10261. (S1 ^operator O1944 = 0.9999999999999999)
  10262. Retracting rl*prefer*rvt*predict-yes*H0*5
  10263. -->
  10264. (S1 ^operator O1943 = 0.)
  10265. --- END Proposal Phase ---
  10266. --- Decision Phase ---
  10267. RL update rl*prefer*rvt*predict-no*H0*2 0.631495 -0.376482 0.255013 -> 0.631495 -0.376482 0.255013(R,m,v=1,0.91623,0.0771562)
  10268. RL update rl*prefer*rvt*predict-no*H0*2*H1*11 0.368505 0.376482 0.744986 -> 0.368505 0.376482 0.744986(R,m,v=1,1,0)
  10269. =>WM: (13672: S1 ^operator O1946)
  10270. 973: O: O1946 (predict-no)
  10271. --- END Decision Phase ---
  10272. --- Application Phase ---
  10273. --- Firing Productions (PE) For State At Depth 1 ---
  10274. --- Inner Elaboration Phase, active level 1 (S1) ---
  10275. Firing apply*operator
  10276. -->
  10277. (I3 ^predict-no N973 + :O )
  10278. Firing apply*operator*complete
  10279. -->
  10280. (I3 ^predict-no N972 - :O )
  10281. inner elaboration loop at bottom goal.
  10282. --- Change Working Memory (PE) ---
  10283. =>WM: (13673: I3 ^predict-no N973)
  10284. <=WM: (13659: N972 ^status complete)
  10285. <=WM: (13658: I3 ^predict-no N972)
  10286. --- Firing Productions (IE) For State At Depth 1 ---
  10287. --- Inner Elaboration Phase, active level 1 (S1) ---
  10288. Firing monitor*world
  10289. -->
  10290. I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
  10291. --- Change Working Memory (IE) ---
  10292. --- END Application Phase ---
  10293. --- Output Phase ---
  10294. ENV: Agent did: predict-no for direction U in state State-A
  10295. In State-A moving U
  10296. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  10297. predict error 0
  10298. dir: dir isU
  10299. --- END Output Phase ---
  10300. |\-/--- Input Phase ---
  10301. =>WM: (13677: I2 ^dir U)
  10302. =>WM: (13676: I2 ^reward 1)
  10303. =>WM: (13675: I2 ^see 0)
  10304. =>WM: (13674: N973 ^status complete)
  10305. <=WM: (13662: I2 ^dir U)
  10306. <=WM: (13661: I2 ^reward 1)
  10307. <=WM: (13660: I2 ^see 0)
  10308. =>WM: (13678: I2 ^level-1 L0-root)
  10309. <=WM: (13663: I2 ^level-1 L0-root)
  10310. --- END Input Phase ---
  10311. --- Proposal Phase ---
  10312. --- Inner Elaboration Phase, active level 1 (S1) ---
  10313. Firing elaborate*copy-see-to-output-link
  10314. -->
  10315. (I3 ^see 0 +)
  10316. Firing elaborate*reward*based*on*reward
  10317. -->
  10318. (R977 ^value 1 +)
  10319. (R1 ^reward R977 +)
  10320. Firing propose*predict-yes
  10321. -->
  10322. (O1947 ^name predict-yes +)
  10323. (S1 ^operator O1947 +)
  10324. Firing propose*predict-no
  10325. -->
  10326. (O1948 ^name predict-no +)
  10327. (S1 ^operator O1948 +)
  10328. Firing rl*prefer*rvt*predict-no*H0*6
  10329. -->
  10330. (S1 ^operator O1946 = 0.9999999999999999)
  10331. Firing rl*prefer*rvt*predict-yes*H0*5
  10332. -->
  10333. (S1 ^operator O1945 = 0.)
  10334. Firing prefer*rvt*predict-yes*H0
  10335. -->
  10336. Firing prefer*rvt*predict-no*H0
  10337. -->
  10338. Firing elaborate*copy-dir-to-output-link
  10339. -->
  10340. (I3 ^dir U +)
  10341. inner elaboration loop at bottom goal.
  10342. Retracting elaborate*copy-see-to-output-link
  10343. -->
  10344. (I3 ^see 0 +)
  10345. Retracting propose*predict-no
  10346. -->
  10347. (O1946 ^name predict-no +)
  10348. (S1 ^operator O1946 +)
  10349. Retracting propose*predict-yes
  10350. -->
  10351. (O1945 ^name predict-yes +)
  10352. (S1 ^operator O1945 +)
  10353. Retracting elaborate*reward*based*on*reward
  10354. -->
  10355. (R976 ^value 1 +)
  10356. (R1 ^reward R976 +)
  10357. Retracting elaborate*copy-dir-to-output-link
  10358. -->
  10359. (I3 ^dir U +)
  10360. Retracting rl*prefer*rvt*predict-no*H0*6
  10361. -->
  10362. (S1 ^operator O1946 = 0.9999999999999999)
  10363. Retracting rl*prefer*rvt*predict-yes*H0*5
  10364. -->
  10365. (S1 ^operator O1945 = 0.)
  10366. =>WM: (13684: S1 ^operator O1948 +)
  10367. =>WM: (13683: S1 ^operator O1947 +)
  10368. =>WM: (13682: O1948 ^name predict-no)
  10369. =>WM: (13681: O1947 ^name predict-yes)
  10370. =>WM: (13680: R977 ^value 1)
  10371. =>WM: (13679: R1 ^reward R977)
  10372. <=WM: (13670: S1 ^operator O1945 +)
  10373. <=WM: (13671: S1 ^operator O1946 +)
  10374. <=WM: (13672: S1 ^operator O1946)
  10375. <=WM: (13665: R1 ^reward R976)
  10376. <=WM: (13668: O1946 ^name predict-no)
  10377. <=WM: (13667: O1945 ^name predict-yes)
  10378. <=WM: (13666: R976 ^value 1)
  10379. --- Inner Elaboration Phase, active level 1 (S1) ---
  10380. Firing prefer*rvt*predict-yes*H0
  10381. -->
  10382. Firing rl*prefer*rvt*predict-yes*H0*5
  10383. -->
  10384. (S1 ^operator O1947 = 0.)
  10385. Firing prefer*rvt*predict-no*H0
  10386. -->
  10387. Firing rl*prefer*rvt*predict-no*H0*6
  10388. -->
  10389. (S1 ^operator O1948 = 0.9999999999999999)
  10390. inner elaboration loop at bottom goal.
  10391. Retracting rl*prefer*rvt*predict-no*H0*6
  10392. -->
  10393. (S1 ^operator O1946 = 0.9999999999999999)
  10394. Retracting rl*prefer*rvt*predict-yes*H0*5
  10395. -->
  10396. (S1 ^operator O1945 = 0.)
  10397. --- END Proposal Phase ---
  10398. --- Decision Phase ---
  10399. RL update rl*prefer*rvt*predict-no*H0*6 1 0 1 -> 1 0 1(R,m,v=1,1,0)
  10400. =>WM: (13685: S1 ^operator O1948)
  10401. 974: O: O1948 (predict-no)
  10402. --- END Decision Phase ---
  10403. --- Application Phase ---
  10404. --- Firing Productions (PE) For State At Depth 1 ---
  10405. --- Inner Elaboration Phase, active level 1 (S1) ---
  10406. Firing apply*operator
  10407. -->
  10408. (I3 ^predict-no N974 + :O )
  10409. Firing apply*operator*complete
  10410. -->
  10411. (I3 ^predict-no N973 - :O )
  10412. inner elaboration loop at bottom goal.
  10413. --- Change Working Memory (PE) ---
  10414. =>WM: (13686: I3 ^predict-no N974)
  10415. <=WM: (13674: N973 ^status complete)
  10416. <=WM: (13673: I3 ^predict-no N973)
  10417. --- Firing Productions (IE) For State At Depth 1 ---
  10418. --- Inner Elaboration Phase, active level 1 (S1) ---
  10419. Firing monitor*world
  10420. -->
  10421. I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
  10422. --- Change Working Memory (IE) ---
  10423. --- END Application Phase ---
  10424. --- Output Phase ---
  10425. ENV: Agent did: predict-no for direction U in state State-A
  10426. In State-A moving U
  10427. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  10428. predict error 0
  10429. dir: dir isU
  10430. --- END Output Phase ---
  10431. |\--- Input Phase ---
  10432. =>WM: (13690: I2 ^dir U)
  10433. =>WM: (13689: I2 ^reward 1)
  10434. =>WM: (13688: I2 ^see 0)
  10435. =>WM: (13687: N974 ^status complete)
  10436. <=WM: (13677: I2 ^dir U)
  10437. <=WM: (13676: I2 ^reward 1)
  10438. <=WM: (13675: I2 ^see 0)
  10439. =>WM: (13691: I2 ^level-1 L0-root)
  10440. <=WM: (13678: I2 ^level-1 L0-root)
  10441. --- END Input Phase ---
  10442. --- Proposal Phase ---
  10443. --- Inner Elaboration Phase, active level 1 (S1) ---
  10444. Firing elaborate*copy-see-to-output-link
  10445. -->
  10446. (I3 ^see 0 +)
  10447. Firing elaborate*reward*based*on*reward
  10448. -->
  10449. (R978 ^value 1 +)
  10450. (R1 ^reward R978 +)
  10451. Firing propose*predict-yes
  10452. -->
  10453. (O1949 ^name predict-yes +)
  10454. (S1 ^operator O1949 +)
  10455. Firing propose*predict-no
  10456. -->
  10457. (O1950 ^name predict-no +)
  10458. (S1 ^operator O1950 +)
  10459. Firing rl*prefer*rvt*predict-no*H0*6
  10460. -->
  10461. (S1 ^operator O1948 = 0.9999999999999999)
  10462. Firing rl*prefer*rvt*predict-yes*H0*5
  10463. -->
  10464. (S1 ^operator O1947 = 0.)
  10465. Firing prefer*rvt*predict-yes*H0
  10466. -->
  10467. Firing prefer*rvt*predict-no*H0
  10468. -->
  10469. Firing elaborate*copy-dir-to-output-link
  10470. -->
  10471. (I3 ^dir U +)
  10472. inner elaboration loop at bottom goal.
  10473. Retracting elaborate*copy-see-to-output-link
  10474. -->
  10475. (I3 ^see 0 +)
  10476. Retracting propose*predict-no
  10477. -->
  10478. (O1948 ^name predict-no +)
  10479. (S1 ^operator O1948 +)
  10480. Retracting propose*predict-yes
  10481. -->
  10482. (O1947 ^name predict-yes +)
  10483. (S1 ^operator O1947 +)
  10484. Retracting elaborate*reward*based*on*reward
  10485. -->
  10486. (R977 ^value 1 +)
  10487. (R1 ^reward R977 +)
  10488. Retracting elaborate*copy-dir-to-output-link
  10489. -->
  10490. (I3 ^dir U +)
  10491. Retracting rl*prefer*rvt*predict-no*H0*6
  10492. -->
  10493. (S1 ^operator O1948 = 0.9999999999999999)
  10494. Retracting rl*prefer*rvt*predict-yes*H0*5
  10495. -->
  10496. (S1 ^operator O1947 = 0.)
  10497. =>WM: (13697: S1 ^operator O1950 +)
  10498. =>WM: (13696: S1 ^operator O1949 +)
  10499. =>WM: (13695: O1950 ^name predict-no)
  10500. =>WM: (13694: O1949 ^name predict-yes)
  10501. =>WM: (13693: R978 ^value 1)
  10502. =>WM: (13692: R1 ^reward R978)
  10503. <=WM: (13683: S1 ^operator O1947 +)
  10504. <=WM: (13684: S1 ^operator O1948 +)
  10505. <=WM: (13685: S1 ^operator O1948)
  10506. <=WM: (13679: R1 ^reward R977)
  10507. <=WM: (13682: O1948 ^name predict-no)
  10508. <=WM: (13681: O1947 ^name predict-yes)
  10509. <=WM: (13680: R977 ^value 1)
  10510. --- Inner Elaboration Phase, active level 1 (S1) ---
  10511. Firing prefer*rvt*predict-yes*H0
  10512. -->
  10513. Firing rl*prefer*rvt*predict-yes*H0*5
  10514. -->
  10515. (S1 ^operator O1949 = 0.)
  10516. Firing prefer*rvt*predict-no*H0
  10517. -->
  10518. Firing rl*prefer*rvt*predict-no*H0*6
  10519. -->
  10520. (S1 ^operator O1950 = 0.9999999999999999)
  10521. inner elaboration loop at bottom goal.
  10522. Retracting rl*prefer*rvt*predict-no*H0*6
  10523. -->
  10524. (S1 ^operator O1948 = 0.9999999999999999)
  10525. Retracting rl*prefer*rvt*predict-yes*H0*5
  10526. -->
  10527. (S1 ^operator O1947 = 0.)
  10528. --- END Proposal Phase ---
  10529. --- Decision Phase ---
  10530. RL update rl*prefer*rvt*predict-no*H0*6 1 0 1 -> 1 0 1(R,m,v=1,1,0)
  10531. =>WM: (13698: S1 ^operator O1950)
  10532. 975: O: O1950 (predict-no)
  10533. --- END Decision Phase ---
  10534. --- Application Phase ---
  10535. --- Firing Productions (PE) For State At Depth 1 ---
  10536. --- Inner Elaboration Phase, active level 1 (S1) ---
  10537. Firing apply*operator
  10538. -->
  10539. (I3 ^predict-no N975 + :O )
  10540. Firing apply*operator*complete
  10541. -->
  10542. (I3 ^predict-no N974 - :O )
  10543. inner elaboration loop at bottom goal.
  10544. --- Change Working Memory (PE) ---
  10545. =>WM: (13699: I3 ^predict-no N975)
  10546. <=WM: (13687: N974 ^status complete)
  10547. <=WM: (13686: I3 ^predict-no N974)
  10548. --- Firing Productions (IE) For State At Depth 1 ---
  10549. --- Inner Elaboration Phase, active level 1 (S1) ---
  10550. Firing monitor*world
  10551. -->
  10552. I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
  10553. --- Change Working Memory (IE) ---
  10554. --- END Application Phase ---
  10555. --- Output Phase ---
  10556. ENV: Agent did: predict-no for direction U in state State-A
  10557. In State-A moving U
  10558. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  10559. predict error 0
  10560. dir: dir isL
  10561. --- END Output Phase ---
  10562. -/--- Input Phase ---
  10563. =>WM: (13703: I2 ^dir L)
  10564. =>WM: (13702: I2 ^reward 1)
  10565. =>WM: (13701: I2 ^see 0)
  10566. =>WM: (13700: N975 ^status complete)
  10567. <=WM: (13690: I2 ^dir U)
  10568. <=WM: (13689: I2 ^reward 1)
  10569. <=WM: (13688: I2 ^see 0)
  10570. =>WM: (13704: I2 ^level-1 L0-root)
  10571. <=WM: (13691: I2 ^level-1 L0-root)
  10572. --- END Input Phase ---
  10573. --- Proposal Phase ---
  10574. --- Inner Elaboration Phase, active level 1 (S1) ---
  10575. Firing rl*prefer*rvt*predict-yes*H0*1*H1*21
  10576. -->
  10577. (S1 ^operator O1949 = 0.3)
  10578. Firing rl*prefer*rvt*predict-no*H0*2*H1*12
  10579. -->
  10580. (S1 ^operator O1950 = 0.744986756180395)
  10581. Firing prefer*rvt*predict-no*H0*2*H1
  10582. -->
  10583. Firing prefer*rvt*predict-yes*H0*1*H1
  10584. -->
  10585. Firing elaborate*copy-see-to-output-link
  10586. -->
  10587. (I3 ^see 0 +)
  10588. Firing elaborate*reward*based*on*reward
  10589. -->
  10590. (R979 ^value 1 +)
  10591. (R1 ^reward R979 +)
  10592. Firing propose*predict-yes
  10593. -->
  10594. (O1951 ^name predict-yes +)
  10595. (S1 ^operator O1951 +)
  10596. Firing propose*predict-no
  10597. -->
  10598. (O1952 ^name predict-no +)
  10599. (S1 ^operator O1952 +)
  10600. Firing rl*prefer*rvt*predict-no*H0*2
  10601. -->
  10602. (S1 ^operator O1950 = 0.2550133620818883)
  10603. Firing rl*prefer*rvt*predict-yes*H0*1
  10604. -->
  10605. (S1 ^operator O1949 = 0.5231208307682875)
  10606. Firing prefer*rvt*predict-yes*H0
  10607. -->
  10608. Firing prefer*rvt*predict-no*H0
  10609. -->
  10610. Firing elaborate*copy-dir-to-output-link
  10611. -->
  10612. (I3 ^dir L +)
  10613. inner elaboration loop at bottom goal.
  10614. Retracting elaborate*copy-see-to-output-link
  10615. -->
  10616. (I3 ^see 0 +)
  10617. Retracting propose*predict-no
  10618. -->
  10619. (O1950 ^name predict-no +)
  10620. (S1 ^operator O1950 +)
  10621. Retracting propose*predict-yes
  10622. -->
  10623. (O1949 ^name predict-yes +)
  10624. (S1 ^operator O1949 +)
  10625. Retracting elaborate*reward*based*on*reward
  10626. -->
  10627. (R978 ^value 1 +)
  10628. (R1 ^reward R978 +)
  10629. Retracting elaborate*copy-dir-to-output-link
  10630. -->
  10631. (I3 ^dir U +)
  10632. Retracting rl*prefer*rvt*predict-no*H0*6
  10633. -->
  10634. (S1 ^operator O1950 = 0.9999999999999999)
  10635. Retracting rl*prefer*rvt*predict-yes*H0*5
  10636. -->
  10637. (S1 ^operator O1949 = 0.)
  10638. =>WM: (13711: S1 ^operator O1952 +)
  10639. =>WM: (13710: S1 ^operator O1951 +)
  10640. =>WM: (13709: I3 ^dir L)
  10641. =>WM: (13708: O1952 ^name predict-no)
  10642. =>WM: (13707: O1951 ^name predict-yes)
  10643. =>WM: (13706: R979 ^value 1)
  10644. =>WM: (13705: R1 ^reward R979)
  10645. <=WM: (13696: S1 ^operator O1949 +)
  10646. <=WM: (13697: S1 ^operator O1950 +)
  10647. <=WM: (13698: S1 ^operator O1950)
  10648. <=WM: (13669: I3 ^dir U)
  10649. <=WM: (13692: R1 ^reward R978)
  10650. <=WM: (13695: O1950 ^name predict-no)
  10651. <=WM: (13694: O1949 ^name predict-yes)
  10652. <=WM: (13693: R978 ^value 1)
  10653. --- Inner Elaboration Phase, active level 1 (S1) ---
  10654. Firing prefer*rvt*predict-yes*H0
  10655. -->
  10656. Firing rl*prefer*rvt*predict-yes*H0*1*H1*21
  10657. -->
  10658. (S1 ^operator O1951 = 0.3)
  10659. Firing rl*prefer*rvt*predict-yes*H0*1
  10660. -->
  10661. (S1 ^operator O1951 = 0.5231208307682875)
  10662. Firing prefer*rvt*predict-yes*H0*1*H1
  10663. -->
  10664. Firing prefer*rvt*predict-no*H0
  10665. -->
  10666. Firing rl*prefer*rvt*predict-no*H0*2*H1*12
  10667. -->
  10668. (S1 ^operator O1952 = 0.744986756180395)
  10669. Firing rl*prefer*rvt*predict-no*H0*2
  10670. -->
  10671. (S1 ^operator O1952 = 0.2550133620818883)
  10672. Firing prefer*rvt*predict-no*H0*2*H1
  10673. -->
  10674. inner elaboration loop at bottom goal.
  10675. Retracting rl*prefer*rvt*predict-no*H0*2
  10676. -->
  10677. (S1 ^operator O1950 = 0.2550133620818883)
  10678. Retracting rl*prefer*rvt*predict-no*H0*2*H1*12
  10679. -->
  10680. (S1 ^operator O1950 = 0.744986756180395)
  10681. Retracting rl*prefer*rvt*predict-yes*H0*1
  10682. -->
  10683. (S1 ^operator O1949 = 0.5231208307682875)
  10684. Retracting rl*prefer*rvt*predict-yes*H0*1*H1*21
  10685. -->
  10686. (S1 ^operator O1949 = 0.3)
  10687. --- END Proposal Phase ---
  10688. --- Decision Phase ---
  10689. RL update rl*prefer*rvt*predict-no*H0*6 1 0 1 -> 1 0 1(R,m,v=1,1,0)
  10690. =>WM: (13712: S1 ^operator O1952)
  10691. 976: O: O1952 (predict-no)
  10692. --- END Decision Phase ---
  10693. --- Application Phase ---
  10694. --- Firing Productions (PE) For State At Depth 1 ---
  10695. --- Inner Elaboration Phase, active level 1 (S1) ---
  10696. Firing apply*operator
  10697. -->
  10698. (I3 ^predict-no N976 + :O )
  10699. Firing apply*operator*complete
  10700. -->
  10701. (I3 ^predict-no N975 - :O )
  10702. inner elaboration loop at bottom goal.
  10703. --- Change Working Memory (PE) ---
  10704. =>WM: (13713: I3 ^predict-no N976)
  10705. <=WM: (13700: N975 ^status complete)
  10706. <=WM: (13699: I3 ^predict-no N975)
  10707. --- Firing Productions (IE) For State At Depth 1 ---
  10708. --- Inner Elaboration Phase, active level 1 (S1) ---
  10709. Firing monitor*world
  10710. -->
  10711. I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
  10712. --- Change Working Memory (IE) ---
  10713. --- END Application Phase ---
  10714. --- Output Phase ---
  10715. ENV: Agent did: predict-no for direction L in state State-A
  10716. In State-A moving L
  10717. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  10718. predict error 0
  10719. dir: dir isR
  10720. --- END Output Phase ---
  10721. |\---- Input Phase ---
  10722. =>WM: (13717: I2 ^dir R)
  10723. =>WM: (13716: I2 ^reward 1)
  10724. =>WM: (13715: I2 ^see 0)
  10725. =>WM: (13714: N976 ^status complete)
  10726. <=WM: (13703: I2 ^dir L)
  10727. <=WM: (13702: I2 ^reward 1)
  10728. <=WM: (13701: I2 ^see 0)
  10729. =>WM: (13718: I2 ^level-1 L0-root)
  10730. <=WM: (13704: I2 ^level-1 L0-root)
  10731. --- END Input Phase ---
  10732. --- Proposal Phase ---
  10733. --- Inner Elaboration Phase, active level 1 (S1) ---
  10734. Firing rl*prefer*rvt*predict-yes*H0*3*H1*14
  10735. -->
  10736. (S1 ^operator O1951 = 0.6170789503736752)
  10737. Firing rl*prefer*rvt*predict-no*H0*4*H1*13
  10738. -->
  10739. (S1 ^operator O1952 = 0.4910065094545203)
  10740. Firing prefer*rvt*predict-no*H0*4*H1
  10741. -->
  10742. Firing prefer*rvt*predict-yes*H0*3*H1
  10743. -->
  10744. Firing elaborate*copy-see-to-output-link
  10745. -->
  10746. (I3 ^see 0 +)
  10747. Firing elaborate*reward*based*on*reward
  10748. -->
  10749. (R980 ^value 1 +)
  10750. (R1 ^reward R980 +)
  10751. Firing propose*predict-yes
  10752. -->
  10753. (O1953 ^name predict-yes +)
  10754. (S1 ^operator O1953 +)
  10755. Firing propose*predict-no
  10756. -->
  10757. (O1954 ^name predict-no +)
  10758. (S1 ^operator O1954 +)
  10759. Firing rl*prefer*rvt*predict-no*H0*4
  10760. -->
  10761. (S1 ^operator O1952 = 0.1269767780720474)
  10762. Firing rl*prefer*rvt*predict-yes*H0*3
  10763. -->
  10764. (S1 ^operator O1951 = 0.3829317273911885)
  10765. Firing prefer*rvt*predict-yes*H0
  10766. -->
  10767. Firing prefer*rvt*predict-no*H0
  10768. -->
  10769. Firing elaborate*copy-dir-to-output-link
  10770. -->
  10771. (I3 ^dir R +)
  10772. inner elaboration loop at bottom goal.
  10773. Retracting elaborate*copy-see-to-output-link
  10774. -->
  10775. (I3 ^see 0 +)
  10776. Retracting propose*predict-no
  10777. -->
  10778. (O1952 ^name predict-no +)
  10779. (S1 ^operator O1952 +)
  10780. Retracting propose*predict-yes
  10781. -->
  10782. (O1951 ^name predict-yes +)
  10783. (S1 ^operator O1951 +)
  10784. Retracting elaborate*reward*based*on*reward
  10785. -->
  10786. (R979 ^value 1 +)
  10787. (R1 ^reward R979 +)
  10788. Retracting elaborate*copy-dir-to-output-link
  10789. -->
  10790. (I3 ^dir L +)
  10791. Retracting rl*prefer*rvt*predict-no*H0*2
  10792. -->
  10793. (S1 ^operator O1952 = 0.2550133620818883)
  10794. Retracting rl*prefer*rvt*predict-no*H0*2*H1*12
  10795. -->
  10796. (S1 ^operator O1952 = 0.744986756180395)
  10797. Retracting rl*prefer*rvt*predict-yes*H0*1
  10798. -->
  10799. (S1 ^operator O1951 = 0.5231208307682875)
  10800. Retracting rl*prefer*rvt*predict-yes*H0*1*H1*21
  10801. -->
  10802. (S1 ^operator O1951 = 0.3)
  10803. =>WM: (13725: S1 ^operator O1954 +)
  10804. =>WM: (13724: S1 ^operator O1953 +)
  10805. =>WM: (13723: I3 ^dir R)
  10806. =>WM: (13722: O1954 ^name predict-no)
  10807. =>WM: (13721: O1953 ^name predict-yes)
  10808. =>WM: (13720: R980 ^value 1)
  10809. =>WM: (13719: R1 ^reward R980)
  10810. <=WM: (13710: S1 ^operator O1951 +)
  10811. <=WM: (13711: S1 ^operator O1952 +)
  10812. <=WM: (13712: S1 ^operator O1952)
  10813. <=WM: (13709: I3 ^dir L)
  10814. <=WM: (13705: R1 ^reward R979)
  10815. <=WM: (13708: O1952 ^name predict-no)
  10816. <=WM: (13707: O1951 ^name predict-yes)
  10817. <=WM: (13706: R979 ^value 1)
  10818. --- Inner Elaboration Phase, active level 1 (S1) ---
  10819. Firing prefer*rvt*predict-yes*H0
  10820. -->
  10821. Firing rl*prefer*rvt*predict-yes*H0*3*H1*14
  10822. -->
  10823. (S1 ^operator O1953 = 0.6170789503736752)
  10824. Firing rl*prefer*rvt*predict-yes*H0*3
  10825. -->
  10826. (S1 ^operator O1953 = 0.3829317273911885)
  10827. Firing prefer*rvt*predict-yes*H0*3*H1
  10828. -->
  10829. Firing prefer*rvt*predict-no*H0
  10830. -->
  10831. Firing rl*prefer*rvt*predict-no*H0*4*H1*13
  10832. -->
  10833. (S1 ^operator O1954 = 0.4910065094545203)
  10834. Firing rl*prefer*rvt*predict-no*H0*4
  10835. -->
  10836. (S1 ^operator O1954 = 0.1269767780720474)
  10837. Firing prefer*rvt*predict-no*H0*4*H1
  10838. -->
  10839. inner elaboration loop at bottom goal.
  10840. Retracting rl*prefer*rvt*predict-no*H0*4
  10841. -->
  10842. (S1 ^operator O1952 = 0.1269767780720474)
  10843. Retracting rl*prefer*rvt*predict-no*H0*4*H1*13
  10844. -->
  10845. (S1 ^operator O1952 = 0.4910065094545203)
  10846. Retracting rl*prefer*rvt*predict-yes*H0*3
  10847. -->
  10848. (S1 ^operator O1951 = 0.3829317273911885)
  10849. Retracting rl*prefer*rvt*predict-yes*H0*3*H1*14
  10850. -->
  10851. (S1 ^operator O1951 = 0.6170789503736752)
  10852. --- END Proposal Phase ---
  10853. --- Decision Phase ---
  10854. RL update rl*prefer*rvt*predict-no*H0*2 0.631495 -0.376482 0.255013 -> 0.631495 -0.376482 0.255013(R,m,v=1,0.916667,0.0767888)
  10855. RL update rl*prefer*rvt*predict-no*H0*2*H1*12 0.368505 0.376482 0.744987 -> 0.368505 0.376482 0.744987(R,m,v=1,1,0)
  10856. =>WM: (13726: S1 ^operator O1953)
  10857. 977: O: O1953 (predict-yes)
  10858. --- END Decision Phase ---
  10859. --- Application Phase ---
  10860. --- Firing Productions (PE) For State At Depth 1 ---
  10861. --- Inner Elaboration Phase, active level 1 (S1) ---
  10862. Firing apply*operator
  10863. -->
  10864. (I3 ^predict-yes N977 + :O )
  10865. Firing apply*operator*complete
  10866. -->
  10867. (I3 ^predict-no N976 - :O )
  10868. inner elaboration loop at bottom goal.
  10869. --- Change Working Memory (PE) ---
  10870. =>WM: (13727: I3 ^predict-yes N977)
  10871. <=WM: (13714: N976 ^status complete)
  10872. <=WM: (13713: I3 ^predict-no N976)
  10873. --- Firing Productions (IE) For State At Depth 1 ---
  10874. --- Inner Elaboration Phase, active level 1 (S1) ---
  10875. Firing monitor*world
  10876. -->
  10877. I see 1 and I'm going to do: predict-yes inner elaboration loop at bottom goal.
  10878. --- Change Working Memory (IE) ---
  10879. --- END Application Phase ---
  10880. --- Output Phase ---
  10881. ENV: Agent did: predict-yes for direction R in state State-A
  10882. In State-A moving R
  10883. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  10884. predict error 0
  10885. dir: dir isU
  10886. --- END Output Phase ---
  10887. /|\--- Input Phase ---
  10888. =>WM: (13731: I2 ^dir U)
  10889. =>WM: (13730: I2 ^reward 1)
  10890. =>WM: (13729: I2 ^see 1)
  10891. =>WM: (13728: N977 ^status complete)
  10892. <=WM: (13717: I2 ^dir R)
  10893. <=WM: (13716: I2 ^reward 1)
  10894. <=WM: (13715: I2 ^see 0)
  10895. =>WM: (13732: I2 ^level-1 R1-root)
  10896. <=WM: (13718: I2 ^level-1 L0-root)
  10897. --- END Input Phase ---
  10898. --- Proposal Phase ---
  10899. --- Inner Elaboration Phase, active level 1 (S1) ---
  10900. Firing elaborate*copy-see-to-output-link
  10901. -->
  10902. (I3 ^see 1 +)
  10903. Firing elaborate*reward*based*on*reward
  10904. -->
  10905. (R981 ^value 1 +)
  10906. (R1 ^reward R981 +)
  10907. Firing propose*predict-yes
  10908. -->
  10909. (O1955 ^name predict-yes +)
  10910. (S1 ^operator O1955 +)
  10911. Firing propose*predict-no
  10912. -->
  10913. (O1956 ^name predict-no +)
  10914. (S1 ^operator O1956 +)
  10915. Firing rl*prefer*rvt*predict-no*H0*6
  10916. -->
  10917. (S1 ^operator O1954 = 0.9999999999999999)
  10918. Firing rl*prefer*rvt*predict-yes*H0*5
  10919. -->
  10920. (S1 ^operator O1953 = 0.)
  10921. Firing prefer*rvt*predict-yes*H0
  10922. -->
  10923. Firing prefer*rvt*predict-no*H0
  10924. -->
  10925. Firing elaborate*copy-dir-to-output-link
  10926. -->
  10927. (I3 ^dir U +)
  10928. inner elaboration loop at bottom goal.
  10929. Retracting elaborate*copy-see-to-output-link
  10930. -->
  10931. (I3 ^see 0 +)
  10932. Retracting propose*predict-no
  10933. -->
  10934. (O1954 ^name predict-no +)
  10935. (S1 ^operator O1954 +)
  10936. Retracting propose*predict-yes
  10937. -->
  10938. (O1953 ^name predict-yes +)
  10939. (S1 ^operator O1953 +)
  10940. Retracting elaborate*reward*based*on*reward
  10941. -->
  10942. (R980 ^value 1 +)
  10943. (R1 ^reward R980 +)
  10944. Retracting elaborate*copy-dir-to-output-link
  10945. -->
  10946. (I3 ^dir R +)
  10947. Retracting rl*prefer*rvt*predict-no*H0*4
  10948. -->
  10949. (S1 ^operator O1954 = 0.1269767780720474)
  10950. Retracting rl*prefer*rvt*predict-no*H0*4*H1*13
  10951. -->
  10952. (S1 ^operator O1954 = 0.4910065094545203)
  10953. Retracting rl*prefer*rvt*predict-yes*H0*3
  10954. -->
  10955. (S1 ^operator O1953 = 0.3829317273911885)
  10956. Retracting rl*prefer*rvt*predict-yes*H0*3*H1*14
  10957. -->
  10958. (S1 ^operator O1953 = 0.6170789503736752)
  10959. =>WM: (13740: S1 ^operator O1956 +)
  10960. =>WM: (13739: S1 ^operator O1955 +)
  10961. =>WM: (13738: I3 ^dir U)
  10962. =>WM: (13737: O1956 ^name predict-no)
  10963. =>WM: (13736: O1955 ^name predict-yes)
  10964. =>WM: (13735: R981 ^value 1)
  10965. =>WM: (13734: R1 ^reward R981)
  10966. =>WM: (13733: I3 ^see 1)
  10967. <=WM: (13724: S1 ^operator O1953 +)
  10968. <=WM: (13726: S1 ^operator O1953)
  10969. <=WM: (13725: S1 ^operator O1954 +)
  10970. <=WM: (13723: I3 ^dir R)
  10971. <=WM: (13719: R1 ^reward R980)
  10972. <=WM: (13664: I3 ^see 0)
  10973. <=WM: (13722: O1954 ^name predict-no)
  10974. <=WM: (13721: O1953 ^name predict-yes)
  10975. <=WM: (13720: R980 ^value 1)
  10976. --- Inner Elaboration Phase, active level 1 (S1) ---
  10977. Firing prefer*rvt*predict-yes*H0
  10978. -->
  10979. Firing rl*prefer*rvt*predict-yes*H0*5
  10980. -->
  10981. (S1 ^operator O1955 = 0.)
  10982. Firing prefer*rvt*predict-no*H0
  10983. -->
  10984. Firing rl*prefer*rvt*predict-no*H0*6
  10985. -->
  10986. (S1 ^operator O1956 = 0.9999999999999999)
  10987. inner elaboration loop at bottom goal.
  10988. Retracting rl*prefer*rvt*predict-no*H0*6
  10989. -->
  10990. (S1 ^operator O1954 = 0.9999999999999999)
  10991. Retracting rl*prefer*rvt*predict-yes*H0*5
  10992. -->
  10993. (S1 ^operator O1953 = 0.)
  10994. --- END Proposal Phase ---
  10995. --- Decision Phase ---
  10996. RL update rl*prefer*rvt*predict-yes*H0*3 0.673126 -0.290194 0.382932 -> 0.673124 -0.290194 0.38293(R,m,v=1,0.96,0.0386577)
  10997. RL update rl*prefer*rvt*predict-yes*H0*3*H1*14 0.326884 0.290195 0.617079 -> 0.326883 0.290195 0.617077(R,m,v=1,1,0)
  10998. =>WM: (13741: S1 ^operator O1956)
  10999. 978: O: O1956 (predict-no)
  11000. --- END Decision Phase ---
  11001. --- Application Phase ---
  11002. --- Firing Productions (PE) For State At Depth 1 ---
  11003. --- Inner Elaboration Phase, active level 1 (S1) ---
  11004. Firing apply*operator
  11005. -->
  11006. (I3 ^predict-no N978 + :O )
  11007. Firing apply*operator*complete
  11008. -->
  11009. (I3 ^predict-yes N977 - :O )
  11010. inner elaboration loop at bottom goal.
  11011. --- Change Working Memory (PE) ---
  11012. =>WM: (13742: I3 ^predict-no N978)
  11013. <=WM: (13728: N977 ^status complete)
  11014. <=WM: (13727: I3 ^predict-yes N977)
  11015. --- Firing Productions (IE) For State At Depth 1 ---
  11016. --- Inner Elaboration Phase, active level 1 (S1) ---
  11017. Firing monitor*world
  11018. -->
  11019. I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
  11020. --- Change Working Memory (IE) ---
  11021. --- END Application Phase ---
  11022. --- Output Phase ---
  11023. ENV: Agent did: predict-no for direction U in state State-B
  11024. In State-B moving U
  11025. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  11026. predict error 0
  11027. dir: dir isR
  11028. --- END Output Phase ---
  11029. -/|--- Input Phase ---
  11030. =>WM: (13746: I2 ^dir R)
  11031. =>WM: (13745: I2 ^reward 1)
  11032. =>WM: (13744: I2 ^see 0)
  11033. =>WM: (13743: N978 ^status complete)
  11034. <=WM: (13731: I2 ^dir U)
  11035. <=WM: (13730: I2 ^reward 1)
  11036. <=WM: (13729: I2 ^see 1)
  11037. =>WM: (13747: I2 ^level-1 R1-root)
  11038. <=WM: (13732: I2 ^level-1 R1-root)
  11039. --- END Input Phase ---
  11040. --- Proposal Phase ---
  11041. --- Inner Elaboration Phase, active level 1 (S1) ---
  11042. Firing rl*prefer*rvt*predict-yes*H0*3*H1*16
  11043. -->
  11044. (S1 ^operator O1955 = 0.08783148430849691)
  11045. Firing rl*prefer*rvt*predict-no*H0*4*H1*15
  11046. -->
  11047. (S1 ^operator O1956 = 0.8730234453553117)
  11048. Firing prefer*rvt*predict-no*H0*4*H1
  11049. -->
  11050. Firing prefer*rvt*predict-yes*H0*3*H1
  11051. -->
  11052. Firing elaborate*copy-see-to-output-link
  11053. -->
  11054. (I3 ^see 0 +)
  11055. Firing elaborate*reward*based*on*reward
  11056. -->
  11057. (R982 ^value 1 +)
  11058. (R1 ^reward R982 +)
  11059. Firing propose*predict-yes
  11060. -->
  11061. (O1957 ^name predict-yes +)
  11062. (S1 ^operator O1957 +)
  11063. Firing propose*predict-no
  11064. -->
  11065. (O1958 ^name predict-no +)
  11066. (S1 ^operator O1958 +)
  11067. Firing rl*prefer*rvt*predict-no*H0*4
  11068. -->
  11069. (S1 ^operator O1956 = 0.1269767780720474)
  11070. Firing rl*prefer*rvt*predict-yes*H0*3
  11071. -->
  11072. (S1 ^operator O1955 = 0.3829301257264589)
  11073. Firing prefer*rvt*predict-yes*H0
  11074. -->
  11075. Firing prefer*rvt*predict-no*H0
  11076. -->
  11077. Firing elaborate*copy-dir-to-output-link
  11078. -->
  11079. (I3 ^dir R +)
  11080. inner elaboration loop at bottom goal.
  11081. Retracting elaborate*copy-see-to-output-link
  11082. -->
  11083. (I3 ^see 1 +)
  11084. Retracting propose*predict-no
  11085. -->
  11086. (O1956 ^name predict-no +)
  11087. (S1 ^operator O1956 +)
  11088. Retracting propose*predict-yes
  11089. -->
  11090. (O1955 ^name predict-yes +)
  11091. (S1 ^operator O1955 +)
  11092. Retracting elaborate*reward*based*on*reward
  11093. -->
  11094. (R981 ^value 1 +)
  11095. (R1 ^reward R981 +)
  11096. Retracting elaborate*copy-dir-to-output-link
  11097. -->
  11098. (I3 ^dir U +)
  11099. Retracting rl*prefer*rvt*predict-no*H0*6
  11100. -->
  11101. (S1 ^operator O1956 = 0.9999999999999999)
  11102. Retracting rl*prefer*rvt*predict-yes*H0*5
  11103. -->
  11104. (S1 ^operator O1955 = 0.)
  11105. =>WM: (13755: S1 ^operator O1958 +)
  11106. =>WM: (13754: S1 ^operator O1957 +)
  11107. =>WM: (13753: I3 ^dir R)
  11108. =>WM: (13752: O1958 ^name predict-no)
  11109. =>WM: (13751: O1957 ^name predict-yes)
  11110. =>WM: (13750: R982 ^value 1)
  11111. =>WM: (13749: R1 ^reward R982)
  11112. =>WM: (13748: I3 ^see 0)
  11113. <=WM: (13739: S1 ^operator O1955 +)
  11114. <=WM: (13740: S1 ^operator O1956 +)
  11115. <=WM: (13741: S1 ^operator O1956)
  11116. <=WM: (13738: I3 ^dir U)
  11117. <=WM: (13734: R1 ^reward R981)
  11118. <=WM: (13733: I3 ^see 1)
  11119. <=WM: (13737: O1956 ^name predict-no)
  11120. <=WM: (13736: O1955 ^name predict-yes)
  11121. <=WM: (13735: R981 ^value 1)
  11122. --- Inner Elaboration Phase, active level 1 (S1) ---
  11123. Firing prefer*rvt*predict-yes*H0
  11124. -->
  11125. Firing rl*prefer*rvt*predict-yes*H0*3*H1*16
  11126. -->
  11127. (S1 ^operator O1957 = 0.08783148430849691)
  11128. Firing rl*prefer*rvt*predict-yes*H0*3
  11129. -->
  11130. (S1 ^operator O1957 = 0.3829301257264589)
  11131. Firing prefer*rvt*predict-yes*H0*3*H1
  11132. -->
  11133. Firing prefer*rvt*predict-no*H0
  11134. -->
  11135. Firing rl*prefer*rvt*predict-no*H0*4*H1*15
  11136. -->
  11137. (S1 ^operator O1958 = 0.8730234453553117)
  11138. Firing rl*prefer*rvt*predict-no*H0*4
  11139. -->
  11140. (S1 ^operator O1958 = 0.1269767780720474)
  11141. Firing prefer*rvt*predict-no*H0*4*H1
  11142. -->
  11143. inner elaboration loop at bottom goal.
  11144. Retracting rl*prefer*rvt*predict-no*H0*4
  11145. -->
  11146. (S1 ^operator O1956 = 0.1269767780720474)
  11147. Retracting rl*prefer*rvt*predict-no*H0*4*H1*15
  11148. -->
  11149. (S1 ^operator O1956 = 0.8730234453553117)
  11150. Retracting rl*prefer*rvt*predict-yes*H0*3
  11151. -->
  11152. (S1 ^operator O1955 = 0.3829301257264589)
  11153. Retracting rl*prefer*rvt*predict-yes*H0*3*H1*16
  11154. -->
  11155. (S1 ^operator O1955 = 0.08783148430849691)
  11156. --- END Proposal Phase ---
  11157. --- Decision Phase ---
  11158. RL update rl*prefer*rvt*predict-no*H0*6 1 0 1 -> 1 0 1(R,m,v=1,1,0)
  11159. =>WM: (13756: S1 ^operator O1958)
  11160. 979: O: O1958 (predict-no)
  11161. --- END Decision Phase ---
  11162. --- Application Phase ---
  11163. --- Firing Productions (PE) For State At Depth 1 ---
  11164. --- Inner Elaboration Phase, active level 1 (S1) ---
  11165. Firing apply*operator
  11166. -->
  11167. (I3 ^predict-no N979 + :O )
  11168. Firing apply*operator*complete
  11169. -->
  11170. (I3 ^predict-no N978 - :O )
  11171. inner elaboration loop at bottom goal.
  11172. --- Change Working Memory (PE) ---
  11173. =>WM: (13757: I3 ^predict-no N979)
  11174. <=WM: (13743: N978 ^status complete)
  11175. <=WM: (13742: I3 ^predict-no N978)
  11176. --- Firing Productions (IE) For State At Depth 1 ---
  11177. --- Inner Elaboration Phase, active level 1 (S1) ---
  11178. Firing monitor*world
  11179. -->
  11180. I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
  11181. --- Change Working Memory (IE) ---
  11182. --- END Application Phase ---
  11183. --- Output Phase ---
  11184. ENV: Agent did: predict-no for direction R in state State-B
  11185. In State-B moving R
  11186. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  11187. predict error 0
  11188. dir: dir isU
  11189. --- END Output Phase ---
  11190. \-/--- Input Phase ---
  11191. =>WM: (13761: I2 ^dir U)
  11192. =>WM: (13760: I2 ^reward 1)
  11193. =>WM: (13759: I2 ^see 0)
  11194. =>WM: (13758: N979 ^status complete)
  11195. <=WM: (13746: I2 ^dir R)
  11196. <=WM: (13745: I2 ^reward 1)
  11197. <=WM: (13744: I2 ^see 0)
  11198. =>WM: (13762: I2 ^level-1 R0-root)
  11199. <=WM: (13747: I2 ^level-1 R1-root)
  11200. --- END Input Phase ---
  11201. --- Proposal Phase ---
  11202. --- Inner Elaboration Phase, active level 1 (S1) ---
  11203. Firing elaborate*copy-see-to-output-link
  11204. -->
  11205. (I3 ^see 0 +)
  11206. Firing elaborate*reward*based*on*reward
  11207. -->
  11208. (R983 ^value 1 +)
  11209. (R1 ^reward R983 +)
  11210. Firing propose*predict-yes
  11211. -->
  11212. (O1959 ^name predict-yes +)
  11213. (S1 ^operator O1959 +)
  11214. Firing propose*predict-no
  11215. -->
  11216. (O1960 ^name predict-no +)
  11217. (S1 ^operator O1960 +)
  11218. Firing rl*prefer*rvt*predict-no*H0*6
  11219. -->
  11220. (S1 ^operator O1958 = 0.9999999999999999)
  11221. Firing rl*prefer*rvt*predict-yes*H0*5
  11222. -->
  11223. (S1 ^operator O1957 = 0.)
  11224. Firing prefer*rvt*predict-yes*H0
  11225. -->
  11226. Firing prefer*rvt*predict-no*H0
  11227. -->
  11228. Firing elaborate*copy-dir-to-output-link
  11229. -->
  11230. (I3 ^dir U +)
  11231. inner elaboration loop at bottom goal.
  11232. Retracting elaborate*copy-see-to-output-link
  11233. -->
  11234. (I3 ^see 0 +)
  11235. Retracting propose*predict-no
  11236. -->
  11237. (O1958 ^name predict-no +)
  11238. (S1 ^operator O1958 +)
  11239. Retracting propose*predict-yes
  11240. -->
  11241. (O1957 ^name predict-yes +)
  11242. (S1 ^operator O1957 +)
  11243. Retracting elaborate*reward*based*on*reward
  11244. -->
  11245. (R982 ^value 1 +)
  11246. (R1 ^reward R982 +)
  11247. Retracting elaborate*copy-dir-to-output-link
  11248. -->
  11249. (I3 ^dir R +)
  11250. Retracting rl*prefer*rvt*predict-no*H0*4
  11251. -->
  11252. (S1 ^operator O1958 = 0.1269767780720474)
  11253. Retracting rl*prefer*rvt*predict-no*H0*4*H1*15
  11254. -->
  11255. (S1 ^operator O1958 = 0.8730234453553117)
  11256. Retracting rl*prefer*rvt*predict-yes*H0*3
  11257. -->
  11258. (S1 ^operator O1957 = 0.3829301257264589)
  11259. Retracting rl*prefer*rvt*predict-yes*H0*3*H1*16
  11260. -->
  11261. (S1 ^operator O1957 = 0.08783148430849691)
  11262. =>WM: (13769: S1 ^operator O1960 +)
  11263. =>WM: (13768: S1 ^operator O1959 +)
  11264. =>WM: (13767: I3 ^dir U)
  11265. =>WM: (13766: O1960 ^name predict-no)
  11266. =>WM: (13765: O1959 ^name predict-yes)
  11267. =>WM: (13764: R983 ^value 1)
  11268. =>WM: (13763: R1 ^reward R983)
  11269. <=WM: (13754: S1 ^operator O1957 +)
  11270. <=WM: (13755: S1 ^operator O1958 +)
  11271. <=WM: (13756: S1 ^operator O1958)
  11272. <=WM: (13753: I3 ^dir R)
  11273. <=WM: (13749: R1 ^reward R982)
  11274. <=WM: (13752: O1958 ^name predict-no)
  11275. <=WM: (13751: O1957 ^name predict-yes)
  11276. <=WM: (13750: R982 ^value 1)
  11277. --- Inner Elaboration Phase, active level 1 (S1) ---
  11278. Firing prefer*rvt*predict-yes*H0
  11279. -->
  11280. Firing rl*prefer*rvt*predict-yes*H0*5
  11281. -->
  11282. (S1 ^operator O1959 = 0.)
  11283. Firing prefer*rvt*predict-no*H0
  11284. -->
  11285. Firing rl*prefer*rvt*predict-no*H0*6
  11286. -->
  11287. (S1 ^operator O1960 = 0.9999999999999999)
  11288. inner elaboration loop at bottom goal.
  11289. Retracting rl*prefer*rvt*predict-no*H0*6
  11290. -->
  11291. (S1 ^operator O1958 = 0.9999999999999999)
  11292. Retracting rl*prefer*rvt*predict-yes*H0*5
  11293. -->
  11294. (S1 ^operator O1957 = 0.)
  11295. --- END Proposal Phase ---
  11296. --- Decision Phase ---
  11297. RL update rl*prefer*rvt*predict-no*H0*4 0.814714 -0.687737 0.126977 -> 0.814714 -0.687737 0.126977(R,m,v=1,0.947977,0.0496034)
  11298. RL update rl*prefer*rvt*predict-no*H0*4*H1*15 0.185286 0.687737 0.873023 -> 0.185286 0.687737 0.873023(R,m,v=1,1,0)
  11299. =>WM: (13770: S1 ^operator O1960)
  11300. 980: O: O1960 (predict-no)
  11301. --- END Decision Phase ---
  11302. --- Application Phase ---
  11303. --- Firing Productions (PE) For State At Depth 1 ---
  11304. --- Inner Elaboration Phase, active level 1 (S1) ---
  11305. Firing apply*operator
  11306. -->
  11307. (I3 ^predict-no N980 + :O )
  11308. Firing apply*operator*complete
  11309. -->
  11310. (I3 ^predict-no N979 - :O )
  11311. inner elaboration loop at bottom goal.
  11312. --- Change Working Memory (PE) ---
  11313. =>WM: (13771: I3 ^predict-no N980)
  11314. <=WM: (13758: N979 ^status complete)
  11315. <=WM: (13757: I3 ^predict-no N979)
  11316. --- Firing Productions (IE) For State At Depth 1 ---
  11317. --- Inner Elaboration Phase, active level 1 (S1) ---
  11318. Firing monitor*world
  11319. -->
  11320. I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
  11321. --- Change Working Memory (IE) ---
  11322. --- END Application Phase ---
  11323. --- Output Phase ---
  11324. ENV: Agent did: predict-no for direction U in state State-B
  11325. In State-B moving U
  11326. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  11327. predict error 0
  11328. dir: dir isL
  11329. --- END Output Phase ---
  11330. |\--- Input Phase ---
  11331. =>WM: (13775: I2 ^dir L)
  11332. =>WM: (13774: I2 ^reward 1)
  11333. =>WM: (13773: I2 ^see 0)
  11334. =>WM: (13772: N980 ^status complete)
  11335. <=WM: (13761: I2 ^dir U)
  11336. <=WM: (13760: I2 ^reward 1)
  11337. <=WM: (13759: I2 ^see 0)
  11338. =>WM: (13776: I2 ^level-1 R0-root)
  11339. <=WM: (13762: I2 ^level-1 R0-root)
  11340. --- END Input Phase ---
  11341. --- Proposal Phase ---
  11342. --- Inner Elaboration Phase, active level 1 (S1) ---
  11343. Firing rl*prefer*rvt*predict-yes*H0*1*H1*19
  11344. -->
  11345. (S1 ^operator O1959 = 0.4768840530102607)
  11346. Firing rl*prefer*rvt*predict-no*H0*2*H1*7
  11347. -->
  11348. (S1 ^operator O1960 = 0.1700769046561409)
  11349. Firing prefer*rvt*predict-no*H0*2*H1
  11350. -->
  11351. Firing prefer*rvt*predict-yes*H0*1*H1
  11352. -->
  11353. Firing elaborate*copy-see-to-output-link
  11354. -->
  11355. (I3 ^see 0 +)
  11356. Firing elaborate*reward*based*on*reward
  11357. -->
  11358. (R984 ^value 1 +)
  11359. (R1 ^reward R984 +)
  11360. Firing propose*predict-yes
  11361. -->
  11362. (O1961 ^name predict-yes +)
  11363. (S1 ^operator O1961 +)
  11364. Firing propose*predict-no
  11365. -->
  11366. (O1962 ^name predict-no +)
  11367. (S1 ^operator O1962 +)
  11368. Firing rl*prefer*rvt*predict-no*H0*2
  11369. -->
  11370. (S1 ^operator O1960 = 0.2550133443425458)
  11371. Firing rl*prefer*rvt*predict-yes*H0*1
  11372. -->
  11373. (S1 ^operator O1959 = 0.5231208307682875)
  11374. Firing prefer*rvt*predict-yes*H0
  11375. -->
  11376. Firing prefer*rvt*predict-no*H0
  11377. -->
  11378. Firing elaborate*copy-dir-to-output-link
  11379. -->
  11380. (I3 ^dir L +)
  11381. inner elaboration loop at bottom goal.
  11382. Retracting elaborate*copy-see-to-output-link
  11383. -->
  11384. (I3 ^see 0 +)
  11385. Retracting propose*predict-no
  11386. -->
  11387. (O1960 ^name predict-no +)
  11388. (S1 ^operator O1960 +)
  11389. Retracting propose*predict-yes
  11390. -->
  11391. (O1959 ^name predict-yes +)
  11392. (S1 ^operator O1959 +)
  11393. Retracting elaborate*reward*based*on*reward
  11394. -->
  11395. (R983 ^value 1 +)
  11396. (R1 ^reward R983 +)
  11397. Retracting elaborate*copy-dir-to-output-link
  11398. -->
  11399. (I3 ^dir U +)
  11400. Retracting rl*prefer*rvt*predict-no*H0*6
  11401. -->
  11402. (S1 ^operator O1960 = 0.9999999999999999)
  11403. Retracting rl*prefer*rvt*predict-yes*H0*5
  11404. -->
  11405. (S1 ^operator O1959 = 0.)
  11406. =>WM: (13783: S1 ^operator O1962 +)
  11407. =>WM: (13782: S1 ^operator O1961 +)
  11408. =>WM: (13781: I3 ^dir L)
  11409. =>WM: (13780: O1962 ^name predict-no)
  11410. =>WM: (13779: O1961 ^name predict-yes)
  11411. =>WM: (13778: R984 ^value 1)
  11412. =>WM: (13777: R1 ^reward R984)
  11413. <=WM: (13768: S1 ^operator O1959 +)
  11414. <=WM: (13769: S1 ^operator O1960 +)
  11415. <=WM: (13770: S1 ^operator O1960)
  11416. <=WM: (13767: I3 ^dir U)
  11417. <=WM: (13763: R1 ^reward R983)
  11418. <=WM: (13766: O1960 ^name predict-no)
  11419. <=WM: (13765: O1959 ^name predict-yes)
  11420. <=WM: (13764: R983 ^value 1)
  11421. --- Inner Elaboration Phase, active level 1 (S1) ---
  11422. Firing prefer*rvt*predict-yes*H0
  11423. -->
  11424. Firing rl*prefer*rvt*predict-yes*H0*1*H1*19
  11425. -->
  11426. (S1 ^operator O1961 = 0.4768840530102607)
  11427. Firing rl*prefer*rvt*predict-yes*H0*1
  11428. -->
  11429. (S1 ^operator O1961 = 0.5231208307682875)
  11430. Firing prefer*rvt*predict-yes*H0*1*H1
  11431. -->
  11432. Firing prefer*rvt*predict-no*H0
  11433. -->
  11434. Firing rl*prefer*rvt*predict-no*H0*2*H1*7
  11435. -->
  11436. (S1 ^operator O1962 = 0.1700769046561409)
  11437. Firing rl*prefer*rvt*predict-no*H0*2
  11438. -->
  11439. (S1 ^operator O1962 = 0.2550133443425458)
  11440. Firing prefer*rvt*predict-no*H0*2*H1
  11441. -->
  11442. inner elaboration loop at bottom goal.
  11443. Retracting rl*prefer*rvt*predict-no*H0*2
  11444. -->
  11445. (S1 ^operator O1960 = 0.2550133443425458)
  11446. Retracting rl*prefer*rvt*predict-no*H0*2*H1*7
  11447. -->
  11448. (S1 ^operator O1960 = 0.1700769046561409)
  11449. Retracting rl*prefer*rvt*predict-yes*H0*1
  11450. -->
  11451. (S1 ^operator O1959 = 0.5231208307682875)
  11452. Retracting rl*prefer*rvt*predict-yes*H0*1*H1*19
  11453. -->
  11454. (S1 ^operator O1959 = 0.4768840530102607)
  11455. --- END Proposal Phase ---
  11456. --- Decision Phase ---
  11457. RL update rl*prefer*rvt*predict-no*H0*6 1 0 1 -> 1 0 1(R,m,v=1,1,0)
  11458. =>WM: (13784: S1 ^operator O1961)
  11459. 981: O: O1961 (predict-yes)
  11460. --- END Decision Phase ---
  11461. --- Application Phase ---
  11462. --- Firing Productions (PE) For State At Depth 1 ---
  11463. --- Inner Elaboration Phase, active level 1 (S1) ---
  11464. Firing apply*operator
  11465. -->
  11466. (I3 ^predict-yes N981 + :O )
  11467. Firing apply*operator*complete
  11468. -->
  11469. (I3 ^predict-no N980 - :O )
  11470. inner elaboration loop at bottom goal.
  11471. --- Change Working Memory (PE) ---
  11472. =>WM: (13785: I3 ^predict-yes N981)
  11473. <=WM: (13772: N980 ^status complete)
  11474. <=WM: (13771: I3 ^predict-no N980)
  11475. --- Firing Productions (IE) For State At Depth 1 ---
  11476. --- Inner Elaboration Phase, active level 1 (S1) ---
  11477. Firing monitor*world
  11478. -->
  11479. I see 1 and I'm going to do: predict-yes inner elaboration loop at bottom goal.
  11480. --- Change Working Memory (IE) ---
  11481. --- END Application Phase ---
  11482. --- Output Phase ---
  11483. ENV: Agent did: predict-yes for direction L in state State-B
  11484. In State-B moving L
  11485. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  11486. predict error 0
  11487. dir: dir isL
  11488. --- END Output Phase ---
  11489. ---- Input Phase ---
  11490. =>WM: (13789: I2 ^dir L)
  11491. =>WM: (13788: I2 ^reward 1)
  11492. =>WM: (13787: I2 ^see 1)
  11493. =>WM: (13786: N981 ^status complete)
  11494. <=WM: (13775: I2 ^dir L)
  11495. <=WM: (13774: I2 ^reward 1)
  11496. <=WM: (13773: I2 ^see 0)
  11497. =>WM: (13790: I2 ^level-1 L1-root)
  11498. <=WM: (13776: I2 ^level-1 R0-root)
  11499. --- END Input Phase ---
  11500. --- Proposal Phase ---
  11501. --- Inner Elaboration Phase, active level 1 (S1) ---
  11502. Firing rl*prefer*rvt*predict-yes*H0*1*H1*20
  11503. -->
  11504. (S1 ^operator O1961 = 0.1693592933936033)
  11505. Firing rl*prefer*rvt*predict-no*H0*2*H1*11
  11506. -->
  11507. (S1 ^operator O1962 = 0.7449863992127084)
  11508. Firing prefer*rvt*predict-no*H0*2*H1
  11509. -->
  11510. Firing prefer*rvt*predict-yes*H0*1*H1
  11511. -->
  11512. Firing elaborate*copy-see-to-output-link
  11513. -->
  11514. (I3 ^see 1 +)
  11515. Firing elaborate*reward*based*on*reward
  11516. -->
  11517. (R985 ^value 1 +)
  11518. (R1 ^reward R985 +)
  11519. Firing propose*predict-yes
  11520. -->
  11521. (O1963 ^name predict-yes +)
  11522. (S1 ^operator O1963 +)
  11523. Firing propose*predict-no
  11524. -->
  11525. (O1964 ^name predict-no +)
  11526. (S1 ^operator O1964 +)
  11527. Firing rl*prefer*rvt*predict-no*H0*2
  11528. -->
  11529. (S1 ^operator O1962 = 0.2550133443425458)
  11530. Firing rl*prefer*rvt*predict-yes*H0*1
  11531. -->
  11532. (S1 ^operator O1961 = 0.5231208307682875)
  11533. Firing prefer*rvt*predict-yes*H0
  11534. -->
  11535. Firing prefer*rvt*predict-no*H0
  11536. -->
  11537. Firing elaborate*copy-dir-to-output-link
  11538. -->
  11539. (I3 ^dir L +)
  11540. inner elaboration loop at bottom goal.
  11541. Retracting elaborate*copy-see-to-output-link
  11542. -->
  11543. (I3 ^see 0 +)
  11544. Retracting propose*predict-no
  11545. -->
  11546. (O1962 ^name predict-no +)
  11547. (S1 ^operator O1962 +)
  11548. Retracting propose*predict-yes
  11549. -->
  11550. (O1961 ^name predict-yes +)
  11551. (S1 ^operator O1961 +)
  11552. Retracting elaborate*reward*based*on*reward
  11553. -->
  11554. (R984 ^value 1 +)
  11555. (R1 ^reward R984 +)
  11556. Retracting elaborate*copy-dir-to-output-link
  11557. -->
  11558. (I3 ^dir L +)
  11559. Retracting rl*prefer*rvt*predict-no*H0*2
  11560. -->
  11561. (S1 ^operator O1962 = 0.2550133443425458)
  11562. Retracting rl*prefer*rvt*predict-no*H0*2*H1*7
  11563. -->
  11564. (S1 ^operator O1962 = 0.1700769046561409)
  11565. Retracting rl*prefer*rvt*predict-yes*H0*1
  11566. -->
  11567. (S1 ^operator O1961 = 0.5231208307682875)
  11568. Retracting rl*prefer*rvt*predict-yes*H0*1*H1*19
  11569. -->
  11570. (S1 ^operator O1961 = 0.4768840530102607)
  11571. =>WM: (13797: S1 ^operator O1964 +)
  11572. =>WM: (13796: S1 ^operator O1963 +)
  11573. =>WM: (13795: O1964 ^name predict-no)
  11574. =>WM: (13794: O1963 ^name predict-yes)
  11575. =>WM: (13793: R985 ^value 1)
  11576. =>WM: (13792: R1 ^reward R985)
  11577. =>WM: (13791: I3 ^see 1)
  11578. <=WM: (13782: S1 ^operator O1961 +)
  11579. <=WM: (13784: S1 ^operator O1961)
  11580. <=WM: (13783: S1 ^operator O1962 +)
  11581. <=WM: (13777: R1 ^reward R984)
  11582. <=WM: (13748: I3 ^see 0)
  11583. <=WM: (13780: O1962 ^name predict-no)
  11584. <=WM: (13779: O1961 ^name predict-yes)
  11585. <=WM: (13778: R984 ^value 1)
  11586. --- Inner Elaboration Phase, active level 1 (S1) ---
  11587. Firing prefer*rvt*predict-yes*H0
  11588. -->
  11589. Firing rl*prefer*rvt*predict-yes*H0*1
  11590. -->
  11591. (S1 ^operator O1963 = 0.5231208307682875)
  11592. Firing prefer*rvt*predict-yes*H0*1*H1
  11593. -->
  11594. Firing rl*prefer*rvt*predict-yes*H0*1*H1*20
  11595. -->
  11596. (S1 ^operator O1963 = 0.1693592933936033)
  11597. Firing prefer*rvt*predict-no*H0
  11598. -->
  11599. Firing rl*prefer*rvt*predict-no*H0*2
  11600. -->
  11601. (S1 ^operator O1964 = 0.2550133443425458)
  11602. Firing prefer*rvt*predict-no*H0*2*H1
  11603. -->
  11604. Firing rl*prefer*rvt*predict-no*H0*2*H1*11
  11605. -->
  11606. (S1 ^operator O1964 = 0.7449863992127084)
  11607. inner elaboration loop at bottom goal.
  11608. Retracting rl*prefer*rvt*predict-no*H0*2
  11609. -->
  11610. (S1 ^operator O1962 = 0.2550133443425458)
  11611. Retracting rl*prefer*rvt*predict-no*H0*2*H1*11
  11612. -->
  11613. (S1 ^operator O1962 = 0.7449863992127084)
  11614. Retracting rl*prefer*rvt*predict-yes*H0*1
  11615. -->
  11616. (S1 ^operator O1961 = 0.5231208307682875)
  11617. Retracting rl*prefer*rvt*predict-yes*H0*1*H1*20
  11618. -->
  11619. (S1 ^operator O1961 = 0.1693592933936033)
  11620. --- END Proposal Phase ---
  11621. --- Decision Phase ---
  11622. RL update rl*prefer*rvt*predict-yes*H0*1 0.727961 -0.20484 0.523121 -> 0.72796 -0.20484 0.52312(R,m,v=1,0.978571,0.0211202)
  11623. RL update rl*prefer*rvt*predict-yes*H0*1*H1*19 0.272045 0.204839 0.476884 -> 0.272045 0.204839 0.476883(R,m,v=1,1,0)
  11624. =>WM: (13798: S1 ^operator O1964)
  11625. 982: O: O1964 (predict-no)
  11626. --- END Decision Phase ---
  11627. --- Application Phase ---
  11628. --- Firing Productions (PE) For State At Depth 1 ---
  11629. --- Inner Elaboration Phase, active level 1 (S1) ---
  11630. Firing apply*operator
  11631. -->
  11632. (I3 ^predict-no N982 + :O )
  11633. Firing apply*operator*complete
  11634. -->
  11635. (I3 ^predict-yes N981 - :O )
  11636. inner elaboration loop at bottom goal.
  11637. --- Change Working Memory (PE) ---
  11638. =>WM: (13799: I3 ^predict-no N982)
  11639. <=WM: (13786: N981 ^status complete)
  11640. <=WM: (13785: I3 ^predict-yes N981)
  11641. --- Firing Productions (IE) For State At Depth 1 ---
  11642. --- Inner Elaboration Phase, active level 1 (S1) ---
  11643. Firing monitor*world
  11644. -->
  11645. I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
  11646. --- Change Working Memory (IE) ---
  11647. --- END Application Phase ---
  11648. --- Output Phase ---
  11649. ENV: Agent did: predict-no for direction L in state State-A
  11650. In State-A moving L
  11651. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  11652. predict error 0
  11653. dir: dir isR
  11654. --- END Output Phase ---
  11655. /|\--- Input Phase ---
  11656. =>WM: (13803: I2 ^dir R)
  11657. =>WM: (13802: I2 ^reward 1)
  11658. =>WM: (13801: I2 ^see 0)
  11659. =>WM: (13800: N982 ^status complete)
  11660. <=WM: (13789: I2 ^dir L)
  11661. <=WM: (13788: I2 ^reward 1)
  11662. <=WM: (13787: I2 ^see 1)
  11663. =>WM: (13804: I2 ^level-1 L0-root)
  11664. <=WM: (13790: I2 ^level-1 L1-root)
  11665. --- END Input Phase ---
  11666. --- Proposal Phase ---
  11667. --- Inner Elaboration Phase, active level 1 (S1) ---
  11668. Firing rl*prefer*rvt*predict-yes*H0*3*H1*14
  11669. -->
  11670. (S1 ^operator O1963 = 0.6170773487089456)
  11671. Firing rl*prefer*rvt*predict-no*H0*4*H1*13
  11672. -->
  11673. (S1 ^operator O1964 = 0.4910065094545203)
  11674. Firing prefer*rvt*predict-no*H0*4*H1
  11675. -->
  11676. Firing prefer*rvt*predict-yes*H0*3*H1
  11677. -->
  11678. Firing elaborate*copy-see-to-output-link
  11679. -->
  11680. (I3 ^see 0 +)
  11681. Firing elaborate*reward*based*on*reward
  11682. -->
  11683. (R986 ^value 1 +)
  11684. (R1 ^reward R986 +)
  11685. Firing propose*predict-yes
  11686. -->
  11687. (O1965 ^name predict-yes +)
  11688. (S1 ^operator O1965 +)
  11689. Firing propose*predict-no
  11690. -->
  11691. (O1966 ^name predict-no +)
  11692. (S1 ^operator O1966 +)
  11693. Firing rl*prefer*rvt*predict-no*H0*4
  11694. -->
  11695. (S1 ^operator O1964 = 0.1269767445579436)
  11696. Firing rl*prefer*rvt*predict-yes*H0*3
  11697. -->
  11698. (S1 ^operator O1963 = 0.3829301257264589)
  11699. Firing prefer*rvt*predict-yes*H0
  11700. -->
  11701. Firing prefer*rvt*predict-no*H0
  11702. -->
  11703. Firing elaborate*copy-dir-to-output-link
  11704. -->
  11705. (I3 ^dir R +)
  11706. inner elaboration loop at bottom goal.
  11707. Retracting elaborate*copy-see-to-output-link
  11708. -->
  11709. (I3 ^see 1 +)
  11710. Retracting propose*predict-no
  11711. -->
  11712. (O1964 ^name predict-no +)
  11713. (S1 ^operator O1964 +)
  11714. Retracting propose*predict-yes
  11715. -->
  11716. (O1963 ^name predict-yes +)
  11717. (S1 ^operator O1963 +)
  11718. Retracting elaborate*reward*based*on*reward
  11719. -->
  11720. (R985 ^value 1 +)
  11721. (R1 ^reward R985 +)
  11722. Retracting elaborate*copy-dir-to-output-link
  11723. -->
  11724. (I3 ^dir L +)
  11725. Retracting rl*prefer*rvt*predict-no*H0*2*H1*11
  11726. -->
  11727. (S1 ^operator O1964 = 0.7449863992127084)
  11728. Retracting rl*prefer*rvt*predict-no*H0*2
  11729. -->
  11730. (S1 ^operator O1964 = 0.2550133443425458)
  11731. Retracting rl*prefer*rvt*predict-yes*H0*1*H1*20
  11732. -->
  11733. (S1 ^operator O1963 = 0.1693592933936033)
  11734. Retracting rl*prefer*rvt*predict-yes*H0*1
  11735. -->
  11736. (S1 ^operator O1963 = 0.5231200982015054)
  11737. =>WM: (13812: S1 ^operator O1966 +)
  11738. =>WM: (13811: S1 ^operator O1965 +)
  11739. =>WM: (13810: I3 ^dir R)
  11740. =>WM: (13809: O1966 ^name predict-no)
  11741. =>WM: (13808: O1965 ^name predict-yes)
  11742. =>WM: (13807: R986 ^value 1)
  11743. =>WM: (13806: R1 ^reward R986)
  11744. =>WM: (13805: I3 ^see 0)
  11745. <=WM: (13796: S1 ^operator O1963 +)
  11746. <=WM: (13797: S1 ^operator O1964 +)
  11747. <=WM: (13798: S1 ^operator O1964)
  11748. <=WM: (13781: I3 ^dir L)
  11749. <=WM: (13792: R1 ^reward R985)
  11750. <=WM: (13791: I3 ^see 1)
  11751. <=WM: (13795: O1964 ^name predict-no)
  11752. <=WM: (13794: O1963 ^name predict-yes)
  11753. <=WM: (13793: R985 ^value 1)
  11754. --- Inner Elaboration Phase, active level 1 (S1) ---
  11755. Firing prefer*rvt*predict-yes*H0
  11756. -->
  11757. Firing rl*prefer*rvt*predict-yes*H0*3
  11758. -->
  11759. (S1 ^operator O1965 = 0.3829301257264589)
  11760. Firing prefer*rvt*predict-yes*H0*3*H1
  11761. -->
  11762. Firing rl*prefer*rvt*predict-yes*H0*3*H1*14
  11763. -->
  11764. (S1 ^operator O1965 = 0.6170773487089456)
  11765. Firing prefer*rvt*predict-no*H0
  11766. -->
  11767. Firing rl*prefer*rvt*predict-no*H0*4
  11768. -->
  11769. (S1 ^operator O1966 = 0.1269767445579436)
  11770. Firing prefer*rvt*predict-no*H0*4*H1
  11771. -->
  11772. Firing rl*prefer*rvt*predict-no*H0*4*H1*13
  11773. -->
  11774. (S1 ^operator O1966 = 0.4910065094545203)
  11775. inner elaboration loop at bottom goal.
  11776. Retracting rl*prefer*rvt*predict-no*H0*4
  11777. -->
  11778. (S1 ^operator O1964 = 0.1269767445579436)
  11779. Retracting rl*prefer*rvt*predict-no*H0*4*H1*13
  11780. -->
  11781. (S1 ^operator O1964 = 0.4910065094545203)
  11782. Retracting rl*prefer*rvt*predict-yes*H0*3
  11783. -->
  11784. (S1 ^operator O1963 = 0.3829301257264589)
  11785. Retracting rl*prefer*rvt*predict-yes*H0*3*H1*14
  11786. -->
  11787. (S1 ^operator O1963 = 0.6170773487089456)
  11788. --- END Proposal Phase ---
  11789. --- Decision Phase ---
  11790. RL update rl*prefer*rvt*predict-no*H0*2 0.631495 -0.376482 0.255013 -> 0.631495 -0.376482 0.255013(R,m,v=1,0.917098,0.0764249)
  11791. RL update rl*prefer*rvt*predict-no*H0*2*H1*11 0.368505 0.376482 0.744986 -> 0.368505 0.376482 0.744986(R,m,v=1,1,0)
  11792. =>WM: (13813: S1 ^operator O1965)
  11793. 983: O: O1965 (predict-yes)
  11794. --- END Decision Phase ---
  11795. --- Application Phase ---
  11796. --- Firing Productions (PE) For State At Depth 1 ---
  11797. --- Inner Elaboration Phase, active level 1 (S1) ---
  11798. Firing apply*operator
  11799. -->
  11800. (I3 ^predict-yes N983 + :O )
  11801. Firing apply*operator*complete
  11802. -->
  11803. (I3 ^predict-no N982 - :O )
  11804. inner elaboration loop at bottom goal.
  11805. --- Change Working Memory (PE) ---
  11806. =>WM: (13814: I3 ^predict-yes N983)
  11807. <=WM: (13800: N982 ^status complete)
  11808. <=WM: (13799: I3 ^predict-no N982)
  11809. --- Firing Productions (IE) For State At Depth 1 ---
  11810. --- Inner Elaboration Phase, active level 1 (S1) ---
  11811. Firing monitor*world
  11812. -->
  11813. I see 1 and I'm going to do: predict-yes inner elaboration loop at bottom goal.
  11814. --- Change Working Memory (IE) ---
  11815. --- END Application Phase ---
  11816. --- Output Phase ---
  11817. ENV: Agent did: predict-yes for direction R in state State-A
  11818. In State-A moving R
  11819. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  11820. predict error 0
  11821. dir: dir isU
  11822. --- END Output Phase ---
  11823. -/|--- Input Phase ---
  11824. =>WM: (13818: I2 ^dir U)
  11825. =>WM: (13817: I2 ^reward 1)
  11826. =>WM: (13816: I2 ^see 1)
  11827. =>WM: (13815: N983 ^status complete)
  11828. <=WM: (13803: I2 ^dir R)
  11829. <=WM: (13802: I2 ^reward 1)
  11830. <=WM: (13801: I2 ^see 0)
  11831. =>WM: (13819: I2 ^level-1 R1-root)
  11832. <=WM: (13804: I2 ^level-1 L0-root)
  11833. --- END Input Phase ---
  11834. --- Proposal Phase ---
  11835. --- Inner Elaboration Phase, active level 1 (S1) ---
  11836. Firing elaborate*copy-see-to-output-link
  11837. -->
  11838. (I3 ^see 1 +)
  11839. Firing elaborate*reward*based*on*reward
  11840. -->
  11841. (R987 ^value 1 +)
  11842. (R1 ^reward R987 +)
  11843. Firing propose*predict-yes
  11844. -->
  11845. (O1967 ^name predict-yes +)
  11846. (S1 ^operator O1967 +)
  11847. Firing propose*predict-no
  11848. -->
  11849. (O1968 ^name predict-no +)
  11850. (S1 ^operator O1968 +)
  11851. Firing rl*prefer*rvt*predict-no*H0*6
  11852. -->
  11853. (S1 ^operator O1966 = 0.9999999999999999)
  11854. Firing rl*prefer*rvt*predict-yes*H0*5
  11855. -->
  11856. (S1 ^operator O1965 = 0.)
  11857. Firing prefer*rvt*predict-yes*H0
  11858. -->
  11859. Firing prefer*rvt*predict-no*H0
  11860. -->
  11861. Firing elaborate*copy-dir-to-output-link
  11862. -->
  11863. (I3 ^dir U +)
  11864. inner elaboration loop at bottom goal.
  11865. Retracting elaborate*copy-see-to-output-link
  11866. -->
  11867. (I3 ^see 0 +)
  11868. Retracting propose*predict-no
  11869. -->
  11870. (O1966 ^name predict-no +)
  11871. (S1 ^operator O1966 +)
  11872. Retracting propose*predict-yes
  11873. -->
  11874. (O1965 ^name predict-yes +)
  11875. (S1 ^operator O1965 +)
  11876. Retracting elaborate*reward*based*on*reward
  11877. -->
  11878. (R986 ^value 1 +)
  11879. (R1 ^reward R986 +)
  11880. Retracting elaborate*copy-dir-to-output-link
  11881. -->
  11882. (I3 ^dir R +)
  11883. Retracting rl*prefer*rvt*predict-no*H0*4*H1*13
  11884. -->
  11885. (S1 ^operator O1966 = 0.4910065094545203)
  11886. Retracting rl*prefer*rvt*predict-no*H0*4
  11887. -->
  11888. (S1 ^operator O1966 = 0.1269767445579436)
  11889. Retracting rl*prefer*rvt*predict-yes*H0*3*H1*14
  11890. -->
  11891. (S1 ^operator O1965 = 0.6170773487089456)
  11892. Retracting rl*prefer*rvt*predict-yes*H0*3
  11893. -->
  11894. (S1 ^operator O1965 = 0.3829301257264589)
  11895. =>WM: (13827: S1 ^operator O1968 +)
  11896. =>WM: (13826: S1 ^operator O1967 +)
  11897. =>WM: (13825: I3 ^dir U)
  11898. =>WM: (13824: O1968 ^name predict-no)
  11899. =>WM: (13823: O1967 ^name predict-yes)
  11900. =>WM: (13822: R987 ^value 1)
  11901. =>WM: (13821: R1 ^reward R987)
  11902. =>WM: (13820: I3 ^see 1)
  11903. <=WM: (13811: S1 ^operator O1965 +)
  11904. <=WM: (13813: S1 ^operator O1965)
  11905. <=WM: (13812: S1 ^operator O1966 +)
  11906. <=WM: (13810: I3 ^dir R)
  11907. <=WM: (13806: R1 ^reward R986)
  11908. <=WM: (13805: I3 ^see 0)
  11909. <=WM: (13809: O1966 ^name predict-no)
  11910. <=WM: (13808: O1965 ^name predict-yes)
  11911. <=WM: (13807: R986 ^value 1)
  11912. --- Inner Elaboration Phase, active level 1 (S1) ---
  11913. Firing prefer*rvt*predict-yes*H0
  11914. -->
  11915. Firing rl*prefer*rvt*predict-yes*H0*5
  11916. -->
  11917. (S1 ^operator O1967 = 0.)
  11918. Firing prefer*rvt*predict-no*H0
  11919. -->
  11920. Firing rl*prefer*rvt*predict-no*H0*6
  11921. -->
  11922. (S1 ^operator O1968 = 0.9999999999999999)
  11923. inner elaboration loop at bottom goal.
  11924. Retracting rl*prefer*rvt*predict-no*H0*6
  11925. -->
  11926. (S1 ^operator O1966 = 0.9999999999999999)
  11927. Retracting rl*prefer*rvt*predict-yes*H0*5
  11928. -->
  11929. (S1 ^operator O1965 = 0.)
  11930. --- END Proposal Phase ---
  11931. --- Decision Phase ---
  11932. RL update rl*prefer*rvt*predict-yes*H0*3 0.673124 -0.290194 0.38293 -> 0.673123 -0.290194 0.382929(R,m,v=1,0.960265,0.0384106)
  11933. RL update rl*prefer*rvt*predict-yes*H0*3*H1*14 0.326883 0.290195 0.617077 -> 0.326882 0.290195 0.617076(R,m,v=1,1,0)
  11934. =>WM: (13828: S1 ^operator O1968)
  11935. 984: O: O1968 (predict-no)
  11936. --- END Decision Phase ---
  11937. --- Application Phase ---
  11938. --- Firing Productions (PE) For State At Depth 1 ---
  11939. --- Inner Elaboration Phase, active level 1 (S1) ---
  11940. Firing apply*operator
  11941. -->
  11942. (I3 ^predict-no N984 + :O )
  11943. Firing apply*operator*complete
  11944. -->
  11945. (I3 ^predict-yes N983 - :O )
  11946. inner elaboration loop at bottom goal.
  11947. --- Change Working Memory (PE) ---
  11948. =>WM: (13829: I3 ^predict-no N984)
  11949. <=WM: (13815: N983 ^status complete)
  11950. <=WM: (13814: I3 ^predict-yes N983)
  11951. --- Firing Productions (IE) For State At Depth 1 ---
  11952. --- Inner Elaboration Phase, active level 1 (S1) ---
  11953. Firing monitor*world
  11954. -->
  11955. I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
  11956. --- Change Working Memory (IE) ---
  11957. --- END Application Phase ---
  11958. --- Output Phase ---
  11959. ENV: Agent did: predict-no for direction U in state State-B
  11960. In State-B moving U
  11961. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  11962. predict error 0
  11963. dir: dir isU
  11964. --- END Output Phase ---
  11965. \-/--- Input Phase ---
  11966. =>WM: (13833: I2 ^dir U)
  11967. =>WM: (13832: I2 ^reward 1)
  11968. =>WM: (13831: I2 ^see 0)
  11969. =>WM: (13830: N984 ^status complete)
  11970. <=WM: (13818: I2 ^dir U)
  11971. <=WM: (13817: I2 ^reward 1)
  11972. <=WM: (13816: I2 ^see 1)
  11973. =>WM: (13834: I2 ^level-1 R1-root)
  11974. <=WM: (13819: I2 ^level-1 R1-root)
  11975. --- END Input Phase ---
  11976. --- Proposal Phase ---
  11977. --- Inner Elaboration Phase, active level 1 (S1) ---
  11978. Firing elaborate*copy-see-to-output-link
  11979. -->
  11980. (I3 ^see 0 +)
  11981. Firing elaborate*reward*based*on*reward
  11982. -->
  11983. (R988 ^value 1 +)
  11984. (R1 ^reward R988 +)
  11985. Firing propose*predict-yes
  11986. -->
  11987. (O1969 ^name predict-yes +)
  11988. (S1 ^operator O1969 +)
  11989. Firing propose*predict-no
  11990. -->
  11991. (O1970 ^name predict-no +)
  11992. (S1 ^operator O1970 +)
  11993. Firing rl*prefer*rvt*predict-no*H0*6
  11994. -->
  11995. (S1 ^operator O1968 = 0.9999999999999999)
  11996. Firing rl*prefer*rvt*predict-yes*H0*5
  11997. -->
  11998. (S1 ^operator O1967 = 0.)
  11999. Firing prefer*rvt*predict-yes*H0
  12000. -->
  12001. Firing prefer*rvt*predict-no*H0
  12002. -->
  12003. Firing elaborate*copy-dir-to-output-link
  12004. -->
  12005. (I3 ^dir U +)
  12006. inner elaboration loop at bottom goal.
  12007. Retracting elaborate*copy-see-to-output-link
  12008. -->
  12009. (I3 ^see 1 +)
  12010. Retracting propose*predict-no
  12011. -->
  12012. (O1968 ^name predict-no +)
  12013. (S1 ^operator O1968 +)
  12014. Retracting propose*predict-yes
  12015. -->
  12016. (O1967 ^name predict-yes +)
  12017. (S1 ^operator O1967 +)
  12018. Retracting elaborate*reward*based*on*reward
  12019. -->
  12020. (R987 ^value 1 +)
  12021. (R1 ^reward R987 +)
  12022. Retracting elaborate*copy-dir-to-output-link
  12023. -->
  12024. (I3 ^dir U +)
  12025. Retracting rl*prefer*rvt*predict-no*H0*6
  12026. -->
  12027. (S1 ^operator O1968 = 0.9999999999999999)
  12028. Retracting rl*prefer*rvt*predict-yes*H0*5
  12029. -->
  12030. (S1 ^operator O1967 = 0.)
  12031. =>WM: (13841: S1 ^operator O1970 +)
  12032. =>WM: (13840: S1 ^operator O1969 +)
  12033. =>WM: (13839: O1970 ^name predict-no)
  12034. =>WM: (13838: O1969 ^name predict-yes)
  12035. =>WM: (13837: R988 ^value 1)
  12036. =>WM: (13836: R1 ^reward R988)
  12037. =>WM: (13835: I3 ^see 0)
  12038. <=WM: (13826: S1 ^operator O1967 +)
  12039. <=WM: (13827: S1 ^operator O1968 +)
  12040. <=WM: (13828: S1 ^operator O1968)
  12041. <=WM: (13821: R1 ^reward R987)
  12042. <=WM: (13820: I3 ^see 1)
  12043. <=WM: (13824: O1968 ^name predict-no)
  12044. <=WM: (13823: O1967 ^name predict-yes)
  12045. <=WM: (13822: R987 ^value 1)
  12046. --- Inner Elaboration Phase, active level 1 (S1) ---
  12047. Firing prefer*rvt*predict-yes*H0
  12048. -->
  12049. Firing rl*prefer*rvt*predict-yes*H0*5
  12050. -->
  12051. (S1 ^operator O1969 = 0.)
  12052. Firing prefer*rvt*predict-no*H0
  12053. -->
  12054. Firing rl*prefer*rvt*predict-no*H0*6
  12055. -->
  12056. (S1 ^operator O1970 = 0.9999999999999999)
  12057. inner elaboration loop at bottom goal.
  12058. Retracting rl*prefer*rvt*predict-no*H0*6
  12059. -->
  12060. (S1 ^operator O1968 = 0.9999999999999999)
  12061. Retracting rl*prefer*rvt*predict-yes*H0*5
  12062. -->
  12063. (S1 ^operator O1967 = 0.)
  12064. --- END Proposal Phase ---
  12065. --- Decision Phase ---
  12066. RL update rl*prefer*rvt*predict-no*H0*6 1 0 1 -> 1 0 1(R,m,v=1,1,0)
  12067. =>WM: (13842: S1 ^operator O1970)
  12068. 985: O: O1970 (predict-no)
  12069. --- END Decision Phase ---
  12070. --- Application Phase ---
  12071. --- Firing Productions (PE) For State At Depth 1 ---
  12072. --- Inner Elaboration Phase, active level 1 (S1) ---
  12073. Firing apply*operator
  12074. -->
  12075. (I3 ^predict-no N985 + :O )
  12076. Firing apply*operator*complete
  12077. -->
  12078. (I3 ^predict-no N984 - :O )
  12079. inner elaboration loop at bottom goal.
  12080. --- Change Working Memory (PE) ---
  12081. =>WM: (13843: I3 ^predict-no N985)
  12082. <=WM: (13830: N984 ^status complete)
  12083. <=WM: (13829: I3 ^predict-no N984)
  12084. --- Firing Productions (IE) For State At Depth 1 ---
  12085. --- Inner Elaboration Phase, active level 1 (S1) ---
  12086. Firing monitor*world
  12087. -->
  12088. I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
  12089. --- Change Working Memory (IE) ---
  12090. --- END Application Phase ---
  12091. --- Output Phase ---
  12092. ENV: Agent did: predict-no for direction U in state State-B
  12093. In State-B moving U
  12094. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  12095. predict error 0
  12096. dir: dir isR
  12097. --- END Output Phase ---
  12098. |\--- Input Phase ---
  12099. =>WM: (13847: I2 ^dir R)
  12100. =>WM: (13846: I2 ^reward 1)
  12101. =>WM: (13845: I2 ^see 0)
  12102. =>WM: (13844: N985 ^status complete)
  12103. <=WM: (13833: I2 ^dir U)
  12104. <=WM: (13832: I2 ^reward 1)
  12105. <=WM: (13831: I2 ^see 0)
  12106. =>WM: (13848: I2 ^level-1 R1-root)
  12107. <=WM: (13834: I2 ^level-1 R1-root)
  12108. --- END Input Phase ---
  12109. --- Proposal Phase ---
  12110. --- Inner Elaboration Phase, active level 1 (S1) ---
  12111. Firing rl*prefer*rvt*predict-yes*H0*3*H1*16
  12112. -->
  12113. (S1 ^operator O1969 = 0.08783148430849691)
  12114. Firing rl*prefer*rvt*predict-no*H0*4*H1*15
  12115. -->
  12116. (S1 ^operator O1970 = 0.8730234118412079)
  12117. Firing prefer*rvt*predict-no*H0*4*H1
  12118. -->
  12119. Firing prefer*rvt*predict-yes*H0*3*H1
  12120. -->
  12121. Firing elaborate*copy-see-to-output-link
  12122. -->
  12123. (I3 ^see 0 +)
  12124. Firing elaborate*reward*based*on*reward
  12125. -->
  12126. (R989 ^value 1 +)
  12127. (R1 ^reward R989 +)
  12128. Firing propose*predict-yes
  12129. -->
  12130. (O1971 ^name predict-yes +)
  12131. (S1 ^operator O1971 +)
  12132. Firing propose*predict-no
  12133. -->
  12134. (O1972 ^name predict-no +)
  12135. (S1 ^operator O1972 +)
  12136. Firing rl*prefer*rvt*predict-no*H0*4
  12137. -->
  12138. (S1 ^operator O1970 = 0.1269767445579436)
  12139. Firing rl*prefer*rvt*predict-yes*H0*3
  12140. -->
  12141. (S1 ^operator O1969 = 0.3829290045611482)
  12142. Firing prefer*rvt*predict-yes*H0
  12143. -->
  12144. Firing prefer*rvt*predict-no*H0
  12145. -->
  12146. Firing elaborate*copy-dir-to-output-link
  12147. -->
  12148. (I3 ^dir R +)
  12149. inner elaboration loop at bottom goal.
  12150. Retracting elaborate*copy-see-to-output-link
  12151. -->
  12152. (I3 ^see 0 +)
  12153. Retracting propose*predict-no
  12154. -->
  12155. (O1970 ^name predict-no +)
  12156. (S1 ^operator O1970 +)
  12157. Retracting propose*predict-yes
  12158. -->
  12159. (O1969 ^name predict-yes +)
  12160. (S1 ^operator O1969 +)
  12161. Retracting elaborate*reward*based*on*reward
  12162. -->
  12163. (R988 ^value 1 +)
  12164. (R1 ^reward R988 +)
  12165. Retracting elaborate*copy-dir-to-output-link
  12166. -->
  12167. (I3 ^dir U +)
  12168. Retracting rl*prefer*rvt*predict-no*H0*6
  12169. -->
  12170. (S1 ^operator O1970 = 0.9999999999999999)
  12171. Retracting rl*prefer*rvt*predict-yes*H0*5
  12172. -->
  12173. (S1 ^operator O1969 = 0.)
  12174. =>WM: (13855: S1 ^operator O1972 +)
  12175. =>WM: (13854: S1 ^operator O1971 +)
  12176. =>WM: (13853: I3 ^dir R)
  12177. =>WM: (13852: O1972 ^name predict-no)
  12178. =>WM: (13851: O1971 ^name predict-yes)
  12179. =>WM: (13850: R989 ^value 1)
  12180. =>WM: (13849: R1 ^reward R989)
  12181. <=WM: (13840: S1 ^operator O1969 +)
  12182. <=WM: (13841: S1 ^operator O1970 +)
  12183. <=WM: (13842: S1 ^operator O1970)
  12184. <=WM: (13825: I3 ^dir U)
  12185. <=WM: (13836: R1 ^reward R988)
  12186. <=WM: (13839: O1970 ^name predict-no)
  12187. <=WM: (13838: O1969 ^name predict-yes)
  12188. <=WM: (13837: R988 ^value 1)
  12189. --- Inner Elaboration Phase, active level 1 (S1) ---
  12190. Firing prefer*rvt*predict-yes*H0
  12191. -->
  12192. Firing rl*prefer*rvt*predict-yes*H0*3*H1*16
  12193. -->
  12194. (S1 ^operator O1971 = 0.08783148430849691)
  12195. Firing rl*prefer*rvt*predict-yes*H0*3
  12196. -->
  12197. (S1 ^operator O1971 = 0.3829290045611482)
  12198. Firing prefer*rvt*predict-yes*H0*3*H1
  12199. -->
  12200. Firing prefer*rvt*predict-no*H0
  12201. -->
  12202. Firing rl*prefer*rvt*predict-no*H0*4*H1*15
  12203. -->
  12204. (S1 ^operator O1972 = 0.8730234118412079)
  12205. Firing rl*prefer*rvt*predict-no*H0*4
  12206. -->
  12207. (S1 ^operator O1972 = 0.1269767445579436)
  12208. Firing prefer*rvt*predict-no*H0*4*H1
  12209. -->
  12210. inner elaboration loop at bottom goal.
  12211. Retracting rl*prefer*rvt*predict-no*H0*4
  12212. -->
  12213. (S1 ^operator O1970 = 0.1269767445579436)
  12214. Retracting rl*prefer*rvt*predict-no*H0*4*H1*15
  12215. -->
  12216. (S1 ^operator O1970 = 0.8730234118412079)
  12217. Retracting rl*prefer*rvt*predict-yes*H0*3
  12218. -->
  12219. (S1 ^operator O1969 = 0.3829290045611482)
  12220. Retracting rl*prefer*rvt*predict-yes*H0*3*H1*16
  12221. -->
  12222. (S1 ^operator O1969 = 0.08783148430849691)
  12223. --- END Proposal Phase ---
  12224. --- Decision Phase ---
  12225. RL update rl*prefer*rvt*predict-no*H0*6 1 0 1 -> 1 0 1(R,m,v=1,1,0)
  12226. =>WM: (13856: S1 ^operator O1972)
  12227. 986: O: O1972 (predict-no)
  12228. --- END Decision Phase ---
  12229. --- Application Phase ---
  12230. --- Firing Productions (PE) For State At Depth 1 ---
  12231. --- Inner Elaboration Phase, active level 1 (S1) ---
  12232. Firing apply*operator
  12233. -->
  12234. (I3 ^predict-no N986 + :O )
  12235. Firing apply*operator*complete
  12236. -->
  12237. (I3 ^predict-no N985 - :O )
  12238. inner elaboration loop at bottom goal.
  12239. --- Change Working Memory (PE) ---
  12240. =>WM: (13857: I3 ^predict-no N986)
  12241. <=WM: (13844: N985 ^status complete)
  12242. <=WM: (13843: I3 ^predict-no N985)
  12243. --- Firing Productions (IE) For State At Depth 1 ---
  12244. --- Inner Elaboration Phase, active level 1 (S1) ---
  12245. Firing monitor*world
  12246. -->
  12247. I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
  12248. --- Change Working Memory (IE) ---
  12249. --- END Application Phase ---
  12250. --- Output Phase ---
  12251. ENV: Agent did: predict-no for direction R in state State-B
  12252. In State-B moving R
  12253. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  12254. predict error 0
  12255. dir: dir isR
  12256. --- END Output Phase ---
  12257. -/|--- Input Phase ---
  12258. =>WM: (13861: I2 ^dir R)
  12259. =>WM: (13860: I2 ^reward 1)
  12260. =>WM: (13859: I2 ^see 0)
  12261. =>WM: (13858: N986 ^status complete)
  12262. <=WM: (13847: I2 ^dir R)
  12263. <=WM: (13846: I2 ^reward 1)
  12264. <=WM: (13845: I2 ^see 0)
  12265. =>WM: (13862: I2 ^level-1 R0-root)
  12266. <=WM: (13848: I2 ^level-1 R1-root)
  12267. --- END Input Phase ---
  12268. --- Proposal Phase ---
  12269. --- Inner Elaboration Phase, active level 1 (S1) ---
  12270. Firing rl*prefer*rvt*predict-yes*H0*3*H1*18
  12271. -->
  12272. (S1 ^operator O1971 = 0.2696941111808541)
  12273. Firing rl*prefer*rvt*predict-no*H0*4*H1*17
  12274. -->
  12275. (S1 ^operator O1972 = 0.8730228631156078)
  12276. Firing prefer*rvt*predict-no*H0*4*H1
  12277. -->
  12278. Firing prefer*rvt*predict-yes*H0*3*H1
  12279. -->
  12280. Firing elaborate*copy-see-to-output-link
  12281. -->
  12282. (I3 ^see 0 +)
  12283. Firing elaborate*reward*based*on*reward
  12284. -->
  12285. (R990 ^value 1 +)
  12286. (R1 ^reward R990 +)
  12287. Firing propose*predict-yes
  12288. -->
  12289. (O1973 ^name predict-yes +)
  12290. (S1 ^operator O1973 +)
  12291. Firing propose*predict-no
  12292. -->
  12293. (O1974 ^name predict-no +)
  12294. (S1 ^operator O1974 +)
  12295. Firing rl*prefer*rvt*predict-no*H0*4
  12296. -->
  12297. (S1 ^operator O1972 = 0.1269767445579436)
  12298. Firing rl*prefer*rvt*predict-yes*H0*3
  12299. -->
  12300. (S1 ^operator O1971 = 0.3829290045611482)
  12301. Firing prefer*rvt*predict-yes*H0
  12302. -->
  12303. Firing prefer*rvt*predict-no*H0
  12304. -->
  12305. Firing elaborate*copy-dir-to-output-link
  12306. -->
  12307. (I3 ^dir R +)
  12308. inner elaboration loop at bottom goal.
  12309. Retracting elaborate*copy-see-to-output-link
  12310. -->
  12311. (I3 ^see 0 +)
  12312. Retracting propose*predict-no
  12313. -->
  12314. (O1972 ^name predict-no +)
  12315. (S1 ^operator O1972 +)
  12316. Retracting propose*predict-yes
  12317. -->
  12318. (O1971 ^name predict-yes +)
  12319. (S1 ^operator O1971 +)
  12320. Retracting elaborate*reward*based*on*reward
  12321. -->
  12322. (R989 ^value 1 +)
  12323. (R1 ^reward R989 +)
  12324. Retracting elaborate*copy-dir-to-output-link
  12325. -->
  12326. (I3 ^dir R +)
  12327. Retracting rl*prefer*rvt*predict-no*H0*4
  12328. -->
  12329. (S1 ^operator O1972 = 0.1269767445579436)
  12330. Retracting rl*prefer*rvt*predict-no*H0*4*H1*15
  12331. -->
  12332. (S1 ^operator O1972 = 0.8730234118412079)
  12333. Retracting rl*prefer*rvt*predict-yes*H0*3
  12334. -->
  12335. (S1 ^operator O1971 = 0.3829290045611482)
  12336. Retracting rl*prefer*rvt*predict-yes*H0*3*H1*16
  12337. -->
  12338. (S1 ^operator O1971 = 0.08783148430849691)
  12339. =>WM: (13868: S1 ^operator O1974 +)
  12340. =>WM: (13867: S1 ^operator O1973 +)
  12341. =>WM: (13866: O1974 ^name predict-no)
  12342. =>WM: (13865: O1973 ^name predict-yes)
  12343. =>WM: (13864: R990 ^value 1)
  12344. =>WM: (13863: R1 ^reward R990)
  12345. <=WM: (13854: S1 ^operator O1971 +)
  12346. <=WM: (13855: S1 ^operator O1972 +)
  12347. <=WM: (13856: S1 ^operator O1972)
  12348. <=WM: (13849: R1 ^reward R989)
  12349. <=WM: (13852: O1972 ^name predict-no)
  12350. <=WM: (13851: O1971 ^name predict-yes)
  12351. <=WM: (13850: R989 ^value 1)
  12352. --- Inner Elaboration Phase, active level 1 (S1) ---
  12353. Firing prefer*rvt*predict-yes*H0
  12354. -->
  12355. Firing rl*prefer*rvt*predict-yes*H0*3
  12356. -->
  12357. (S1 ^operator O1973 = 0.3829290045611482)
  12358. Firing prefer*rvt*predict-yes*H0*3*H1
  12359. -->
  12360. Firing rl*prefer*rvt*predict-yes*H0*3*H1*18
  12361. -->
  12362. (S1 ^operator O1973 = 0.2696941111808541)
  12363. Firing prefer*rvt*predict-no*H0
  12364. -->
  12365. Firing rl*prefer*rvt*predict-no*H0*4
  12366. -->
  12367. (S1 ^operator O1974 = 0.1269767445579436)
  12368. Firing prefer*rvt*predict-no*H0*4*H1
  12369. -->
  12370. Firing rl*prefer*rvt*predict-no*H0*4*H1*17
  12371. -->
  12372. (S1 ^operator O1974 = 0.8730228631156078)
  12373. inner elaboration loop at bottom goal.
  12374. Retracting rl*prefer*rvt*predict-no*H0*4
  12375. -->
  12376. (S1 ^operator O1972 = 0.1269767445579436)
  12377. Retracting rl*prefer*rvt*predict-no*H0*4*H1*17
  12378. -->
  12379. (S1 ^operator O1972 = 0.8730228631156078)
  12380. Retracting rl*prefer*rvt*predict-yes*H0*3
  12381. -->
  12382. (S1 ^operator O1971 = 0.3829290045611482)
  12383. Retracting rl*prefer*rvt*predict-yes*H0*3*H1*18
  12384. -->
  12385. (S1 ^operator O1971 = 0.2696941111808541)
  12386. --- END Proposal Phase ---
  12387. --- Decision Phase ---
  12388. RL update rl*prefer*rvt*predict-no*H0*4 0.814714 -0.687737 0.126977 -> 0.814714 -0.687737 0.126977(R,m,v=1,0.948276,0.0493323)
  12389. RL update rl*prefer*rvt*predict-no*H0*4*H1*15 0.185286 0.687737 0.873023 -> 0.185286 0.687737 0.873023(R,m,v=1,1,0)
  12390. =>WM: (13869: S1 ^operator O1974)
  12391. 987: O: O1974 (predict-no)
  12392. --- END Decision Phase ---
  12393. --- Application Phase ---
  12394. --- Firing Productions (PE) For State At Depth 1 ---
  12395. --- Inner Elaboration Phase, active level 1 (S1) ---
  12396. Firing apply*operator
  12397. -->
  12398. (I3 ^predict-no N987 + :O )
  12399. Firing apply*operator*complete
  12400. -->
  12401. (I3 ^predict-no N986 - :O )
  12402. inner elaboration loop at bottom goal.
  12403. --- Change Working Memory (PE) ---
  12404. =>WM: (13870: I3 ^predict-no N987)
  12405. <=WM: (13858: N986 ^status complete)
  12406. <=WM: (13857: I3 ^predict-no N986)
  12407. --- Firing Productions (IE) For State At Depth 1 ---
  12408. --- Inner Elaboration Phase, active level 1 (S1) ---
  12409. Firing monitor*world
  12410. -->
  12411. I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
  12412. --- Change Working Memory (IE) ---
  12413. --- END Application Phase ---
  12414. --- Output Phase ---
  12415. ENV: Agent did: predict-no for direction R in state State-B
  12416. In State-B moving R
  12417. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  12418. predict error 0
  12419. dir: dir isR
  12420. --- END Output Phase ---
  12421. \-/|--- Input Phase ---
  12422. =>WM: (13874: I2 ^dir R)
  12423. =>WM: (13873: I2 ^reward 1)
  12424. =>WM: (13872: I2 ^see 0)
  12425. =>WM: (13871: N987 ^status complete)
  12426. <=WM: (13861: I2 ^dir R)
  12427. <=WM: (13860: I2 ^reward 1)
  12428. <=WM: (13859: I2 ^see 0)
  12429. =>WM: (13875: I2 ^level-1 R0-root)
  12430. <=WM: (13862: I2 ^level-1 R0-root)
  12431. --- END Input Phase ---
  12432. --- Proposal Phase ---
  12433. --- Inner Elaboration Phase, active level 1 (S1) ---
  12434. Firing rl*prefer*rvt*predict-yes*H0*3*H1*18
  12435. -->
  12436. (S1 ^operator O1973 = 0.2696941111808541)
  12437. Firing rl*prefer*rvt*predict-no*H0*4*H1*17
  12438. -->
  12439. (S1 ^operator O1974 = 0.8730228631156078)
  12440. Firing prefer*rvt*predict-no*H0*4*H1
  12441. -->
  12442. Firing prefer*rvt*predict-yes*H0*3*H1
  12443. -->
  12444. Firing elaborate*copy-see-to-output-link
  12445. -->
  12446. (I3 ^see 0 +)
  12447. Firing elaborate*reward*based*on*reward
  12448. -->
  12449. (R991 ^value 1 +)
  12450. (R1 ^reward R991 +)
  12451. Firing propose*predict-yes
  12452. -->
  12453. (O1975 ^name predict-yes +)
  12454. (S1 ^operator O1975 +)
  12455. Firing propose*predict-no
  12456. -->
  12457. (O1976 ^name predict-no +)
  12458. (S1 ^operator O1976 +)
  12459. Firing rl*prefer*rvt*predict-no*H0*4
  12460. -->
  12461. (S1 ^operator O1974 = 0.1269767210980709)
  12462. Firing rl*prefer*rvt*predict-yes*H0*3
  12463. -->
  12464. (S1 ^operator O1973 = 0.3829290045611482)
  12465. Firing prefer*rvt*predict-yes*H0
  12466. -->
  12467. Firing prefer*rvt*predict-no*H0
  12468. -->
  12469. Firing elaborate*copy-dir-to-output-link
  12470. -->
  12471. (I3 ^dir R +)
  12472. inner elaboration loop at bottom goal.
  12473. Retracting elaborate*copy-see-to-output-link
  12474. -->
  12475. (I3 ^see 0 +)
  12476. Retracting propose*predict-no
  12477. -->
  12478. (O1974 ^name predict-no +)
  12479. (S1 ^operator O1974 +)
  12480. Retracting propose*predict-yes
  12481. -->
  12482. (O1973 ^name predict-yes +)
  12483. (S1 ^operator O1973 +)
  12484. Retracting elaborate*reward*based*on*reward
  12485. -->
  12486. (R990 ^value 1 +)
  12487. (R1 ^reward R990 +)
  12488. Retracting elaborate*copy-dir-to-output-link
  12489. -->
  12490. (I3 ^dir R +)
  12491. Retracting rl*prefer*rvt*predict-no*H0*4*H1*17
  12492. -->
  12493. (S1 ^operator O1974 = 0.8730228631156078)
  12494. Retracting rl*prefer*rvt*predict-no*H0*4
  12495. -->
  12496. (S1 ^operator O1974 = 0.1269767210980709)
  12497. Retracting rl*prefer*rvt*predict-yes*H0*3*H1*18
  12498. -->
  12499. (S1 ^operator O1973 = 0.2696941111808541)
  12500. Retracting rl*prefer*rvt*predict-yes*H0*3
  12501. -->
  12502. (S1 ^operator O1973 = 0.3829290045611482)
  12503. =>WM: (13881: S1 ^operator O1976 +)
  12504. =>WM: (13880: S1 ^operator O1975 +)
  12505. =>WM: (13879: O1976 ^name predict-no)
  12506. =>WM: (13878: O1975 ^name predict-yes)
  12507. =>WM: (13877: R991 ^value 1)
  12508. =>WM: (13876: R1 ^reward R991)
  12509. <=WM: (13867: S1 ^operator O1973 +)
  12510. <=WM: (13868: S1 ^operator O1974 +)
  12511. <=WM: (13869: S1 ^operator O1974)
  12512. <=WM: (13863: R1 ^reward R990)
  12513. <=WM: (13866: O1974 ^name predict-no)
  12514. <=WM: (13865: O1973 ^name predict-yes)
  12515. <=WM: (13864: R990 ^value 1)
  12516. --- Inner Elaboration Phase, active level 1 (S1) ---
  12517. Firing prefer*rvt*predict-yes*H0
  12518. -->
  12519. Firing rl*prefer*rvt*predict-yes*H0*3
  12520. -->
  12521. (S1 ^operator O1975 = 0.3829290045611482)
  12522. Firing prefer*rvt*predict-yes*H0*3*H1
  12523. -->
  12524. Firing rl*prefer*rvt*predict-yes*H0*3*H1*18
  12525. -->
  12526. (S1 ^operator O1975 = 0.2696941111808541)
  12527. Firing prefer*rvt*predict-no*H0
  12528. -->
  12529. Firing rl*prefer*rvt*predict-no*H0*4
  12530. -->
  12531. (S1 ^operator O1976 = 0.1269767210980709)
  12532. Firing prefer*rvt*predict-no*H0*4*H1
  12533. -->
  12534. Firing rl*prefer*rvt*predict-no*H0*4*H1*17
  12535. -->
  12536. (S1 ^operator O1976 = 0.8730228631156078)
  12537. inner elaboration loop at bottom goal.
  12538. Retracting rl*prefer*rvt*predict-no*H0*4
  12539. -->
  12540. (S1 ^operator O1974 = 0.1269767210980709)
  12541. Retracting rl*prefer*rvt*predict-no*H0*4*H1*17
  12542. -->
  12543. (S1 ^operator O1974 = 0.8730228631156078)
  12544. Retracting rl*prefer*rvt*predict-yes*H0*3
  12545. -->
  12546. (S1 ^operator O1973 = 0.3829290045611482)
  12547. Retracting rl*prefer*rvt*predict-yes*H0*3*H1*18
  12548. -->
  12549. (S1 ^operator O1973 = 0.2696941111808541)
  12550. --- END Proposal Phase ---
  12551. --- Decision Phase ---
  12552. RL update rl*prefer*rvt*predict-no*H0*4 0.814714 -0.687737 0.126977 -> 0.814714 -0.687737 0.126977(R,m,v=1,0.948571,0.049064)
  12553. RL update rl*prefer*rvt*predict-no*H0*4*H1*17 0.185286 0.687737 0.873023 -> 0.185286 0.687737 0.873023(R,m,v=1,1,0)
  12554. =>WM: (13882: S1 ^operator O1976)
  12555. 988: O: O1976 (predict-no)
  12556. --- END Decision Phase ---
  12557. --- Application Phase ---
  12558. --- Firing Productions (PE) For State At Depth 1 ---
  12559. --- Inner Elaboration Phase, active level 1 (S1) ---
  12560. Firing apply*operator
  12561. -->
  12562. (I3 ^predict-no N988 + :O )
  12563. Firing apply*operator*complete
  12564. -->
  12565. (I3 ^predict-no N987 - :O )
  12566. inner elaboration loop at bottom goal.
  12567. --- Change Working Memory (PE) ---
  12568. =>WM: (13883: I3 ^predict-no N988)
  12569. <=WM: (13871: N987 ^status complete)
  12570. <=WM: (13870: I3 ^predict-no N987)
  12571. --- Firing Productions (IE) For State At Depth 1 ---
  12572. --- Inner Elaboration Phase, active level 1 (S1) ---
  12573. Firing monitor*world
  12574. -->
  12575. I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
  12576. --- Change Working Memory (IE) ---
  12577. --- END Application Phase ---
  12578. --- Output Phase ---
  12579. ENV: Agent did: predict-no for direction R in state State-B
  12580. In State-B moving R
  12581. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  12582. predict error 0
  12583. dir: dir isR
  12584. --- END Output Phase ---
  12585. \---- Input Phase ---
  12586. =>WM: (13887: I2 ^dir R)
  12587. =>WM: (13886: I2 ^reward 1)
  12588. =>WM: (13885: I2 ^see 0)
  12589. =>WM: (13884: N988 ^status complete)
  12590. <=WM: (13874: I2 ^dir R)
  12591. <=WM: (13873: I2 ^reward 1)
  12592. <=WM: (13872: I2 ^see 0)
  12593. =>WM: (13888: I2 ^level-1 R0-root)
  12594. <=WM: (13875: I2 ^level-1 R0-root)
  12595. --- END Input Phase ---
  12596. --- Proposal Phase ---
  12597. --- Inner Elaboration Phase, active level 1 (S1) ---
  12598. Firing rl*prefer*rvt*predict-yes*H0*3*H1*18
  12599. -->
  12600. (S1 ^operator O1975 = 0.2696941111808541)
  12601. Firing rl*prefer*rvt*predict-no*H0*4*H1*17
  12602. -->
  12603. (S1 ^operator O1976 = 0.8730229254835561)
  12604. Firing prefer*rvt*predict-no*H0*4*H1
  12605. -->
  12606. Firing prefer*rvt*predict-yes*H0*3*H1
  12607. -->
  12608. Firing elaborate*copy-see-to-output-link
  12609. -->
  12610. (I3 ^see 0 +)
  12611. Firing elaborate*reward*based*on*reward
  12612. -->
  12613. (R992 ^value 1 +)
  12614. (R1 ^reward R992 +)
  12615. Firing propose*predict-yes
  12616. -->
  12617. (O1977 ^name predict-yes +)
  12618. (S1 ^operator O1977 +)
  12619. Firing propose*predict-no
  12620. -->
  12621. (O1978 ^name predict-no +)
  12622. (S1 ^operator O1978 +)
  12623. Firing rl*prefer*rvt*predict-no*H0*4
  12624. -->
  12625. (S1 ^operator O1976 = 0.126976783466019)
  12626. Firing rl*prefer*rvt*predict-yes*H0*3
  12627. -->
  12628. (S1 ^operator O1975 = 0.3829290045611482)
  12629. Firing prefer*rvt*predict-yes*H0
  12630. -->
  12631. Firing prefer*rvt*predict-no*H0
  12632. -->
  12633. Firing elaborate*copy-dir-to-output-link
  12634. -->
  12635. (I3 ^dir R +)
  12636. inner elaboration loop at bottom goal.
  12637. Retracting elaborate*copy-see-to-output-link
  12638. -->
  12639. (I3 ^see 0 +)
  12640. Retracting propose*predict-no
  12641. -->
  12642. (O1976 ^name predict-no +)
  12643. (S1 ^operator O1976 +)
  12644. Retracting propose*predict-yes
  12645. -->
  12646. (O1975 ^name predict-yes +)
  12647. (S1 ^operator O1975 +)
  12648. Retracting elaborate*reward*based*on*reward
  12649. -->
  12650. (R991 ^value 1 +)
  12651. (R1 ^reward R991 +)
  12652. Retracting elaborate*copy-dir-to-output-link
  12653. -->
  12654. (I3 ^dir R +)
  12655. Retracting rl*prefer*rvt*predict-no*H0*4*H1*17
  12656. -->
  12657. (S1 ^operator O1976 = 0.8730229254835561)
  12658. Retracting rl*prefer*rvt*predict-no*H0*4
  12659. -->
  12660. (S1 ^operator O1976 = 0.126976783466019)
  12661. Retracting rl*prefer*rvt*predict-yes*H0*3*H1*18
  12662. -->
  12663. (S1 ^operator O1975 = 0.2696941111808541)
  12664. Retracting rl*prefer*rvt*predict-yes*H0*3
  12665. -->
  12666. (S1 ^operator O1975 = 0.3829290045611482)
  12667. =>WM: (13894: S1 ^operator O1978 +)
  12668. =>WM: (13893: S1 ^operator O1977 +)
  12669. =>WM: (13892: O1978 ^name predict-no)
  12670. =>WM: (13891: O1977 ^name predict-yes)
  12671. =>WM: (13890: R992 ^value 1)
  12672. =>WM: (13889: R1 ^reward R992)
  12673. <=WM: (13880: S1 ^operator O1975 +)
  12674. <=WM: (13881: S1 ^operator O1976 +)
  12675. <=WM: (13882: S1 ^operator O1976)
  12676. <=WM: (13876: R1 ^reward R991)
  12677. <=WM: (13879: O1976 ^name predict-no)
  12678. <=WM: (13878: O1975 ^name predict-yes)
  12679. <=WM: (13877: R991 ^value 1)
  12680. --- Inner Elaboration Phase, active level 1 (S1) ---
  12681. Firing prefer*rvt*predict-yes*H0
  12682. -->
  12683. Firing rl*prefer*rvt*predict-yes*H0*3
  12684. -->
  12685. (S1 ^operator O1977 = 0.3829290045611482)
  12686. Firing prefer*rvt*predict-yes*H0*3*H1
  12687. -->
  12688. Firing rl*prefer*rvt*predict-yes*H0*3*H1*18
  12689. -->
  12690. (S1 ^operator O1977 = 0.2696941111808541)
  12691. Firing prefer*rvt*predict-no*H0
  12692. -->
  12693. Firing rl*prefer*rvt*predict-no*H0*4
  12694. -->
  12695. (S1 ^operator O1978 = 0.126976783466019)
  12696. Firing prefer*rvt*predict-no*H0*4*H1
  12697. -->
  12698. Firing rl*prefer*rvt*predict-no*H0*4*H1*17
  12699. -->
  12700. (S1 ^operator O1978 = 0.8730229254835561)
  12701. inner elaboration loop at bottom goal.
  12702. Retracting rl*prefer*rvt*predict-no*H0*4
  12703. -->
  12704. (S1 ^operator O1976 = 0.126976783466019)
  12705. Retracting rl*prefer*rvt*predict-no*H0*4*H1*17
  12706. -->
  12707. (S1 ^operator O1976 = 0.8730229254835561)
  12708. Retracting rl*prefer*rvt*predict-yes*H0*3
  12709. -->
  12710. (S1 ^operator O1975 = 0.3829290045611482)
  12711. Retracting rl*prefer*rvt*predict-yes*H0*3*H1*18
  12712. -->
  12713. (S1 ^operator O1975 = 0.2696941111808541)
  12714. --- END Proposal Phase ---
  12715. --- Decision Phase ---
  12716. RL update rl*prefer*rvt*predict-no*H0*4 0.814714 -0.687737 0.126977 -> 0.814714 -0.687737 0.126977(R,m,v=1,0.948864,0.0487987)
  12717. RL update rl*prefer*rvt*predict-no*H0*4*H1*17 0.185286 0.687737 0.873023 -> 0.185286 0.687737 0.873023(R,m,v=1,1,0)
  12718. =>WM: (13895: S1 ^operator O1978)
  12719. 989: O: O1978 (predict-no)
  12720. --- END Decision Phase ---
  12721. --- Application Phase ---
  12722. --- Firing Productions (PE) For State At Depth 1 ---
  12723. --- Inner Elaboration Phase, active level 1 (S1) ---
  12724. Firing apply*operator
  12725. -->
  12726. (I3 ^predict-no N989 + :O )
  12727. Firing apply*operator*complete
  12728. -->
  12729. (I3 ^predict-no N988 - :O )
  12730. inner elaboration loop at bottom goal.
  12731. --- Change Working Memory (PE) ---
  12732. =>WM: (13896: I3 ^predict-no N989)
  12733. <=WM: (13884: N988 ^status complete)
  12734. <=WM: (13883: I3 ^predict-no N988)
  12735. --- Firing Productions (IE) For State At Depth 1 ---
  12736. --- Inner Elaboration Phase, active level 1 (S1) ---
  12737. Firing monitor*world
  12738. -->
  12739. I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
  12740. --- Change Working Memory (IE) ---
  12741. --- END Application Phase ---
  12742. --- Output Phase ---
  12743. ENV: Agent did: predict-no for direction R in state State-B
  12744. In State-B moving R
  12745. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  12746. predict error 0
  12747. dir: dir isR
  12748. --- END Output Phase ---
  12749. /|\--- Input Phase ---
  12750. =>WM: (13900: I2 ^dir R)
  12751. =>WM: (13899: I2 ^reward 1)
  12752. =>WM: (13898: I2 ^see 0)
  12753. =>WM: (13897: N989 ^status complete)
  12754. <=WM: (13887: I2 ^dir R)
  12755. <=WM: (13886: I2 ^reward 1)
  12756. <=WM: (13885: I2 ^see 0)
  12757. =>WM: (13901: I2 ^level-1 R0-root)
  12758. <=WM: (13888: I2 ^level-1 R0-root)
  12759. --- END Input Phase ---
  12760. --- Proposal Phase ---
  12761. --- Inner Elaboration Phase, active level 1 (S1) ---
  12762. Firing rl*prefer*rvt*predict-yes*H0*3*H1*18
  12763. -->
  12764. (S1 ^operator O1977 = 0.2696941111808541)
  12765. Firing rl*prefer*rvt*predict-no*H0*4*H1*17
  12766. -->
  12767. (S1 ^operator O1978 = 0.8730229691411198)
  12768. Firing prefer*rvt*predict-no*H0*4*H1
  12769. -->
  12770. Firing prefer*rvt*predict-yes*H0*3*H1
  12771. -->
  12772. Firing elaborate*copy-see-to-output-link
  12773. -->
  12774. (I3 ^see 0 +)
  12775. Firing elaborate*reward*based*on*reward
  12776. -->
  12777. (R993 ^value 1 +)
  12778. (R1 ^reward R993 +)
  12779. Firing propose*predict-yes
  12780. -->
  12781. (O1979 ^name predict-yes +)
  12782. (S1 ^operator O1979 +)
  12783. Firing propose*predict-no
  12784. -->
  12785. (O1980 ^name predict-no +)
  12786. (S1 ^operator O1980 +)
  12787. Firing rl*prefer*rvt*predict-no*H0*4
  12788. -->
  12789. (S1 ^operator O1978 = 0.1269768271235827)
  12790. Firing rl*prefer*rvt*predict-yes*H0*3
  12791. -->
  12792. (S1 ^operator O1977 = 0.3829290045611482)
  12793. Firing prefer*rvt*predict-yes*H0
  12794. -->
  12795. Firing prefer*rvt*predict-no*H0
  12796. -->
  12797. Firing elaborate*copy-dir-to-output-link
  12798. -->
  12799. (I3 ^dir R +)
  12800. inner elaboration loop at bottom goal.
  12801. Retracting elaborate*copy-see-to-output-link
  12802. -->
  12803. (I3 ^see 0 +)
  12804. Retracting propose*predict-no
  12805. -->
  12806. (O1978 ^name predict-no +)
  12807. (S1 ^operator O1978 +)
  12808. Retracting propose*predict-yes
  12809. -->
  12810. (O1977 ^name predict-yes +)
  12811. (S1 ^operator O1977 +)
  12812. Retracting elaborate*reward*based*on*reward
  12813. -->
  12814. (R992 ^value 1 +)
  12815. (R1 ^reward R992 +)
  12816. Retracting elaborate*copy-dir-to-output-link
  12817. -->
  12818. (I3 ^dir R +)
  12819. Retracting rl*prefer*rvt*predict-no*H0*4*H1*17
  12820. -->
  12821. (S1 ^operator O1978 = 0.8730229691411198)
  12822. Retracting rl*prefer*rvt*predict-no*H0*4
  12823. -->
  12824. (S1 ^operator O1978 = 0.1269768271235827)
  12825. Retracting rl*prefer*rvt*predict-yes*H0*3*H1*18
  12826. -->
  12827. (S1 ^operator O1977 = 0.2696941111808541)
  12828. Retracting rl*prefer*rvt*predict-yes*H0*3
  12829. -->
  12830. (S1 ^operator O1977 = 0.3829290045611482)
  12831. =>WM: (13907: S1 ^operator O1980 +)
  12832. =>WM: (13906: S1 ^operator O1979 +)
  12833. =>WM: (13905: O1980 ^name predict-no)
  12834. =>WM: (13904: O1979 ^name predict-yes)
  12835. =>WM: (13903: R993 ^value 1)
  12836. =>WM: (13902: R1 ^reward R993)
  12837. <=WM: (13893: S1 ^operator O1977 +)
  12838. <=WM: (13894: S1 ^operator O1978 +)
  12839. <=WM: (13895: S1 ^operator O1978)
  12840. <=WM: (13889: R1 ^reward R992)
  12841. <=WM: (13892: O1978 ^name predict-no)
  12842. <=WM: (13891: O1977 ^name predict-yes)
  12843. <=WM: (13890: R992 ^value 1)
  12844. --- Inner Elaboration Phase, active level 1 (S1) ---
  12845. Firing prefer*rvt*predict-yes*H0
  12846. -->
  12847. Firing rl*prefer*rvt*predict-yes*H0*3
  12848. -->
  12849. (S1 ^operator O1979 = 0.3829290045611482)
  12850. Firing prefer*rvt*predict-yes*H0*3*H1
  12851. -->
  12852. Firing rl*prefer*rvt*predict-yes*H0*3*H1*18
  12853. -->
  12854. (S1 ^operator O1979 = 0.2696941111808541)
  12855. Firing prefer*rvt*predict-no*H0
  12856. -->
  12857. Firing rl*prefer*rvt*predict-no*H0*4
  12858. -->
  12859. (S1 ^operator O1980 = 0.1269768271235827)
  12860. Firing prefer*rvt*predict-no*H0*4*H1
  12861. -->
  12862. Firing rl*prefer*rvt*predict-no*H0*4*H1*17
  12863. -->
  12864. (S1 ^operator O1980 = 0.8730229691411198)
  12865. inner elaboration loop at bottom goal.
  12866. Retracting rl*prefer*rvt*predict-no*H0*4
  12867. -->
  12868. (S1 ^operator O1978 = 0.1269768271235827)
  12869. Retracting rl*prefer*rvt*predict-no*H0*4*H1*17
  12870. -->
  12871. (S1 ^operator O1978 = 0.8730229691411198)
  12872. Retracting rl*prefer*rvt*predict-yes*H0*3
  12873. -->
  12874. (S1 ^operator O1977 = 0.3829290045611482)
  12875. Retracting rl*prefer*rvt*predict-yes*H0*3*H1*18
  12876. -->
  12877. (S1 ^operator O1977 = 0.2696941111808541)
  12878. --- END Proposal Phase ---
  12879. --- Decision Phase ---
  12880. RL update rl*prefer*rvt*predict-no*H0*4 0.814714 -0.687737 0.126977 -> 0.814714 -0.687737 0.126977(R,m,v=1,0.949153,0.0485362)
  12881. RL update rl*prefer*rvt*predict-no*H0*4*H1*17 0.185286 0.687737 0.873023 -> 0.185286 0.687737 0.873023(R,m,v=1,1,0)
  12882. =>WM: (13908: S1 ^operator O1980)
  12883. 990: O: O1980 (predict-no)
  12884. --- END Decision Phase ---
  12885. --- Application Phase ---
  12886. --- Firing Productions (PE) For State At Depth 1 ---
  12887. --- Inner Elaboration Phase, active level 1 (S1) ---
  12888. Firing apply*operator
  12889. -->
  12890. (I3 ^predict-no N990 + :O )
  12891. Firing apply*operator*complete
  12892. -->
  12893. (I3 ^predict-no N989 - :O )
  12894. inner elaboration loop at bottom goal.
  12895. --- Change Working Memory (PE) ---
  12896. =>WM: (13909: I3 ^predict-no N990)
  12897. <=WM: (13897: N989 ^status complete)
  12898. <=WM: (13896: I3 ^predict-no N989)
  12899. --- Firing Productions (IE) For State At Depth 1 ---
  12900. --- Inner Elaboration Phase, active level 1 (S1) ---
  12901. Firing monitor*world
  12902. -->
  12903. I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
  12904. --- Change Working Memory (IE) ---
  12905. --- END Application Phase ---
  12906. --- Output Phase ---
  12907. ENV: Agent did: predict-no for direction R in state State-B
  12908. In State-B moving R
  12909. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  12910. predict error 0
  12911. dir: dir isU
  12912. --- END Output Phase ---
  12913. -/--- Input Phase ---
  12914. =>WM: (13913: I2 ^dir U)
  12915. =>WM: (13912: I2 ^reward 1)
  12916. =>WM: (13911: I2 ^see 0)
  12917. =>WM: (13910: N990 ^status complete)
  12918. <=WM: (13900: I2 ^dir R)
  12919. <=WM: (13899: I2 ^reward 1)
  12920. <=WM: (13898: I2 ^see 0)
  12921. =>WM: (13914: I2 ^level-1 R0-root)
  12922. <=WM: (13901: I2 ^level-1 R0-root)
  12923. --- END Input Phase ---
  12924. --- Proposal Phase ---
  12925. --- Inner Elaboration Phase, active level 1 (S1) ---
  12926. Firing elaborate*copy-see-to-output-link
  12927. -->
  12928. (I3 ^see 0 +)
  12929. Firing elaborate*reward*based*on*reward
  12930. -->
  12931. (R994 ^value 1 +)
  12932. (R1 ^reward R994 +)
  12933. Firing propose*predict-yes
  12934. -->
  12935. (O1981 ^name predict-yes +)
  12936. (S1 ^operator O1981 +)
  12937. Firing propose*predict-no
  12938. -->
  12939. (O1982 ^name predict-no +)
  12940. (S1 ^operator O1982 +)
  12941. Firing rl*prefer*rvt*predict-no*H0*6
  12942. -->
  12943. (S1 ^operator O1980 = 0.9999999999999999)
  12944. Firing rl*prefer*rvt*predict-yes*H0*5
  12945. -->
  12946. (S1 ^operator O1979 = 0.)
  12947. Firing prefer*rvt*predict-yes*H0
  12948. -->
  12949. Firing prefer*rvt*predict-no*H0
  12950. -->
  12951. Firing elaborate*copy-dir-to-output-link
  12952. -->
  12953. (I3 ^dir U +)
  12954. inner elaboration loop at bottom goal.
  12955. Retracting elaborate*copy-see-to-output-link
  12956. -->
  12957. (I3 ^see 0 +)
  12958. Retracting propose*predict-no
  12959. -->
  12960. (O1980 ^name predict-no +)
  12961. (S1 ^operator O1980 +)
  12962. Retracting propose*predict-yes
  12963. -->
  12964. (O1979 ^name predict-yes +)
  12965. (S1 ^operator O1979 +)
  12966. Retracting elaborate*reward*based*on*reward
  12967. -->
  12968. (R993 ^value 1 +)
  12969. (R1 ^reward R993 +)
  12970. Retracting elaborate*copy-dir-to-output-link
  12971. -->
  12972. (I3 ^dir R +)
  12973. Retracting rl*prefer*rvt*predict-no*H0*4*H1*17
  12974. -->
  12975. (S1 ^operator O1980 = 0.8730229997014144)
  12976. Retracting rl*prefer*rvt*predict-no*H0*4
  12977. -->
  12978. (S1 ^operator O1980 = 0.1269768576838773)
  12979. Retracting rl*prefer*rvt*predict-yes*H0*3*H1*18
  12980. -->
  12981. (S1 ^operator O1979 = 0.2696941111808541)
  12982. Retracting rl*prefer*rvt*predict-yes*H0*3
  12983. -->
  12984. (S1 ^operator O1979 = 0.3829290045611482)
  12985. =>WM: (13921: S1 ^operator O1982 +)
  12986. =>WM: (13920: S1 ^operator O1981 +)
  12987. =>WM: (13919: I3 ^dir U)
  12988. =>WM: (13918: O1982 ^name predict-no)
  12989. =>WM: (13917: O1981 ^name predict-yes)
  12990. =>WM: (13916: R994 ^value 1)
  12991. =>WM: (13915: R1 ^reward R994)
  12992. <=WM: (13906: S1 ^operator O1979 +)
  12993. <=WM: (13907: S1 ^operator O1980 +)
  12994. <=WM: (13908: S1 ^operator O1980)
  12995. <=WM: (13853: I3 ^dir R)
  12996. <=WM: (13902: R1 ^reward R993)
  12997. <=WM: (13905: O1980 ^name predict-no)
  12998. <=WM: (13904: O1979 ^name predict-yes)
  12999. <=WM: (13903: R993 ^value 1)
  13000. --- Inner Elaboration Phase, active level 1 (S1) ---
  13001. Firing prefer*rvt*predict-yes*H0
  13002. -->
  13003. Firing rl*prefer*rvt*predict-yes*H0*5
  13004. -->
  13005. (S1 ^operator O1981 = 0.)
  13006. Firing prefer*rvt*predict-no*H0
  13007. -->
  13008. Firing rl*prefer*rvt*predict-no*H0*6
  13009. -->
  13010. (S1 ^operator O1982 = 0.9999999999999999)
  13011. inner elaboration loop at bottom goal.
  13012. Retracting rl*prefer*rvt*predict-no*H0*6
  13013. -->
  13014. (S1 ^operator O1980 = 0.9999999999999999)
  13015. Retracting rl*prefer*rvt*predict-yes*H0*5
  13016. -->
  13017. (S1 ^operator O1979 = 0.)
  13018. --- END Proposal Phase ---
  13019. --- Decision Phase ---
  13020. RL update rl*prefer*rvt*predict-no*H0*4 0.814714 -0.687737 0.126977 -> 0.814714 -0.687737 0.126977(R,m,v=1,0.949438,0.0482765)
  13021. RL update rl*prefer*rvt*predict-no*H0*4*H1*17 0.185286 0.687737 0.873023 -> 0.185286 0.687737 0.873023(R,m,v=1,1,0)
  13022. =>WM: (13922: S1 ^operator O1982)
  13023. 991: O: O1982 (predict-no)
  13024. --- END Decision Phase ---
  13025. --- Application Phase ---
  13026. --- Firing Productions (PE) For State At Depth 1 ---
  13027. --- Inner Elaboration Phase, active level 1 (S1) ---
  13028. Firing apply*operator
  13029. -->
  13030. (I3 ^predict-no N991 + :O )
  13031. Firing apply*operator*complete
  13032. -->
  13033. (I3 ^predict-no N990 - :O )
  13034. inner elaboration loop at bottom goal.
  13035. --- Change Working Memory (PE) ---
  13036. =>WM: (13923: I3 ^predict-no N991)
  13037. <=WM: (13910: N990 ^status complete)
  13038. <=WM: (13909: I3 ^predict-no N990)
  13039. --- Firing Productions (IE) For State At Depth 1 ---
  13040. --- Inner Elaboration Phase, active level 1 (S1) ---
  13041. Firing monitor*world
  13042. -->
  13043. I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
  13044. --- Change Working Memory (IE) ---
  13045. --- END Application Phase ---
  13046. --- Output Phase ---
  13047. ENV: Agent did: predict-no for direction U in state State-B
  13048. In State-B moving U
  13049. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  13050. predict error 0
  13051. dir: dir isL
  13052. --- END Output Phase ---
  13053. |--- Input Phase ---
  13054. =>WM: (13927: I2 ^dir L)
  13055. =>WM: (13926: I2 ^reward 1)
  13056. =>WM: (13925: I2 ^see 0)
  13057. =>WM: (13924: N991 ^status complete)
  13058. <=WM: (13913: I2 ^dir U)
  13059. <=WM: (13912: I2 ^reward 1)
  13060. <=WM: (13911: I2 ^see 0)
  13061. =>WM: (13928: I2 ^level-1 R0-root)
  13062. <=WM: (13914: I2 ^level-1 R0-root)
  13063. --- END Input Phase ---
  13064. --- Proposal Phase ---
  13065. --- Inner Elaboration Phase, active level 1 (S1) ---
  13066. Firing rl*prefer*rvt*predict-yes*H0*1*H1*19
  13067. -->
  13068. (S1 ^operator O1981 = 0.4768833204434785)
  13069. Firing rl*prefer*rvt*predict-no*H0*2*H1*7
  13070. -->
  13071. (S1 ^operator O1982 = 0.1700769046561409)
  13072. Firing prefer*rvt*predict-no*H0*2*H1
  13073. -->
  13074. Firing prefer*rvt*predict-yes*H0*1*H1
  13075. -->
  13076. Firing elaborate*copy-see-to-output-link
  13077. -->
  13078. (I3 ^see 0 +)
  13079. Firing elaborate*reward*based*on*reward
  13080. -->
  13081. (R995 ^value 1 +)
  13082. (R1 ^reward R995 +)
  13083. Firing propose*predict-yes
  13084. -->
  13085. (O1983 ^name predict-yes +)
  13086. (S1 ^operator O1983 +)
  13087. Firing propose*predict-no
  13088. -->
  13089. (O1984 ^name predict-no +)
  13090. (S1 ^operator O1984 +)
  13091. Firing rl*prefer*rvt*predict-no*H0*2
  13092. -->
  13093. (S1 ^operator O1982 = 0.2550133828092577)
  13094. Firing rl*prefer*rvt*predict-yes*H0*1
  13095. -->
  13096. (S1 ^operator O1981 = 0.5231200982015054)
  13097. Firing prefer*rvt*predict-yes*H0
  13098. -->
  13099. Firing prefer*rvt*predict-no*H0
  13100. -->
  13101. Firing elaborate*copy-dir-to-output-link
  13102. -->
  13103. (I3 ^dir L +)
  13104. inner elaboration loop at bottom goal.
  13105. Retracting elaborate*copy-see-to-output-link
  13106. -->
  13107. (I3 ^see 0 +)
  13108. Retracting propose*predict-no
  13109. -->
  13110. (O1982 ^name predict-no +)
  13111. (S1 ^operator O1982 +)
  13112. Retracting propose*predict-yes
  13113. -->
  13114. (O1981 ^name predict-yes +)
  13115. (S1 ^operator O1981 +)
  13116. Retracting elaborate*reward*based*on*reward
  13117. -->
  13118. (R994 ^value 1 +)
  13119. (R1 ^reward R994 +)
  13120. Retracting elaborate*copy-dir-to-output-link
  13121. -->
  13122. (I3 ^dir U +)
  13123. Retracting rl*prefer*rvt*predict-no*H0*6
  13124. -->
  13125. (S1 ^operator O1982 = 0.9999999999999999)
  13126. Retracting rl*prefer*rvt*predict-yes*H0*5
  13127. -->
  13128. (S1 ^operator O1981 = 0.)
  13129. =>WM: (13935: S1 ^operator O1984 +)
  13130. =>WM: (13934: S1 ^operator O1983 +)
  13131. =>WM: (13933: I3 ^dir L)
  13132. =>WM: (13932: O1984 ^name predict-no)
  13133. =>WM: (13931: O1983 ^name predict-yes)
  13134. =>WM: (13930: R995 ^value 1)
  13135. =>WM: (13929: R1 ^reward R995)
  13136. <=WM: (13920: S1 ^operator O1981 +)
  13137. <=WM: (13921: S1 ^operator O1982 +)
  13138. <=WM: (13922: S1 ^operator O1982)
  13139. <=WM: (13919: I3 ^dir U)
  13140. <=WM: (13915: R1 ^reward R994)
  13141. <=WM: (13918: O1982 ^name predict-no)
  13142. <=WM: (13917: O1981 ^name predict-yes)
  13143. <=WM: (13916: R994 ^value 1)
  13144. --- Inner Elaboration Phase, active level 1 (S1) ---
  13145. Firing prefer*rvt*predict-yes*H0
  13146. -->
  13147. Firing rl*prefer*rvt*predict-yes*H0*1*H1*19
  13148. -->
  13149. (S1 ^operator O1983 = 0.4768833204434785)
  13150. Firing rl*prefer*rvt*predict-yes*H0*1
  13151. -->
  13152. (S1 ^operator O1983 = 0.5231200982015054)
  13153. Firing prefer*rvt*predict-yes*H0*1*H1
  13154. -->
  13155. Firing prefer*rvt*predict-no*H0
  13156. -->
  13157. Firing rl*prefer*rvt*predict-no*H0*2*H1*7
  13158. -->
  13159. (S1 ^operator O1984 = 0.1700769046561409)
  13160. Firing rl*prefer*rvt*predict-no*H0*2
  13161. -->
  13162. (S1 ^operator O1984 = 0.2550133828092577)
  13163. Firing prefer*rvt*predict-no*H0*2*H1
  13164. -->
  13165. inner elaboration loop at bottom goal.
  13166. Retracting rl*prefer*rvt*predict-no*H0*2
  13167. -->
  13168. (S1 ^operator O1982 = 0.2550133828092577)
  13169. Retracting rl*prefer*rvt*predict-no*H0*2*H1*7
  13170. -->
  13171. (S1 ^operator O1982 = 0.1700769046561409)
  13172. Retracting rl*prefer*rvt*predict-yes*H0*1
  13173. -->
  13174. (S1 ^operator O1981 = 0.5231200982015054)
  13175. Retracting rl*prefer*rvt*predict-yes*H0*1*H1*19
  13176. -->
  13177. (S1 ^operator O1981 = 0.4768833204434785)
  13178. --- END Proposal Phase ---
  13179. --- Decision Phase ---
  13180. RL update rl*prefer*rvt*predict-no*H0*6 1 0 1 -> 1 0 1(R,m,v=1,1,0)
  13181. =>WM: (13936: S1 ^operator O1983)
  13182. 992: O: O1983 (predict-yes)
  13183. --- END Decision Phase ---
  13184. --- Application Phase ---
  13185. --- Firing Productions (PE) For State At Depth 1 ---
  13186. --- Inner Elaboration Phase, active level 1 (S1) ---
  13187. Firing apply*operator
  13188. -->
  13189. (I3 ^predict-yes N992 + :O )
  13190. Firing apply*operator*complete
  13191. -->
  13192. (I3 ^predict-no N991 - :O )
  13193. inner elaboration loop at bottom goal.
  13194. --- Change Working Memory (PE) ---
  13195. =>WM: (13937: I3 ^predict-yes N992)
  13196. <=WM: (13924: N991 ^status complete)
  13197. <=WM: (13923: I3 ^predict-no N991)
  13198. --- Firing Productions (IE) For State At Depth 1 ---
  13199. --- Inner Elaboration Phase, active level 1 (S1) ---
  13200. Firing monitor*world
  13201. -->
  13202. I see 1 and I'm going to do: predict-yes inner elaboration loop at bottom goal.
  13203. --- Change Working Memory (IE) ---
  13204. --- END Application Phase ---
  13205. --- Output Phase ---
  13206. ENV: Agent did: predict-yes for direction L in state State-B
  13207. In State-B moving L
  13208. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  13209. predict error 0
  13210. dir: dir isR
  13211. --- END Output Phase ---
  13212. \-/--- Input Phase ---
  13213. =>WM: (13941: I2 ^dir R)
  13214. =>WM: (13940: I2 ^reward 1)
  13215. =>WM: (13939: I2 ^see 1)
  13216. =>WM: (13938: N992 ^status complete)
  13217. <=WM: (13927: I2 ^dir L)
  13218. <=WM: (13926: I2 ^reward 1)
  13219. <=WM: (13925: I2 ^see 0)
  13220. =>WM: (13942: I2 ^level-1 L1-root)
  13221. <=WM: (13928: I2 ^level-1 R0-root)
  13222. --- END Input Phase ---
  13223. --- Proposal Phase ---
  13224. --- Inner Elaboration Phase, active level 1 (S1) ---
  13225. Firing rl*prefer*rvt*predict-yes*H0*3*H1*9
  13226. -->
  13227. (S1 ^operator O1983 = 0.6170271815281626)
  13228. Firing rl*prefer*rvt*predict-no*H0*4*H1*8
  13229. -->
  13230. (S1 ^operator O1984 = 0.4901349546100854)
  13231. Firing prefer*rvt*predict-no*H0*4*H1
  13232. -->
  13233. Firing prefer*rvt*predict-yes*H0*3*H1
  13234. -->
  13235. Firing elaborate*copy-see-to-output-link
  13236. -->
  13237. (I3 ^see 1 +)
  13238. Firing elaborate*reward*based*on*reward
  13239. -->
  13240. (R996 ^value 1 +)
  13241. (R1 ^reward R996 +)
  13242. Firing propose*predict-yes
  13243. -->
  13244. (O1985 ^name predict-yes +)
  13245. (S1 ^operator O1985 +)
  13246. Firing propose*predict-no
  13247. -->
  13248. (O1986 ^name predict-no +)
  13249. (S1 ^operator O1986 +)
  13250. Firing rl*prefer*rvt*predict-no*H0*4
  13251. -->
  13252. (S1 ^operator O1984 = 0.1269768790760836)
  13253. Firing rl*prefer*rvt*predict-yes*H0*3
  13254. -->
  13255. (S1 ^operator O1983 = 0.3829290045611482)
  13256. Firing prefer*rvt*predict-yes*H0
  13257. -->
  13258. Firing prefer*rvt*predict-no*H0
  13259. -->
  13260. Firing elaborate*copy-dir-to-output-link
  13261. -->
  13262. (I3 ^dir R +)
  13263. inner elaboration loop at bottom goal.
  13264. Retracting elaborate*copy-see-to-output-link
  13265. -->
  13266. (I3 ^see 0 +)
  13267. Retracting propose*predict-no
  13268. -->
  13269. (O1984 ^name predict-no +)
  13270. (S1 ^operator O1984 +)
  13271. Retracting propose*predict-yes
  13272. -->
  13273. (O1983 ^name predict-yes +)
  13274. (S1 ^operator O1983 +)
  13275. Retracting elaborate*reward*based*on*reward
  13276. -->
  13277. (R995 ^value 1 +)
  13278. (R1 ^reward R995 +)
  13279. Retracting elaborate*copy-dir-to-output-link
  13280. -->
  13281. (I3 ^dir L +)
  13282. Retracting rl*prefer*rvt*predict-no*H0*2
  13283. -->
  13284. (S1 ^operator O1984 = 0.2550133828092577)
  13285. Retracting rl*prefer*rvt*predict-no*H0*2*H1*7
  13286. -->
  13287. (S1 ^operator O1984 = 0.1700769046561409)
  13288. Retracting rl*prefer*rvt*predict-yes*H0*1
  13289. -->
  13290. (S1 ^operator O1983 = 0.5231200982015054)
  13291. Retracting rl*prefer*rvt*predict-yes*H0*1*H1*19
  13292. -->
  13293. (S1 ^operator O1983 = 0.4768833204434785)
  13294. =>WM: (13950: S1 ^operator O1986 +)
  13295. =>WM: (13949: S1 ^operator O1985 +)
  13296. =>WM: (13948: I3 ^dir R)
  13297. =>WM: (13947: O1986 ^name predict-no)
  13298. =>WM: (13946: O1985 ^name predict-yes)
  13299. =>WM: (13945: R996 ^value 1)
  13300. =>WM: (13944: R1 ^reward R996)
  13301. =>WM: (13943: I3 ^see 1)
  13302. <=WM: (13934: S1 ^operator O1983 +)
  13303. <=WM: (13936: S1 ^operator O1983)
  13304. <=WM: (13935: S1 ^operator O1984 +)
  13305. <=WM: (13933: I3 ^dir L)
  13306. <=WM: (13929: R1 ^reward R995)
  13307. <=WM: (13835: I3 ^see 0)
  13308. <=WM: (13932: O1984 ^name predict-no)
  13309. <=WM: (13931: O1983 ^name predict-yes)
  13310. <=WM: (13930: R995 ^value 1)
  13311. --- Inner Elaboration Phase, active level 1 (S1) ---
  13312. Firing prefer*rvt*predict-yes*H0
  13313. -->
  13314. Firing rl*prefer*rvt*predict-yes*H0*3
  13315. -->
  13316. (S1 ^operator O1985 = 0.3829290045611482)
  13317. Firing prefer*rvt*predict-yes*H0*3*H1
  13318. -->
  13319. Firing rl*prefer*rvt*predict-yes*H0*3*H1*9
  13320. -->
  13321. (S1 ^operator O1985 = 0.6170271815281626)
  13322. Firing prefer*rvt*predict-no*H0
  13323. -->
  13324. Firing rl*prefer*rvt*predict-no*H0*4
  13325. -->
  13326. (S1 ^operator O1986 = 0.1269768790760836)
  13327. Firing prefer*rvt*predict-no*H0*4*H1
  13328. -->
  13329. Firing rl*prefer*rvt*predict-no*H0*4*H1*8
  13330. -->
  13331. (S1 ^operator O1986 = 0.4901349546100854)
  13332. inner elaboration loop at bottom goal.
  13333. Retracting rl*prefer*rvt*predict-no*H0*4
  13334. -->
  13335. (S1 ^operator O1984 = 0.1269768790760836)
  13336. Retracting rl*prefer*rvt*predict-no*H0*4*H1*8
  13337. -->
  13338. (S1 ^operator O1984 = 0.4901349546100854)
  13339. Retracting rl*prefer*rvt*predict-yes*H0*3
  13340. -->
  13341. (S1 ^operator O1983 = 0.3829290045611482)
  13342. Retracting rl*prefer*rvt*predict-yes*H0*3*H1*9
  13343. -->
  13344. (S1 ^operator O1983 = 0.6170271815281626)
  13345. --- END Proposal Phase ---
  13346. --- Decision Phase ---
  13347. RL update rl*prefer*rvt*predict-yes*H0*1 0.72796 -0.20484 0.52312 -> 0.727959 -0.20484 0.52312(R,m,v=1,0.978723,0.0209726)
  13348. RL update rl*prefer*rvt*predict-yes*H0*1*H1*19 0.272045 0.204839 0.476883 -> 0.272044 0.204839 0.476883(R,m,v=1,1,0)
  13349. =>WM: (13951: S1 ^operator O1985)
  13350. 993: O: O1985 (predict-yes)
  13351. --- END Decision Phase ---
  13352. --- Application Phase ---
  13353. --- Firing Productions (PE) For State At Depth 1 ---
  13354. --- Inner Elaboration Phase, active level 1 (S1) ---
  13355. Firing apply*operator
  13356. -->
  13357. (I3 ^predict-yes N993 + :O )
  13358. Firing apply*operator*complete
  13359. -->
  13360. (I3 ^predict-yes N992 - :O )
  13361. inner elaboration loop at bottom goal.
  13362. --- Change Working Memory (PE) ---
  13363. =>WM: (13952: I3 ^predict-yes N993)
  13364. <=WM: (13938: N992 ^status complete)
  13365. <=WM: (13937: I3 ^predict-yes N992)
  13366. --- Firing Productions (IE) For State At Depth 1 ---
  13367. --- Inner Elaboration Phase, active level 1 (S1) ---
  13368. Firing monitor*world
  13369. -->
  13370. I see 1 and I'm going to do: predict-yes inner elaboration loop at bottom goal.
  13371. --- Change Working Memory (IE) ---
  13372. --- END Application Phase ---
  13373. --- Output Phase ---
  13374. ENV: Agent did: predict-yes for direction R in state State-A
  13375. In State-A moving R
  13376. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  13377. predict error 0
  13378. dir: dir isU
  13379. --- END Output Phase ---
  13380. |\---- Input Phase ---
  13381. =>WM: (13956: I2 ^dir U)
  13382. =>WM: (13955: I2 ^reward 1)
  13383. =>WM: (13954: I2 ^see 1)
  13384. =>WM: (13953: N993 ^status complete)
  13385. <=WM: (13941: I2 ^dir R)
  13386. <=WM: (13940: I2 ^reward 1)
  13387. <=WM: (13939: I2 ^see 1)
  13388. =>WM: (13957: I2 ^level-1 R1-root)
  13389. <=WM: (13942: I2 ^level-1 L1-root)
  13390. --- END Input Phase ---
  13391. --- Proposal Phase ---
  13392. --- Inner Elaboration Phase, active level 1 (S1) ---
  13393. Firing elaborate*copy-see-to-output-link
  13394. -->
  13395. (I3 ^see 1 +)
  13396. Firing elaborate*reward*based*on*reward
  13397. -->
  13398. (R997 ^value 1 +)
  13399. (R1 ^reward R997 +)
  13400. Firing propose*predict-yes
  13401. -->
  13402. (O1987 ^name predict-yes +)
  13403. (S1 ^operator O1987 +)
  13404. Firing propose*predict-no
  13405. -->
  13406. (O1988 ^name predict-no +)
  13407. (S1 ^operator O1988 +)
  13408. Firing rl*prefer*rvt*predict-no*H0*6
  13409. -->
  13410. (S1 ^operator O1986 = 0.9999999999999999)
  13411. Firing rl*prefer*rvt*predict-yes*H0*5
  13412. -->
  13413. (S1 ^operator O1985 = 0.)
  13414. Firing prefer*rvt*predict-yes*H0
  13415. -->
  13416. Firing prefer*rvt*predict-no*H0
  13417. -->
  13418. Firing elaborate*copy-dir-to-output-link
  13419. -->
  13420. (I3 ^dir U +)
  13421. inner elaboration loop at bottom goal.
  13422. Retracting elaborate*copy-see-to-output-link
  13423. -->
  13424. (I3 ^see 1 +)
  13425. Retracting propose*predict-no
  13426. -->
  13427. (O1986 ^name predict-no +)
  13428. (S1 ^operator O1986 +)
  13429. Retracting propose*predict-yes
  13430. -->
  13431. (O1985 ^name predict-yes +)
  13432. (S1 ^operator O1985 +)
  13433. Retracting elaborate*reward*based*on*reward
  13434. -->
  13435. (R996 ^value 1 +)
  13436. (R1 ^reward R996 +)
  13437. Retracting elaborate*copy-dir-to-output-link
  13438. -->
  13439. (I3 ^dir R +)
  13440. Retracting rl*prefer*rvt*predict-no*H0*4*H1*8
  13441. -->
  13442. (S1 ^operator O1986 = 0.4901349546100854)
  13443. Retracting rl*prefer*rvt*predict-no*H0*4
  13444. -->
  13445. (S1 ^operator O1986 = 0.1269768790760836)
  13446. Retracting rl*prefer*rvt*predict-yes*H0*3*H1*9
  13447. -->
  13448. (S1 ^operator O1985 = 0.6170271815281626)
  13449. Retracting rl*prefer*rvt*predict-yes*H0*3
  13450. -->
  13451. (S1 ^operator O1985 = 0.3829290045611482)
  13452. =>WM: (13964: S1 ^operator O1988 +)
  13453. =>WM: (13963: S1 ^operator O1987 +)
  13454. =>WM: (13962: I3 ^dir U)
  13455. =>WM: (13961: O1988 ^name predict-no)
  13456. =>WM: (13960: O1987 ^name predict-yes)
  13457. =>WM: (13959: R997 ^value 1)
  13458. =>WM: (13958: R1 ^reward R997)
  13459. <=WM: (13949: S1 ^operator O1985 +)
  13460. <=WM: (13951: S1 ^operator O1985)
  13461. <=WM: (13950: S1 ^operator O1986 +)
  13462. <=WM: (13948: I3 ^dir R)
  13463. <=WM: (13944: R1 ^reward R996)
  13464. <=WM: (13947: O1986 ^name predict-no)
  13465. <=WM: (13946: O1985 ^name predict-yes)
  13466. <=WM: (13945: R996 ^value 1)
  13467. --- Inner Elaboration Phase, active level 1 (S1) ---
  13468. Firing prefer*rvt*predict-yes*H0
  13469. -->
  13470. Firing rl*prefer*rvt*predict-yes*H0*5
  13471. -->
  13472. (S1 ^operator O1987 = 0.)
  13473. Firing prefer*rvt*predict-no*H0
  13474. -->
  13475. Firing rl*prefer*rvt*predict-no*H0*6
  13476. -->
  13477. (S1 ^operator O1988 = 0.9999999999999999)
  13478. inner elaboration loop at bottom goal.
  13479. Retracting rl*prefer*rvt*predict-no*H0*6
  13480. -->
  13481. (S1 ^operator O1986 = 0.9999999999999999)
  13482. Retracting rl*prefer*rvt*predict-yes*H0*5
  13483. -->
  13484. (S1 ^operator O1985 = 0.)
  13485. --- END Proposal Phase ---
  13486. --- Decision Phase ---
  13487. RL update rl*prefer*rvt*predict-yes*H0*3 0.673123 -0.290194 0.382929 -> 0.673129 -0.290194 0.382936(R,m,v=1,0.960526,0.0381666)
  13488. RL update rl*prefer*rvt*predict-yes*H0*3*H1*9 0.326837 0.29019 0.617027 -> 0.326843 0.290191 0.617034(R,m,v=1,1,0)
  13489. =>WM: (13965: S1 ^operator O1988)
  13490. 994: O: O1988 (predict-no)
  13491. --- END Decision Phase ---
  13492. --- Application Phase ---
  13493. --- Firing Productions (PE) For State At Depth 1 ---
  13494. --- Inner Elaboration Phase, active level 1 (S1) ---
  13495. Firing apply*operator
  13496. -->
  13497. (I3 ^predict-no N994 + :O )
  13498. Firing apply*operator*complete
  13499. -->
  13500. (I3 ^predict-yes N993 - :O )
  13501. inner elaboration loop at bottom goal.
  13502. --- Change Working Memory (PE) ---
  13503. =>WM: (13966: I3 ^predict-no N994)
  13504. <=WM: (13953: N993 ^status complete)
  13505. <=WM: (13952: I3 ^predict-yes N993)
  13506. --- Firing Productions (IE) For State At Depth 1 ---
  13507. --- Inner Elaboration Phase, active level 1 (S1) ---
  13508. Firing monitor*world
  13509. -->
  13510. I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
  13511. --- Change Working Memory (IE) ---
  13512. --- END Application Phase ---
  13513. --- Output Phase ---
  13514. ENV: Agent did: predict-no for direction U in state State-B
  13515. In State-B moving U
  13516. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  13517. predict error 0
  13518. dir: dir isU
  13519. --- END Output Phase ---
  13520. /|\--- Input Phase ---
  13521. =>WM: (13970: I2 ^dir U)
  13522. =>WM: (13969: I2 ^reward 1)
  13523. =>WM: (13968: I2 ^see 0)
  13524. =>WM: (13967: N994 ^status complete)
  13525. <=WM: (13956: I2 ^dir U)
  13526. <=WM: (13955: I2 ^reward 1)
  13527. <=WM: (13954: I2 ^see 1)
  13528. =>WM: (13971: I2 ^level-1 R1-root)
  13529. <=WM: (13957: I2 ^level-1 R1-root)
  13530. --- END Input Phase ---
  13531. --- Proposal Phase ---
  13532. --- Inner Elaboration Phase, active level 1 (S1) ---
  13533. Firing elaborate*copy-see-to-output-link
  13534. -->
  13535. (I3 ^see 0 +)
  13536. Firing elaborate*reward*based*on*reward
  13537. -->
  13538. (R998 ^value 1 +)
  13539. (R1 ^reward R998 +)
  13540. Firing propose*predict-yes
  13541. -->
  13542. (O1989 ^name predict-yes +)
  13543. (S1 ^operator O1989 +)
  13544. Firing propose*predict-no
  13545. -->
  13546. (O1990 ^name predict-no +)
  13547. (S1 ^operator O1990 +)
  13548. Firing rl*prefer*rvt*predict-no*H0*6
  13549. -->
  13550. (S1 ^operator O1988 = 0.9999999999999999)
  13551. Firing rl*prefer*rvt*predict-yes*H0*5
  13552. -->
  13553. (S1 ^operator O1987 = 0.)
  13554. Firing prefer*rvt*predict-yes*H0
  13555. -->
  13556. Firing prefer*rvt*predict-no*H0
  13557. -->
  13558. Firing elaborate*copy-dir-to-output-link
  13559. -->
  13560. (I3 ^dir U +)
  13561. inner elaboration loop at bottom goal.
  13562. Retracting elaborate*copy-see-to-output-link
  13563. -->
  13564. (I3 ^see 1 +)
  13565. Retracting propose*predict-no
  13566. -->
  13567. (O1988 ^name predict-no +)
  13568. (S1 ^operator O1988 +)
  13569. Retracting propose*predict-yes
  13570. -->
  13571. (O1987 ^name predict-yes +)
  13572. (S1 ^operator O1987 +)
  13573. Retracting elaborate*reward*based*on*reward
  13574. -->
  13575. (R997 ^value 1 +)
  13576. (R1 ^reward R997 +)
  13577. Retracting elaborate*copy-dir-to-output-link
  13578. -->
  13579. (I3 ^dir U +)
  13580. Retracting rl*prefer*rvt*predict-no*H0*6
  13581. -->
  13582. (S1 ^operator O1988 = 0.9999999999999999)
  13583. Retracting rl*prefer*rvt*predict-yes*H0*5
  13584. -->
  13585. (S1 ^operator O1987 = 0.)
  13586. =>WM: (13978: S1 ^operator O1990 +)
  13587. =>WM: (13977: S1 ^operator O1989 +)
  13588. =>WM: (13976: O1990 ^name predict-no)
  13589. =>WM: (13975: O1989 ^name predict-yes)
  13590. =>WM: (13974: R998 ^value 1)
  13591. =>WM: (13973: R1 ^reward R998)
  13592. =>WM: (13972: I3 ^see 0)
  13593. <=WM: (13963: S1 ^operator O1987 +)
  13594. <=WM: (13964: S1 ^operator O1988 +)
  13595. <=WM: (13965: S1 ^operator O1988)
  13596. <=WM: (13958: R1 ^reward R997)
  13597. <=WM: (13943: I3 ^see 1)
  13598. <=WM: (13961: O1988 ^name predict-no)
  13599. <=WM: (13960: O1987 ^name predict-yes)
  13600. <=WM: (13959: R997 ^value 1)
  13601. --- Inner Elaboration Phase, active level 1 (S1) ---
  13602. Firing prefer*rvt*predict-yes*H0
  13603. -->
  13604. Firing rl*prefer*rvt*predict-yes*H0*5
  13605. -->
  13606. (S1 ^operator O1989 = 0.)
  13607. Firing prefer*rvt*predict-no*H0
  13608. -->
  13609. Firing rl*prefer*rvt*predict-no*H0*6
  13610. -->
  13611. (S1 ^operator O1990 = 0.9999999999999999)
  13612. inner elaboration loop at bottom goal.
  13613. Retracting rl*prefer*rvt*predict-no*H0*6
  13614. -->
  13615. (S1 ^operator O1988 = 0.9999999999999999)
  13616. Retracting rl*prefer*rvt*predict-yes*H0*5
  13617. -->
  13618. (S1 ^operator O1987 = 0.)
  13619. --- END Proposal Phase ---
  13620. --- Decision Phase ---
  13621. RL update rl*prefer*rvt*predict-no*H0*6 1 0 1 -> 1 0 1(R,m,v=1,1,0)
  13622. =>WM: (13979: S1 ^operator O1990)
  13623. 995: O: O1990 (predict-no)
  13624. --- END Decision Phase ---
  13625. --- Application Phase ---
  13626. --- Firing Productions (PE) For State At Depth 1 ---
  13627. --- Inner Elaboration Phase, active level 1 (S1) ---
  13628. Firing apply*operator
  13629. -->
  13630. (I3 ^predict-no N995 + :O )
  13631. Firing apply*operator*complete
  13632. -->
  13633. (I3 ^predict-no N994 - :O )
  13634. inner elaboration loop at bottom goal.
  13635. --- Change Working Memory (PE) ---
  13636. =>WM: (13980: I3 ^predict-no N995)
  13637. <=WM: (13967: N994 ^status complete)
  13638. <=WM: (13966: I3 ^predict-no N994)
  13639. --- Firing Productions (IE) For State At Depth 1 ---
  13640. --- Inner Elaboration Phase, active level 1 (S1) ---
  13641. Firing monitor*world
  13642. -->
  13643. I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
  13644. --- Change Working Memory (IE) ---
  13645. --- END Application Phase ---
  13646. --- Output Phase ---
  13647. ENV: Agent did: predict-no for direction U in state State-B
  13648. In State-B moving U
  13649. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  13650. predict error 0
  13651. dir: dir isL
  13652. --- END Output Phase ---
  13653. -/--- Input Phase ---
  13654. =>WM: (13984: I2 ^dir L)
  13655. =>WM: (13983: I2 ^reward 1)
  13656. =>WM: (13982: I2 ^see 0)
  13657. =>WM: (13981: N995 ^status complete)
  13658. <=WM: (13970: I2 ^dir U)
  13659. <=WM: (13969: I2 ^reward 1)
  13660. <=WM: (13968: I2 ^see 0)
  13661. =>WM: (13985: I2 ^level-1 R1-root)
  13662. <=WM: (13971: I2 ^level-1 R1-root)
  13663. --- END Input Phase ---
  13664. --- Proposal Phase ---
  13665. --- Inner Elaboration Phase, active level 1 (S1) ---
  13666. Firing rl*prefer*rvt*predict-yes*H0*1*H1*22
  13667. -->
  13668. (S1 ^operator O1989 = 0.4768774843644236)
  13669. Firing rl*prefer*rvt*predict-no*H0*2*H1*10
  13670. -->
  13671. (S1 ^operator O1990 = -0.01194930198035649)
  13672. Firing prefer*rvt*predict-no*H0*2*H1
  13673. -->
  13674. Firing prefer*rvt*predict-yes*H0*1*H1
  13675. -->
  13676. Firing elaborate*copy-see-to-output-link
  13677. -->
  13678. (I3 ^see 0 +)
  13679. Firing elaborate*reward*based*on*reward
  13680. -->
  13681. (R999 ^value 1 +)
  13682. (R1 ^reward R999 +)
  13683. Firing propose*predict-yes
  13684. -->
  13685. (O1991 ^name predict-yes +)
  13686. (S1 ^operator O1991 +)
  13687. Firing propose*predict-no
  13688. -->
  13689. (O1992 ^name predict-no +)
  13690. (S1 ^operator O1992 +)
  13691. Firing rl*prefer*rvt*predict-no*H0*2
  13692. -->
  13693. (S1 ^operator O1990 = 0.2550133828092577)
  13694. Firing rl*prefer*rvt*predict-yes*H0*1
  13695. -->
  13696. (S1 ^operator O1989 = 0.5231195854047579)
  13697. Firing prefer*rvt*predict-yes*H0
  13698. -->
  13699. Firing prefer*rvt*predict-no*H0
  13700. -->
  13701. Firing elaborate*copy-dir-to-output-link
  13702. -->
  13703. (I3 ^dir L +)
  13704. inner elaboration loop at bottom goal.
  13705. Retracting elaborate*copy-see-to-output-link
  13706. -->
  13707. (I3 ^see 0 +)
  13708. Retracting propose*predict-no
  13709. -->
  13710. (O1990 ^name predict-no +)
  13711. (S1 ^operator O1990 +)
  13712. Retracting propose*predict-yes
  13713. -->
  13714. (O1989 ^name predict-yes +)
  13715. (S1 ^operator O1989 +)
  13716. Retracting elaborate*reward*based*on*reward
  13717. -->
  13718. (R998 ^value 1 +)
  13719. (R1 ^reward R998 +)
  13720. Retracting elaborate*copy-dir-to-output-link
  13721. -->
  13722. (I3 ^dir U +)
  13723. Retracting rl*prefer*rvt*predict-no*H0*6
  13724. -->
  13725. (S1 ^operator O1990 = 0.9999999999999999)
  13726. Retracting rl*prefer*rvt*predict-yes*H0*5
  13727. -->
  13728. (S1 ^operator O1989 = 0.)
  13729. =>WM: (13992: S1 ^operator O1992 +)
  13730. =>WM: (13991: S1 ^operator O1991 +)
  13731. =>WM: (13990: I3 ^dir L)
  13732. =>WM: (13989: O1992 ^name predict-no)
  13733. =>WM: (13988: O1991 ^name predict-yes)
  13734. =>WM: (13987: R999 ^value 1)
  13735. =>WM: (13986: R1 ^reward R999)
  13736. <=WM: (13977: S1 ^operator O1989 +)
  13737. <=WM: (13978: S1 ^operator O1990 +)
  13738. <=WM: (13979: S1 ^operator O1990)
  13739. <=WM: (13962: I3 ^dir U)
  13740. <=WM: (13973: R1 ^reward R998)
  13741. <=WM: (13976: O1990 ^name predict-no)
  13742. <=WM: (13975: O1989 ^name predict-yes)
  13743. <=WM: (13974: R998 ^value 1)
  13744. --- Inner Elaboration Phase, active level 1 (S1) ---
  13745. Firing prefer*rvt*predict-yes*H0
  13746. -->
  13747. Firing rl*prefer*rvt*predict-yes*H0*1*H1*22
  13748. -->
  13749. (S1 ^operator O1991 = 0.4768774843644236)
  13750. Firing rl*prefer*rvt*predict-yes*H0*1
  13751. -->
  13752. (S1 ^operator O1991 = 0.5231195854047579)
  13753. Firing prefer*rvt*predict-yes*H0*1*H1
  13754. -->
  13755. Firing prefer*rvt*predict-no*H0
  13756. -->
  13757. Firing rl*prefer*rvt*predict-no*H0*2*H1*10
  13758. -->
  13759. (S1 ^operator O1992 = -0.01194930198035649)
  13760. Firing rl*prefer*rvt*predict-no*H0*2
  13761. -->
  13762. (S1 ^operator O1992 = 0.2550133828092577)
  13763. Firing prefer*rvt*predict-no*H0*2*H1
  13764. -->
  13765. inner elaboration loop at bottom goal.
  13766. Retracting rl*prefer*rvt*predict-no*H0*2
  13767. -->
  13768. (S1 ^operator O1990 = 0.2550133828092577)
  13769. Retracting rl*prefer*rvt*predict-no*H0*2*H1*10
  13770. -->
  13771. (S1 ^operator O1990 = -0.01194930198035649)
  13772. Retracting rl*prefer*rvt*predict-yes*H0*1
  13773. -->
  13774. (S1 ^operator O1989 = 0.5231195854047579)
  13775. Retracting rl*prefer*rvt*predict-yes*H0*1*H1*22
  13776. -->
  13777. (S1 ^operator O1989 = 0.4768774843644236)
  13778. --- END Proposal Phase ---
  13779. --- Decision Phase ---
  13780. RL update rl*prefer*rvt*predict-no*H0*6 1 0 1 -> 1 0 1(R,m,v=1,1,0)
  13781. =>WM: (13993: S1 ^operator O1991)
  13782. 996: O: O1991 (predict-yes)
  13783. --- END Decision Phase ---
  13784. --- Application Phase ---
  13785. --- Firing Productions (PE) For State At Depth 1 ---
  13786. --- Inner Elaboration Phase, active level 1 (S1) ---
  13787. Firing apply*operator
  13788. -->
  13789. (I3 ^predict-yes N996 + :O )
  13790. Firing apply*operator*complete
  13791. -->
  13792. (I3 ^predict-no N995 - :O )
  13793. inner elaboration loop at bottom goal.
  13794. --- Change Working Memory (PE) ---
  13795. =>WM: (13994: I3 ^predict-yes N996)
  13796. <=WM: (13981: N995 ^status complete)
  13797. <=WM: (13980: I3 ^predict-no N995)
  13798. --- Firing Productions (IE) For State At Depth 1 ---
  13799. --- Inner Elaboration Phase, active level 1 (S1) ---
  13800. Firing monitor*world
  13801. -->
  13802. I see 1 and I'm going to do: predict-yes inner elaboration loop at bottom goal.
  13803. --- Change Working Memory (IE) ---
  13804. --- END Application Phase ---
  13805. --- Output Phase ---
  13806. ENV: Agent did: predict-yes for direction L in state State-B
  13807. In State-B moving L
  13808. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  13809. predict error 0
  13810. dir: dir isU
  13811. --- END Output Phase ---
  13812. |\--- Input Phase ---
  13813. =>WM: (13998: I2 ^dir U)
  13814. =>WM: (13997: I2 ^reward 1)
  13815. =>WM: (13996: I2 ^see 1)
  13816. =>WM: (13995: N996 ^status complete)
  13817. <=WM: (13984: I2 ^dir L)
  13818. <=WM: (13983: I2 ^reward 1)
  13819. <=WM: (13982: I2 ^see 0)
  13820. =>WM: (13999: I2 ^level-1 L1-root)
  13821. <=WM: (13985: I2 ^level-1 R1-root)
  13822. --- END Input Phase ---
  13823. --- Proposal Phase ---
  13824. --- Inner Elaboration Phase, active level 1 (S1) ---
  13825. Firing elaborate*copy-see-to-output-link
  13826. -->
  13827. (I3 ^see 1 +)
  13828. Firing elaborate*reward*based*on*reward
  13829. -->
  13830. (R1000 ^value 1 +)
  13831. (R1 ^reward R1000 +)
  13832. Firing propose*predict-yes
  13833. -->
  13834. (O1993 ^name predict-yes +)
  13835. (S1 ^operator O1993 +)
  13836. Firing propose*predict-no
  13837. -->
  13838. (O1994 ^name predict-no +)
  13839. (S1 ^operator O1994 +)
  13840. Firing rl*prefer*rvt*predict-no*H0*6
  13841. -->
  13842. (S1 ^operator O1992 = 0.9999999999999999)
  13843. Firing rl*prefer*rvt*predict-yes*H0*5
  13844. -->
  13845. (S1 ^operator O1991 = 0.)
  13846. Firing prefer*rvt*predict-yes*H0
  13847. -->
  13848. Firing prefer*rvt*predict-no*H0
  13849. -->
  13850. Firing elaborate*copy-dir-to-output-link
  13851. -->
  13852. (I3 ^dir U +)
  13853. inner elaboration loop at bottom goal.
  13854. Retracting elaborate*copy-see-to-output-link
  13855. -->
  13856. (I3 ^see 0 +)
  13857. Retracting propose*predict-no
  13858. -->
  13859. (O1992 ^name predict-no +)
  13860. (S1 ^operator O1992 +)
  13861. Retracting propose*predict-yes
  13862. -->
  13863. (O1991 ^name predict-yes +)
  13864. (S1 ^operator O1991 +)
  13865. Retracting elaborate*reward*based*on*reward
  13866. -->
  13867. (R999 ^value 1 +)
  13868. (R1 ^reward R999 +)
  13869. Retracting elaborate*copy-dir-to-output-link
  13870. -->
  13871. (I3 ^dir L +)
  13872. Retracting rl*prefer*rvt*predict-no*H0*2
  13873. -->
  13874. (S1 ^operator O1992 = 0.2550133828092577)
  13875. Retracting rl*prefer*rvt*predict-no*H0*2*H1*10
  13876. -->
  13877. (S1 ^operator O1992 = -0.01194930198035649)
  13878. Retracting rl*prefer*rvt*predict-yes*H0*1
  13879. -->
  13880. (S1 ^operator O1991 = 0.5231195854047579)
  13881. Retracting rl*prefer*rvt*predict-yes*H0*1*H1*22
  13882. -->
  13883. (S1 ^operator O1991 = 0.4768774843644236)
  13884. =>WM: (14007: S1 ^operator O1994 +)
  13885. =>WM: (14006: S1 ^operator O1993 +)
  13886. =>WM: (14005: I3 ^dir U)
  13887. =>WM: (14004: O1994 ^name predict-no)
  13888. =>WM: (14003: O1993 ^name predict-yes)
  13889. =>WM: (14002: R1000 ^value 1)
  13890. =>WM: (14001: R1 ^reward R1000)
  13891. =>WM: (14000: I3 ^see 1)
  13892. <=WM: (13991: S1 ^operator O1991 +)
  13893. <=WM: (13993: S1 ^operator O1991)
  13894. <=WM: (13992: S1 ^operator O1992 +)
  13895. <=WM: (13990: I3 ^dir L)
  13896. <=WM: (13986: R1 ^reward R999)
  13897. <=WM: (13972: I3 ^see 0)
  13898. <=WM: (13989: O1992 ^name predict-no)
  13899. <=WM: (13988: O1991 ^name predict-yes)
  13900. <=WM: (13987: R999 ^value 1)
  13901. --- Inner Elaboration Phase, active level 1 (S1) ---
  13902. Firing prefer*rvt*predict-yes*H0
  13903. -->
  13904. Firing rl*prefer*rvt*predict-yes*H0*5
  13905. -->
  13906. (S1 ^operator O1993 = 0.)
  13907. Firing prefer*rvt*predict-no*H0
  13908. -->
  13909. Firing rl*prefer*rvt*predict-no*H0*6
  13910. -->
  13911. (S1 ^operator O1994 = 0.9999999999999999)
  13912. inner elaboration loop at bottom goal.
  13913. Retracting rl*prefer*rvt*predict-no*H0*6
  13914. -->
  13915. (S1 ^operator O1992 = 0.9999999999999999)
  13916. Retracting rl*prefer*rvt*predict-yes*H0*5
  13917. -->
  13918. (S1 ^operator O1991 = 0.)
  13919. --- END Proposal Phase ---
  13920. --- Decision Phase ---
  13921. RL update rl*prefer*rvt*predict-yes*H0*1 0.727959 -0.20484 0.52312 -> 0.72796 -0.20484 0.52312(R,m,v=1,0.978873,0.0208271)
  13922. RL update rl*prefer*rvt*predict-yes*H0*1*H1*22 0.272037 0.204841 0.476877 -> 0.272037 0.204841 0.476878(R,m,v=1,1,0)
  13923. =>WM: (14008: S1 ^operator O1994)
  13924. 997: O: O1994 (predict-no)
  13925. --- END Decision Phase ---
  13926. --- Application Phase ---
  13927. --- Firing Productions (PE) For State At Depth 1 ---
  13928. --- Inner Elaboration Phase, active level 1 (S1) ---
  13929. Firing apply*operator
  13930. -->
  13931. (I3 ^predict-no N997 + :O )
  13932. Firing apply*operator*complete
  13933. -->
  13934. (I3 ^predict-yes N996 - :O )
  13935. inner elaboration loop at bottom goal.
  13936. --- Change Working Memory (PE) ---
  13937. =>WM: (14009: I3 ^predict-no N997)
  13938. <=WM: (13995: N996 ^status complete)
  13939. <=WM: (13994: I3 ^predict-yes N996)
  13940. --- Firing Productions (IE) For State At Depth 1 ---
  13941. --- Inner Elaboration Phase, active level 1 (S1) ---
  13942. Firing monitor*world
  13943. -->
  13944. I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
  13945. --- Change Working Memory (IE) ---
  13946. --- END Application Phase ---
  13947. --- Output Phase ---
  13948. ENV: Agent did: predict-no for direction U in state State-A
  13949. In State-A moving U
  13950. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  13951. predict error 0
  13952. dir: dir isU
  13953. --- END Output Phase ---
  13954. -/|--- Input Phase ---
  13955. =>WM: (14013: I2 ^dir U)
  13956. =>WM: (14012: I2 ^reward 1)
  13957. =>WM: (14011: I2 ^see 0)
  13958. =>WM: (14010: N997 ^status complete)
  13959. <=WM: (13998: I2 ^dir U)
  13960. <=WM: (13997: I2 ^reward 1)
  13961. <=WM: (13996: I2 ^see 1)
  13962. =>WM: (14014: I2 ^level-1 L1-root)
  13963. <=WM: (13999: I2 ^level-1 L1-root)
  13964. --- END Input Phase ---
  13965. --- Proposal Phase ---
  13966. --- Inner Elaboration Phase, active level 1 (S1) ---
  13967. Firing elaborate*copy-see-to-output-link
  13968. -->
  13969. (I3 ^see 0 +)
  13970. Firing elaborate*reward*based*on*reward
  13971. -->
  13972. (R1001 ^value 1 +)
  13973. (R1 ^reward R1001 +)
  13974. Firing propose*predict-yes
  13975. -->
  13976. (O1995 ^name predict-yes +)
  13977. (S1 ^operator O1995 +)
  13978. Firing propose*predict-no
  13979. -->
  13980. (O1996 ^name predict-no +)
  13981. (S1 ^operator O1996 +)
  13982. Firing rl*prefer*rvt*predict-no*H0*6
  13983. -->
  13984. (S1 ^operator O1994 = 0.9999999999999999)
  13985. Firing rl*prefer*rvt*predict-yes*H0*5
  13986. -->
  13987. (S1 ^operator O1993 = 0.)
  13988. Firing prefer*rvt*predict-yes*H0
  13989. -->
  13990. Firing prefer*rvt*predict-no*H0
  13991. -->
  13992. Firing elaborate*copy-dir-to-output-link
  13993. -->
  13994. (I3 ^dir U +)
  13995. inner elaboration loop at bottom goal.
  13996. Retracting elaborate*copy-see-to-output-link
  13997. -->
  13998. (I3 ^see 1 +)
  13999. Retracting propose*predict-no
  14000. -->
  14001. (O1994 ^name predict-no +)
  14002. (S1 ^operator O1994 +)
  14003. Retracting propose*predict-yes
  14004. -->
  14005. (O1993 ^name predict-yes +)
  14006. (S1 ^operator O1993 +)
  14007. Retracting elaborate*reward*based*on*reward
  14008. -->
  14009. (R1000 ^value 1 +)
  14010. (R1 ^reward R1000 +)
  14011. Retracting elaborate*copy-dir-to-output-link
  14012. -->
  14013. (I3 ^dir U +)
  14014. Retracting rl*prefer*rvt*predict-no*H0*6
  14015. -->
  14016. (S1 ^operator O1994 = 0.9999999999999999)
  14017. Retracting rl*prefer*rvt*predict-yes*H0*5
  14018. -->
  14019. (S1 ^operator O1993 = 0.)
  14020. =>WM: (14021: S1 ^operator O1996 +)
  14021. =>WM: (14020: S1 ^operator O1995 +)
  14022. =>WM: (14019: O1996 ^name predict-no)
  14023. =>WM: (14018: O1995 ^name predict-yes)
  14024. =>WM: (14017: R1001 ^value 1)
  14025. =>WM: (14016: R1 ^reward R1001)
  14026. =>WM: (14015: I3 ^see 0)
  14027. <=WM: (14006: S1 ^operator O1993 +)
  14028. <=WM: (14007: S1 ^operator O1994 +)
  14029. <=WM: (14008: S1 ^operator O1994)
  14030. <=WM: (14001: R1 ^reward R1000)
  14031. <=WM: (14000: I3 ^see 1)
  14032. <=WM: (14004: O1994 ^name predict-no)
  14033. <=WM: (14003: O1993 ^name predict-yes)
  14034. <=WM: (14002: R1000 ^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*5
  14039. -->
  14040. (S1 ^operator O1995 = 0.)
  14041. Firing prefer*rvt*predict-no*H0
  14042. -->
  14043. Firing rl*prefer*rvt*predict-no*H0*6
  14044. -->
  14045. (S1 ^operator O1996 = 0.9999999999999999)
  14046. inner elaboration loop at bottom goal.
  14047. Retracting rl*prefer*rvt*predict-no*H0*6
  14048. -->
  14049. (S1 ^operator O1994 = 0.9999999999999999)
  14050. Retracting rl*prefer*rvt*predict-yes*H0*5
  14051. -->
  14052. (S1 ^operator O1993 = 0.)
  14053. --- END Proposal Phase ---
  14054. --- Decision Phase ---
  14055. RL update rl*prefer*rvt*predict-no*H0*6 1 0 1 -> 1 0 1(R,m,v=1,1,0)
  14056. =>WM: (14022: S1 ^operator O1996)
  14057. 998: O: O1996 (predict-no)
  14058. --- END Decision Phase ---
  14059. --- Application Phase ---
  14060. --- Firing Productions (PE) For State At Depth 1 ---
  14061. --- Inner Elaboration Phase, active level 1 (S1) ---
  14062. Firing apply*operator
  14063. -->
  14064. (I3 ^predict-no N998 + :O )
  14065. Firing apply*operator*complete
  14066. -->
  14067. (I3 ^predict-no N997 - :O )
  14068. inner elaboration loop at bottom goal.
  14069. --- Change Working Memory (PE) ---
  14070. =>WM: (14023: I3 ^predict-no N998)
  14071. <=WM: (14010: N997 ^status complete)
  14072. <=WM: (14009: I3 ^predict-no N997)
  14073. --- Firing Productions (IE) For State At Depth 1 ---
  14074. --- Inner Elaboration Phase, active level 1 (S1) ---
  14075. Firing monitor*world
  14076. -->
  14077. I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
  14078. --- Change Working Memory (IE) ---
  14079. --- END Application Phase ---
  14080. --- Output Phase ---
  14081. ENV: Agent did: predict-no for direction U in state State-A
  14082. In State-A moving U
  14083. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  14084. predict error 0
  14085. dir: dir isL
  14086. --- END Output Phase ---
  14087. \-/--- Input Phase ---
  14088. =>WM: (14027: I2 ^dir L)
  14089. =>WM: (14026: I2 ^reward 1)
  14090. =>WM: (14025: I2 ^see 0)
  14091. =>WM: (14024: N998 ^status complete)
  14092. <=WM: (14013: I2 ^dir U)
  14093. <=WM: (14012: I2 ^reward 1)
  14094. <=WM: (14011: I2 ^see 0)
  14095. =>WM: (14028: I2 ^level-1 L1-root)
  14096. <=WM: (14014: I2 ^level-1 L1-root)
  14097. --- END Input Phase ---
  14098. --- Proposal Phase ---
  14099. --- Inner Elaboration Phase, active level 1 (S1) ---
  14100. Firing rl*prefer*rvt*predict-yes*H0*1*H1*20
  14101. -->
  14102. (S1 ^operator O1995 = 0.1693592933936033)
  14103. Firing rl*prefer*rvt*predict-no*H0*2*H1*11
  14104. -->
  14105. (S1 ^operator O1996 = 0.7449864376794202)
  14106. Firing prefer*rvt*predict-no*H0*2*H1
  14107. -->
  14108. Firing prefer*rvt*predict-yes*H0*1*H1
  14109. -->
  14110. Firing elaborate*copy-see-to-output-link
  14111. -->
  14112. (I3 ^see 0 +)
  14113. Firing elaborate*reward*based*on*reward
  14114. -->
  14115. (R1002 ^value 1 +)
  14116. (R1 ^reward R1002 +)
  14117. Firing propose*predict-yes
  14118. -->
  14119. (O1997 ^name predict-yes +)
  14120. (S1 ^operator O1997 +)
  14121. Firing propose*predict-no
  14122. -->
  14123. (O1998 ^name predict-no +)
  14124. (S1 ^operator O1998 +)
  14125. Firing rl*prefer*rvt*predict-no*H0*2
  14126. -->
  14127. (S1 ^operator O1996 = 0.2550133828092577)
  14128. Firing rl*prefer*rvt*predict-yes*H0*1
  14129. -->
  14130. (S1 ^operator O1995 = 0.5231200249393807)
  14131. Firing prefer*rvt*predict-yes*H0
  14132. -->
  14133. Firing prefer*rvt*predict-no*H0
  14134. -->
  14135. Firing elaborate*copy-dir-to-output-link
  14136. -->
  14137. (I3 ^dir L +)
  14138. inner elaboration loop at bottom goal.
  14139. Retracting elaborate*copy-see-to-output-link
  14140. -->
  14141. (I3 ^see 0 +)
  14142. Retracting propose*predict-no
  14143. -->
  14144. (O1996 ^name predict-no +)
  14145. (S1 ^operator O1996 +)
  14146. Retracting propose*predict-yes
  14147. -->
  14148. (O1995 ^name predict-yes +)
  14149. (S1 ^operator O1995 +)
  14150. Retracting elaborate*reward*based*on*reward
  14151. -->
  14152. (R1001 ^value 1 +)
  14153. (R1 ^reward R1001 +)
  14154. Retracting elaborate*copy-dir-to-output-link
  14155. -->
  14156. (I3 ^dir U +)
  14157. Retracting rl*prefer*rvt*predict-no*H0*6
  14158. -->
  14159. (S1 ^operator O1996 = 0.9999999999999999)
  14160. Retracting rl*prefer*rvt*predict-yes*H0*5
  14161. -->
  14162. (S1 ^operator O1995 = 0.)
  14163. =>WM: (14035: S1 ^operator O1998 +)
  14164. =>WM: (14034: S1 ^operator O1997 +)
  14165. =>WM: (14033: I3 ^dir L)
  14166. =>WM: (14032: O1998 ^name predict-no)
  14167. =>WM: (14031: O1997 ^name predict-yes)
  14168. =>WM: (14030: R1002 ^value 1)
  14169. =>WM: (14029: R1 ^reward R1002)
  14170. <=WM: (14020: S1 ^operator O1995 +)
  14171. <=WM: (14021: S1 ^operator O1996 +)
  14172. <=WM: (14022: S1 ^operator O1996)
  14173. <=WM: (14005: I3 ^dir U)
  14174. <=WM: (14016: R1 ^reward R1001)
  14175. <=WM: (14019: O1996 ^name predict-no)
  14176. <=WM: (14018: O1995 ^name predict-yes)
  14177. <=WM: (14017: R1001 ^value 1)
  14178. --- Inner Elaboration Phase, active level 1 (S1) ---
  14179. Firing prefer*rvt*predict-yes*H0
  14180. -->
  14181. Firing rl*prefer*rvt*predict-yes*H0*1*H1*20
  14182. -->
  14183. (S1 ^operator O1997 = 0.1693592933936033)
  14184. Firing rl*prefer*rvt*predict-yes*H0*1
  14185. -->
  14186. (S1 ^operator O1997 = 0.5231200249393807)
  14187. Firing prefer*rvt*predict-yes*H0*1*H1
  14188. -->
  14189. Firing prefer*rvt*predict-no*H0
  14190. -->
  14191. Firing rl*prefer*rvt*predict-no*H0*2*H1*11
  14192. -->
  14193. (S1 ^operator O1998 = 0.7449864376794202)
  14194. Firing rl*prefer*rvt*predict-no*H0*2
  14195. -->
  14196. (S1 ^operator O1998 = 0.2550133828092577)
  14197. Firing prefer*rvt*predict-no*H0*2*H1
  14198. -->
  14199. inner elaboration loop at bottom goal.
  14200. Retracting rl*prefer*rvt*predict-no*H0*2
  14201. -->
  14202. (S1 ^operator O1996 = 0.2550133828092577)
  14203. Retracting rl*prefer*rvt*predict-no*H0*2*H1*11
  14204. -->
  14205. (S1 ^operator O1996 = 0.7449864376794202)
  14206. Retracting rl*prefer*rvt*predict-yes*H0*1
  14207. -->
  14208. (S1 ^operator O1995 = 0.5231200249393807)
  14209. Retracting rl*prefer*rvt*predict-yes*H0*1*H1*20
  14210. -->
  14211. (S1 ^operator O1995 = 0.1693592933936033)
  14212. --- END Proposal Phase ---
  14213. --- Decision Phase ---
  14214. RL update rl*prefer*rvt*predict-no*H0*6 1 0 1 -> 1 0 1(R,m,v=1,1,0)
  14215. =>WM: (14036: S1 ^operator O1998)
  14216. 999: O: O1998 (predict-no)
  14217. --- END Decision Phase ---
  14218. --- Application Phase ---
  14219. --- Firing Productions (PE) For State At Depth 1 ---
  14220. --- Inner Elaboration Phase, active level 1 (S1) ---
  14221. Firing apply*operator
  14222. -->
  14223. (I3 ^predict-no N999 + :O )
  14224. Firing apply*operator*complete
  14225. -->
  14226. (I3 ^predict-no N998 - :O )
  14227. inner elaboration loop at bottom goal.
  14228. --- Change Working Memory (PE) ---
  14229. =>WM: (14037: I3 ^predict-no N999)
  14230. <=WM: (14024: N998 ^status complete)
  14231. <=WM: (14023: I3 ^predict-no N998)
  14232. --- Firing Productions (IE) For State At Depth 1 ---
  14233. --- Inner Elaboration Phase, active level 1 (S1) ---
  14234. Firing monitor*world
  14235. -->
  14236. I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
  14237. --- Change Working Memory (IE) ---
  14238. --- END Application Phase ---
  14239. --- Output Phase ---
  14240. ENV: Agent did: predict-no for direction L in state State-A
  14241. In State-A moving L
  14242. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  14243. predict error 0
  14244. dir: dir isL
  14245. --- END Output Phase ---
  14246. |\---- Input Phase ---
  14247. =>WM: (14041: I2 ^dir L)
  14248. =>WM: (14040: I2 ^reward 1)
  14249. =>WM: (14039: I2 ^see 0)
  14250. =>WM: (14038: N999 ^status complete)
  14251. <=WM: (14027: I2 ^dir L)
  14252. <=WM: (14026: I2 ^reward 1)
  14253. <=WM: (14025: I2 ^see 0)
  14254. =>WM: (14042: I2 ^level-1 L0-root)
  14255. <=WM: (14028: I2 ^level-1 L1-root)
  14256. --- END Input Phase ---
  14257. --- Proposal Phase ---
  14258. --- Inner Elaboration Phase, active level 1 (S1) ---
  14259. Firing rl*prefer*rvt*predict-yes*H0*1*H1*21
  14260. -->
  14261. (S1 ^operator O1997 = 0.3)
  14262. Firing rl*prefer*rvt*predict-no*H0*2*H1*12
  14263. -->
  14264. (S1 ^operator O1998 = 0.7449867384410525)
  14265. Firing prefer*rvt*predict-no*H0*2*H1
  14266. -->
  14267. Firing prefer*rvt*predict-yes*H0*1*H1
  14268. -->
  14269. Firing elaborate*copy-see-to-output-link
  14270. -->
  14271. (I3 ^see 0 +)
  14272. Firing elaborate*reward*based*on*reward
  14273. -->
  14274. (R1003 ^value 1 +)
  14275. (R1 ^reward R1003 +)
  14276. Firing propose*predict-yes
  14277. -->
  14278. (O1999 ^name predict-yes +)
  14279. (S1 ^operator O1999 +)
  14280. Firing propose*predict-no
  14281. -->
  14282. (O2000 ^name predict-no +)
  14283. (S1 ^operator O2000 +)
  14284. Firing rl*prefer*rvt*predict-no*H0*2
  14285. -->
  14286. (S1 ^operator O1998 = 0.2550133828092577)
  14287. Firing rl*prefer*rvt*predict-yes*H0*1
  14288. -->
  14289. (S1 ^operator O1997 = 0.5231200249393807)
  14290. Firing prefer*rvt*predict-yes*H0
  14291. -->
  14292. Firing prefer*rvt*predict-no*H0
  14293. -->
  14294. Firing elaborate*copy-dir-to-output-link
  14295. -->
  14296. (I3 ^dir L +)
  14297. inner elaboration loop at bottom goal.
  14298. Retracting elaborate*copy-see-to-output-link
  14299. -->
  14300. (I3 ^see 0 +)
  14301. Retracting propose*predict-no
  14302. -->
  14303. (O1998 ^name predict-no +)
  14304. (S1 ^operator O1998 +)
  14305. Retracting propose*predict-yes
  14306. -->
  14307. (O1997 ^name predict-yes +)
  14308. (S1 ^operator O1997 +)
  14309. Retracting elaborate*reward*based*on*reward
  14310. -->
  14311. (R1002 ^value 1 +)
  14312. (R1 ^reward R1002 +)
  14313. Retracting elaborate*copy-dir-to-output-link
  14314. -->
  14315. (I3 ^dir L +)
  14316. Retracting rl*prefer*rvt*predict-no*H0*2
  14317. -->
  14318. (S1 ^operator O1998 = 0.2550133828092577)
  14319. Retracting rl*prefer*rvt*predict-no*H0*2*H1*11
  14320. -->
  14321. (S1 ^operator O1998 = 0.7449864376794202)
  14322. Retracting rl*prefer*rvt*predict-yes*H0*1
  14323. -->
  14324. (S1 ^operator O1997 = 0.5231200249393807)
  14325. Retracting rl*prefer*rvt*predict-yes*H0*1*H1*20
  14326. -->
  14327. (S1 ^operator O1997 = 0.1693592933936033)
  14328. =>WM: (14048: S1 ^operator O2000 +)
  14329. =>WM: (14047: S1 ^operator O1999 +)
  14330. =>WM: (14046: O2000 ^name predict-no)
  14331. =>WM: (14045: O1999 ^name predict-yes)
  14332. =>WM: (14044: R1003 ^value 1)
  14333. =>WM: (14043: R1 ^reward R1003)
  14334. <=WM: (14034: S1 ^operator O1997 +)
  14335. <=WM: (14035: S1 ^operator O1998 +)
  14336. <=WM: (14036: S1 ^operator O1998)
  14337. <=WM: (14029: R1 ^reward R1002)
  14338. <=WM: (14032: O1998 ^name predict-no)
  14339. <=WM: (14031: O1997 ^name predict-yes)
  14340. <=WM: (14030: R1002 ^value 1)
  14341. --- Inner Elaboration Phase, active level 1 (S1) ---
  14342. Firing prefer*rvt*predict-yes*H0
  14343. -->
  14344. Firing rl*prefer*rvt*predict-yes*H0*1
  14345. -->
  14346. (S1 ^operator O1999 = 0.5231200249393807)
  14347. Firing prefer*rvt*predict-yes*H0*1*H1
  14348. -->
  14349. Firing rl*prefer*rvt*predict-yes*H0*1*H1*21
  14350. -->
  14351. (S1 ^operator O1999 = 0.3)
  14352. Firing prefer*rvt*predict-no*H0
  14353. -->
  14354. Firing rl*prefer*rvt*predict-no*H0*2
  14355. -->
  14356. (S1 ^operator O2000 = 0.2550133828092577)
  14357. Firing prefer*rvt*predict-no*H0*2*H1
  14358. -->
  14359. Firing rl*prefer*rvt*predict-no*H0*2*H1*12
  14360. -->
  14361. (S1 ^operator O2000 = 0.7449867384410525)
  14362. inner elaboration loop at bottom goal.
  14363. Retracting rl*prefer*rvt*predict-no*H0*2
  14364. -->
  14365. (S1 ^operator O1998 = 0.2550133828092577)
  14366. Retracting rl*prefer*rvt*predict-no*H0*2*H1*12
  14367. -->
  14368. (S1 ^operator O1998 = 0.7449867384410525)
  14369. Retracting rl*prefer*rvt*predict-yes*H0*1
  14370. -->
  14371. (S1 ^operator O1997 = 0.5231200249393807)
  14372. Retracting rl*prefer*rvt*predict-yes*H0*1*H1*21
  14373. -->
  14374. (S1 ^operator O1997 = 0.3)
  14375. --- END Proposal Phase ---
  14376. --- Decision Phase ---
  14377. RL update rl*prefer*rvt*predict-no*H0*2 0.631495 -0.376482 0.255013 -> 0.631495 -0.376482 0.255013(R,m,v=1,0.917526,0.0760643)
  14378. RL update rl*prefer*rvt*predict-no*H0*2*H1*11 0.368505 0.376482 0.744986 -> 0.368505 0.376482 0.744986(R,m,v=1,1,0)
  14379. =>WM: (14049: S1 ^operator O2000)
  14380. 1000: O: O2000 (predict-no)
  14381. --- END Decision Phase ---
  14382. --- Application Phase ---
  14383. --- Firing Productions (PE) For State At Depth 1 ---
  14384. --- Inner Elaboration Phase, active level 1 (S1) ---
  14385. Firing apply*operator
  14386. -->
  14387. (I3 ^predict-no N1000 + :O )
  14388. Firing apply*operator*complete
  14389. -->
  14390. (I3 ^predict-no N999 - :O )
  14391. inner elaboration loop at bottom goal.
  14392. --- Change Working Memory (PE) ---
  14393. =>WM: (14050: I3 ^predict-no N1000)
  14394. <=WM: (14038: N999 ^status complete)
  14395. <=WM: (14037: I3 ^predict-no N999)
  14396. --- Firing Productions (IE) For State At Depth 1 ---
  14397. --- Inner Elaboration Phase, active level 1 (S1) ---
  14398. Firing monitor*world
  14399. -->
  14400. I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
  14401. --- Change Working Memory (IE) ---
  14402. --- END Application Phase ---
  14403. --- Output Phase ---
  14404. ENV: Agent did: predict-no for direction L in state State-A
  14405. In State-A moving L
  14406. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  14407. predict error 0
  14408. dir: dir isL
  14409. --- END Output Phase ---
  14410. /|\-/--- Input Phase ---
  14411. =>WM: (14054: I2 ^dir L)
  14412. =>WM: (14053: I2 ^reward 1)
  14413. =>WM: (14052: I2 ^see 0)
  14414. =>WM: (14051: N1000 ^status complete)
  14415. <=WM: (14041: I2 ^dir L)
  14416. <=WM: (14040: I2 ^reward 1)
  14417. <=WM: (14039: I2 ^see 0)
  14418. =>WM: (14055: I2 ^level-1 L0-root)
  14419. <=WM: (14042: I2 ^level-1 L0-root)
  14420. --- END Input Phase ---
  14421. --- Proposal Phase ---
  14422. --- Inner Elaboration Phase, active level 1 (S1) ---
  14423. Firing rl*prefer*rvt*predict-yes*H0*1*H1*21
  14424. -->
  14425. (S1 ^operator O1999 = 0.3)
  14426. Firing rl*prefer*rvt*predict-no*H0*2*H1*12
  14427. -->
  14428. (S1 ^operator O2000 = 0.7449867384410525)
  14429. Firing prefer*rvt*predict-no*H0*2*H1
  14430. -->
  14431. Firing prefer*rvt*predict-yes*H0*1*H1
  14432. -->
  14433. Firing elaborate*copy-see-to-output-link
  14434. -->
  14435. (I3 ^see 0 +)
  14436. Firing elaborate*reward*based*on*reward
  14437. -->
  14438. (R1004 ^value 1 +)
  14439. (R1 ^reward R1004 +)
  14440. Firing propose*predict-yes
  14441. -->
  14442. (O2001 ^name predict-yes +)
  14443. (S1 ^operator O2001 +)
  14444. Firing propose*predict-no
  14445. -->
  14446. (O2002 ^name predict-no +)
  14447. (S1 ^operator O2002 +)
  14448. Firing rl*prefer*rvt*predict-no*H0*2
  14449. -->
  14450. (S1 ^operator O2000 = 0.255013409735956)
  14451. Firing rl*prefer*rvt*predict-yes*H0*1
  14452. -->
  14453. (S1 ^operator O1999 = 0.5231200249393807)
  14454. Firing prefer*rvt*predict-yes*H0
  14455. -->
  14456. Firing prefer*rvt*predict-no*H0
  14457. -->
  14458. Firing elaborate*copy-dir-to-output-link
  14459. -->
  14460. (I3 ^dir L +)
  14461. inner elaboration loop at bottom goal.
  14462. Retracting elaborate*copy-see-to-output-link
  14463. -->
  14464. (I3 ^see 0 +)
  14465. Retracting propose*predict-no
  14466. -->
  14467. (O2000 ^name predict-no +)
  14468. (S1 ^operator O2000 +)
  14469. Retracting propose*predict-yes
  14470. -->
  14471. (O1999 ^name predict-yes +)
  14472. (S1 ^operator O1999 +)
  14473. Retracting elaborate*reward*based*on*reward
  14474. -->
  14475. (R1003 ^value 1 +)
  14476. (R1 ^reward R1003 +)
  14477. Retracting elaborate*copy-dir-to-output-link
  14478. -->
  14479. (I3 ^dir L +)
  14480. Retracting rl*prefer*rvt*predict-no*H0*2*H1*12
  14481. -->
  14482. (S1 ^operator O2000 = 0.7449867384410525)
  14483. Retracting rl*prefer*rvt*predict-no*H0*2
  14484. -->
  14485. (S1 ^operator O2000 = 0.255013409735956)
  14486. Retracting rl*prefer*rvt*predict-yes*H0*1*H1*21
  14487. -->
  14488. (S1 ^operator O1999 = 0.3)
  14489. Retracting rl*prefer*rvt*predict-yes*H0*1
  14490. -->
  14491. (S1 ^operator O1999 = 0.5231200249393807)
  14492. =>WM: (14061: S1 ^operator O2002 +)
  14493. =>WM: (14060: S1 ^operator O2001 +)
  14494. =>WM: (14059: O2002 ^name predict-no)
  14495. =>WM: (14058: O2001 ^name predict-yes)
  14496. =>WM: (14057: R1004 ^value 1)
  14497. =>WM: (14056: R1 ^reward R1004)
  14498. <=WM: (14047: S1 ^operator O1999 +)
  14499. <=WM: (14048: S1 ^operator O2000 +)
  14500. <=WM: (14049: S1 ^operator O2000)
  14501. <=WM: (14043: R1 ^reward R1003)
  14502. <=WM: (14046: O2000 ^name predict-no)
  14503. <=WM: (14045: O1999 ^name predict-yes)
  14504. <=WM: (14044: R1003 ^value 1)
  14505. --- Inner Elaboration Phase, active level 1 (S1) ---
  14506. Firing prefer*rvt*predict-yes*H0
  14507. -->
  14508. Firing rl*prefer*rvt*predict-yes*H0*1
  14509. -->
  14510. (S1 ^operator O2001 = 0.5231200249393807)
  14511. Firing prefer*rvt*predict-yes*H0*1*H1
  14512. -->
  14513. Firing rl*prefer*rvt*predict-yes*H0*1*H1*21
  14514. -->
  14515. (S1 ^operator O2001 = 0.3)
  14516. Firing prefer*rvt*predict-no*H0
  14517. -->
  14518. Firing rl*prefer*rvt*predict-no*H0*2
  14519. -->
  14520. (S1 ^operator O2002 = 0.255013409735956)
  14521. Firing prefer*rvt*predict-no*H0*2*H1
  14522. -->
  14523. Firing rl*prefer*rvt*predict-no*H0*2*H1*12
  14524. -->
  14525. (S1 ^operator O2002 = 0.7449867384410525)
  14526. inner elaboration loop at bottom goal.
  14527. Retracting rl*prefer*rvt*predict-no*H0*2
  14528. -->
  14529. (S1 ^operator O2000 = 0.255013409735956)
  14530. Retracting rl*prefer*rvt*predict-no*H0*2*H1*12
  14531. -->
  14532. (S1 ^operator O2000 = 0.7449867384410525)
  14533. Retracting rl*prefer*rvt*predict-yes*H0*1
  14534. -->
  14535. (S1 ^operator O1999 = 0.5231200249393807)
  14536. Retracting rl*prefer*rvt*predict-yes*H0*1*H1*21
  14537. -->
  14538. (S1 ^operator O1999 = 0.3)
  14539. --- END Proposal Phase ---
  14540. --- Decision Phase ---
  14541. RL update rl*prefer*rvt*predict-no*H0*2 0.631495 -0.376482 0.255013 -> 0.631495 -0.376482 0.255013(R,m,v=1,0.917949,0.0757071)
  14542. RL update rl*prefer*rvt*predict-no*H0*2*H1*12 0.368505 0.376482 0.744987 -> 0.368505 0.376482 0.744987(R,m,v=1,1,0)
  14543. =>WM: (14062: S1 ^operator O2002)
  14544. 1001: O: O2002 (predict-no)
  14545. --- END Decision Phase ---
  14546. --- Application Phase ---
  14547. --- Firing Productions (PE) For State At Depth 1 ---
  14548. --- Inner Elaboration Phase, active level 1 (S1) ---
  14549. Firing apply*operator
  14550. -->
  14551. (I3 ^predict-no N1001 + :O )
  14552. Firing apply*operator*complete
  14553. -->
  14554. (I3 ^predict-no N1000 - :O )
  14555. inner elaboration loop at bottom goal.
  14556. --- Change Working Memory (PE) ---
  14557. =>WM: (14063: I3 ^predict-no N1001)
  14558. <=WM: (14051: N1000 ^status complete)
  14559. <=WM: (14050: I3 ^predict-no N1000)
  14560. --- Firing Productions (IE) For State At Depth 1 ---
  14561. --- Inner Elaboration Phase, active level 1 (S1) ---
  14562. Firing monitor*world
  14563. -->
  14564. I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
  14565. --- Change Working Memory (IE) ---
  14566. --- END Application Phase ---
  14567. --- Output Phase ---
  14568. ENV: Agent did: predict-no for direction L in state State-A
  14569. In State-A moving L
  14570. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  14571. predict error 0
  14572. dir: dir isL
  14573. --- END Output Phase ---
  14574. |--- Input Phase ---
  14575. =>WM: (14067: I2 ^dir L)
  14576. =>WM: (14066: I2 ^reward 1)
  14577. =>WM: (14065: I2 ^see 0)
  14578. =>WM: (14064: N1001 ^status complete)
  14579. <=WM: (14054: I2 ^dir L)
  14580. <=WM: (14053: I2 ^reward 1)
  14581. <=WM: (14052: I2 ^see 0)
  14582. =>WM: (14068: I2 ^level-1 L0-root)
  14583. <=WM: (14055: I2 ^level-1 L0-root)
  14584. --- END Input Phase ---
  14585. --- Proposal Phase ---
  14586. --- Inner Elaboration Phase, active level 1 (S1) ---
  14587. Firing rl*prefer*rvt*predict-yes*H0*1*H1*21
  14588. -->
  14589. (S1 ^operator O2001 = 0.3)
  14590. Firing rl*prefer*rvt*predict-no*H0*2*H1*12
  14591. -->
  14592. (S1 ^operator O2002 = 0.7449867162145012)
  14593. Firing prefer*rvt*predict-no*H0*2*H1
  14594. -->
  14595. Firing prefer*rvt*predict-yes*H0*1*H1
  14596. -->
  14597. Firing elaborate*copy-see-to-output-link
  14598. -->
  14599. (I3 ^see 0 +)
  14600. Firing elaborate*reward*based*on*reward
  14601. -->
  14602. (R1005 ^value 1 +)
  14603. (R1 ^reward R1005 +)
  14604. Firing propose*predict-yes
  14605. -->
  14606. (O2003 ^name predict-yes +)
  14607. (S1 ^operator O2003 +)
  14608. Firing propose*predict-no
  14609. -->
  14610. (O2004 ^name predict-no +)
  14611. (S1 ^operator O2004 +)
  14612. Firing rl*prefer*rvt*predict-no*H0*2
  14613. -->
  14614. (S1 ^operator O2002 = 0.2550133875094047)
  14615. Firing rl*prefer*rvt*predict-yes*H0*1
  14616. -->
  14617. (S1 ^operator O2001 = 0.5231200249393807)
  14618. Firing prefer*rvt*predict-yes*H0
  14619. -->
  14620. Firing prefer*rvt*predict-no*H0
  14621. -->
  14622. Firing elaborate*copy-dir-to-output-link
  14623. -->
  14624. (I3 ^dir L +)
  14625. inner elaboration loop at bottom goal.
  14626. Retracting elaborate*copy-see-to-output-link
  14627. -->
  14628. (I3 ^see 0 +)
  14629. Retracting propose*predict-no
  14630. -->
  14631. (O2002 ^name predict-no +)
  14632. (S1 ^operator O2002 +)
  14633. Retracting propose*predict-yes
  14634. -->
  14635. (O2001 ^name predict-yes +)
  14636. (S1 ^operator O2001 +)
  14637. Retracting elaborate*reward*based*on*reward
  14638. -->
  14639. (R1004 ^value 1 +)
  14640. (R1 ^reward R1004 +)
  14641. Retracting elaborate*copy-dir-to-output-link
  14642. -->
  14643. (I3 ^dir L +)
  14644. Retracting rl*prefer*rvt*predict-no*H0*2*H1*12
  14645. -->
  14646. (S1 ^operator O2002 = 0.7449867162145012)
  14647. Retracting rl*prefer*rvt*predict-no*H0*2
  14648. -->
  14649. (S1 ^operator O2002 = 0.2550133875094047)
  14650. Retracting rl*prefer*rvt*predict-yes*H0*1*H1*21
  14651. -->
  14652. (S1 ^operator O2001 = 0.3)
  14653. Retracting rl*prefer*rvt*predict-yes*H0*1
  14654. -->
  14655. (S1 ^operator O2001 = 0.5231200249393807)
  14656. =>WM: (14074: S1 ^operator O2004 +)
  14657. =>WM: (14073: S1 ^operator O2003 +)
  14658. =>WM: (14072: O2004 ^name predict-no)
  14659. =>WM: (14071: O2003 ^name predict-yes)
  14660. =>WM: (14070: R1005 ^value 1)
  14661. =>WM: (14069: R1 ^reward R1005)
  14662. <=WM: (14060: S1 ^operator O2001 +)
  14663. <=WM: (14061: S1 ^operator O2002 +)
  14664. <=WM: (14062: S1 ^operator O2002)
  14665. <=WM: (14056: R1 ^reward R1004)
  14666. <=WM: (14059: O2002 ^name predict-no)
  14667. <=WM: (14058: O2001 ^name predict-yes)
  14668. <=WM: (14057: R1004 ^value 1)
  14669. --- Inner Elaboration Phase, active level 1 (S1) ---
  14670. Firing prefer*rvt*predict-yes*H0
  14671. -->
  14672. Firing rl*prefer*rvt*predict-yes*H0*1
  14673. -->
  14674. (S1 ^operator O2003 = 0.5231200249393807)
  14675. Firing prefer*rvt*predict-yes*H0*1*H1
  14676. -->
  14677. Firing rl*prefer*rvt*predict-yes*H0*1*H1*21
  14678. -->
  14679. (S1 ^operator O2003 = 0.3)
  14680. Firing prefer*rvt*predict-no*H0
  14681. -->
  14682. Firing rl*prefer*rvt*predict-no*H0*2
  14683. -->
  14684. (S1 ^operator O2004 = 0.2550133875094047)
  14685. Firing prefer*rvt*predict-no*H0*2*H1
  14686. -->
  14687. Firing rl*prefer*rvt*predict-no*H0*2*H1*12
  14688. -->
  14689. (S1 ^operator O2004 = 0.7449867162145012)
  14690. inner elaboration loop at bottom goal.
  14691. Retracting rl*prefer*rvt*predict-no*H0*2
  14692. -->
  14693. (S1 ^operator O2002 = 0.2550133875094047)
  14694. Retracting rl*prefer*rvt*predict-no*H0*2*H1*12
  14695. -->
  14696. (S1 ^operator O2002 = 0.7449867162145012)
  14697. Retracting rl*prefer*rvt*predict-yes*H0*1
  14698. -->
  14699. (S1 ^operator O2001 = 0.5231200249393807)
  14700. Retracting rl*prefer*rvt*predict-yes*H0*1*H1*21
  14701. -->
  14702. (S1 ^operator O2001 = 0.3)
  14703. --- END Proposal Phase ---
  14704. --- Decision Phase ---
  14705. RL update rl*prefer*rvt*predict-no*H0*2 0.631495 -0.376482 0.255013 -> 0.631495 -0.376482 0.255013(R,m,v=1,0.918367,0.0753532)
  14706. RL update rl*prefer*rvt*predict-no*H0*2*H1*12 0.368505 0.376482 0.744987 -> 0.368505 0.376482 0.744987(R,m,v=1,1,0)
  14707. =>WM: (14075: S1 ^operator O2004)
  14708. 1002: O: O2004 (predict-no)
  14709. --- END Decision Phase ---
  14710. --- Application Phase ---
  14711. --- Firing Productions (PE) For State At Depth 1 ---
  14712. --- Inner Elaboration Phase, active level 1 (S1) ---
  14713. Firing apply*operator
  14714. -->
  14715. (I3 ^predict-no N1002 + :O )
  14716. Firing apply*operator*complete
  14717. -->
  14718. (I3 ^predict-no N1001 - :O )
  14719. inner elaboration loop at bottom goal.
  14720. --- Change Working Memory (PE) ---
  14721. =>WM: (14076: I3 ^predict-no N1002)
  14722. <=WM: (14064: N1001 ^status complete)
  14723. <=WM: (14063: I3 ^predict-no N1001)
  14724. --- Firing Productions (IE) For State At Depth 1 ---
  14725. --- Inner Elaboration Phase, active level 1 (S1) ---
  14726. Firing monitor*world
  14727. -->
  14728. I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
  14729. --- Change Working Memory (IE) ---
  14730. --- END Application Phase ---
  14731. --- Output Phase ---
  14732. ENV: Agent did: predict-no for direction L in state State-A
  14733. In State-A moving L
  14734. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  14735. predict error 0
  14736. dir: dir isU
  14737. --- END Output Phase ---
  14738. \---- Input Phase ---
  14739. =>WM: (14080: I2 ^dir U)
  14740. =>WM: (14079: I2 ^reward 1)
  14741. =>WM: (14078: I2 ^see 0)
  14742. =>WM: (14077: N1002 ^status complete)
  14743. <=WM: (14067: I2 ^dir L)
  14744. <=WM: (14066: I2 ^reward 1)
  14745. <=WM: (14065: I2 ^see 0)
  14746. =>WM: (14081: I2 ^level-1 L0-root)
  14747. <=WM: (14068: I2 ^level-1 L0-root)
  14748. --- END Input Phase ---
  14749. --- Proposal Phase ---
  14750. --- Inner Elaboration Phase, active level 1 (S1) ---
  14751. Firing elaborate*copy-see-to-output-link
  14752. -->
  14753. (I3 ^see 0 +)
  14754. Firing elaborate*reward*based*on*reward
  14755. -->
  14756. (R1006 ^value 1 +)
  14757. (R1 ^reward R1006 +)
  14758. Firing propose*predict-yes
  14759. -->
  14760. (O2005 ^name predict-yes +)
  14761. (S1 ^operator O2005 +)
  14762. Firing propose*predict-no
  14763. -->
  14764. (O2006 ^name predict-no +)
  14765. (S1 ^operator O2006 +)
  14766. Firing rl*prefer*rvt*predict-no*H0*6
  14767. -->
  14768. (S1 ^operator O2004 = 0.9999999999999999)
  14769. Firing rl*prefer*rvt*predict-yes*H0*5
  14770. -->
  14771. (S1 ^operator O2003 = 0.)
  14772. Firing prefer*rvt*predict-yes*H0
  14773. -->
  14774. Firing prefer*rvt*predict-no*H0
  14775. -->
  14776. Firing elaborate*copy-dir-to-output-link
  14777. -->
  14778. (I3 ^dir U +)
  14779. inner elaboration loop at bottom goal.
  14780. Retracting elaborate*copy-see-to-output-link
  14781. -->
  14782. (I3 ^see 0 +)
  14783. Retracting propose*predict-no
  14784. -->
  14785. (O2004 ^name predict-no +)
  14786. (S1 ^operator O2004 +)
  14787. Retracting propose*predict-yes
  14788. -->
  14789. (O2003 ^name predict-yes +)
  14790. (S1 ^operator O2003 +)
  14791. Retracting elaborate*reward*based*on*reward
  14792. -->
  14793. (R1005 ^value 1 +)
  14794. (R1 ^reward R1005 +)
  14795. Retracting elaborate*copy-dir-to-output-link
  14796. -->
  14797. (I3 ^dir L +)
  14798. Retracting rl*prefer*rvt*predict-no*H0*2*H1*12
  14799. -->
  14800. (S1 ^operator O2004 = 0.7449867006559153)
  14801. Retracting rl*prefer*rvt*predict-no*H0*2
  14802. -->
  14803. (S1 ^operator O2004 = 0.2550133719508188)
  14804. Retracting rl*prefer*rvt*predict-yes*H0*1*H1*21
  14805. -->
  14806. (S1 ^operator O2003 = 0.3)
  14807. Retracting rl*prefer*rvt*predict-yes*H0*1
  14808. -->
  14809. (S1 ^operator O2003 = 0.5231200249393807)
  14810. =>WM: (14088: S1 ^operator O2006 +)
  14811. =>WM: (14087: S1 ^operator O2005 +)
  14812. =>WM: (14086: I3 ^dir U)
  14813. =>WM: (14085: O2006 ^name predict-no)
  14814. =>WM: (14084: O2005 ^name predict-yes)
  14815. =>WM: (14083: R1006 ^value 1)
  14816. =>WM: (14082: R1 ^reward R1006)
  14817. <=WM: (14073: S1 ^operator O2003 +)
  14818. <=WM: (14074: S1 ^operator O2004 +)
  14819. <=WM: (14075: S1 ^operator O2004)
  14820. <=WM: (14033: I3 ^dir L)
  14821. <=WM: (14069: R1 ^reward R1005)
  14822. <=WM: (14072: O2004 ^name predict-no)
  14823. <=WM: (14071: O2003 ^name predict-yes)
  14824. <=WM: (14070: R1005 ^value 1)
  14825. --- Inner Elaboration Phase, active level 1 (S1) ---
  14826. Firing prefer*rvt*predict-yes*H0
  14827. -->
  14828. Firing rl*prefer*rvt*predict-yes*H0*5
  14829. -->
  14830. (S1 ^operator O2005 = 0.)
  14831. Firing prefer*rvt*predict-no*H0
  14832. -->
  14833. Firing rl*prefer*rvt*predict-no*H0*6
  14834. -->
  14835. (S1 ^operator O2006 = 0.9999999999999999)
  14836. inner elaboration loop at bottom goal.
  14837. Retracting rl*prefer*rvt*predict-no*H0*6
  14838. -->
  14839. (S1 ^operator O2004 = 0.9999999999999999)
  14840. Retracting rl*prefer*rvt*predict-yes*H0*5
  14841. -->
  14842. (S1 ^operator O2003 = 0.)
  14843. --- END Proposal Phase ---
  14844. --- Decision Phase ---
  14845. RL update rl*prefer*rvt*predict-no*H0*2 0.631495 -0.376482 0.255013 -> 0.631495 -0.376482 0.255013(R,m,v=1,0.918782,0.0750026)
  14846. RL update rl*prefer*rvt*predict-no*H0*2*H1*12 0.368505 0.376482 0.744987 -> 0.368505 0.376482 0.744987(R,m,v=1,1,0)
  14847. =>WM: (14089: S1 ^operator O2006)
  14848. 1003: O: O2006 (predict-no)
  14849. --- END Decision Phase ---
  14850. --- Application Phase ---
  14851. --- Firing Productions (PE) For State At Depth 1 ---
  14852. --- Inner Elaboration Phase, active level 1 (S1) ---
  14853. Firing apply*operator
  14854. -->
  14855. (I3 ^predict-no N1003 + :O )
  14856. Firing apply*operator*complete
  14857. -->
  14858. (I3 ^predict-no N1002 - :O )
  14859. inner elaboration loop at bottom goal.
  14860. --- Change Working Memory (PE) ---
  14861. =>WM: (14090: I3 ^predict-no N1003)
  14862. <=WM: (14077: N1002 ^status complete)
  14863. <=WM: (14076: I3 ^predict-no N1002)
  14864. --- Firing Productions (IE) For State At Depth 1 ---
  14865. --- Inner Elaboration Phase, active level 1 (S1) ---
  14866. Firing monitor*world
  14867. -->
  14868. I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
  14869. --- Change Working Memory (IE) ---
  14870. --- END Application Phase ---
  14871. --- Output Phase ---
  14872. ENV: Agent did: predict-no for direction U in state State-A
  14873. In State-A moving U
  14874. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  14875. predict error 0
  14876. dir: dir isR
  14877. --- END Output Phase ---
  14878. /|\--- Input Phase ---
  14879. =>WM: (14094: I2 ^dir R)
  14880. =>WM: (14093: I2 ^reward 1)
  14881. =>WM: (14092: I2 ^see 0)
  14882. =>WM: (14091: N1003 ^status complete)
  14883. <=WM: (14080: I2 ^dir U)
  14884. <=WM: (14079: I2 ^reward 1)
  14885. <=WM: (14078: I2 ^see 0)
  14886. =>WM: (14095: I2 ^level-1 L0-root)
  14887. <=WM: (14081: I2 ^level-1 L0-root)
  14888. --- END Input Phase ---
  14889. --- Proposal Phase ---
  14890. --- Inner Elaboration Phase, active level 1 (S1) ---
  14891. Firing rl*prefer*rvt*predict-yes*H0*3*H1*14
  14892. -->
  14893. (S1 ^operator O2005 = 0.617076227543635)
  14894. Firing rl*prefer*rvt*predict-no*H0*4*H1*13
  14895. -->
  14896. (S1 ^operator O2006 = 0.4910065094545203)
  14897. Firing prefer*rvt*predict-no*H0*4*H1
  14898. -->
  14899. Firing prefer*rvt*predict-yes*H0*3*H1
  14900. -->
  14901. Firing elaborate*copy-see-to-output-link
  14902. -->
  14903. (I3 ^see 0 +)
  14904. Firing elaborate*reward*based*on*reward
  14905. -->
  14906. (R1007 ^value 1 +)
  14907. (R1 ^reward R1007 +)
  14908. Firing propose*predict-yes
  14909. -->
  14910. (O2007 ^name predict-yes +)
  14911. (S1 ^operator O2007 +)
  14912. Firing propose*predict-no
  14913. -->
  14914. (O2008 ^name predict-no +)
  14915. (S1 ^operator O2008 +)
  14916. Firing rl*prefer*rvt*predict-no*H0*4
  14917. -->
  14918. (S1 ^operator O2006 = 0.1269768790760836)
  14919. Firing rl*prefer*rvt*predict-yes*H0*3
  14920. -->
  14921. (S1 ^operator O2005 = 0.3829355766477516)
  14922. Firing prefer*rvt*predict-yes*H0
  14923. -->
  14924. Firing prefer*rvt*predict-no*H0
  14925. -->
  14926. Firing elaborate*copy-dir-to-output-link
  14927. -->
  14928. (I3 ^dir R +)
  14929. inner elaboration loop at bottom goal.
  14930. Retracting elaborate*copy-see-to-output-link
  14931. -->
  14932. (I3 ^see 0 +)
  14933. Retracting propose*predict-no
  14934. -->
  14935. (O2006 ^name predict-no +)
  14936. (S1 ^operator O2006 +)
  14937. Retracting propose*predict-yes
  14938. -->
  14939. (O2005 ^name predict-yes +)
  14940. (S1 ^operator O2005 +)
  14941. Retracting elaborate*reward*based*on*reward
  14942. -->
  14943. (R1006 ^value 1 +)
  14944. (R1 ^reward R1006 +)
  14945. Retracting elaborate*copy-dir-to-output-link
  14946. -->
  14947. (I3 ^dir U +)
  14948. Retracting rl*prefer*rvt*predict-no*H0*6
  14949. -->
  14950. (S1 ^operator O2006 = 0.9999999999999999)
  14951. Retracting rl*prefer*rvt*predict-yes*H0*5
  14952. -->
  14953. (S1 ^operator O2005 = 0.)
  14954. =>WM: (14102: S1 ^operator O2008 +)
  14955. =>WM: (14101: S1 ^operator O2007 +)
  14956. =>WM: (14100: I3 ^dir R)
  14957. =>WM: (14099: O2008 ^name predict-no)
  14958. =>WM: (14098: O2007 ^name predict-yes)
  14959. =>WM: (14097: R1007 ^value 1)
  14960. =>WM: (14096: R1 ^reward R1007)
  14961. <=WM: (14087: S1 ^operator O2005 +)
  14962. <=WM: (14088: S1 ^operator O2006 +)
  14963. <=WM: (14089: S1 ^operator O2006)
  14964. <=WM: (14086: I3 ^dir U)
  14965. <=WM: (14082: R1 ^reward R1006)
  14966. <=WM: (14085: O2006 ^name predict-no)
  14967. <=WM: (14084: O2005 ^name predict-yes)
  14968. <=WM: (14083: R1006 ^value 1)
  14969. --- Inner Elaboration Phase, active level 1 (S1) ---
  14970. Firing prefer*rvt*predict-yes*H0
  14971. -->
  14972. Firing rl*prefer*rvt*predict-yes*H0*3*H1*14
  14973. -->
  14974. (S1 ^operator O2007 = 0.617076227543635)
  14975. Firing rl*prefer*rvt*predict-yes*H0*3
  14976. -->
  14977. (S1 ^operator O2007 = 0.3829355766477516)
  14978. Firing prefer*rvt*predict-yes*H0*3*H1
  14979. -->
  14980. Firing prefer*rvt*predict-no*H0
  14981. -->
  14982. Firing rl*prefer*rvt*predict-no*H0*4*H1*13
  14983. -->
  14984. (S1 ^operator O2008 = 0.4910065094545203)
  14985. Firing rl*prefer*rvt*predict-no*H0*4
  14986. -->
  14987. (S1 ^operator O2008 = 0.1269768790760836)
  14988. Firing prefer*rvt*predict-no*H0*4*H1
  14989. -->
  14990. inner elaboration loop at bottom goal.
  14991. Retracting rl*prefer*rvt*predict-no*H0*4
  14992. -->
  14993. (S1 ^operator O2006 = 0.1269768790760836)
  14994. Retracting rl*prefer*rvt*predict-no*H0*4*H1*13
  14995. -->
  14996. (S1 ^operator O2006 = 0.4910065094545203)
  14997. Retracting rl*prefer*rvt*predict-yes*H0*3
  14998. -->
  14999. (S1 ^operator O2005 = 0.3829355766477516)
  15000. Retracting rl*prefer*rvt*predict-yes*H0*3*H1*14
  15001. -->
  15002. (S1 ^operator O2005 = 0.617076227543635)
  15003. --- END Proposal Phase ---
  15004. --- Decision Phase ---
  15005. RL update rl*prefer*rvt*predict-no*H0*6 1 0 1 -> 1 0 1(R,m,v=1,1,0)
  15006. =>WM: (14103: S1 ^operator O2007)
  15007. 1004: O: O2007 (predict-yes)
  15008. --- END Decision Phase ---
  15009. --- Application Phase ---
  15010. --- Firing Productions (PE) For State At Depth 1 ---
  15011. --- Inner Elaboration Phase, active level 1 (S1) ---
  15012. Firing apply*operator
  15013. -->
  15014. (I3 ^predict-yes N1004 + :O )
  15015. Firing apply*operator*complete
  15016. -->
  15017. (I3 ^predict-no N1003 - :O )
  15018. inner elaboration loop at bottom goal.
  15019. --- Change Working Memory (PE) ---
  15020. =>WM: (14104: I3 ^predict-yes N1004)
  15021. <=WM: (14091: N1003 ^status complete)
  15022. <=WM: (14090: I3 ^predict-no N1003)
  15023. --- Firing Productions (IE) For State At Depth 1 ---
  15024. --- Inner Elaboration Phase, active level 1 (S1) ---
  15025. Firing monitor*world
  15026. -->
  15027. I see 1 and I'm going to do: predict-yes inner elaboration loop at bottom goal.
  15028. --- Change Working Memory (IE) ---
  15029. --- END Application Phase ---
  15030. --- Output Phase ---
  15031. ENV: Agent did: predict-yes for direction R in state State-A
  15032. In State-A moving R
  15033. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  15034. predict error 0
  15035. dir: dir isU
  15036. --- END Output Phase ---
  15037. -/|--- Input Phase ---
  15038. =>WM: (14108: I2 ^dir U)
  15039. =>WM: (14107: I2 ^reward 1)
  15040. =>WM: (14106: I2 ^see 1)
  15041. =>WM: (14105: N1004 ^status complete)
  15042. <=WM: (14094: I2 ^dir R)
  15043. <=WM: (14093: I2 ^reward 1)
  15044. <=WM: (14092: I2 ^see 0)
  15045. =>WM: (14109: I2 ^level-1 R1-root)
  15046. <=WM: (14095: I2 ^level-1 L0-root)
  15047. --- END Input Phase ---
  15048. --- Proposal Phase ---
  15049. --- Inner Elaboration Phase, active level 1 (S1) ---
  15050. Firing elaborate*copy-see-to-output-link
  15051. -->
  15052. (I3 ^see 1 +)
  15053. Firing elaborate*reward*based*on*reward
  15054. -->
  15055. (R1008 ^value 1 +)
  15056. (R1 ^reward R1008 +)
  15057. Firing propose*predict-yes
  15058. -->
  15059. (O2009 ^name predict-yes +)
  15060. (S1 ^operator O2009 +)
  15061. Firing propose*predict-no
  15062. -->
  15063. (O2010 ^name predict-no +)
  15064. (S1 ^operator O2010 +)
  15065. Firing rl*prefer*rvt*predict-no*H0*6
  15066. -->
  15067. (S1 ^operator O2008 = 0.9999999999999999)
  15068. Firing rl*prefer*rvt*predict-yes*H0*5
  15069. -->
  15070. (S1 ^operator O2007 = 0.)
  15071. Firing prefer*rvt*predict-yes*H0
  15072. -->
  15073. Firing prefer*rvt*predict-no*H0
  15074. -->
  15075. Firing elaborate*copy-dir-to-output-link
  15076. -->
  15077. (I3 ^dir U +)
  15078. inner elaboration loop at bottom goal.
  15079. Retracting elaborate*copy-see-to-output-link
  15080. -->
  15081. (I3 ^see 0 +)
  15082. Retracting propose*predict-no
  15083. -->
  15084. (O2008 ^name predict-no +)
  15085. (S1 ^operator O2008 +)
  15086. Retracting propose*predict-yes
  15087. -->
  15088. (O2007 ^name predict-yes +)
  15089. (S1 ^operator O2007 +)
  15090. Retracting elaborate*reward*based*on*reward
  15091. -->
  15092. (R1007 ^value 1 +)
  15093. (R1 ^reward R1007 +)
  15094. Retracting elaborate*copy-dir-to-output-link
  15095. -->
  15096. (I3 ^dir R +)
  15097. Retracting rl*prefer*rvt*predict-no*H0*4
  15098. -->
  15099. (S1 ^operator O2008 = 0.1269768790760836)
  15100. Retracting rl*prefer*rvt*predict-no*H0*4*H1*13
  15101. -->
  15102. (S1 ^operator O2008 = 0.4910065094545203)
  15103. Retracting rl*prefer*rvt*predict-yes*H0*3
  15104. -->
  15105. (S1 ^operator O2007 = 0.3829355766477516)
  15106. Retracting rl*prefer*rvt*predict-yes*H0*3*H1*14
  15107. -->
  15108. (S1 ^operator O2007 = 0.617076227543635)
  15109. =>WM: (14117: S1 ^operator O2010 +)
  15110. =>WM: (14116: S1 ^operator O2009 +)
  15111. =>WM: (14115: I3 ^dir U)
  15112. =>WM: (14114: O2010 ^name predict-no)
  15113. =>WM: (14113: O2009 ^name predict-yes)
  15114. =>WM: (14112: R1008 ^value 1)
  15115. =>WM: (14111: R1 ^reward R1008)
  15116. =>WM: (14110: I3 ^see 1)
  15117. <=WM: (14101: S1 ^operator O2007 +)
  15118. <=WM: (14103: S1 ^operator O2007)
  15119. <=WM: (14102: S1 ^operator O2008 +)
  15120. <=WM: (14100: I3 ^dir R)
  15121. <=WM: (14096: R1 ^reward R1007)
  15122. <=WM: (14015: I3 ^see 0)
  15123. <=WM: (14099: O2008 ^name predict-no)
  15124. <=WM: (14098: O2007 ^name predict-yes)
  15125. <=WM: (14097: R1007 ^value 1)
  15126. --- Inner Elaboration Phase, active level 1 (S1) ---
  15127. Firing prefer*rvt*predict-yes*H0
  15128. -->
  15129. Firing rl*prefer*rvt*predict-yes*H0*5
  15130. -->
  15131. (S1 ^operator O2009 = 0.)
  15132. Firing prefer*rvt*predict-no*H0
  15133. -->
  15134. Firing rl*prefer*rvt*predict-no*H0*6
  15135. -->
  15136. (S1 ^operator O2010 = 0.9999999999999999)
  15137. inner elaboration loop at bottom goal.
  15138. Retracting rl*prefer*rvt*predict-no*H0*6
  15139. -->
  15140. (S1 ^operator O2008 = 0.9999999999999999)
  15141. Retracting rl*prefer*rvt*predict-yes*H0*5
  15142. -->
  15143. (S1 ^operator O2007 = 0.)
  15144. --- END Proposal Phase ---
  15145. --- Decision Phase ---
  15146. RL update rl*prefer*rvt*predict-yes*H0*3 0.673129 -0.290194 0.382936 -> 0.673128 -0.290194 0.382934(R,m,v=1,0.960784,0.0379257)
  15147. RL update rl*prefer*rvt*predict-yes*H0*3*H1*14 0.326882 0.290195 0.617076 -> 0.32688 0.290194 0.617074(R,m,v=1,1,0)
  15148. =>WM: (14118: S1 ^operator O2010)
  15149. 1005: O: O2010 (predict-no)
  15150. --- END Decision Phase ---
  15151. --- Application Phase ---
  15152. --- Firing Productions (PE) For State At Depth 1 ---
  15153. --- Inner Elaboration Phase, active level 1 (S1) ---
  15154. Firing apply*operator
  15155. -->
  15156. (I3 ^predict-no N1005 + :O )
  15157. Firing apply*operator*complete
  15158. -->
  15159. (I3 ^predict-yes N1004 - :O )
  15160. inner elaboration loop at bottom goal.
  15161. --- Change Working Memory (PE) ---
  15162. =>WM: (14119: I3 ^predict-no N1005)
  15163. <=WM: (14105: N1004 ^status complete)
  15164. <=WM: (14104: I3 ^predict-yes N1004)
  15165. --- Firing Productions (IE) For State At Depth 1 ---
  15166. --- Inner Elaboration Phase, active level 1 (S1) ---
  15167. Firing monitor*world
  15168. -->
  15169. I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
  15170. --- Change Working Memory (IE) ---
  15171. --- END Application Phase ---
  15172. --- Output Phase ---
  15173. ENV: Agent did: predict-no for direction U in state State-B
  15174. In State-B moving U
  15175. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  15176. predict error 0
  15177. dir: dir isL
  15178. --- END Output Phase ---
  15179. \-/--- Input Phase ---
  15180. =>WM: (14123: I2 ^dir L)
  15181. =>WM: (14122: I2 ^reward 1)
  15182. =>WM: (14121: I2 ^see 0)
  15183. =>WM: (14120: N1005 ^status complete)
  15184. <=WM: (14108: I2 ^dir U)
  15185. <=WM: (14107: I2 ^reward 1)
  15186. <=WM: (14106: I2 ^see 1)
  15187. =>WM: (14124: I2 ^level-1 R1-root)
  15188. <=WM: (14109: I2 ^level-1 R1-root)
  15189. --- END Input Phase ---
  15190. --- Proposal Phase ---
  15191. --- Inner Elaboration Phase, active level 1 (S1) ---
  15192. Firing rl*prefer*rvt*predict-yes*H0*1*H1*22
  15193. -->
  15194. (S1 ^operator O2009 = 0.4768779238990463)
  15195. Firing rl*prefer*rvt*predict-no*H0*2*H1*10
  15196. -->
  15197. (S1 ^operator O2010 = -0.01194930198035649)
  15198. Firing prefer*rvt*predict-no*H0*2*H1
  15199. -->
  15200. Firing prefer*rvt*predict-yes*H0*1*H1
  15201. -->
  15202. Firing elaborate*copy-see-to-output-link
  15203. -->
  15204. (I3 ^see 0 +)
  15205. Firing elaborate*reward*based*on*reward
  15206. -->
  15207. (R1009 ^value 1 +)
  15208. (R1 ^reward R1009 +)
  15209. Firing propose*predict-yes
  15210. -->
  15211. (O2011 ^name predict-yes +)
  15212. (S1 ^operator O2011 +)
  15213. Firing propose*predict-no
  15214. -->
  15215. (O2012 ^name predict-no +)
  15216. (S1 ^operator O2012 +)
  15217. Firing rl*prefer*rvt*predict-no*H0*2
  15218. -->
  15219. (S1 ^operator O2010 = 0.2550133610598087)
  15220. Firing rl*prefer*rvt*predict-yes*H0*1
  15221. -->
  15222. (S1 ^operator O2009 = 0.5231200249393807)
  15223. Firing prefer*rvt*predict-yes*H0
  15224. -->
  15225. Firing prefer*rvt*predict-no*H0
  15226. -->
  15227. Firing elaborate*copy-dir-to-output-link
  15228. -->
  15229. (I3 ^dir L +)
  15230. inner elaboration loop at bottom goal.
  15231. Retracting elaborate*copy-see-to-output-link
  15232. -->
  15233. (I3 ^see 1 +)
  15234. Retracting propose*predict-no
  15235. -->
  15236. (O2010 ^name predict-no +)
  15237. (S1 ^operator O2010 +)
  15238. Retracting propose*predict-yes
  15239. -->
  15240. (O2009 ^name predict-yes +)
  15241. (S1 ^operator O2009 +)
  15242. Retracting elaborate*reward*based*on*reward
  15243. -->
  15244. (R1008 ^value 1 +)
  15245. (R1 ^reward R1008 +)
  15246. Retracting elaborate*copy-dir-to-output-link
  15247. -->
  15248. (I3 ^dir U +)
  15249. Retracting rl*prefer*rvt*predict-no*H0*6
  15250. -->
  15251. (S1 ^operator O2010 = 0.9999999999999999)
  15252. Retracting rl*prefer*rvt*predict-yes*H0*5
  15253. -->
  15254. (S1 ^operator O2009 = 0.)
  15255. =>WM: (14132: S1 ^operator O2012 +)
  15256. =>WM: (14131: S1 ^operator O2011 +)
  15257. =>WM: (14130: I3 ^dir L)
  15258. =>WM: (14129: O2012 ^name predict-no)
  15259. =>WM: (14128: O2011 ^name predict-yes)
  15260. =>WM: (14127: R1009 ^value 1)
  15261. =>WM: (14126: R1 ^reward R1009)
  15262. =>WM: (14125: I3 ^see 0)
  15263. <=WM: (14116: S1 ^operator O2009 +)
  15264. <=WM: (14117: S1 ^operator O2010 +)
  15265. <=WM: (14118: S1 ^operator O2010)
  15266. <=WM: (14115: I3 ^dir U)
  15267. <=WM: (14111: R1 ^reward R1008)
  15268. <=WM: (14110: I3 ^see 1)
  15269. <=WM: (14114: O2010 ^name predict-no)
  15270. <=WM: (14113: O2009 ^name predict-yes)
  15271. <=WM: (14112: R1008 ^value 1)
  15272. --- Inner Elaboration Phase, active level 1 (S1) ---
  15273. Firing prefer*rvt*predict-yes*H0
  15274. -->
  15275. Firing rl*prefer*rvt*predict-yes*H0*1*H1*22
  15276. -->
  15277. (S1 ^operator O2011 = 0.4768779238990463)
  15278. Firing rl*prefer*rvt*predict-yes*H0*1
  15279. -->
  15280. (S1 ^operator O2011 = 0.5231200249393807)
  15281. Firing prefer*rvt*predict-yes*H0*1*H1
  15282. -->
  15283. Firing prefer*rvt*predict-no*H0
  15284. -->
  15285. Firing rl*prefer*rvt*predict-no*H0*2*H1*10
  15286. -->
  15287. (S1 ^operator O2012 = -0.01194930198035649)
  15288. Firing rl*prefer*rvt*predict-no*H0*2
  15289. -->
  15290. (S1 ^operator O2012 = 0.2550133610598087)
  15291. Firing prefer*rvt*predict-no*H0*2*H1
  15292. -->
  15293. inner elaboration loop at bottom goal.
  15294. Retracting rl*prefer*rvt*predict-no*H0*2
  15295. -->
  15296. (S1 ^operator O2010 = 0.2550133610598087)
  15297. Retracting rl*prefer*rvt*predict-no*H0*2*H1*10
  15298. -->
  15299. (S1 ^operator O2010 = -0.01194930198035649)
  15300. Retracting rl*prefer*rvt*predict-yes*H0*1
  15301. -->
  15302. (S1 ^operator O2009 = 0.5231200249393807)
  15303. Retracting rl*prefer*rvt*predict-yes*H0*1*H1*22
  15304. -->
  15305. (S1 ^operator O2009 = 0.4768779238990463)
  15306. --- END Proposal Phase ---
  15307. --- Decision Phase ---
  15308. RL update rl*prefer*rvt*predict-no*H0*6 1 0 1 -> 1 0 1(R,m,v=1,1,0)
  15309. =>WM: (14133: S1 ^operator O2011)
  15310. 1006: O: O2011 (predict-yes)
  15311. --- END Decision Phase ---
  15312. --- Application Phase ---
  15313. --- Firing Productions (PE) For State At Depth 1 ---
  15314. --- Inner Elaboration Phase, active level 1 (S1) ---
  15315. Firing apply*operator
  15316. -->
  15317. (I3 ^predict-yes N1006 + :O )
  15318. Firing apply*operator*complete
  15319. -->
  15320. (I3 ^predict-no N1005 - :O )
  15321. inner elaboration loop at bottom goal.
  15322. --- Change Working Memory (PE) ---
  15323. =>WM: (14134: I3 ^predict-yes N1006)
  15324. <=WM: (14120: N1005 ^status complete)
  15325. <=WM: (14119: I3 ^predict-no N1005)
  15326. --- Firing Productions (IE) For State At Depth 1 ---
  15327. --- Inner Elaboration Phase, active level 1 (S1) ---
  15328. Firing monitor*world
  15329. -->
  15330. I see 1 and I'm going to do: predict-yes inner elaboration loop at bottom goal.
  15331. --- Change Working Memory (IE) ---
  15332. --- END Application Phase ---
  15333. --- Output Phase ---
  15334. ENV: Agent did: predict-yes for direction L in state State-B
  15335. In State-B moving L
  15336. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  15337. predict error 0
  15338. dir: dir isL
  15339. --- END Output Phase ---
  15340. |\---- Input Phase ---
  15341. =>WM: (14138: I2 ^dir L)
  15342. =>WM: (14137: I2 ^reward 1)
  15343. =>WM: (14136: I2 ^see 1)
  15344. =>WM: (14135: N1006 ^status complete)
  15345. <=WM: (14123: I2 ^dir L)
  15346. <=WM: (14122: I2 ^reward 1)
  15347. <=WM: (14121: I2 ^see 0)
  15348. =>WM: (14139: I2 ^level-1 L1-root)
  15349. <=WM: (14124: I2 ^level-1 R1-root)
  15350. --- END Input Phase ---
  15351. --- Proposal Phase ---
  15352. --- Inner Elaboration Phase, active level 1 (S1) ---
  15353. Firing rl*prefer*rvt*predict-yes*H0*1*H1*20
  15354. -->
  15355. (S1 ^operator O2011 = 0.1693592933936033)
  15356. Firing rl*prefer*rvt*predict-no*H0*2*H1*11
  15357. -->
  15358. (S1 ^operator O2012 = 0.7449864646061185)
  15359. Firing prefer*rvt*predict-no*H0*2*H1
  15360. -->
  15361. Firing prefer*rvt*predict-yes*H0*1*H1
  15362. -->
  15363. Firing elaborate*copy-see-to-output-link
  15364. -->
  15365. (I3 ^see 1 +)
  15366. Firing elaborate*reward*based*on*reward
  15367. -->
  15368. (R1010 ^value 1 +)
  15369. (R1 ^reward R1010 +)
  15370. Firing propose*predict-yes
  15371. -->
  15372. (O2013 ^name predict-yes +)
  15373. (S1 ^operator O2013 +)
  15374. Firing propose*predict-no
  15375. -->
  15376. (O2014 ^name predict-no +)
  15377. (S1 ^operator O2014 +)
  15378. Firing rl*prefer*rvt*predict-no*H0*2
  15379. -->
  15380. (S1 ^operator O2012 = 0.2550133610598087)
  15381. Firing rl*prefer*rvt*predict-yes*H0*1
  15382. -->
  15383. (S1 ^operator O2011 = 0.5231200249393807)
  15384. Firing prefer*rvt*predict-yes*H0
  15385. -->
  15386. Firing prefer*rvt*predict-no*H0
  15387. -->
  15388. Firing elaborate*copy-dir-to-output-link
  15389. -->
  15390. (I3 ^dir L +)
  15391. inner elaboration loop at bottom goal.
  15392. Retracting elaborate*copy-see-to-output-link
  15393. -->
  15394. (I3 ^see 0 +)
  15395. Retracting propose*predict-no
  15396. -->
  15397. (O2012 ^name predict-no +)
  15398. (S1 ^operator O2012 +)
  15399. Retracting propose*predict-yes
  15400. -->
  15401. (O2011 ^name predict-yes +)
  15402. (S1 ^operator O2011 +)
  15403. Retracting elaborate*reward*based*on*reward
  15404. -->
  15405. (R1009 ^value 1 +)
  15406. (R1 ^reward R1009 +)
  15407. Retracting elaborate*copy-dir-to-output-link
  15408. -->
  15409. (I3 ^dir L +)
  15410. Retracting rl*prefer*rvt*predict-no*H0*2
  15411. -->
  15412. (S1 ^operator O2012 = 0.2550133610598087)
  15413. Retracting rl*prefer*rvt*predict-no*H0*2*H1*10
  15414. -->
  15415. (S1 ^operator O2012 = -0.01194930198035649)
  15416. Retracting rl*prefer*rvt*predict-yes*H0*1
  15417. -->
  15418. (S1 ^operator O2011 = 0.5231200249393807)
  15419. Retracting rl*prefer*rvt*predict-yes*H0*1*H1*22
  15420. -->
  15421. (S1 ^operator O2011 = 0.4768779238990463)
  15422. =>WM: (14146: S1 ^operator O2014 +)
  15423. =>WM: (14145: S1 ^operator O2013 +)
  15424. =>WM: (14144: O2014 ^name predict-no)
  15425. =>WM: (14143: O2013 ^name predict-yes)
  15426. =>WM: (14142: R1010 ^value 1)
  15427. =>WM: (14141: R1 ^reward R1010)
  15428. =>WM: (14140: I3 ^see 1)
  15429. <=WM: (14131: S1 ^operator O2011 +)
  15430. <=WM: (14133: S1 ^operator O2011)
  15431. <=WM: (14132: S1 ^operator O2012 +)
  15432. <=WM: (14126: R1 ^reward R1009)
  15433. <=WM: (14125: I3 ^see 0)
  15434. <=WM: (14129: O2012 ^name predict-no)
  15435. <=WM: (14128: O2011 ^name predict-yes)
  15436. <=WM: (14127: R1009 ^value 1)
  15437. --- Inner Elaboration Phase, active level 1 (S1) ---
  15438. Firing prefer*rvt*predict-yes*H0
  15439. -->
  15440. Firing rl*prefer*rvt*predict-yes*H0*1
  15441. -->
  15442. (S1 ^operator O2013 = 0.5231200249393807)
  15443. Firing prefer*rvt*predict-yes*H0*1*H1
  15444. -->
  15445. Firing rl*prefer*rvt*predict-yes*H0*1*H1*20
  15446. -->
  15447. (S1 ^operator O2013 = 0.1693592933936033)
  15448. Firing prefer*rvt*predict-no*H0
  15449. -->
  15450. Firing rl*prefer*rvt*predict-no*H0*2
  15451. -->
  15452. (S1 ^operator O2014 = 0.2550133610598087)
  15453. Firing prefer*rvt*predict-no*H0*2*H1
  15454. -->
  15455. Firing rl*prefer*rvt*predict-no*H0*2*H1*11
  15456. -->
  15457. (S1 ^operator O2014 = 0.7449864646061185)
  15458. inner elaboration loop at bottom goal.
  15459. Retracting rl*prefer*rvt*predict-no*H0*2
  15460. -->
  15461. (S1 ^operator O2012 = 0.2550133610598087)
  15462. Retracting rl*prefer*rvt*predict-no*H0*2*H1*11
  15463. -->
  15464. (S1 ^operator O2012 = 0.7449864646061185)
  15465. Retracting rl*prefer*rvt*predict-yes*H0*1
  15466. -->
  15467. (S1 ^operator O2011 = 0.5231200249393807)
  15468. Retracting rl*prefer*rvt*predict-yes*H0*1*H1*20
  15469. -->
  15470. (S1 ^operator O2011 = 0.1693592933936033)
  15471. --- END Proposal Phase ---
  15472. --- Decision Phase ---
  15473. RL update rl*prefer*rvt*predict-yes*H0*1 0.72796 -0.20484 0.52312 -> 0.72796 -0.20484 0.52312(R,m,v=1,0.979021,0.0206835)
  15474. RL update rl*prefer*rvt*predict-yes*H0*1*H1*22 0.272037 0.204841 0.476878 -> 0.272038 0.20484 0.476878(R,m,v=1,1,0)
  15475. =>WM: (14147: S1 ^operator O2014)
  15476. 1007: O: O2014 (predict-no)
  15477. --- END Decision Phase ---
  15478. --- Application Phase ---
  15479. --- Firing Productions (PE) For State At Depth 1 ---
  15480. --- Inner Elaboration Phase, active level 1 (S1) ---
  15481. Firing apply*operator
  15482. -->
  15483. (I3 ^predict-no N1007 + :O )
  15484. Firing apply*operator*complete
  15485. -->
  15486. (I3 ^predict-yes N1006 - :O )
  15487. inner elaboration loop at bottom goal.
  15488. --- Change Working Memory (PE) ---
  15489. =>WM: (14148: I3 ^predict-no N1007)
  15490. <=WM: (14135: N1006 ^status complete)
  15491. <=WM: (14134: I3 ^predict-yes N1006)
  15492. --- Firing Productions (IE) For State At Depth 1 ---
  15493. --- Inner Elaboration Phase, active level 1 (S1) ---
  15494. Firing monitor*world
  15495. -->
  15496. I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
  15497. --- Change Working Memory (IE) ---
  15498. --- END Application Phase ---
  15499. --- Output Phase ---
  15500. ENV: Agent did: predict-no for direction L in state State-A
  15501. In State-A moving L
  15502. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  15503. predict error 0
  15504. dir: dir isU
  15505. --- END Output Phase ---
  15506. /|\--- Input Phase ---
  15507. =>WM: (14152: I2 ^dir U)
  15508. =>WM: (14151: I2 ^reward 1)
  15509. =>WM: (14150: I2 ^see 0)
  15510. =>WM: (14149: N1007 ^status complete)
  15511. <=WM: (14138: I2 ^dir L)
  15512. <=WM: (14137: I2 ^reward 1)
  15513. <=WM: (14136: I2 ^see 1)
  15514. =>WM: (14153: I2 ^level-1 L0-root)
  15515. <=WM: (14139: I2 ^level-1 L1-root)
  15516. --- END Input Phase ---
  15517. --- Proposal Phase ---
  15518. --- Inner Elaboration Phase, active level 1 (S1) ---
  15519. Firing elaborate*copy-see-to-output-link
  15520. -->
  15521. (I3 ^see 0 +)
  15522. Firing elaborate*reward*based*on*reward
  15523. -->
  15524. (R1011 ^value 1 +)
  15525. (R1 ^reward R1011 +)
  15526. Firing propose*predict-yes
  15527. -->
  15528. (O2015 ^name predict-yes +)
  15529. (S1 ^operator O2015 +)
  15530. Firing propose*predict-no
  15531. -->
  15532. (O2016 ^name predict-no +)
  15533. (S1 ^operator O2016 +)
  15534. Firing rl*prefer*rvt*predict-no*H0*6
  15535. -->
  15536. (S1 ^operator O2014 = 0.9999999999999999)
  15537. Firing rl*prefer*rvt*predict-yes*H0*5
  15538. -->
  15539. (S1 ^operator O2013 = 0.)
  15540. Firing prefer*rvt*predict-yes*H0
  15541. -->
  15542. Firing prefer*rvt*predict-no*H0
  15543. -->
  15544. Firing elaborate*copy-dir-to-output-link
  15545. -->
  15546. (I3 ^dir U +)
  15547. inner elaboration loop at bottom goal.
  15548. Retracting elaborate*copy-see-to-output-link
  15549. -->
  15550. (I3 ^see 1 +)
  15551. Retracting propose*predict-no
  15552. -->
  15553. (O2014 ^name predict-no +)
  15554. (S1 ^operator O2014 +)
  15555. Retracting propose*predict-yes
  15556. -->
  15557. (O2013 ^name predict-yes +)
  15558. (S1 ^operator O2013 +)
  15559. Retracting elaborate*reward*based*on*reward
  15560. -->
  15561. (R1010 ^value 1 +)
  15562. (R1 ^reward R1010 +)
  15563. Retracting elaborate*copy-dir-to-output-link
  15564. -->
  15565. (I3 ^dir L +)
  15566. Retracting rl*prefer*rvt*predict-no*H0*2*H1*11
  15567. -->
  15568. (S1 ^operator O2014 = 0.7449864646061185)
  15569. Retracting rl*prefer*rvt*predict-no*H0*2
  15570. -->
  15571. (S1 ^operator O2014 = 0.2550133610598087)
  15572. Retracting rl*prefer*rvt*predict-yes*H0*1*H1*20
  15573. -->
  15574. (S1 ^operator O2013 = 0.1693592933936033)
  15575. Retracting rl*prefer*rvt*predict-yes*H0*1
  15576. -->
  15577. (S1 ^operator O2013 = 0.5231203326136166)
  15578. =>WM: (14161: S1 ^operator O2016 +)
  15579. =>WM: (14160: S1 ^operator O2015 +)
  15580. =>WM: (14159: I3 ^dir U)
  15581. =>WM: (14158: O2016 ^name predict-no)
  15582. =>WM: (14157: O2015 ^name predict-yes)
  15583. =>WM: (14156: R1011 ^value 1)
  15584. =>WM: (14155: R1 ^reward R1011)
  15585. =>WM: (14154: I3 ^see 0)
  15586. <=WM: (14145: S1 ^operator O2013 +)
  15587. <=WM: (14146: S1 ^operator O2014 +)
  15588. <=WM: (14147: S1 ^operator O2014)
  15589. <=WM: (14130: I3 ^dir L)
  15590. <=WM: (14141: R1 ^reward R1010)
  15591. <=WM: (14140: I3 ^see 1)
  15592. <=WM: (14144: O2014 ^name predict-no)
  15593. <=WM: (14143: O2013 ^name predict-yes)
  15594. <=WM: (14142: R1010 ^value 1)
  15595. --- Inner Elaboration Phase, active level 1 (S1) ---
  15596. Firing prefer*rvt*predict-yes*H0
  15597. -->
  15598. Firing rl*prefer*rvt*predict-yes*H0*5
  15599. -->
  15600. (S1 ^operator O2015 = 0.)
  15601. Firing prefer*rvt*predict-no*H0
  15602. -->
  15603. Firing rl*prefer*rvt*predict-no*H0*6
  15604. -->
  15605. (S1 ^operator O2016 = 0.9999999999999999)
  15606. inner elaboration loop at bottom goal.
  15607. Retracting rl*prefer*rvt*predict-no*H0*6
  15608. -->
  15609. (S1 ^operator O2014 = 0.9999999999999999)
  15610. Retracting rl*prefer*rvt*predict-yes*H0*5
  15611. -->
  15612. (S1 ^operator O2013 = 0.)
  15613. --- END Proposal Phase ---
  15614. --- Decision Phase ---
  15615. RL update rl*prefer*rvt*predict-no*H0*2 0.631495 -0.376482 0.255013 -> 0.631495 -0.376482 0.255013(R,m,v=1,0.919192,0.0746552)
  15616. RL update rl*prefer*rvt*predict-no*H0*2*H1*11 0.368505 0.376482 0.744986 -> 0.368505 0.376482 0.744986(R,m,v=1,1,0)
  15617. =>WM: (14162: S1 ^operator O2016)
  15618. 1008: O: O2016 (predict-no)
  15619. --- END Decision Phase ---
  15620. --- Application Phase ---
  15621. --- Firing Productions (PE) For State At Depth 1 ---
  15622. --- Inner Elaboration Phase, active level 1 (S1) ---
  15623. Firing apply*operator
  15624. -->
  15625. (I3 ^predict-no N1008 + :O )
  15626. Firing apply*operator*complete
  15627. -->
  15628. (I3 ^predict-no N1007 - :O )
  15629. inner elaboration loop at bottom goal.
  15630. --- Change Working Memory (PE) ---
  15631. =>WM: (14163: I3 ^predict-no N1008)
  15632. <=WM: (14149: N1007 ^status complete)
  15633. <=WM: (14148: I3 ^predict-no N1007)
  15634. --- Firing Productions (IE) For State At Depth 1 ---
  15635. --- Inner Elaboration Phase, active level 1 (S1) ---
  15636. Firing monitor*world
  15637. -->
  15638. I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
  15639. --- Change Working Memory (IE) ---
  15640. --- END Application Phase ---
  15641. --- Output Phase ---
  15642. ENV: Agent did: predict-no for direction U in state State-A
  15643. In State-A moving U
  15644. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  15645. predict error 0
  15646. dir: dir isU
  15647. --- END Output Phase ---
  15648. -/|--- Input Phase ---
  15649. =>WM: (14167: I2 ^dir U)
  15650. =>WM: (14166: I2 ^reward 1)
  15651. =>WM: (14165: I2 ^see 0)
  15652. =>WM: (14164: N1008 ^status complete)
  15653. <=WM: (14152: I2 ^dir U)
  15654. <=WM: (14151: I2 ^reward 1)
  15655. <=WM: (14150: I2 ^see 0)
  15656. =>WM: (14168: I2 ^level-1 L0-root)
  15657. <=WM: (14153: I2 ^level-1 L0-root)
  15658. --- END Input Phase ---
  15659. --- Proposal Phase ---
  15660. --- Inner Elaboration Phase, active level 1 (S1) ---
  15661. Firing elaborate*copy-see-to-output-link
  15662. -->
  15663. (I3 ^see 0 +)
  15664. Firing elaborate*reward*based*on*reward
  15665. -->
  15666. (R1012 ^value 1 +)
  15667. (R1 ^reward R1012 +)
  15668. Firing propose*predict-yes
  15669. -->
  15670. (O2017 ^name predict-yes +)
  15671. (S1 ^operator O2017 +)
  15672. Firing propose*predict-no
  15673. -->
  15674. (O2018 ^name predict-no +)
  15675. (S1 ^operator O2018 +)
  15676. Firing rl*prefer*rvt*predict-no*H0*6
  15677. -->
  15678. (S1 ^operator O2016 = 0.9999999999999999)
  15679. Firing rl*prefer*rvt*predict-yes*H0*5
  15680. -->
  15681. (S1 ^operator O2015 = 0.)
  15682. Firing prefer*rvt*predict-yes*H0
  15683. -->
  15684. Firing prefer*rvt*predict-no*H0
  15685. -->
  15686. Firing elaborate*copy-dir-to-output-link
  15687. -->
  15688. (I3 ^dir U +)
  15689. inner