PageRenderTime 152ms CodeModel.GetById 37ms RepoModel.GetById 1ms app.codeStats 0ms

/flipv2/20121112-101138-2.5K-ReLST-Evan/stdout-flip-2.5K_1.txt

https://bitbucket.org/evan13579b/soar-ziggurat
Plain Text | 16488 lines | 15744 code | 744 blank | 0 comment | 0 complexity | 8fe8da33e930370e6e29c9100f9bdef9 MD5 | raw file
Possible License(s): BSD-3-Clause
  1. Seeding... 1
  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 1 ...
  10. soar> Entering slave mode:
  11. - log file 'rl-slave-2.5K_1.log'....
  12. - will exit slave mode after 2500 decisions
  13. waiting for commands from an externally connected sml process...
  14. -/|sleeping...
  15. \sleeping...
  16. -sleeping...
  17. /sleeping...
  18. |sleeping...
  19. \-/|\-/|\-/sleeping...
  20. |\-/|\-sleeping...
  21. /1: O: O1 (predict-yes)
  22. I see 0 and I'm going to do: predict-yes
  23. ENV: Agent did: predict-yes for direction L in state State-A
  24. In State-A moving L
  25. ENV: (next state, see, prediction correct?) = (State-A, 0, False)
  26. predict error 1
  27. dir: dir isU
  28. rule alias: '*'
  29. rule alias: '*'
  30. |\-/|\-/2: O: O4 (predict-no)
  31. I see 0 and I'm going to do: predict-no
  32. ENV: Agent did: predict-no for direction U in state State-A
  33. In State-A moving U
  34. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  35. predict error 0
  36. dir: dir isU
  37. |\-3: O: O5 (predict-yes)
  38. I see 1 and I'm going to do: predict-yes
  39. ENV: Agent did: predict-yes for direction U in state State-A
  40. In State-A moving U
  41. ENV: (next state, see, prediction correct?) = (State-A, 0, False)
  42. predict error 1
  43. dir: dir isL
  44. /|\4: O: O7 (predict-yes)
  45. I see 0 and I'm going to do: predict-yes
  46. ENV: Agent did: predict-yes for direction L in state State-A
  47. In State-A moving L
  48. ENV: (next state, see, prediction correct?) = (State-A, 0, False)
  49. predict error 1
  50. dir: dir isR
  51. -/5: O: O10 (predict-no)
  52. I see 0 and I'm going to do: predict-no
  53. ENV: Agent did: predict-no for direction R in state State-A
  54. In State-A moving R
  55. ENV: (next state, see, prediction correct?) = (State-B, 1, False)
  56. predict error 1
  57. dir: dir isR
  58. |6: O: O11 (predict-yes)
  59. I see 0 and I'm going to do: predict-yes
  60. ENV: Agent did: predict-yes for direction R in state State-B
  61. In State-B moving R
  62. ENV: (next state, see, prediction correct?) = (State-B, 0, False)
  63. predict error 1
  64. dir: dir isR
  65. \-/7: O: O13 (predict-yes)
  66. I see 0 and I'm going to do: predict-yes
  67. ENV: Agent did: predict-yes for direction R in state State-B
  68. In State-B moving R
  69. ENV: (next state, see, prediction correct?) = (State-B, 0, False)
  70. predict error 1
  71. dir: dir isU
  72. |\-8: O: O16 (predict-no)
  73. I see 0 and I'm going to do: predict-no
  74. ENV: Agent did: predict-no for direction U in state State-B
  75. In State-B moving U
  76. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  77. predict error 0
  78. dir: dir isL
  79. /|\9: O: O18 (predict-no)
  80. I see 1 and I'm going to do: predict-no
  81. ENV: Agent did: predict-no for direction L in state State-B
  82. In State-B moving L
  83. ENV: (next state, see, prediction correct?) = (State-A, 1, False)
  84. predict error 1
  85. dir: dir isL
  86. -/|10: O: O20 (predict-no)
  87. I see 0 and I'm going to do: predict-no
  88. ENV: Agent did: predict-no for direction L in state State-A
  89. In State-A moving L
  90. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  91. predict error 0
  92. dir: dir isU
  93. \-/11: O: O22 (predict-no)
  94. I see 1 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: O23 (predict-yes)
  105. I see 1 and I'm going to do: predict-yes
  106. ENV: Agent did: predict-yes for direction R in state State-A
  107. In State-A moving R
  108. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  109. predict error 0
  110. dir: dir isU
  111. \-/13: O: O26 (predict-no)
  112. I see 1 and I'm going to do: predict-no
  113. ENV: Agent did: predict-no for direction U in state State-B
  114. In State-B moving U
  115. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  116. predict error 0
  117. dir: dir isL
  118. |\-14: O: O28 (predict-no)
  119. I see 1 and I'm going to do: predict-no
  120. ENV: Agent did: predict-no for direction L in state State-B
  121. In State-B moving L
  122. ENV: (next state, see, prediction correct?) = (State-A, 1, False)
  123. predict error 1
  124. dir: dir isR
  125. /|15: O: O30 (predict-no)
  126. I see 0 and I'm going to do: predict-no
  127. ENV: Agent did: predict-no for direction R in state State-A
  128. In State-A moving R
  129. ENV: (next state, see, prediction correct?) = (State-B, 1, False)
  130. predict error 1
  131. dir: dir isU
  132. \-/16: O: O32 (predict-no)
  133. I see 0 and I'm going to do: predict-no
  134. ENV: Agent did: predict-no for direction U in state State-B
  135. In State-B moving U
  136. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  137. predict error 0
  138. dir: dir isL
  139. |\-/17: O: O33 (predict-yes)
  140. I see 1 and I'm going to do: predict-yes
  141. ENV: Agent did: predict-yes for direction L in state State-B
  142. In State-B moving L
  143. ENV: (next state, see, prediction correct?) = (State-A, 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-A
  149. In State-A moving U
  150. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  151. predict error 0
  152. dir: dir isU
  153. /|\19: O: O38 (predict-no)
  154. I see 1 and I'm going to do: predict-no
  155. ENV: Agent did: predict-no for direction U in state State-A
  156. In State-A moving U
  157. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  158. predict error 0
  159. dir: dir isL
  160. -/|20: O: O39 (predict-yes)
  161. I see 1 and I'm going to do: predict-yes
  162. ENV: Agent did: predict-yes for direction L in state State-A
  163. In State-A moving L
  164. ENV: (next state, see, prediction correct?) = (State-A, 0, False)
  165. predict error 1
  166. dir: dir isL
  167. \-21: O: O41 (predict-yes)
  168. I see 0 and I'm going to do: predict-yes
  169. ENV: Agent did: predict-yes for direction L in state State-A
  170. In State-A moving L
  171. ENV: (next state, see, prediction correct?) = (State-A, 0, False)
  172. predict error 1
  173. dir: dir isR
  174. /22: O: O43 (predict-yes)
  175. I see 0 and I'm going to do: predict-yes
  176. ENV: Agent did: predict-yes for direction R in state State-A
  177. In State-A moving R
  178. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  179. predict error 0
  180. dir: dir isU
  181. |\-23: O: O46 (predict-no)
  182. I see 1 and I'm going to do: predict-no
  183. ENV: Agent did: predict-no for direction U in state State-B
  184. In State-B moving U
  185. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  186. predict error 0
  187. dir: dir isR
  188. /24: O: O47 (predict-yes)
  189. I see 1 and I'm going to do: predict-yes
  190. ENV: Agent did: predict-yes for direction R in state State-B
  191. In State-B moving R
  192. ENV: (next state, see, prediction correct?) = (State-B, 0, 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 isR
  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 R in state State-A
  205. In State-A moving R
  206. ENV: (next state, see, prediction correct?) = (State-B, 1, False)
  207. predict error 1
  208. dir: dir isL
  209. \-/27: O: O54 (predict-no)
  210. I see 0 and I'm going to do: predict-no
  211. ENV: Agent did: predict-no for direction L in state State-B
  212. In State-B moving L
  213. ENV: (next state, see, prediction correct?) = (State-A, 1, False)
  214. predict error 1
  215. dir: dir isL
  216. |\-28: O: O56 (predict-no)
  217. I see 0 and I'm going to do: predict-no
  218. ENV: Agent did: predict-no for direction L in state State-A
  219. In State-A moving L
  220. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  221. predict error 0
  222. dir: dir isR
  223. /|\29: O: O57 (predict-yes)
  224. I see 1 and I'm going to do: predict-yes
  225. ENV: Agent did: predict-yes for direction R in state State-A
  226. In State-A moving R
  227. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  228. predict error 0
  229. dir: dir isR
  230. -/|30: O: O59 (predict-yes)
  231. I see 1 and I'm going to do: predict-yes
  232. ENV: Agent did: predict-yes for direction R in state State-B
  233. In State-B moving R
  234. ENV: (next state, see, prediction correct?) = (State-B, 0, False)
  235. predict error 1
  236. dir: dir isL
  237. \-/31: O: O62 (predict-no)
  238. I see 0 and I'm going to do: predict-no
  239. ENV: Agent did: predict-no for direction L in state State-B
  240. In State-B moving L
  241. ENV: (next state, see, prediction correct?) = (State-A, 1, False)
  242. predict error 1
  243. dir: dir isL
  244. |32: O: O64 (predict-no)
  245. I see 0 and I'm going to do: predict-no
  246. ENV: Agent did: predict-no for direction L in state State-A
  247. In State-A moving L
  248. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  249. predict error 0
  250. dir: dir isL
  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 L in state State-A
  254. In State-A moving L
  255. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  256. predict error 0
  257. dir: dir isR
  258. |\-34: O: O67 (predict-yes)
  259. I see 1 and I'm going to do: predict-yes
  260. ENV: Agent did: predict-yes for direction R in state State-A
  261. In State-A moving R
  262. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  263. predict error 0
  264. dir: dir isL
  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 L in state State-B
  268. In State-B moving L
  269. ENV: (next state, see, prediction correct?) = (State-A, 1, False)
  270. predict error 1
  271. dir: dir isL
  272. /|\36: O: O72 (predict-no)
  273. I see 0 and I'm going to do: predict-no
  274. ENV: Agent did: predict-no for direction L in state State-A
  275. In State-A moving L
  276. ENV: (next state, see, prediction correct?) = (State-A, 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-A
  282. In State-A moving U
  283. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  284. predict error 0
  285. dir: dir isR
  286. \-38: O: O76 (predict-no)
  287. I see 1 and I'm going to do: predict-no
  288. ENV: Agent did: predict-no for direction R in state State-A
  289. In State-A moving R
  290. ENV: (next state, see, prediction correct?) = (State-B, 1, False)
  291. predict error 1
  292. dir: dir isR
  293. /|39: O: O77 (predict-yes)
  294. I see 0 and I'm going to do: predict-yes
  295. ENV: Agent did: predict-yes for direction R in state State-B
  296. In State-B moving R
  297. ENV: (next state, see, prediction correct?) = (State-B, 0, False)
  298. predict error 1
  299. dir: dir isL
  300. \-/40: O: O80 (predict-no)
  301. I see 0 and I'm going to do: predict-no
  302. ENV: Agent did: predict-no for direction L in state State-B
  303. In State-B moving L
  304. ENV: (next state, see, prediction correct?) = (State-A, 1, False)
  305. predict error 1
  306. dir: dir isU
  307. |41: O: O82 (predict-no)
  308. I see 0 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 isU
  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 U in state State-A
  317. In State-A moving U
  318. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  319. predict error 0
  320. dir: dir isL
  321. -43: O: O85 (predict-yes)
  322. I see 1 and I'm going to do: predict-yes
  323. ENV: Agent did: predict-yes for direction L in state State-A
  324. In State-A moving L
  325. ENV: (next state, see, prediction correct?) = (State-A, 0, False)
  326. predict error 1
  327. dir: dir isL
  328. /|\44: O: O88 (predict-no)
  329. I see 0 and I'm going to do: predict-no
  330. ENV: Agent did: predict-no for direction L in state State-A
  331. In State-A moving L
  332. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  333. predict error 0
  334. dir: dir isU
  335. -/|45: O: O90 (predict-no)
  336. I see 1 and I'm going to do: predict-no
  337. ENV: Agent did: predict-no for direction U in state State-A
  338. In State-A moving U
  339. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  340. predict error 0
  341. dir: dir isU
  342. \-46: O: O92 (predict-no)
  343. I see 1 and I'm going to do: predict-no
  344. ENV: Agent did: predict-no for direction U in state State-A
  345. In State-A moving U
  346. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  347. predict error 0
  348. dir: dir isU
  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 U in state State-A
  352. In State-A moving U
  353. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  354. predict error 0
  355. dir: dir isR
  356. -48: O: O95 (predict-yes)
  357. I see 1 and I'm going to do: predict-yes
  358. ENV: Agent did: predict-yes for direction R in state State-A
  359. In State-A moving R
  360. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  361. predict error 0
  362. dir: dir isU
  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 U in state State-B
  366. In State-B moving U
  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 isL
  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 L in state State-B
  381. In State-B moving L
  382. ENV: (next state, see, prediction correct?) = (State-A, 1, False)
  383. predict error 1
  384. dir: dir isR
  385. rule alias: '*'
  386. rule alias: '*'
  387. \52: O: O104 (predict-no)
  388. I see 0 and I'm going to do: predict-no
  389. ENV: Agent did: predict-no for direction R in state State-A
  390. In State-A moving R
  391. ENV: (next state, see, prediction correct?) = (State-B, 1, False)
  392. predict error 1
  393. dir: dir isU
  394. -/53: O: O106 (predict-no)
  395. I see 0 and I'm going to do: predict-no
  396. ENV: Agent did: predict-no for direction U in state State-B
  397. In State-B moving U
  398. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  399. predict error 0
  400. dir: dir isU
  401. |\-54: O: O108 (predict-no)
  402. I see 1 and I'm going to do: predict-no
  403. ENV: Agent did: predict-no for direction U in state State-B
  404. In State-B moving U
  405. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  406. predict error 0
  407. dir: dir isR
  408. /|\55: O: O109 (predict-yes)
  409. I see 1 and I'm going to do: predict-yes
  410. ENV: Agent did: predict-yes for direction R in state State-B
  411. In State-B moving R
  412. ENV: (next state, see, prediction correct?) = (State-B, 0, False)
  413. predict error 1
  414. dir: dir isR
  415. -/56: O: O111 (predict-yes)
  416. I see 0 and I'm going to do: predict-yes
  417. ENV: Agent did: predict-yes for direction R in state State-B
  418. In State-B moving R
  419. ENV: (next state, see, prediction correct?) = (State-B, 0, False)
  420. predict error 1
  421. dir: dir isL
  422. |\57: O: O114 (predict-no)
  423. I see 0 and I'm going to do: predict-no
  424. ENV: Agent did: predict-no for direction L in state State-B
  425. In State-B moving L
  426. ENV: (next state, see, prediction correct?) = (State-A, 1, False)
  427. predict error 1
  428. dir: dir isL
  429. -/58: O: O116 (predict-no)
  430. I see 0 and I'm going to do: predict-no
  431. ENV: Agent did: predict-no for direction L in state State-A
  432. In State-A moving L
  433. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  434. predict error 0
  435. dir: dir isU
  436. |\-59: O: O118 (predict-no)
  437. I see 1 and I'm going to do: predict-no
  438. ENV: Agent did: predict-no for direction U in state State-A
  439. In State-A moving U
  440. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  441. predict error 0
  442. dir: dir isR
  443. /|\60: O: O119 (predict-yes)
  444. I see 1 and I'm going to do: predict-yes
  445. ENV: Agent did: predict-yes for direction R in state State-A
  446. In State-A moving R
  447. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  448. predict error 0
  449. dir: dir isL
  450. -/|61: O: O122 (predict-no)
  451. I see 1 and I'm going to do: predict-no
  452. ENV: Agent did: predict-no for direction L in state State-B
  453. In State-B moving L
  454. ENV: (next state, see, prediction correct?) = (State-A, 1, False)
  455. predict error 1
  456. dir: dir isR
  457. rule alias: '*'
  458. rule alias: '*'
  459. rule alias: '*'
  460. rule alias: '*'
  461. rule alias: '*'
  462. rule alias: '*'
  463. rule alias: '*'
  464. rule alias: '*'
  465. \62: O: O123 (predict-yes)
  466. I see 0 and I'm going to do: predict-yes
  467. ENV: Agent did: predict-yes for direction R in state State-A
  468. In State-A moving R
  469. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  470. predict error 0
  471. dir: dir isU
  472. -/|63: O: O126 (predict-no)
  473. I see 1 and I'm going to do: predict-no
  474. ENV: Agent did: predict-no for direction U in state State-B
  475. In State-B moving U
  476. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  477. predict error 0
  478. dir: dir isU
  479. \-/64: O: O128 (predict-no)
  480. I see 1 and I'm going to do: predict-no
  481. ENV: Agent did: predict-no for direction U in state State-B
  482. In State-B moving U
  483. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  484. predict error 0
  485. dir: dir isR
  486. |\-65: O: O129 (predict-yes)
  487. I see 1 and I'm going to do: predict-yes
  488. ENV: Agent did: predict-yes for direction R in state State-B
  489. In State-B moving R
  490. ENV: (next state, see, prediction correct?) = (State-B, 0, False)
  491. predict error 1
  492. dir: dir isR
  493. /|66: O: O132 (predict-no)
  494. I see 0 and I'm going to do: predict-no
  495. ENV: Agent did: predict-no for direction R in state State-B
  496. In State-B moving R
  497. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  498. predict error 0
  499. dir: dir isR
  500. \-/67: O: O134 (predict-no)
  501. I see 1 and I'm going to do: predict-no
  502. ENV: Agent did: predict-no for direction R in state State-B
  503. In State-B moving R
  504. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  505. predict error 0
  506. dir: dir isU
  507. |\68: O: O136 (predict-no)
  508. I see 1 and I'm going to do: predict-no
  509. ENV: Agent did: predict-no for direction U in state State-B
  510. In State-B moving U
  511. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  512. predict error 0
  513. dir: dir isR
  514. -/|69: O: O138 (predict-no)
  515. I see 1 and I'm going to do: predict-no
  516. ENV: Agent did: predict-no for direction R in state State-B
  517. In State-B moving R
  518. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  519. predict error 0
  520. dir: dir isR
  521. \70: O: O139 (predict-yes)
  522. I see 1 and I'm going to do: predict-yes
  523. ENV: Agent did: predict-yes for direction R in state State-B
  524. In State-B moving R
  525. ENV: (next state, see, prediction correct?) = (State-B, 0, False)
  526. predict error 1
  527. dir: dir isR
  528. -/71: O: O142 (predict-no)
  529. I see 0 and I'm going to do: predict-no
  530. ENV: Agent did: predict-no for direction R in state State-B
  531. In State-B moving R
  532. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  533. predict error 0
  534. dir: dir isL
  535. |72: O: O144 (predict-no)
  536. I see 1 and I'm going to do: predict-no
  537. ENV: Agent did: predict-no for direction L in state State-B
  538. In State-B moving L
  539. ENV: (next state, see, prediction correct?) = (State-A, 1, False)
  540. predict error 1
  541. dir: dir isL
  542. \-/73: O: O146 (predict-no)
  543. I see 0 and I'm going to do: predict-no
  544. ENV: Agent did: predict-no for direction L in state State-A
  545. In State-A moving L
  546. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  547. predict error 0
  548. dir: dir isU
  549. |\-74: O: O148 (predict-no)
  550. I see 1 and I'm going to do: predict-no
  551. ENV: Agent did: predict-no for direction U in state State-A
  552. In State-A moving U
  553. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  554. predict error 0
  555. dir: dir isU
  556. /|\75: O: O149 (predict-yes)
  557. I see 1 and I'm going to do: predict-yes
  558. ENV: Agent did: predict-yes for direction U in state State-A
  559. In State-A moving U
  560. ENV: (next state, see, prediction correct?) = (State-A, 0, False)
  561. predict error 1
  562. dir: dir isR
  563. -/|76: O: O151 (predict-yes)
  564. I see 0 and I'm going to do: predict-yes
  565. ENV: Agent did: predict-yes for direction R in state State-A
  566. In State-A moving R
  567. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  568. predict error 0
  569. dir: dir isR
  570. \-/77: O: O154 (predict-no)
  571. I see 1 and I'm going to do: predict-no
  572. ENV: Agent did: predict-no for direction R in state State-B
  573. In State-B moving R
  574. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  575. predict error 0
  576. dir: dir isL
  577. |\-78: O: O156 (predict-no)
  578. I see 1 and I'm going to do: predict-no
  579. ENV: Agent did: predict-no for direction L in state State-B
  580. In State-B moving L
  581. ENV: (next state, see, prediction correct?) = (State-A, 1, False)
  582. predict error 1
  583. dir: dir isR
  584. /|\79: O: O158 (predict-no)
  585. I see 0 and I'm going to do: predict-no
  586. ENV: Agent did: predict-no for direction R in state State-A
  587. In State-A moving R
  588. ENV: (next state, see, prediction correct?) = (State-B, 1, False)
  589. predict error 1
  590. dir: dir isU
  591. -/80: O: O160 (predict-no)
  592. I see 0 and I'm going to do: predict-no
  593. ENV: Agent did: predict-no for direction U in state State-B
  594. In State-B moving U
  595. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  596. predict error 0
  597. dir: dir isU
  598. |\-81: O: O162 (predict-no)
  599. I see 1 and I'm going to do: predict-no
  600. ENV: Agent did: predict-no for direction U in state State-B
  601. In State-B moving U
  602. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  603. predict error 0
  604. dir: dir isR
  605. /82: O: O163 (predict-yes)
  606. I see 1 and I'm going to do: predict-yes
  607. ENV: Agent did: predict-yes for direction R in state State-B
  608. In State-B moving R
  609. ENV: (next state, see, prediction correct?) = (State-B, 0, False)
  610. predict error 1
  611. dir: dir isU
  612. |\-83: O: O166 (predict-no)
  613. I see 0 and I'm going to do: predict-no
  614. ENV: Agent did: predict-no for direction U in state State-B
  615. In State-B moving U
  616. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  617. predict error 0
  618. dir: dir isL
  619. /|\84: O: O167 (predict-yes)
  620. I see 1 and I'm going to do: predict-yes
  621. ENV: Agent did: predict-yes for direction L in state State-B
  622. In State-B moving L
  623. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  624. predict error 0
  625. dir: dir isR
  626. -/85: O: O170 (predict-no)
  627. I see 1 and I'm going to do: predict-no
  628. ENV: Agent did: predict-no for direction R in state State-A
  629. In State-A moving R
  630. ENV: (next state, see, prediction correct?) = (State-B, 1, False)
  631. predict error 1
  632. dir: dir isU
  633. |\-86: O: O172 (predict-no)
  634. I see 0 and I'm going to do: predict-no
  635. ENV: Agent did: predict-no for direction U in state State-B
  636. In State-B moving U
  637. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  638. predict error 0
  639. dir: dir isR
  640. /|87: O: O174 (predict-no)
  641. I see 1 and I'm going to do: predict-no
  642. ENV: Agent did: predict-no for direction R in state State-B
  643. In State-B moving R
  644. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  645. predict error 0
  646. dir: dir isR
  647. \-/88: O: O176 (predict-no)
  648. I see 1 and I'm going to do: predict-no
  649. ENV: Agent did: predict-no for direction R in state State-B
  650. In State-B moving R
  651. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  652. predict error 0
  653. dir: dir isL
  654. |\89: O: O177 (predict-yes)
  655. I see 1 and I'm going to do: predict-yes
  656. ENV: Agent did: predict-yes for direction L in state State-B
  657. In State-B moving L
  658. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  659. predict error 0
  660. dir: dir isR
  661. -/|90: O: O179 (predict-yes)
  662. I see 1 and I'm going to do: predict-yes
  663. ENV: Agent did: predict-yes for direction R in state State-A
  664. In State-A moving R
  665. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  666. predict error 0
  667. dir: dir isU
  668. \-/91: O: O182 (predict-no)
  669. I see 1 and I'm going to do: predict-no
  670. ENV: Agent did: predict-no for direction U in state State-B
  671. In State-B moving U
  672. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  673. predict error 0
  674. dir: dir isL
  675. |92: O: O183 (predict-yes)
  676. I see 1 and I'm going to do: predict-yes
  677. ENV: Agent did: predict-yes for direction L in state State-B
  678. In State-B moving L
  679. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  680. predict error 0
  681. dir: dir isU
  682. \-/93: O: O186 (predict-no)
  683. I see 1 and I'm going to do: predict-no
  684. ENV: Agent did: predict-no for direction U in state State-A
  685. In State-A moving U
  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 isU
  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 U in state State-A
  699. In State-A moving U
  700. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  701. predict error 0
  702. dir: dir isU
  703. \-96: O: O191 (predict-yes)
  704. I see 1 and I'm going to do: predict-yes
  705. ENV: Agent did: predict-yes for direction U in state State-A
  706. In State-A moving U
  707. ENV: (next state, see, prediction correct?) = (State-A, 0, False)
  708. predict error 1
  709. dir: dir isU
  710. /|\97: O: O194 (predict-no)
  711. I see 0 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: O196 (predict-no)
  718. I see 1 and I'm going to do: predict-no
  719. ENV: Agent did: predict-no for direction R in state State-A
  720. In State-A moving R
  721. ENV: (next state, see, prediction correct?) = (State-B, 1, False)
  722. predict error 1
  723. dir: dir isR
  724. |\-99: O: O198 (predict-no)
  725. I see 0 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 isL
  738. \-/101: O: O201 (predict-yes)
  739. I see 1 and I'm going to do: predict-yes
  740. ENV: Agent did: predict-yes for direction L in state State-B
  741. In State-B moving L
  742. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  743. predict error 0
  744. dir: dir isU
  745. |\102: O: O203 (predict-yes)
  746. I see 1 and I'm going to do: predict-yes
  747. ENV: Agent did: predict-yes for direction U in state State-A
  748. In State-A moving U
  749. ENV: (next state, see, prediction correct?) = (State-A, 0, False)
  750. predict error 1
  751. dir: dir isR
  752. -/|103: O: O205 (predict-yes)
  753. I see 0 and I'm going to do: predict-yes
  754. ENV: Agent did: predict-yes for direction R in state State-A
  755. In State-A moving R
  756. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  757. predict error 0
  758. dir: dir isL
  759. \-/104: O: O207 (predict-yes)
  760. I see 1 and I'm going to do: predict-yes
  761. ENV: Agent did: predict-yes for direction L in state State-B
  762. In State-B moving L
  763. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  764. predict error 0
  765. dir: dir isR
  766. |\-105: O: O209 (predict-yes)
  767. I see 1 and I'm going to do: predict-yes
  768. ENV: Agent did: predict-yes for direction R in state State-A
  769. In State-A moving R
  770. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  771. predict error 0
  772. dir: dir isR
  773. /|\106: O: O211 (predict-yes)
  774. I see 1 and I'm going to do: predict-yes
  775. ENV: Agent did: predict-yes for direction R in state State-B
  776. In State-B moving R
  777. ENV: (next state, see, prediction correct?) = (State-B, 0, False)
  778. predict error 1
  779. dir: dir isR
  780. -/|107: O: O213 (predict-yes)
  781. I see 0 and I'm going to do: predict-yes
  782. ENV: Agent did: predict-yes for direction R in state State-B
  783. In State-B moving R
  784. ENV: (next state, see, prediction correct?) = (State-B, 0, False)
  785. predict error 1
  786. dir: dir isR
  787. \-/108: O: O216 (predict-no)
  788. I see 0 and I'm going to do: predict-no
  789. ENV: Agent did: predict-no for direction R in state State-B
  790. In State-B moving R
  791. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  792. predict error 0
  793. dir: dir isR
  794. |\109: O: O218 (predict-no)
  795. I see 1 and I'm going to do: predict-no
  796. ENV: Agent did: predict-no for direction R in state State-B
  797. In State-B moving R
  798. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  799. predict error 0
  800. dir: dir isR
  801. -/|110: O: O220 (predict-no)
  802. I see 1 and I'm going to do: predict-no
  803. ENV: Agent did: predict-no for direction R in state State-B
  804. In State-B moving R
  805. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  806. predict error 0
  807. dir: dir isR
  808. \-/111: O: O222 (predict-no)
  809. I see 1 and I'm going to do: predict-no
  810. ENV: Agent did: predict-no for direction R in state State-B
  811. In State-B moving R
  812. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  813. predict error 0
  814. dir: dir isR
  815. |112: O: O223 (predict-yes)
  816. I see 1 and I'm going to do: predict-yes
  817. ENV: Agent did: predict-yes for direction R in state State-B
  818. In State-B moving R
  819. ENV: (next state, see, prediction correct?) = (State-B, 0, False)
  820. predict error 1
  821. dir: dir isL
  822. \113: O: O225 (predict-yes)
  823. I see 0 and I'm going to do: predict-yes
  824. ENV: Agent did: predict-yes for direction L in state State-B
  825. In State-B moving L
  826. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  827. predict error 0
  828. dir: dir isL
  829. -/|114: O: O228 (predict-no)
  830. I see 1 and I'm going to do: predict-no
  831. ENV: Agent did: predict-no for direction L in state State-A
  832. In State-A moving L
  833. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  834. predict error 0
  835. dir: dir isL
  836. \-/115: O: O230 (predict-no)
  837. I see 1 and I'm going to do: predict-no
  838. ENV: Agent did: predict-no for direction L in state State-A
  839. In State-A moving L
  840. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  841. predict error 0
  842. dir: dir isR
  843. |\116: O: O232 (predict-no)
  844. I see 1 and I'm going to do: predict-no
  845. ENV: Agent did: predict-no for direction R in state State-A
  846. In State-A moving R
  847. ENV: (next state, see, prediction correct?) = (State-B, 1, False)
  848. predict error 1
  849. dir: dir isU
  850. -/|117: O: O234 (predict-no)
  851. I see 0 and I'm going to do: predict-no
  852. ENV: Agent did: predict-no for direction U in state State-B
  853. In State-B moving U
  854. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  855. predict error 0
  856. dir: dir isU
  857. \-/118: O: O236 (predict-no)
  858. I see 1 and I'm going to do: predict-no
  859. ENV: Agent did: predict-no for direction U in state State-B
  860. In State-B moving U
  861. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  862. predict error 0
  863. dir: dir isU
  864. |\119: O: O238 (predict-no)
  865. I see 1 and I'm going to do: predict-no
  866. ENV: Agent did: predict-no for direction U in state State-B
  867. In State-B moving U
  868. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  869. predict error 0
  870. dir: dir isU
  871. -/120: O: O239 (predict-yes)
  872. I see 1 and I'm going to do: predict-yes
  873. ENV: Agent did: predict-yes for direction U in state State-B
  874. In State-B moving U
  875. ENV: (next state, see, prediction correct?) = (State-B, 0, False)
  876. predict error 1
  877. dir: dir isL
  878. |\-/121: O: O241 (predict-yes)
  879. I see 0 and I'm going to do: predict-yes
  880. ENV: Agent did: predict-yes for direction L in state State-B
  881. In State-B moving L
  882. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  883. predict error 0
  884. dir: dir isU
  885. rule alias: '*'
  886. rule alias: '*'
  887. |122: O: O244 (predict-no)
  888. I see 1 and I'm going to do: predict-no
  889. ENV: Agent did: predict-no for direction U in state State-A
  890. In State-A moving U
  891. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  892. predict error 0
  893. dir: dir isU
  894. \-/123: O: O246 (predict-no)
  895. I see 1 and I'm going to do: predict-no
  896. ENV: Agent did: predict-no for direction U in state State-A
  897. In State-A moving U
  898. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  899. predict error 0
  900. dir: dir isL
  901. |\-124: O: O248 (predict-no)
  902. I see 1 and I'm going to do: predict-no
  903. ENV: Agent did: predict-no for direction L in state State-A
  904. In State-A moving L
  905. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  906. predict error 0
  907. dir: dir isL
  908. /|\125: O: O250 (predict-no)
  909. I see 1 and I'm going to do: predict-no
  910. ENV: Agent did: predict-no for direction L in state State-A
  911. In State-A moving L
  912. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  913. predict error 0
  914. dir: dir isL
  915. -/|126: O: O252 (predict-no)
  916. I see 1 and I'm going to do: predict-no
  917. ENV: Agent did: predict-no for direction L in state State-A
  918. In State-A moving L
  919. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  920. predict error 0
  921. dir: dir isU
  922. \-127: O: O254 (predict-no)
  923. I see 1 and I'm going to do: predict-no
  924. ENV: Agent did: predict-no for direction U in state State-A
  925. In State-A moving U
  926. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  927. predict error 0
  928. dir: dir isL
  929. /|\128: O: O256 (predict-no)
  930. I see 1 and I'm going to do: predict-no
  931. ENV: Agent did: predict-no for direction L in state State-A
  932. In State-A moving L
  933. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  934. predict error 0
  935. dir: dir isL
  936. -/|129: O: O258 (predict-no)
  937. I see 1 and I'm going to do: predict-no
  938. ENV: Agent did: predict-no for direction L in state State-A
  939. In State-A moving L
  940. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  941. predict error 0
  942. dir: dir isR
  943. \-/130: O: O259 (predict-yes)
  944. I see 1 and I'm going to do: predict-yes
  945. ENV: Agent did: predict-yes for direction R in state State-A
  946. In State-A moving R
  947. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  948. predict error 0
  949. dir: dir isR
  950. |\131: O: O262 (predict-no)
  951. I see 1 and I'm going to do: predict-no
  952. ENV: Agent did: predict-no for direction R in state State-B
  953. In State-B moving R
  954. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  955. predict error 0
  956. dir: dir isL
  957. -132: O: O263 (predict-yes)
  958. I see 1 and I'm going to do: predict-yes
  959. ENV: Agent did: predict-yes for direction L in state State-B
  960. In State-B moving L
  961. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  962. predict error 0
  963. dir: dir isL
  964. /|\133: O: O266 (predict-no)
  965. I see 1 and I'm going to do: predict-no
  966. ENV: Agent did: predict-no for direction L in state State-A
  967. In State-A moving L
  968. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  969. predict error 0
  970. dir: dir isR
  971. -/|134: O: O267 (predict-yes)
  972. I see 1 and I'm going to do: predict-yes
  973. ENV: Agent did: predict-yes for direction R in state State-A
  974. In State-A moving R
  975. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  976. predict error 0
  977. dir: dir isL
  978. \-135: O: O270 (predict-no)
  979. I see 1 and I'm going to do: predict-no
  980. ENV: Agent did: predict-no for direction L in state State-B
  981. In State-B moving L
  982. ENV: (next state, see, prediction correct?) = (State-A, 1, False)
  983. predict error 1
  984. dir: dir isL
  985. /|\136: O: O272 (predict-no)
  986. I see 0 and I'm going to do: predict-no
  987. ENV: Agent did: predict-no for direction L in state State-A
  988. In State-A moving L
  989. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  990. predict error 0
  991. dir: dir isU
  992. -/|137: O: O274 (predict-no)
  993. I see 1 and I'm going to do: predict-no
  994. ENV: Agent did: predict-no for direction U in state State-A
  995. In State-A moving U
  996. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  997. predict error 0
  998. dir: dir isR
  999. \-138: O: O276 (predict-no)
  1000. I see 1 and I'm going to do: predict-no
  1001. ENV: Agent did: predict-no for direction R in state State-A
  1002. In State-A moving R
  1003. ENV: (next state, see, prediction correct?) = (State-B, 1, False)
  1004. predict error 1
  1005. dir: dir isL
  1006. /|139: O: O277 (predict-yes)
  1007. I see 0 and I'm going to do: predict-yes
  1008. ENV: Agent did: predict-yes for direction L in state State-B
  1009. In State-B moving L
  1010. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  1011. predict error 0
  1012. dir: dir isR
  1013. \-/140: O: O279 (predict-yes)
  1014. I see 1 and I'm going to do: predict-yes
  1015. ENV: Agent did: predict-yes for direction R in state State-A
  1016. In State-A moving R
  1017. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  1018. predict error 0
  1019. dir: dir isL
  1020. |\-141: O: O282 (predict-no)
  1021. I see 1 and I'm going to do: predict-no
  1022. ENV: Agent did: predict-no for direction L in state State-B
  1023. In State-B moving L
  1024. ENV: (next state, see, prediction correct?) = (State-A, 1, False)
  1025. predict error 1
  1026. dir: dir isR
  1027. /142: O: O283 (predict-yes)
  1028. I see 0 and I'm going to do: predict-yes
  1029. ENV: Agent did: predict-yes for direction R in state State-A
  1030. In State-A moving R
  1031. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  1032. predict error 0
  1033. dir: dir isR
  1034. |\-143: O: O286 (predict-no)
  1035. I see 1 and I'm going to do: predict-no
  1036. ENV: Agent did: predict-no for direction R in state State-B
  1037. In State-B moving R
  1038. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  1039. predict error 0
  1040. dir: dir isL
  1041. /|\144: O: O287 (predict-yes)
  1042. I see 1 and I'm going to do: predict-yes
  1043. ENV: Agent did: predict-yes for direction L in state State-B
  1044. In State-B moving L
  1045. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  1046. predict error 0
  1047. dir: dir isL
  1048. -145: O: O290 (predict-no)
  1049. I see 1 and I'm going to do: predict-no
  1050. ENV: Agent did: predict-no for direction L in state State-A
  1051. In State-A moving L
  1052. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  1053. predict error 0
  1054. dir: dir isU
  1055. /|146: O: O292 (predict-no)
  1056. I see 1 and I'm going to do: predict-no
  1057. ENV: Agent did: predict-no for direction U in state State-A
  1058. In State-A moving U
  1059. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  1060. predict error 0
  1061. dir: dir isR
  1062. \-147: O: O294 (predict-no)
  1063. I see 1 and I'm going to do: predict-no
  1064. ENV: Agent did: predict-no for direction R in state State-A
  1065. In State-A moving R
  1066. ENV: (next state, see, prediction correct?) = (State-B, 1, False)
  1067. predict error 1
  1068. dir: dir isL
  1069. /148: O: O295 (predict-yes)
  1070. I see 0 and I'm going to do: predict-yes
  1071. ENV: Agent did: predict-yes for direction L in state State-B
  1072. In State-B moving L
  1073. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  1074. predict error 0
  1075. dir: dir isR
  1076. |\-149: O: O297 (predict-yes)
  1077. I see 1 and I'm going to do: predict-yes
  1078. ENV: Agent did: predict-yes for direction R in state State-A
  1079. In State-A moving R
  1080. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  1081. predict error 0
  1082. dir: dir isU
  1083. /|\150: O: O300 (predict-no)
  1084. I see 1 and I'm going to do: predict-no
  1085. ENV: Agent did: predict-no for direction U in state State-B
  1086. In State-B moving U
  1087. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  1088. predict error 0
  1089. dir: dir isL
  1090. -/|151: O: O301 (predict-yes)
  1091. I see 1 and I'm going to do: predict-yes
  1092. ENV: Agent did: predict-yes for direction L in state State-B
  1093. In State-B moving L
  1094. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  1095. predict error 0
  1096. dir: dir isL
  1097. \152: O: O303 (predict-yes)
  1098. I see 1 and I'm going to do: predict-yes
  1099. ENV: Agent did: predict-yes for direction L in state State-A
  1100. In State-A moving L
  1101. ENV: (next state, see, prediction correct?) = (State-A, 0, False)
  1102. predict error 1
  1103. dir: dir isL
  1104. -/153: O: O306 (predict-no)
  1105. I see 0 and I'm going to do: predict-no
  1106. ENV: Agent did: predict-no for direction L in state State-A
  1107. In State-A moving L
  1108. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  1109. predict error 0
  1110. dir: dir isU
  1111. |\-154: O: O308 (predict-no)
  1112. I see 1 and I'm going to do: predict-no
  1113. ENV: Agent did: predict-no for direction U in state State-A
  1114. In State-A moving U
  1115. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  1116. predict error 0
  1117. dir: dir isL
  1118. /|\155: O: O310 (predict-no)
  1119. I see 1 and I'm going to do: predict-no
  1120. ENV: Agent did: predict-no for direction L in state State-A
  1121. In State-A moving L
  1122. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  1123. predict error 0
  1124. dir: dir isU
  1125. -156: O: O312 (predict-no)
  1126. I see 1 and I'm going to do: predict-no
  1127. ENV: Agent did: predict-no for direction U in state State-A
  1128. In State-A moving U
  1129. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  1130. predict error 0
  1131. dir: dir isU
  1132. /|\157: O: O313 (predict-yes)
  1133. I see 1 and I'm going to do: predict-yes
  1134. ENV: Agent did: predict-yes for direction U in state State-A
  1135. In State-A moving U
  1136. ENV: (next state, see, prediction correct?) = (State-A, 0, False)
  1137. predict error 1
  1138. dir: dir isR
  1139. -/|158: O: O315 (predict-yes)
  1140. I see 0 and I'm going to do: predict-yes
  1141. ENV: Agent did: predict-yes for direction R in state State-A
  1142. In State-A moving R
  1143. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  1144. predict error 0
  1145. dir: dir isL
  1146. \-/159: O: O317 (predict-yes)
  1147. I see 1 and I'm going to do: predict-yes
  1148. ENV: Agent did: predict-yes for direction L in state State-B
  1149. In State-B moving L
  1150. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  1151. predict error 0
  1152. dir: dir isU
  1153. |\-160: O: O320 (predict-no)
  1154. I see 1 and I'm going to do: predict-no
  1155. ENV: Agent did: predict-no for direction U in state State-A
  1156. In State-A moving U
  1157. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  1158. predict error 0
  1159. dir: dir isU
  1160. /|161: O: O322 (predict-no)
  1161. I see 1 and I'm going to do: predict-no
  1162. ENV: Agent did: predict-no for direction U in state State-A
  1163. In State-A moving U
  1164. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  1165. predict error 0
  1166. dir: dir isR
  1167. \162: O: O323 (predict-yes)
  1168. I see 1 and I'm going to do: predict-yes
  1169. ENV: Agent did: predict-yes for direction R in state State-A
  1170. In State-A moving R
  1171. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  1172. predict error 0
  1173. dir: dir isL
  1174. -/163: O: O325 (predict-yes)
  1175. I see 1 and I'm going to do: predict-yes
  1176. ENV: Agent did: predict-yes for direction L in state State-B
  1177. In State-B moving L
  1178. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  1179. predict error 0
  1180. dir: dir isR
  1181. |\-164: O: O327 (predict-yes)
  1182. I see 1 and I'm going to do: predict-yes
  1183. ENV: Agent did: predict-yes for direction R in state State-A
  1184. In State-A moving R
  1185. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  1186. predict error 0
  1187. dir: dir isR
  1188. /|\165: O: O329 (predict-yes)
  1189. I see 1 and I'm going to do: predict-yes
  1190. ENV: Agent did: predict-yes for direction R in state State-B
  1191. In State-B moving R
  1192. ENV: (next state, see, prediction correct?) = (State-B, 0, False)
  1193. predict error 1
  1194. dir: dir isR
  1195. -/|166: O: O332 (predict-no)
  1196. I see 0 and I'm going to do: predict-no
  1197. ENV: Agent did: predict-no for direction R in state State-B
  1198. In State-B moving R
  1199. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  1200. predict error 0
  1201. dir: dir isL
  1202. \-/167: O: O333 (predict-yes)
  1203. I see 1 and I'm going to do: predict-yes
  1204. ENV: Agent did: predict-yes for direction L in state State-B
  1205. In State-B moving L
  1206. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  1207. predict error 0
  1208. dir: dir isR
  1209. |\168: O: O335 (predict-yes)
  1210. I see 1 and I'm going to do: predict-yes
  1211. ENV: Agent did: predict-yes for direction R in state State-A
  1212. In State-A moving R
  1213. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  1214. predict error 0
  1215. dir: dir isL
  1216. -/|169: O: O337 (predict-yes)
  1217. I see 1 and I'm going to do: predict-yes
  1218. ENV: Agent did: predict-yes for direction L in state State-B
  1219. In State-B moving L
  1220. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  1221. predict error 0
  1222. dir: dir isL
  1223. \-/170: O: O340 (predict-no)
  1224. I see 1 and I'm going to do: predict-no
  1225. ENV: Agent did: predict-no for direction L in state State-A
  1226. In State-A moving L
  1227. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  1228. predict error 0
  1229. dir: dir isU
  1230. |\171: O: O341 (predict-yes)
  1231. I see 1 and I'm going to do: predict-yes
  1232. ENV: Agent did: predict-yes for direction U in state State-A
  1233. In State-A moving U
  1234. ENV: (next state, see, prediction correct?) = (State-A, 0, False)
  1235. predict error 1
  1236. dir: dir isU
  1237. -172: O: O344 (predict-no)
  1238. I see 0 and I'm going to do: predict-no
  1239. ENV: Agent did: predict-no for direction U in state State-A
  1240. In State-A moving U
  1241. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  1242. predict error 0
  1243. dir: dir isL
  1244. /|\173: O: O345 (predict-yes)
  1245. I see 1 and I'm going to do: predict-yes
  1246. ENV: Agent did: predict-yes for direction L in state State-A
  1247. In State-A moving L
  1248. ENV: (next state, see, prediction correct?) = (State-A, 0, False)
  1249. predict error 1
  1250. dir: dir isU
  1251. -/|174: O: O348 (predict-no)
  1252. I see 0 and I'm going to do: predict-no
  1253. ENV: Agent did: predict-no for direction U in state State-A
  1254. In State-A moving U
  1255. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  1256. predict error 0
  1257. dir: dir isL
  1258. \-/175: O: O350 (predict-no)
  1259. I see 1 and I'm going to do: predict-no
  1260. ENV: Agent did: predict-no for direction L in state State-A
  1261. In State-A moving L
  1262. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  1263. predict error 0
  1264. dir: dir isU
  1265. |\-176: O: O352 (predict-no)
  1266. I see 1 and I'm going to do: predict-no
  1267. ENV: Agent did: predict-no for direction U in state State-A
  1268. In State-A moving U
  1269. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  1270. predict error 0
  1271. dir: dir isU
  1272. /|\177: O: O354 (predict-no)
  1273. I see 1 and I'm going to do: predict-no
  1274. ENV: Agent did: predict-no for direction U in state State-A
  1275. In State-A moving U
  1276. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  1277. predict error 0
  1278. dir: dir isR
  1279. -/178: O: O355 (predict-yes)
  1280. I see 1 and I'm going to do: predict-yes
  1281. ENV: Agent did: predict-yes for direction R in state State-A
  1282. In State-A moving R
  1283. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  1284. predict error 0
  1285. dir: dir isL
  1286. |\-179: O: O357 (predict-yes)
  1287. I see 1 and I'm going to do: predict-yes
  1288. ENV: Agent did: predict-yes for direction L in state State-B
  1289. In State-B moving L
  1290. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  1291. predict error 0
  1292. dir: dir isL
  1293. /|\180: O: O360 (predict-no)
  1294. I see 1 and I'm going to do: predict-no
  1295. ENV: Agent did: predict-no for direction L in state State-A
  1296. In State-A moving L
  1297. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  1298. predict error 0
  1299. dir: dir isU
  1300. -/|181: O: O362 (predict-no)
  1301. I see 1 and I'm going to do: predict-no
  1302. ENV: Agent did: predict-no for direction U in state State-A
  1303. In State-A moving U
  1304. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  1305. predict error 0
  1306. dir: dir isL
  1307. \182: O: O363 (predict-yes)
  1308. I see 1 and I'm going to do: predict-yes
  1309. ENV: Agent did: predict-yes for direction L in state State-A
  1310. In State-A moving L
  1311. ENV: (next state, see, prediction correct?) = (State-A, 0, False)
  1312. predict error 1
  1313. dir: dir isU
  1314. -/183: O: O366 (predict-no)
  1315. I see 0 and I'm going to do: predict-no
  1316. ENV: Agent did: predict-no for direction U in state State-A
  1317. In State-A moving U
  1318. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  1319. predict error 0
  1320. dir: dir isU
  1321. |184: O: O367 (predict-yes)
  1322. I see 1 and I'm going to do: predict-yes
  1323. ENV: Agent did: predict-yes for direction U in state State-A
  1324. In State-A moving U
  1325. ENV: (next state, see, prediction correct?) = (State-A, 0, False)
  1326. predict error 1
  1327. dir: dir isR
  1328. \-/185: O: O370 (predict-no)
  1329. I see 0 and I'm going to do: predict-no
  1330. ENV: Agent did: predict-no for direction R in state State-A
  1331. In State-A moving R
  1332. ENV: (next state, see, prediction correct?) = (State-B, 1, False)
  1333. predict error 1
  1334. dir: dir isL
  1335. |\-186: O: O372 (predict-no)
  1336. I see 0 and I'm going to do: predict-no
  1337. ENV: Agent did: predict-no for direction L in state State-B
  1338. In State-B moving L
  1339. ENV: (next state, see, prediction correct?) = (State-A, 1, False)
  1340. predict error 1
  1341. dir: dir isU
  1342. /|\187: O: O374 (predict-no)
  1343. I see 0 and I'm going to do: predict-no
  1344. ENV: Agent did: predict-no for direction U in state State-A
  1345. In State-A moving U
  1346. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  1347. predict error 0
  1348. dir: dir isU
  1349. -/188: O: O376 (predict-no)
  1350. I see 1 and I'm going to do: predict-no
  1351. ENV: Agent did: predict-no for direction U in state State-A
  1352. In State-A moving U
  1353. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  1354. predict error 0
  1355. dir: dir isU
  1356. |\-189: O: O377 (predict-yes)
  1357. I see 1 and I'm going to do: predict-yes
  1358. ENV: Agent did: predict-yes for direction U in state State-A
  1359. In State-A moving U
  1360. ENV: (next state, see, prediction correct?) = (State-A, 0, False)
  1361. predict error 1
  1362. dir: dir isR
  1363. /|190: O: O379 (predict-yes)
  1364. I see 0 and I'm going to do: predict-yes
  1365. ENV: Agent did: predict-yes for direction R in state State-A
  1366. In State-A moving R
  1367. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  1368. predict error 0
  1369. dir: dir isR
  1370. \-191: O: O382 (predict-no)
  1371. I see 1 and I'm going to do: predict-no
  1372. ENV: Agent did: predict-no for direction R in state State-B
  1373. In State-B moving R
  1374. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  1375. predict error 0
  1376. dir: dir isR
  1377. /192: O: O384 (predict-no)
  1378. I see 1 and I'm going to do: predict-no
  1379. ENV: Agent did: predict-no for direction R in state State-B
  1380. In State-B moving R
  1381. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  1382. predict error 0
  1383. dir: dir isL
  1384. |\-193: O: O385 (predict-yes)
  1385. I see 1 and I'm going to do: predict-yes
  1386. ENV: Agent did: predict-yes for direction L in state State-B
  1387. In State-B moving L
  1388. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  1389. predict error 0
  1390. dir: dir isU
  1391. /|\194: O: O388 (predict-no)
  1392. I see 1 and I'm going to do: predict-no
  1393. ENV: Agent did: predict-no for direction U in state State-A
  1394. In State-A moving U
  1395. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  1396. predict error 0
  1397. dir: dir isR
  1398. -/195: O: O389 (predict-yes)
  1399. I see 1 and I'm going to do: predict-yes
  1400. ENV: Agent did: predict-yes for direction R in state State-A
  1401. In State-A moving R
  1402. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  1403. predict error 0
  1404. dir: dir isL
  1405. |\-196: O: O391 (predict-yes)
  1406. I see 1 and I'm going to do: predict-yes
  1407. ENV: Agent did: predict-yes for direction L in state State-B
  1408. In State-B moving L
  1409. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  1410. predict error 0
  1411. dir: dir isL
  1412. /197: O: O394 (predict-no)
  1413. I see 1 and I'm going to do: predict-no
  1414. ENV: Agent did: predict-no for direction L in state State-A
  1415. In State-A moving L
  1416. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  1417. predict error 0
  1418. dir: dir isR
  1419. |\-198: O: O395 (predict-yes)
  1420. I see 1 and I'm going to do: predict-yes
  1421. ENV: Agent did: predict-yes for direction R in state State-A
  1422. In State-A moving R
  1423. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  1424. predict error 0
  1425. dir: dir isL
  1426. /|\199: O: O397 (predict-yes)
  1427. I see 1 and I'm going to do: predict-yes
  1428. ENV: Agent did: predict-yes for direction L in state State-B
  1429. In State-B moving L
  1430. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  1431. predict error 0
  1432. dir: dir isR
  1433. -/|200: O: O399 (predict-yes)
  1434. I see 1 and I'm going to do: predict-yes
  1435. ENV: Agent did: predict-yes for direction R in state State-A
  1436. In State-A moving R
  1437. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  1438. predict error 0
  1439. dir: dir isL
  1440. \-/201: O: O401 (predict-yes)
  1441. I see 1 and I'm going to do: predict-yes
  1442. ENV: Agent did: predict-yes for direction L in state State-B
  1443. In State-B moving L
  1444. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  1445. predict error 0
  1446. dir: dir isU
  1447. |202: O: O404 (predict-no)
  1448. I see 1 and I'm going to do: predict-no
  1449. ENV: Agent did: predict-no for direction U in state State-A
  1450. In State-A moving U
  1451. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  1452. predict error 0
  1453. dir: dir isU
  1454. \-/203: O: O406 (predict-no)
  1455. I see 1 and I'm going to do: predict-no
  1456. ENV: Agent did: predict-no for direction U in state State-A
  1457. In State-A moving U
  1458. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  1459. predict error 0
  1460. dir: dir isL
  1461. |\-204: O: O408 (predict-no)
  1462. I see 1 and I'm going to do: predict-no
  1463. ENV: Agent did: predict-no for direction L in state State-A
  1464. In State-A moving L
  1465. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  1466. predict error 0
  1467. dir: dir isL
  1468. /|205: O: O409 (predict-yes)
  1469. I see 1 and I'm going to do: predict-yes
  1470. ENV: Agent did: predict-yes for direction L in state State-A
  1471. In State-A moving L
  1472. ENV: (next state, see, prediction correct?) = (State-A, 0, False)
  1473. predict error 1
  1474. dir: dir isL
  1475. \-/206: O: O412 (predict-no)
  1476. I see 0 and I'm going to do: predict-no
  1477. ENV: Agent did: predict-no for direction L in state State-A
  1478. In State-A moving L
  1479. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  1480. predict error 0
  1481. dir: dir isU
  1482. |\-207: O: O414 (predict-no)
  1483. I see 1 and I'm going to do: predict-no
  1484. ENV: Agent did: predict-no for direction U in state State-A
  1485. In State-A moving U
  1486. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  1487. predict error 0
  1488. dir: dir isU
  1489. /|\208: O: O416 (predict-no)
  1490. I see 1 and I'm going to do: predict-no
  1491. ENV: Agent did: predict-no for direction U in state State-A
  1492. In State-A moving U
  1493. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  1494. predict error 0
  1495. dir: dir isR
  1496. -/|209: O: O417 (predict-yes)
  1497. I see 1 and I'm going to do: predict-yes
  1498. ENV: Agent did: predict-yes for direction R in state State-A
  1499. In State-A moving R
  1500. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  1501. predict error 0
  1502. dir: dir isL
  1503. \-/210: O: O419 (predict-yes)
  1504. I see 1 and I'm going to do: predict-yes
  1505. ENV: Agent did: predict-yes for direction L in state State-B
  1506. In State-B moving L
  1507. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  1508. predict error 0
  1509. dir: dir isU
  1510. |\-/211: O: O422 (predict-no)
  1511. I see 1 and I'm going to do: predict-no
  1512. ENV: Agent did: predict-no for direction U in state State-A
  1513. In State-A moving U
  1514. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  1515. predict error 0
  1516. dir: dir isU
  1517. |212: O: O424 (predict-no)
  1518. I see 1 and I'm going to do: predict-no
  1519. ENV: Agent did: predict-no for direction U in state State-A
  1520. In State-A moving U
  1521. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  1522. predict error 0
  1523. dir: dir isU
  1524. \-/213: O: O426 (predict-no)
  1525. I see 1 and I'm going to do: predict-no
  1526. ENV: Agent did: predict-no for direction U in state State-A
  1527. In State-A moving U
  1528. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  1529. predict error 0
  1530. dir: dir isR
  1531. |\214: O: O427 (predict-yes)
  1532. I see 1 and I'm going to do: predict-yes
  1533. ENV: Agent did: predict-yes for direction R in state State-A
  1534. In State-A moving R
  1535. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  1536. predict error 0
  1537. dir: dir isU
  1538. -/|215: O: O430 (predict-no)
  1539. I see 1 and I'm going to do: predict-no
  1540. ENV: Agent did: predict-no for direction U in state State-B
  1541. In State-B moving U
  1542. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  1543. predict error 0
  1544. dir: dir isU
  1545. \-216: O: O432 (predict-no)
  1546. I see 1 and I'm going to do: predict-no
  1547. ENV: Agent did: predict-no for direction U in state State-B
  1548. In State-B moving U
  1549. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  1550. predict error 0
  1551. dir: dir isR
  1552. /217: O: O434 (predict-no)
  1553. I see 1 and I'm going to do: predict-no
  1554. ENV: Agent did: predict-no for direction R in state State-B
  1555. In State-B moving R
  1556. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  1557. predict error 0
  1558. dir: dir isU
  1559. |\218: O: O436 (predict-no)
  1560. I see 1 and I'm going to do: predict-no
  1561. ENV: Agent did: predict-no for direction U in state State-B
  1562. In State-B moving U
  1563. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  1564. predict error 0
  1565. dir: dir isL
  1566. -219: O: O437 (predict-yes)
  1567. I see 1 and I'm going to do: predict-yes
  1568. ENV: Agent did: predict-yes for direction L in state State-B
  1569. In State-B moving L
  1570. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  1571. predict error 0
  1572. dir: dir isU
  1573. /|220: O: O439 (predict-yes)
  1574. I see 1 and I'm going to do: predict-yes
  1575. ENV: Agent did: predict-yes for direction U in state State-A
  1576. In State-A moving U
  1577. ENV: (next state, see, prediction correct?) = (State-A, 0, False)
  1578. predict error 1
  1579. dir: dir isL
  1580. \-/221: O: O442 (predict-no)
  1581. I see 0 and I'm going to do: predict-no
  1582. ENV: Agent did: predict-no for direction L in state State-A
  1583. In State-A moving L
  1584. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  1585. predict error 0
  1586. dir: dir isL
  1587. |222: O: O444 (predict-no)
  1588. I see 1 and I'm going to do: predict-no
  1589. ENV: Agent did: predict-no for direction L in state State-A
  1590. In State-A moving L
  1591. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  1592. predict error 0
  1593. dir: dir isU
  1594. \-/223: O: O445 (predict-yes)
  1595. I see 1 and I'm going to do: predict-yes
  1596. ENV: Agent did: predict-yes for direction U in state State-A
  1597. In State-A moving U
  1598. ENV: (next state, see, prediction correct?) = (State-A, 0, False)
  1599. predict error 1
  1600. dir: dir isL
  1601. |\-224: O: O448 (predict-no)
  1602. I see 0 and I'm going to do: predict-no
  1603. ENV: Agent did: predict-no for direction L in state State-A
  1604. In State-A moving L
  1605. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  1606. predict error 0
  1607. dir: dir isU
  1608. /|225: O: O450 (predict-no)
  1609. I see 1 and I'm going to do: predict-no
  1610. ENV: Agent did: predict-no for direction U in state State-A
  1611. In State-A moving U
  1612. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  1613. predict error 0
  1614. dir: dir isR
  1615. \-/226: O: O451 (predict-yes)
  1616. I see 1 and I'm going to do: predict-yes
  1617. ENV: Agent did: predict-yes for direction R in state State-A
  1618. In State-A moving R
  1619. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  1620. predict error 0
  1621. dir: dir isU
  1622. |\227: O: O454 (predict-no)
  1623. I see 1 and I'm going to do: predict-no
  1624. ENV: Agent did: predict-no for direction U in state State-B
  1625. In State-B moving U
  1626. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  1627. predict error 0
  1628. dir: dir isR
  1629. -/|228: O: O455 (predict-yes)
  1630. I see 1 and I'm going to do: predict-yes
  1631. ENV: Agent did: predict-yes for direction R in state State-B
  1632. In State-B moving R
  1633. ENV: (next state, see, prediction correct?) = (State-B, 0, False)
  1634. predict error 1
  1635. dir: dir isR
  1636. \-/229: O: O458 (predict-no)
  1637. I see 0 and I'm going to do: predict-no
  1638. ENV: Agent did: predict-no for direction R in state State-B
  1639. In State-B moving R
  1640. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  1641. predict error 0
  1642. dir: dir isL
  1643. |230: O: O459 (predict-yes)
  1644. I see 1 and I'm going to do: predict-yes
  1645. ENV: Agent did: predict-yes for direction L in state State-B
  1646. In State-B moving L
  1647. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  1648. predict error 0
  1649. dir: dir isU
  1650. \231: O: O461 (predict-yes)
  1651. I see 1 and I'm going to do: predict-yes
  1652. ENV: Agent did: predict-yes for direction U in state State-A
  1653. In State-A moving U
  1654. ENV: (next state, see, prediction correct?) = (State-A, 0, False)
  1655. predict error 1
  1656. dir: dir isR
  1657. -232: O: O463 (predict-yes)
  1658. I see 0 and I'm going to do: predict-yes
  1659. ENV: Agent did: predict-yes for direction R in state State-A
  1660. In State-A moving R
  1661. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  1662. predict error 0
  1663. dir: dir isU
  1664. /|\233: O: O466 (predict-no)
  1665. I see 1 and I'm going to do: predict-no
  1666. ENV: Agent did: predict-no for direction U in state State-B
  1667. In State-B moving U
  1668. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  1669. predict error 0
  1670. dir: dir isU
  1671. -/234: O: O468 (predict-no)
  1672. I see 1 and I'm going to do: predict-no
  1673. ENV: Agent did: predict-no for direction U in state State-B
  1674. In State-B moving U
  1675. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  1676. predict error 0
  1677. dir: dir isL
  1678. |\-235: O: O469 (predict-yes)
  1679. I see 1 and I'm going to do: predict-yes
  1680. ENV: Agent did: predict-yes for direction L in state State-B
  1681. In State-B moving L
  1682. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  1683. predict error 0
  1684. dir: dir isR
  1685. /|\236: O: O471 (predict-yes)
  1686. I see 1 and I'm going to do: predict-yes
  1687. ENV: Agent did: predict-yes for direction R in state State-A
  1688. In State-A moving R
  1689. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  1690. predict error 0
  1691. dir: dir isL
  1692. -237: O: O473 (predict-yes)
  1693. I see 1 and I'm going to do: predict-yes
  1694. ENV: Agent did: predict-yes for direction L in state State-B
  1695. In State-B moving L
  1696. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  1697. predict error 0
  1698. dir: dir isL
  1699. /|\238: O: O475 (predict-yes)
  1700. I see 1 and I'm going to do: predict-yes
  1701. ENV: Agent did: predict-yes for direction L in state State-A
  1702. In State-A moving L
  1703. ENV: (next state, see, prediction correct?) = (State-A, 0, False)
  1704. predict error 1
  1705. dir: dir isL
  1706. -/239: O: O478 (predict-no)
  1707. I see 0 and I'm going to do: predict-no
  1708. ENV: Agent did: predict-no for direction L in state State-A
  1709. In State-A moving L
  1710. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  1711. predict error 0
  1712. dir: dir isU
  1713. |240: O: O480 (predict-no)
  1714. I see 1 and I'm going to do: predict-no
  1715. ENV: Agent did: predict-no for direction U in state State-A
  1716. In State-A moving U
  1717. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  1718. predict error 0
  1719. dir: dir isU
  1720. \241: O: O482 (predict-no)
  1721. I see 1 and I'm going to do: predict-no
  1722. ENV: Agent did: predict-no for direction U in state State-A
  1723. In State-A moving U
  1724. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  1725. predict error 0
  1726. dir: dir isU
  1727. -242: O: O484 (predict-no)
  1728. I see 1 and I'm going to do: predict-no
  1729. ENV: Agent did: predict-no for direction U in state State-A
  1730. In State-A moving U
  1731. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  1732. predict error 0
  1733. dir: dir isR
  1734. /|\243: O: O485 (predict-yes)
  1735. I see 1 and I'm going to do: predict-yes
  1736. ENV: Agent did: predict-yes for direction R in state State-A
  1737. In State-A moving R
  1738. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  1739. predict error 0
  1740. dir: dir isR
  1741. -244: O: O487 (predict-yes)
  1742. I see 1 and I'm going to do: predict-yes
  1743. ENV: Agent did: predict-yes for direction R in state State-B
  1744. In State-B moving R
  1745. ENV: (next state, see, prediction correct?) = (State-B, 0, False)
  1746. predict error 1
  1747. dir: dir isU
  1748. /|\245: O: O490 (predict-no)
  1749. I see 0 and I'm going to do: predict-no
  1750. ENV: Agent did: predict-no for direction U in state State-B
  1751. In State-B moving U
  1752. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  1753. predict error 0
  1754. dir: dir isR
  1755. -/|246: O: O492 (predict-no)
  1756. I see 1 and I'm going to do: predict-no
  1757. ENV: Agent did: predict-no for direction R in state State-B
  1758. In State-B moving R
  1759. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  1760. predict error 0
  1761. dir: dir isR
  1762. \-/247: O: O494 (predict-no)
  1763. I see 1 and I'm going to do: predict-no
  1764. ENV: Agent did: predict-no for direction R in state State-B
  1765. In State-B moving R
  1766. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  1767. predict error 0
  1768. dir: dir isL
  1769. |\248: O: O495 (predict-yes)
  1770. I see 1 and I'm going to do: predict-yes
  1771. ENV: Agent did: predict-yes for direction L in state State-B
  1772. In State-B moving L
  1773. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  1774. predict error 0
  1775. dir: dir isL
  1776. -/|249: O: O498 (predict-no)
  1777. I see 1 and I'm going to do: predict-no
  1778. ENV: Agent did: predict-no for direction L in state State-A
  1779. In State-A moving L
  1780. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  1781. predict error 0
  1782. dir: dir isL
  1783. \-/250: O: O500 (predict-no)
  1784. I see 1 and I'm going to do: predict-no
  1785. ENV: Agent did: predict-no for direction L in state State-A
  1786. In State-A moving L
  1787. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  1788. predict error 0
  1789. dir: dir isU
  1790. |251: O: O502 (predict-no)
  1791. I see 1 and I'm going to do: predict-no
  1792. ENV: Agent did: predict-no for direction U in state State-A
  1793. In State-A moving U
  1794. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  1795. predict error 0
  1796. dir: dir isR
  1797. \252: O: O503 (predict-yes)
  1798. I see 1 and I'm going to do: predict-yes
  1799. ENV: Agent did: predict-yes for direction R in state State-A
  1800. In State-A moving R
  1801. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  1802. predict error 0
  1803. dir: dir isU
  1804. -/|253: O: O506 (predict-no)
  1805. I see 1 and I'm going to do: predict-no
  1806. ENV: Agent did: predict-no for direction U in state State-B
  1807. In State-B moving U
  1808. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  1809. predict error 0
  1810. dir: dir isR
  1811. \-/254: O: O507 (predict-yes)
  1812. I see 1 and I'm going to do: predict-yes
  1813. ENV: Agent did: predict-yes for direction R in state State-B
  1814. In State-B moving R
  1815. ENV: (next state, see, prediction correct?) = (State-B, 0, False)
  1816. predict error 1
  1817. dir: dir isL
  1818. |\-255: O: O510 (predict-no)
  1819. I see 0 and I'm going to do: predict-no
  1820. ENV: Agent did: predict-no for direction L in state State-B
  1821. In State-B moving L
  1822. ENV: (next state, see, prediction correct?) = (State-A, 1, False)
  1823. predict error 1
  1824. dir: dir isU
  1825. /|256: O: O511 (predict-yes)
  1826. I see 0 and I'm going to do: predict-yes
  1827. ENV: Agent did: predict-yes for direction U in state State-A
  1828. In State-A moving U
  1829. ENV: (next state, see, prediction correct?) = (State-A, 0, False)
  1830. predict error 1
  1831. dir: dir isU
  1832. \-/257: O: O514 (predict-no)
  1833. I see 0 and I'm going to do: predict-no
  1834. ENV: Agent did: predict-no for direction U in state State-A
  1835. In State-A moving U
  1836. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  1837. predict error 0
  1838. dir: dir isL
  1839. |\-/258: O: O516 (predict-no)
  1840. I see 1 and I'm going to do: predict-no
  1841. ENV: Agent did: predict-no for direction L in state State-A
  1842. In State-A moving L
  1843. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  1844. predict error 0
  1845. dir: dir isU
  1846. |\-259: O: O518 (predict-no)
  1847. I see 1 and I'm going to do: predict-no
  1848. ENV: Agent did: predict-no for direction U in state State-A
  1849. In State-A moving U
  1850. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  1851. predict error 0
  1852. dir: dir isL
  1853. /|260: O: O520 (predict-no)
  1854. I see 1 and I'm going to do: predict-no
  1855. ENV: Agent did: predict-no for direction L in state State-A
  1856. In State-A moving L
  1857. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  1858. predict error 0
  1859. dir: dir isL
  1860. \-/261: O: O522 (predict-no)
  1861. I see 1 and I'm going to do: predict-no
  1862. ENV: Agent did: predict-no for direction L in state State-A
  1863. In State-A moving L
  1864. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  1865. predict error 0
  1866. dir: dir isU
  1867. |262: O: O524 (predict-no)
  1868. I see 1 and I'm going to do: predict-no
  1869. ENV: Agent did: predict-no for direction U in state State-A
  1870. In State-A moving U
  1871. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  1872. predict error 0
  1873. dir: dir isL
  1874. \-263: O: O526 (predict-no)
  1875. I see 1 and I'm going to do: predict-no
  1876. ENV: Agent did: predict-no for direction L in state State-A
  1877. In State-A moving L
  1878. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  1879. predict error 0
  1880. dir: dir isL
  1881. /|\264: O: O528 (predict-no)
  1882. I see 1 and I'm going to do: predict-no
  1883. ENV: Agent did: predict-no for direction L in state State-A
  1884. In State-A moving L
  1885. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  1886. predict error 0
  1887. dir: dir isU
  1888. -/|265: O: O530 (predict-no)
  1889. I see 1 and I'm going to do: predict-no
  1890. ENV: Agent did: predict-no for direction U in state State-A
  1891. In State-A moving U
  1892. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  1893. predict error 0
  1894. dir: dir isR
  1895. \-/266: O: O532 (predict-no)
  1896. I see 1 and I'm going to do: predict-no
  1897. ENV: Agent did: predict-no for direction R in state State-A
  1898. In State-A moving R
  1899. ENV: (next state, see, prediction correct?) = (State-B, 1, False)
  1900. predict error 1
  1901. dir: dir isL
  1902. |\-267: O: O534 (predict-no)
  1903. I see 0 and I'm going to do: predict-no
  1904. ENV: Agent did: predict-no for direction L in state State-B
  1905. In State-B moving L
  1906. ENV: (next state, see, prediction correct?) = (State-A, 1, False)
  1907. predict error 1
  1908. dir: dir isL
  1909. /|\268: O: O536 (predict-no)
  1910. I see 0 and I'm going to do: predict-no
  1911. ENV: Agent did: predict-no for direction L in state State-A
  1912. In State-A moving L
  1913. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  1914. predict error 0
  1915. dir: dir isL
  1916. -269: O: O538 (predict-no)
  1917. I see 1 and I'm going to do: predict-no
  1918. ENV: Agent did: predict-no for direction L in state State-A
  1919. In State-A moving L
  1920. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  1921. predict error 0
  1922. dir: dir isU
  1923. /|270: O: O540 (predict-no)
  1924. I see 1 and I'm going to do: predict-no
  1925. ENV: Agent did: predict-no for direction U in state State-A
  1926. In State-A moving U
  1927. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  1928. predict error 0
  1929. dir: dir isL
  1930. \-/271: O: O542 (predict-no)
  1931. I see 1 and I'm going to do: predict-no
  1932. ENV: Agent did: predict-no for direction L in state State-A
  1933. In State-A moving L
  1934. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  1935. predict error 0
  1936. dir: dir isU
  1937. |272: O: O544 (predict-no)
  1938. I see 1 and I'm going to do: predict-no
  1939. ENV: Agent did: predict-no for direction U in state State-A
  1940. In State-A moving U
  1941. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  1942. predict error 0
  1943. dir: dir isR
  1944. \-273: O: O545 (predict-yes)
  1945. I see 1 and I'm going to do: predict-yes
  1946. ENV: Agent did: predict-yes for direction R in state State-A
  1947. In State-A moving R
  1948. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  1949. predict error 0
  1950. dir: dir isU
  1951. /|\274: O: O548 (predict-no)
  1952. I see 1 and I'm going to do: predict-no
  1953. ENV: Agent did: predict-no for direction U in state State-B
  1954. In State-B moving U
  1955. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  1956. predict error 0
  1957. dir: dir isU
  1958. -/275: O: O550 (predict-no)
  1959. I see 1 and I'm going to do: predict-no
  1960. ENV: Agent did: predict-no for direction U in state State-B
  1961. In State-B moving U
  1962. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  1963. predict error 0
  1964. dir: dir isL
  1965. |\276: O: O551 (predict-yes)
  1966. I see 1 and I'm going to do: predict-yes
  1967. ENV: Agent did: predict-yes for direction L in state State-B
  1968. In State-B moving L
  1969. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  1970. predict error 0
  1971. dir: dir isL
  1972. -277: O: O554 (predict-no)
  1973. I see 1 and I'm going to do: predict-no
  1974. ENV: Agent did: predict-no for direction L in state State-A
  1975. In State-A moving L
  1976. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  1977. predict error 0
  1978. dir: dir isR
  1979. /|\278: O: O555 (predict-yes)
  1980. I see 1 and I'm going to do: predict-yes
  1981. ENV: Agent did: predict-yes for direction R in state State-A
  1982. In State-A moving R
  1983. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  1984. predict error 0
  1985. dir: dir isL
  1986. -/|279: O: O557 (predict-yes)
  1987. I see 1 and I'm going to do: predict-yes
  1988. ENV: Agent did: predict-yes for direction L in state State-B
  1989. In State-B moving L
  1990. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  1991. predict error 0
  1992. dir: dir isR
  1993. \-/280: O: O559 (predict-yes)
  1994. I see 1 and I'm going to do: predict-yes
  1995. ENV: Agent did: predict-yes for direction R in state State-A
  1996. In State-A moving R
  1997. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  1998. predict error 0
  1999. dir: dir isL
  2000. |\281: O: O561 (predict-yes)
  2001. I see 1 and I'm going to do: predict-yes
  2002. ENV: Agent did: predict-yes for direction L in state State-B
  2003. In State-B moving L
  2004. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  2005. predict error 0
  2006. dir: dir isL
  2007. -282: O: O563 (predict-yes)
  2008. I see 1 and I'm going to do: predict-yes
  2009. ENV: Agent did: predict-yes for direction L in state State-A
  2010. In State-A moving L
  2011. ENV: (next state, see, prediction correct?) = (State-A, 0, False)
  2012. predict error 1
  2013. dir: dir isU
  2014. /|283: O: O566 (predict-no)
  2015. I see 0 and I'm going to do: predict-no
  2016. ENV: Agent did: predict-no for direction U in state State-A
  2017. In State-A moving U
  2018. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  2019. predict error 0
  2020. dir: dir isL
  2021. \-/284: O: O568 (predict-no)
  2022. I see 1 and I'm going to do: predict-no
  2023. ENV: Agent did: predict-no for direction L in state State-A
  2024. In State-A moving L
  2025. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  2026. predict error 0
  2027. dir: dir isR
  2028. |\-285: O: O569 (predict-yes)
  2029. I see 1 and I'm going to do: predict-yes
  2030. ENV: Agent did: predict-yes for direction R in state State-A
  2031. In State-A moving R
  2032. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  2033. predict error 0
  2034. dir: dir isR
  2035. /|\-286: O: O572 (predict-no)
  2036. I see 1 and I'm going to do: predict-no
  2037. ENV: Agent did: predict-no for direction R in state State-B
  2038. In State-B moving R
  2039. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2040. predict error 0
  2041. dir: dir isL
  2042. /|\287: O: O574 (predict-no)
  2043. I see 1 and I'm going to do: predict-no
  2044. ENV: Agent did: predict-no for direction L in state State-B
  2045. In State-B moving L
  2046. ENV: (next state, see, prediction correct?) = (State-A, 1, False)
  2047. predict error 1
  2048. dir: dir isL
  2049. -/|288: O: O576 (predict-no)
  2050. I see 0 and I'm going to do: predict-no
  2051. ENV: Agent did: predict-no for direction L in state State-A
  2052. In State-A moving L
  2053. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  2054. predict error 0
  2055. dir: dir isU
  2056. \289: O: O578 (predict-no)
  2057. I see 1 and I'm going to do: predict-no
  2058. ENV: Agent did: predict-no for direction U in state State-A
  2059. In State-A moving U
  2060. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  2061. predict error 0
  2062. dir: dir isU
  2063. -/|290: O: O580 (predict-no)
  2064. I see 1 and I'm going to do: predict-no
  2065. ENV: Agent did: predict-no for direction U in state State-A
  2066. In State-A moving U
  2067. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  2068. predict error 0
  2069. dir: dir isU
  2070. \-/291: O: O582 (predict-no)
  2071. I see 1 and I'm going to do: predict-no
  2072. ENV: Agent did: predict-no for direction U in state State-A
  2073. In State-A moving U
  2074. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  2075. predict error 0
  2076. dir: dir isL
  2077. |292: O: O584 (predict-no)
  2078. I see 1 and I'm going to do: predict-no
  2079. ENV: Agent did: predict-no for direction L in state State-A
  2080. In State-A moving L
  2081. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  2082. predict error 0
  2083. dir: dir isL
  2084. \-293: O: O586 (predict-no)
  2085. I see 1 and I'm going to do: predict-no
  2086. ENV: Agent did: predict-no for direction L in state State-A
  2087. In State-A moving L
  2088. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  2089. predict error 0
  2090. dir: dir isR
  2091. /|294: O: O587 (predict-yes)
  2092. I see 1 and I'm going to do: predict-yes
  2093. ENV: Agent did: predict-yes for direction R in state State-A
  2094. In State-A moving R
  2095. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  2096. predict error 0
  2097. dir: dir isU
  2098. \-/295: O: O590 (predict-no)
  2099. I see 1 and I'm going to do: predict-no
  2100. ENV: Agent did: predict-no for direction U in state State-B
  2101. In State-B moving U
  2102. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2103. predict error 0
  2104. dir: dir isR
  2105. |\-296: O: O592 (predict-no)
  2106. I see 1 and I'm going to do: predict-no
  2107. ENV: Agent did: predict-no for direction R in state State-B
  2108. In State-B moving R
  2109. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2110. predict error 0
  2111. dir: dir isU
  2112. /297: O: O594 (predict-no)
  2113. I see 1 and I'm going to do: predict-no
  2114. ENV: Agent did: predict-no for direction U in state State-B
  2115. In State-B moving U
  2116. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2117. predict error 0
  2118. dir: dir isR
  2119. |\-298: O: O596 (predict-no)
  2120. I see 1 and I'm going to do: predict-no
  2121. ENV: Agent did: predict-no for direction R in state State-B
  2122. In State-B moving R
  2123. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2124. predict error 0
  2125. dir: dir isL
  2126. /|\299: O: O597 (predict-yes)
  2127. I see 1 and I'm going to do: predict-yes
  2128. ENV: Agent did: predict-yes for direction L in state State-B
  2129. In State-B moving L
  2130. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  2131. predict error 0
  2132. dir: dir isR
  2133. -/|300: O: O599 (predict-yes)
  2134. I see 1 and I'm going to do: predict-yes
  2135. ENV: Agent did: predict-yes for direction R in state State-A
  2136. In State-A moving R
  2137. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  2138. predict error 0
  2139. dir: dir isL
  2140. \-/|\-301: O: O601 (predict-yes)
  2141. I see 1 and I'm going to do: predict-yes
  2142. ENV: Agent did: predict-yes for direction L in state State-B
  2143. In State-B moving L
  2144. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  2145. predict error 0
  2146. dir: dir isL
  2147. /302: O: O604 (predict-no)
  2148. I see 1 and I'm going to do: predict-no
  2149. ENV: Agent did: predict-no for direction L in state State-A
  2150. In State-A moving L
  2151. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  2152. predict error 0
  2153. dir: dir isL
  2154. |\-303: O: O606 (predict-no)
  2155. I see 1 and I'm going to do: predict-no
  2156. ENV: Agent did: predict-no for direction L in state State-A
  2157. In State-A moving L
  2158. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  2159. predict error 0
  2160. dir: dir isL
  2161. /|\304: O: O608 (predict-no)
  2162. I see 1 and I'm going to do: predict-no
  2163. ENV: Agent did: predict-no for direction L in state State-A
  2164. In State-A moving L
  2165. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  2166. predict error 0
  2167. dir: dir isU
  2168. -/|\305: O: O610 (predict-no)
  2169. I see 1 and I'm going to do: predict-no
  2170. ENV: Agent did: predict-no for direction U in state State-A
  2171. In State-A moving U
  2172. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  2173. predict error 0
  2174. dir: dir isR
  2175. -/|306: O: O611 (predict-yes)
  2176. I see 1 and I'm going to do: predict-yes
  2177. ENV: Agent did: predict-yes for direction R in state State-A
  2178. In State-A moving R
  2179. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  2180. predict error 0
  2181. dir: dir isR
  2182. \-/307: O: O614 (predict-no)
  2183. I see 1 and I'm going to do: predict-no
  2184. ENV: Agent did: predict-no for direction R in state State-B
  2185. In State-B moving R
  2186. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2187. predict error 0
  2188. dir: dir isR
  2189. |\308: O: O616 (predict-no)
  2190. I see 1 and I'm going to do: predict-no
  2191. ENV: Agent did: predict-no for direction R in state State-B
  2192. In State-B moving R
  2193. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2194. predict error 0
  2195. dir: dir isU
  2196. -/309: O: O618 (predict-no)
  2197. I see 1 and I'm going to do: predict-no
  2198. ENV: Agent did: predict-no for direction U in state State-B
  2199. In State-B moving U
  2200. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2201. predict error 0
  2202. dir: dir isR
  2203. |\310: O: O620 (predict-no)
  2204. I see 1 and I'm going to do: predict-no
  2205. ENV: Agent did: predict-no for direction R in state State-B
  2206. In State-B moving R
  2207. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2208. predict error 0
  2209. dir: dir isL
  2210. -/311: O: O621 (predict-yes)
  2211. I see 1 and I'm going to do: predict-yes
  2212. ENV: Agent did: predict-yes for direction L in state State-B
  2213. In State-B moving L
  2214. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  2215. predict error 0
  2216. dir: dir isL
  2217. |312: O: O624 (predict-no)
  2218. I see 1 and I'm going to do: predict-no
  2219. ENV: Agent did: predict-no for direction L in state State-A
  2220. In State-A moving L
  2221. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  2222. predict error 0
  2223. dir: dir isL
  2224. \-313: O: O626 (predict-no)
  2225. I see 1 and I'm going to do: predict-no
  2226. ENV: Agent did: predict-no for direction L in state State-A
  2227. In State-A moving L
  2228. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  2229. predict error 0
  2230. dir: dir isU
  2231. /|\314: O: O628 (predict-no)
  2232. I see 1 and I'm going to do: predict-no
  2233. ENV: Agent did: predict-no for direction U in state State-A
  2234. In State-A moving U
  2235. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  2236. predict error 0
  2237. dir: dir isU
  2238. -/|315: O: O630 (predict-no)
  2239. I see 1 and I'm going to do: predict-no
  2240. ENV: Agent did: predict-no for direction U in state State-A
  2241. In State-A moving U
  2242. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  2243. predict error 0
  2244. dir: dir isL
  2245. \-/316: O: O632 (predict-no)
  2246. I see 1 and I'm going to do: predict-no
  2247. ENV: Agent did: predict-no for direction L in state State-A
  2248. In State-A moving L
  2249. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  2250. predict error 0
  2251. dir: dir isR
  2252. |\-317: O: O634 (predict-no)
  2253. I see 1 and I'm going to do: predict-no
  2254. ENV: Agent did: predict-no for direction R in state State-A
  2255. In State-A moving R
  2256. ENV: (next state, see, prediction correct?) = (State-B, 1, False)
  2257. predict error 1
  2258. dir: dir isR
  2259. /|318: O: O636 (predict-no)
  2260. I see 0 and I'm going to do: predict-no
  2261. ENV: Agent did: predict-no for direction R in state State-B
  2262. In State-B moving R
  2263. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2264. predict error 0
  2265. dir: dir isR
  2266. \-/319: O: O638 (predict-no)
  2267. I see 1 and I'm going to do: predict-no
  2268. ENV: Agent did: predict-no for direction R in state State-B
  2269. In State-B moving R
  2270. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2271. predict error 0
  2272. dir: dir isR
  2273. |\320: O: O640 (predict-no)
  2274. I see 1 and I'm going to do: predict-no
  2275. ENV: Agent did: predict-no for direction R in state State-B
  2276. In State-B moving R
  2277. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2278. predict error 0
  2279. dir: dir isL
  2280. -/|321: O: O641 (predict-yes)
  2281. I see 1 and I'm going to do: predict-yes
  2282. ENV: Agent did: predict-yes for direction L in state State-B
  2283. In State-B moving L
  2284. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  2285. predict error 0
  2286. dir: dir isL
  2287. \322: O: O643 (predict-yes)
  2288. I see 1 and I'm going to do: predict-yes
  2289. ENV: Agent did: predict-yes for direction L in state State-A
  2290. In State-A moving L
  2291. ENV: (next state, see, prediction correct?) = (State-A, 0, False)
  2292. predict error 1
  2293. dir: dir isL
  2294. -/|323: O: O645 (predict-yes)
  2295. I see 0 and I'm going to do: predict-yes
  2296. ENV: Agent did: predict-yes for direction L in state State-A
  2297. In State-A moving L
  2298. ENV: (next state, see, prediction correct?) = (State-A, 0, False)
  2299. predict error 1
  2300. dir: dir isL
  2301. \-/324: O: O648 (predict-no)
  2302. I see 0 and I'm going to do: predict-no
  2303. ENV: Agent did: predict-no for direction L in state State-A
  2304. In State-A moving L
  2305. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  2306. predict error 0
  2307. dir: dir isR
  2308. |\-325: O: O649 (predict-yes)
  2309. I see 1 and I'm going to do: predict-yes
  2310. ENV: Agent did: predict-yes for direction R in state State-A
  2311. In State-A moving R
  2312. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  2313. predict error 0
  2314. dir: dir isL
  2315. /|\326: O: O651 (predict-yes)
  2316. I see 1 and I'm going to do: predict-yes
  2317. ENV: Agent did: predict-yes for direction L in state State-B
  2318. In State-B moving L
  2319. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  2320. predict error 0
  2321. dir: dir isL
  2322. -/|327: O: O654 (predict-no)
  2323. I see 1 and I'm going to do: predict-no
  2324. ENV: Agent did: predict-no for direction L in state State-A
  2325. In State-A moving L
  2326. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  2327. predict error 0
  2328. dir: dir isR
  2329. \-/328: O: O655 (predict-yes)
  2330. I see 1 and I'm going to do: predict-yes
  2331. ENV: Agent did: predict-yes for direction R in state State-A
  2332. In State-A moving R
  2333. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  2334. predict error 0
  2335. dir: dir isL
  2336. |\-329: O: O657 (predict-yes)
  2337. I see 1 and I'm going to do: predict-yes
  2338. ENV: Agent did: predict-yes for direction L in state State-B
  2339. In State-B moving L
  2340. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  2341. predict error 0
  2342. dir: dir isU
  2343. /|330: O: O660 (predict-no)
  2344. I see 1 and I'm going to do: predict-no
  2345. ENV: Agent did: predict-no for direction U in state State-A
  2346. In State-A moving U
  2347. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  2348. predict error 0
  2349. dir: dir isR
  2350. \-/331: O: O661 (predict-yes)
  2351. I see 1 and I'm going to do: predict-yes
  2352. ENV: Agent did: predict-yes for direction R in state State-A
  2353. In State-A moving R
  2354. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  2355. predict error 0
  2356. dir: dir isU
  2357. |332: O: O663 (predict-yes)
  2358. I see 1 and I'm going to do: predict-yes
  2359. ENV: Agent did: predict-yes for direction U in state State-B
  2360. In State-B moving U
  2361. ENV: (next state, see, prediction correct?) = (State-B, 0, False)
  2362. predict error 1
  2363. dir: dir isL
  2364. \-/333: O: O665 (predict-yes)
  2365. I see 0 and I'm going to do: predict-yes
  2366. ENV: Agent did: predict-yes for direction L in state State-B
  2367. In State-B moving L
  2368. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  2369. predict error 0
  2370. dir: dir isR
  2371. |\-334: O: O667 (predict-yes)
  2372. I see 1 and I'm going to do: predict-yes
  2373. ENV: Agent did: predict-yes for direction R in state State-A
  2374. In State-A moving R
  2375. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  2376. predict error 0
  2377. dir: dir isU
  2378. /|\335: O: O670 (predict-no)
  2379. I see 1 and I'm going to do: predict-no
  2380. ENV: Agent did: predict-no for direction U in state State-B
  2381. In State-B moving U
  2382. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2383. predict error 0
  2384. dir: dir isL
  2385. -/|336: O: O671 (predict-yes)
  2386. I see 1 and I'm going to do: predict-yes
  2387. ENV: Agent did: predict-yes for direction L in state State-B
  2388. In State-B moving L
  2389. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  2390. predict error 0
  2391. dir: dir isU
  2392. \-/|337: O: O673 (predict-yes)
  2393. I see 1 and I'm going to do: predict-yes
  2394. ENV: Agent did: predict-yes for direction U in state State-A
  2395. In State-A moving U
  2396. ENV: (next state, see, prediction correct?) = (State-A, 0, False)
  2397. predict error 1
  2398. dir: dir isL
  2399. \-/338: O: O676 (predict-no)
  2400. I see 0 and I'm going to do: predict-no
  2401. ENV: Agent did: predict-no for direction L in state State-A
  2402. In State-A moving L
  2403. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  2404. predict error 0
  2405. dir: dir isU
  2406. |\-339: O: O678 (predict-no)
  2407. I see 1 and I'm going to do: predict-no
  2408. ENV: Agent did: predict-no for direction U in state State-A
  2409. In State-A moving U
  2410. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  2411. predict error 0
  2412. dir: dir isU
  2413. /|\340: O: O680 (predict-no)
  2414. I see 1 and I'm going to do: predict-no
  2415. ENV: Agent did: predict-no for direction U in state State-A
  2416. In State-A moving U
  2417. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  2418. predict error 0
  2419. dir: dir isU
  2420. -/|341: O: O682 (predict-no)
  2421. I see 1 and I'm going to do: predict-no
  2422. ENV: Agent did: predict-no for direction U in state State-A
  2423. In State-A moving U
  2424. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  2425. predict error 0
  2426. dir: dir isL
  2427. \342: O: O684 (predict-no)
  2428. I see 1 and I'm going to do: predict-no
  2429. ENV: Agent did: predict-no for direction L in state State-A
  2430. In State-A moving L
  2431. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  2432. predict error 0
  2433. dir: dir isL
  2434. -/|343: O: O686 (predict-no)
  2435. I see 1 and I'm going to do: predict-no
  2436. ENV: Agent did: predict-no for direction L in state State-A
  2437. In State-A moving L
  2438. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  2439. predict error 0
  2440. dir: dir isR
  2441. \-/344: O: O687 (predict-yes)
  2442. I see 1 and I'm going to do: predict-yes
  2443. ENV: Agent did: predict-yes for direction R in state State-A
  2444. In State-A moving R
  2445. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  2446. predict error 0
  2447. dir: dir isU
  2448. |\-345: O: O689 (predict-yes)
  2449. I see 1 and I'm going to do: predict-yes
  2450. ENV: Agent did: predict-yes for direction U in state State-B
  2451. In State-B moving U
  2452. ENV: (next state, see, prediction correct?) = (State-B, 0, False)
  2453. predict error 1
  2454. dir: dir isL
  2455. /|\346: O: O691 (predict-yes)
  2456. I see 0 and I'm going to do: predict-yes
  2457. ENV: Agent did: predict-yes for direction L in state State-B
  2458. In State-B moving L
  2459. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  2460. predict error 0
  2461. dir: dir isU
  2462. -/|\347: O: O693 (predict-yes)
  2463. I see 1 and I'm going to do: predict-yes
  2464. ENV: Agent did: predict-yes for direction U in state State-A
  2465. In State-A moving U
  2466. ENV: (next state, see, prediction correct?) = (State-A, 0, False)
  2467. predict error 1
  2468. dir: dir isL
  2469. -/|348: O: O696 (predict-no)
  2470. I see 0 and I'm going to do: predict-no
  2471. ENV: Agent did: predict-no for direction L in state State-A
  2472. In State-A moving L
  2473. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  2474. predict error 0
  2475. dir: dir isU
  2476. \-/349: O: O698 (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 isL
  2483. |\-350: O: O700 (predict-no)
  2484. I see 1 and I'm going to do: predict-no
  2485. ENV: Agent did: predict-no for direction L in state State-A
  2486. In State-A moving L
  2487. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  2488. predict error 0
  2489. dir: dir isL
  2490. /|\351: O: O702 (predict-no)
  2491. I see 1 and I'm going to do: predict-no
  2492. ENV: Agent did: predict-no for direction L in state State-A
  2493. In State-A moving L
  2494. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  2495. predict error 0
  2496. dir: dir isU
  2497. -352: O: O704 (predict-no)
  2498. I see 1 and I'm going to do: predict-no
  2499. ENV: Agent did: predict-no for direction U in state State-A
  2500. In State-A moving U
  2501. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  2502. predict error 0
  2503. dir: dir isU
  2504. /|\353: O: O706 (predict-no)
  2505. I see 1 and I'm going to do: predict-no
  2506. ENV: Agent did: predict-no for direction U in state State-A
  2507. In State-A moving U
  2508. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  2509. predict error 0
  2510. dir: dir isU
  2511. -354: O: O708 (predict-no)
  2512. I see 1 and I'm going to do: predict-no
  2513. ENV: Agent did: predict-no for direction U in state State-A
  2514. In State-A moving U
  2515. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  2516. predict error 0
  2517. dir: dir isU
  2518. /|\355: O: O710 (predict-no)
  2519. I see 1 and I'm going to do: predict-no
  2520. ENV: Agent did: predict-no for direction U in state State-A
  2521. In State-A moving U
  2522. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  2523. predict error 0
  2524. dir: dir isU
  2525. -356: O: O712 (predict-no)
  2526. I see 1 and I'm going to do: predict-no
  2527. ENV: Agent did: predict-no for direction U in state State-A
  2528. In State-A moving U
  2529. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  2530. predict error 0
  2531. dir: dir isU
  2532. /|357: O: O714 (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 isL
  2539. \-358: O: O716 (predict-no)
  2540. I see 1 and I'm going to do: predict-no
  2541. ENV: Agent did: predict-no for direction L in state State-A
  2542. In State-A moving L
  2543. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  2544. predict error 0
  2545. dir: dir isR
  2546. /|\359: O: O718 (predict-no)
  2547. I see 1 and I'm going to do: predict-no
  2548. ENV: Agent did: predict-no for direction R in state State-A
  2549. In State-A moving R
  2550. ENV: (next state, see, prediction correct?) = (State-B, 1, False)
  2551. predict error 1
  2552. dir: dir isL
  2553. -/|360: O: O719 (predict-yes)
  2554. I see 0 and I'm going to do: predict-yes
  2555. ENV: Agent did: predict-yes for direction L in state State-B
  2556. In State-B moving L
  2557. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  2558. predict error 0
  2559. dir: dir isU
  2560. \-/361: O: O722 (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-A
  2563. In State-A moving U
  2564. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  2565. predict error 0
  2566. dir: dir isU
  2567. |362: O: O724 (predict-no)
  2568. I see 1 and I'm going to do: predict-no
  2569. ENV: Agent did: predict-no for direction U in state State-A
  2570. In State-A moving U
  2571. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  2572. predict error 0
  2573. dir: dir isL
  2574. \363: O: O726 (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. -/364: O: O728 (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 isU
  2588. |\-365: O: O730 (predict-no)
  2589. I see 1 and I'm going to do: predict-no
  2590. ENV: Agent did: predict-no for direction U in state State-A
  2591. In State-A moving U
  2592. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  2593. predict error 0
  2594. dir: dir isU
  2595. /|\366: O: O732 (predict-no)
  2596. I see 1 and I'm going to do: predict-no
  2597. ENV: Agent did: predict-no for direction U in state State-A
  2598. In State-A moving U
  2599. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  2600. predict error 0
  2601. dir: dir isR
  2602. -367: O: O733 (predict-yes)
  2603. I see 1 and I'm going to do: predict-yes
  2604. ENV: Agent did: predict-yes for direction R in state State-A
  2605. In State-A moving R
  2606. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  2607. predict error 0
  2608. dir: dir isR
  2609. /|\368: O: O735 (predict-yes)
  2610. I see 1 and I'm going to do: predict-yes
  2611. ENV: Agent did: predict-yes for direction R in state State-B
  2612. In State-B moving R
  2613. ENV: (next state, see, prediction correct?) = (State-B, 0, False)
  2614. predict error 1
  2615. dir: dir isU
  2616. -/|369: O: O738 (predict-no)
  2617. I see 0 and I'm going to do: predict-no
  2618. ENV: Agent did: predict-no for direction U in state State-B
  2619. In State-B moving U
  2620. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2621. predict error 0
  2622. dir: dir isR
  2623. \-370: O: O740 (predict-no)
  2624. I see 1 and I'm going to do: predict-no
  2625. ENV: Agent did: predict-no for direction R in state State-B
  2626. In State-B moving R
  2627. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2628. predict error 0
  2629. dir: dir isR
  2630. /|\371: O: O742 (predict-no)
  2631. I see 1 and I'm going to do: predict-no
  2632. ENV: Agent did: predict-no for direction R in state State-B
  2633. In State-B moving R
  2634. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2635. predict error 0
  2636. dir: dir isR
  2637. -372: O: O744 (predict-no)
  2638. I see 1 and I'm going to do: predict-no
  2639. ENV: Agent did: predict-no for direction R in state State-B
  2640. In State-B moving R
  2641. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2642. predict error 0
  2643. dir: dir isL
  2644. /|\373: O: O745 (predict-yes)
  2645. I see 1 and I'm going to do: predict-yes
  2646. ENV: Agent did: predict-yes for direction L in state State-B
  2647. In State-B moving L
  2648. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  2649. predict error 0
  2650. dir: dir isL
  2651. -/374: O: O748 (predict-no)
  2652. I see 1 and I'm going to do: predict-no
  2653. ENV: Agent did: predict-no for direction L in state State-A
  2654. In State-A moving L
  2655. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  2656. predict error 0
  2657. dir: dir isR
  2658. |\375: O: O749 (predict-yes)
  2659. I see 1 and I'm going to do: predict-yes
  2660. ENV: Agent did: predict-yes for direction R in state State-A
  2661. In State-A moving R
  2662. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  2663. predict error 0
  2664. dir: dir isR
  2665. -/|376: O: O752 (predict-no)
  2666. I see 1 and I'm going to do: predict-no
  2667. ENV: Agent did: predict-no for direction R in state State-B
  2668. In State-B moving R
  2669. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2670. predict error 0
  2671. dir: dir isR
  2672. \-377: O: O754 (predict-no)
  2673. I see 1 and I'm going to do: predict-no
  2674. ENV: Agent did: predict-no for direction R in state State-B
  2675. In State-B moving R
  2676. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2677. predict error 0
  2678. dir: dir isL
  2679. /|\378: O: O755 (predict-yes)
  2680. I see 1 and I'm going to do: predict-yes
  2681. ENV: Agent did: predict-yes for direction L in state State-B
  2682. In State-B moving L
  2683. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  2684. predict error 0
  2685. dir: dir isR
  2686. -/379: O: O757 (predict-yes)
  2687. I see 1 and I'm going to do: predict-yes
  2688. ENV: Agent did: predict-yes for direction R in state State-A
  2689. In State-A moving R
  2690. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  2691. predict error 0
  2692. dir: dir isL
  2693. |\380: O: O759 (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 isL
  2700. -/|381: O: O762 (predict-no)
  2701. I see 1 and I'm going to do: predict-no
  2702. ENV: Agent did: predict-no for direction L in state State-A
  2703. In State-A moving L
  2704. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  2705. predict error 0
  2706. dir: dir isL
  2707. \382: O: O764 (predict-no)
  2708. I see 1 and I'm going to do: predict-no
  2709. ENV: Agent did: predict-no for direction L in state State-A
  2710. In State-A moving L
  2711. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  2712. predict error 0
  2713. dir: dir isU
  2714. -/|383: O: O766 (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 isR
  2721. \-384: O: O767 (predict-yes)
  2722. I see 1 and I'm going to do: predict-yes
  2723. ENV: Agent did: predict-yes for direction R in state State-A
  2724. In State-A moving R
  2725. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  2726. predict error 0
  2727. dir: dir isR
  2728. /|\385: O: O770 (predict-no)
  2729. I see 1 and I'm going to do: predict-no
  2730. ENV: Agent did: predict-no for direction R in state State-B
  2731. In State-B moving R
  2732. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2733. predict error 0
  2734. dir: dir isR
  2735. -/|386: O: O772 (predict-no)
  2736. I see 1 and I'm going to do: predict-no
  2737. ENV: Agent did: predict-no for direction R in state State-B
  2738. In State-B moving R
  2739. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2740. predict error 0
  2741. dir: dir isL
  2742. \-/387: O: O773 (predict-yes)
  2743. I see 1 and I'm going to do: predict-yes
  2744. ENV: Agent did: predict-yes for direction L in state State-B
  2745. In State-B moving L
  2746. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  2747. predict error 0
  2748. dir: dir isL
  2749. |\-388: O: O776 (predict-no)
  2750. I see 1 and I'm going to do: predict-no
  2751. ENV: Agent did: predict-no for direction L in state State-A
  2752. In State-A moving L
  2753. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  2754. predict error 0
  2755. dir: dir isR
  2756. /|\389: O: O777 (predict-yes)
  2757. I see 1 and I'm going to do: predict-yes
  2758. ENV: Agent did: predict-yes for direction R in state State-A
  2759. In State-A moving R
  2760. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  2761. predict error 0
  2762. dir: dir isR
  2763. -/390: O: O779 (predict-yes)
  2764. I see 1 and I'm going to do: predict-yes
  2765. ENV: Agent did: predict-yes for direction R in state State-B
  2766. In State-B moving R
  2767. ENV: (next state, see, prediction correct?) = (State-B, 0, False)
  2768. predict error 1
  2769. dir: dir isR
  2770. |\391: O: O782 (predict-no)
  2771. I see 0 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. -392: O: O784 (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. /|393: O: O786 (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. \-/394: O: O788 (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 isL
  2798. |\-395: O: O789 (predict-yes)
  2799. I see 1 and I'm going to do: predict-yes
  2800. ENV: Agent did: predict-yes for direction L in state State-B
  2801. In State-B moving L
  2802. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  2803. predict error 0
  2804. dir: dir isR
  2805. /|\396: O: O791 (predict-yes)
  2806. I see 1 and I'm going to do: predict-yes
  2807. ENV: Agent did: predict-yes for direction R in state State-A
  2808. In State-A moving R
  2809. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  2810. predict error 0
  2811. dir: dir isR
  2812. -/|397: O: O794 (predict-no)
  2813. I see 1 and I'm going to do: predict-no
  2814. ENV: Agent did: predict-no for direction R in state State-B
  2815. In State-B moving R
  2816. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2817. predict error 0
  2818. dir: dir isL
  2819. \-/398: O: O795 (predict-yes)
  2820. I see 1 and I'm going to do: predict-yes
  2821. ENV: Agent did: predict-yes for direction L in state State-B
  2822. In State-B moving L
  2823. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  2824. predict error 0
  2825. dir: dir isR
  2826. |399: O: O797 (predict-yes)
  2827. I see 1 and I'm going to do: predict-yes
  2828. ENV: Agent did: predict-yes for direction R in state State-A
  2829. In State-A moving R
  2830. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  2831. predict error 0
  2832. dir: dir isR
  2833. \-/400: O: O800 (predict-no)
  2834. I see 1 and I'm going to do: predict-no
  2835. ENV: Agent did: predict-no for direction R in state State-B
  2836. In State-B moving R
  2837. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2838. predict error 0
  2839. dir: dir isU
  2840. |\-401: O: O802 (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-B
  2843. In State-B moving U
  2844. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2845. predict error 0
  2846. dir: dir isU
  2847. /402: O: O804 (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-B
  2850. In State-B moving U
  2851. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2852. predict error 0
  2853. dir: dir isL
  2854. |\-403: O: O805 (predict-yes)
  2855. I see 1 and I'm going to do: predict-yes
  2856. ENV: Agent did: predict-yes for direction L in state State-B
  2857. In State-B moving L
  2858. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  2859. predict error 0
  2860. dir: dir isR
  2861. /|\404: O: O807 (predict-yes)
  2862. I see 1 and I'm going to do: predict-yes
  2863. ENV: Agent did: predict-yes for direction R in state State-A
  2864. In State-A moving R
  2865. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  2866. predict error 0
  2867. dir: dir isL
  2868. -/|405: O: O809 (predict-yes)
  2869. I see 1 and I'm going to do: predict-yes
  2870. ENV: Agent did: predict-yes for direction L in state State-B
  2871. In State-B moving L
  2872. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  2873. predict error 0
  2874. dir: dir isL
  2875. \-/406: O: O812 (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 isR
  2882. |\-407: O: O813 (predict-yes)
  2883. I see 1 and I'm going to do: predict-yes
  2884. ENV: Agent did: predict-yes for direction R in state State-A
  2885. In State-A moving R
  2886. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  2887. predict error 0
  2888. dir: dir isU
  2889. /|408: O: O816 (predict-no)
  2890. I see 1 and I'm going to do: predict-no
  2891. ENV: Agent did: predict-no for direction U in state State-B
  2892. In State-B moving U
  2893. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2894. predict error 0
  2895. dir: dir isL
  2896. \-/409: O: O817 (predict-yes)
  2897. I see 1 and I'm going to do: predict-yes
  2898. ENV: Agent did: predict-yes for direction L in state State-B
  2899. In State-B moving L
  2900. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  2901. predict error 0
  2902. dir: dir isU
  2903. |\-410: O: O820 (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. /|\411: O: O822 (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. -412: O: O824 (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. /|\413: O: O826 (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 isU
  2931. -/414: O: O828 (predict-no)
  2932. I see 1 and I'm going to do: predict-no
  2933. ENV: Agent did: predict-no for direction U in state State-A
  2934. In State-A moving U
  2935. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  2936. predict error 0
  2937. dir: dir isR
  2938. |\-415: O: O830 (predict-no)
  2939. I see 1 and I'm going to do: predict-no
  2940. ENV: Agent did: predict-no for direction R in state State-A
  2941. In State-A moving R
  2942. ENV: (next state, see, prediction correct?) = (State-B, 1, False)
  2943. predict error 1
  2944. dir: dir isU
  2945. /|416: O: O831 (predict-yes)
  2946. I see 0 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 isU
  2952. \-/417: O: O834 (predict-no)
  2953. I see 0 and I'm going to do: predict-no
  2954. ENV: Agent did: predict-no for direction U in state State-B
  2955. In State-B moving U
  2956. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2957. predict error 0
  2958. dir: dir isR
  2959. |\-418: O: O836 (predict-no)
  2960. I see 1 and I'm going to do: predict-no
  2961. ENV: Agent did: predict-no for direction R in state State-B
  2962. In State-B moving R
  2963. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2964. predict error 0
  2965. dir: dir isU
  2966. /|\419: O: O838 (predict-no)
  2967. I see 1 and I'm going to do: predict-no
  2968. ENV: Agent did: predict-no for direction U in state State-B
  2969. In State-B moving U
  2970. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2971. predict error 0
  2972. dir: dir isU
  2973. -/420: O: O840 (predict-no)
  2974. I see 1 and I'm going to do: predict-no
  2975. ENV: Agent did: predict-no for direction U in state State-B
  2976. In State-B moving U
  2977. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2978. predict error 0
  2979. dir: dir isU
  2980. |\-421: O: O841 (predict-yes)
  2981. I see 1 and I'm going to do: predict-yes
  2982. ENV: Agent did: predict-yes for direction U in state State-B
  2983. In State-B moving U
  2984. ENV: (next state, see, prediction correct?) = (State-B, 0, False)
  2985. predict error 1
  2986. dir: dir isR
  2987. /422: O: O844 (predict-no)
  2988. I see 0 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 isL
  2994. |\-423: O: O845 (predict-yes)
  2995. I see 1 and I'm going to do: predict-yes
  2996. ENV: Agent did: predict-yes for direction L in state State-B
  2997. In State-B moving L
  2998. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  2999. predict error 0
  3000. dir: dir isL
  3001. /|424: O: O848 (predict-no)
  3002. I see 1 and I'm going to do: predict-no
  3003. ENV: Agent did: predict-no for direction L in state State-A
  3004. In State-A moving L
  3005. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3006. predict error 0
  3007. dir: dir isL
  3008. \425: O: O850 (predict-no)
  3009. I see 1 and I'm going to do: predict-no
  3010. ENV: Agent did: predict-no for direction L in state State-A
  3011. In State-A moving L
  3012. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3013. predict error 0
  3014. dir: dir isR
  3015. -/|426: O: O851 (predict-yes)
  3016. I see 1 and I'm going to do: predict-yes
  3017. ENV: Agent did: predict-yes for direction R in state State-A
  3018. In State-A moving R
  3019. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  3020. predict error 0
  3021. dir: dir isU
  3022. \-/427: O: O854 (predict-no)
  3023. I see 1 and I'm going to do: predict-no
  3024. ENV: Agent did: predict-no for direction U in state State-B
  3025. In State-B moving U
  3026. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3027. predict error 0
  3028. dir: dir isL
  3029. |\-428: O: O855 (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 isU
  3036. /|\429: O: O858 (predict-no)
  3037. I see 1 and I'm going to do: predict-no
  3038. ENV: Agent did: predict-no for direction U in state State-A
  3039. In State-A moving U
  3040. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3041. predict error 0
  3042. dir: dir isU
  3043. -/|430: O: O860 (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-A
  3046. In State-A moving U
  3047. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3048. predict error 0
  3049. dir: dir isR
  3050. \-/431: O: O861 (predict-yes)
  3051. I see 1 and I'm going to do: predict-yes
  3052. ENV: Agent did: predict-yes for direction R in state State-A
  3053. In State-A moving R
  3054. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  3055. predict error 0
  3056. dir: dir isR
  3057. |432: O: O864 (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. \433: O: O865 (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 isU
  3071. -/|434: O: O868 (predict-no)
  3072. I see 1 and I'm going to do: predict-no
  3073. ENV: Agent did: predict-no for direction U in state State-A
  3074. In State-A moving U
  3075. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3076. predict error 0
  3077. dir: dir isL
  3078. \435: O: O870 (predict-no)
  3079. I see 1 and I'm going to do: predict-no
  3080. ENV: Agent did: predict-no for direction L in state State-A
  3081. In State-A moving L
  3082. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3083. predict error 0
  3084. dir: dir isU
  3085. -/|436: O: O872 (predict-no)
  3086. I see 1 and I'm going to do: predict-no
  3087. ENV: Agent did: predict-no for direction U in state State-A
  3088. In State-A moving U
  3089. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3090. predict error 0
  3091. dir: dir isU
  3092. \-437: O: O874 (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 isR
  3099. /|\438: O: O875 (predict-yes)
  3100. I see 1 and I'm going to do: predict-yes
  3101. ENV: Agent did: predict-yes for direction R in state State-A
  3102. In State-A moving R
  3103. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  3104. predict error 0
  3105. dir: dir isL
  3106. -439: O: O877 (predict-yes)
  3107. I see 1 and I'm going to do: predict-yes
  3108. ENV: Agent did: predict-yes for direction L in state State-B
  3109. In State-B moving L
  3110. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  3111. predict error 0
  3112. dir: dir isU
  3113. /|440: O: O880 (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 isU
  3120. \-/441: O: O882 (predict-no)
  3121. I see 1 and I'm going to do: predict-no
  3122. ENV: Agent did: predict-no for direction U in state State-A
  3123. In State-A moving U
  3124. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3125. predict error 0
  3126. dir: dir isL
  3127. |442: O: O884 (predict-no)
  3128. I see 1 and I'm going to do: predict-no
  3129. ENV: Agent did: predict-no for direction L in state State-A
  3130. In State-A moving L
  3131. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3132. predict error 0
  3133. dir: dir isU
  3134. \-/443: O: O886 (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-A
  3137. In State-A moving U
  3138. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3139. predict error 0
  3140. dir: dir isU
  3141. |\-444: O: O888 (predict-no)
  3142. I see 1 and I'm going to do: predict-no
  3143. ENV: Agent did: predict-no for direction U in state State-A
  3144. In State-A moving U
  3145. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3146. predict error 0
  3147. dir: dir isR
  3148. /|\445: O: O890 (predict-no)
  3149. I see 1 and I'm going to do: predict-no
  3150. ENV: Agent did: predict-no for direction R in state State-A
  3151. In State-A moving R
  3152. ENV: (next state, see, prediction correct?) = (State-B, 1, False)
  3153. predict error 1
  3154. dir: dir isU
  3155. -/446: O: O892 (predict-no)
  3156. I see 0 and I'm going to do: predict-no
  3157. ENV: Agent did: predict-no for direction U in state State-B
  3158. In State-B moving U
  3159. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3160. predict error 0
  3161. dir: dir isR
  3162. |\-447: O: O894 (predict-no)
  3163. I see 1 and I'm going to do: predict-no
  3164. ENV: Agent did: predict-no for direction R in state State-B
  3165. In State-B moving R
  3166. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3167. predict error 0
  3168. dir: dir isU
  3169. /|\448: O: O895 (predict-yes)
  3170. I see 1 and I'm going to do: predict-yes
  3171. ENV: Agent did: predict-yes for direction U in state State-B
  3172. In State-B moving U
  3173. ENV: (next state, see, prediction correct?) = (State-B, 0, False)
  3174. predict error 1
  3175. dir: dir isU
  3176. -/|449: O: O898 (predict-no)
  3177. I see 0 and I'm going to do: predict-no
  3178. ENV: Agent did: predict-no for direction U in state State-B
  3179. In State-B moving U
  3180. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3181. predict error 0
  3182. dir: dir isR
  3183. \-450: O: O900 (predict-no)
  3184. I see 1 and I'm going to do: predict-no
  3185. ENV: Agent did: predict-no for direction R in state State-B
  3186. In State-B moving R
  3187. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3188. predict error 0
  3189. dir: dir isU
  3190. /|\451: O: O902 (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-B
  3193. In State-B moving U
  3194. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3195. predict error 0
  3196. dir: dir isR
  3197. -452: O: O904 (predict-no)
  3198. I see 1 and I'm going to do: predict-no
  3199. ENV: Agent did: predict-no for direction R in state State-B
  3200. In State-B moving R
  3201. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3202. predict error 0
  3203. dir: dir isL
  3204. /|453: O: O905 (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 isL
  3211. \-/454: O: O908 (predict-no)
  3212. I see 1 and I'm going to do: predict-no
  3213. ENV: Agent did: predict-no for direction L in state State-A
  3214. In State-A moving L
  3215. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3216. predict error 0
  3217. dir: dir isL
  3218. |\-455: O: O909 (predict-yes)
  3219. I see 1 and I'm going to do: predict-yes
  3220. ENV: Agent did: predict-yes for direction L in state State-A
  3221. In State-A moving L
  3222. ENV: (next state, see, prediction correct?) = (State-A, 0, False)
  3223. predict error 1
  3224. dir: dir isU
  3225. /|\456: O: O912 (predict-no)
  3226. I see 0 and I'm going to do: predict-no
  3227. ENV: Agent did: predict-no for direction U in state State-A
  3228. In State-A moving U
  3229. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3230. predict error 0
  3231. dir: dir isU
  3232. -457: O: O914 (predict-no)
  3233. I see 1 and I'm going to do: predict-no
  3234. ENV: Agent did: predict-no for direction U in state State-A
  3235. In State-A moving U
  3236. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3237. predict error 0
  3238. dir: dir isL
  3239. /|\458: O: O916 (predict-no)
  3240. I see 1 and I'm going to do: predict-no
  3241. ENV: Agent did: predict-no for direction L in state State-A
  3242. In State-A moving L
  3243. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3244. predict error 0
  3245. dir: dir isR
  3246. -/|459: O: O917 (predict-yes)
  3247. I see 1 and I'm going to do: predict-yes
  3248. ENV: Agent did: predict-yes for direction R in state State-A
  3249. In State-A moving R
  3250. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  3251. predict error 0
  3252. dir: dir isR
  3253. \-/460: O: O920 (predict-no)
  3254. I see 1 and I'm going to do: predict-no
  3255. ENV: Agent did: predict-no for direction R in state State-B
  3256. In State-B moving R
  3257. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3258. predict error 0
  3259. dir: dir isL
  3260. |\461: O: O921 (predict-yes)
  3261. I see 1 and I'm going to do: predict-yes
  3262. ENV: Agent did: predict-yes for direction L in state State-B
  3263. In State-B moving L
  3264. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  3265. predict error 0
  3266. dir: dir isL
  3267. -462: O: O924 (predict-no)
  3268. I see 1 and I'm going to do: predict-no
  3269. ENV: Agent did: predict-no for direction L in state State-A
  3270. In State-A moving L
  3271. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3272. predict error 0
  3273. dir: dir isL
  3274. /|\463: O: O926 (predict-no)
  3275. I see 1 and I'm going to do: predict-no
  3276. ENV: Agent did: predict-no for direction L in state State-A
  3277. In State-A moving L
  3278. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3279. predict error 0
  3280. dir: dir isU
  3281. -/|464: O: O928 (predict-no)
  3282. I see 1 and I'm going to do: predict-no
  3283. ENV: Agent did: predict-no for direction U in state State-A
  3284. In State-A moving U
  3285. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3286. predict error 0
  3287. dir: dir isL
  3288. \-/465: O: O930 (predict-no)
  3289. I see 1 and I'm going to do: predict-no
  3290. ENV: Agent did: predict-no for direction L in state State-A
  3291. In State-A moving L
  3292. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3293. predict error 0
  3294. dir: dir isL
  3295. |466: O: O932 (predict-no)
  3296. I see 1 and I'm going to do: predict-no
  3297. ENV: Agent did: predict-no for direction L in state State-A
  3298. In State-A moving L
  3299. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3300. predict error 0
  3301. dir: dir isR
  3302. \-/467: O: O933 (predict-yes)
  3303. I see 1 and I'm going to do: predict-yes
  3304. ENV: Agent did: predict-yes for direction R in state State-A
  3305. In State-A moving R
  3306. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  3307. predict error 0
  3308. dir: dir isL
  3309. |468: O: O935 (predict-yes)
  3310. I see 1 and I'm going to do: predict-yes
  3311. ENV: Agent did: predict-yes for direction L in state State-B
  3312. In State-B moving L
  3313. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  3314. predict error 0
  3315. dir: dir isR
  3316. \-/469: O: O938 (predict-no)
  3317. I see 1 and I'm going to do: predict-no
  3318. ENV: Agent did: predict-no for direction R in state State-A
  3319. In State-A moving R
  3320. ENV: (next state, see, prediction correct?) = (State-B, 1, False)
  3321. predict error 1
  3322. dir: dir isR
  3323. |\-470: O: O940 (predict-no)
  3324. I see 0 and I'm going to do: predict-no
  3325. ENV: Agent did: predict-no for direction R in state State-B
  3326. In State-B moving R
  3327. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3328. predict error 0
  3329. dir: dir isU
  3330. /|\471: O: O942 (predict-no)
  3331. I see 1 and I'm going to do: predict-no
  3332. ENV: Agent did: predict-no for direction U in state State-B
  3333. In State-B moving U
  3334. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3335. predict error 0
  3336. dir: dir isL
  3337. -472: O: O943 (predict-yes)
  3338. I see 1 and I'm going to do: predict-yes
  3339. ENV: Agent did: predict-yes for direction L in state State-B
  3340. In State-B moving L
  3341. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  3342. predict error 0
  3343. dir: dir isL
  3344. /|\473: O: O945 (predict-yes)
  3345. I see 1 and I'm going to do: predict-yes
  3346. ENV: Agent did: predict-yes for direction L in state State-A
  3347. In State-A moving L
  3348. ENV: (next state, see, prediction correct?) = (State-A, 0, False)
  3349. predict error 1
  3350. dir: dir isR
  3351. -474: O: O947 (predict-yes)
  3352. I see 0 and I'm going to do: predict-yes
  3353. ENV: Agent did: predict-yes for direction R in state State-A
  3354. In State-A moving R
  3355. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  3356. predict error 0
  3357. dir: dir isL
  3358. /|\475: O: O949 (predict-yes)
  3359. I see 1 and I'm going to do: predict-yes
  3360. ENV: Agent did: predict-yes for direction L in state State-B
  3361. In State-B moving L
  3362. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  3363. predict error 0
  3364. dir: dir isR
  3365. -/|476: O: O952 (predict-no)
  3366. I see 1 and I'm going to do: predict-no
  3367. ENV: Agent did: predict-no for direction R in state State-A
  3368. In State-A moving R
  3369. ENV: (next state, see, prediction correct?) = (State-B, 1, False)
  3370. predict error 1
  3371. dir: dir isL
  3372. \-/477: O: O953 (predict-yes)
  3373. I see 0 and I'm going to do: predict-yes
  3374. ENV: Agent did: predict-yes for direction L in state State-B
  3375. In State-B moving L
  3376. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  3377. predict error 0
  3378. dir: dir isU
  3379. |\-478: O: O956 (predict-no)
  3380. I see 1 and I'm going to do: predict-no
  3381. ENV: Agent did: predict-no for direction U in state State-A
  3382. In State-A moving U
  3383. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3384. predict error 0
  3385. dir: dir isU
  3386. /|\479: O: O958 (predict-no)
  3387. I see 1 and I'm going to do: predict-no
  3388. ENV: Agent did: predict-no for direction U in state State-A
  3389. In State-A moving U
  3390. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3391. predict error 0
  3392. dir: dir isU
  3393. -/480: O: O960 (predict-no)
  3394. I see 1 and I'm going to do: predict-no
  3395. ENV: Agent did: predict-no for direction U in state State-A
  3396. In State-A moving U
  3397. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3398. predict error 0
  3399. dir: dir isU
  3400. |\481: O: O962 (predict-no)
  3401. I see 1 and I'm going to do: predict-no
  3402. ENV: Agent did: predict-no for direction U in state State-A
  3403. In State-A moving U
  3404. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3405. predict error 0
  3406. dir: dir isR
  3407. -482: O: O963 (predict-yes)
  3408. I see 1 and I'm going to do: predict-yes
  3409. ENV: Agent did: predict-yes for direction R in state State-A
  3410. In State-A moving R
  3411. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  3412. predict error 0
  3413. dir: dir isR
  3414. /|\483: O: O966 (predict-no)
  3415. I see 1 and I'm going to do: predict-no
  3416. ENV: Agent did: predict-no for direction R in state State-B
  3417. In State-B moving R
  3418. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3419. predict error 0
  3420. dir: dir isU
  3421. -/|484: O: O968 (predict-no)
  3422. I see 1 and I'm going to do: predict-no
  3423. ENV: Agent did: predict-no for direction U in state State-B
  3424. In State-B moving U
  3425. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3426. predict error 0
  3427. dir: dir isU
  3428. \-/485: O: O970 (predict-no)
  3429. I see 1 and I'm going to do: predict-no
  3430. ENV: Agent did: predict-no for direction U in state State-B
  3431. In State-B moving U
  3432. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3433. predict error 0
  3434. dir: dir isR
  3435. |\-486: O: O972 (predict-no)
  3436. I see 1 and I'm going to do: predict-no
  3437. ENV: Agent did: predict-no for direction R in state State-B
  3438. In State-B moving R
  3439. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3440. predict error 0
  3441. dir: dir isR
  3442. /|\487: O: O974 (predict-no)
  3443. I see 1 and I'm going to do: predict-no
  3444. ENV: Agent did: predict-no for direction R in state State-B
  3445. In State-B moving R
  3446. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3447. predict error 0
  3448. dir: dir isL
  3449. -/|488: O: O975 (predict-yes)
  3450. I see 1 and I'm going to do: predict-yes
  3451. ENV: Agent did: predict-yes for direction L in state State-B
  3452. In State-B moving L
  3453. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  3454. predict error 0
  3455. dir: dir isL
  3456. \-/489: O: O978 (predict-no)
  3457. I see 1 and I'm going to do: predict-no
  3458. ENV: Agent did: predict-no for direction L in state State-A
  3459. In State-A moving L
  3460. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3461. predict error 0
  3462. dir: dir isU
  3463. |\-490: O: O980 (predict-no)
  3464. I see 1 and I'm going to do: predict-no
  3465. ENV: Agent did: predict-no for direction U in state State-A
  3466. In State-A moving U
  3467. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3468. predict error 0
  3469. dir: dir isL
  3470. /|\491: O: O982 (predict-no)
  3471. I see 1 and I'm going to do: predict-no
  3472. ENV: Agent did: predict-no for direction L in state State-A
  3473. In State-A moving L
  3474. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3475. predict error 0
  3476. dir: dir isU
  3477. -492: O: O984 (predict-no)
  3478. I see 1 and I'm going to do: predict-no
  3479. ENV: Agent did: predict-no for direction U in state State-A
  3480. In State-A moving U
  3481. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3482. predict error 0
  3483. dir: dir isR
  3484. /|\493: O: O985 (predict-yes)
  3485. I see 1 and I'm going to do: predict-yes
  3486. ENV: Agent did: predict-yes for direction R in state State-A
  3487. In State-A moving R
  3488. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  3489. predict error 0
  3490. dir: dir isU
  3491. -/|494: O: O988 (predict-no)
  3492. I see 1 and I'm going to do: predict-no
  3493. ENV: Agent did: predict-no for direction U in state State-B
  3494. In State-B moving U
  3495. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3496. predict error 0
  3497. dir: dir isU
  3498. \-/495: O: O990 (predict-no)
  3499. I see 1 and I'm going to do: predict-no
  3500. ENV: Agent did: predict-no for direction U in state State-B
  3501. In State-B moving U
  3502. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3503. predict error 0
  3504. dir: dir isU
  3505. |\-496: O: O992 (predict-no)
  3506. I see 1 and I'm going to do: predict-no
  3507. ENV: Agent did: predict-no for direction U in state State-B
  3508. In State-B moving U
  3509. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3510. predict error 0
  3511. dir: dir isL
  3512. /|\497: O: O993 (predict-yes)
  3513. I see 1 and I'm going to do: predict-yes
  3514. ENV: Agent did: predict-yes for direction L in state State-B
  3515. In State-B moving L
  3516. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  3517. predict error 0
  3518. dir: dir isR
  3519. -/|498: O: O995 (predict-yes)
  3520. I see 1 and I'm going to do: predict-yes
  3521. ENV: Agent did: predict-yes for direction R in state State-A
  3522. In State-A moving R
  3523. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  3524. predict error 0
  3525. dir: dir isR
  3526. \-/499: O: O998 (predict-no)
  3527. I see 1 and I'm going to do: predict-no
  3528. ENV: Agent did: predict-no for direction R in state State-B
  3529. In State-B moving R
  3530. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3531. predict error 0
  3532. dir: dir isL
  3533. |\-500: O: O999 (predict-yes)
  3534. I see 1 and I'm going to do: predict-yes
  3535. ENV: Agent did: predict-yes for direction L in state State-B
  3536. In State-B moving L
  3537. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  3538. predict error 0
  3539. dir: dir isR
  3540. /|\-/|501: O: O1001 (predict-yes)
  3541. I see 1 and I'm going to do: predict-yes
  3542. ENV: Agent did: predict-yes for direction R in state State-A
  3543. In State-A moving R
  3544. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  3545. predict error 0
  3546. dir: dir isR
  3547. \502: O: O1004 (predict-no)
  3548. I see 1 and I'm going to do: predict-no
  3549. ENV: Agent did: predict-no for direction R in state State-B
  3550. In State-B moving R
  3551. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3552. predict error 0
  3553. dir: dir isR
  3554. -/|503: O: O1006 (predict-no)
  3555. I see 1 and I'm going to do: predict-no
  3556. ENV: Agent did: predict-no for direction R in state State-B
  3557. In State-B moving R
  3558. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3559. predict error 0
  3560. dir: dir isL
  3561. \-/504: O: O1007 (predict-yes)
  3562. I see 1 and I'm going to do: predict-yes
  3563. ENV: Agent did: predict-yes for direction L in state State-B
  3564. In State-B moving L
  3565. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  3566. predict error 0
  3567. dir: dir isR
  3568. |\505: O: O1009 (predict-yes)
  3569. I see 1 and I'm going to do: predict-yes
  3570. ENV: Agent did: predict-yes for direction R in state State-A
  3571. In State-A moving R
  3572. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  3573. predict error 0
  3574. dir: dir isR
  3575. -/506: O: O1012 (predict-no)
  3576. I see 1 and I'm going to do: predict-no
  3577. ENV: Agent did: predict-no for direction R in state State-B
  3578. In State-B moving R
  3579. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3580. predict error 0
  3581. dir: dir isL
  3582. |\-507: O: O1013 (predict-yes)
  3583. I see 1 and I'm going to do: predict-yes
  3584. ENV: Agent did: predict-yes for direction L in state State-B
  3585. In State-B moving L
  3586. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  3587. predict error 0
  3588. dir: dir isR
  3589. /|\508: O: O1015 (predict-yes)
  3590. I see 1 and I'm going to do: predict-yes
  3591. ENV: Agent did: predict-yes for direction R in state State-A
  3592. In State-A moving R
  3593. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  3594. predict error 0
  3595. dir: dir isU
  3596. -509: O: O1018 (predict-no)
  3597. I see 1 and I'm going to do: predict-no
  3598. ENV: Agent did: predict-no for direction U in state State-B
  3599. In State-B moving U
  3600. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3601. predict error 0
  3602. dir: dir isU
  3603. /|\510: O: O1020 (predict-no)
  3604. I see 1 and I'm going to do: predict-no
  3605. ENV: Agent did: predict-no for direction U in state State-B
  3606. In State-B moving U
  3607. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3608. predict error 0
  3609. dir: dir isR
  3610. -/|511: O: O1022 (predict-no)
  3611. I see 1 and I'm going to do: predict-no
  3612. ENV: Agent did: predict-no for direction R in state State-B
  3613. In State-B moving R
  3614. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3615. predict error 0
  3616. dir: dir isR
  3617. \512: O: O1023 (predict-yes)
  3618. I see 1 and I'm going to do: predict-yes
  3619. ENV: Agent did: predict-yes for direction R in state State-B
  3620. In State-B moving R
  3621. ENV: (next state, see, prediction correct?) = (State-B, 0, False)
  3622. predict error 1
  3623. dir: dir isR
  3624. -/|513: O: O1026 (predict-no)
  3625. I see 0 and I'm going to do: predict-no
  3626. ENV: Agent did: predict-no for direction R in state State-B
  3627. In State-B moving R
  3628. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3629. predict error 0
  3630. dir: dir isL
  3631. \-/514: O: O1027 (predict-yes)
  3632. I see 1 and I'm going to do: predict-yes
  3633. ENV: Agent did: predict-yes for direction L in state State-B
  3634. In State-B moving L
  3635. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  3636. predict error 0
  3637. dir: dir isL
  3638. |\-515: O: O1030 (predict-no)
  3639. I see 1 and I'm going to do: predict-no
  3640. ENV: Agent did: predict-no for direction L in state State-A
  3641. In State-A moving L
  3642. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3643. predict error 0
  3644. dir: dir isL
  3645. /|\516: O: O1032 (predict-no)
  3646. I see 1 and I'm going to do: predict-no
  3647. ENV: Agent did: predict-no for direction L in state State-A
  3648. In State-A moving L
  3649. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3650. predict error 0
  3651. dir: dir isR
  3652. -/|517: O: O1034 (predict-no)
  3653. I see 1 and I'm going to do: predict-no
  3654. ENV: Agent did: predict-no for direction R in state State-A
  3655. In State-A moving R
  3656. ENV: (next state, see, prediction correct?) = (State-B, 1, False)
  3657. predict error 1
  3658. dir: dir isU
  3659. \518: O: O1036 (predict-no)
  3660. I see 0 and I'm going to do: predict-no
  3661. ENV: Agent did: predict-no for direction U in state State-B
  3662. In State-B moving U
  3663. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3664. predict error 0
  3665. dir: dir isU
  3666. -/519: O: O1038 (predict-no)
  3667. I see 1 and I'm going to do: predict-no
  3668. ENV: Agent did: predict-no for direction U in state State-B
  3669. In State-B moving U
  3670. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3671. predict error 0
  3672. dir: dir isR
  3673. |\-520: O: O1040 (predict-no)
  3674. I see 1 and I'm going to do: predict-no
  3675. ENV: Agent did: predict-no for direction R in state State-B
  3676. In State-B moving R
  3677. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3678. predict error 0
  3679. dir: dir isU
  3680. /|\521: O: O1042 (predict-no)
  3681. I see 1 and I'm going to do: predict-no
  3682. ENV: Agent did: predict-no for direction U in state State-B
  3683. In State-B moving U
  3684. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3685. predict error 0
  3686. dir: dir isR
  3687. -522: O: O1044 (predict-no)
  3688. I see 1 and I'm going to do: predict-no
  3689. ENV: Agent did: predict-no for direction R in state State-B
  3690. In State-B moving R
  3691. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3692. predict error 0
  3693. dir: dir isU
  3694. /|\523: O: O1046 (predict-no)
  3695. I see 1 and I'm going to do: predict-no
  3696. ENV: Agent did: predict-no for direction U in state State-B
  3697. In State-B moving U
  3698. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3699. predict error 0
  3700. dir: dir isR
  3701. -/524: O: O1048 (predict-no)
  3702. I see 1 and I'm going to do: predict-no
  3703. ENV: Agent did: predict-no for direction R in state State-B
  3704. In State-B moving R
  3705. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3706. predict error 0
  3707. dir: dir isU
  3708. |\-/525: O: O1050 (predict-no)
  3709. I see 1 and I'm going to do: predict-no
  3710. ENV: Agent did: predict-no for direction U in state State-B
  3711. In State-B moving U
  3712. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3713. predict error 0
  3714. dir: dir isU
  3715. |\526: O: O1052 (predict-no)
  3716. I see 1 and I'm going to do: predict-no
  3717. ENV: Agent did: predict-no for direction U in state State-B
  3718. In State-B moving U
  3719. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3720. predict error 0
  3721. dir: dir isL
  3722. -/|527: O: O1053 (predict-yes)
  3723. I see 1 and I'm going to do: predict-yes
  3724. ENV: Agent did: predict-yes for direction L in state State-B
  3725. In State-B moving L
  3726. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  3727. predict error 0
  3728. dir: dir isL
  3729. \-/528: O: O1056 (predict-no)
  3730. I see 1 and I'm going to do: predict-no
  3731. ENV: Agent did: predict-no for direction L in state State-A
  3732. In State-A moving L
  3733. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3734. predict error 0
  3735. dir: dir isR
  3736. |\-529: O: O1057 (predict-yes)
  3737. I see 1 and I'm going to do: predict-yes
  3738. ENV: Agent did: predict-yes for direction R in state State-A
  3739. In State-A moving R
  3740. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  3741. predict error 0
  3742. dir: dir isR
  3743. /|\530: O: O1060 (predict-no)
  3744. I see 1 and I'm going to do: predict-no
  3745. ENV: Agent did: predict-no for direction R in state State-B
  3746. In State-B moving R
  3747. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3748. predict error 0
  3749. dir: dir isR
  3750. -/|531: O: O1062 (predict-no)
  3751. I see 1 and I'm going to do: predict-no
  3752. ENV: Agent did: predict-no for direction R in state State-B
  3753. In State-B moving R
  3754. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3755. predict error 0
  3756. dir: dir isL
  3757. \532: O: O1063 (predict-yes)
  3758. I see 1 and I'm going to do: predict-yes
  3759. ENV: Agent did: predict-yes for direction L in state State-B
  3760. In State-B moving L
  3761. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  3762. predict error 0
  3763. dir: dir isR
  3764. -/533: O: O1065 (predict-yes)
  3765. I see 1 and I'm going to do: predict-yes
  3766. ENV: Agent did: predict-yes for direction R in state State-A
  3767. In State-A moving R
  3768. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  3769. predict error 0
  3770. dir: dir isR
  3771. |\534: O: O1068 (predict-no)
  3772. I see 1 and I'm going to do: predict-no
  3773. ENV: Agent did: predict-no for direction R in state State-B
  3774. In State-B moving R
  3775. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3776. predict error 0
  3777. dir: dir isR
  3778. -/|535: O: O1070 (predict-no)
  3779. I see 1 and I'm going to do: predict-no
  3780. ENV: Agent did: predict-no for direction R in state State-B
  3781. In State-B moving R
  3782. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3783. predict error 0
  3784. dir: dir isU
  3785. \-/536: O: O1072 (predict-no)
  3786. I see 1 and I'm going to do: predict-no
  3787. ENV: Agent did: predict-no for direction U in state State-B
  3788. In State-B moving U
  3789. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3790. predict error 0
  3791. dir: dir isR
  3792. |\-537: O: O1074 (predict-no)
  3793. I see 1 and I'm going to do: predict-no
  3794. ENV: Agent did: predict-no for direction R in state State-B
  3795. In State-B moving R
  3796. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3797. predict error 0
  3798. dir: dir isU
  3799. /|\538: O: O1076 (predict-no)
  3800. I see 1 and I'm going to do: predict-no
  3801. ENV: Agent did: predict-no for direction U in state State-B
  3802. In State-B moving U
  3803. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3804. predict error 0
  3805. dir: dir isU
  3806. -539: O: O1078 (predict-no)
  3807. I see 1 and I'm going to do: predict-no
  3808. ENV: Agent did: predict-no for direction U in state State-B
  3809. In State-B moving U
  3810. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3811. predict error 0
  3812. dir: dir isU
  3813. /|540: O: O1080 (predict-no)
  3814. I see 1 and I'm going to do: predict-no
  3815. ENV: Agent did: predict-no for direction U in state State-B
  3816. In State-B moving U
  3817. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3818. predict error 0
  3819. dir: dir isR
  3820. \-/541: O: O1082 (predict-no)
  3821. I see 1 and I'm going to do: predict-no
  3822. ENV: Agent did: predict-no for direction R in state State-B
  3823. In State-B moving R
  3824. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3825. predict error 0
  3826. dir: dir isU
  3827. |542: O: O1083 (predict-yes)
  3828. I see 1 and I'm going to do: predict-yes
  3829. ENV: Agent did: predict-yes for direction U in state State-B
  3830. In State-B moving U
  3831. ENV: (next state, see, prediction correct?) = (State-B, 0, False)
  3832. predict error 1
  3833. dir: dir isR
  3834. \-/543: O: O1086 (predict-no)
  3835. I see 0 and I'm going to do: predict-no
  3836. ENV: Agent did: predict-no for direction R in state State-B
  3837. In State-B moving R
  3838. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3839. predict error 0
  3840. dir: dir isR
  3841. |\-544: O: O1088 (predict-no)
  3842. I see 1 and I'm going to do: predict-no
  3843. ENV: Agent did: predict-no for direction R in state State-B
  3844. In State-B moving R
  3845. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3846. predict error 0
  3847. dir: dir isR
  3848. /|\545: O: O1090 (predict-no)
  3849. I see 1 and I'm going to do: predict-no
  3850. ENV: Agent did: predict-no for direction R in state State-B
  3851. In State-B moving R
  3852. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3853. predict error 0
  3854. dir: dir isR
  3855. -/546: O: O1092 (predict-no)
  3856. I see 1 and I'm going to do: predict-no
  3857. ENV: Agent did: predict-no for direction R in state State-B
  3858. In State-B moving R
  3859. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3860. predict error 0
  3861. dir: dir isR
  3862. |\547: O: O1094 (predict-no)
  3863. I see 1 and I'm going to do: predict-no
  3864. ENV: Agent did: predict-no for direction R in state State-B
  3865. In State-B moving R
  3866. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3867. predict error 0
  3868. dir: dir isR
  3869. -/|548: O: O1096 (predict-no)
  3870. I see 1 and I'm going to do: predict-no
  3871. ENV: Agent did: predict-no for direction R in state State-B
  3872. In State-B moving R
  3873. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3874. predict error 0
  3875. dir: dir isU
  3876. \-/549: O: O1098 (predict-no)
  3877. I see 1 and I'm going to do: predict-no
  3878. ENV: Agent did: predict-no for direction U in state State-B
  3879. In State-B moving U
  3880. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3881. predict error 0
  3882. dir: dir isU
  3883. |550: O: O1099 (predict-yes)
  3884. I see 1 and I'm going to do: predict-yes
  3885. ENV: Agent did: predict-yes for direction U in state State-B
  3886. In State-B moving U
  3887. ENV: (next state, see, prediction correct?) = (State-B, 0, False)
  3888. predict error 1
  3889. dir: dir isU
  3890. \-/551: O: O1102 (predict-no)
  3891. I see 0 and I'm going to do: predict-no
  3892. ENV: Agent did: predict-no for direction U in state State-B
  3893. In State-B moving U
  3894. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3895. predict error 0
  3896. dir: dir isU
  3897. |552: O: O1104 (predict-no)
  3898. I see 1 and I'm going to do: predict-no
  3899. ENV: Agent did: predict-no for direction U in state State-B
  3900. In State-B moving U
  3901. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3902. predict error 0
  3903. dir: dir isU
  3904. \-/553: O: O1105 (predict-yes)
  3905. I see 1 and I'm going to do: predict-yes
  3906. ENV: Agent did: predict-yes for direction U in state State-B
  3907. In State-B moving U
  3908. ENV: (next state, see, prediction correct?) = (State-B, 0, False)
  3909. predict error 1
  3910. dir: dir isR
  3911. |\-554: O: O1108 (predict-no)
  3912. I see 0 and I'm going to do: predict-no
  3913. ENV: Agent did: predict-no for direction R in state State-B
  3914. In State-B moving R
  3915. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3916. predict error 0
  3917. dir: dir isR
  3918. /|\555: O: O1110 (predict-no)
  3919. I see 1 and I'm going to do: predict-no
  3920. ENV: Agent did: predict-no for direction R in state State-B
  3921. In State-B moving R
  3922. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3923. predict error 0
  3924. dir: dir isL
  3925. -556: O: O1111 (predict-yes)
  3926. I see 1 and I'm going to do: predict-yes
  3927. ENV: Agent did: predict-yes for direction L in state State-B
  3928. In State-B moving L
  3929. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  3930. predict error 0
  3931. dir: dir isU
  3932. /|\557: O: O1114 (predict-no)
  3933. I see 1 and I'm going to do: predict-no
  3934. ENV: Agent did: predict-no for direction U in state State-A
  3935. In State-A moving U
  3936. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3937. predict error 0
  3938. dir: dir isU
  3939. -/|558: O: O1116 (predict-no)
  3940. I see 1 and I'm going to do: predict-no
  3941. ENV: Agent did: predict-no for direction U in state State-A
  3942. In State-A moving U
  3943. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3944. predict error 0
  3945. dir: dir isR
  3946. \-/559: O: O1118 (predict-no)
  3947. I see 1 and I'm going to do: predict-no
  3948. ENV: Agent did: predict-no for direction R in state State-A
  3949. In State-A moving R
  3950. ENV: (next state, see, prediction correct?) = (State-B, 1, False)
  3951. predict error 1
  3952. dir: dir isL
  3953. |\-560: O: O1119 (predict-yes)
  3954. I see 0 and I'm going to do: predict-yes
  3955. ENV: Agent did: predict-yes for direction L in state State-B
  3956. In State-B moving L
  3957. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  3958. predict error 0
  3959. dir: dir isU
  3960. /|\561: O: O1122 (predict-no)
  3961. I see 1 and I'm going to do: predict-no
  3962. ENV: Agent did: predict-no for direction U in state State-A
  3963. In State-A moving U
  3964. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3965. predict error 0
  3966. dir: dir isR
  3967. -562: O: O1124 (predict-no)
  3968. I see 1 and I'm going to do: predict-no
  3969. ENV: Agent did: predict-no for direction R in state State-A
  3970. In State-A moving R
  3971. ENV: (next state, see, prediction correct?) = (State-B, 1, False)
  3972. predict error 1
  3973. dir: dir isR
  3974. /|563: O: O1126 (predict-no)
  3975. I see 0 and I'm going to do: predict-no
  3976. ENV: Agent did: predict-no for direction R in state State-B
  3977. In State-B moving R
  3978. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3979. predict error 0
  3980. dir: dir isL
  3981. \-/564: O: O1127 (predict-yes)
  3982. I see 1 and I'm going to do: predict-yes
  3983. ENV: Agent did: predict-yes for direction L in state State-B
  3984. In State-B moving L
  3985. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  3986. predict error 0
  3987. dir: dir isR
  3988. |\565: O: O1129 (predict-yes)
  3989. I see 1 and I'm going to do: predict-yes
  3990. ENV: Agent did: predict-yes for direction R in state State-A
  3991. In State-A moving R
  3992. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  3993. predict error 0
  3994. dir: dir isU
  3995. -/|566: O: O1132 (predict-no)
  3996. I see 1 and I'm going to do: predict-no
  3997. ENV: Agent did: predict-no for direction U in state State-B
  3998. In State-B moving U
  3999. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4000. predict error 0
  4001. dir: dir isR
  4002. \-/567: O: O1134 (predict-no)
  4003. I see 1 and I'm going to do: predict-no
  4004. ENV: Agent did: predict-no for direction R in state State-B
  4005. In State-B moving R
  4006. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4007. predict error 0
  4008. dir: dir isR
  4009. |\568: O: O1136 (predict-no)
  4010. I see 1 and I'm going to do: predict-no
  4011. ENV: Agent did: predict-no for direction R in state State-B
  4012. In State-B moving R
  4013. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4014. predict error 0
  4015. dir: dir isR
  4016. -/|\569: O: O1138 (predict-no)
  4017. I see 1 and I'm going to do: predict-no
  4018. ENV: Agent did: predict-no for direction R in state State-B
  4019. In State-B moving R
  4020. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4021. predict error 0
  4022. dir: dir isL
  4023. -/|570: O: O1139 (predict-yes)
  4024. I see 1 and I'm going to do: predict-yes
  4025. ENV: Agent did: predict-yes for direction L in state State-B
  4026. In State-B moving L
  4027. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  4028. predict error 0
  4029. dir: dir isR
  4030. \-571: O: O1141 (predict-yes)
  4031. I see 1 and I'm going to do: predict-yes
  4032. ENV: Agent did: predict-yes for direction R in state State-A
  4033. In State-A moving R
  4034. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  4035. predict error 0
  4036. dir: dir isU
  4037. /572: O: O1144 (predict-no)
  4038. I see 1 and I'm going to do: predict-no
  4039. ENV: Agent did: predict-no for direction U in state State-B
  4040. In State-B moving U
  4041. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4042. predict error 0
  4043. dir: dir isU
  4044. |\-573: O: O1146 (predict-no)
  4045. I see 1 and I'm going to do: predict-no
  4046. ENV: Agent did: predict-no for direction U in state State-B
  4047. In State-B moving U
  4048. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4049. predict error 0
  4050. dir: dir isR
  4051. /|\574: O: O1148 (predict-no)
  4052. I see 1 and I'm going to do: predict-no
  4053. ENV: Agent did: predict-no for direction R in state State-B
  4054. In State-B moving R
  4055. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4056. predict error 0
  4057. dir: dir isU
  4058. -/|575: O: O1150 (predict-no)
  4059. I see 1 and I'm going to do: predict-no
  4060. ENV: Agent did: predict-no for direction U in state State-B
  4061. In State-B moving U
  4062. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4063. predict error 0
  4064. dir: dir isR
  4065. \-/576: O: O1152 (predict-no)
  4066. I see 1 and I'm going to do: predict-no
  4067. ENV: Agent did: predict-no for direction R in state State-B
  4068. In State-B moving R
  4069. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4070. predict error 0
  4071. dir: dir isL
  4072. |577: O: O1153 (predict-yes)
  4073. I see 1 and I'm going to do: predict-yes
  4074. ENV: Agent did: predict-yes for direction L in state State-B
  4075. In State-B moving L
  4076. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  4077. predict error 0
  4078. dir: dir isL
  4079. \-/578: O: O1156 (predict-no)
  4080. I see 1 and I'm going to do: predict-no
  4081. ENV: Agent did: predict-no for direction L in state State-A
  4082. In State-A moving L
  4083. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4084. predict error 0
  4085. dir: dir isU
  4086. |\-579: O: O1158 (predict-no)
  4087. I see 1 and I'm going to do: predict-no
  4088. ENV: Agent did: predict-no for direction U in state State-A
  4089. In State-A moving U
  4090. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4091. predict error 0
  4092. dir: dir isL
  4093. /|580: O: O1160 (predict-no)
  4094. I see 1 and I'm going to do: predict-no
  4095. ENV: Agent did: predict-no for direction L in state State-A
  4096. In State-A moving L
  4097. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4098. predict error 0
  4099. dir: dir isL
  4100. \-/581: O: O1162 (predict-no)
  4101. I see 1 and I'm going to do: predict-no
  4102. ENV: Agent did: predict-no for direction L in state State-A
  4103. In State-A moving L
  4104. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4105. predict error 0
  4106. dir: dir isU
  4107. |582: O: O1164 (predict-no)
  4108. I see 1 and I'm going to do: predict-no
  4109. ENV: Agent did: predict-no for direction U in state State-A
  4110. In State-A moving U
  4111. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4112. predict error 0
  4113. dir: dir isR
  4114. \-/583: O: O1165 (predict-yes)
  4115. I see 1 and I'm going to do: predict-yes
  4116. ENV: Agent did: predict-yes for direction R in state State-A
  4117. In State-A moving R
  4118. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  4119. predict error 0
  4120. dir: dir isR
  4121. |\-584: O: O1168 (predict-no)
  4122. I see 1 and I'm going to do: predict-no
  4123. ENV: Agent did: predict-no for direction R in state State-B
  4124. In State-B moving R
  4125. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4126. predict error 0
  4127. dir: dir isR
  4128. /|585: O: O1170 (predict-no)
  4129. I see 1 and I'm going to do: predict-no
  4130. ENV: Agent did: predict-no for direction R in state State-B
  4131. In State-B moving R
  4132. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4133. predict error 0
  4134. dir: dir isU
  4135. \586: O: O1172 (predict-no)
  4136. I see 1 and I'm going to do: predict-no
  4137. ENV: Agent did: predict-no for direction U in state State-B
  4138. In State-B moving U
  4139. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4140. predict error 0
  4141. dir: dir isL
  4142. -/|587: O: O1173 (predict-yes)
  4143. I see 1 and I'm going to do: predict-yes
  4144. ENV: Agent did: predict-yes for direction L in state State-B
  4145. In State-B moving L
  4146. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  4147. predict error 0
  4148. dir: dir isR
  4149. \-588: O: O1175 (predict-yes)
  4150. I see 1 and I'm going to do: predict-yes
  4151. ENV: Agent did: predict-yes for direction R in state State-A
  4152. In State-A moving R
  4153. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  4154. predict error 0
  4155. dir: dir isU
  4156. /|\589: O: O1178 (predict-no)
  4157. I see 1 and I'm going to do: predict-no
  4158. ENV: Agent did: predict-no for direction U in state State-B
  4159. In State-B moving U
  4160. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4161. predict error 0
  4162. dir: dir isU
  4163. -/|590: O: O1180 (predict-no)
  4164. I see 1 and I'm going to do: predict-no
  4165. ENV: Agent did: predict-no for direction U in state State-B
  4166. In State-B moving U
  4167. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4168. predict error 0
  4169. dir: dir isL
  4170. \-/591: O: O1181 (predict-yes)
  4171. I see 1 and I'm going to do: predict-yes
  4172. ENV: Agent did: predict-yes for direction L in state State-B
  4173. In State-B moving L
  4174. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  4175. predict error 0
  4176. dir: dir isR
  4177. |592: O: O1183 (predict-yes)
  4178. I see 1 and I'm going to do: predict-yes
  4179. ENV: Agent did: predict-yes for direction R in state State-A
  4180. In State-A moving R
  4181. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  4182. predict error 0
  4183. dir: dir isL
  4184. \-/|593: O: O1185 (predict-yes)
  4185. I see 1 and I'm going to do: predict-yes
  4186. ENV: Agent did: predict-yes for direction L in state State-B
  4187. In State-B moving L
  4188. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  4189. predict error 0
  4190. dir: dir isR
  4191. \-/594: O: O1187 (predict-yes)
  4192. I see 1 and I'm going to do: predict-yes
  4193. ENV: Agent did: predict-yes for direction R in state State-A
  4194. In State-A moving R
  4195. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  4196. predict error 0
  4197. dir: dir isL
  4198. |\-/595: O: O1189 (predict-yes)
  4199. I see 1 and I'm going to do: predict-yes
  4200. ENV: Agent did: predict-yes for direction L in state State-B
  4201. In State-B moving L
  4202. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  4203. predict error 0
  4204. dir: dir isU
  4205. |\-596: O: O1192 (predict-no)
  4206. I see 1 and I'm going to do: predict-no
  4207. ENV: Agent did: predict-no for direction U in state State-A
  4208. In State-A moving U
  4209. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4210. predict error 0
  4211. dir: dir isU
  4212. /|\597: O: O1194 (predict-no)
  4213. I see 1 and I'm going to do: predict-no
  4214. ENV: Agent did: predict-no for direction U in state State-A
  4215. In State-A moving U
  4216. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4217. predict error 0
  4218. dir: dir isL
  4219. -/598: O: O1196 (predict-no)
  4220. I see 1 and I'm going to do: predict-no
  4221. ENV: Agent did: predict-no for direction L in state State-A
  4222. In State-A moving L
  4223. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4224. predict error 0
  4225. dir: dir isL
  4226. |\-599: O: O1198 (predict-no)
  4227. I see 1 and I'm going to do: predict-no
  4228. ENV: Agent did: predict-no for direction L in state State-A
  4229. In State-A moving L
  4230. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4231. predict error 0
  4232. dir: dir isU
  4233. /|600: O: O1200 (predict-no)
  4234. I see 1 and I'm going to do: predict-no
  4235. ENV: Agent did: predict-no for direction U in state State-A
  4236. In State-A moving U
  4237. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4238. predict error 0
  4239. dir: dir isU
  4240. \-/601: O: O1202 (predict-no)
  4241. I see 1 and I'm going to do: predict-no
  4242. ENV: Agent did: predict-no for direction U in state State-A
  4243. In State-A moving U
  4244. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4245. predict error 0
  4246. dir: dir isU
  4247. |602: O: O1204 (predict-no)
  4248. I see 1 and I'm going to do: predict-no
  4249. ENV: Agent did: predict-no for direction U in state State-A
  4250. In State-A moving U
  4251. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4252. predict error 0
  4253. dir: dir isL
  4254. \-603: O: O1206 (predict-no)
  4255. I see 1 and I'm going to do: predict-no
  4256. ENV: Agent did: predict-no for direction L in state State-A
  4257. In State-A moving L
  4258. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4259. predict error 0
  4260. dir: dir isU
  4261. /604: O: O1208 (predict-no)
  4262. I see 1 and I'm going to do: predict-no
  4263. ENV: Agent did: predict-no for direction U in state State-A
  4264. In State-A moving U
  4265. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4266. predict error 0
  4267. dir: dir isR
  4268. |\-605: O: O1209 (predict-yes)
  4269. I see 1 and I'm going to do: predict-yes
  4270. ENV: Agent did: predict-yes for direction R in state State-A
  4271. In State-A moving R
  4272. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  4273. predict error 0
  4274. dir: dir isL
  4275. /|\606: O: O1211 (predict-yes)
  4276. I see 1 and I'm going to do: predict-yes
  4277. ENV: Agent did: predict-yes for direction L in state State-B
  4278. In State-B moving L
  4279. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  4280. predict error 0
  4281. dir: dir isR
  4282. -607: O: O1213 (predict-yes)
  4283. I see 1 and I'm going to do: predict-yes
  4284. ENV: Agent did: predict-yes for direction R in state State-A
  4285. In State-A moving R
  4286. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  4287. predict error 0
  4288. dir: dir isU
  4289. /|\608: O: O1216 (predict-no)
  4290. I see 1 and I'm going to do: predict-no
  4291. ENV: Agent did: predict-no for direction U in state State-B
  4292. In State-B moving U
  4293. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4294. predict error 0
  4295. dir: dir isU
  4296. -/|609: O: O1218 (predict-no)
  4297. I see 1 and I'm going to do: predict-no
  4298. ENV: Agent did: predict-no for direction U in state State-B
  4299. In State-B moving U
  4300. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4301. predict error 0
  4302. dir: dir isL
  4303. \-/610: O: O1219 (predict-yes)
  4304. I see 1 and I'm going to do: predict-yes
  4305. ENV: Agent did: predict-yes for direction L in state State-B
  4306. In State-B moving L
  4307. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  4308. predict error 0
  4309. dir: dir isR
  4310. |\-611: O: O1221 (predict-yes)
  4311. I see 1 and I'm going to do: predict-yes
  4312. ENV: Agent did: predict-yes for direction R in state State-A
  4313. In State-A moving R
  4314. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  4315. predict error 0
  4316. dir: dir isL
  4317. /612: O: O1224 (predict-no)
  4318. I see 1 and I'm going to do: predict-no
  4319. ENV: Agent did: predict-no for direction L in state State-B
  4320. In State-B moving L
  4321. ENV: (next state, see, prediction correct?) = (State-A, 1, False)
  4322. predict error 1
  4323. dir: dir isU
  4324. |\613: O: O1226 (predict-no)
  4325. I see 0 and I'm going to do: predict-no
  4326. ENV: Agent did: predict-no for direction U in state State-A
  4327. In State-A moving U
  4328. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4329. predict error 0
  4330. dir: dir isR
  4331. -/|614: O: O1227 (predict-yes)
  4332. I see 1 and I'm going to do: predict-yes
  4333. ENV: Agent did: predict-yes for direction R in state State-A
  4334. In State-A moving R
  4335. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  4336. predict error 0
  4337. dir: dir isU
  4338. \-/615: O: O1230 (predict-no)
  4339. I see 1 and I'm going to do: predict-no
  4340. ENV: Agent did: predict-no for direction U in state State-B
  4341. In State-B moving U
  4342. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4343. predict error 0
  4344. dir: dir isU
  4345. |\-616: O: O1232 (predict-no)
  4346. I see 1 and I'm going to do: predict-no
  4347. ENV: Agent did: predict-no for direction U in state State-B
  4348. In State-B moving U
  4349. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4350. predict error 0
  4351. dir: dir isR
  4352. /|\617: O: O1233 (predict-yes)
  4353. I see 1 and I'm going to do: predict-yes
  4354. ENV: Agent did: predict-yes for direction R in state State-B
  4355. In State-B moving R
  4356. ENV: (next state, see, prediction correct?) = (State-B, 0, False)
  4357. predict error 1
  4358. dir: dir isL
  4359. -/|618: O: O1235 (predict-yes)
  4360. I see 0 and I'm going to do: predict-yes
  4361. ENV: Agent did: predict-yes for direction L in state State-B
  4362. In State-B moving L
  4363. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  4364. predict error 0
  4365. dir: dir isR
  4366. \-/619: O: O1237 (predict-yes)
  4367. I see 1 and I'm going to do: predict-yes
  4368. ENV: Agent did: predict-yes for direction R in state State-A
  4369. In State-A moving R
  4370. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  4371. predict error 0
  4372. dir: dir isL
  4373. |\620: O: O1239 (predict-yes)
  4374. I see 1 and I'm going to do: predict-yes
  4375. ENV: Agent did: predict-yes for direction L in state State-B
  4376. In State-B moving L
  4377. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  4378. predict error 0
  4379. dir: dir isL
  4380. -/|621: O: O1242 (predict-no)
  4381. I see 1 and I'm going to do: predict-no
  4382. ENV: Agent did: predict-no for direction L in state State-A
  4383. In State-A moving L
  4384. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4385. predict error 0
  4386. dir: dir isU
  4387. \622: O: O1244 (predict-no)
  4388. I see 1 and I'm going to do: predict-no
  4389. ENV: Agent did: predict-no for direction U in state State-A
  4390. In State-A moving U
  4391. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4392. predict error 0
  4393. dir: dir isR
  4394. -/|623: O: O1245 (predict-yes)
  4395. I see 1 and I'm going to do: predict-yes
  4396. ENV: Agent did: predict-yes for direction R in state State-A
  4397. In State-A moving R
  4398. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  4399. predict error 0
  4400. dir: dir isU
  4401. \-/624: O: O1248 (predict-no)
  4402. I see 1 and I'm going to do: predict-no
  4403. ENV: Agent did: predict-no for direction U in state State-B
  4404. In State-B moving U
  4405. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4406. predict error 0
  4407. dir: dir isL
  4408. |\-625: O: O1249 (predict-yes)
  4409. I see 1 and I'm going to do: predict-yes
  4410. ENV: Agent did: predict-yes for direction L in state State-B
  4411. In State-B moving L
  4412. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  4413. predict error 0
  4414. dir: dir isU
  4415. /|\626: O: O1252 (predict-no)
  4416. I see 1 and I'm going to do: predict-no
  4417. ENV: Agent did: predict-no for direction U in state State-A
  4418. In State-A moving U
  4419. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4420. predict error 0
  4421. dir: dir isU
  4422. -/|627: O: O1254 (predict-no)
  4423. I see 1 and I'm going to do: predict-no
  4424. ENV: Agent did: predict-no for direction U in state State-A
  4425. In State-A moving U
  4426. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4427. predict error 0
  4428. dir: dir isL
  4429. \-/628: O: O1256 (predict-no)
  4430. I see 1 and I'm going to do: predict-no
  4431. ENV: Agent did: predict-no for direction L in state State-A
  4432. In State-A moving L
  4433. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4434. predict error 0
  4435. dir: dir isL
  4436. |\-629: O: O1258 (predict-no)
  4437. I see 1 and I'm going to do: predict-no
  4438. ENV: Agent did: predict-no for direction L in state State-A
  4439. In State-A moving L
  4440. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4441. predict error 0
  4442. dir: dir isR
  4443. /|\630: O: O1259 (predict-yes)
  4444. I see 1 and I'm going to do: predict-yes
  4445. ENV: Agent did: predict-yes for direction R in state State-A
  4446. In State-A moving R
  4447. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  4448. predict error 0
  4449. dir: dir isR
  4450. -/|631: O: O1262 (predict-no)
  4451. I see 1 and I'm going to do: predict-no
  4452. ENV: Agent did: predict-no for direction R in state State-B
  4453. In State-B moving R
  4454. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4455. predict error 0
  4456. dir: dir isL
  4457. \632: O: O1263 (predict-yes)
  4458. I see 1 and I'm going to do: predict-yes
  4459. ENV: Agent did: predict-yes for direction L in state State-B
  4460. In State-B moving L
  4461. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  4462. predict error 0
  4463. dir: dir isL
  4464. -/|633: O: O1266 (predict-no)
  4465. I see 1 and I'm going to do: predict-no
  4466. ENV: Agent did: predict-no for direction L in state State-A
  4467. In State-A moving L
  4468. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4469. predict error 0
  4470. dir: dir isL
  4471. \-/634: O: O1268 (predict-no)
  4472. I see 1 and I'm going to do: predict-no
  4473. ENV: Agent did: predict-no for direction L in state State-A
  4474. In State-A moving L
  4475. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4476. predict error 0
  4477. dir: dir isR
  4478. |\635: O: O1269 (predict-yes)
  4479. I see 1 and I'm going to do: predict-yes
  4480. ENV: Agent did: predict-yes for direction R in state State-A
  4481. In State-A moving R
  4482. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  4483. predict error 0
  4484. dir: dir isU
  4485. -636: O: O1272 (predict-no)
  4486. I see 1 and I'm going to do: predict-no
  4487. ENV: Agent did: predict-no for direction U in state State-B
  4488. In State-B moving U
  4489. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4490. predict error 0
  4491. dir: dir isL
  4492. /|\637: O: O1273 (predict-yes)
  4493. I see 1 and I'm going to do: predict-yes
  4494. ENV: Agent did: predict-yes for direction L in state State-B
  4495. In State-B moving L
  4496. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  4497. predict error 0
  4498. dir: dir isL
  4499. -/|638: O: O1276 (predict-no)
  4500. I see 1 and I'm going to do: predict-no
  4501. ENV: Agent did: predict-no for direction L in state State-A
  4502. In State-A moving L
  4503. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4504. predict error 0
  4505. dir: dir isU
  4506. \-/639: O: O1278 (predict-no)
  4507. I see 1 and I'm going to do: predict-no
  4508. ENV: Agent did: predict-no for direction U in state State-A
  4509. In State-A moving U
  4510. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4511. predict error 0
  4512. dir: dir isU
  4513. |\-640: O: O1280 (predict-no)
  4514. I see 1 and I'm going to do: predict-no
  4515. ENV: Agent did: predict-no for direction U in state State-A
  4516. In State-A moving U
  4517. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4518. predict error 0
  4519. dir: dir isU
  4520. /|641: O: O1282 (predict-no)
  4521. I see 1 and I'm going to do: predict-no
  4522. ENV: Agent did: predict-no for direction U in state State-A
  4523. In State-A moving U
  4524. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4525. predict error 0
  4526. dir: dir isR
  4527. \642: O: O1283 (predict-yes)
  4528. I see 1 and I'm going to do: predict-yes
  4529. ENV: Agent did: predict-yes for direction R in state State-A
  4530. In State-A moving R
  4531. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  4532. predict error 0
  4533. dir: dir isR
  4534. -643: O: O1286 (predict-no)
  4535. I see 1 and I'm going to do: predict-no
  4536. ENV: Agent did: predict-no for direction R in state State-B
  4537. In State-B moving R
  4538. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4539. predict error 0
  4540. dir: dir isU
  4541. /|\644: O: O1288 (predict-no)
  4542. I see 1 and I'm going to do: predict-no
  4543. ENV: Agent did: predict-no for direction U in state State-B
  4544. In State-B moving U
  4545. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4546. predict error 0
  4547. dir: dir isL
  4548. -/645: O: O1289 (predict-yes)
  4549. I see 1 and I'm going to do: predict-yes
  4550. ENV: Agent did: predict-yes for direction L in state State-B
  4551. In State-B moving L
  4552. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  4553. predict error 0
  4554. dir: dir isU
  4555. |\-646: O: O1292 (predict-no)
  4556. I see 1 and I'm going to do: predict-no
  4557. ENV: Agent did: predict-no for direction U in state State-A
  4558. In State-A moving U
  4559. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4560. predict error 0
  4561. dir: dir isL
  4562. /|\647: O: O1294 (predict-no)
  4563. I see 1 and I'm going to do: predict-no
  4564. ENV: Agent did: predict-no for direction L in state State-A
  4565. In State-A moving L
  4566. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4567. predict error 0
  4568. dir: dir isR
  4569. -/|648: O: O1295 (predict-yes)
  4570. I see 1 and I'm going to do: predict-yes
  4571. ENV: Agent did: predict-yes for direction R in state State-A
  4572. In State-A moving R
  4573. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  4574. predict error 0
  4575. dir: dir isR
  4576. \-/649: O: O1298 (predict-no)
  4577. I see 1 and I'm going to do: predict-no
  4578. ENV: Agent did: predict-no for direction R in state State-B
  4579. In State-B moving R
  4580. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4581. predict error 0
  4582. dir: dir isR
  4583. |\-650: O: O1300 (predict-no)
  4584. I see 1 and I'm going to do: predict-no
  4585. ENV: Agent did: predict-no for direction R in state State-B
  4586. In State-B moving R
  4587. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4588. predict error 0
  4589. dir: dir isL
  4590. /|\651: O: O1301 (predict-yes)
  4591. I see 1 and I'm going to do: predict-yes
  4592. ENV: Agent did: predict-yes for direction L in state State-B
  4593. In State-B moving L
  4594. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  4595. predict error 0
  4596. dir: dir isL
  4597. -652: O: O1304 (predict-no)
  4598. I see 1 and I'm going to do: predict-no
  4599. ENV: Agent did: predict-no for direction L in state State-A
  4600. In State-A moving L
  4601. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4602. predict error 0
  4603. dir: dir isU
  4604. /|653: O: O1306 (predict-no)
  4605. I see 1 and I'm going to do: predict-no
  4606. ENV: Agent did: predict-no for direction U in state State-A
  4607. In State-A moving U
  4608. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4609. predict error 0
  4610. dir: dir isR
  4611. \-/654: O: O1308 (predict-no)
  4612. I see 1 and I'm going to do: predict-no
  4613. ENV: Agent did: predict-no for direction R in state State-A
  4614. In State-A moving R
  4615. ENV: (next state, see, prediction correct?) = (State-B, 1, False)
  4616. predict error 1
  4617. dir: dir isR
  4618. |\-655: O: O1310 (predict-no)
  4619. I see 0 and I'm going to do: predict-no
  4620. ENV: Agent did: predict-no for direction R in state State-B
  4621. In State-B moving R
  4622. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4623. predict error 0
  4624. dir: dir isL
  4625. /|\656: O: O1311 (predict-yes)
  4626. I see 1 and I'm going to do: predict-yes
  4627. ENV: Agent did: predict-yes for direction L in state State-B
  4628. In State-B moving L
  4629. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  4630. predict error 0
  4631. dir: dir isU
  4632. -/|657: O: O1314 (predict-no)
  4633. I see 1 and I'm going to do: predict-no
  4634. ENV: Agent did: predict-no for direction U in state State-A
  4635. In State-A moving U
  4636. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4637. predict error 0
  4638. dir: dir isL
  4639. \-/658: O: O1316 (predict-no)
  4640. I see 1 and I'm going to do: predict-no
  4641. ENV: Agent did: predict-no for direction L in state State-A
  4642. In State-A moving L
  4643. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4644. predict error 0
  4645. dir: dir isR
  4646. |\-659: O: O1317 (predict-yes)
  4647. I see 1 and I'm going to do: predict-yes
  4648. ENV: Agent did: predict-yes for direction R in state State-A
  4649. In State-A moving R
  4650. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  4651. predict error 0
  4652. dir: dir isU
  4653. /|\660: O: O1320 (predict-no)
  4654. I see 1 and I'm going to do: predict-no
  4655. ENV: Agent did: predict-no for direction U in state State-B
  4656. In State-B moving U
  4657. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4658. predict error 0
  4659. dir: dir isU
  4660. -/661: O: O1322 (predict-no)
  4661. I see 1 and I'm going to do: predict-no
  4662. ENV: Agent did: predict-no for direction U in state State-B
  4663. In State-B moving U
  4664. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4665. predict error 0
  4666. dir: dir isL
  4667. |662: O: O1323 (predict-yes)
  4668. I see 1 and I'm going to do: predict-yes
  4669. ENV: Agent did: predict-yes for direction L in state State-B
  4670. In State-B moving L
  4671. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  4672. predict error 0
  4673. dir: dir isU
  4674. \-/663: O: O1326 (predict-no)
  4675. I see 1 and I'm going to do: predict-no
  4676. ENV: Agent did: predict-no for direction U in state State-A
  4677. In State-A moving U
  4678. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4679. predict error 0
  4680. dir: dir isU
  4681. |\664: O: O1328 (predict-no)
  4682. I see 1 and I'm going to do: predict-no
  4683. ENV: Agent did: predict-no for direction U in state State-A
  4684. In State-A moving U
  4685. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4686. predict error 0
  4687. dir: dir isL
  4688. -/|665: O: O1330 (predict-no)
  4689. I see 1 and I'm going to do: predict-no
  4690. ENV: Agent did: predict-no for direction L in state State-A
  4691. In State-A moving L
  4692. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4693. predict error 0
  4694. dir: dir isR
  4695. \-/666: O: O1331 (predict-yes)
  4696. I see 1 and I'm going to do: predict-yes
  4697. ENV: Agent did: predict-yes for direction R in state State-A
  4698. In State-A moving R
  4699. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  4700. predict error 0
  4701. dir: dir isR
  4702. |\-667: O: O1334 (predict-no)
  4703. I see 1 and I'm going to do: predict-no
  4704. ENV: Agent did: predict-no for direction R in state State-B
  4705. In State-B moving R
  4706. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4707. predict error 0
  4708. dir: dir isU
  4709. /|\668: O: O1336 (predict-no)
  4710. I see 1 and I'm going to do: predict-no
  4711. ENV: Agent did: predict-no for direction U in state State-B
  4712. In State-B moving U
  4713. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4714. predict error 0
  4715. dir: dir isR
  4716. -669: O: O1338 (predict-no)
  4717. I see 1 and I'm going to do: predict-no
  4718. ENV: Agent did: predict-no for direction R in state State-B
  4719. In State-B moving R
  4720. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4721. predict error 0
  4722. dir: dir isU
  4723. /|\670: O: O1340 (predict-no)
  4724. I see 1 and I'm going to do: predict-no
  4725. ENV: Agent did: predict-no for direction U in state State-B
  4726. In State-B moving U
  4727. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4728. predict error 0
  4729. dir: dir isU
  4730. -/|671: O: O1341 (predict-yes)
  4731. I see 1 and I'm going to do: predict-yes
  4732. ENV: Agent did: predict-yes for direction U in state State-B
  4733. In State-B moving U
  4734. ENV: (next state, see, prediction correct?) = (State-B, 0, False)
  4735. predict error 1
  4736. dir: dir isL
  4737. \672: O: O1343 (predict-yes)
  4738. I see 0 and I'm going to do: predict-yes
  4739. ENV: Agent did: predict-yes for direction L in state State-B
  4740. In State-B moving L
  4741. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  4742. predict error 0
  4743. dir: dir isU
  4744. -673: O: O1346 (predict-no)
  4745. I see 1 and I'm going to do: predict-no
  4746. ENV: Agent did: predict-no for direction U in state State-A
  4747. In State-A moving U
  4748. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4749. predict error 0
  4750. dir: dir isL
  4751. /|\674: O: O1348 (predict-no)
  4752. I see 1 and I'm going to do: predict-no
  4753. ENV: Agent did: predict-no for direction L in state State-A
  4754. In State-A moving L
  4755. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4756. predict error 0
  4757. dir: dir isL
  4758. -/|675: O: O1350 (predict-no)
  4759. I see 1 and I'm going to do: predict-no
  4760. ENV: Agent did: predict-no for direction L in state State-A
  4761. In State-A moving L
  4762. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4763. predict error 0
  4764. dir: dir isR
  4765. \676: O: O1351 (predict-yes)
  4766. I see 1 and I'm going to do: predict-yes
  4767. ENV: Agent did: predict-yes for direction R in state State-A
  4768. In State-A moving R
  4769. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  4770. predict error 0
  4771. dir: dir isL
  4772. -/677: O: O1353 (predict-yes)
  4773. I see 1 and I'm going to do: predict-yes
  4774. ENV: Agent did: predict-yes for direction L in state State-B
  4775. In State-B moving L
  4776. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  4777. predict error 0
  4778. dir: dir isR
  4779. |\-678: O: O1355 (predict-yes)
  4780. I see 1 and I'm going to do: predict-yes
  4781. ENV: Agent did: predict-yes for direction R in state State-A
  4782. In State-A moving R
  4783. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  4784. predict error 0
  4785. dir: dir isL
  4786. /|\679: O: O1357 (predict-yes)
  4787. I see 1 and I'm going to do: predict-yes
  4788. ENV: Agent did: predict-yes for direction L in state State-B
  4789. In State-B moving L
  4790. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  4791. predict error 0
  4792. dir: dir isR
  4793. -/|680: O: O1359 (predict-yes)
  4794. I see 1 and I'm going to do: predict-yes
  4795. ENV: Agent did: predict-yes for direction R in state State-A
  4796. In State-A moving R
  4797. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  4798. predict error 0
  4799. dir: dir isU
  4800. \-/681: O: O1362 (predict-no)
  4801. I see 1 and I'm going to do: predict-no
  4802. ENV: Agent did: predict-no for direction U in state State-B
  4803. In State-B moving U
  4804. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4805. predict error 0
  4806. dir: dir isU
  4807. |682: O: O1364 (predict-no)
  4808. I see 1 and I'm going to do: predict-no
  4809. ENV: Agent did: predict-no for direction U in state State-B
  4810. In State-B moving U
  4811. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4812. predict error 0
  4813. dir: dir isL
  4814. \-/683: O: O1365 (predict-yes)
  4815. I see 1 and I'm going to do: predict-yes
  4816. ENV: Agent did: predict-yes for direction L in state State-B
  4817. In State-B moving L
  4818. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  4819. predict error 0
  4820. dir: dir isL
  4821. |\-684: O: O1368 (predict-no)
  4822. I see 1 and I'm going to do: predict-no
  4823. ENV: Agent did: predict-no for direction L in state State-A
  4824. In State-A moving L
  4825. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4826. predict error 0
  4827. dir: dir isU
  4828. /|685: O: O1370 (predict-no)
  4829. I see 1 and I'm going to do: predict-no
  4830. ENV: Agent did: predict-no for direction U in state State-A
  4831. In State-A moving U
  4832. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4833. predict error 0
  4834. dir: dir isL
  4835. \-/686: O: O1372 (predict-no)
  4836. I see 1 and I'm going to do: predict-no
  4837. ENV: Agent did: predict-no for direction L in state State-A
  4838. In State-A moving L
  4839. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4840. predict error 0
  4841. dir: dir isL
  4842. |\-687: O: O1374 (predict-no)
  4843. I see 1 and I'm going to do: predict-no
  4844. ENV: Agent did: predict-no for direction L in state State-A
  4845. In State-A moving L
  4846. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4847. predict error 0
  4848. dir: dir isL
  4849. /|\688: O: O1376 (predict-no)
  4850. I see 1 and I'm going to do: predict-no
  4851. ENV: Agent did: predict-no for direction L in state State-A
  4852. In State-A moving L
  4853. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4854. predict error 0
  4855. dir: dir isL
  4856. -/|\689: O: O1378 (predict-no)
  4857. I see 1 and I'm going to do: predict-no
  4858. ENV: Agent did: predict-no for direction L in state State-A
  4859. In State-A moving L
  4860. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4861. predict error 0
  4862. dir: dir isL
  4863. -/690: O: O1380 (predict-no)
  4864. I see 1 and I'm going to do: predict-no
  4865. ENV: Agent did: predict-no for direction L in state State-A
  4866. In State-A moving L
  4867. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4868. predict error 0
  4869. dir: dir isR
  4870. |691: O: O1381 (predict-yes)
  4871. I see 1 and I'm going to do: predict-yes
  4872. ENV: Agent did: predict-yes for direction R in state State-A
  4873. In State-A moving R
  4874. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  4875. predict error 0
  4876. dir: dir isU
  4877. \692: O: O1384 (predict-no)
  4878. I see 1 and I'm going to do: predict-no
  4879. ENV: Agent did: predict-no for direction U in state State-B
  4880. In State-B moving U
  4881. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4882. predict error 0
  4883. dir: dir isU
  4884. -/|693: O: O1386 (predict-no)
  4885. I see 1 and I'm going to do: predict-no
  4886. ENV: Agent did: predict-no for direction U in state State-B
  4887. In State-B moving U
  4888. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4889. predict error 0
  4890. dir: dir isU
  4891. \-/694: O: O1388 (predict-no)
  4892. I see 1 and I'm going to do: predict-no
  4893. ENV: Agent did: predict-no for direction U in state State-B
  4894. In State-B moving U
  4895. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4896. predict error 0
  4897. dir: dir isR
  4898. |\695: O: O1390 (predict-no)
  4899. I see 1 and I'm going to do: predict-no
  4900. ENV: Agent did: predict-no for direction R in state State-B
  4901. In State-B moving R
  4902. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4903. predict error 0
  4904. dir: dir isR
  4905. -/|696: O: O1392 (predict-no)
  4906. I see 1 and I'm going to do: predict-no
  4907. ENV: Agent did: predict-no for direction R in state State-B
  4908. In State-B moving R
  4909. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4910. predict error 0
  4911. dir: dir isR
  4912. \-/697: O: O1394 (predict-no)
  4913. I see 1 and I'm going to do: predict-no
  4914. ENV: Agent did: predict-no for direction R in state State-B
  4915. In State-B moving R
  4916. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4917. predict error 0
  4918. dir: dir isU
  4919. |\698: O: O1396 (predict-no)
  4920. I see 1 and I'm going to do: predict-no
  4921. ENV: Agent did: predict-no for direction U in state State-B
  4922. In State-B moving U
  4923. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4924. predict error 0
  4925. dir: dir isR
  4926. -/|699: O: O1398 (predict-no)
  4927. I see 1 and I'm going to do: predict-no
  4928. ENV: Agent did: predict-no for direction R in state State-B
  4929. In State-B moving R
  4930. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4931. predict error 0
  4932. dir: dir isL
  4933. \-/700: O: O1399 (predict-yes)
  4934. I see 1 and I'm going to do: predict-yes
  4935. ENV: Agent did: predict-yes for direction L in state State-B
  4936. In State-B moving L
  4937. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  4938. predict error 0
  4939. dir: dir isL
  4940. |\701: O: O1402 (predict-no)
  4941. I see 1 and I'm going to do: predict-no
  4942. ENV: Agent did: predict-no for direction L in state State-A
  4943. In State-A moving L
  4944. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4945. predict error 0
  4946. dir: dir isU
  4947. -702: O: O1404 (predict-no)
  4948. I see 1 and I'm going to do: predict-no
  4949. ENV: Agent did: predict-no for direction U in state State-A
  4950. In State-A moving U
  4951. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4952. predict error 0
  4953. dir: dir isR
  4954. /|703: O: O1405 (predict-yes)
  4955. I see 1 and I'm going to do: predict-yes
  4956. ENV: Agent did: predict-yes for direction R in state State-A
  4957. In State-A moving R
  4958. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  4959. predict error 0
  4960. dir: dir isR
  4961. \-/704: O: O1408 (predict-no)
  4962. I see 1 and I'm going to do: predict-no
  4963. ENV: Agent did: predict-no for direction R in state State-B
  4964. In State-B moving R
  4965. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4966. predict error 0
  4967. dir: dir isR
  4968. |\-705: O: O1409 (predict-yes)
  4969. I see 1 and I'm going to do: predict-yes
  4970. ENV: Agent did: predict-yes for direction R in state State-B
  4971. In State-B moving R
  4972. ENV: (next state, see, prediction correct?) = (State-B, 0, False)
  4973. predict error 1
  4974. dir: dir isR
  4975. /706: O: O1412 (predict-no)
  4976. I see 0 and I'm going to do: predict-no
  4977. ENV: Agent did: predict-no for direction R in state State-B
  4978. In State-B moving R
  4979. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4980. predict error 0
  4981. dir: dir isR
  4982. |\-707: O: O1414 (predict-no)
  4983. I see 1 and I'm going to do: predict-no
  4984. ENV: Agent did: predict-no for direction R in state State-B
  4985. In State-B moving R
  4986. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4987. predict error 0
  4988. dir: dir isL
  4989. /|708: O: O1415 (predict-yes)
  4990. I see 1 and I'm going to do: predict-yes
  4991. ENV: Agent did: predict-yes for direction L in state State-B
  4992. In State-B moving L
  4993. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  4994. predict error 0
  4995. dir: dir isR
  4996. \-/709: O: O1417 (predict-yes)
  4997. I see 1 and I'm going to do: predict-yes
  4998. ENV: Agent did: predict-yes for direction R in state State-A
  4999. In State-A moving R
  5000. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  5001. predict error 0
  5002. dir: dir isR
  5003. |710: O: O1420 (predict-no)
  5004. I see 1 and I'm going to do: predict-no
  5005. ENV: Agent did: predict-no for direction R in state State-B
  5006. In State-B moving R
  5007. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5008. predict error 0
  5009. dir: dir isL
  5010. \-/711: O: O1421 (predict-yes)
  5011. I see 1 and I'm going to do: predict-yes
  5012. ENV: Agent did: predict-yes for direction L in state State-B
  5013. In State-B moving L
  5014. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  5015. predict error 0
  5016. dir: dir isU
  5017. |712: O: O1424 (predict-no)
  5018. I see 1 and I'm going to do: predict-no
  5019. ENV: Agent did: predict-no for direction U in state State-A
  5020. In State-A moving U
  5021. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  5022. predict error 0
  5023. dir: dir isR
  5024. \-/713: O: O1425 (predict-yes)
  5025. I see 1 and I'm going to do: predict-yes
  5026. ENV: Agent did: predict-yes for direction R in state State-A
  5027. In State-A moving R
  5028. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  5029. predict error 0
  5030. dir: dir isR
  5031. |\714: O: O1428 (predict-no)
  5032. I see 1 and I'm going to do: predict-no
  5033. ENV: Agent did: predict-no for direction R in state State-B
  5034. In State-B moving R
  5035. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5036. predict error 0
  5037. dir: dir isU
  5038. -/|715: O: O1430 (predict-no)
  5039. I see 1 and I'm going to do: predict-no
  5040. ENV: Agent did: predict-no for direction U in state State-B
  5041. In State-B moving U
  5042. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5043. predict error 0
  5044. dir: dir isU
  5045. \-/716: O: O1432 (predict-no)
  5046. I see 1 and I'm going to do: predict-no
  5047. ENV: Agent did: predict-no for direction U in state State-B
  5048. In State-B moving U
  5049. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5050. predict error 0
  5051. dir: dir isU
  5052. |\-717: O: O1434 (predict-no)
  5053. I see 1 and I'm going to do: predict-no
  5054. ENV: Agent did: predict-no for direction U in state State-B
  5055. In State-B moving U
  5056. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5057. predict error 0
  5058. dir: dir isU
  5059. /|718: O: O1436 (predict-no)
  5060. I see 1 and I'm going to do: predict-no
  5061. ENV: Agent did: predict-no for direction U in state State-B
  5062. In State-B moving U
  5063. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5064. predict error 0
  5065. dir: dir isL
  5066. \-719: O: O1437 (predict-yes)
  5067. I see 1 and I'm going to do: predict-yes
  5068. ENV: Agent did: predict-yes for direction L in state State-B
  5069. In State-B moving L
  5070. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  5071. predict error 0
  5072. dir: dir isU
  5073. /|\720: O: O1440 (predict-no)
  5074. I see 1 and I'm going to do: predict-no
  5075. ENV: Agent did: predict-no for direction U in state State-A
  5076. In State-A moving U
  5077. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  5078. predict error 0
  5079. dir: dir isL
  5080. -/|721: O: O1442 (predict-no)
  5081. I see 1 and I'm going to do: predict-no
  5082. ENV: Agent did: predict-no for direction L in state State-A
  5083. In State-A moving L
  5084. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  5085. predict error 0
  5086. dir: dir isU
  5087. \722: O: O1444 (predict-no)
  5088. I see 1 and I'm going to do: predict-no
  5089. ENV: Agent did: predict-no for direction U in state State-A
  5090. In State-A moving U
  5091. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  5092. predict error 0
  5093. dir: dir isU
  5094. -/|723: O: O1446 (predict-no)
  5095. I see 1 and I'm going to do: predict-no
  5096. ENV: Agent did: predict-no for direction U in state State-A
  5097. In State-A moving U
  5098. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  5099. predict error 0
  5100. dir: dir isU
  5101. \-/724: O: O1448 (predict-no)
  5102. I see 1 and I'm going to do: predict-no
  5103. ENV: Agent did: predict-no for direction U in state State-A
  5104. In State-A moving U
  5105. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  5106. predict error 0
  5107. dir: dir isL
  5108. |\-725: O: O1450 (predict-no)
  5109. I see 1 and I'm going to do: predict-no
  5110. ENV: Agent did: predict-no for direction L in state State-A
  5111. In State-A moving L
  5112. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  5113. predict error 0
  5114. dir: dir isL
  5115. /|726: O: O1452 (predict-no)
  5116. I see 1 and I'm going to do: predict-no
  5117. ENV: Agent did: predict-no for direction L in state State-A
  5118. In State-A moving L
  5119. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  5120. predict error 0
  5121. dir: dir isU
  5122. \-/727: O: O1454 (predict-no)
  5123. I see 1 and I'm going to do: predict-no
  5124. ENV: Agent did: predict-no for direction U in state State-A
  5125. In State-A moving U
  5126. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  5127. predict error 0
  5128. dir: dir isR
  5129. |\-728: O: O1455 (predict-yes)
  5130. I see 1 and I'm going to do: predict-yes
  5131. ENV: Agent did: predict-yes for direction R in state State-A
  5132. In State-A moving R
  5133. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  5134. predict error 0
  5135. dir: dir isR
  5136. /|\729: O: O1458 (predict-no)
  5137. I see 1 and I'm going to do: predict-no
  5138. ENV: Agent did: predict-no for direction R in state State-B
  5139. In State-B moving R
  5140. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5141. predict error 0
  5142. dir: dir isU
  5143. -730: O: O1460 (predict-no)
  5144. I see 1 and I'm going to do: predict-no
  5145. ENV: Agent did: predict-no for direction U in state State-B
  5146. In State-B moving U
  5147. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5148. predict error 0
  5149. dir: dir isL
  5150. /731: O: O1461 (predict-yes)
  5151. I see 1 and I'm going to do: predict-yes
  5152. ENV: Agent did: predict-yes for direction L in state State-B
  5153. In State-B moving L
  5154. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  5155. predict error 0
  5156. dir: dir isR
  5157. |732: O: O1463 (predict-yes)
  5158. I see 1 and I'm going to do: predict-yes
  5159. ENV: Agent did: predict-yes for direction R in state State-A
  5160. In State-A moving R
  5161. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  5162. predict error 0
  5163. dir: dir isR
  5164. \-/733: O: O1466 (predict-no)
  5165. I see 1 and I'm going to do: predict-no
  5166. ENV: Agent did: predict-no for direction R in state State-B
  5167. In State-B moving R
  5168. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5169. predict error 0
  5170. dir: dir isL
  5171. |\734: O: O1467 (predict-yes)
  5172. I see 1 and I'm going to do: predict-yes
  5173. ENV: Agent did: predict-yes for direction L in state State-B
  5174. In State-B moving L
  5175. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  5176. predict error 0
  5177. dir: dir isR
  5178. -/735: O: O1469 (predict-yes)
  5179. I see 1 and I'm going to do: predict-yes
  5180. ENV: Agent did: predict-yes for direction R in state State-A
  5181. In State-A moving R
  5182. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  5183. predict error 0
  5184. dir: dir isU
  5185. |\736: O: O1472 (predict-no)
  5186. I see 1 and I'm going to do: predict-no
  5187. ENV: Agent did: predict-no for direction U in state State-B
  5188. In State-B moving U
  5189. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5190. predict error 0
  5191. dir: dir isU
  5192. -/|737: O: O1474 (predict-no)
  5193. I see 1 and I'm going to do: predict-no
  5194. ENV: Agent did: predict-no for direction U in state State-B
  5195. In State-B moving U
  5196. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5197. predict error 0
  5198. dir: dir isL
  5199. \-/738: O: O1475 (predict-yes)
  5200. I see 1 and I'm going to do: predict-yes
  5201. ENV: Agent did: predict-yes for direction L in state State-B
  5202. In State-B moving L
  5203. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  5204. predict error 0
  5205. dir: dir isR
  5206. |\-739: O: O1477 (predict-yes)
  5207. I see 1 and I'm going to do: predict-yes
  5208. ENV: Agent did: predict-yes for direction R in state State-A
  5209. In State-A moving R
  5210. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  5211. predict error 0
  5212. dir: dir isL
  5213. /|740: O: O1479 (predict-yes)
  5214. I see 1 and I'm going to do: predict-yes
  5215. ENV: Agent did: predict-yes for direction L in state State-B
  5216. In State-B moving L
  5217. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  5218. predict error 0
  5219. dir: dir isU
  5220. \-/741: O: O1482 (predict-no)
  5221. I see 1 and I'm going to do: predict-no
  5222. ENV: Agent did: predict-no for direction U in state State-A
  5223. In State-A moving U
  5224. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  5225. predict error 0
  5226. dir: dir isL
  5227. |742: O: O1484 (predict-no)
  5228. I see 1 and I'm going to do: predict-no
  5229. ENV: Agent did: predict-no for direction L in state State-A
  5230. In State-A moving L
  5231. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  5232. predict error 0
  5233. dir: dir isL
  5234. \-/743: O: O1486 (predict-no)
  5235. I see 1 and I'm going to do: predict-no
  5236. ENV: Agent did: predict-no for direction L in state State-A
  5237. In State-A moving L
  5238. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  5239. predict error 0
  5240. dir: dir isR
  5241. |\-744: O: O1487 (predict-yes)
  5242. I see 1 and I'm going to do: predict-yes
  5243. ENV: Agent did: predict-yes for direction R in state State-A
  5244. In State-A moving R
  5245. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  5246. predict error 0
  5247. dir: dir isU
  5248. /|\745: O: O1490 (predict-no)
  5249. I see 1 and I'm going to do: predict-no
  5250. ENV: Agent did: predict-no for direction U in state State-B
  5251. In State-B moving U
  5252. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5253. predict error 0
  5254. dir: dir isL
  5255. -/|746: O: O1491 (predict-yes)
  5256. I see 1 and I'm going to do: predict-yes
  5257. ENV: Agent did: predict-yes for direction L in state State-B
  5258. In State-B moving L
  5259. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  5260. predict error 0
  5261. dir: dir isL
  5262. \-/747: O: O1494 (predict-no)
  5263. I see 1 and I'm going to do: predict-no
  5264. ENV: Agent did: predict-no for direction L in state State-A
  5265. In State-A moving L
  5266. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  5267. predict error 0
  5268. dir: dir isU
  5269. |\748: O: O1496 (predict-no)
  5270. I see 1 and I'm going to do: predict-no
  5271. ENV: Agent did: predict-no for direction U in state State-A
  5272. In State-A moving U
  5273. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  5274. predict error 0
  5275. dir: dir isU
  5276. -/|749: O: O1498 (predict-no)
  5277. I see 1 and I'm going to do: predict-no
  5278. ENV: Agent did: predict-no for direction U in state State-A
  5279. In State-A moving U
  5280. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  5281. predict error 0
  5282. dir: dir isU
  5283. \-/750: O: O1500 (predict-no)
  5284. I see 1 and I'm going to do: predict-no
  5285. ENV: Agent did: predict-no for direction U in state State-A
  5286. In State-A moving U
  5287. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  5288. predict error 0
  5289. dir: dir isL
  5290. |\751: O: O1502 (predict-no)
  5291. I see 1 and I'm going to do: predict-no
  5292. ENV: Agent did: predict-no for direction L in state State-A
  5293. In State-A moving L
  5294. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  5295. predict error 0
  5296. dir: dir isR
  5297. -752: O: O1503 (predict-yes)
  5298. I see 1 and I'm going to do: predict-yes
  5299. ENV: Agent did: predict-yes for direction R in state State-A
  5300. In State-A moving R
  5301. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  5302. predict error 0
  5303. dir: dir isL
  5304. /|\753: O: O1505 (predict-yes)
  5305. I see 1 and I'm going to do: predict-yes
  5306. ENV: Agent did: predict-yes for direction L in state State-B
  5307. In State-B moving L
  5308. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  5309. predict error 0
  5310. dir: dir isR
  5311. -/|754: O: O1507 (predict-yes)
  5312. I see 1 and I'm going to do: predict-yes
  5313. ENV: Agent did: predict-yes for direction R in state State-A
  5314. In State-A moving R
  5315. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  5316. predict error 0
  5317. dir: dir isL
  5318. \-/755: O: O1509 (predict-yes)
  5319. I see 1 and I'm going to do: predict-yes
  5320. ENV: Agent did: predict-yes for direction L in state State-B
  5321. In State-B moving L
  5322. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  5323. predict error 0
  5324. dir: dir isR
  5325. |756: O: O1511 (predict-yes)
  5326. I see 1 and I'm going to do: predict-yes
  5327. ENV: Agent did: predict-yes for direction R in state State-A
  5328. In State-A moving R
  5329. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  5330. predict error 0
  5331. dir: dir isU
  5332. \-/757: O: O1514 (predict-no)
  5333. I see 1 and I'm going to do: predict-no
  5334. ENV: Agent did: predict-no for direction U in state State-B
  5335. In State-B moving U
  5336. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5337. predict error 0
  5338. dir: dir isU
  5339. |758: O: O1516 (predict-no)
  5340. I see 1 and I'm going to do: predict-no
  5341. ENV: Agent did: predict-no for direction U in state State-B
  5342. In State-B moving U
  5343. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5344. predict error 0
  5345. dir: dir isR
  5346. \-759: O: O1518 (predict-no)
  5347. I see 1 and I'm going to do: predict-no
  5348. ENV: Agent did: predict-no for direction R in state State-B
  5349. In State-B moving R
  5350. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5351. predict error 0
  5352. dir: dir isL
  5353. /|\760: O: O1519 (predict-yes)
  5354. I see 1 and I'm going to do: predict-yes
  5355. ENV: Agent did: predict-yes for direction L in state State-B
  5356. In State-B moving L
  5357. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  5358. predict error 0
  5359. dir: dir isR
  5360. -/761: O: O1521 (predict-yes)
  5361. I see 1 and I'm going to do: predict-yes
  5362. ENV: Agent did: predict-yes for direction R in state State-A
  5363. In State-A moving R
  5364. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  5365. predict error 0
  5366. dir: dir isR
  5367. |762: O: O1524 (predict-no)
  5368. I see 1 and I'm going to do: predict-no
  5369. ENV: Agent did: predict-no for direction R in state State-B
  5370. In State-B moving R
  5371. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5372. predict error 0
  5373. dir: dir isU
  5374. \-/763: O: O1526 (predict-no)
  5375. I see 1 and I'm going to do: predict-no
  5376. ENV: Agent did: predict-no for direction U in state State-B
  5377. In State-B moving U
  5378. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5379. predict error 0
  5380. dir: dir isU
  5381. |\-764: O: O1528 (predict-no)
  5382. I see 1 and I'm going to do: predict-no
  5383. ENV: Agent did: predict-no for direction U in state State-B
  5384. In State-B moving U
  5385. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5386. predict error 0
  5387. dir: dir isU
  5388. /|765: O: O1530 (predict-no)
  5389. I see 1 and I'm going to do: predict-no
  5390. ENV: Agent did: predict-no for direction U in state State-B
  5391. In State-B moving U
  5392. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5393. predict error 0
  5394. dir: dir isU
  5395. \-/766: O: O1532 (predict-no)
  5396. I see 1 and I'm going to do: predict-no
  5397. ENV: Agent did: predict-no for direction U in state State-B
  5398. In State-B moving U
  5399. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5400. predict error 0
  5401. dir: dir isR
  5402. |\767: O: O1534 (predict-no)
  5403. I see 1 and I'm going to do: predict-no
  5404. ENV: Agent did: predict-no for direction R in state State-B
  5405. In State-B moving R
  5406. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5407. predict error 0
  5408. dir: dir isU
  5409. -768: O: O1536 (predict-no)
  5410. I see 1 and I'm going to do: predict-no
  5411. ENV: Agent did: predict-no for direction U in state State-B
  5412. In State-B moving U
  5413. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5414. predict error 0
  5415. dir: dir isU
  5416. /|\769: O: O1538 (predict-no)
  5417. I see 1 and I'm going to do: predict-no
  5418. ENV: Agent did: predict-no for direction U in state State-B
  5419. In State-B moving U
  5420. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5421. predict error 0
  5422. dir: dir isL
  5423. -/|770: O: O1539 (predict-yes)
  5424. I see 1 and I'm going to do: predict-yes
  5425. ENV: Agent did: predict-yes for direction L in state State-B
  5426. In State-B moving L
  5427. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  5428. predict error 0
  5429. dir: dir isL
  5430. \-/771: O: O1542 (predict-no)
  5431. I see 1 and I'm going to do: predict-no
  5432. ENV: Agent did: predict-no for direction L in state State-A
  5433. In State-A moving L
  5434. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  5435. predict error 0
  5436. dir: dir isR
  5437. |772: O: O1543 (predict-yes)
  5438. I see 1 and I'm going to do: predict-yes
  5439. ENV: Agent did: predict-yes for direction R in state State-A
  5440. In State-A moving R
  5441. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  5442. predict error 0
  5443. dir: dir isR
  5444. \-773: O: O1546 (predict-no)
  5445. I see 1 and I'm going to do: predict-no
  5446. ENV: Agent did: predict-no for direction R in state State-B
  5447. In State-B moving R
  5448. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5449. predict error 0
  5450. dir: dir isL
  5451. /|\774: O: O1547 (predict-yes)
  5452. I see 1 and I'm going to do: predict-yes
  5453. ENV: Agent did: predict-yes for direction L in state State-B
  5454. In State-B moving L
  5455. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  5456. predict error 0
  5457. dir: dir isR
  5458. -/775: O: O1549 (predict-yes)
  5459. I see 1 and I'm going to do: predict-yes
  5460. ENV: Agent did: predict-yes for direction R in state State-A
  5461. In State-A moving R
  5462. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  5463. predict error 0
  5464. dir: dir isR
  5465. |776: O: O1552 (predict-no)
  5466. I see 1 and I'm going to do: predict-no
  5467. ENV: Agent did: predict-no for direction R in state State-B
  5468. In State-B moving R
  5469. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5470. predict error 0
  5471. dir: dir isL
  5472. \-/777: O: O1553 (predict-yes)
  5473. I see 1 and I'm going to do: predict-yes
  5474. ENV: Agent did: predict-yes for direction L in state State-B
  5475. In State-B moving L
  5476. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  5477. predict error 0
  5478. dir: dir isU
  5479. |\778: O: O1556 (predict-no)
  5480. I see 1 and I'm going to do: predict-no
  5481. ENV: Agent did: predict-no for direction U in state State-A
  5482. In State-A moving U
  5483. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  5484. predict error 0
  5485. dir: dir isR
  5486. -/|779: O: O1557 (predict-yes)
  5487. I see 1 and I'm going to do: predict-yes
  5488. ENV: Agent did: predict-yes for direction R in state State-A
  5489. In State-A moving R
  5490. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  5491. predict error 0
  5492. dir: dir isL
  5493. \-/780: O: O1559 (predict-yes)
  5494. I see 1 and I'm going to do: predict-yes
  5495. ENV: Agent did: predict-yes for direction L in state State-B
  5496. In State-B moving L
  5497. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  5498. predict error 0
  5499. dir: dir isL
  5500. |\-781: O: O1562 (predict-no)
  5501. I see 1 and I'm going to do: predict-no
  5502. ENV: Agent did: predict-no for direction L in state State-A
  5503. In State-A moving L
  5504. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  5505. predict error 0
  5506. dir: dir isR
  5507. /782: O: O1563 (predict-yes)
  5508. I see 1 and I'm going to do: predict-yes
  5509. ENV: Agent did: predict-yes for direction R in state State-A
  5510. In State-A moving R
  5511. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  5512. predict error 0
  5513. dir: dir isL
  5514. |783: O: O1565 (predict-yes)
  5515. I see 1 and I'm going to do: predict-yes
  5516. ENV: Agent did: predict-yes for direction L in state State-B
  5517. In State-B moving L
  5518. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  5519. predict error 0
  5520. dir: dir isU
  5521. \-/784: O: O1568 (predict-no)
  5522. I see 1 and I'm going to do: predict-no
  5523. ENV: Agent did: predict-no for direction U in state State-A
  5524. In State-A moving U
  5525. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  5526. predict error 0
  5527. dir: dir isR
  5528. |\-785: O: O1569 (predict-yes)
  5529. I see 1 and I'm going to do: predict-yes
  5530. ENV: Agent did: predict-yes for direction R in state State-A
  5531. In State-A moving R
  5532. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  5533. predict error 0
  5534. dir: dir isR
  5535. /786: O: O1572 (predict-no)
  5536. I see 1 and I'm going to do: predict-no
  5537. ENV: Agent did: predict-no for direction R in state State-B
  5538. In State-B moving R
  5539. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5540. predict error 0
  5541. dir: dir isL
  5542. |\-787: O: O1573 (predict-yes)
  5543. I see 1 and I'm going to do: predict-yes
  5544. ENV: Agent did: predict-yes for direction L in state State-B
  5545. In State-B moving L
  5546. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  5547. predict error 0
  5548. dir: dir isU
  5549. /|788: O: O1576 (predict-no)
  5550. I see 1 and I'm going to do: predict-no
  5551. ENV: Agent did: predict-no for direction U in state State-A
  5552. In State-A moving U
  5553. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  5554. predict error 0
  5555. dir: dir isL
  5556. \-789: O: O1578 (predict-no)
  5557. I see 1 and I'm going to do: predict-no
  5558. ENV: Agent did: predict-no for direction L in state State-A
  5559. In State-A moving L
  5560. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  5561. predict error 0
  5562. dir: dir isL
  5563. /|\790: O: O1580 (predict-no)
  5564. I see 1 and I'm going to do: predict-no
  5565. ENV: Agent did: predict-no for direction L in state State-A
  5566. In State-A moving L
  5567. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  5568. predict error 0
  5569. dir: dir isL
  5570. -/|791: O: O1582 (predict-no)
  5571. I see 1 and I'm going to do: predict-no
  5572. ENV: Agent did: predict-no for direction L in state State-A
  5573. In State-A moving L
  5574. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  5575. predict error 0
  5576. dir: dir isU
  5577. \792: O: O1584 (predict-no)
  5578. I see 1 and I'm going to do: predict-no
  5579. ENV: Agent did: predict-no for direction U in state State-A
  5580. In State-A moving U
  5581. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  5582. predict error 0
  5583. dir: dir isR
  5584. -/|793: O: O1585 (predict-yes)
  5585. I see 1 and I'm going to do: predict-yes
  5586. ENV: Agent did: predict-yes for direction R in state State-A
  5587. In State-A moving R
  5588. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  5589. predict error 0
  5590. dir: dir isU
  5591. \-794: O: O1588 (predict-no)
  5592. I see 1 and I'm going to do: predict-no
  5593. ENV: Agent did: predict-no for direction U in state State-B
  5594. In State-B moving U
  5595. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5596. predict error 0
  5597. dir: dir isU
  5598. /|\795: O: O1590 (predict-no)
  5599. I see 1 and I'm going to do: predict-no
  5600. ENV: Agent did: predict-no for direction U in state State-B
  5601. In State-B moving U
  5602. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5603. predict error 0
  5604. dir: dir isU
  5605. -796: O: O1592 (predict-no)
  5606. I see 1 and I'm going to do: predict-no
  5607. ENV: Agent did: predict-no for direction U in state State-B
  5608. In State-B moving U
  5609. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5610. predict error 0
  5611. dir: dir isU
  5612. /|\797: O: O1594 (predict-no)
  5613. I see 1 and I'm going to do: predict-no
  5614. ENV: Agent did: predict-no for direction U in state State-B
  5615. In State-B moving U
  5616. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5617. predict error 0
  5618. dir: dir isU
  5619. -/|798: O: O1596 (predict-no)
  5620. I see 1 and I'm going to do: predict-no
  5621. ENV: Agent did: predict-no for direction U in state State-B
  5622. In State-B moving U
  5623. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5624. predict error 0
  5625. dir: dir isU
  5626. \-/799: O: O1598 (predict-no)
  5627. I see 1 and I'm going to do: predict-no
  5628. ENV: Agent did: predict-no for direction U in state State-B
  5629. In State-B moving U
  5630. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5631. predict error 0
  5632. dir: dir isU
  5633. |\800: O: O1600 (predict-no)
  5634. I see 1 and I'm going to do: predict-no
  5635. ENV: Agent did: predict-no for direction U in state State-B
  5636. In State-B moving U
  5637. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5638. predict error 0
  5639. dir: dir isL
  5640. -/|801: O: O1601 (predict-yes)
  5641. I see 1 and I'm going to do: predict-yes
  5642. ENV: Agent did: predict-yes for direction L in state State-B
  5643. In State-B moving L
  5644. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  5645. predict error 0
  5646. dir: dir isR
  5647. \802: O: O1603 (predict-yes)
  5648. I see 1 and I'm going to do: predict-yes
  5649. ENV: Agent did: predict-yes for direction R in state State-A
  5650. In State-A moving R
  5651. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  5652. predict error 0
  5653. dir: dir isR
  5654. -/|803: O: O1606 (predict-no)
  5655. I see 1 and I'm going to do: predict-no
  5656. ENV: Agent did: predict-no for direction R in state State-B
  5657. In State-B moving R
  5658. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5659. predict error 0
  5660. dir: dir isU
  5661. \-/804: O: O1608 (predict-no)
  5662. I see 1 and I'm going to do: predict-no
  5663. ENV: Agent did: predict-no for direction U in state State-B
  5664. In State-B moving U
  5665. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5666. predict error 0
  5667. dir: dir isU
  5668. |\-805: O: O1610 (predict-no)
  5669. I see 1 and I'm going to do: predict-no
  5670. ENV: Agent did: predict-no for direction U in state State-B
  5671. In State-B moving U
  5672. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5673. predict error 0
  5674. dir: dir isU
  5675. /|\806: O: O1612 (predict-no)
  5676. I see 1 and I'm going to do: predict-no
  5677. ENV: Agent did: predict-no for direction U in state State-B
  5678. In State-B moving U
  5679. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5680. predict error 0
  5681. dir: dir isU
  5682. -/|807: O: O1614 (predict-no)
  5683. I see 1 and I'm going to do: predict-no
  5684. ENV: Agent did: predict-no for direction U in state State-B
  5685. In State-B moving U
  5686. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5687. predict error 0
  5688. dir: dir isR
  5689. \-808: O: O1616 (predict-no)
  5690. I see 1 and I'm going to do: predict-no
  5691. ENV: Agent did: predict-no for direction R in state State-B
  5692. In State-B moving R
  5693. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5694. predict error 0
  5695. dir: dir isU
  5696. /|\809: O: O1618 (predict-no)
  5697. I see 1 and I'm going to do: predict-no
  5698. ENV: Agent did: predict-no for direction U in state State-B
  5699. In State-B moving U
  5700. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5701. predict error 0
  5702. dir: dir isR
  5703. -/810: O: O1620 (predict-no)
  5704. I see 1 and I'm going to do: predict-no
  5705. ENV: Agent did: predict-no for direction R in state State-B
  5706. In State-B moving R
  5707. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5708. predict error 0
  5709. dir: dir isR
  5710. |\-/sleeping...
  5711. |811: O: O1622 (predict-no)
  5712. I see 1 and I'm going to do: predict-no
  5713. ENV: Agent did: predict-no for direction R in state State-B
  5714. In State-B moving R
  5715. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5716. predict error 0
  5717. dir: dir isR
  5718. \812: O: O1624 (predict-no)
  5719. I see 1 and I'm going to do: predict-no
  5720. ENV: Agent did: predict-no for direction R in state State-B
  5721. In State-B moving R
  5722. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5723. predict error 0
  5724. dir: dir isU
  5725. -/|813: O: O1626 (predict-no)
  5726. I see 1 and I'm going to do: predict-no
  5727. ENV: Agent did: predict-no for direction U in state State-B
  5728. In State-B moving U
  5729. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5730. predict error 0
  5731. dir: dir isR
  5732. \-/814: O: O1628 (predict-no)
  5733. I see 1 and I'm going to do: predict-no
  5734. ENV: Agent did: predict-no for direction R in state State-B
  5735. In State-B moving R
  5736. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5737. predict error 0
  5738. dir: dir isL
  5739. |\-815: O: O1629 (predict-yes)
  5740. I see 1 and I'm going to do: predict-yes
  5741. ENV: Agent did: predict-yes for direction L in state State-B
  5742. In State-B moving L
  5743. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  5744. predict error 0
  5745. dir: dir isL
  5746. /|816: O: O1632 (predict-no)
  5747. I see 1 and I'm going to do: predict-no
  5748. ENV: Agent did: predict-no for direction L in state State-A
  5749. In State-A moving L
  5750. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  5751. predict error 0
  5752. dir: dir isU
  5753. \-/817: O: O1634 (predict-no)
  5754. I see 1 and I'm going to do: predict-no
  5755. ENV: Agent did: predict-no for direction U in state State-A
  5756. In State-A moving U
  5757. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  5758. predict error 0
  5759. dir: dir isR
  5760. |\-818: O: O1636 (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-A
  5763. In State-A moving R
  5764. ENV: (next state, see, prediction correct?) = (State-B, 1, False)
  5765. predict error 1
  5766. dir: dir isU
  5767. /|\819: O: O1638 (predict-no)
  5768. I see 0 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. -/|\820: O: O1639 (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. -/|821: O: O1641 (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. \822: O: O1644 (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 isL
  5795. -/|823: O: O1645 (predict-yes)
  5796. I see 1 and I'm going to do: predict-yes
  5797. ENV: Agent did: predict-yes for direction L in state State-B
  5798. In State-B moving L
  5799. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  5800. predict error 0
  5801. dir: dir isL
  5802. \-/824: O: O1648 (predict-no)
  5803. I see 1 and I'm going to do: predict-no
  5804. ENV: Agent did: predict-no for direction L in state State-A
  5805. In State-A moving L
  5806. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  5807. predict error 0
  5808. dir: dir isR
  5809. |\825: O: O1649 (predict-yes)
  5810. I see 1 and I'm going to do: predict-yes
  5811. ENV: Agent did: predict-yes for direction R in state State-A
  5812. In State-A moving R
  5813. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  5814. predict error 0
  5815. dir: dir isL
  5816. -/|826: O: O1651 (predict-yes)
  5817. I see 1 and I'm going to do: predict-yes
  5818. ENV: Agent did: predict-yes for direction L in state State-B
  5819. In State-B moving L
  5820. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  5821. predict error 0
  5822. dir: dir isL
  5823. \-/827: O: O1654 (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. |\-828: O: O1656 (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. /|\829: O: O1657 (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. -/|830: O: O1660 (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. \-/831: O: O1661 (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. |832: O: O1664 (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 isU
  5865. \-/833: O: O1666 (predict-no)
  5866. I see 1 and I'm going to do: predict-no
  5867. ENV: Agent did: predict-no for direction U in state State-A
  5868. In State-A moving U
  5869. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  5870. predict error 0
  5871. dir: dir isR
  5872. |\-834: O: O1667 (predict-yes)
  5873. I see 1 and I'm going to do: predict-yes
  5874. ENV: Agent did: predict-yes for direction R in state State-A
  5875. In State-A moving R
  5876. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  5877. predict error 0
  5878. dir: dir isL
  5879. /|835: O: O1669 (predict-yes)
  5880. I see 1 and I'm going to do: predict-yes
  5881. ENV: Agent did: predict-yes for direction L in state State-B
  5882. In State-B moving L
  5883. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  5884. predict error 0
  5885. dir: dir isU
  5886. \-/836: O: O1672 (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-A
  5889. In State-A moving U
  5890. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  5891. predict error 0
  5892. dir: dir isL
  5893. |\-837: O: O1674 (predict-no)
  5894. I see 1 and I'm going to do: predict-no
  5895. ENV: Agent did: predict-no for direction L in state State-A
  5896. In State-A moving L
  5897. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  5898. predict error 0
  5899. dir: dir isR
  5900. /|\838: O: O1675 (predict-yes)
  5901. I see 1 and I'm going to do: predict-yes
  5902. ENV: Agent did: predict-yes for direction R in state State-A
  5903. In State-A moving R
  5904. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  5905. predict error 0
  5906. dir: dir isU
  5907. -/|839: O: O1678 (predict-no)
  5908. I see 1 and I'm going to do: predict-no
  5909. ENV: Agent did: predict-no for direction U in state State-B
  5910. In State-B moving U
  5911. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5912. predict error 0
  5913. dir: dir isU
  5914. \-/840: O: O1680 (predict-no)
  5915. I see 1 and I'm going to do: predict-no
  5916. ENV: Agent did: predict-no for direction U in state State-B
  5917. In State-B moving U
  5918. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5919. predict error 0
  5920. dir: dir isL
  5921. |\-/841: O: O1681 (predict-yes)
  5922. I see 1 and I'm going to do: predict-yes
  5923. ENV: Agent did: predict-yes for direction L in state State-B
  5924. In State-B moving L
  5925. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  5926. predict error 0
  5927. dir: dir isU
  5928. |842: O: O1684 (predict-no)
  5929. I see 1 and I'm going to do: predict-no
  5930. ENV: Agent did: predict-no for direction U in state State-A
  5931. In State-A moving U
  5932. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  5933. predict error 0
  5934. dir: dir isR
  5935. \-/843: O: O1685 (predict-yes)
  5936. I see 1 and I'm going to do: predict-yes
  5937. ENV: Agent did: predict-yes for direction R in state State-A
  5938. In State-A moving R
  5939. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  5940. predict error 0
  5941. dir: dir isU
  5942. |\-844: O: O1688 (predict-no)
  5943. I see 1 and I'm going to do: predict-no
  5944. ENV: Agent did: predict-no for direction U in state State-B
  5945. In State-B moving U
  5946. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5947. predict error 0
  5948. dir: dir isU
  5949. /|\845: O: O1690 (predict-no)
  5950. I see 1 and I'm going to do: predict-no
  5951. ENV: Agent did: predict-no for direction U in state State-B
  5952. In State-B moving U
  5953. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5954. predict error 0
  5955. dir: dir isR
  5956. -/|846: O: O1692 (predict-no)
  5957. I see 1 and I'm going to do: predict-no
  5958. ENV: Agent did: predict-no for direction R in state State-B
  5959. In State-B moving R
  5960. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5961. predict error 0
  5962. dir: dir isU
  5963. \-/847: O: O1694 (predict-no)
  5964. I see 1 and I'm going to do: predict-no
  5965. ENV: Agent did: predict-no for direction U in state State-B
  5966. In State-B moving U
  5967. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5968. predict error 0
  5969. dir: dir isR
  5970. |\-848: O: O1696 (predict-no)
  5971. I see 1 and I'm going to do: predict-no
  5972. ENV: Agent did: predict-no for direction R in state State-B
  5973. In State-B moving R
  5974. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5975. predict error 0
  5976. dir: dir isU
  5977. /|849: O: O1698 (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-B
  5980. In State-B moving U
  5981. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5982. predict error 0
  5983. dir: dir isU
  5984. \-/850: O: O1700 (predict-no)
  5985. I see 1 and I'm going to do: predict-no
  5986. ENV: Agent did: predict-no for direction U in state State-B
  5987. In State-B moving U
  5988. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5989. predict error 0
  5990. dir: dir isU
  5991. |\851: O: O1702 (predict-no)
  5992. I see 1 and I'm going to do: predict-no
  5993. ENV: Agent did: predict-no for direction U in state State-B
  5994. In State-B moving U
  5995. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5996. predict error 0
  5997. dir: dir isU
  5998. -852: O: O1704 (predict-no)
  5999. I see 1 and I'm going to do: predict-no
  6000. ENV: Agent did: predict-no for direction U in state State-B
  6001. In State-B moving U
  6002. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  6003. predict error 0
  6004. dir: dir isU
  6005. /|\853: O: O1706 (predict-no)
  6006. I see 1 and I'm going to do: predict-no
  6007. ENV: Agent did: predict-no for direction U in state State-B
  6008. In State-B moving U
  6009. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  6010. predict error 0
  6011. dir: dir isL
  6012. -/|854: O: O1707 (predict-yes)
  6013. I see 1 and I'm going to do: predict-yes
  6014. ENV: Agent did: predict-yes for direction L in state State-B
  6015. In State-B moving L
  6016. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  6017. predict error 0
  6018. dir: dir isL
  6019. \-/855: O: O1710 (predict-no)
  6020. I see 1 and I'm going to do: predict-no
  6021. ENV: Agent did: predict-no for direction L in state State-A
  6022. In State-A moving L
  6023. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  6024. predict error 0
  6025. dir: dir isU
  6026. |\-856: O: O1712 (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-A
  6029. In State-A moving U
  6030. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  6031. predict error 0
  6032. dir: dir isU
  6033. /|857: O: O1714 (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-A
  6036. In State-A moving U
  6037. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  6038. predict error 0
  6039. dir: dir isR
  6040. \-/858: O: O1715 (predict-yes)
  6041. I see 1 and I'm going to do: predict-yes
  6042. ENV: Agent did: predict-yes for direction R in state State-A
  6043. In State-A moving R
  6044. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  6045. predict error 0
  6046. dir: dir isR
  6047. |\859: O: O1718 (predict-no)
  6048. I see 1 and I'm going to do: predict-no
  6049. ENV: Agent did: predict-no for direction R in state State-B
  6050. In State-B moving R
  6051. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  6052. predict error 0
  6053. dir: dir isR
  6054. -/|860: O: O1720 (predict-no)
  6055. I see 1 and I'm going to do: predict-no
  6056. ENV: Agent did: predict-no for direction R in state State-B
  6057. In State-B moving R
  6058. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  6059. predict error 0
  6060. dir: dir isU
  6061. \-/861: O: O1722 (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-B
  6064. In State-B moving U
  6065. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  6066. predict error 0
  6067. dir: dir isU
  6068. |862: O: O1724 (predict-no)
  6069. I see 1 and I'm going to do: predict-no
  6070. ENV: Agent did: predict-no for direction U in state State-B
  6071. In State-B moving U
  6072. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  6073. predict error 0
  6074. dir: dir isR
  6075. \-/863: O: O1726 (predict-no)
  6076. I see 1 and I'm going to do: predict-no
  6077. ENV: Agent did: predict-no for direction R in state State-B
  6078. In State-B moving R
  6079. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  6080. predict error 0
  6081. dir: dir isL
  6082. |\-864: O: O1727 (predict-yes)
  6083. I see 1 and I'm going to do: predict-yes
  6084. ENV: Agent did: predict-yes for direction L in state State-B
  6085. In State-B moving L
  6086. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  6087. predict error 0
  6088. dir: dir isU
  6089. /865: O: O1730 (predict-no)
  6090. I see 1 and I'm going to do: predict-no
  6091. ENV: Agent did: predict-no for direction U in state State-A
  6092. In State-A moving U
  6093. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  6094. predict error 0
  6095. dir: dir isR
  6096. |\-866: O: O1731 (predict-yes)
  6097. I see 1 and I'm going to do: predict-yes
  6098. ENV: Agent did: predict-yes for direction R in state State-A
  6099. In State-A moving R
  6100. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  6101. predict error 0
  6102. dir: dir isL
  6103. /|\867: O: O1733 (predict-yes)
  6104. I see 1 and I'm going to do: predict-yes
  6105. ENV: Agent did: predict-yes for direction L in state State-B
  6106. In State-B moving L
  6107. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  6108. predict error 0
  6109. dir: dir isL
  6110. -/|868: O: O1736 (predict-no)
  6111. I see 1 and I'm going to do: predict-no
  6112. ENV: Agent did: predict-no for direction L in state State-A
  6113. In State-A moving L
  6114. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  6115. predict error 0
  6116. dir: dir isU
  6117. \-/869: O: O1738 (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-A
  6120. In State-A moving U
  6121. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  6122. predict error 0
  6123. dir: dir isL
  6124. |\870: O: O1740 (predict-no)
  6125. I see 1 and I'm going to do: predict-no
  6126. ENV: Agent did: predict-no for direction L in state State-A
  6127. In State-A moving L
  6128. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  6129. predict error 0
  6130. dir: dir isL
  6131. -/871: O: O1742 (predict-no)
  6132. I see 1 and I'm going to do: predict-no
  6133. ENV: Agent did: predict-no for direction L in state State-A
  6134. In State-A moving L
  6135. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  6136. predict error 0
  6137. dir: dir isL
  6138. |872: O: O1744 (predict-no)
  6139. I see 1 and I'm going to do: predict-no
  6140. ENV: Agent did: predict-no for direction L in state State-A
  6141. In State-A moving L
  6142. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  6143. predict error 0
  6144. dir: dir isU
  6145. \873: O: O1746 (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-A
  6148. In State-A moving U
  6149. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  6150. predict error 0
  6151. dir: dir isU
  6152. -/|874: O: O1748 (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-A
  6155. In State-A moving U
  6156. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  6157. predict error 0
  6158. dir: dir isU
  6159. \-/875: O: O1750 (predict-no)
  6160. I see 1 and I'm going to do: predict-no
  6161. ENV: Agent did: predict-no for direction U in state State-A
  6162. In State-A moving U
  6163. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  6164. predict error 0
  6165. dir: dir isR
  6166. |876: O: O1751 (predict-yes)
  6167. I see 1 and I'm going to do: predict-yes
  6168. ENV: Agent did: predict-yes for direction R in state State-A
  6169. In State-A moving R
  6170. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  6171. predict error 0
  6172. dir: dir isR
  6173. \-/877: O: O1754 (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 isR
  6180. |878: O: O1756 (predict-no)
  6181. I see 1 and I'm going to do: predict-no
  6182. ENV: Agent did: predict-no for direction R in state State-B
  6183. In State-B moving R
  6184. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  6185. predict error 0
  6186. dir: dir isR
  6187. \879: O: O1758 (predict-no)
  6188. I see 1 and I'm going to do: predict-no
  6189. ENV: Agent did: predict-no for direction R in state State-B
  6190. In State-B moving R
  6191. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  6192. predict error 0
  6193. dir: dir isR
  6194. -/880: O: O1760 (predict-no)
  6195. I see 1 and I'm going to do: predict-no
  6196. ENV: Agent did: predict-no for direction R in state State-B
  6197. In State-B moving R
  6198. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  6199. predict error 0
  6200. dir: dir isU
  6201. |881: O: O1762 (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-B
  6204. In State-B moving U
  6205. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  6206. predict error 0
  6207. dir: dir isU
  6208. \882: O: O1764 (predict-no)
  6209. I see 1 and I'm going to do: predict-no
  6210. ENV: Agent did: predict-no for direction U in state State-B
  6211. In State-B moving U
  6212. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  6213. predict error 0
  6214. dir: dir isR
  6215. -/|883: O: O1766 (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. \-/884: O: O1768 (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 isL
  6229. |\-885: O: O1769 (predict-yes)
  6230. I see 1 and I'm going to do: predict-yes
  6231. ENV: Agent did: predict-yes for direction L in state State-B
  6232. In State-B moving L
  6233. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  6234. predict error 0
  6235. dir: dir isL
  6236. /|\886: O: O1772 (predict-no)
  6237. I see 1 and I'm going to do: predict-no
  6238. ENV: Agent did: predict-no for direction L in state State-A
  6239. In State-A moving L
  6240. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  6241. predict error 0
  6242. dir: dir isR
  6243. -/|887: O: O1773 (predict-yes)
  6244. I see 1 and I'm going to do: predict-yes
  6245. ENV: Agent did: predict-yes for direction R in state State-A
  6246. In State-A moving R
  6247. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  6248. predict error 0
  6249. dir: dir isR
  6250. \-/888: O: O1776 (predict-no)
  6251. I see 1 and I'm going to do: predict-no
  6252. ENV: Agent did: predict-no for direction R in state State-B
  6253. In State-B moving R
  6254. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  6255. predict error 0
  6256. dir: dir isR
  6257. |\-889: O: O1778 (predict-no)
  6258. I see 1 and I'm going to do: predict-no
  6259. ENV: Agent did: predict-no for direction R in state State-B
  6260. In State-B moving R
  6261. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  6262. predict error 0
  6263. dir: dir isU
  6264. /|\890: O: O1780 (predict-no)
  6265. I see 1 and I'm going to do: predict-no
  6266. ENV: Agent did: predict-no for direction U in state State-B
  6267. In State-B moving U
  6268. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  6269. predict error 0
  6270. dir: dir isL
  6271. -891: O: O1781 (predict-yes)
  6272. I see 1 and I'm going to do: predict-yes
  6273. ENV: Agent did: predict-yes for direction L in state State-B
  6274. In State-B moving L
  6275. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  6276. predict error 0
  6277. dir: dir isR
  6278. /892: O: O1783 (predict-yes)
  6279. I see 1 and I'm going to do: predict-yes
  6280. ENV: Agent did: predict-yes for direction R in state State-A
  6281. In State-A moving R
  6282. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  6283. predict error 0
  6284. dir: dir isU
  6285. |\-893: O: O1786 (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. /|894: O: O1788 (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 isR
  6299. \-/895: O: O1790 (predict-no)
  6300. I see 1 and I'm going to do: predict-no
  6301. ENV: Agent did: predict-no for direction R in state State-B
  6302. In State-B moving R
  6303. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  6304. predict error 0
  6305. dir: dir isR
  6306. |\-896: O: O1792 (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 isR
  6313. /|\897: O: O1794 (predict-no)
  6314. I see 1 and I'm going to do: predict-no
  6315. ENV: Agent did: predict-no for direction R in state State-B
  6316. In State-B moving R
  6317. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  6318. predict error 0
  6319. dir: dir isU
  6320. -/898: O: O1796 (predict-no)
  6321. I see 1 and I'm going to do: predict-no
  6322. ENV: Agent did: predict-no for direction U in state State-B
  6323. In State-B moving U
  6324. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  6325. predict error 0
  6326. dir: dir isU
  6327. |\899: O: O1798 (predict-no)
  6328. I see 1 and I'm going to do: predict-no
  6329. ENV: Agent did: predict-no for direction U in state State-B
  6330. In State-B moving U
  6331. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  6332. predict error 0
  6333. dir: dir isU
  6334. -/|900: O: O1800 (predict-no)
  6335. I see 1 and I'm going to do: predict-no
  6336. ENV: Agent did: predict-no for direction U in state State-B
  6337. In State-B moving U
  6338. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  6339. predict error 0
  6340. dir: dir isU
  6341. \-/901: O: O1802 (predict-no)
  6342. I see 1 and I'm going to do: predict-no
  6343. ENV: Agent did: predict-no for direction U in state State-B
  6344. In State-B moving U
  6345. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  6346. predict error 0
  6347. dir: dir isU
  6348. |902: O: O1804 (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-B
  6351. In State-B moving U
  6352. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  6353. predict error 0
  6354. dir: dir isU
  6355. \-/903: O: O1806 (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-B
  6358. In State-B moving U
  6359. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  6360. predict error 0
  6361. dir: dir isR
  6362. |\-904: O: O1808 (predict-no)
  6363. I see 1 and I'm going to do: predict-no
  6364. ENV: Agent did: predict-no for direction R in state State-B
  6365. In State-B moving R
  6366. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  6367. predict error 0
  6368. dir: dir isR
  6369. /|\905: O: O1810 (predict-no)
  6370. I see 1 and I'm going to do: predict-no
  6371. ENV: Agent did: predict-no for direction R in state State-B
  6372. In State-B moving R
  6373. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  6374. predict error 0
  6375. dir: dir isU
  6376. -906: O: O1812 (predict-no)
  6377. I see 1 and I'm going to do: predict-no
  6378. ENV: Agent did: predict-no for direction U in state State-B
  6379. In State-B moving U
  6380. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  6381. predict error 0
  6382. dir: dir isR
  6383. /|\907: O: O1814 (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. -908: O: O1816 (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 isR
  6397. /|909: O: O1818 (predict-no)
  6398. I see 1 and I'm going to do: predict-no
  6399. ENV: Agent did: predict-no for direction R in state State-B
  6400. In State-B moving R
  6401. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  6402. predict error 0
  6403. dir: dir isR
  6404. \-/910: O: O1820 (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 isR
  6411. |\-911: O: O1822 (predict-no)
  6412. I see 1 and I'm going to do: predict-no
  6413. ENV: Agent did: predict-no for direction R in state State-B
  6414. In State-B moving R
  6415. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  6416. predict error 0
  6417. dir: dir isL
  6418. /912: O: O1823 (predict-yes)
  6419. I see 1 and I'm going to do: predict-yes
  6420. ENV: Agent did: predict-yes for direction L in state State-B
  6421. In State-B moving L
  6422. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  6423. predict error 0
  6424. dir: dir isR
  6425. |\-913: O: O1825 (predict-yes)
  6426. I see 1 and I'm going to do: predict-yes
  6427. ENV: Agent did: predict-yes for direction R in state State-A
  6428. In State-A moving R
  6429. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  6430. predict error 0
  6431. dir: dir isR
  6432. /|914: O: O1828 (predict-no)
  6433. I see 1 and I'm going to do: predict-no
  6434. ENV: Agent did: predict-no for direction R in state State-B
  6435. In State-B moving R
  6436. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  6437. predict error 0
  6438. dir: dir isL
  6439. \-/915: O: O1829 (predict-yes)
  6440. I see 1 and I'm going to do: predict-yes
  6441. ENV: Agent did: predict-yes for direction L in state State-B
  6442. In State-B moving L
  6443. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  6444. predict error 0
  6445. dir: dir isL
  6446. |\-916: O: O1832 (predict-no)
  6447. I see 1 and I'm going to do: predict-no
  6448. ENV: Agent did: predict-no for direction L in state State-A
  6449. In State-A moving L
  6450. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  6451. predict error 0
  6452. dir: dir isL
  6453. /|\917: O: O1834 (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. -/|918: O: O1836 (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 isR
  6467. \-/919: O: O1837 (predict-yes)
  6468. I see 1 and I'm going to do: predict-yes
  6469. ENV: Agent did: predict-yes for direction R in state State-A
  6470. In State-A moving R
  6471. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  6472. predict error 0
  6473. dir: dir isL
  6474. |\-920: O: O1839 (predict-yes)
  6475. I see 1 and I'm going to do: predict-yes
  6476. ENV: Agent did: predict-yes for direction L in state State-B
  6477. In State-B moving L
  6478. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  6479. predict error 0
  6480. dir: dir isU
  6481. /|\921: O: O1842 (predict-no)
  6482. I see 1 and I'm going to do: predict-no
  6483. ENV: Agent did: predict-no for direction U in state State-A
  6484. In State-A moving U
  6485. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  6486. predict error 0
  6487. dir: dir isL
  6488. -922: O: O1844 (predict-no)
  6489. I see 1 and I'm going to do: predict-no
  6490. ENV: Agent did: predict-no for direction L in state State-A
  6491. In State-A moving L
  6492. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  6493. predict error 0
  6494. dir: dir isR
  6495. /|\923: O: O1845 (predict-yes)
  6496. I see 1 and I'm going to do: predict-yes
  6497. ENV: Agent did: predict-yes for direction R in state State-A
  6498. In State-A moving R
  6499. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  6500. predict error 0
  6501. dir: dir isU
  6502. -/|924: O: O1848 (predict-no)
  6503. I see 1 and I'm going to do: predict-no
  6504. ENV: Agent did: predict-no for direction U in state State-B
  6505. In State-B moving U
  6506. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  6507. predict error 0
  6508. dir: dir isU
  6509. \-/925: O: O1850 (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-B
  6512. In State-B moving U
  6513. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  6514. predict error 0
  6515. dir: dir isR
  6516. |\-/926: O: O1852 (predict-no)
  6517. I see 1 and I'm going to do: predict-no
  6518. ENV: Agent did: predict-no for direction R in state State-B
  6519. In State-B moving R
  6520. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  6521. predict error 0
  6522. dir: dir isU
  6523. |\-927: O: O1854 (predict-no)
  6524. I see 1 and I'm going to do: predict-no
  6525. ENV: Agent did: predict-no for direction U in state State-B
  6526. In State-B moving U
  6527. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  6528. predict error 0
  6529. dir: dir isR
  6530. /|\928: O: O1856 (predict-no)
  6531. I see 1 and I'm going to do: predict-no
  6532. ENV: Agent did: predict-no for direction R in state State-B
  6533. In State-B moving R
  6534. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  6535. predict error 0
  6536. dir: dir isU
  6537. -/|929: O: O1858 (predict-no)
  6538. I see 1 and I'm going to do: predict-no
  6539. ENV: Agent did: predict-no for direction U in state State-B
  6540. In State-B moving U
  6541. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  6542. predict error 0
  6543. dir: dir isR
  6544. \-930: O: O1860 (predict-no)
  6545. I see 1 and I'm going to do: predict-no
  6546. ENV: Agent did: predict-no for direction R in state State-B
  6547. In State-B moving R
  6548. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  6549. predict error 0
  6550. dir: dir isU
  6551. /|\931: O: O1862 (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. -932: O: O1864 (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 isL
  6565. /933: O: O1865 (predict-yes)
  6566. I see 1 and I'm going to do: predict-yes
  6567. ENV: Agent did: predict-yes for direction L in state State-B
  6568. In State-B moving L
  6569. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  6570. predict error 0
  6571. dir: dir isL
  6572. |\-934: O: O1868 (predict-no)
  6573. I see 1 and I'm going to do: predict-no
  6574. ENV: Agent did: predict-no for direction L in state State-A
  6575. In State-A moving L
  6576. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  6577. predict error 0
  6578. dir: dir isU
  6579. /|\935: O: O1870 (predict-no)
  6580. I see 1 and I'm going to do: predict-no
  6581. ENV: Agent did: predict-no for direction U in state State-A
  6582. In State-A moving U
  6583. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  6584. predict error 0
  6585. dir: dir isL
  6586. -/936: O: O1872 (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 isL
  6593. |\-937: O: O1874 (predict-no)
  6594. I see 1 and I'm going to do: predict-no
  6595. ENV: Agent did: predict-no for direction L in state State-A
  6596. In State-A moving L
  6597. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  6598. predict error 0
  6599. dir: dir isL
  6600. /|\938: O: O1876 (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 isR
  6607. -/939: O: O1877 (predict-yes)
  6608. I see 1 and I'm going to do: predict-yes
  6609. ENV: Agent did: predict-yes for direction R in state State-A
  6610. In State-A moving R
  6611. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  6612. predict error 0
  6613. dir: dir isU
  6614. |\940: O: O1880 (predict-no)
  6615. I see 1 and I'm going to do: predict-no
  6616. ENV: Agent did: predict-no for direction U in state State-B
  6617. In State-B moving U
  6618. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  6619. predict error 0
  6620. dir: dir isR
  6621. -/|941: O: O1882 (predict-no)
  6622. I see 1 and I'm going to do: predict-no
  6623. ENV: Agent did: predict-no for direction R in state State-B
  6624. In State-B moving R
  6625. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  6626. predict error 0
  6627. dir: dir isU
  6628. \942: O: O1884 (predict-no)
  6629. I see 1 and I'm going to do: predict-no
  6630. ENV: Agent did: predict-no for direction U in state State-B
  6631. In State-B moving U
  6632. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  6633. predict error 0
  6634. dir: dir isU
  6635. -/943: O: O1886 (predict-no)
  6636. I see 1 and I'm going to do: predict-no
  6637. ENV: Agent did: predict-no for direction U in state State-B
  6638. In State-B moving U
  6639. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  6640. predict error 0
  6641. dir: dir isL
  6642. |\944: O: O1887 (predict-yes)
  6643. I see 1 and I'm going to do: predict-yes
  6644. ENV: Agent did: predict-yes for direction L in state State-B
  6645. In State-B moving L
  6646. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  6647. predict error 0
  6648. dir: dir isR
  6649. -/945: O: O1889 (predict-yes)
  6650. I see 1 and I'm going to do: predict-yes
  6651. ENV: Agent did: predict-yes for direction R in state State-A
  6652. In State-A moving R
  6653. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  6654. predict error 0
  6655. dir: dir isU
  6656. |\946: O: O1892 (predict-no)
  6657. I see 1 and I'm going to do: predict-no
  6658. ENV: Agent did: predict-no for direction U in state State-B
  6659. In State-B moving U
  6660. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  6661. predict error 0
  6662. dir: dir isR
  6663. -/|947: O: O1894 (predict-no)
  6664. I see 1 and I'm going to do: predict-no
  6665. ENV: Agent did: predict-no for direction R in state State-B
  6666. In State-B moving R
  6667. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  6668. predict error 0
  6669. dir: dir isR
  6670. \-/948: O: O1896 (predict-no)
  6671. I see 1 and I'm going to do: predict-no
  6672. ENV: Agent did: predict-no for direction R in state State-B
  6673. In State-B moving R
  6674. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  6675. predict error 0
  6676. dir: dir isR
  6677. |\-949: O: O1898 (predict-no)
  6678. I see 1 and I'm going to do: predict-no
  6679. ENV: Agent did: predict-no for direction R in state State-B
  6680. In State-B moving R
  6681. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  6682. predict error 0
  6683. dir: dir isU
  6684. /950: O: O1900 (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-B
  6687. In State-B moving U
  6688. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  6689. predict error 0
  6690. dir: dir isU
  6691. |\-/|\-/|--- Input Phase ---
  6692. =>WM: (13307: I2 ^dir U)
  6693. =>WM: (13306: I2 ^reward 1)
  6694. =>WM: (13305: I2 ^see 0)
  6695. =>WM: (13304: N950 ^status complete)
  6696. <=WM: (13293: I2 ^dir U)
  6697. <=WM: (13292: I2 ^reward 1)
  6698. <=WM: (13291: I2 ^see 0)
  6699. =>WM: (13308: I2 ^level-1 R0-root)
  6700. <=WM: (13294: I2 ^level-1 R0-root)
  6701. --- END Input Phase ---
  6702. --- Proposal Phase ---
  6703. --- Inner Elaboration Phase, active level 1 (S1) ---
  6704. Firing elaborate*copy-see-to-output-link
  6705. -->
  6706. (I3 ^see 0 +)
  6707. Firing elaborate*reward*based*on*reward
  6708. -->
  6709. (R954 ^value 1 +)
  6710. (R1 ^reward R954 +)
  6711. Firing propose*predict-yes
  6712. -->
  6713. (O1901 ^name predict-yes +)
  6714. (S1 ^operator O1901 +)
  6715. Firing propose*predict-no
  6716. -->
  6717. (O1902 ^name predict-no +)
  6718. (S1 ^operator O1902 +)
  6719. Firing rl*prefer*rvt*predict-no*H0*4
  6720. -->
  6721. (S1 ^operator O1900 = 1.)
  6722. Firing rl*prefer*rvt*predict-yes*H0*3
  6723. -->
  6724. (S1 ^operator O1899 = 0.)
  6725. Firing prefer*rvt*predict-yes*H0
  6726. -->
  6727. Firing prefer*rvt*predict-no*H0
  6728. -->
  6729. Firing elaborate*copy-dir-to-output-link
  6730. -->
  6731. (I3 ^dir U +)
  6732. inner elaboration loop at bottom goal.
  6733. Retracting elaborate*copy-see-to-output-link
  6734. -->
  6735. (I3 ^see 0 +)
  6736. Retracting propose*predict-no
  6737. -->
  6738. (O1900 ^name predict-no +)
  6739. (S1 ^operator O1900 +)
  6740. Retracting propose*predict-yes
  6741. -->
  6742. (O1899 ^name predict-yes +)
  6743. (S1 ^operator O1899 +)
  6744. Retracting elaborate*reward*based*on*reward
  6745. -->
  6746. (R953 ^value 1 +)
  6747. (R1 ^reward R953 +)
  6748. Retracting elaborate*copy-dir-to-output-link
  6749. -->
  6750. (I3 ^dir U +)
  6751. Retracting rl*prefer*rvt*predict-no*H0*4
  6752. -->
  6753. (S1 ^operator O1900 = 1.)
  6754. Retracting rl*prefer*rvt*predict-yes*H0*3
  6755. -->
  6756. (S1 ^operator O1899 = 0.)
  6757. =>WM: (13314: S1 ^operator O1902 +)
  6758. =>WM: (13313: S1 ^operator O1901 +)
  6759. =>WM: (13312: O1902 ^name predict-no)
  6760. =>WM: (13311: O1901 ^name predict-yes)
  6761. =>WM: (13310: R954 ^value 1)
  6762. =>WM: (13309: R1 ^reward R954)
  6763. <=WM: (13300: S1 ^operator O1899 +)
  6764. <=WM: (13301: S1 ^operator O1900 +)
  6765. <=WM: (13302: S1 ^operator O1900)
  6766. <=WM: (13295: R1 ^reward R953)
  6767. <=WM: (13298: O1900 ^name predict-no)
  6768. <=WM: (13297: O1899 ^name predict-yes)
  6769. <=WM: (13296: R953 ^value 1)
  6770. --- Inner Elaboration Phase, active level 1 (S1) ---
  6771. Firing prefer*rvt*predict-yes*H0
  6772. -->
  6773. Firing rl*prefer*rvt*predict-yes*H0*3
  6774. -->
  6775. (S1 ^operator O1901 = 0.)
  6776. Firing prefer*rvt*predict-no*H0
  6777. -->
  6778. Firing rl*prefer*rvt*predict-no*H0*4
  6779. -->
  6780. (S1 ^operator O1902 = 1.)
  6781. inner elaboration loop at bottom goal.
  6782. Retracting rl*prefer*rvt*predict-no*H0*4
  6783. -->
  6784. (S1 ^operator O1900 = 1.)
  6785. Retracting rl*prefer*rvt*predict-yes*H0*3
  6786. -->
  6787. (S1 ^operator O1899 = 0.)
  6788. --- END Proposal Phase ---
  6789. --- Decision Phase ---
  6790. RL update rl*prefer*rvt*predict-no*H0*4 1 0 1 -> 1 0 1(R,m,v=1,1,0)
  6791. =>WM: (13315: S1 ^operator O1902)
  6792. 951: O: O1902 (predict-no)
  6793. --- END Decision Phase ---
  6794. --- Application Phase ---
  6795. --- Firing Productions (PE) For State At Depth 1 ---
  6796. --- Inner Elaboration Phase, active level 1 (S1) ---
  6797. Firing apply*operator
  6798. -->
  6799. (I3 ^predict-no N951 + :O )
  6800. Firing apply*operator*complete
  6801. -->
  6802. (I3 ^predict-no N950 - :O )
  6803. inner elaboration loop at bottom goal.
  6804. --- Change Working Memory (PE) ---
  6805. =>WM: (13316: I3 ^predict-no N951)
  6806. <=WM: (13304: N950 ^status complete)
  6807. <=WM: (13303: I3 ^predict-no N950)
  6808. --- Firing Productions (IE) For State At Depth 1 ---
  6809. --- Inner Elaboration Phase, active level 1 (S1) ---
  6810. Firing monitor*world
  6811. -->
  6812. I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
  6813. --- Change Working Memory (IE) ---
  6814. --- END Application Phase ---
  6815. --- Output Phase ---
  6816. ENV: Agent did: predict-no for direction U in state State-B
  6817. In State-B moving U
  6818. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  6819. predict error 0
  6820. dir: dir isL
  6821. --- END Output Phase ---
  6822. \--- Input Phase ---
  6823. =>WM: (13320: I2 ^dir L)
  6824. =>WM: (13319: I2 ^reward 1)
  6825. =>WM: (13318: I2 ^see 0)
  6826. =>WM: (13317: N951 ^status complete)
  6827. <=WM: (13307: I2 ^dir U)
  6828. <=WM: (13306: I2 ^reward 1)
  6829. <=WM: (13305: I2 ^see 0)
  6830. =>WM: (13321: I2 ^level-1 R0-root)
  6831. <=WM: (13308: I2 ^level-1 R0-root)
  6832. --- END Input Phase ---
  6833. --- Proposal Phase ---
  6834. --- Inner Elaboration Phase, active level 1 (S1) ---
  6835. Firing rl*prefer*rvt*predict-no*H0*2*H1*12
  6836. -->
  6837. (S1 ^operator O1902 = -0.1359494083332169)
  6838. Firing rl*prefer*rvt*predict-yes*H0*1*H1*13
  6839. -->
  6840. (S1 ^operator O1901 = 0.650078869260899)
  6841. Firing prefer*rvt*predict-no*H0*2*H1
  6842. -->
  6843. Firing prefer*rvt*predict-yes*H0*1*H1
  6844. -->
  6845. Firing elaborate*copy-see-to-output-link
  6846. -->
  6847. (I3 ^see 0 +)
  6848. Firing elaborate*reward*based*on*reward
  6849. -->
  6850. (R955 ^value 1 +)
  6851. (R1 ^reward R955 +)
  6852. Firing propose*predict-yes
  6853. -->
  6854. (O1903 ^name predict-yes +)
  6855. (S1 ^operator O1903 +)
  6856. Firing propose*predict-no
  6857. -->
  6858. (O1904 ^name predict-no +)
  6859. (S1 ^operator O1904 +)
  6860. Firing rl*prefer*rvt*predict-no*H0*2
  6861. -->
  6862. (S1 ^operator O1902 = 0.2381451287000689)
  6863. Firing rl*prefer*rvt*predict-yes*H0*1
  6864. -->
  6865. (S1 ^operator O1901 = 0.3499208298136254)
  6866. Firing prefer*rvt*predict-yes*H0
  6867. -->
  6868. Firing prefer*rvt*predict-no*H0
  6869. -->
  6870. Firing elaborate*copy-dir-to-output-link
  6871. -->
  6872. (I3 ^dir L +)
  6873. inner elaboration loop at bottom goal.
  6874. Retracting elaborate*copy-see-to-output-link
  6875. -->
  6876. (I3 ^see 0 +)
  6877. Retracting propose*predict-no
  6878. -->
  6879. (O1902 ^name predict-no +)
  6880. (S1 ^operator O1902 +)
  6881. Retracting propose*predict-yes
  6882. -->
  6883. (O1901 ^name predict-yes +)
  6884. (S1 ^operator O1901 +)
  6885. Retracting elaborate*reward*based*on*reward
  6886. -->
  6887. (R954 ^value 1 +)
  6888. (R1 ^reward R954 +)
  6889. Retracting elaborate*copy-dir-to-output-link
  6890. -->
  6891. (I3 ^dir U +)
  6892. Retracting rl*prefer*rvt*predict-no*H0*4
  6893. -->
  6894. (S1 ^operator O1902 = 1.)
  6895. Retracting rl*prefer*rvt*predict-yes*H0*3
  6896. -->
  6897. (S1 ^operator O1901 = 0.)
  6898. =>WM: (13328: S1 ^operator O1904 +)
  6899. =>WM: (13327: S1 ^operator O1903 +)
  6900. =>WM: (13326: I3 ^dir L)
  6901. =>WM: (13325: O1904 ^name predict-no)
  6902. =>WM: (13324: O1903 ^name predict-yes)
  6903. =>WM: (13323: R955 ^value 1)
  6904. =>WM: (13322: R1 ^reward R955)
  6905. <=WM: (13313: S1 ^operator O1901 +)
  6906. <=WM: (13314: S1 ^operator O1902 +)
  6907. <=WM: (13315: S1 ^operator O1902)
  6908. <=WM: (13299: I3 ^dir U)
  6909. <=WM: (13309: R1 ^reward R954)
  6910. <=WM: (13312: O1902 ^name predict-no)
  6911. <=WM: (13311: O1901 ^name predict-yes)
  6912. <=WM: (13310: R954 ^value 1)
  6913. --- Inner Elaboration Phase, active level 1 (S1) ---
  6914. Firing prefer*rvt*predict-yes*H0
  6915. -->
  6916. Firing rl*prefer*rvt*predict-yes*H0*1*H1*13
  6917. -->
  6918. (S1 ^operator O1903 = 0.650078869260899)
  6919. Firing rl*prefer*rvt*predict-yes*H0*1
  6920. -->
  6921. (S1 ^operator O1903 = 0.3499208298136254)
  6922. Firing prefer*rvt*predict-yes*H0*1*H1
  6923. -->
  6924. Firing prefer*rvt*predict-no*H0
  6925. -->
  6926. Firing rl*prefer*rvt*predict-no*H0*2*H1*12
  6927. -->
  6928. (S1 ^operator O1904 = -0.1359494083332169)
  6929. Firing rl*prefer*rvt*predict-no*H0*2
  6930. -->
  6931. (S1 ^operator O1904 = 0.2381451287000689)
  6932. Firing prefer*rvt*predict-no*H0*2*H1
  6933. -->
  6934. inner elaboration loop at bottom goal.
  6935. Retracting rl*prefer*rvt*predict-no*H0*2
  6936. -->
  6937. (S1 ^operator O1902 = 0.2381451287000689)
  6938. Retracting rl*prefer*rvt*predict-no*H0*2*H1*12
  6939. -->
  6940. (S1 ^operator O1902 = -0.1359494083332169)
  6941. Retracting rl*prefer*rvt*predict-yes*H0*1
  6942. -->
  6943. (S1 ^operator O1901 = 0.3499208298136254)
  6944. Retracting rl*prefer*rvt*predict-yes*H0*1*H1*13
  6945. -->
  6946. (S1 ^operator O1901 = 0.650078869260899)
  6947. --- END Proposal Phase ---
  6948. --- Decision Phase ---
  6949. RL update rl*prefer*rvt*predict-no*H0*4 1 0 1 -> 1 0 1(R,m,v=1,1,0)
  6950. =>WM: (13329: S1 ^operator O1903)
  6951. 952: O: O1903 (predict-yes)
  6952. --- END Decision Phase ---
  6953. --- Application Phase ---
  6954. --- Firing Productions (PE) For State At Depth 1 ---
  6955. --- Inner Elaboration Phase, active level 1 (S1) ---
  6956. Firing apply*operator
  6957. -->
  6958. (I3 ^predict-yes N952 + :O )
  6959. Firing apply*operator*complete
  6960. -->
  6961. (I3 ^predict-no N951 - :O )
  6962. inner elaboration loop at bottom goal.
  6963. --- Change Working Memory (PE) ---
  6964. =>WM: (13330: I3 ^predict-yes N952)
  6965. <=WM: (13317: N951 ^status complete)
  6966. <=WM: (13316: I3 ^predict-no N951)
  6967. --- Firing Productions (IE) For State At Depth 1 ---
  6968. --- Inner Elaboration Phase, active level 1 (S1) ---
  6969. Firing monitor*world
  6970. -->
  6971. I see 1 and I'm going to do: predict-yes inner elaboration loop at bottom goal.
  6972. --- Change Working Memory (IE) ---
  6973. --- END Application Phase ---
  6974. --- Output Phase ---
  6975. ENV: Agent did: predict-yes for direction L in state State-B
  6976. In State-B moving L
  6977. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  6978. predict error 0
  6979. dir: dir isR
  6980. --- END Output Phase ---
  6981. -/|--- Input Phase ---
  6982. =>WM: (13334: I2 ^dir R)
  6983. =>WM: (13333: I2 ^reward 1)
  6984. =>WM: (13332: I2 ^see 1)
  6985. =>WM: (13331: N952 ^status complete)
  6986. <=WM: (13320: I2 ^dir L)
  6987. <=WM: (13319: I2 ^reward 1)
  6988. <=WM: (13318: I2 ^see 0)
  6989. =>WM: (13335: I2 ^level-1 L1-root)
  6990. <=WM: (13321: I2 ^level-1 R0-root)
  6991. --- END Input Phase ---
  6992. --- Proposal Phase ---
  6993. --- Inner Elaboration Phase, active level 1 (S1) ---
  6994. Firing rl*prefer*rvt*predict-yes*H0*5*H1*9
  6995. -->
  6996. (S1 ^operator O1903 = 0.776301464817437)
  6997. Firing prefer*rvt*predict-yes*H0*5*H1
  6998. -->
  6999. Firing elaborate*copy-see-to-output-link
  7000. -->
  7001. (I3 ^see 1 +)
  7002. Firing elaborate*reward*based*on*reward
  7003. -->
  7004. (R956 ^value 1 +)
  7005. (R1 ^reward R956 +)
  7006. Firing propose*predict-yes
  7007. -->
  7008. (O1905 ^name predict-yes +)
  7009. (S1 ^operator O1905 +)
  7010. Firing propose*predict-no
  7011. -->
  7012. (O1906 ^name predict-no +)
  7013. (S1 ^operator O1906 +)
  7014. Firing rl*prefer*rvt*predict-no*H0*6
  7015. -->
  7016. (S1 ^operator O1904 = 0.9993817332271659)
  7017. Firing rl*prefer*rvt*predict-yes*H0*5
  7018. -->
  7019. (S1 ^operator O1903 = 0.2239652448743312)
  7020. Firing prefer*rvt*predict-yes*H0
  7021. -->
  7022. Firing prefer*rvt*predict-no*H0
  7023. -->
  7024. Firing elaborate*copy-dir-to-output-link
  7025. -->
  7026. (I3 ^dir R +)
  7027. inner elaboration loop at bottom goal.
  7028. Retracting elaborate*copy-see-to-output-link
  7029. -->
  7030. (I3 ^see 0 +)
  7031. Retracting propose*predict-no
  7032. -->
  7033. (O1904 ^name predict-no +)
  7034. (S1 ^operator O1904 +)
  7035. Retracting propose*predict-yes
  7036. -->
  7037. (O1903 ^name predict-yes +)
  7038. (S1 ^operator O1903 +)
  7039. Retracting elaborate*reward*based*on*reward
  7040. -->
  7041. (R955 ^value 1 +)
  7042. (R1 ^reward R955 +)
  7043. Retracting elaborate*copy-dir-to-output-link
  7044. -->
  7045. (I3 ^dir L +)
  7046. Retracting rl*prefer*rvt*predict-no*H0*2
  7047. -->
  7048. (S1 ^operator O1904 = 0.2381451287000689)
  7049. Retracting rl*prefer*rvt*predict-no*H0*2*H1*12
  7050. -->
  7051. (S1 ^operator O1904 = -0.1359494083332169)
  7052. Retracting rl*prefer*rvt*predict-yes*H0*1
  7053. -->
  7054. (S1 ^operator O1903 = 0.3499208298136254)
  7055. Retracting rl*prefer*rvt*predict-yes*H0*1*H1*13
  7056. -->
  7057. (S1 ^operator O1903 = 0.650078869260899)
  7058. =>WM: (13343: S1 ^operator O1906 +)
  7059. =>WM: (13342: S1 ^operator O1905 +)
  7060. =>WM: (13341: I3 ^dir R)
  7061. =>WM: (13340: O1906 ^name predict-no)
  7062. =>WM: (13339: O1905 ^name predict-yes)
  7063. =>WM: (13338: R956 ^value 1)
  7064. =>WM: (13337: R1 ^reward R956)
  7065. =>WM: (13336: I3 ^see 1)
  7066. <=WM: (13327: S1 ^operator O1903 +)
  7067. <=WM: (13329: S1 ^operator O1903)
  7068. <=WM: (13328: S1 ^operator O1904 +)
  7069. <=WM: (13326: I3 ^dir L)
  7070. <=WM: (13322: R1 ^reward R955)
  7071. <=WM: (13254: I3 ^see 0)
  7072. <=WM: (13325: O1904 ^name predict-no)
  7073. <=WM: (13324: O1903 ^name predict-yes)
  7074. <=WM: (13323: R955 ^value 1)
  7075. --- Inner Elaboration Phase, active level 1 (S1) ---
  7076. Firing prefer*rvt*predict-yes*H0
  7077. -->
  7078. Firing rl*prefer*rvt*predict-yes*H0*5
  7079. -->
  7080. (S1 ^operator O1905 = 0.2239652448743312)
  7081. Firing prefer*rvt*predict-yes*H0*5*H1
  7082. -->
  7083. Firing rl*prefer*rvt*predict-yes*H0*5*H1*9
  7084. -->
  7085. (S1 ^operator O1905 = 0.776301464817437)
  7086. Firing prefer*rvt*predict-no*H0
  7087. -->
  7088. Firing rl*prefer*rvt*predict-no*H0*6
  7089. -->
  7090. (S1 ^operator O1906 = 0.9993817332271659)
  7091. inner elaboration loop at bottom goal.
  7092. Retracting rl*prefer*rvt*predict-no*H0*6
  7093. -->
  7094. (S1 ^operator O1904 = 0.9993817332271659)
  7095. Retracting rl*prefer*rvt*predict-yes*H0*5
  7096. -->
  7097. (S1 ^operator O1903 = 0.2239652448743312)
  7098. Retracting rl*prefer*rvt*predict-yes*H0*5*H1*9
  7099. -->
  7100. (S1 ^operator O1903 = 0.776301464817437)
  7101. --- END Proposal Phase ---
  7102. --- Decision Phase ---
  7103. RL update rl*prefer*rvt*predict-yes*H0*1 0.407927 -0.0580062 0.349921 -> 0.407927 -0.0580059 0.349921(R,m,v=1,0.895833,0.0939685)
  7104. RL update rl*prefer*rvt*predict-yes*H0*1*H1*13 0.592076 0.0580024 0.650079 -> 0.592076 0.0580028 0.650079(R,m,v=1,1,0)
  7105. =>WM: (13344: S1 ^operator O1905)
  7106. 953: O: O1905 (predict-yes)
  7107. --- END Decision Phase ---
  7108. --- Application Phase ---
  7109. --- Firing Productions (PE) For State At Depth 1 ---
  7110. --- Inner Elaboration Phase, active level 1 (S1) ---
  7111. Firing apply*operator
  7112. -->
  7113. (I3 ^predict-yes N953 + :O )
  7114. Firing apply*operator*complete
  7115. -->
  7116. (I3 ^predict-yes N952 - :O )
  7117. inner elaboration loop at bottom goal.
  7118. --- Change Working Memory (PE) ---
  7119. =>WM: (13345: I3 ^predict-yes N953)
  7120. <=WM: (13331: N952 ^status complete)
  7121. <=WM: (13330: I3 ^predict-yes N952)
  7122. --- Firing Productions (IE) For State At Depth 1 ---
  7123. --- Inner Elaboration Phase, active level 1 (S1) ---
  7124. Firing monitor*world
  7125. -->
  7126. I see 1 and I'm going to do: predict-yes inner elaboration loop at bottom goal.
  7127. --- Change Working Memory (IE) ---
  7128. --- END Application Phase ---
  7129. --- Output Phase ---
  7130. ENV: Agent did: predict-yes for direction R in state State-A
  7131. In State-A moving R
  7132. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  7133. predict error 0
  7134. dir: dir isR
  7135. --- END Output Phase ---
  7136. \-/--- Input Phase ---
  7137. =>WM: (13349: I2 ^dir R)
  7138. =>WM: (13348: I2 ^reward 1)
  7139. =>WM: (13347: I2 ^see 1)
  7140. =>WM: (13346: N953 ^status complete)
  7141. <=WM: (13334: I2 ^dir R)
  7142. <=WM: (13333: I2 ^reward 1)
  7143. <=WM: (13332: I2 ^see 1)
  7144. =>WM: (13350: I2 ^level-1 R1-root)
  7145. <=WM: (13335: I2 ^level-1 L1-root)
  7146. --- END Input Phase ---
  7147. --- Proposal Phase ---
  7148. --- Inner Elaboration Phase, active level 1 (S1) ---
  7149. Firing rl*prefer*rvt*predict-yes*H0*5*H1*10
  7150. -->
  7151. (S1 ^operator O1905 = -0.2099933006338622)
  7152. Firing prefer*rvt*predict-yes*H0*5*H1
  7153. -->
  7154. Firing elaborate*copy-see-to-output-link
  7155. -->
  7156. (I3 ^see 1 +)
  7157. Firing elaborate*reward*based*on*reward
  7158. -->
  7159. (R957 ^value 1 +)
  7160. (R1 ^reward R957 +)
  7161. Firing propose*predict-yes
  7162. -->
  7163. (O1907 ^name predict-yes +)
  7164. (S1 ^operator O1907 +)
  7165. Firing propose*predict-no
  7166. -->
  7167. (O1908 ^name predict-no +)
  7168. (S1 ^operator O1908 +)
  7169. Firing rl*prefer*rvt*predict-no*H0*6
  7170. -->
  7171. (S1 ^operator O1906 = 0.9993817332271659)
  7172. Firing rl*prefer*rvt*predict-yes*H0*5
  7173. -->
  7174. (S1 ^operator O1905 = 0.2239652448743312)
  7175. Firing prefer*rvt*predict-yes*H0
  7176. -->
  7177. Firing prefer*rvt*predict-no*H0
  7178. -->
  7179. Firing elaborate*copy-dir-to-output-link
  7180. -->
  7181. (I3 ^dir R +)
  7182. inner elaboration loop at bottom goal.
  7183. Retracting elaborate*copy-see-to-output-link
  7184. -->
  7185. (I3 ^see 1 +)
  7186. Retracting propose*predict-no
  7187. -->
  7188. (O1906 ^name predict-no +)
  7189. (S1 ^operator O1906 +)
  7190. Retracting propose*predict-yes
  7191. -->
  7192. (O1905 ^name predict-yes +)
  7193. (S1 ^operator O1905 +)
  7194. Retracting elaborate*reward*based*on*reward
  7195. -->
  7196. (R956 ^value 1 +)
  7197. (R1 ^reward R956 +)
  7198. Retracting elaborate*copy-dir-to-output-link
  7199. -->
  7200. (I3 ^dir R +)
  7201. Retracting rl*prefer*rvt*predict-no*H0*6
  7202. -->
  7203. (S1 ^operator O1906 = 0.9993817332271659)
  7204. Retracting rl*prefer*rvt*predict-yes*H0*5*H1*9
  7205. -->
  7206. (S1 ^operator O1905 = 0.776301464817437)
  7207. Retracting rl*prefer*rvt*predict-yes*H0*5
  7208. -->
  7209. (S1 ^operator O1905 = 0.2239652448743312)
  7210. =>WM: (13356: S1 ^operator O1908 +)
  7211. =>WM: (13355: S1 ^operator O1907 +)
  7212. =>WM: (13354: O1908 ^name predict-no)
  7213. =>WM: (13353: O1907 ^name predict-yes)
  7214. =>WM: (13352: R957 ^value 1)
  7215. =>WM: (13351: R1 ^reward R957)
  7216. <=WM: (13342: S1 ^operator O1905 +)
  7217. <=WM: (13344: S1 ^operator O1905)
  7218. <=WM: (13343: S1 ^operator O1906 +)
  7219. <=WM: (13337: R1 ^reward R956)
  7220. <=WM: (13340: O1906 ^name predict-no)
  7221. <=WM: (13339: O1905 ^name predict-yes)
  7222. <=WM: (13338: R956 ^value 1)
  7223. --- Inner Elaboration Phase, active level 1 (S1) ---
  7224. Firing prefer*rvt*predict-yes*H0
  7225. -->
  7226. Firing rl*prefer*rvt*predict-yes*H0*5
  7227. -->
  7228. (S1 ^operator O1907 = 0.2239652448743312)
  7229. Firing prefer*rvt*predict-yes*H0*5*H1
  7230. -->
  7231. Firing rl*prefer*rvt*predict-yes*H0*5*H1*10
  7232. -->
  7233. (S1 ^operator O1907 = -0.2099933006338622)
  7234. Firing prefer*rvt*predict-no*H0
  7235. -->
  7236. Firing rl*prefer*rvt*predict-no*H0*6
  7237. -->
  7238. (S1 ^operator O1908 = 0.9993817332271659)
  7239. inner elaboration loop at bottom goal.
  7240. Retracting rl*prefer*rvt*predict-no*H0*6
  7241. -->
  7242. (S1 ^operator O1906 = 0.9993817332271659)
  7243. Retracting rl*prefer*rvt*predict-yes*H0*5
  7244. -->
  7245. (S1 ^operator O1905 = 0.2239652448743312)
  7246. Retracting rl*prefer*rvt*predict-yes*H0*5*H1*10
  7247. -->
  7248. (S1 ^operator O1905 = -0.2099933006338622)
  7249. --- END Proposal Phase ---
  7250. --- Decision Phase ---
  7251. RL update rl*prefer*rvt*predict-yes*H0*5 0.553576 -0.329611 0.223965 -> 0.553554 -0.329611 0.223943(R,m,v=1,0.85034,0.128133)
  7252. RL update rl*prefer*rvt*predict-yes*H0*5*H1*9 0.44669 0.329612 0.776301 -> 0.446664 0.329612 0.776275(R,m,v=1,1,0)
  7253. =>WM: (13357: S1 ^operator O1908)
  7254. 954: O: O1908 (predict-no)
  7255. --- END Decision Phase ---
  7256. --- Application Phase ---
  7257. --- Firing Productions (PE) For State At Depth 1 ---
  7258. --- Inner Elaboration Phase, active level 1 (S1) ---
  7259. Firing apply*operator
  7260. -->
  7261. (I3 ^predict-no N954 + :O )
  7262. Firing apply*operator*complete
  7263. -->
  7264. (I3 ^predict-yes N953 - :O )
  7265. inner elaboration loop at bottom goal.
  7266. --- Change Working Memory (PE) ---
  7267. =>WM: (13358: I3 ^predict-no N954)
  7268. <=WM: (13346: N953 ^status complete)
  7269. <=WM: (13345: I3 ^predict-yes N953)
  7270. --- Firing Productions (IE) For State At Depth 1 ---
  7271. --- Inner Elaboration Phase, active level 1 (S1) ---
  7272. Firing monitor*world
  7273. -->
  7274. I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
  7275. --- Change Working Memory (IE) ---
  7276. --- END Application Phase ---
  7277. --- Output Phase ---
  7278. ENV: Agent did: predict-no for direction R in state State-B
  7279. In State-B moving R
  7280. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  7281. predict error 0
  7282. dir: dir isU
  7283. --- END Output Phase ---
  7284. |\--- Input Phase ---
  7285. =>WM: (13362: I2 ^dir U)
  7286. =>WM: (13361: I2 ^reward 1)
  7287. =>WM: (13360: I2 ^see 0)
  7288. =>WM: (13359: N954 ^status complete)
  7289. <=WM: (13349: I2 ^dir R)
  7290. <=WM: (13348: I2 ^reward 1)
  7291. <=WM: (13347: I2 ^see 1)
  7292. =>WM: (13363: I2 ^level-1 R0-root)
  7293. <=WM: (13350: I2 ^level-1 R1-root)
  7294. --- END Input Phase ---
  7295. --- Proposal Phase ---
  7296. --- Inner Elaboration Phase, active level 1 (S1) ---
  7297. Firing elaborate*copy-see-to-output-link
  7298. -->
  7299. (I3 ^see 0 +)
  7300. Firing elaborate*reward*based*on*reward
  7301. -->
  7302. (R958 ^value 1 +)
  7303. (R1 ^reward R958 +)
  7304. Firing propose*predict-yes
  7305. -->
  7306. (O1909 ^name predict-yes +)
  7307. (S1 ^operator O1909 +)
  7308. Firing propose*predict-no
  7309. -->
  7310. (O1910 ^name predict-no +)
  7311. (S1 ^operator O1910 +)
  7312. Firing rl*prefer*rvt*predict-no*H0*4
  7313. -->
  7314. (S1 ^operator O1908 = 1.)
  7315. Firing rl*prefer*rvt*predict-yes*H0*3
  7316. -->
  7317. (S1 ^operator O1907 = 0.)
  7318. Firing prefer*rvt*predict-yes*H0
  7319. -->
  7320. Firing prefer*rvt*predict-no*H0
  7321. -->
  7322. Firing elaborate*copy-dir-to-output-link
  7323. -->
  7324. (I3 ^dir U +)
  7325. inner elaboration loop at bottom goal.
  7326. Retracting elaborate*copy-see-to-output-link
  7327. -->
  7328. (I3 ^see 1 +)
  7329. Retracting propose*predict-no
  7330. -->
  7331. (O1908 ^name predict-no +)
  7332. (S1 ^operator O1908 +)
  7333. Retracting propose*predict-yes
  7334. -->
  7335. (O1907 ^name predict-yes +)
  7336. (S1 ^operator O1907 +)
  7337. Retracting elaborate*reward*based*on*reward
  7338. -->
  7339. (R957 ^value 1 +)
  7340. (R1 ^reward R957 +)
  7341. Retracting elaborate*copy-dir-to-output-link
  7342. -->
  7343. (I3 ^dir R +)
  7344. Retracting rl*prefer*rvt*predict-no*H0*6
  7345. -->
  7346. (S1 ^operator O1908 = 0.9993817332271659)
  7347. Retracting rl*prefer*rvt*predict-yes*H0*5*H1*10
  7348. -->
  7349. (S1 ^operator O1907 = -0.2099933006338622)
  7350. Retracting rl*prefer*rvt*predict-yes*H0*5
  7351. -->
  7352. (S1 ^operator O1907 = 0.2239429835695002)
  7353. =>WM: (13371: S1 ^operator O1910 +)
  7354. =>WM: (13370: S1 ^operator O1909 +)
  7355. =>WM: (13369: I3 ^dir U)
  7356. =>WM: (13368: O1910 ^name predict-no)
  7357. =>WM: (13367: O1909 ^name predict-yes)
  7358. =>WM: (13366: R958 ^value 1)
  7359. =>WM: (13365: R1 ^reward R958)
  7360. =>WM: (13364: I3 ^see 0)
  7361. <=WM: (13355: S1 ^operator O1907 +)
  7362. <=WM: (13356: S1 ^operator O1908 +)
  7363. <=WM: (13357: S1 ^operator O1908)
  7364. <=WM: (13341: I3 ^dir R)
  7365. <=WM: (13351: R1 ^reward R957)
  7366. <=WM: (13336: I3 ^see 1)
  7367. <=WM: (13354: O1908 ^name predict-no)
  7368. <=WM: (13353: O1907 ^name predict-yes)
  7369. <=WM: (13352: R957 ^value 1)
  7370. --- Inner Elaboration Phase, active level 1 (S1) ---
  7371. Firing prefer*rvt*predict-yes*H0
  7372. -->
  7373. Firing rl*prefer*rvt*predict-yes*H0*3
  7374. -->
  7375. (S1 ^operator O1909 = 0.)
  7376. Firing prefer*rvt*predict-no*H0
  7377. -->
  7378. Firing rl*prefer*rvt*predict-no*H0*4
  7379. -->
  7380. (S1 ^operator O1910 = 1.)
  7381. inner elaboration loop at bottom goal.
  7382. Retracting rl*prefer*rvt*predict-no*H0*4
  7383. -->
  7384. (S1 ^operator O1908 = 1.)
  7385. Retracting rl*prefer*rvt*predict-yes*H0*3
  7386. -->
  7387. (S1 ^operator O1907 = 0.)
  7388. --- END Proposal Phase ---
  7389. --- Decision Phase ---
  7390. RL update rl*prefer*rvt*predict-no*H0*6 0.999382 0 0.999382 -> 0.999482 0 0.999482(R,m,v=1,0.858824,0.121963)
  7391. =>WM: (13372: S1 ^operator O1910)
  7392. 955: O: O1910 (predict-no)
  7393. --- END Decision Phase ---
  7394. --- Application Phase ---
  7395. --- Firing Productions (PE) For State At Depth 1 ---
  7396. --- Inner Elaboration Phase, active level 1 (S1) ---
  7397. Firing apply*operator
  7398. -->
  7399. (I3 ^predict-no N955 + :O )
  7400. Firing apply*operator*complete
  7401. -->
  7402. (I3 ^predict-no N954 - :O )
  7403. inner elaboration loop at bottom goal.
  7404. --- Change Working Memory (PE) ---
  7405. =>WM: (13373: I3 ^predict-no N955)
  7406. <=WM: (13359: N954 ^status complete)
  7407. <=WM: (13358: I3 ^predict-no N954)
  7408. --- Firing Productions (IE) For State At Depth 1 ---
  7409. --- Inner Elaboration Phase, active level 1 (S1) ---
  7410. Firing monitor*world
  7411. -->
  7412. I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
  7413. --- Change Working Memory (IE) ---
  7414. --- END Application Phase ---
  7415. --- Output Phase ---
  7416. ENV: Agent did: predict-no for direction U in state State-B
  7417. In State-B moving U
  7418. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  7419. predict error 0
  7420. dir: dir isL
  7421. --- END Output Phase ---
  7422. -/|--- Input Phase ---
  7423. =>WM: (13377: I2 ^dir L)
  7424. =>WM: (13376: I2 ^reward 1)
  7425. =>WM: (13375: I2 ^see 0)
  7426. =>WM: (13374: N955 ^status complete)
  7427. <=WM: (13362: I2 ^dir U)
  7428. <=WM: (13361: I2 ^reward 1)
  7429. <=WM: (13360: I2 ^see 0)
  7430. =>WM: (13378: I2 ^level-1 R0-root)
  7431. <=WM: (13363: I2 ^level-1 R0-root)
  7432. --- END Input Phase ---
  7433. --- Proposal Phase ---
  7434. --- Inner Elaboration Phase, active level 1 (S1) ---
  7435. Firing rl*prefer*rvt*predict-no*H0*2*H1*12
  7436. -->
  7437. (S1 ^operator O1910 = -0.1359494083332169)
  7438. Firing rl*prefer*rvt*predict-yes*H0*1*H1*13
  7439. -->
  7440. (S1 ^operator O1909 = 0.650078898339267)
  7441. Firing prefer*rvt*predict-no*H0*2*H1
  7442. -->
  7443. Firing prefer*rvt*predict-yes*H0*1*H1
  7444. -->
  7445. Firing elaborate*copy-see-to-output-link
  7446. -->
  7447. (I3 ^see 0 +)
  7448. Firing elaborate*reward*based*on*reward
  7449. -->
  7450. (R959 ^value 1 +)
  7451. (R1 ^reward R959 +)
  7452. Firing propose*predict-yes
  7453. -->
  7454. (O1911 ^name predict-yes +)
  7455. (S1 ^operator O1911 +)
  7456. Firing propose*predict-no
  7457. -->
  7458. (O1912 ^name predict-no +)
  7459. (S1 ^operator O1912 +)
  7460. Firing rl*prefer*rvt*predict-no*H0*2
  7461. -->
  7462. (S1 ^operator O1910 = 0.2381451287000689)
  7463. Firing rl*prefer*rvt*predict-yes*H0*1
  7464. -->
  7465. (S1 ^operator O1909 = 0.3499208550175523)
  7466. Firing prefer*rvt*predict-yes*H0
  7467. -->
  7468. Firing prefer*rvt*predict-no*H0
  7469. -->
  7470. Firing elaborate*copy-dir-to-output-link
  7471. -->
  7472. (I3 ^dir L +)
  7473. inner elaboration loop at bottom goal.
  7474. Retracting elaborate*copy-see-to-output-link
  7475. -->
  7476. (I3 ^see 0 +)
  7477. Retracting propose*predict-no
  7478. -->
  7479. (O1910 ^name predict-no +)
  7480. (S1 ^operator O1910 +)
  7481. Retracting propose*predict-yes
  7482. -->
  7483. (O1909 ^name predict-yes +)
  7484. (S1 ^operator O1909 +)
  7485. Retracting elaborate*reward*based*on*reward
  7486. -->
  7487. (R958 ^value 1 +)
  7488. (R1 ^reward R958 +)
  7489. Retracting elaborate*copy-dir-to-output-link
  7490. -->
  7491. (I3 ^dir U +)
  7492. Retracting rl*prefer*rvt*predict-no*H0*4
  7493. -->
  7494. (S1 ^operator O1910 = 1.)
  7495. Retracting rl*prefer*rvt*predict-yes*H0*3
  7496. -->
  7497. (S1 ^operator O1909 = 0.)
  7498. =>WM: (13385: S1 ^operator O1912 +)
  7499. =>WM: (13384: S1 ^operator O1911 +)
  7500. =>WM: (13383: I3 ^dir L)
  7501. =>WM: (13382: O1912 ^name predict-no)
  7502. =>WM: (13381: O1911 ^name predict-yes)
  7503. =>WM: (13380: R959 ^value 1)
  7504. =>WM: (13379: R1 ^reward R959)
  7505. <=WM: (13370: S1 ^operator O1909 +)
  7506. <=WM: (13371: S1 ^operator O1910 +)
  7507. <=WM: (13372: S1 ^operator O1910)
  7508. <=WM: (13369: I3 ^dir U)
  7509. <=WM: (13365: R1 ^reward R958)
  7510. <=WM: (13368: O1910 ^name predict-no)
  7511. <=WM: (13367: O1909 ^name predict-yes)
  7512. <=WM: (13366: R958 ^value 1)
  7513. --- Inner Elaboration Phase, active level 1 (S1) ---
  7514. Firing prefer*rvt*predict-yes*H0
  7515. -->
  7516. Firing rl*prefer*rvt*predict-yes*H0*1*H1*13
  7517. -->
  7518. (S1 ^operator O1911 = 0.650078898339267)
  7519. Firing rl*prefer*rvt*predict-yes*H0*1
  7520. -->
  7521. (S1 ^operator O1911 = 0.3499208550175523)
  7522. Firing prefer*rvt*predict-yes*H0*1*H1
  7523. -->
  7524. Firing prefer*rvt*predict-no*H0
  7525. -->
  7526. Firing rl*prefer*rvt*predict-no*H0*2*H1*12
  7527. -->
  7528. (S1 ^operator O1912 = -0.1359494083332169)
  7529. Firing rl*prefer*rvt*predict-no*H0*2
  7530. -->
  7531. (S1 ^operator O1912 = 0.2381451287000689)
  7532. Firing prefer*rvt*predict-no*H0*2*H1
  7533. -->
  7534. inner elaboration loop at bottom goal.
  7535. Retracting rl*prefer*rvt*predict-no*H0*2
  7536. -->
  7537. (S1 ^operator O1910 = 0.2381451287000689)
  7538. Retracting rl*prefer*rvt*predict-no*H0*2*H1*12
  7539. -->
  7540. (S1 ^operator O1910 = -0.1359494083332169)
  7541. Retracting rl*prefer*rvt*predict-yes*H0*1
  7542. -->
  7543. (S1 ^operator O1909 = 0.3499208550175523)
  7544. Retracting rl*prefer*rvt*predict-yes*H0*1*H1*13
  7545. -->
  7546. (S1 ^operator O1909 = 0.650078898339267)
  7547. --- END Proposal Phase ---
  7548. --- Decision Phase ---
  7549. RL update rl*prefer*rvt*predict-no*H0*4 1 0 1 -> 1 0 1(R,m,v=1,1,0)
  7550. =>WM: (13386: S1 ^operator O1911)
  7551. 956: O: O1911 (predict-yes)
  7552. --- END Decision Phase ---
  7553. --- Application Phase ---
  7554. --- Firing Productions (PE) For State At Depth 1 ---
  7555. --- Inner Elaboration Phase, active level 1 (S1) ---
  7556. Firing apply*operator
  7557. -->
  7558. (I3 ^predict-yes N956 + :O )
  7559. Firing apply*operator*complete
  7560. -->
  7561. (I3 ^predict-no N955 - :O )
  7562. inner elaboration loop at bottom goal.
  7563. --- Change Working Memory (PE) ---
  7564. =>WM: (13387: I3 ^predict-yes N956)
  7565. <=WM: (13374: N955 ^status complete)
  7566. <=WM: (13373: I3 ^predict-no N955)
  7567. --- Firing Productions (IE) For State At Depth 1 ---
  7568. --- Inner Elaboration Phase, active level 1 (S1) ---
  7569. Firing monitor*world
  7570. -->
  7571. I see 1 and I'm going to do: predict-yes inner elaboration loop at bottom goal.
  7572. --- Change Working Memory (IE) ---
  7573. --- END Application Phase ---
  7574. --- Output Phase ---
  7575. ENV: Agent did: predict-yes for direction L in state State-B
  7576. In State-B moving L
  7577. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  7578. predict error 0
  7579. dir: dir isL
  7580. --- END Output Phase ---
  7581. \-/--- Input Phase ---
  7582. =>WM: (13391: I2 ^dir L)
  7583. =>WM: (13390: I2 ^reward 1)
  7584. =>WM: (13389: I2 ^see 1)
  7585. =>WM: (13388: N956 ^status complete)
  7586. <=WM: (13377: I2 ^dir L)
  7587. <=WM: (13376: I2 ^reward 1)
  7588. <=WM: (13375: I2 ^see 0)
  7589. =>WM: (13392: I2 ^level-1 L1-root)
  7590. <=WM: (13378: I2 ^level-1 R0-root)
  7591. --- END Input Phase ---
  7592. --- Proposal Phase ---
  7593. --- Inner Elaboration Phase, active level 1 (S1) ---
  7594. Firing rl*prefer*rvt*predict-no*H0*2*H1*14
  7595. -->
  7596. (S1 ^operator O1912 = 0.7619030205000717)
  7597. Firing rl*prefer*rvt*predict-yes*H0*1*H1*15
  7598. -->
  7599. (S1 ^operator O1911 = -0.2915346922215271)
  7600. Firing prefer*rvt*predict-no*H0*2*H1
  7601. -->
  7602. Firing prefer*rvt*predict-yes*H0*1*H1
  7603. -->
  7604. Firing elaborate*copy-see-to-output-link
  7605. -->
  7606. (I3 ^see 1 +)
  7607. Firing elaborate*reward*based*on*reward
  7608. -->
  7609. (R960 ^value 1 +)
  7610. (R1 ^reward R960 +)
  7611. Firing propose*predict-yes
  7612. -->
  7613. (O1913 ^name predict-yes +)
  7614. (S1 ^operator O1913 +)
  7615. Firing propose*predict-no
  7616. -->
  7617. (O1914 ^name predict-no +)
  7618. (S1 ^operator O1914 +)
  7619. Firing rl*prefer*rvt*predict-no*H0*2
  7620. -->
  7621. (S1 ^operator O1912 = 0.2381451287000689)
  7622. Firing rl*prefer*rvt*predict-yes*H0*1
  7623. -->
  7624. (S1 ^operator O1911 = 0.3499208550175523)
  7625. Firing prefer*rvt*predict-yes*H0
  7626. -->
  7627. Firing prefer*rvt*predict-no*H0
  7628. -->
  7629. Firing elaborate*copy-dir-to-output-link
  7630. -->
  7631. (I3 ^dir L +)
  7632. inner elaboration loop at bottom goal.
  7633. Retracting elaborate*copy-see-to-output-link
  7634. -->
  7635. (I3 ^see 0 +)
  7636. Retracting propose*predict-no
  7637. -->
  7638. (O1912 ^name predict-no +)
  7639. (S1 ^operator O1912 +)
  7640. Retracting propose*predict-yes
  7641. -->
  7642. (O1911 ^name predict-yes +)
  7643. (S1 ^operator O1911 +)
  7644. Retracting elaborate*reward*based*on*reward
  7645. -->
  7646. (R959 ^value 1 +)
  7647. (R1 ^reward R959 +)
  7648. Retracting elaborate*copy-dir-to-output-link
  7649. -->
  7650. (I3 ^dir L +)
  7651. Retracting rl*prefer*rvt*predict-no*H0*2
  7652. -->
  7653. (S1 ^operator O1912 = 0.2381451287000689)
  7654. Retracting rl*prefer*rvt*predict-no*H0*2*H1*12
  7655. -->
  7656. (S1 ^operator O1912 = -0.1359494083332169)
  7657. Retracting rl*prefer*rvt*predict-yes*H0*1
  7658. -->
  7659. (S1 ^operator O1911 = 0.3499208550175523)
  7660. Retracting rl*prefer*rvt*predict-yes*H0*1*H1*13
  7661. -->
  7662. (S1 ^operator O1911 = 0.650078898339267)
  7663. =>WM: (13399: S1 ^operator O1914 +)
  7664. =>WM: (13398: S1 ^operator O1913 +)
  7665. =>WM: (13397: O1914 ^name predict-no)
  7666. =>WM: (13396: O1913 ^name predict-yes)
  7667. =>WM: (13395: R960 ^value 1)
  7668. =>WM: (13394: R1 ^reward R960)
  7669. =>WM: (13393: I3 ^see 1)
  7670. <=WM: (13384: S1 ^operator O1911 +)
  7671. <=WM: (13386: S1 ^operator O1911)
  7672. <=WM: (13385: S1 ^operator O1912 +)
  7673. <=WM: (13379: R1 ^reward R959)
  7674. <=WM: (13364: I3 ^see 0)
  7675. <=WM: (13382: O1912 ^name predict-no)
  7676. <=WM: (13381: O1911 ^name predict-yes)
  7677. <=WM: (13380: R959 ^value 1)
  7678. --- Inner Elaboration Phase, active level 1 (S1) ---
  7679. Firing prefer*rvt*predict-yes*H0
  7680. -->
  7681. Firing rl*prefer*rvt*predict-yes*H0*1
  7682. -->
  7683. (S1 ^operator O1913 = 0.3499208550175523)
  7684. Firing prefer*rvt*predict-yes*H0*1*H1
  7685. -->
  7686. Firing rl*prefer*rvt*predict-yes*H0*1*H1*15
  7687. -->
  7688. (S1 ^operator O1913 = -0.2915346922215271)
  7689. Firing prefer*rvt*predict-no*H0
  7690. -->
  7691. Firing rl*prefer*rvt*predict-no*H0*2
  7692. -->
  7693. (S1 ^operator O1914 = 0.2381451287000689)
  7694. Firing prefer*rvt*predict-no*H0*2*H1
  7695. -->
  7696. Firing rl*prefer*rvt*predict-no*H0*2*H1*14
  7697. -->
  7698. (S1 ^operator O1914 = 0.7619030205000717)
  7699. inner elaboration loop at bottom goal.
  7700. Retracting rl*prefer*rvt*predict-no*H0*2
  7701. -->
  7702. (S1 ^operator O1912 = 0.2381451287000689)
  7703. Retracting rl*prefer*rvt*predict-no*H0*2*H1*14
  7704. -->
  7705. (S1 ^operator O1912 = 0.7619030205000717)
  7706. Retracting rl*prefer*rvt*predict-yes*H0*1
  7707. -->
  7708. (S1 ^operator O1911 = 0.3499208550175523)
  7709. Retracting rl*prefer*rvt*predict-yes*H0*1*H1*15
  7710. -->
  7711. (S1 ^operator O1911 = -0.2915346922215271)
  7712. --- END Proposal Phase ---
  7713. --- Decision Phase ---
  7714. RL update rl*prefer*rvt*predict-yes*H0*1 0.407927 -0.0580059 0.349921 -> 0.407926 -0.0580056 0.349921(R,m,v=1,0.896552,0.0933908)
  7715. RL update rl*prefer*rvt*predict-yes*H0*1*H1*13 0.592076 0.0580028 0.650079 -> 0.592076 0.0580031 0.650079(R,m,v=1,1,0)
  7716. =>WM: (13400: S1 ^operator O1914)
  7717. 957: O: O1914 (predict-no)
  7718. --- END Decision Phase ---
  7719. --- Application Phase ---
  7720. --- Firing Productions (PE) For State At Depth 1 ---
  7721. --- Inner Elaboration Phase, active level 1 (S1) ---
  7722. Firing apply*operator
  7723. -->
  7724. (I3 ^predict-no N957 + :O )
  7725. Firing apply*operator*complete
  7726. -->
  7727. (I3 ^predict-yes N956 - :O )
  7728. inner elaboration loop at bottom goal.
  7729. --- Change Working Memory (PE) ---
  7730. =>WM: (13401: I3 ^predict-no N957)
  7731. <=WM: (13388: N956 ^status complete)
  7732. <=WM: (13387: I3 ^predict-yes N956)
  7733. --- Firing Productions (IE) For State At Depth 1 ---
  7734. --- Inner Elaboration Phase, active level 1 (S1) ---
  7735. Firing monitor*world
  7736. -->
  7737. I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
  7738. --- Change Working Memory (IE) ---
  7739. --- END Application Phase ---
  7740. --- Output Phase ---
  7741. ENV: Agent did: predict-no for direction L in state State-A
  7742. In State-A moving L
  7743. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  7744. predict error 0
  7745. dir: dir isL
  7746. --- END Output Phase ---
  7747. |\---- Input Phase ---
  7748. =>WM: (13405: I2 ^dir L)
  7749. =>WM: (13404: I2 ^reward 1)
  7750. =>WM: (13403: I2 ^see 0)
  7751. =>WM: (13402: N957 ^status complete)
  7752. <=WM: (13391: I2 ^dir L)
  7753. <=WM: (13390: I2 ^reward 1)
  7754. <=WM: (13389: I2 ^see 1)
  7755. =>WM: (13406: I2 ^level-1 L0-root)
  7756. <=WM: (13392: I2 ^level-1 L1-root)
  7757. --- END Input Phase ---
  7758. --- Proposal Phase ---
  7759. --- Inner Elaboration Phase, active level 1 (S1) ---
  7760. Firing rl*prefer*rvt*predict-no*H0*2*H1*17
  7761. -->
  7762. (S1 ^operator O1914 = 0.7618095533793801)
  7763. Firing rl*prefer*rvt*predict-yes*H0*1*H1*18
  7764. -->
  7765. (S1 ^operator O1913 = -0.2828328840504906)
  7766. Firing prefer*rvt*predict-no*H0*2*H1
  7767. -->
  7768. Firing prefer*rvt*predict-yes*H0*1*H1
  7769. -->
  7770. Firing elaborate*copy-see-to-output-link
  7771. -->
  7772. (I3 ^see 0 +)
  7773. Firing elaborate*reward*based*on*reward
  7774. -->
  7775. (R961 ^value 1 +)
  7776. (R1 ^reward R961 +)
  7777. Firing propose*predict-yes
  7778. -->
  7779. (O1915 ^name predict-yes +)
  7780. (S1 ^operator O1915 +)
  7781. Firing propose*predict-no
  7782. -->
  7783. (O1916 ^name predict-no +)
  7784. (S1 ^operator O1916 +)
  7785. Firing rl*prefer*rvt*predict-no*H0*2
  7786. -->
  7787. (S1 ^operator O1914 = 0.2381451287000689)
  7788. Firing rl*prefer*rvt*predict-yes*H0*1
  7789. -->
  7790. (S1 ^operator O1913 = 0.3499208756511618)
  7791. Firing prefer*rvt*predict-yes*H0
  7792. -->
  7793. Firing prefer*rvt*predict-no*H0
  7794. -->
  7795. Firing elaborate*copy-dir-to-output-link
  7796. -->
  7797. (I3 ^dir L +)
  7798. inner elaboration loop at bottom goal.
  7799. Retracting elaborate*copy-see-to-output-link
  7800. -->
  7801. (I3 ^see 1 +)
  7802. Retracting propose*predict-no
  7803. -->
  7804. (O1914 ^name predict-no +)
  7805. (S1 ^operator O1914 +)
  7806. Retracting propose*predict-yes
  7807. -->
  7808. (O1913 ^name predict-yes +)
  7809. (S1 ^operator O1913 +)
  7810. Retracting elaborate*reward*based*on*reward
  7811. -->
  7812. (R960 ^value 1 +)
  7813. (R1 ^reward R960 +)
  7814. Retracting elaborate*copy-dir-to-output-link
  7815. -->
  7816. (I3 ^dir L +)
  7817. Retracting rl*prefer*rvt*predict-no*H0*2*H1*14
  7818. -->
  7819. (S1 ^operator O1914 = 0.7619030205000717)
  7820. Retracting rl*prefer*rvt*predict-no*H0*2
  7821. -->
  7822. (S1 ^operator O1914 = 0.2381451287000689)
  7823. Retracting rl*prefer*rvt*predict-yes*H0*1*H1*15
  7824. -->
  7825. (S1 ^operator O1913 = -0.2915346922215271)
  7826. Retracting rl*prefer*rvt*predict-yes*H0*1
  7827. -->
  7828. (S1 ^operator O1913 = 0.3499208756511618)
  7829. =>WM: (13413: S1 ^operator O1916 +)
  7830. =>WM: (13412: S1 ^operator O1915 +)
  7831. =>WM: (13411: O1916 ^name predict-no)
  7832. =>WM: (13410: O1915 ^name predict-yes)
  7833. =>WM: (13409: R961 ^value 1)
  7834. =>WM: (13408: R1 ^reward R961)
  7835. =>WM: (13407: I3 ^see 0)
  7836. <=WM: (13398: S1 ^operator O1913 +)
  7837. <=WM: (13399: S1 ^operator O1914 +)
  7838. <=WM: (13400: S1 ^operator O1914)
  7839. <=WM: (13394: R1 ^reward R960)
  7840. <=WM: (13393: I3 ^see 1)
  7841. <=WM: (13397: O1914 ^name predict-no)
  7842. <=WM: (13396: O1913 ^name predict-yes)
  7843. <=WM: (13395: R960 ^value 1)
  7844. --- Inner Elaboration Phase, active level 1 (S1) ---
  7845. Firing prefer*rvt*predict-yes*H0
  7846. -->
  7847. Firing rl*prefer*rvt*predict-yes*H0*1
  7848. -->
  7849. (S1 ^operator O1915 = 0.3499208756511618)
  7850. Firing prefer*rvt*predict-yes*H0*1*H1
  7851. -->
  7852. Firing rl*prefer*rvt*predict-yes*H0*1*H1*18
  7853. -->
  7854. (S1 ^operator O1915 = -0.2828328840504906)
  7855. Firing prefer*rvt*predict-no*H0
  7856. -->
  7857. Firing rl*prefer*rvt*predict-no*H0*2
  7858. -->
  7859. (S1 ^operator O1916 = 0.2381451287000689)
  7860. Firing prefer*rvt*predict-no*H0*2*H1
  7861. -->
  7862. Firing rl*prefer*rvt*predict-no*H0*2*H1*17
  7863. -->
  7864. (S1 ^operator O1916 = 0.7618095533793801)
  7865. inner elaboration loop at bottom goal.
  7866. Retracting rl*prefer*rvt*predict-no*H0*2
  7867. -->
  7868. (S1 ^operator O1914 = 0.2381451287000689)
  7869. Retracting rl*prefer*rvt*predict-no*H0*2*H1*17
  7870. -->
  7871. (S1 ^operator O1914 = 0.7618095533793801)
  7872. Retracting rl*prefer*rvt*predict-yes*H0*1
  7873. -->
  7874. (S1 ^operator O1913 = 0.3499208756511618)
  7875. Retracting rl*prefer*rvt*predict-yes*H0*1*H1*18
  7876. -->
  7877. (S1 ^operator O1913 = -0.2828328840504906)
  7878. --- END Proposal Phase ---
  7879. --- Decision Phase ---
  7880. RL update rl*prefer*rvt*predict-no*H0*2 0.569329 -0.331184 0.238145 -> 0.569322 -0.331181 0.238141(R,m,v=1,0.880503,0.105883)
  7881. RL update rl*prefer*rvt*predict-no*H0*2*H1*14 0.430754 0.331149 0.761903 -> 0.430746 0.331153 0.761898(R,m,v=1,1,0)
  7882. =>WM: (13414: S1 ^operator O1916)
  7883. 958: O: O1916 (predict-no)
  7884. --- END Decision Phase ---
  7885. --- Application Phase ---
  7886. --- Firing Productions (PE) For State At Depth 1 ---
  7887. --- Inner Elaboration Phase, active level 1 (S1) ---
  7888. Firing apply*operator
  7889. -->
  7890. (I3 ^predict-no N958 + :O )
  7891. Firing apply*operator*complete
  7892. -->
  7893. (I3 ^predict-no N957 - :O )
  7894. inner elaboration loop at bottom goal.
  7895. --- Change Working Memory (PE) ---
  7896. =>WM: (13415: I3 ^predict-no N958)
  7897. <=WM: (13402: N957 ^status complete)
  7898. <=WM: (13401: I3 ^predict-no N957)
  7899. --- Firing Productions (IE) For State At Depth 1 ---
  7900. --- Inner Elaboration Phase, active level 1 (S1) ---
  7901. Firing monitor*world
  7902. -->
  7903. I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
  7904. --- Change Working Memory (IE) ---
  7905. --- END Application Phase ---
  7906. --- Output Phase ---
  7907. ENV: Agent did: predict-no for direction L in state State-A
  7908. In State-A moving L
  7909. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  7910. predict error 0
  7911. dir: dir isR
  7912. --- END Output Phase ---
  7913. /|\---- Input Phase ---
  7914. =>WM: (13419: I2 ^dir R)
  7915. =>WM: (13418: I2 ^reward 1)
  7916. =>WM: (13417: I2 ^see 0)
  7917. =>WM: (13416: N958 ^status complete)
  7918. <=WM: (13405: I2 ^dir L)
  7919. <=WM: (13404: I2 ^reward 1)
  7920. <=WM: (13403: I2 ^see 0)
  7921. =>WM: (13420: I2 ^level-1 L0-root)
  7922. <=WM: (13406: I2 ^level-1 L0-root)
  7923. --- END Input Phase ---
  7924. --- Proposal Phase ---
  7925. --- Inner Elaboration Phase, active level 1 (S1) ---
  7926. Firing rl*prefer*rvt*predict-yes*H0*5*H1*16
  7927. -->
  7928. (S1 ^operator O1915 = 0.7757627104044436)
  7929. Firing prefer*rvt*predict-yes*H0*5*H1
  7930. -->
  7931. Firing elaborate*copy-see-to-output-link
  7932. -->
  7933. (I3 ^see 0 +)
  7934. Firing elaborate*reward*based*on*reward
  7935. -->
  7936. (R962 ^value 1 +)
  7937. (R1 ^reward R962 +)
  7938. Firing propose*predict-yes
  7939. -->
  7940. (O1917 ^name predict-yes +)
  7941. (S1 ^operator O1917 +)
  7942. Firing propose*predict-no
  7943. -->
  7944. (O1918 ^name predict-no +)
  7945. (S1 ^operator O1918 +)
  7946. Firing rl*prefer*rvt*predict-no*H0*6
  7947. -->
  7948. (S1 ^operator O1916 = 0.9994824970933811)
  7949. Firing rl*prefer*rvt*predict-yes*H0*5
  7950. -->
  7951. (S1 ^operator O1915 = 0.2239429835695002)
  7952. Firing prefer*rvt*predict-yes*H0
  7953. -->
  7954. Firing prefer*rvt*predict-no*H0
  7955. -->
  7956. Firing elaborate*copy-dir-to-output-link
  7957. -->
  7958. (I3 ^dir R +)
  7959. inner elaboration loop at bottom goal.
  7960. Retracting elaborate*copy-see-to-output-link
  7961. -->
  7962. (I3 ^see 0 +)
  7963. Retracting propose*predict-no
  7964. -->
  7965. (O1916 ^name predict-no +)
  7966. (S1 ^operator O1916 +)
  7967. Retracting propose*predict-yes
  7968. -->
  7969. (O1915 ^name predict-yes +)
  7970. (S1 ^operator O1915 +)
  7971. Retracting elaborate*reward*based*on*reward
  7972. -->
  7973. (R961 ^value 1 +)
  7974. (R1 ^reward R961 +)
  7975. Retracting elaborate*copy-dir-to-output-link
  7976. -->
  7977. (I3 ^dir L +)
  7978. Retracting rl*prefer*rvt*predict-no*H0*2*H1*17
  7979. -->
  7980. (S1 ^operator O1916 = 0.7618095533793801)
  7981. Retracting rl*prefer*rvt*predict-no*H0*2
  7982. -->
  7983. (S1 ^operator O1916 = 0.2381411618224798)
  7984. Retracting rl*prefer*rvt*predict-yes*H0*1*H1*18
  7985. -->
  7986. (S1 ^operator O1915 = -0.2828328840504906)
  7987. Retracting rl*prefer*rvt*predict-yes*H0*1
  7988. -->
  7989. (S1 ^operator O1915 = 0.3499208756511618)
  7990. =>WM: (13427: S1 ^operator O1918 +)
  7991. =>WM: (13426: S1 ^operator O1917 +)
  7992. =>WM: (13425: I3 ^dir R)
  7993. =>WM: (13424: O1918 ^name predict-no)
  7994. =>WM: (13423: O1917 ^name predict-yes)
  7995. =>WM: (13422: R962 ^value 1)
  7996. =>WM: (13421: R1 ^reward R962)
  7997. <=WM: (13412: S1 ^operator O1915 +)
  7998. <=WM: (13413: S1 ^operator O1916 +)
  7999. <=WM: (13414: S1 ^operator O1916)
  8000. <=WM: (13383: I3 ^dir L)
  8001. <=WM: (13408: R1 ^reward R961)
  8002. <=WM: (13411: O1916 ^name predict-no)
  8003. <=WM: (13410: O1915 ^name predict-yes)
  8004. <=WM: (13409: R961 ^value 1)
  8005. --- Inner Elaboration Phase, active level 1 (S1) ---
  8006. Firing prefer*rvt*predict-yes*H0
  8007. -->
  8008. Firing rl*prefer*rvt*predict-yes*H0*5*H1*16
  8009. -->
  8010. (S1 ^operator O1917 = 0.7757627104044436)
  8011. Firing rl*prefer*rvt*predict-yes*H0*5
  8012. -->
  8013. (S1 ^operator O1917 = 0.2239429835695002)
  8014. Firing prefer*rvt*predict-yes*H0*5*H1
  8015. -->
  8016. Firing prefer*rvt*predict-no*H0
  8017. -->
  8018. Firing rl*prefer*rvt*predict-no*H0*6
  8019. -->
  8020. (S1 ^operator O1918 = 0.9994824970933811)
  8021. inner elaboration loop at bottom goal.
  8022. Retracting rl*prefer*rvt*predict-no*H0*6
  8023. -->
  8024. (S1 ^operator O1916 = 0.9994824970933811)
  8025. Retracting rl*prefer*rvt*predict-yes*H0*5
  8026. -->
  8027. (S1 ^operator O1915 = 0.2239429835695002)
  8028. Retracting rl*prefer*rvt*predict-yes*H0*5*H1*16
  8029. -->
  8030. (S1 ^operator O1915 = 0.7757627104044436)
  8031. --- END Proposal Phase ---
  8032. --- Decision Phase ---
  8033. RL update rl*prefer*rvt*predict-no*H0*2 0.569322 -0.331181 0.238141 -> 0.569329 -0.331184 0.238145(R,m,v=1,0.88125,0.105307)
  8034. RL update rl*prefer*rvt*predict-no*H0*2*H1*17 0.430594 0.331216 0.76181 -> 0.430602 0.331212 0.761814(R,m,v=1,1,0)
  8035. =>WM: (13428: S1 ^operator O1917)
  8036. 959: O: O1917 (predict-yes)
  8037. --- END Decision Phase ---
  8038. --- Application Phase ---
  8039. --- Firing Productions (PE) For State At Depth 1 ---
  8040. --- Inner Elaboration Phase, active level 1 (S1) ---
  8041. Firing apply*operator
  8042. -->
  8043. (I3 ^predict-yes N959 + :O )
  8044. Firing apply*operator*complete
  8045. -->
  8046. (I3 ^predict-no N958 - :O )
  8047. inner elaboration loop at bottom goal.
  8048. --- Change Working Memory (PE) ---
  8049. =>WM: (13429: I3 ^predict-yes N959)
  8050. <=WM: (13416: N958 ^status complete)
  8051. <=WM: (13415: I3 ^predict-no N958)
  8052. --- Firing Productions (IE) For State At Depth 1 ---
  8053. --- Inner Elaboration Phase, active level 1 (S1) ---
  8054. Firing monitor*world
  8055. -->
  8056. I see 1 and I'm going to do: predict-yes inner elaboration loop at bottom goal.
  8057. --- Change Working Memory (IE) ---
  8058. --- END Application Phase ---
  8059. --- Output Phase ---
  8060. ENV: Agent did: predict-yes for direction R in state State-A
  8061. In State-A moving R
  8062. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  8063. predict error 0
  8064. dir: dir isU
  8065. --- END Output Phase ---
  8066. /|--- Input Phase ---
  8067. =>WM: (13433: I2 ^dir U)
  8068. =>WM: (13432: I2 ^reward 1)
  8069. =>WM: (13431: I2 ^see 1)
  8070. =>WM: (13430: N959 ^status complete)
  8071. <=WM: (13419: I2 ^dir R)
  8072. <=WM: (13418: I2 ^reward 1)
  8073. <=WM: (13417: I2 ^see 0)
  8074. =>WM: (13434: I2 ^level-1 R1-root)
  8075. <=WM: (13420: I2 ^level-1 L0-root)
  8076. --- END Input Phase ---
  8077. --- Proposal Phase ---
  8078. --- Inner Elaboration Phase, active level 1 (S1) ---
  8079. Firing elaborate*copy-see-to-output-link
  8080. -->
  8081. (I3 ^see 1 +)
  8082. Firing elaborate*reward*based*on*reward
  8083. -->
  8084. (R963 ^value 1 +)
  8085. (R1 ^reward R963 +)
  8086. Firing propose*predict-yes
  8087. -->
  8088. (O1919 ^name predict-yes +)
  8089. (S1 ^operator O1919 +)
  8090. Firing propose*predict-no
  8091. -->
  8092. (O1920 ^name predict-no +)
  8093. (S1 ^operator O1920 +)
  8094. Firing rl*prefer*rvt*predict-no*H0*4
  8095. -->
  8096. (S1 ^operator O1918 = 1.)
  8097. Firing rl*prefer*rvt*predict-yes*H0*3
  8098. -->
  8099. (S1 ^operator O1917 = 0.)
  8100. Firing prefer*rvt*predict-yes*H0
  8101. -->
  8102. Firing prefer*rvt*predict-no*H0
  8103. -->
  8104. Firing elaborate*copy-dir-to-output-link
  8105. -->
  8106. (I3 ^dir U +)
  8107. inner elaboration loop at bottom goal.
  8108. Retracting elaborate*copy-see-to-output-link
  8109. -->
  8110. (I3 ^see 0 +)
  8111. Retracting propose*predict-no
  8112. -->
  8113. (O1918 ^name predict-no +)
  8114. (S1 ^operator O1918 +)
  8115. Retracting propose*predict-yes
  8116. -->
  8117. (O1917 ^name predict-yes +)
  8118. (S1 ^operator O1917 +)
  8119. Retracting elaborate*reward*based*on*reward
  8120. -->
  8121. (R962 ^value 1 +)
  8122. (R1 ^reward R962 +)
  8123. Retracting elaborate*copy-dir-to-output-link
  8124. -->
  8125. (I3 ^dir R +)
  8126. Retracting rl*prefer*rvt*predict-no*H0*6
  8127. -->
  8128. (S1 ^operator O1918 = 0.9994824970933811)
  8129. Retracting rl*prefer*rvt*predict-yes*H0*5
  8130. -->
  8131. (S1 ^operator O1917 = 0.2239429835695002)
  8132. Retracting rl*prefer*rvt*predict-yes*H0*5*H1*16
  8133. -->
  8134. (S1 ^operator O1917 = 0.7757627104044436)
  8135. =>WM: (13442: S1 ^operator O1920 +)
  8136. =>WM: (13441: S1 ^operator O1919 +)
  8137. =>WM: (13440: I3 ^dir U)
  8138. =>WM: (13439: O1920 ^name predict-no)
  8139. =>WM: (13438: O1919 ^name predict-yes)
  8140. =>WM: (13437: R963 ^value 1)
  8141. =>WM: (13436: R1 ^reward R963)
  8142. =>WM: (13435: I3 ^see 1)
  8143. <=WM: (13426: S1 ^operator O1917 +)
  8144. <=WM: (13428: S1 ^operator O1917)
  8145. <=WM: (13427: S1 ^operator O1918 +)
  8146. <=WM: (13425: I3 ^dir R)
  8147. <=WM: (13421: R1 ^reward R962)
  8148. <=WM: (13407: I3 ^see 0)
  8149. <=WM: (13424: O1918 ^name predict-no)
  8150. <=WM: (13423: O1917 ^name predict-yes)
  8151. <=WM: (13422: R962 ^value 1)
  8152. --- Inner Elaboration Phase, active level 1 (S1) ---
  8153. Firing prefer*rvt*predict-yes*H0
  8154. -->
  8155. Firing rl*prefer*rvt*predict-yes*H0*3
  8156. -->
  8157. (S1 ^operator O1919 = 0.)
  8158. Firing prefer*rvt*predict-no*H0
  8159. -->
  8160. Firing rl*prefer*rvt*predict-no*H0*4
  8161. -->
  8162. (S1 ^operator O1920 = 1.)
  8163. inner elaboration loop at bottom goal.
  8164. Retracting rl*prefer*rvt*predict-no*H0*4
  8165. -->
  8166. (S1 ^operator O1918 = 1.)
  8167. Retracting rl*prefer*rvt*predict-yes*H0*3
  8168. -->
  8169. (S1 ^operator O1917 = 0.)
  8170. --- END Proposal Phase ---
  8171. --- Decision Phase ---
  8172. RL update rl*prefer*rvt*predict-yes*H0*5 0.553554 -0.329611 0.223943 -> 0.553579 -0.329611 0.223968(R,m,v=1,0.851351,0.127413)
  8173. RL update rl*prefer*rvt*predict-yes*H0*5*H1*16 0.446145 0.329618 0.775763 -> 0.446175 0.329617 0.775792(R,m,v=1,1,0)
  8174. =>WM: (13443: S1 ^operator O1920)
  8175. 960: O: O1920 (predict-no)
  8176. --- END Decision Phase ---
  8177. --- Application Phase ---
  8178. --- Firing Productions (PE) For State At Depth 1 ---
  8179. --- Inner Elaboration Phase, active level 1 (S1) ---
  8180. Firing apply*operator
  8181. -->
  8182. (I3 ^predict-no N960 + :O )
  8183. Firing apply*operator*complete
  8184. -->
  8185. (I3 ^predict-yes N959 - :O )
  8186. inner elaboration loop at bottom goal.
  8187. --- Change Working Memory (PE) ---
  8188. =>WM: (13444: I3 ^predict-no N960)
  8189. <=WM: (13430: N959 ^status complete)
  8190. <=WM: (13429: I3 ^predict-yes N959)
  8191. --- Firing Productions (IE) For State At Depth 1 ---
  8192. --- Inner Elaboration Phase, active level 1 (S1) ---
  8193. Firing monitor*world
  8194. -->
  8195. I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
  8196. --- Change Working Memory (IE) ---
  8197. --- END Application Phase ---
  8198. --- Output Phase ---
  8199. ENV: Agent did: predict-no for direction U in state State-B
  8200. In State-B moving U
  8201. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  8202. predict error 0
  8203. dir: dir isU
  8204. --- END Output Phase ---
  8205. \---- Input Phase ---
  8206. =>WM: (13448: I2 ^dir U)
  8207. =>WM: (13447: I2 ^reward 1)
  8208. =>WM: (13446: I2 ^see 0)
  8209. =>WM: (13445: N960 ^status complete)
  8210. <=WM: (13433: I2 ^dir U)
  8211. <=WM: (13432: I2 ^reward 1)
  8212. <=WM: (13431: I2 ^see 1)
  8213. =>WM: (13449: I2 ^level-1 R1-root)
  8214. <=WM: (13434: I2 ^level-1 R1-root)
  8215. --- END Input Phase ---
  8216. --- Proposal Phase ---
  8217. --- Inner Elaboration Phase, active level 1 (S1) ---
  8218. Firing elaborate*copy-see-to-output-link
  8219. -->
  8220. (I3 ^see 0 +)
  8221. Firing elaborate*reward*based*on*reward
  8222. -->
  8223. (R964 ^value 1 +)
  8224. (R1 ^reward R964 +)
  8225. Firing propose*predict-yes
  8226. -->
  8227. (O1921 ^name predict-yes +)
  8228. (S1 ^operator O1921 +)
  8229. Firing propose*predict-no
  8230. -->
  8231. (O1922 ^name predict-no +)
  8232. (S1 ^operator O1922 +)
  8233. Firing rl*prefer*rvt*predict-no*H0*4
  8234. -->
  8235. (S1 ^operator O1920 = 1.)
  8236. Firing rl*prefer*rvt*predict-yes*H0*3
  8237. -->
  8238. (S1 ^operator O1919 = 0.)
  8239. Firing prefer*rvt*predict-yes*H0
  8240. -->
  8241. Firing prefer*rvt*predict-no*H0
  8242. -->
  8243. Firing elaborate*copy-dir-to-output-link
  8244. -->
  8245. (I3 ^dir U +)
  8246. inner elaboration loop at bottom goal.
  8247. Retracting elaborate*copy-see-to-output-link
  8248. -->
  8249. (I3 ^see 1 +)
  8250. Retracting propose*predict-no
  8251. -->
  8252. (O1920 ^name predict-no +)
  8253. (S1 ^operator O1920 +)
  8254. Retracting propose*predict-yes
  8255. -->
  8256. (O1919 ^name predict-yes +)
  8257. (S1 ^operator O1919 +)
  8258. Retracting elaborate*reward*based*on*reward
  8259. -->
  8260. (R963 ^value 1 +)
  8261. (R1 ^reward R963 +)
  8262. Retracting elaborate*copy-dir-to-output-link
  8263. -->
  8264. (I3 ^dir U +)
  8265. Retracting rl*prefer*rvt*predict-no*H0*4
  8266. -->
  8267. (S1 ^operator O1920 = 1.)
  8268. Retracting rl*prefer*rvt*predict-yes*H0*3
  8269. -->
  8270. (S1 ^operator O1919 = 0.)
  8271. =>WM: (13456: S1 ^operator O1922 +)
  8272. =>WM: (13455: S1 ^operator O1921 +)
  8273. =>WM: (13454: O1922 ^name predict-no)
  8274. =>WM: (13453: O1921 ^name predict-yes)
  8275. =>WM: (13452: R964 ^value 1)
  8276. =>WM: (13451: R1 ^reward R964)
  8277. =>WM: (13450: I3 ^see 0)
  8278. <=WM: (13441: S1 ^operator O1919 +)
  8279. <=WM: (13442: S1 ^operator O1920 +)
  8280. <=WM: (13443: S1 ^operator O1920)
  8281. <=WM: (13436: R1 ^reward R963)
  8282. <=WM: (13435: I3 ^see 1)
  8283. <=WM: (13439: O1920 ^name predict-no)
  8284. <=WM: (13438: O1919 ^name predict-yes)
  8285. <=WM: (13437: R963 ^value 1)
  8286. --- Inner Elaboration Phase, active level 1 (S1) ---
  8287. Firing prefer*rvt*predict-yes*H0
  8288. -->
  8289. Firing rl*prefer*rvt*predict-yes*H0*3
  8290. -->
  8291. (S1 ^operator O1921 = 0.)
  8292. Firing prefer*rvt*predict-no*H0
  8293. -->
  8294. Firing rl*prefer*rvt*predict-no*H0*4
  8295. -->
  8296. (S1 ^operator O1922 = 1.)
  8297. inner elaboration loop at bottom goal.
  8298. Retracting rl*prefer*rvt*predict-no*H0*4
  8299. -->
  8300. (S1 ^operator O1920 = 1.)
  8301. Retracting rl*prefer*rvt*predict-yes*H0*3
  8302. -->
  8303. (S1 ^operator O1919 = 0.)
  8304. --- END Proposal Phase ---
  8305. --- Decision Phase ---
  8306. RL update rl*prefer*rvt*predict-no*H0*4 1 0 1 -> 1 0 1(R,m,v=1,1,0)
  8307. =>WM: (13457: S1 ^operator O1922)
  8308. 961: O: O1922 (predict-no)
  8309. --- END Decision Phase ---
  8310. --- Application Phase ---
  8311. --- Firing Productions (PE) For State At Depth 1 ---
  8312. --- Inner Elaboration Phase, active level 1 (S1) ---
  8313. Firing apply*operator
  8314. -->
  8315. (I3 ^predict-no N961 + :O )
  8316. Firing apply*operator*complete
  8317. -->
  8318. (I3 ^predict-no N960 - :O )
  8319. inner elaboration loop at bottom goal.
  8320. --- Change Working Memory (PE) ---
  8321. =>WM: (13458: I3 ^predict-no N961)
  8322. <=WM: (13445: N960 ^status complete)
  8323. <=WM: (13444: I3 ^predict-no N960)
  8324. --- Firing Productions (IE) For State At Depth 1 ---
  8325. --- Inner Elaboration Phase, active level 1 (S1) ---
  8326. Firing monitor*world
  8327. -->
  8328. I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
  8329. --- Change Working Memory (IE) ---
  8330. --- END Application Phase ---
  8331. --- Output Phase ---
  8332. ENV: Agent did: predict-no for direction U in state State-B
  8333. In State-B moving U
  8334. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  8335. predict error 0
  8336. dir: dir isU
  8337. --- END Output Phase ---
  8338. /--- Input Phase ---
  8339. =>WM: (13462: I2 ^dir U)
  8340. =>WM: (13461: I2 ^reward 1)
  8341. =>WM: (13460: I2 ^see 0)
  8342. =>WM: (13459: N961 ^status complete)
  8343. <=WM: (13448: I2 ^dir U)
  8344. <=WM: (13447: I2 ^reward 1)
  8345. <=WM: (13446: I2 ^see 0)
  8346. =>WM: (13463: I2 ^level-1 R1-root)
  8347. <=WM: (13449: I2 ^level-1 R1-root)
  8348. --- END Input Phase ---
  8349. --- Proposal Phase ---
  8350. --- Inner Elaboration Phase, active level 1 (S1) ---
  8351. Firing elaborate*copy-see-to-output-link
  8352. -->
  8353. (I3 ^see 0 +)
  8354. Firing elaborate*reward*based*on*reward
  8355. -->
  8356. (R965 ^value 1 +)
  8357. (R1 ^reward R965 +)
  8358. Firing propose*predict-yes
  8359. -->
  8360. (O1923 ^name predict-yes +)
  8361. (S1 ^operator O1923 +)
  8362. Firing propose*predict-no
  8363. -->
  8364. (O1924 ^name predict-no +)
  8365. (S1 ^operator O1924 +)
  8366. Firing rl*prefer*rvt*predict-no*H0*4
  8367. -->
  8368. (S1 ^operator O1922 = 1.)
  8369. Firing rl*prefer*rvt*predict-yes*H0*3
  8370. -->
  8371. (S1 ^operator O1921 = 0.)
  8372. Firing prefer*rvt*predict-yes*H0
  8373. -->
  8374. Firing prefer*rvt*predict-no*H0
  8375. -->
  8376. Firing elaborate*copy-dir-to-output-link
  8377. -->
  8378. (I3 ^dir U +)
  8379. inner elaboration loop at bottom goal.
  8380. Retracting elaborate*copy-see-to-output-link
  8381. -->
  8382. (I3 ^see 0 +)
  8383. Retracting propose*predict-no
  8384. -->
  8385. (O1922 ^name predict-no +)
  8386. (S1 ^operator O1922 +)
  8387. Retracting propose*predict-yes
  8388. -->
  8389. (O1921 ^name predict-yes +)
  8390. (S1 ^operator O1921 +)
  8391. Retracting elaborate*reward*based*on*reward
  8392. -->
  8393. (R964 ^value 1 +)
  8394. (R1 ^reward R964 +)
  8395. Retracting elaborate*copy-dir-to-output-link
  8396. -->
  8397. (I3 ^dir U +)
  8398. Retracting rl*prefer*rvt*predict-no*H0*4
  8399. -->
  8400. (S1 ^operator O1922 = 1.)
  8401. Retracting rl*prefer*rvt*predict-yes*H0*3
  8402. -->
  8403. (S1 ^operator O1921 = 0.)
  8404. =>WM: (13469: S1 ^operator O1924 +)
  8405. =>WM: (13468: S1 ^operator O1923 +)
  8406. =>WM: (13467: O1924 ^name predict-no)
  8407. =>WM: (13466: O1923 ^name predict-yes)
  8408. =>WM: (13465: R965 ^value 1)
  8409. =>WM: (13464: R1 ^reward R965)
  8410. <=WM: (13455: S1 ^operator O1921 +)
  8411. <=WM: (13456: S1 ^operator O1922 +)
  8412. <=WM: (13457: S1 ^operator O1922)
  8413. <=WM: (13451: R1 ^reward R964)
  8414. <=WM: (13454: O1922 ^name predict-no)
  8415. <=WM: (13453: O1921 ^name predict-yes)
  8416. <=WM: (13452: R964 ^value 1)
  8417. --- Inner Elaboration Phase, active level 1 (S1) ---
  8418. Firing prefer*rvt*predict-yes*H0
  8419. -->
  8420. Firing rl*prefer*rvt*predict-yes*H0*3
  8421. -->
  8422. (S1 ^operator O1923 = 0.)
  8423. Firing prefer*rvt*predict-no*H0
  8424. -->
  8425. Firing rl*prefer*rvt*predict-no*H0*4
  8426. -->
  8427. (S1 ^operator O1924 = 1.)
  8428. inner elaboration loop at bottom goal.
  8429. Retracting rl*prefer*rvt*predict-no*H0*4
  8430. -->
  8431. (S1 ^operator O1922 = 1.)
  8432. Retracting rl*prefer*rvt*predict-yes*H0*3
  8433. -->
  8434. (S1 ^operator O1921 = 0.)
  8435. --- END Proposal Phase ---
  8436. --- Decision Phase ---
  8437. RL update rl*prefer*rvt*predict-no*H0*4 1 0 1 -> 1 0 1(R,m,v=1,1,0)
  8438. =>WM: (13470: S1 ^operator O1924)
  8439. 962: O: O1924 (predict-no)
  8440. --- END Decision Phase ---
  8441. --- Application Phase ---
  8442. --- Firing Productions (PE) For State At Depth 1 ---
  8443. --- Inner Elaboration Phase, active level 1 (S1) ---
  8444. Firing apply*operator
  8445. -->
  8446. (I3 ^predict-no N962 + :O )
  8447. Firing apply*operator*complete
  8448. -->
  8449. (I3 ^predict-no N961 - :O )
  8450. inner elaboration loop at bottom goal.
  8451. --- Change Working Memory (PE) ---
  8452. =>WM: (13471: I3 ^predict-no N962)
  8453. <=WM: (13459: N961 ^status complete)
  8454. <=WM: (13458: I3 ^predict-no N961)
  8455. --- Firing Productions (IE) For State At Depth 1 ---
  8456. --- Inner Elaboration Phase, active level 1 (S1) ---
  8457. Firing monitor*world
  8458. -->
  8459. I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
  8460. --- Change Working Memory (IE) ---
  8461. --- END Application Phase ---
  8462. --- Output Phase ---
  8463. ENV: Agent did: predict-no for direction U in state State-B
  8464. In State-B moving U
  8465. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  8466. predict error 0
  8467. dir: dir isU
  8468. --- END Output Phase ---
  8469. |\--- Input Phase ---
  8470. =>WM: (13475: I2 ^dir U)
  8471. =>WM: (13474: I2 ^reward 1)
  8472. =>WM: (13473: I2 ^see 0)
  8473. =>WM: (13472: N962 ^status complete)
  8474. <=WM: (13462: I2 ^dir U)
  8475. <=WM: (13461: I2 ^reward 1)
  8476. <=WM: (13460: I2 ^see 0)
  8477. =>WM: (13476: I2 ^level-1 R1-root)
  8478. <=WM: (13463: I2 ^level-1 R1-root)
  8479. --- END Input Phase ---
  8480. --- Proposal Phase ---
  8481. --- Inner Elaboration Phase, active level 1 (S1) ---
  8482. Firing elaborate*copy-see-to-output-link
  8483. -->
  8484. (I3 ^see 0 +)
  8485. Firing elaborate*reward*based*on*reward
  8486. -->
  8487. (R966 ^value 1 +)
  8488. (R1 ^reward R966 +)
  8489. Firing propose*predict-yes
  8490. -->
  8491. (O1925 ^name predict-yes +)
  8492. (S1 ^operator O1925 +)
  8493. Firing propose*predict-no
  8494. -->
  8495. (O1926 ^name predict-no +)
  8496. (S1 ^operator O1926 +)
  8497. Firing rl*prefer*rvt*predict-no*H0*4
  8498. -->
  8499. (S1 ^operator O1924 = 1.)
  8500. Firing rl*prefer*rvt*predict-yes*H0*3
  8501. -->
  8502. (S1 ^operator O1923 = 0.)
  8503. Firing prefer*rvt*predict-yes*H0
  8504. -->
  8505. Firing prefer*rvt*predict-no*H0
  8506. -->
  8507. Firing elaborate*copy-dir-to-output-link
  8508. -->
  8509. (I3 ^dir U +)
  8510. inner elaboration loop at bottom goal.
  8511. Retracting elaborate*copy-see-to-output-link
  8512. -->
  8513. (I3 ^see 0 +)
  8514. Retracting propose*predict-no
  8515. -->
  8516. (O1924 ^name predict-no +)
  8517. (S1 ^operator O1924 +)
  8518. Retracting propose*predict-yes
  8519. -->
  8520. (O1923 ^name predict-yes +)
  8521. (S1 ^operator O1923 +)
  8522. Retracting elaborate*reward*based*on*reward
  8523. -->
  8524. (R965 ^value 1 +)
  8525. (R1 ^reward R965 +)
  8526. Retracting elaborate*copy-dir-to-output-link
  8527. -->
  8528. (I3 ^dir U +)
  8529. Retracting rl*prefer*rvt*predict-no*H0*4
  8530. -->
  8531. (S1 ^operator O1924 = 1.)
  8532. Retracting rl*prefer*rvt*predict-yes*H0*3
  8533. -->
  8534. (S1 ^operator O1923 = 0.)
  8535. =>WM: (13482: S1 ^operator O1926 +)
  8536. =>WM: (13481: S1 ^operator O1925 +)
  8537. =>WM: (13480: O1926 ^name predict-no)
  8538. =>WM: (13479: O1925 ^name predict-yes)
  8539. =>WM: (13478: R966 ^value 1)
  8540. =>WM: (13477: R1 ^reward R966)
  8541. <=WM: (13468: S1 ^operator O1923 +)
  8542. <=WM: (13469: S1 ^operator O1924 +)
  8543. <=WM: (13470: S1 ^operator O1924)
  8544. <=WM: (13464: R1 ^reward R965)
  8545. <=WM: (13467: O1924 ^name predict-no)
  8546. <=WM: (13466: O1923 ^name predict-yes)
  8547. <=WM: (13465: R965 ^value 1)
  8548. --- Inner Elaboration Phase, active level 1 (S1) ---
  8549. Firing prefer*rvt*predict-yes*H0
  8550. -->
  8551. Firing rl*prefer*rvt*predict-yes*H0*3
  8552. -->
  8553. (S1 ^operator O1925 = 0.)
  8554. Firing prefer*rvt*predict-no*H0
  8555. -->
  8556. Firing rl*prefer*rvt*predict-no*H0*4
  8557. -->
  8558. (S1 ^operator O1926 = 1.)
  8559. inner elaboration loop at bottom goal.
  8560. Retracting rl*prefer*rvt*predict-no*H0*4
  8561. -->
  8562. (S1 ^operator O1924 = 1.)
  8563. Retracting rl*prefer*rvt*predict-yes*H0*3
  8564. -->
  8565. (S1 ^operator O1923 = 0.)
  8566. --- END Proposal Phase ---
  8567. --- Decision Phase ---
  8568. RL update rl*prefer*rvt*predict-no*H0*4 1 0 1 -> 1 0 1(R,m,v=1,1,0)
  8569. =>WM: (13483: S1 ^operator O1926)
  8570. 963: O: O1926 (predict-no)
  8571. --- END Decision Phase ---
  8572. --- Application Phase ---
  8573. --- Firing Productions (PE) For State At Depth 1 ---
  8574. --- Inner Elaboration Phase, active level 1 (S1) ---
  8575. Firing apply*operator
  8576. -->
  8577. (I3 ^predict-no N963 + :O )
  8578. Firing apply*operator*complete
  8579. -->
  8580. (I3 ^predict-no N962 - :O )
  8581. inner elaboration loop at bottom goal.
  8582. --- Change Working Memory (PE) ---
  8583. =>WM: (13484: I3 ^predict-no N963)
  8584. <=WM: (13472: N962 ^status complete)
  8585. <=WM: (13471: I3 ^predict-no N962)
  8586. --- Firing Productions (IE) For State At Depth 1 ---
  8587. --- Inner Elaboration Phase, active level 1 (S1) ---
  8588. Firing monitor*world
  8589. -->
  8590. I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
  8591. --- Change Working Memory (IE) ---
  8592. --- END Application Phase ---
  8593. --- Output Phase ---
  8594. ENV: Agent did: predict-no for direction U in state State-B
  8595. In State-B moving U
  8596. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  8597. predict error 0
  8598. dir: dir isL
  8599. --- END Output Phase ---
  8600. -/|--- Input Phase ---
  8601. =>WM: (13488: I2 ^dir L)
  8602. =>WM: (13487: I2 ^reward 1)
  8603. =>WM: (13486: I2 ^see 0)
  8604. =>WM: (13485: N963 ^status complete)
  8605. <=WM: (13475: I2 ^dir U)
  8606. <=WM: (13474: I2 ^reward 1)
  8607. <=WM: (13473: I2 ^see 0)
  8608. =>WM: (13489: I2 ^level-1 R1-root)
  8609. <=WM: (13476: I2 ^level-1 R1-root)
  8610. --- END Input Phase ---
  8611. --- Proposal Phase ---
  8612. --- Inner Elaboration Phase, active level 1 (S1) ---
  8613. Firing rl*prefer*rvt*predict-no*H0*2*H1*8
  8614. -->
  8615. (S1 ^operator O1926 = -0.1970449706966682)
  8616. Firing rl*prefer*rvt*predict-yes*H0*1*H1*7
  8617. -->
  8618. (S1 ^operator O1925 = 0.6500793403913283)
  8619. Firing prefer*rvt*predict-no*H0*2*H1
  8620. -->
  8621. Firing prefer*rvt*predict-yes*H0*1*H1
  8622. -->
  8623. Firing elaborate*copy-see-to-output-link
  8624. -->
  8625. (I3 ^see 0 +)
  8626. Firing elaborate*reward*based*on*reward
  8627. -->
  8628. (R967 ^value 1 +)
  8629. (R1 ^reward R967 +)
  8630. Firing propose*predict-yes
  8631. -->
  8632. (O1927 ^name predict-yes +)
  8633. (S1 ^operator O1927 +)
  8634. Firing propose*predict-no
  8635. -->
  8636. (O1928 ^name predict-no +)
  8637. (S1 ^operator O1928 +)
  8638. Firing rl*prefer*rvt*predict-no*H0*2
  8639. -->
  8640. (S1 ^operator O1926 = 0.2381452180684112)
  8641. Firing rl*prefer*rvt*predict-yes*H0*1
  8642. -->
  8643. (S1 ^operator O1925 = 0.3499208756511618)
  8644. Firing prefer*rvt*predict-yes*H0
  8645. -->
  8646. Firing prefer*rvt*predict-no*H0
  8647. -->
  8648. Firing elaborate*copy-dir-to-output-link
  8649. -->
  8650. (I3 ^dir L +)
  8651. inner elaboration loop at bottom goal.
  8652. Retracting elaborate*copy-see-to-output-link
  8653. -->
  8654. (I3 ^see 0 +)
  8655. Retracting propose*predict-no
  8656. -->
  8657. (O1926 ^name predict-no +)
  8658. (S1 ^operator O1926 +)
  8659. Retracting propose*predict-yes
  8660. -->
  8661. (O1925 ^name predict-yes +)
  8662. (S1 ^operator O1925 +)
  8663. Retracting elaborate*reward*based*on*reward
  8664. -->
  8665. (R966 ^value 1 +)
  8666. (R1 ^reward R966 +)
  8667. Retracting elaborate*copy-dir-to-output-link
  8668. -->
  8669. (I3 ^dir U +)
  8670. Retracting rl*prefer*rvt*predict-no*H0*4
  8671. -->
  8672. (S1 ^operator O1926 = 1.)
  8673. Retracting rl*prefer*rvt*predict-yes*H0*3
  8674. -->
  8675. (S1 ^operator O1925 = 0.)
  8676. =>WM: (13496: S1 ^operator O1928 +)
  8677. =>WM: (13495: S1 ^operator O1927 +)
  8678. =>WM: (13494: I3 ^dir L)
  8679. =>WM: (13493: O1928 ^name predict-no)
  8680. =>WM: (13492: O1927 ^name predict-yes)
  8681. =>WM: (13491: R967 ^value 1)
  8682. =>WM: (13490: R1 ^reward R967)
  8683. <=WM: (13481: S1 ^operator O1925 +)
  8684. <=WM: (13482: S1 ^operator O1926 +)
  8685. <=WM: (13483: S1 ^operator O1926)
  8686. <=WM: (13440: I3 ^dir U)
  8687. <=WM: (13477: R1 ^reward R966)
  8688. <=WM: (13480: O1926 ^name predict-no)
  8689. <=WM: (13479: O1925 ^name predict-yes)
  8690. <=WM: (13478: R966 ^value 1)
  8691. --- Inner Elaboration Phase, active level 1 (S1) ---
  8692. Firing prefer*rvt*predict-yes*H0
  8693. -->
  8694. Firing rl*prefer*rvt*predict-yes*H0*1*H1*7
  8695. -->
  8696. (S1 ^operator O1927 = 0.6500793403913283)
  8697. Firing rl*prefer*rvt*predict-yes*H0*1
  8698. -->
  8699. (S1 ^operator O1927 = 0.3499208756511618)
  8700. Firing prefer*rvt*predict-yes*H0*1*H1
  8701. -->
  8702. Firing prefer*rvt*predict-no*H0
  8703. -->
  8704. Firing rl*prefer*rvt*predict-no*H0*2*H1*8
  8705. -->
  8706. (S1 ^operator O1928 = -0.1970449706966682)
  8707. Firing rl*prefer*rvt*predict-no*H0*2
  8708. -->
  8709. (S1 ^operator O1928 = 0.2381452180684112)
  8710. Firing prefer*rvt*predict-no*H0*2*H1
  8711. -->
  8712. inner elaboration loop at bottom goal.
  8713. Retracting rl*prefer*rvt*predict-no*H0*2
  8714. -->
  8715. (S1 ^operator O1926 = 0.2381452180684112)
  8716. Retracting rl*prefer*rvt*predict-no*H0*2*H1*8
  8717. -->
  8718. (S1 ^operator O1926 = -0.1970449706966682)
  8719. Retracting rl*prefer*rvt*predict-yes*H0*1
  8720. -->
  8721. (S1 ^operator O1925 = 0.3499208756511618)
  8722. Retracting rl*prefer*rvt*predict-yes*H0*1*H1*7
  8723. -->
  8724. (S1 ^operator O1925 = 0.6500793403913283)
  8725. --- END Proposal Phase ---
  8726. --- Decision Phase ---
  8727. RL update rl*prefer*rvt*predict-no*H0*4 1 0 1 -> 1 0 1(R,m,v=1,1,0)
  8728. =>WM: (13497: S1 ^operator O1927)
  8729. 964: O: O1927 (predict-yes)
  8730. --- END Decision Phase ---
  8731. --- Application Phase ---
  8732. --- Firing Productions (PE) For State At Depth 1 ---
  8733. --- Inner Elaboration Phase, active level 1 (S1) ---
  8734. Firing apply*operator
  8735. -->
  8736. (I3 ^predict-yes N964 + :O )
  8737. Firing apply*operator*complete
  8738. -->
  8739. (I3 ^predict-no N963 - :O )
  8740. inner elaboration loop at bottom goal.
  8741. --- Change Working Memory (PE) ---
  8742. =>WM: (13498: I3 ^predict-yes N964)
  8743. <=WM: (13485: N963 ^status complete)
  8744. <=WM: (13484: I3 ^predict-no N963)
  8745. --- Firing Productions (IE) For State At Depth 1 ---
  8746. --- Inner Elaboration Phase, active level 1 (S1) ---
  8747. Firing monitor*world
  8748. -->
  8749. I see 1 and I'm going to do: predict-yes inner elaboration loop at bottom goal.
  8750. --- Change Working Memory (IE) ---
  8751. --- END Application Phase ---
  8752. --- Output Phase ---
  8753. ENV: Agent did: predict-yes for direction L in state State-B
  8754. In State-B moving L
  8755. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  8756. predict error 0
  8757. dir: dir isR
  8758. --- END Output Phase ---
  8759. \---- Input Phase ---
  8760. =>WM: (13502: I2 ^dir R)
  8761. =>WM: (13501: I2 ^reward 1)
  8762. =>WM: (13500: I2 ^see 1)
  8763. =>WM: (13499: N964 ^status complete)
  8764. <=WM: (13488: I2 ^dir L)
  8765. <=WM: (13487: I2 ^reward 1)
  8766. <=WM: (13486: I2 ^see 0)
  8767. =>WM: (13503: I2 ^level-1 L1-root)
  8768. <=WM: (13489: I2 ^level-1 R1-root)
  8769. --- END Input Phase ---
  8770. --- Proposal Phase ---
  8771. --- Inner Elaboration Phase, active level 1 (S1) ---
  8772. Firing rl*prefer*rvt*predict-yes*H0*5*H1*9
  8773. -->
  8774. (S1 ^operator O1927 = 0.7762753724407851)
  8775. Firing prefer*rvt*predict-yes*H0*5*H1
  8776. -->
  8777. Firing elaborate*copy-see-to-output-link
  8778. -->
  8779. (I3 ^see 1 +)
  8780. Firing elaborate*reward*based*on*reward
  8781. -->
  8782. (R968 ^value 1 +)
  8783. (R1 ^reward R968 +)
  8784. Firing propose*predict-yes
  8785. -->
  8786. (O1929 ^name predict-yes +)
  8787. (S1 ^operator O1929 +)
  8788. Firing propose*predict-no
  8789. -->
  8790. (O1930 ^name predict-no +)
  8791. (S1 ^operator O1930 +)
  8792. Firing rl*prefer*rvt*predict-no*H0*6
  8793. -->
  8794. (S1 ^operator O1928 = 0.9994824970933811)
  8795. Firing rl*prefer*rvt*predict-yes*H0*5
  8796. -->
  8797. (S1 ^operator O1927 = 0.2239675204720327)
  8798. Firing prefer*rvt*predict-yes*H0
  8799. -->
  8800. Firing prefer*rvt*predict-no*H0
  8801. -->
  8802. Firing elaborate*copy-dir-to-output-link
  8803. -->
  8804. (I3 ^dir R +)
  8805. inner elaboration loop at bottom goal.
  8806. Retracting elaborate*copy-see-to-output-link
  8807. -->
  8808. (I3 ^see 0 +)
  8809. Retracting propose*predict-no
  8810. -->
  8811. (O1928 ^name predict-no +)
  8812. (S1 ^operator O1928 +)
  8813. Retracting propose*predict-yes
  8814. -->
  8815. (O1927 ^name predict-yes +)
  8816. (S1 ^operator O1927 +)
  8817. Retracting elaborate*reward*based*on*reward
  8818. -->
  8819. (R967 ^value 1 +)
  8820. (R1 ^reward R967 +)
  8821. Retracting elaborate*copy-dir-to-output-link
  8822. -->
  8823. (I3 ^dir L +)
  8824. Retracting rl*prefer*rvt*predict-no*H0*2
  8825. -->
  8826. (S1 ^operator O1928 = 0.2381452180684112)
  8827. Retracting rl*prefer*rvt*predict-no*H0*2*H1*8
  8828. -->
  8829. (S1 ^operator O1928 = -0.1970449706966682)
  8830. Retracting rl*prefer*rvt*predict-yes*H0*1
  8831. -->
  8832. (S1 ^operator O1927 = 0.3499208756511618)
  8833. Retracting rl*prefer*rvt*predict-yes*H0*1*H1*7
  8834. -->
  8835. (S1 ^operator O1927 = 0.6500793403913283)
  8836. =>WM: (13511: S1 ^operator O1930 +)
  8837. =>WM: (13510: S1 ^operator O1929 +)
  8838. =>WM: (13509: I3 ^dir R)
  8839. =>WM: (13508: O1930 ^name predict-no)
  8840. =>WM: (13507: O1929 ^name predict-yes)
  8841. =>WM: (13506: R968 ^value 1)
  8842. =>WM: (13505: R1 ^reward R968)
  8843. =>WM: (13504: I3 ^see 1)
  8844. <=WM: (13495: S1 ^operator O1927 +)
  8845. <=WM: (13497: S1 ^operator O1927)
  8846. <=WM: (13496: S1 ^operator O1928 +)
  8847. <=WM: (13494: I3 ^dir L)
  8848. <=WM: (13490: R1 ^reward R967)
  8849. <=WM: (13450: I3 ^see 0)
  8850. <=WM: (13493: O1928 ^name predict-no)
  8851. <=WM: (13492: O1927 ^name predict-yes)
  8852. <=WM: (13491: R967 ^value 1)
  8853. --- Inner Elaboration Phase, active level 1 (S1) ---
  8854. Firing prefer*rvt*predict-yes*H0
  8855. -->
  8856. Firing rl*prefer*rvt*predict-yes*H0*5
  8857. -->
  8858. (S1 ^operator O1929 = 0.2239675204720327)
  8859. Firing prefer*rvt*predict-yes*H0*5*H1
  8860. -->
  8861. Firing rl*prefer*rvt*predict-yes*H0*5*H1*9
  8862. -->
  8863. (S1 ^operator O1929 = 0.7762753724407851)
  8864. Firing prefer*rvt*predict-no*H0
  8865. -->
  8866. Firing rl*prefer*rvt*predict-no*H0*6
  8867. -->
  8868. (S1 ^operator O1930 = 0.9994824970933811)
  8869. inner elaboration loop at bottom goal.
  8870. Retracting rl*prefer*rvt*predict-no*H0*6
  8871. -->
  8872. (S1 ^operator O1928 = 0.9994824970933811)
  8873. Retracting rl*prefer*rvt*predict-yes*H0*5
  8874. -->
  8875. (S1 ^operator O1927 = 0.2239675204720327)
  8876. Retracting rl*prefer*rvt*predict-yes*H0*5*H1*9
  8877. -->
  8878. (S1 ^operator O1927 = 0.7762753724407851)
  8879. --- END Proposal Phase ---
  8880. --- Decision Phase ---
  8881. RL update rl*prefer*rvt*predict-yes*H0*1 0.407926 -0.0580056 0.349921 -> 0.407927 -0.0580064 0.349921(R,m,v=1,0.89726,0.09282)
  8882. RL update rl*prefer*rvt*predict-yes*H0*1*H1*7 0.592064 0.0580154 0.650079 -> 0.592065 0.0580144 0.650079(R,m,v=1,1,0)
  8883. =>WM: (13512: S1 ^operator O1929)
  8884. 965: O: O1929 (predict-yes)
  8885. --- END Decision Phase ---
  8886. --- Application Phase ---
  8887. --- Firing Productions (PE) For State At Depth 1 ---
  8888. --- Inner Elaboration Phase, active level 1 (S1) ---
  8889. Firing apply*operator
  8890. -->
  8891. (I3 ^predict-yes N965 + :O )
  8892. Firing apply*operator*complete
  8893. -->
  8894. (I3 ^predict-yes N964 - :O )
  8895. inner elaboration loop at bottom goal.
  8896. --- Change Working Memory (PE) ---
  8897. =>WM: (13513: I3 ^predict-yes N965)
  8898. <=WM: (13499: N964 ^status complete)
  8899. <=WM: (13498: I3 ^predict-yes N964)
  8900. --- Firing Productions (IE) For State At Depth 1 ---
  8901. --- Inner Elaboration Phase, active level 1 (S1) ---
  8902. Firing monitor*world
  8903. -->
  8904. I see 1 and I'm going to do: predict-yes inner elaboration loop at bottom goal.
  8905. --- Change Working Memory (IE) ---
  8906. --- END Application Phase ---
  8907. --- Output Phase ---
  8908. ENV: Agent did: predict-yes for direction R in state State-A
  8909. In State-A moving R
  8910. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  8911. predict error 0
  8912. dir: dir isU
  8913. --- END Output Phase ---
  8914. /|\--- Input Phase ---
  8915. =>WM: (13517: I2 ^dir U)
  8916. =>WM: (13516: I2 ^reward 1)
  8917. =>WM: (13515: I2 ^see 1)
  8918. =>WM: (13514: N965 ^status complete)
  8919. <=WM: (13502: I2 ^dir R)
  8920. <=WM: (13501: I2 ^reward 1)
  8921. <=WM: (13500: I2 ^see 1)
  8922. =>WM: (13518: I2 ^level-1 R1-root)
  8923. <=WM: (13503: I2 ^level-1 L1-root)
  8924. --- END Input Phase ---
  8925. --- Proposal Phase ---
  8926. --- Inner Elaboration Phase, active level 1 (S1) ---
  8927. Firing elaborate*copy-see-to-output-link
  8928. -->
  8929. (I3 ^see 1 +)
  8930. Firing elaborate*reward*based*on*reward
  8931. -->
  8932. (R969 ^value 1 +)
  8933. (R1 ^reward R969 +)
  8934. Firing propose*predict-yes
  8935. -->
  8936. (O1931 ^name predict-yes +)
  8937. (S1 ^operator O1931 +)
  8938. Firing propose*predict-no
  8939. -->
  8940. (O1932 ^name predict-no +)
  8941. (S1 ^operator O1932 +)
  8942. Firing rl*prefer*rvt*predict-no*H0*4
  8943. -->
  8944. (S1 ^operator O1930 = 1.)
  8945. Firing rl*prefer*rvt*predict-yes*H0*3
  8946. -->
  8947. (S1 ^operator O1929 = 0.)
  8948. Firing prefer*rvt*predict-yes*H0
  8949. -->
  8950. Firing prefer*rvt*predict-no*H0
  8951. -->
  8952. Firing elaborate*copy-dir-to-output-link
  8953. -->
  8954. (I3 ^dir U +)
  8955. inner elaboration loop at bottom goal.
  8956. Retracting elaborate*copy-see-to-output-link
  8957. -->
  8958. (I3 ^see 1 +)
  8959. Retracting propose*predict-no
  8960. -->
  8961. (O1930 ^name predict-no +)
  8962. (S1 ^operator O1930 +)
  8963. Retracting propose*predict-yes
  8964. -->
  8965. (O1929 ^name predict-yes +)
  8966. (S1 ^operator O1929 +)
  8967. Retracting elaborate*reward*based*on*reward
  8968. -->
  8969. (R968 ^value 1 +)
  8970. (R1 ^reward R968 +)
  8971. Retracting elaborate*copy-dir-to-output-link
  8972. -->
  8973. (I3 ^dir R +)
  8974. Retracting rl*prefer*rvt*predict-no*H0*6
  8975. -->
  8976. (S1 ^operator O1930 = 0.9994824970933811)
  8977. Retracting rl*prefer*rvt*predict-yes*H0*5*H1*9
  8978. -->
  8979. (S1 ^operator O1929 = 0.7762753724407851)
  8980. Retracting rl*prefer*rvt*predict-yes*H0*5
  8981. -->
  8982. (S1 ^operator O1929 = 0.2239675204720327)
  8983. =>WM: (13525: S1 ^operator O1932 +)
  8984. =>WM: (13524: S1 ^operator O1931 +)
  8985. =>WM: (13523: I3 ^dir U)
  8986. =>WM: (13522: O1932 ^name predict-no)
  8987. =>WM: (13521: O1931 ^name predict-yes)
  8988. =>WM: (13520: R969 ^value 1)
  8989. =>WM: (13519: R1 ^reward R969)
  8990. <=WM: (13510: S1 ^operator O1929 +)
  8991. <=WM: (13512: S1 ^operator O1929)
  8992. <=WM: (13511: S1 ^operator O1930 +)
  8993. <=WM: (13509: I3 ^dir R)
  8994. <=WM: (13505: R1 ^reward R968)
  8995. <=WM: (13508: O1930 ^name predict-no)
  8996. <=WM: (13507: O1929 ^name predict-yes)
  8997. <=WM: (13506: R968 ^value 1)
  8998. --- Inner Elaboration Phase, active level 1 (S1) ---
  8999. Firing prefer*rvt*predict-yes*H0
  9000. -->
  9001. Firing rl*prefer*rvt*predict-yes*H0*3
  9002. -->
  9003. (S1 ^operator O1931 = 0.)
  9004. Firing prefer*rvt*predict-no*H0
  9005. -->
  9006. Firing rl*prefer*rvt*predict-no*H0*4
  9007. -->
  9008. (S1 ^operator O1932 = 1.)
  9009. inner elaboration loop at bottom goal.
  9010. Retracting rl*prefer*rvt*predict-no*H0*4
  9011. -->
  9012. (S1 ^operator O1930 = 1.)
  9013. Retracting rl*prefer*rvt*predict-yes*H0*3
  9014. -->
  9015. (S1 ^operator O1929 = 0.)
  9016. --- END Proposal Phase ---
  9017. --- Decision Phase ---
  9018. RL update rl*prefer*rvt*predict-yes*H0*5 0.553579 -0.329611 0.223968 -> 0.553559 -0.329612 0.223947(R,m,v=1,0.852349,0.126701)
  9019. RL update rl*prefer*rvt*predict-yes*H0*5*H1*9 0.446664 0.329612 0.776275 -> 0.44664 0.329612 0.776252(R,m,v=1,1,0)
  9020. =>WM: (13526: S1 ^operator O1932)
  9021. 966: O: O1932 (predict-no)
  9022. --- END Decision Phase ---
  9023. --- Application Phase ---
  9024. --- Firing Productions (PE) For State At Depth 1 ---
  9025. --- Inner Elaboration Phase, active level 1 (S1) ---
  9026. Firing apply*operator
  9027. -->
  9028. (I3 ^predict-no N966 + :O )
  9029. Firing apply*operator*complete
  9030. -->
  9031. (I3 ^predict-yes N965 - :O )
  9032. inner elaboration loop at bottom goal.
  9033. --- Change Working Memory (PE) ---
  9034. =>WM: (13527: I3 ^predict-no N966)
  9035. <=WM: (13514: N965 ^status complete)
  9036. <=WM: (13513: I3 ^predict-yes N965)
  9037. --- Firing Productions (IE) For State At Depth 1 ---
  9038. --- Inner Elaboration Phase, active level 1 (S1) ---
  9039. Firing monitor*world
  9040. -->
  9041. I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
  9042. --- Change Working Memory (IE) ---
  9043. --- END Application Phase ---
  9044. --- Output Phase ---
  9045. ENV: Agent did: predict-no for direction U in state State-B
  9046. In State-B moving U
  9047. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  9048. predict error 0
  9049. dir: dir isL
  9050. --- END Output Phase ---
  9051. ---- Input Phase ---
  9052. =>WM: (13531: I2 ^dir L)
  9053. =>WM: (13530: I2 ^reward 1)
  9054. =>WM: (13529: I2 ^see 0)
  9055. =>WM: (13528: N966 ^status complete)
  9056. <=WM: (13517: I2 ^dir U)
  9057. <=WM: (13516: I2 ^reward 1)
  9058. <=WM: (13515: I2 ^see 1)
  9059. =>WM: (13532: I2 ^level-1 R1-root)
  9060. <=WM: (13518: I2 ^level-1 R1-root)
  9061. --- END Input Phase ---
  9062. --- Proposal Phase ---
  9063. --- Inner Elaboration Phase, active level 1 (S1) ---
  9064. Firing rl*prefer*rvt*predict-no*H0*2*H1*8
  9065. -->
  9066. (S1 ^operator O1932 = -0.1970449706966682)
  9067. Firing rl*prefer*rvt*predict-yes*H0*1*H1*7
  9068. -->
  9069. (S1 ^operator O1931 = 0.6500793194524461)
  9070. Firing prefer*rvt*predict-no*H0*2*H1
  9071. -->
  9072. Firing prefer*rvt*predict-yes*H0*1*H1
  9073. -->
  9074. Firing elaborate*copy-see-to-output-link
  9075. -->
  9076. (I3 ^see 0 +)
  9077. Firing elaborate*reward*based*on*reward
  9078. -->
  9079. (R970 ^value 1 +)
  9080. (R1 ^reward R970 +)
  9081. Firing propose*predict-yes
  9082. -->
  9083. (O1933 ^name predict-yes +)
  9084. (S1 ^operator O1933 +)
  9085. Firing propose*predict-no
  9086. -->
  9087. (O1934 ^name predict-no +)
  9088. (S1 ^operator O1934 +)
  9089. Firing rl*prefer*rvt*predict-no*H0*2
  9090. -->
  9091. (S1 ^operator O1932 = 0.2381452180684112)
  9092. Firing rl*prefer*rvt*predict-yes*H0*1
  9093. -->
  9094. (S1 ^operator O1931 = 0.3499208575982964)
  9095. Firing prefer*rvt*predict-yes*H0
  9096. -->
  9097. Firing prefer*rvt*predict-no*H0
  9098. -->
  9099. Firing elaborate*copy-dir-to-output-link
  9100. -->
  9101. (I3 ^dir L +)
  9102. inner elaboration loop at bottom goal.
  9103. Retracting elaborate*copy-see-to-output-link
  9104. -->
  9105. (I3 ^see 1 +)
  9106. Retracting propose*predict-no
  9107. -->
  9108. (O1932 ^name predict-no +)
  9109. (S1 ^operator O1932 +)
  9110. Retracting propose*predict-yes
  9111. -->
  9112. (O1931 ^name predict-yes +)
  9113. (S1 ^operator O1931 +)
  9114. Retracting elaborate*reward*based*on*reward
  9115. -->
  9116. (R969 ^value 1 +)
  9117. (R1 ^reward R969 +)
  9118. Retracting elaborate*copy-dir-to-output-link
  9119. -->
  9120. (I3 ^dir U +)
  9121. Retracting rl*prefer*rvt*predict-no*H0*4
  9122. -->
  9123. (S1 ^operator O1932 = 1.)
  9124. Retracting rl*prefer*rvt*predict-yes*H0*3
  9125. -->
  9126. (S1 ^operator O1931 = 0.)
  9127. =>WM: (13540: S1 ^operator O1934 +)
  9128. =>WM: (13539: S1 ^operator O1933 +)
  9129. =>WM: (13538: I3 ^dir L)
  9130. =>WM: (13537: O1934 ^name predict-no)
  9131. =>WM: (13536: O1933 ^name predict-yes)
  9132. =>WM: (13535: R970 ^value 1)
  9133. =>WM: (13534: R1 ^reward R970)
  9134. =>WM: (13533: I3 ^see 0)
  9135. <=WM: (13524: S1 ^operator O1931 +)
  9136. <=WM: (13525: S1 ^operator O1932 +)
  9137. <=WM: (13526: S1 ^operator O1932)
  9138. <=WM: (13523: I3 ^dir U)
  9139. <=WM: (13519: R1 ^reward R969)
  9140. <=WM: (13504: I3 ^see 1)
  9141. <=WM: (13522: O1932 ^name predict-no)
  9142. <=WM: (13521: O1931 ^name predict-yes)
  9143. <=WM: (13520: R969 ^value 1)
  9144. --- Inner Elaboration Phase, active level 1 (S1) ---
  9145. Firing prefer*rvt*predict-yes*H0
  9146. -->
  9147. Firing rl*prefer*rvt*predict-yes*H0*1*H1*7
  9148. -->
  9149. (S1 ^operator O1933 = 0.6500793194524461)
  9150. Firing rl*prefer*rvt*predict-yes*H0*1
  9151. -->
  9152. (S1 ^operator O1933 = 0.3499208575982964)
  9153. Firing prefer*rvt*predict-yes*H0*1*H1
  9154. -->
  9155. Firing prefer*rvt*predict-no*H0
  9156. -->
  9157. Firing rl*prefer*rvt*predict-no*H0*2*H1*8
  9158. -->
  9159. (S1 ^operator O1934 = -0.1970449706966682)
  9160. Firing rl*prefer*rvt*predict-no*H0*2
  9161. -->
  9162. (S1 ^operator O1934 = 0.2381452180684112)
  9163. Firing prefer*rvt*predict-no*H0*2*H1
  9164. -->
  9165. inner elaboration loop at bottom goal.
  9166. Retracting rl*prefer*rvt*predict-no*H0*2
  9167. -->
  9168. (S1 ^operator O1932 = 0.2381452180684112)
  9169. Retracting rl*prefer*rvt*predict-no*H0*2*H1*8
  9170. -->
  9171. (S1 ^operator O1932 = -0.1970449706966682)
  9172. Retracting rl*prefer*rvt*predict-yes*H0*1
  9173. -->
  9174. (S1 ^operator O1931 = 0.3499208575982964)
  9175. Retracting rl*prefer*rvt*predict-yes*H0*1*H1*7
  9176. -->
  9177. (S1 ^operator O1931 = 0.6500793194524461)
  9178. --- END Proposal Phase ---
  9179. --- Decision Phase ---
  9180. RL update rl*prefer*rvt*predict-no*H0*4 1 0 1 -> 1 0 1(R,m,v=1,1,0)
  9181. =>WM: (13541: S1 ^operator O1933)
  9182. 967: O: O1933 (predict-yes)
  9183. --- END Decision Phase ---
  9184. --- Application Phase ---
  9185. --- Firing Productions (PE) For State At Depth 1 ---
  9186. --- Inner Elaboration Phase, active level 1 (S1) ---
  9187. Firing apply*operator
  9188. -->
  9189. (I3 ^predict-yes N967 + :O )
  9190. Firing apply*operator*complete
  9191. -->
  9192. (I3 ^predict-no N966 - :O )
  9193. inner elaboration loop at bottom goal.
  9194. --- Change Working Memory (PE) ---
  9195. =>WM: (13542: I3 ^predict-yes N967)
  9196. <=WM: (13528: N966 ^status complete)
  9197. <=WM: (13527: I3 ^predict-no N966)
  9198. --- Firing Productions (IE) For State At Depth 1 ---
  9199. --- Inner Elaboration Phase, active level 1 (S1) ---
  9200. Firing monitor*world
  9201. -->
  9202. I see 1 and I'm going to do: predict-yes inner elaboration loop at bottom goal.
  9203. --- Change Working Memory (IE) ---
  9204. --- END Application Phase ---
  9205. --- Output Phase ---
  9206. ENV: Agent did: predict-yes for direction L in state State-B
  9207. In State-B moving L
  9208. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  9209. predict error 0
  9210. dir: dir isR
  9211. --- END Output Phase ---
  9212. /|\--- Input Phase ---
  9213. =>WM: (13546: I2 ^dir R)
  9214. =>WM: (13545: I2 ^reward 1)
  9215. =>WM: (13544: I2 ^see 1)
  9216. =>WM: (13543: N967 ^status complete)
  9217. <=WM: (13531: I2 ^dir L)
  9218. <=WM: (13530: I2 ^reward 1)
  9219. <=WM: (13529: I2 ^see 0)
  9220. =>WM: (13547: I2 ^level-1 L1-root)
  9221. <=WM: (13532: I2 ^level-1 R1-root)
  9222. --- END Input Phase ---
  9223. --- Proposal Phase ---
  9224. --- Inner Elaboration Phase, active level 1 (S1) ---
  9225. Firing rl*prefer*rvt*predict-yes*H0*5*H1*9
  9226. -->
  9227. (S1 ^operator O1933 = 0.7762516854360593)
  9228. Firing prefer*rvt*predict-yes*H0*5*H1
  9229. -->
  9230. Firing elaborate*copy-see-to-output-link
  9231. -->
  9232. (I3 ^see 1 +)
  9233. Firing elaborate*reward*based*on*reward
  9234. -->
  9235. (R971 ^value 1 +)
  9236. (R1 ^reward R971 +)
  9237. Firing propose*predict-yes
  9238. -->
  9239. (O1935 ^name predict-yes +)
  9240. (S1 ^operator O1935 +)
  9241. Firing propose*predict-no
  9242. -->
  9243. (O1936 ^name predict-no +)
  9244. (S1 ^operator O1936 +)
  9245. Firing rl*prefer*rvt*predict-no*H0*6
  9246. -->
  9247. (S1 ^operator O1934 = 0.9994824970933811)
  9248. Firing rl*prefer*rvt*predict-yes*H0*5
  9249. -->
  9250. (S1 ^operator O1933 = 0.2239472927001273)
  9251. Firing prefer*rvt*predict-yes*H0
  9252. -->
  9253. Firing prefer*rvt*predict-no*H0
  9254. -->
  9255. Firing elaborate*copy-dir-to-output-link
  9256. -->
  9257. (I3 ^dir R +)
  9258. inner elaboration loop at bottom goal.
  9259. Retracting elaborate*copy-see-to-output-link
  9260. -->
  9261. (I3 ^see 0 +)
  9262. Retracting propose*predict-no
  9263. -->
  9264. (O1934 ^name predict-no +)
  9265. (S1 ^operator O1934 +)
  9266. Retracting propose*predict-yes
  9267. -->
  9268. (O1933 ^name predict-yes +)
  9269. (S1 ^operator O1933 +)
  9270. Retracting elaborate*reward*based*on*reward
  9271. -->
  9272. (R970 ^value 1 +)
  9273. (R1 ^reward R970 +)
  9274. Retracting elaborate*copy-dir-to-output-link
  9275. -->
  9276. (I3 ^dir L +)
  9277. Retracting rl*prefer*rvt*predict-no*H0*2
  9278. -->
  9279. (S1 ^operator O1934 = 0.2381452180684112)
  9280. Retracting rl*prefer*rvt*predict-no*H0*2*H1*8
  9281. -->
  9282. (S1 ^operator O1934 = -0.1970449706966682)
  9283. Retracting rl*prefer*rvt*predict-yes*H0*1
  9284. -->
  9285. (S1 ^operator O1933 = 0.3499208575982964)
  9286. Retracting rl*prefer*rvt*predict-yes*H0*1*H1*7
  9287. -->
  9288. (S1 ^operator O1933 = 0.6500793194524461)
  9289. =>WM: (13555: S1 ^operator O1936 +)
  9290. =>WM: (13554: S1 ^operator O1935 +)
  9291. =>WM: (13553: I3 ^dir R)
  9292. =>WM: (13552: O1936 ^name predict-no)
  9293. =>WM: (13551: O1935 ^name predict-yes)
  9294. =>WM: (13550: R971 ^value 1)
  9295. =>WM: (13549: R1 ^reward R971)
  9296. =>WM: (13548: I3 ^see 1)
  9297. <=WM: (13539: S1 ^operator O1933 +)
  9298. <=WM: (13541: S1 ^operator O1933)
  9299. <=WM: (13540: S1 ^operator O1934 +)
  9300. <=WM: (13538: I3 ^dir L)
  9301. <=WM: (13534: R1 ^reward R970)
  9302. <=WM: (13533: I3 ^see 0)
  9303. <=WM: (13537: O1934 ^name predict-no)
  9304. <=WM: (13536: O1933 ^name predict-yes)
  9305. <=WM: (13535: R970 ^value 1)
  9306. --- Inner Elaboration Phase, active level 1 (S1) ---
  9307. Firing prefer*rvt*predict-yes*H0
  9308. -->
  9309. Firing rl*prefer*rvt*predict-yes*H0*5
  9310. -->
  9311. (S1 ^operator O1935 = 0.2239472927001273)
  9312. Firing prefer*rvt*predict-yes*H0*5*H1
  9313. -->
  9314. Firing rl*prefer*rvt*predict-yes*H0*5*H1*9
  9315. -->
  9316. (S1 ^operator O1935 = 0.7762516854360593)
  9317. Firing prefer*rvt*predict-no*H0
  9318. -->
  9319. Firing rl*prefer*rvt*predict-no*H0*6
  9320. -->
  9321. (S1 ^operator O1936 = 0.9994824970933811)
  9322. inner elaboration loop at bottom goal.
  9323. Retracting rl*prefer*rvt*predict-no*H0*6
  9324. -->
  9325. (S1 ^operator O1934 = 0.9994824970933811)
  9326. Retracting rl*prefer*rvt*predict-yes*H0*5
  9327. -->
  9328. (S1 ^operator O1933 = 0.2239472927001273)
  9329. Retracting rl*prefer*rvt*predict-yes*H0*5*H1*9
  9330. -->
  9331. (S1 ^operator O1933 = 0.7762516854360593)
  9332. --- END Proposal Phase ---
  9333. --- Decision Phase ---
  9334. RL update rl*prefer*rvt*predict-yes*H0*1 0.407927 -0.0580064 0.349921 -> 0.407928 -0.0580071 0.349921(R,m,v=1,0.897959,0.0922561)
  9335. RL update rl*prefer*rvt*predict-yes*H0*1*H1*7 0.592065 0.0580144 0.650079 -> 0.592066 0.0580136 0.650079(R,m,v=1,1,0)
  9336. =>WM: (13556: S1 ^operator O1935)
  9337. 968: O: O1935 (predict-yes)
  9338. --- END Decision Phase ---
  9339. --- Application Phase ---
  9340. --- Firing Productions (PE) For State At Depth 1 ---
  9341. --- Inner Elaboration Phase, active level 1 (S1) ---
  9342. Firing apply*operator
  9343. -->
  9344. (I3 ^predict-yes N968 + :O )
  9345. Firing apply*operator*complete
  9346. -->
  9347. (I3 ^predict-yes N967 - :O )
  9348. inner elaboration loop at bottom goal.
  9349. --- Change Working Memory (PE) ---
  9350. =>WM: (13557: I3 ^predict-yes N968)
  9351. <=WM: (13543: N967 ^status complete)
  9352. <=WM: (13542: I3 ^predict-yes N967)
  9353. --- Firing Productions (IE) For State At Depth 1 ---
  9354. --- Inner Elaboration Phase, active level 1 (S1) ---
  9355. Firing monitor*world
  9356. -->
  9357. I see 1 and I'm going to do: predict-yes inner elaboration loop at bottom goal.
  9358. --- Change Working Memory (IE) ---
  9359. --- END Application Phase ---
  9360. --- Output Phase ---
  9361. ENV: Agent did: predict-yes for direction R in state State-A
  9362. In State-A moving R
  9363. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  9364. predict error 0
  9365. dir: dir isU
  9366. --- END Output Phase ---
  9367. -/--- Input Phase ---
  9368. =>WM: (13561: I2 ^dir U)
  9369. =>WM: (13560: I2 ^reward 1)
  9370. =>WM: (13559: I2 ^see 1)
  9371. =>WM: (13558: N968 ^status complete)
  9372. <=WM: (13546: I2 ^dir R)
  9373. <=WM: (13545: I2 ^reward 1)
  9374. <=WM: (13544: I2 ^see 1)
  9375. =>WM: (13562: I2 ^level-1 R1-root)
  9376. <=WM: (13547: I2 ^level-1 L1-root)
  9377. --- END Input Phase ---
  9378. --- Proposal Phase ---
  9379. --- Inner Elaboration Phase, active level 1 (S1) ---
  9380. Firing elaborate*copy-see-to-output-link
  9381. -->
  9382. (I3 ^see 1 +)
  9383. Firing elaborate*reward*based*on*reward
  9384. -->
  9385. (R972 ^value 1 +)
  9386. (R1 ^reward R972 +)
  9387. Firing propose*predict-yes
  9388. -->
  9389. (O1937 ^name predict-yes +)
  9390. (S1 ^operator O1937 +)
  9391. Firing propose*predict-no
  9392. -->
  9393. (O1938 ^name predict-no +)
  9394. (S1 ^operator O1938 +)
  9395. Firing rl*prefer*rvt*predict-no*H0*4
  9396. -->
  9397. (S1 ^operator O1936 = 1.)
  9398. Firing rl*prefer*rvt*predict-yes*H0*3
  9399. -->
  9400. (S1 ^operator O1935 = 0.)
  9401. Firing prefer*rvt*predict-yes*H0
  9402. -->
  9403. Firing prefer*rvt*predict-no*H0
  9404. -->
  9405. Firing elaborate*copy-dir-to-output-link
  9406. -->
  9407. (I3 ^dir U +)
  9408. inner elaboration loop at bottom goal.
  9409. Retracting elaborate*copy-see-to-output-link
  9410. -->
  9411. (I3 ^see 1 +)
  9412. Retracting propose*predict-no
  9413. -->
  9414. (O1936 ^name predict-no +)
  9415. (S1 ^operator O1936 +)
  9416. Retracting propose*predict-yes
  9417. -->
  9418. (O1935 ^name predict-yes +)
  9419. (S1 ^operator O1935 +)
  9420. Retracting elaborate*reward*based*on*reward
  9421. -->
  9422. (R971 ^value 1 +)
  9423. (R1 ^reward R971 +)
  9424. Retracting elaborate*copy-dir-to-output-link
  9425. -->
  9426. (I3 ^dir R +)
  9427. Retracting rl*prefer*rvt*predict-no*H0*6
  9428. -->
  9429. (S1 ^operator O1936 = 0.9994824970933811)
  9430. Retracting rl*prefer*rvt*predict-yes*H0*5*H1*9
  9431. -->
  9432. (S1 ^operator O1935 = 0.7762516854360593)
  9433. Retracting rl*prefer*rvt*predict-yes*H0*5
  9434. -->
  9435. (S1 ^operator O1935 = 0.2239472927001273)
  9436. =>WM: (13569: S1 ^operator O1938 +)
  9437. =>WM: (13568: S1 ^operator O1937 +)
  9438. =>WM: (13567: I3 ^dir U)
  9439. =>WM: (13566: O1938 ^name predict-no)
  9440. =>WM: (13565: O1937 ^name predict-yes)
  9441. =>WM: (13564: R972 ^value 1)
  9442. =>WM: (13563: R1 ^reward R972)
  9443. <=WM: (13554: S1 ^operator O1935 +)
  9444. <=WM: (13556: S1 ^operator O1935)
  9445. <=WM: (13555: S1 ^operator O1936 +)
  9446. <=WM: (13553: I3 ^dir R)
  9447. <=WM: (13549: R1 ^reward R971)
  9448. <=WM: (13552: O1936 ^name predict-no)
  9449. <=WM: (13551: O1935 ^name predict-yes)
  9450. <=WM: (13550: R971 ^value 1)
  9451. --- Inner Elaboration Phase, active level 1 (S1) ---
  9452. Firing prefer*rvt*predict-yes*H0
  9453. -->
  9454. Firing rl*prefer*rvt*predict-yes*H0*3
  9455. -->
  9456. (S1 ^operator O1937 = 0.)
  9457. Firing prefer*rvt*predict-no*H0
  9458. -->
  9459. Firing rl*prefer*rvt*predict-no*H0*4
  9460. -->
  9461. (S1 ^operator O1938 = 1.)
  9462. inner elaboration loop at bottom goal.
  9463. Retracting rl*prefer*rvt*predict-no*H0*4
  9464. -->
  9465. (S1 ^operator O1936 = 1.)
  9466. Retracting rl*prefer*rvt*predict-yes*H0*3
  9467. -->
  9468. (S1 ^operator O1935 = 0.)
  9469. --- END Proposal Phase ---
  9470. --- Decision Phase ---
  9471. RL update rl*prefer*rvt*predict-yes*H0*5 0.553559 -0.329612 0.223947 -> 0.553542 -0.329612 0.223931(R,m,v=1,0.853333,0.125996)
  9472. RL update rl*prefer*rvt*predict-yes*H0*5*H1*9 0.44664 0.329612 0.776252 -> 0.446621 0.329612 0.776232(R,m,v=1,1,0)
  9473. =>WM: (13570: S1 ^operator O1938)
  9474. 969: O: O1938 (predict-no)
  9475. --- END Decision Phase ---
  9476. --- Application Phase ---
  9477. --- Firing Productions (PE) For State At Depth 1 ---
  9478. --- Inner Elaboration Phase, active level 1 (S1) ---
  9479. Firing apply*operator
  9480. -->
  9481. (I3 ^predict-no N969 + :O )
  9482. Firing apply*operator*complete
  9483. -->
  9484. (I3 ^predict-yes N968 - :O )
  9485. inner elaboration loop at bottom goal.
  9486. --- Change Working Memory (PE) ---
  9487. =>WM: (13571: I3 ^predict-no N969)
  9488. <=WM: (13558: N968 ^status complete)
  9489. <=WM: (13557: I3 ^predict-yes N968)
  9490. --- Firing Productions (IE) For State At Depth 1 ---
  9491. --- Inner Elaboration Phase, active level 1 (S1) ---
  9492. Firing monitor*world
  9493. -->
  9494. I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
  9495. --- Change Working Memory (IE) ---
  9496. --- END Application Phase ---
  9497. --- Output Phase ---
  9498. ENV: Agent did: predict-no for direction U in state State-B
  9499. In State-B moving U
  9500. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  9501. predict error 0
  9502. dir: dir isL
  9503. --- END Output Phase ---
  9504. |\--- Input Phase ---
  9505. =>WM: (13575: I2 ^dir L)
  9506. =>WM: (13574: I2 ^reward 1)
  9507. =>WM: (13573: I2 ^see 0)
  9508. =>WM: (13572: N969 ^status complete)
  9509. <=WM: (13561: I2 ^dir U)
  9510. <=WM: (13560: I2 ^reward 1)
  9511. <=WM: (13559: I2 ^see 1)
  9512. =>WM: (13576: I2 ^level-1 R1-root)
  9513. <=WM: (13562: I2 ^level-1 R1-root)
  9514. --- END Input Phase ---
  9515. --- Proposal Phase ---
  9516. --- Inner Elaboration Phase, active level 1 (S1) ---
  9517. Firing rl*prefer*rvt*predict-no*H0*2*H1*8
  9518. -->
  9519. (S1 ^operator O1938 = -0.1970449706966682)
  9520. Firing rl*prefer*rvt*predict-yes*H0*1*H1*7
  9521. -->
  9522. (S1 ^operator O1937 = 0.6500793023440685)
  9523. Firing prefer*rvt*predict-no*H0*2*H1
  9524. -->
  9525. Firing prefer*rvt*predict-yes*H0*1*H1
  9526. -->
  9527. Firing elaborate*copy-see-to-output-link
  9528. -->
  9529. (I3 ^see 0 +)
  9530. Firing elaborate*reward*based*on*reward
  9531. -->
  9532. (R973 ^value 1 +)
  9533. (R1 ^reward R973 +)
  9534. Firing propose*predict-yes
  9535. -->
  9536. (O1939 ^name predict-yes +)
  9537. (S1 ^operator O1939 +)
  9538. Firing propose*predict-no
  9539. -->
  9540. (O1940 ^name predict-no +)
  9541. (S1 ^operator O1940 +)
  9542. Firing rl*prefer*rvt*predict-no*H0*2
  9543. -->
  9544. (S1 ^operator O1938 = 0.2381452180684112)
  9545. Firing rl*prefer*rvt*predict-yes*H0*1
  9546. -->
  9547. (S1 ^operator O1937 = 0.3499208428205036)
  9548. Firing prefer*rvt*predict-yes*H0
  9549. -->
  9550. Firing prefer*rvt*predict-no*H0
  9551. -->
  9552. Firing elaborate*copy-dir-to-output-link
  9553. -->
  9554. (I3 ^dir L +)
  9555. inner elaboration loop at bottom goal.
  9556. Retracting elaborate*copy-see-to-output-link
  9557. -->
  9558. (I3 ^see 1 +)
  9559. Retracting propose*predict-no
  9560. -->
  9561. (O1938 ^name predict-no +)
  9562. (S1 ^operator O1938 +)
  9563. Retracting propose*predict-yes
  9564. -->
  9565. (O1937 ^name predict-yes +)
  9566. (S1 ^operator O1937 +)
  9567. Retracting elaborate*reward*based*on*reward
  9568. -->
  9569. (R972 ^value 1 +)
  9570. (R1 ^reward R972 +)
  9571. Retracting elaborate*copy-dir-to-output-link
  9572. -->
  9573. (I3 ^dir U +)
  9574. Retracting rl*prefer*rvt*predict-no*H0*4
  9575. -->
  9576. (S1 ^operator O1938 = 1.)
  9577. Retracting rl*prefer*rvt*predict-yes*H0*3
  9578. -->
  9579. (S1 ^operator O1937 = 0.)
  9580. =>WM: (13584: S1 ^operator O1940 +)
  9581. =>WM: (13583: S1 ^operator O1939 +)
  9582. =>WM: (13582: I3 ^dir L)
  9583. =>WM: (13581: O1940 ^name predict-no)
  9584. =>WM: (13580: O1939 ^name predict-yes)
  9585. =>WM: (13579: R973 ^value 1)
  9586. =>WM: (13578: R1 ^reward R973)
  9587. =>WM: (13577: I3 ^see 0)
  9588. <=WM: (13568: S1 ^operator O1937 +)
  9589. <=WM: (13569: S1 ^operator O1938 +)
  9590. <=WM: (13570: S1 ^operator O1938)
  9591. <=WM: (13567: I3 ^dir U)
  9592. <=WM: (13563: R1 ^reward R972)
  9593. <=WM: (13548: I3 ^see 1)
  9594. <=WM: (13566: O1938 ^name predict-no)
  9595. <=WM: (13565: O1937 ^name predict-yes)
  9596. <=WM: (13564: R972 ^value 1)
  9597. --- Inner Elaboration Phase, active level 1 (S1) ---
  9598. Firing prefer*rvt*predict-yes*H0
  9599. -->
  9600. Firing rl*prefer*rvt*predict-yes*H0*1*H1*7
  9601. -->
  9602. (S1 ^operator O1939 = 0.6500793023440685)
  9603. Firing rl*prefer*rvt*predict-yes*H0*1
  9604. -->
  9605. (S1 ^operator O1939 = 0.3499208428205036)
  9606. Firing prefer*rvt*predict-yes*H0*1*H1
  9607. -->
  9608. Firing prefer*rvt*predict-no*H0
  9609. -->
  9610. Firing rl*prefer*rvt*predict-no*H0*2*H1*8
  9611. -->
  9612. (S1 ^operator O1940 = -0.1970449706966682)
  9613. Firing rl*prefer*rvt*predict-no*H0*2
  9614. -->
  9615. (S1 ^operator O1940 = 0.2381452180684112)
  9616. Firing prefer*rvt*predict-no*H0*2*H1
  9617. -->
  9618. inner elaboration loop at bottom goal.
  9619. Retracting rl*prefer*rvt*predict-no*H0*2
  9620. -->
  9621. (S1 ^operator O1938 = 0.2381452180684112)
  9622. Retracting rl*prefer*rvt*predict-no*H0*2*H1*8
  9623. -->
  9624. (S1 ^operator O1938 = -0.1970449706966682)
  9625. Retracting rl*prefer*rvt*predict-yes*H0*1
  9626. -->
  9627. (S1 ^operator O1937 = 0.3499208428205036)
  9628. Retracting rl*prefer*rvt*predict-yes*H0*1*H1*7
  9629. -->
  9630. (S1 ^operator O1937 = 0.6500793023440685)
  9631. --- END Proposal Phase ---
  9632. --- Decision Phase ---
  9633. RL update rl*prefer*rvt*predict-no*H0*4 1 0 1 -> 1 0 1(R,m,v=1,1,0)
  9634. =>WM: (13585: S1 ^operator O1939)
  9635. 970: O: O1939 (predict-yes)
  9636. --- END Decision Phase ---
  9637. --- Application Phase ---
  9638. --- Firing Productions (PE) For State At Depth 1 ---
  9639. --- Inner Elaboration Phase, active level 1 (S1) ---
  9640. Firing apply*operator
  9641. -->
  9642. (I3 ^predict-yes N970 + :O )
  9643. Firing apply*operator*complete
  9644. -->
  9645. (I3 ^predict-no N969 - :O )
  9646. inner elaboration loop at bottom goal.
  9647. --- Change Working Memory (PE) ---
  9648. =>WM: (13586: I3 ^predict-yes N970)
  9649. <=WM: (13572: N969 ^status complete)
  9650. <=WM: (13571: I3 ^predict-no N969)
  9651. --- Firing Productions (IE) For State At Depth 1 ---
  9652. --- Inner Elaboration Phase, active level 1 (S1) ---
  9653. Firing monitor*world
  9654. -->
  9655. I see 1 and I'm going to do: predict-yes inner elaboration loop at bottom goal.
  9656. --- Change Working Memory (IE) ---
  9657. --- END Application Phase ---
  9658. --- Output Phase ---
  9659. ENV: Agent did: predict-yes for direction L in state State-B
  9660. In State-B moving L
  9661. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  9662. predict error 0
  9663. dir: dir isU
  9664. --- END Output Phase ---
  9665. -/|--- Input Phase ---
  9666. =>WM: (13590: I2 ^dir U)
  9667. =>WM: (13589: I2 ^reward 1)
  9668. =>WM: (13588: I2 ^see 1)
  9669. =>WM: (13587: N970 ^status complete)
  9670. <=WM: (13575: I2 ^dir L)
  9671. <=WM: (13574: I2 ^reward 1)
  9672. <=WM: (13573: I2 ^see 0)
  9673. =>WM: (13591: I2 ^level-1 L1-root)
  9674. <=WM: (13576: I2 ^level-1 R1-root)
  9675. --- END Input Phase ---
  9676. --- Proposal Phase ---
  9677. --- Inner Elaboration Phase, active level 1 (S1) ---
  9678. Firing elaborate*copy-see-to-output-link
  9679. -->
  9680. (I3 ^see 1 +)
  9681. Firing elaborate*reward*based*on*reward
  9682. -->
  9683. (R974 ^value 1 +)
  9684. (R1 ^reward R974 +)
  9685. Firing propose*predict-yes
  9686. -->
  9687. (O1941 ^name predict-yes +)
  9688. (S1 ^operator O1941 +)
  9689. Firing propose*predict-no
  9690. -->
  9691. (O1942 ^name predict-no +)
  9692. (S1 ^operator O1942 +)
  9693. Firing rl*prefer*rvt*predict-no*H0*4
  9694. -->
  9695. (S1 ^operator O1940 = 1.)
  9696. Firing rl*prefer*rvt*predict-yes*H0*3
  9697. -->
  9698. (S1 ^operator O1939 = 0.)
  9699. Firing prefer*rvt*predict-yes*H0
  9700. -->
  9701. Firing prefer*rvt*predict-no*H0
  9702. -->
  9703. Firing elaborate*copy-dir-to-output-link
  9704. -->
  9705. (I3 ^dir U +)
  9706. inner elaboration loop at bottom goal.
  9707. Retracting elaborate*copy-see-to-output-link
  9708. -->
  9709. (I3 ^see 0 +)
  9710. Retracting propose*predict-no
  9711. -->
  9712. (O1940 ^name predict-no +)
  9713. (S1 ^operator O1940 +)
  9714. Retracting propose*predict-yes
  9715. -->
  9716. (O1939 ^name predict-yes +)
  9717. (S1 ^operator O1939 +)
  9718. Retracting elaborate*reward*based*on*reward
  9719. -->
  9720. (R973 ^value 1 +)
  9721. (R1 ^reward R973 +)
  9722. Retracting elaborate*copy-dir-to-output-link
  9723. -->
  9724. (I3 ^dir L +)
  9725. Retracting rl*prefer*rvt*predict-no*H0*2
  9726. -->
  9727. (S1 ^operator O1940 = 0.2381452180684112)
  9728. Retracting rl*prefer*rvt*predict-no*H0*2*H1*8
  9729. -->
  9730. (S1 ^operator O1940 = -0.1970449706966682)
  9731. Retracting rl*prefer*rvt*predict-yes*H0*1
  9732. -->
  9733. (S1 ^operator O1939 = 0.3499208428205036)
  9734. Retracting rl*prefer*rvt*predict-yes*H0*1*H1*7
  9735. -->
  9736. (S1 ^operator O1939 = 0.6500793023440685)
  9737. =>WM: (13599: S1 ^operator O1942 +)
  9738. =>WM: (13598: S1 ^operator O1941 +)
  9739. =>WM: (13597: I3 ^dir U)
  9740. =>WM: (13596: O1942 ^name predict-no)
  9741. =>WM: (13595: O1941 ^name predict-yes)
  9742. =>WM: (13594: R974 ^value 1)
  9743. =>WM: (13593: R1 ^reward R974)
  9744. =>WM: (13592: I3 ^see 1)
  9745. <=WM: (13583: S1 ^operator O1939 +)
  9746. <=WM: (13585: S1 ^operator O1939)
  9747. <=WM: (13584: S1 ^operator O1940 +)
  9748. <=WM: (13582: I3 ^dir L)
  9749. <=WM: (13578: R1 ^reward R973)
  9750. <=WM: (13577: I3 ^see 0)
  9751. <=WM: (13581: O1940 ^name predict-no)
  9752. <=WM: (13580: O1939 ^name predict-yes)
  9753. <=WM: (13579: R973 ^value 1)
  9754. --- Inner Elaboration Phase, active level 1 (S1) ---
  9755. Firing prefer*rvt*predict-yes*H0
  9756. -->
  9757. Firing rl*prefer*rvt*predict-yes*H0*3
  9758. -->
  9759. (S1 ^operator O1941 = 0.)
  9760. Firing prefer*rvt*predict-no*H0
  9761. -->
  9762. Firing rl*prefer*rvt*predict-no*H0*4
  9763. -->
  9764. (S1 ^operator O1942 = 1.)
  9765. inner elaboration loop at bottom goal.
  9766. Retracting rl*prefer*rvt*predict-no*H0*4
  9767. -->
  9768. (S1 ^operator O1940 = 1.)
  9769. Retracting rl*prefer*rvt*predict-yes*H0*3
  9770. -->
  9771. (S1 ^operator O1939 = 0.)
  9772. --- END Proposal Phase ---
  9773. --- Decision Phase ---
  9774. RL update rl*prefer*rvt*predict-yes*H0*1 0.407928 -0.0580071 0.349921 -> 0.407928 -0.0580076 0.349921(R,m,v=1,0.898649,0.0916988)
  9775. RL update rl*prefer*rvt*predict-yes*H0*1*H1*7 0.592066 0.0580136 0.650079 -> 0.592066 0.058013 0.650079(R,m,v=1,1,0)
  9776. =>WM: (13600: S1 ^operator O1942)
  9777. 971: O: O1942 (predict-no)
  9778. --- END Decision Phase ---
  9779. --- Application Phase ---
  9780. --- Firing Productions (PE) For State At Depth 1 ---
  9781. --- Inner Elaboration Phase, active level 1 (S1) ---
  9782. Firing apply*operator
  9783. -->
  9784. (I3 ^predict-no N971 + :O )
  9785. Firing apply*operator*complete
  9786. -->
  9787. (I3 ^predict-yes N970 - :O )
  9788. inner elaboration loop at bottom goal.
  9789. --- Change Working Memory (PE) ---
  9790. =>WM: (13601: I3 ^predict-no N971)
  9791. <=WM: (13587: N970 ^status complete)
  9792. <=WM: (13586: I3 ^predict-yes N970)
  9793. --- Firing Productions (IE) For State At Depth 1 ---
  9794. --- Inner Elaboration Phase, active level 1 (S1) ---
  9795. Firing monitor*world
  9796. -->
  9797. I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
  9798. --- Change Working Memory (IE) ---
  9799. --- END Application Phase ---
  9800. --- Output Phase ---
  9801. ENV: Agent did: predict-no for direction U in state State-A
  9802. In State-A moving U
  9803. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  9804. predict error 0
  9805. dir: dir isL
  9806. --- END Output Phase ---
  9807. \--- Input Phase ---
  9808. =>WM: (13605: I2 ^dir L)
  9809. =>WM: (13604: I2 ^reward 1)
  9810. =>WM: (13603: I2 ^see 0)
  9811. =>WM: (13602: N971 ^status complete)
  9812. <=WM: (13590: I2 ^dir U)
  9813. <=WM: (13589: I2 ^reward 1)
  9814. <=WM: (13588: I2 ^see 1)
  9815. =>WM: (13606: I2 ^level-1 L1-root)
  9816. <=WM: (13591: I2 ^level-1 L1-root)
  9817. --- END Input Phase ---
  9818. --- Proposal Phase ---
  9819. --- Inner Elaboration Phase, active level 1 (S1) ---
  9820. Firing rl*prefer*rvt*predict-no*H0*2*H1*14
  9821. -->
  9822. (S1 ^operator O1942 = 0.7618983949435152)
  9823. Firing rl*prefer*rvt*predict-yes*H0*1*H1*15
  9824. -->
  9825. (S1 ^operator O1941 = -0.2915346922215271)
  9826. Firing prefer*rvt*predict-no*H0*2*H1
  9827. -->
  9828. Firing prefer*rvt*predict-yes*H0*1*H1
  9829. -->
  9830. Firing elaborate*copy-see-to-output-link
  9831. -->
  9832. (I3 ^see 0 +)
  9833. Firing elaborate*reward*based*on*reward
  9834. -->
  9835. (R975 ^value 1 +)
  9836. (R1 ^reward R975 +)
  9837. Firing propose*predict-yes
  9838. -->
  9839. (O1943 ^name predict-yes +)
  9840. (S1 ^operator O1943 +)
  9841. Firing propose*predict-no
  9842. -->
  9843. (O1944 ^name predict-no +)
  9844. (S1 ^operator O1944 +)
  9845. Firing rl*prefer*rvt*predict-no*H0*2
  9846. -->
  9847. (S1 ^operator O1942 = 0.2381452180684112)
  9848. Firing rl*prefer*rvt*predict-yes*H0*1
  9849. -->
  9850. (S1 ^operator O1941 = 0.3499208307178328)
  9851. Firing prefer*rvt*predict-yes*H0
  9852. -->
  9853. Firing prefer*rvt*predict-no*H0
  9854. -->
  9855. Firing elaborate*copy-dir-to-output-link
  9856. -->
  9857. (I3 ^dir L +)
  9858. inner elaboration loop at bottom goal.
  9859. Retracting elaborate*copy-see-to-output-link
  9860. -->
  9861. (I3 ^see 1 +)
  9862. Retracting propose*predict-no
  9863. -->
  9864. (O1942 ^name predict-no +)
  9865. (S1 ^operator O1942 +)
  9866. Retracting propose*predict-yes
  9867. -->
  9868. (O1941 ^name predict-yes +)
  9869. (S1 ^operator O1941 +)
  9870. Retracting elaborate*reward*based*on*reward
  9871. -->
  9872. (R974 ^value 1 +)
  9873. (R1 ^reward R974 +)
  9874. Retracting elaborate*copy-dir-to-output-link
  9875. -->
  9876. (I3 ^dir U +)
  9877. Retracting rl*prefer*rvt*predict-no*H0*4
  9878. -->
  9879. (S1 ^operator O1942 = 1.)
  9880. Retracting rl*prefer*rvt*predict-yes*H0*3
  9881. -->
  9882. (S1 ^operator O1941 = 0.)
  9883. =>WM: (13614: S1 ^operator O1944 +)
  9884. =>WM: (13613: S1 ^operator O1943 +)
  9885. =>WM: (13612: I3 ^dir L)
  9886. =>WM: (13611: O1944 ^name predict-no)
  9887. =>WM: (13610: O1943 ^name predict-yes)
  9888. =>WM: (13609: R975 ^value 1)
  9889. =>WM: (13608: R1 ^reward R975)
  9890. =>WM: (13607: I3 ^see 0)
  9891. <=WM: (13598: S1 ^operator O1941 +)
  9892. <=WM: (13599: S1 ^operator O1942 +)
  9893. <=WM: (13600: S1 ^operator O1942)
  9894. <=WM: (13597: I3 ^dir U)
  9895. <=WM: (13593: R1 ^reward R974)
  9896. <=WM: (13592: I3 ^see 1)
  9897. <=WM: (13596: O1942 ^name predict-no)
  9898. <=WM: (13595: O1941 ^name predict-yes)
  9899. <=WM: (13594: R974 ^value 1)
  9900. --- Inner Elaboration Phase, active level 1 (S1) ---
  9901. Firing prefer*rvt*predict-yes*H0
  9902. -->
  9903. Firing rl*prefer*rvt*predict-yes*H0*1*H1*15
  9904. -->
  9905. (S1 ^operator O1943 = -0.2915346922215271)
  9906. Firing rl*prefer*rvt*predict-yes*H0*1
  9907. -->
  9908. (S1 ^operator O1943 = 0.3499208307178328)
  9909. Firing prefer*rvt*predict-yes*H0*1*H1
  9910. -->
  9911. Firing prefer*rvt*predict-no*H0
  9912. -->
  9913. Firing rl*prefer*rvt*predict-no*H0*2*H1*14
  9914. -->
  9915. (S1 ^operator O1944 = 0.7618983949435152)
  9916. Firing rl*prefer*rvt*predict-no*H0*2
  9917. -->
  9918. (S1 ^operator O1944 = 0.2381452180684112)
  9919. Firing prefer*rvt*predict-no*H0*2*H1
  9920. -->
  9921. inner elaboration loop at bottom goal.
  9922. Retracting rl*prefer*rvt*predict-no*H0*2
  9923. -->
  9924. (S1 ^operator O1942 = 0.2381452180684112)
  9925. Retracting rl*prefer*rvt*predict-no*H0*2*H1*14
  9926. -->
  9927. (S1 ^operator O1942 = 0.7618983949435152)
  9928. Retracting rl*prefer*rvt*predict-yes*H0*1
  9929. -->
  9930. (S1 ^operator O1941 = 0.3499208307178328)
  9931. Retracting rl*prefer*rvt*predict-yes*H0*1*H1*15
  9932. -->
  9933. (S1 ^operator O1941 = -0.2915346922215271)
  9934. --- END Proposal Phase ---
  9935. --- Decision Phase ---
  9936. RL update rl*prefer*rvt*predict-no*H0*4 1 0 1 -> 1 0 1(R,m,v=1,1,0)
  9937. =>WM: (13615: S1 ^operator O1944)
  9938. 972: O: O1944 (predict-no)
  9939. --- END Decision Phase ---
  9940. --- Application Phase ---
  9941. --- Firing Productions (PE) For State At Depth 1 ---
  9942. --- Inner Elaboration Phase, active level 1 (S1) ---
  9943. Firing apply*operator
  9944. -->
  9945. (I3 ^predict-no N972 + :O )
  9946. Firing apply*operator*complete
  9947. -->
  9948. (I3 ^predict-no N971 - :O )
  9949. inner elaboration loop at bottom goal.
  9950. --- Change Working Memory (PE) ---
  9951. =>WM: (13616: I3 ^predict-no N972)
  9952. <=WM: (13602: N971 ^status complete)
  9953. <=WM: (13601: I3 ^predict-no N971)
  9954. --- Firing Productions (IE) For State At Depth 1 ---
  9955. --- Inner Elaboration Phase, active level 1 (S1) ---
  9956. Firing monitor*world
  9957. -->
  9958. I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
  9959. --- Change Working Memory (IE) ---
  9960. --- END Application Phase ---
  9961. --- Output Phase ---
  9962. ENV: Agent did: predict-no for direction L in state State-A
  9963. In State-A moving L
  9964. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  9965. predict error 0
  9966. dir: dir isR
  9967. --- END Output Phase ---
  9968. -/|--- Input Phase ---
  9969. =>WM: (13620: I2 ^dir R)
  9970. =>WM: (13619: I2 ^reward 1)
  9971. =>WM: (13618: I2 ^see 0)
  9972. =>WM: (13617: N972 ^status complete)
  9973. <=WM: (13605: I2 ^dir L)
  9974. <=WM: (13604: I2 ^reward 1)
  9975. <=WM: (13603: I2 ^see 0)
  9976. =>WM: (13621: I2 ^level-1 L0-root)
  9977. <=WM: (13606: I2 ^level-1 L1-root)
  9978. --- END Input Phase ---
  9979. --- Proposal Phase ---
  9980. --- Inner Elaboration Phase, active level 1 (S1) ---
  9981. Firing rl*prefer*rvt*predict-yes*H0*5*H1*16
  9982. -->
  9983. (S1 ^operator O1943 = 0.7757915959678818)
  9984. Firing prefer*rvt*predict-yes*H0*5*H1
  9985. -->
  9986. Firing elaborate*copy-see-to-output-link
  9987. -->
  9988. (I3 ^see 0 +)
  9989. Firing elaborate*reward*based*on*reward
  9990. -->
  9991. (R976 ^value 1 +)
  9992. (R1 ^reward R976 +)
  9993. Firing propose*predict-yes
  9994. -->
  9995. (O1945 ^name predict-yes +)
  9996. (S1 ^operator O1945 +)
  9997. Firing propose*predict-no
  9998. -->
  9999. (O1946 ^name predict-no +)
  10000. (S1 ^operator O1946 +)
  10001. Firing rl*prefer*rvt*predict-no*H0*6
  10002. -->
  10003. (S1 ^operator O1944 = 0.9994824970933811)
  10004. Firing rl*prefer*rvt*predict-yes*H0*5
  10005. -->
  10006. (S1 ^operator O1943 = 0.2239307405283143)
  10007. Firing prefer*rvt*predict-yes*H0
  10008. -->
  10009. Firing prefer*rvt*predict-no*H0
  10010. -->
  10011. Firing elaborate*copy-dir-to-output-link
  10012. -->
  10013. (I3 ^dir R +)
  10014. inner elaboration loop at bottom goal.
  10015. Retracting elaborate*copy-see-to-output-link
  10016. -->
  10017. (I3 ^see 0 +)
  10018. Retracting propose*predict-no
  10019. -->
  10020. (O1944 ^name predict-no +)
  10021. (S1 ^operator O1944 +)
  10022. Retracting propose*predict-yes
  10023. -->
  10024. (O1943 ^name predict-yes +)
  10025. (S1 ^operator O1943 +)
  10026. Retracting elaborate*reward*based*on*reward
  10027. -->
  10028. (R975 ^value 1 +)
  10029. (R1 ^reward R975 +)
  10030. Retracting elaborate*copy-dir-to-output-link
  10031. -->
  10032. (I3 ^dir L +)
  10033. Retracting rl*prefer*rvt*predict-no*H0*2
  10034. -->
  10035. (S1 ^operator O1944 = 0.2381452180684112)
  10036. Retracting rl*prefer*rvt*predict-no*H0*2*H1*14
  10037. -->
  10038. (S1 ^operator O1944 = 0.7618983949435152)
  10039. Retracting rl*prefer*rvt*predict-yes*H0*1
  10040. -->
  10041. (S1 ^operator O1943 = 0.3499208307178328)
  10042. Retracting rl*prefer*rvt*predict-yes*H0*1*H1*15
  10043. -->
  10044. (S1 ^operator O1943 = -0.2915346922215271)
  10045. =>WM: (13628: S1 ^operator O1946 +)
  10046. =>WM: (13627: S1 ^operator O1945 +)
  10047. =>WM: (13626: I3 ^dir R)
  10048. =>WM: (13625: O1946 ^name predict-no)
  10049. =>WM: (13624: O1945 ^name predict-yes)
  10050. =>WM: (13623: R976 ^value 1)
  10051. =>WM: (13622: R1 ^reward R976)
  10052. <=WM: (13613: S1 ^operator O1943 +)
  10053. <=WM: (13614: S1 ^operator O1944 +)
  10054. <=WM: (13615: S1 ^operator O1944)
  10055. <=WM: (13612: I3 ^dir L)
  10056. <=WM: (13608: R1 ^reward R975)
  10057. <=WM: (13611: O1944 ^name predict-no)
  10058. <=WM: (13610: O1943 ^name predict-yes)
  10059. <=WM: (13609: R975 ^value 1)
  10060. --- Inner Elaboration Phase, active level 1 (S1) ---
  10061. Firing prefer*rvt*predict-yes*H0
  10062. -->
  10063. Firing rl*prefer*rvt*predict-yes*H0*5
  10064. -->
  10065. (S1 ^operator O1945 = 0.2239307405283143)
  10066. Firing prefer*rvt*predict-yes*H0*5*H1
  10067. -->
  10068. Firing rl*prefer*rvt*predict-yes*H0*5*H1*16
  10069. -->
  10070. (S1 ^operator O1945 = 0.7757915959678818)
  10071. Firing prefer*rvt*predict-no*H0
  10072. -->
  10073. Firing rl*prefer*rvt*predict-no*H0*6
  10074. -->
  10075. (S1 ^operator O1946 = 0.9994824970933811)
  10076. inner elaboration loop at bottom goal.
  10077. Retracting rl*prefer*rvt*predict-no*H0*6
  10078. -->
  10079. (S1 ^operator O1944 = 0.9994824970933811)
  10080. Retracting rl*prefer*rvt*predict-yes*H0*5
  10081. -->
  10082. (S1 ^operator O1943 = 0.2239307405283143)
  10083. Retracting rl*prefer*rvt*predict-yes*H0*5*H1*16
  10084. -->
  10085. (S1 ^operator O1943 = 0.7757915959678818)
  10086. --- END Proposal Phase ---
  10087. --- Decision Phase ---
  10088. RL update rl*prefer*rvt*predict-no*H0*2 0.569329 -0.331184 0.238145 -> 0.569323 -0.331182 0.238142(R,m,v=1,0.881988,0.104736)
  10089. RL update rl*prefer*rvt*predict-no*H0*2*H1*14 0.430746 0.331153 0.761898 -> 0.430739 0.331156 0.761894(R,m,v=1,1,0)
  10090. =>WM: (13629: S1 ^operator O1945)
  10091. 973: O: O1945 (predict-yes)
  10092. --- END Decision Phase ---
  10093. --- Application Phase ---
  10094. --- Firing Productions (PE) For State At Depth 1 ---
  10095. --- Inner Elaboration Phase, active level 1 (S1) ---
  10096. Firing apply*operator
  10097. -->
  10098. (I3 ^predict-yes N973 + :O )
  10099. Firing apply*operator*complete
  10100. -->
  10101. (I3 ^predict-no N972 - :O )
  10102. inner elaboration loop at bottom goal.
  10103. --- Change Working Memory (PE) ---
  10104. =>WM: (13630: I3 ^predict-yes N973)
  10105. <=WM: (13617: N972 ^status complete)
  10106. <=WM: (13616: I3 ^predict-no N972)
  10107. --- Firing Productions (IE) For State At Depth 1 ---
  10108. --- Inner Elaboration Phase, active level 1 (S1) ---
  10109. Firing monitor*world
  10110. -->
  10111. I see 1 and I'm going to do: predict-yes inner elaboration loop at bottom goal.
  10112. --- Change Working Memory (IE) ---
  10113. --- END Application Phase ---
  10114. --- Output Phase ---
  10115. ENV: Agent did: predict-yes for direction R in state State-A
  10116. In State-A moving R
  10117. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  10118. predict error 0
  10119. dir: dir isU
  10120. --- END Output Phase ---
  10121. \-/--- Input Phase ---
  10122. =>WM: (13634: I2 ^dir U)
  10123. =>WM: (13633: I2 ^reward 1)
  10124. =>WM: (13632: I2 ^see 1)
  10125. =>WM: (13631: N973 ^status complete)
  10126. <=WM: (13620: I2 ^dir R)
  10127. <=WM: (13619: I2 ^reward 1)
  10128. <=WM: (13618: I2 ^see 0)
  10129. =>WM: (13635: I2 ^level-1 R1-root)
  10130. <=WM: (13621: I2 ^level-1 L0-root)
  10131. --- END Input Phase ---
  10132. --- Proposal Phase ---
  10133. --- Inner Elaboration Phase, active level 1 (S1) ---
  10134. Firing elaborate*copy-see-to-output-link
  10135. -->
  10136. (I3 ^see 1 +)
  10137. Firing elaborate*reward*based*on*reward
  10138. -->
  10139. (R977 ^value 1 +)
  10140. (R1 ^reward R977 +)
  10141. Firing propose*predict-yes
  10142. -->
  10143. (O1947 ^name predict-yes +)
  10144. (S1 ^operator O1947 +)
  10145. Firing propose*predict-no
  10146. -->
  10147. (O1948 ^name predict-no +)
  10148. (S1 ^operator O1948 +)
  10149. Firing rl*prefer*rvt*predict-no*H0*4
  10150. -->
  10151. (S1 ^operator O1946 = 1.)
  10152. Firing rl*prefer*rvt*predict-yes*H0*3
  10153. -->
  10154. (S1 ^operator O1945 = 0.)
  10155. Firing prefer*rvt*predict-yes*H0
  10156. -->
  10157. Firing prefer*rvt*predict-no*H0
  10158. -->
  10159. Firing elaborate*copy-dir-to-output-link
  10160. -->
  10161. (I3 ^dir U +)
  10162. inner elaboration loop at bottom goal.
  10163. Retracting elaborate*copy-see-to-output-link
  10164. -->
  10165. (I3 ^see 0 +)
  10166. Retracting propose*predict-no
  10167. -->
  10168. (O1946 ^name predict-no +)
  10169. (S1 ^operator O1946 +)
  10170. Retracting propose*predict-yes
  10171. -->
  10172. (O1945 ^name predict-yes +)
  10173. (S1 ^operator O1945 +)
  10174. Retracting elaborate*reward*based*on*reward
  10175. -->
  10176. (R976 ^value 1 +)
  10177. (R1 ^reward R976 +)
  10178. Retracting elaborate*copy-dir-to-output-link
  10179. -->
  10180. (I3 ^dir R +)
  10181. Retracting rl*prefer*rvt*predict-no*H0*6
  10182. -->
  10183. (S1 ^operator O1946 = 0.9994824970933811)
  10184. Retracting rl*prefer*rvt*predict-yes*H0*5*H1*16
  10185. -->
  10186. (S1 ^operator O1945 = 0.7757915959678818)
  10187. Retracting rl*prefer*rvt*predict-yes*H0*5
  10188. -->
  10189. (S1 ^operator O1945 = 0.2239307405283143)
  10190. =>WM: (13643: S1 ^operator O1948 +)
  10191. =>WM: (13642: S1 ^operator O1947 +)
  10192. =>WM: (13641: I3 ^dir U)
  10193. =>WM: (13640: O1948 ^name predict-no)
  10194. =>WM: (13639: O1947 ^name predict-yes)
  10195. =>WM: (13638: R977 ^value 1)
  10196. =>WM: (13637: R1 ^reward R977)
  10197. =>WM: (13636: I3 ^see 1)
  10198. <=WM: (13627: S1 ^operator O1945 +)
  10199. <=WM: (13629: S1 ^operator O1945)
  10200. <=WM: (13628: S1 ^operator O1946 +)
  10201. <=WM: (13626: I3 ^dir R)
  10202. <=WM: (13622: R1 ^reward R976)
  10203. <=WM: (13607: I3 ^see 0)
  10204. <=WM: (13625: O1946 ^name predict-no)
  10205. <=WM: (13624: O1945 ^name predict-yes)
  10206. <=WM: (13623: R976 ^value 1)
  10207. --- Inner Elaboration Phase, active level 1 (S1) ---
  10208. Firing prefer*rvt*predict-yes*H0
  10209. -->
  10210. Firing rl*prefer*rvt*predict-yes*H0*3
  10211. -->
  10212. (S1 ^operator O1947 = 0.)
  10213. Firing prefer*rvt*predict-no*H0
  10214. -->
  10215. Firing rl*prefer*rvt*predict-no*H0*4
  10216. -->
  10217. (S1 ^operator O1948 = 1.)
  10218. inner elaboration loop at bottom goal.
  10219. Retracting rl*prefer*rvt*predict-no*H0*4
  10220. -->
  10221. (S1 ^operator O1946 = 1.)
  10222. Retracting rl*prefer*rvt*predict-yes*H0*3
  10223. -->
  10224. (S1 ^operator O1945 = 0.)
  10225. --- END Proposal Phase ---
  10226. --- Decision Phase ---
  10227. RL update rl*prefer*rvt*predict-yes*H0*5 0.553542 -0.329612 0.223931 -> 0.553566 -0.329612 0.223954(R,m,v=1,0.854305,0.125298)
  10228. RL update rl*prefer*rvt*predict-yes*H0*5*H1*16 0.446175 0.329617 0.775792 -> 0.446202 0.329616 0.775819(R,m,v=1,1,0)
  10229. =>WM: (13644: S1 ^operator O1948)
  10230. 974: O: O1948 (predict-no)
  10231. --- END Decision Phase ---
  10232. --- Application Phase ---
  10233. --- Firing Productions (PE) For State At Depth 1 ---
  10234. --- Inner Elaboration Phase, active level 1 (S1) ---
  10235. Firing apply*operator
  10236. -->
  10237. (I3 ^predict-no N974 + :O )
  10238. Firing apply*operator*complete
  10239. -->
  10240. (I3 ^predict-yes N973 - :O )
  10241. inner elaboration loop at bottom goal.
  10242. --- Change Working Memory (PE) ---
  10243. =>WM: (13645: I3 ^predict-no N974)
  10244. <=WM: (13631: N973 ^status complete)
  10245. <=WM: (13630: I3 ^predict-yes N973)
  10246. --- Firing Productions (IE) For State At Depth 1 ---
  10247. --- Inner Elaboration Phase, active level 1 (S1) ---
  10248. Firing monitor*world
  10249. -->
  10250. I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
  10251. --- Change Working Memory (IE) ---
  10252. --- END Application Phase ---
  10253. --- Output Phase ---
  10254. ENV: Agent did: predict-no for direction U in state State-B
  10255. In State-B moving U
  10256. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  10257. predict error 0
  10258. dir: dir isL
  10259. --- END Output Phase ---
  10260. |\---- Input Phase ---
  10261. =>WM: (13649: I2 ^dir L)
  10262. =>WM: (13648: I2 ^reward 1)
  10263. =>WM: (13647: I2 ^see 0)
  10264. =>WM: (13646: N974 ^status complete)
  10265. <=WM: (13634: I2 ^dir U)
  10266. <=WM: (13633: I2 ^reward 1)
  10267. <=WM: (13632: I2 ^see 1)
  10268. =>WM: (13650: I2 ^level-1 R1-root)
  10269. <=WM: (13635: I2 ^level-1 R1-root)
  10270. --- END Input Phase ---
  10271. --- Proposal Phase ---
  10272. --- Inner Elaboration Phase, active level 1 (S1) ---
  10273. Firing rl*prefer*rvt*predict-no*H0*2*H1*8
  10274. -->
  10275. (S1 ^operator O1948 = -0.1970449706966682)
  10276. Firing rl*prefer*rvt*predict-yes*H0*1*H1*7
  10277. -->
  10278. (S1 ^operator O1947 = 0.6500792883581119)
  10279. Firing prefer*rvt*predict-no*H0*2*H1
  10280. -->
  10281. Firing prefer*rvt*predict-yes*H0*1*H1
  10282. -->
  10283. Firing elaborate*copy-see-to-output-link
  10284. -->
  10285. (I3 ^see 0 +)
  10286. Firing elaborate*reward*based*on*reward
  10287. -->
  10288. (R978 ^value 1 +)
  10289. (R1 ^reward R978 +)
  10290. Firing propose*predict-yes
  10291. -->
  10292. (O1949 ^name predict-yes +)
  10293. (S1 ^operator O1949 +)
  10294. Firing propose*predict-no
  10295. -->
  10296. (O1950 ^name predict-no +)
  10297. (S1 ^operator O1950 +)
  10298. Firing rl*prefer*rvt*predict-no*H0*2
  10299. -->
  10300. (S1 ^operator O1948 = 0.2381416323002802)
  10301. Firing rl*prefer*rvt*predict-yes*H0*1
  10302. -->
  10303. (S1 ^operator O1947 = 0.3499208307178328)
  10304. Firing prefer*rvt*predict-yes*H0
  10305. -->
  10306. Firing prefer*rvt*predict-no*H0
  10307. -->
  10308. Firing elaborate*copy-dir-to-output-link
  10309. -->
  10310. (I3 ^dir L +)
  10311. inner elaboration loop at bottom goal.
  10312. Retracting elaborate*copy-see-to-output-link
  10313. -->
  10314. (I3 ^see 1 +)
  10315. Retracting propose*predict-no
  10316. -->
  10317. (O1948 ^name predict-no +)
  10318. (S1 ^operator O1948 +)
  10319. Retracting propose*predict-yes
  10320. -->
  10321. (O1947 ^name predict-yes +)
  10322. (S1 ^operator O1947 +)
  10323. Retracting elaborate*reward*based*on*reward
  10324. -->
  10325. (R977 ^value 1 +)
  10326. (R1 ^reward R977 +)
  10327. Retracting elaborate*copy-dir-to-output-link
  10328. -->
  10329. (I3 ^dir U +)
  10330. Retracting rl*prefer*rvt*predict-no*H0*4
  10331. -->
  10332. (S1 ^operator O1948 = 1.)
  10333. Retracting rl*prefer*rvt*predict-yes*H0*3
  10334. -->
  10335. (S1 ^operator O1947 = 0.)
  10336. =>WM: (13658: S1 ^operator O1950 +)
  10337. =>WM: (13657: S1 ^operator O1949 +)
  10338. =>WM: (13656: I3 ^dir L)
  10339. =>WM: (13655: O1950 ^name predict-no)
  10340. =>WM: (13654: O1949 ^name predict-yes)
  10341. =>WM: (13653: R978 ^value 1)
  10342. =>WM: (13652: R1 ^reward R978)
  10343. =>WM: (13651: I3 ^see 0)
  10344. <=WM: (13642: S1 ^operator O1947 +)
  10345. <=WM: (13643: S1 ^operator O1948 +)
  10346. <=WM: (13644: S1 ^operator O1948)
  10347. <=WM: (13641: I3 ^dir U)
  10348. <=WM: (13637: R1 ^reward R977)
  10349. <=WM: (13636: I3 ^see 1)
  10350. <=WM: (13640: O1948 ^name predict-no)
  10351. <=WM: (13639: O1947 ^name predict-yes)
  10352. <=WM: (13638: R977 ^value 1)
  10353. --- Inner Elaboration Phase, active level 1 (S1) ---
  10354. Firing prefer*rvt*predict-yes*H0
  10355. -->
  10356. Firing rl*prefer*rvt*predict-yes*H0*1*H1*7
  10357. -->
  10358. (S1 ^operator O1949 = 0.6500792883581119)
  10359. Firing rl*prefer*rvt*predict-yes*H0*1
  10360. -->
  10361. (S1 ^operator O1949 = 0.3499208307178328)
  10362. Firing prefer*rvt*predict-yes*H0*1*H1
  10363. -->
  10364. Firing prefer*rvt*predict-no*H0
  10365. -->
  10366. Firing rl*prefer*rvt*predict-no*H0*2*H1*8
  10367. -->
  10368. (S1 ^operator O1950 = -0.1970449706966682)
  10369. Firing rl*prefer*rvt*predict-no*H0*2
  10370. -->
  10371. (S1 ^operator O1950 = 0.2381416323002802)
  10372. Firing prefer*rvt*predict-no*H0*2*H1
  10373. -->
  10374. inner elaboration loop at bottom goal.
  10375. Retracting rl*prefer*rvt*predict-no*H0*2
  10376. -->
  10377. (S1 ^operator O1948 = 0.2381416323002802)
  10378. Retracting rl*prefer*rvt*predict-no*H0*2*H1*8
  10379. -->
  10380. (S1 ^operator O1948 = -0.1970449706966682)
  10381. Retracting rl*prefer*rvt*predict-yes*H0*1
  10382. -->
  10383. (S1 ^operator O1947 = 0.3499208307178328)
  10384. Retracting rl*prefer*rvt*predict-yes*H0*1*H1*7
  10385. -->
  10386. (S1 ^operator O1947 = 0.6500792883581119)
  10387. --- END Proposal Phase ---
  10388. --- Decision Phase ---
  10389. RL update rl*prefer*rvt*predict-no*H0*4 1 0 1 -> 1 0 1(R,m,v=1,1,0)
  10390. =>WM: (13659: S1 ^operator O1949)
  10391. 975: O: O1949 (predict-yes)
  10392. --- END Decision Phase ---
  10393. --- Application Phase ---
  10394. --- Firing Productions (PE) For State At Depth 1 ---
  10395. --- Inner Elaboration Phase, active level 1 (S1) ---
  10396. Firing apply*operator
  10397. -->
  10398. (I3 ^predict-yes N975 + :O )
  10399. Firing apply*operator*complete
  10400. -->
  10401. (I3 ^predict-no N974 - :O )
  10402. inner elaboration loop at bottom goal.
  10403. --- Change Working Memory (PE) ---
  10404. =>WM: (13660: I3 ^predict-yes N975)
  10405. <=WM: (13646: N974 ^status complete)
  10406. <=WM: (13645: I3 ^predict-no N974)
  10407. --- Firing Productions (IE) For State At Depth 1 ---
  10408. --- Inner Elaboration Phase, active level 1 (S1) ---
  10409. Firing monitor*world
  10410. -->
  10411. I see 1 and I'm going to do: predict-yes inner elaboration loop at bottom goal.
  10412. --- Change Working Memory (IE) ---
  10413. --- END Application Phase ---
  10414. --- Output Phase ---
  10415. ENV: Agent did: predict-yes for direction L in state State-B
  10416. In State-B moving L
  10417. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  10418. predict error 0
  10419. dir: dir isR
  10420. --- END Output Phase ---
  10421. /|\--- Input Phase ---
  10422. =>WM: (13664: I2 ^dir R)
  10423. =>WM: (13663: I2 ^reward 1)
  10424. =>WM: (13662: I2 ^see 1)
  10425. =>WM: (13661: N975 ^status complete)
  10426. <=WM: (13649: I2 ^dir L)
  10427. <=WM: (13648: I2 ^reward 1)
  10428. <=WM: (13647: I2 ^see 0)
  10429. =>WM: (13665: I2 ^level-1 L1-root)
  10430. <=WM: (13650: I2 ^level-1 R1-root)
  10431. --- END Input Phase ---
  10432. --- Proposal Phase ---
  10433. --- Inner Elaboration Phase, active level 1 (S1) ---
  10434. Firing rl*prefer*rvt*predict-yes*H0*5*H1*9
  10435. -->
  10436. (S1 ^operator O1949 = 0.7762323413835726)
  10437. Firing prefer*rvt*predict-yes*H0*5*H1
  10438. -->
  10439. Firing elaborate*copy-see-to-output-link
  10440. -->
  10441. (I3 ^see 1 +)
  10442. Firing elaborate*reward*based*on*reward
  10443. -->
  10444. (R979 ^value 1 +)
  10445. (R1 ^reward R979 +)
  10446. Firing propose*predict-yes
  10447. -->
  10448. (O1951 ^name predict-yes +)
  10449. (S1 ^operator O1951 +)
  10450. Firing propose*predict-no
  10451. -->
  10452. (O1952 ^name predict-no +)
  10453. (S1 ^operator O1952 +)
  10454. Firing rl*prefer*rvt*predict-no*H0*6
  10455. -->
  10456. (S1 ^operator O1950 = 0.9994824970933811)
  10457. Firing rl*prefer*rvt*predict-yes*H0*5
  10458. -->
  10459. (S1 ^operator O1949 = 0.223953812706386)
  10460. Firing prefer*rvt*predict-yes*H0
  10461. -->
  10462. Firing prefer*rvt*predict-no*H0
  10463. -->
  10464. Firing elaborate*copy-dir-to-output-link
  10465. -->
  10466. (I3 ^dir R +)
  10467. inner elaboration loop at bottom goal.
  10468. Retracting elaborate*copy-see-to-output-link
  10469. -->
  10470. (I3 ^see 0 +)
  10471. Retracting propose*predict-no
  10472. -->
  10473. (O1950 ^name predict-no +)
  10474. (S1 ^operator O1950 +)
  10475. Retracting propose*predict-yes
  10476. -->
  10477. (O1949 ^name predict-yes +)
  10478. (S1 ^operator O1949 +)
  10479. Retracting elaborate*reward*based*on*reward
  10480. -->
  10481. (R978 ^value 1 +)
  10482. (R1 ^reward R978 +)
  10483. Retracting elaborate*copy-dir-to-output-link
  10484. -->
  10485. (I3 ^dir L +)
  10486. Retracting rl*prefer*rvt*predict-no*H0*2
  10487. -->
  10488. (S1 ^operator O1950 = 0.2381416323002802)
  10489. Retracting rl*prefer*rvt*predict-no*H0*2*H1*8
  10490. -->
  10491. (S1 ^operator O1950 = -0.1970449706966682)
  10492. Retracting rl*prefer*rvt*predict-yes*H0*1
  10493. -->
  10494. (S1 ^operator O1949 = 0.3499208307178328)
  10495. Retracting rl*prefer*rvt*predict-yes*H0*1*H1*7
  10496. -->
  10497. (S1 ^operator O1949 = 0.6500792883581119)
  10498. =>WM: (13673: S1 ^operator O1952 +)
  10499. =>WM: (13672: S1 ^operator O1951 +)
  10500. =>WM: (13671: I3 ^dir R)
  10501. =>WM: (13670: O1952 ^name predict-no)
  10502. =>WM: (13669: O1951 ^name predict-yes)
  10503. =>WM: (13668: R979 ^value 1)
  10504. =>WM: (13667: R1 ^reward R979)
  10505. =>WM: (13666: I3 ^see 1)
  10506. <=WM: (13657: S1 ^operator O1949 +)
  10507. <=WM: (13659: S1 ^operator O1949)
  10508. <=WM: (13658: S1 ^operator O1950 +)
  10509. <=WM: (13656: I3 ^dir L)
  10510. <=WM: (13652: R1 ^reward R978)
  10511. <=WM: (13651: I3 ^see 0)
  10512. <=WM: (13655: O1950 ^name predict-no)
  10513. <=WM: (13654: O1949 ^name predict-yes)
  10514. <=WM: (13653: R978 ^value 1)
  10515. --- Inner Elaboration Phase, active level 1 (S1) ---
  10516. Firing prefer*rvt*predict-yes*H0
  10517. -->
  10518. Firing rl*prefer*rvt*predict-yes*H0*5
  10519. -->
  10520. (S1 ^operator O1951 = 0.223953812706386)
  10521. Firing prefer*rvt*predict-yes*H0*5*H1
  10522. -->
  10523. Firing rl*prefer*rvt*predict-yes*H0*5*H1*9
  10524. -->
  10525. (S1 ^operator O1951 = 0.7762323413835726)
  10526. Firing prefer*rvt*predict-no*H0
  10527. -->
  10528. Firing rl*prefer*rvt*predict-no*H0*6
  10529. -->
  10530. (S1 ^operator O1952 = 0.9994824970933811)
  10531. inner elaboration loop at bottom goal.
  10532. Retracting rl*prefer*rvt*predict-no*H0*6
  10533. -->
  10534. (S1 ^operator O1950 = 0.9994824970933811)
  10535. Retracting rl*prefer*rvt*predict-yes*H0*5
  10536. -->
  10537. (S1 ^operator O1949 = 0.223953812706386)
  10538. Retracting rl*prefer*rvt*predict-yes*H0*5*H1*9
  10539. -->
  10540. (S1 ^operator O1949 = 0.7762323413835726)
  10541. --- END Proposal Phase ---
  10542. --- Decision Phase ---
  10543. RL update rl*prefer*rvt*predict-yes*H0*1 0.407928 -0.0580076 0.349921 -> 0.407929 -0.0580081 0.349921(R,m,v=1,0.899329,0.0911482)
  10544. RL update rl*prefer*rvt*predict-yes*H0*1*H1*7 0.592066 0.058013 0.650079 -> 0.592067 0.0580125 0.650079(R,m,v=1,1,0)
  10545. =>WM: (13674: S1 ^operator O1951)
  10546. 976: O: O1951 (predict-yes)
  10547. --- END Decision Phase ---
  10548. --- Application Phase ---
  10549. --- Firing Productions (PE) For State At Depth 1 ---
  10550. --- Inner Elaboration Phase, active level 1 (S1) ---
  10551. Firing apply*operator
  10552. -->
  10553. (I3 ^predict-yes N976 + :O )
  10554. Firing apply*operator*complete
  10555. -->
  10556. (I3 ^predict-yes N975 - :O )
  10557. inner elaboration loop at bottom goal.
  10558. --- Change Working Memory (PE) ---
  10559. =>WM: (13675: I3 ^predict-yes N976)
  10560. <=WM: (13661: N975 ^status complete)
  10561. <=WM: (13660: I3 ^predict-yes N975)
  10562. --- Firing Productions (IE) For State At Depth 1 ---
  10563. --- Inner Elaboration Phase, active level 1 (S1) ---
  10564. Firing monitor*world
  10565. -->
  10566. I see 1 and I'm going to do: predict-yes inner elaboration loop at bottom goal.
  10567. --- Change Working Memory (IE) ---
  10568. --- END Application Phase ---
  10569. --- Output Phase ---
  10570. ENV: Agent did: predict-yes for direction R in state State-A
  10571. In State-A moving R
  10572. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  10573. predict error 0
  10574. dir: dir isR
  10575. --- END Output Phase ---
  10576. -/|--- Input Phase ---
  10577. =>WM: (13679: I2 ^dir R)
  10578. =>WM: (13678: I2 ^reward 1)
  10579. =>WM: (13677: I2 ^see 1)
  10580. =>WM: (13676: N976 ^status complete)
  10581. <=WM: (13664: I2 ^dir R)
  10582. <=WM: (13663: I2 ^reward 1)
  10583. <=WM: (13662: I2 ^see 1)
  10584. =>WM: (13680: I2 ^level-1 R1-root)
  10585. <=WM: (13665: I2 ^level-1 L1-root)
  10586. --- END Input Phase ---
  10587. --- Proposal Phase ---
  10588. --- Inner Elaboration Phase, active level 1 (S1) ---
  10589. Firing rl*prefer*rvt*predict-yes*H0*5*H1*10
  10590. -->
  10591. (S1 ^operator O1951 = -0.2099933006338622)
  10592. Firing prefer*rvt*predict-yes*H0*5*H1
  10593. -->
  10594. Firing elaborate*copy-see-to-output-link
  10595. -->
  10596. (I3 ^see 1 +)
  10597. Firing elaborate*reward*based*on*reward
  10598. -->
  10599. (R980 ^value 1 +)
  10600. (R1 ^reward R980 +)
  10601. Firing propose*predict-yes
  10602. -->
  10603. (O1953 ^name predict-yes +)
  10604. (S1 ^operator O1953 +)
  10605. Firing propose*predict-no
  10606. -->
  10607. (O1954 ^name predict-no +)
  10608. (S1 ^operator O1954 +)
  10609. Firing rl*prefer*rvt*predict-no*H0*6
  10610. -->
  10611. (S1 ^operator O1952 = 0.9994824970933811)
  10612. Firing rl*prefer*rvt*predict-yes*H0*5
  10613. -->
  10614. (S1 ^operator O1951 = 0.223953812706386)
  10615. Firing prefer*rvt*predict-yes*H0
  10616. -->
  10617. Firing prefer*rvt*predict-no*H0
  10618. -->
  10619. Firing elaborate*copy-dir-to-output-link
  10620. -->
  10621. (I3 ^dir R +)
  10622. inner elaboration loop at bottom goal.
  10623. Retracting elaborate*copy-see-to-output-link
  10624. -->
  10625. (I3 ^see 1 +)
  10626. Retracting propose*predict-no
  10627. -->
  10628. (O1952 ^name predict-no +)
  10629. (S1 ^operator O1952 +)
  10630. Retracting propose*predict-yes
  10631. -->
  10632. (O1951 ^name predict-yes +)
  10633. (S1 ^operator O1951 +)
  10634. Retracting elaborate*reward*based*on*reward
  10635. -->
  10636. (R979 ^value 1 +)
  10637. (R1 ^reward R979 +)
  10638. Retracting elaborate*copy-dir-to-output-link
  10639. -->
  10640. (I3 ^dir R +)
  10641. Retracting rl*prefer*rvt*predict-no*H0*6
  10642. -->
  10643. (S1 ^operator O1952 = 0.9994824970933811)
  10644. Retracting rl*prefer*rvt*predict-yes*H0*5*H1*9
  10645. -->
  10646. (S1 ^operator O1951 = 0.7762323413835726)
  10647. Retracting rl*prefer*rvt*predict-yes*H0*5
  10648. -->
  10649. (S1 ^operator O1951 = 0.223953812706386)
  10650. =>WM: (13686: S1 ^operator O1954 +)
  10651. =>WM: (13685: S1 ^operator O1953 +)
  10652. =>WM: (13684: O1954 ^name predict-no)
  10653. =>WM: (13683: O1953 ^name predict-yes)
  10654. =>WM: (13682: R980 ^value 1)
  10655. =>WM: (13681: R1 ^reward R980)
  10656. <=WM: (13672: S1 ^operator O1951 +)
  10657. <=WM: (13674: S1 ^operator O1951)
  10658. <=WM: (13673: S1 ^operator O1952 +)
  10659. <=WM: (13667: R1 ^reward R979)
  10660. <=WM: (13670: O1952 ^name predict-no)
  10661. <=WM: (13669: O1951 ^name predict-yes)
  10662. <=WM: (13668: R979 ^value 1)
  10663. --- Inner Elaboration Phase, active level 1 (S1) ---
  10664. Firing prefer*rvt*predict-yes*H0
  10665. -->
  10666. Firing rl*prefer*rvt*predict-yes*H0*5
  10667. -->
  10668. (S1 ^operator O1953 = 0.223953812706386)
  10669. Firing prefer*rvt*predict-yes*H0*5*H1
  10670. -->
  10671. Firing rl*prefer*rvt*predict-yes*H0*5*H1*10
  10672. -->
  10673. (S1 ^operator O1953 = -0.2099933006338622)
  10674. Firing prefer*rvt*predict-no*H0
  10675. -->
  10676. Firing rl*prefer*rvt*predict-no*H0*6
  10677. -->
  10678. (S1 ^operator O1954 = 0.9994824970933811)
  10679. inner elaboration loop at bottom goal.
  10680. Retracting rl*prefer*rvt*predict-no*H0*6
  10681. -->
  10682. (S1 ^operator O1952 = 0.9994824970933811)
  10683. Retracting rl*prefer*rvt*predict-yes*H0*5
  10684. -->
  10685. (S1 ^operator O1951 = 0.223953812706386)
  10686. Retracting rl*prefer*rvt*predict-yes*H0*5*H1*10
  10687. -->
  10688. (S1 ^operator O1951 = -0.2099933006338622)
  10689. --- END Proposal Phase ---
  10690. --- Decision Phase ---
  10691. RL update rl*prefer*rvt*predict-yes*H0*5 0.553566 -0.329612 0.223954 -> 0.55355 -0.329612 0.223938(R,m,v=1,0.855263,0.124608)
  10692. RL update rl*prefer*rvt*predict-yes*H0*5*H1*9 0.446621 0.329612 0.776232 -> 0.446603 0.329612 0.776214(R,m,v=1,1,0)
  10693. =>WM: (13687: S1 ^operator O1954)
  10694. 977: O: O1954 (predict-no)
  10695. --- END Decision Phase ---
  10696. --- Application Phase ---
  10697. --- Firing Productions (PE) For State At Depth 1 ---
  10698. --- Inner Elaboration Phase, active level 1 (S1) ---
  10699. Firing apply*operator
  10700. -->
  10701. (I3 ^predict-no N977 + :O )
  10702. Firing apply*operator*complete
  10703. -->
  10704. (I3 ^predict-yes N976 - :O )
  10705. inner elaboration loop at bottom goal.
  10706. --- Change Working Memory (PE) ---
  10707. =>WM: (13688: I3 ^predict-no N977)
  10708. <=WM: (13676: N976 ^status complete)
  10709. <=WM: (13675: I3 ^predict-yes N976)
  10710. --- Firing Productions (IE) For State At Depth 1 ---
  10711. --- Inner Elaboration Phase, active level 1 (S1) ---
  10712. Firing monitor*world
  10713. -->
  10714. I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
  10715. --- Change Working Memory (IE) ---
  10716. --- END Application Phase ---
  10717. --- Output Phase ---
  10718. ENV: Agent did: predict-no for direction R in state State-B
  10719. In State-B moving R
  10720. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  10721. predict error 0
  10722. dir: dir isU
  10723. --- END Output Phase ---
  10724. \-/--- Input Phase ---
  10725. =>WM: (13692: I2 ^dir U)
  10726. =>WM: (13691: I2 ^reward 1)
  10727. =>WM: (13690: I2 ^see 0)
  10728. =>WM: (13689: N977 ^status complete)
  10729. <=WM: (13679: I2 ^dir R)
  10730. <=WM: (13678: I2 ^reward 1)
  10731. <=WM: (13677: I2 ^see 1)
  10732. =>WM: (13693: I2 ^level-1 R0-root)
  10733. <=WM: (13680: I2 ^level-1 R1-root)
  10734. --- END Input Phase ---
  10735. --- Proposal Phase ---
  10736. --- Inner Elaboration Phase, active level 1 (S1) ---
  10737. Firing elaborate*copy-see-to-output-link
  10738. -->
  10739. (I3 ^see 0 +)
  10740. Firing elaborate*reward*based*on*reward
  10741. -->
  10742. (R981 ^value 1 +)
  10743. (R1 ^reward R981 +)
  10744. Firing propose*predict-yes
  10745. -->
  10746. (O1955 ^name predict-yes +)
  10747. (S1 ^operator O1955 +)
  10748. Firing propose*predict-no
  10749. -->
  10750. (O1956 ^name predict-no +)
  10751. (S1 ^operator O1956 +)
  10752. Firing rl*prefer*rvt*predict-no*H0*4
  10753. -->
  10754. (S1 ^operator O1954 = 1.)
  10755. Firing rl*prefer*rvt*predict-yes*H0*3
  10756. -->
  10757. (S1 ^operator O1953 = 0.)
  10758. Firing prefer*rvt*predict-yes*H0
  10759. -->
  10760. Firing prefer*rvt*predict-no*H0
  10761. -->
  10762. Firing elaborate*copy-dir-to-output-link
  10763. -->
  10764. (I3 ^dir U +)
  10765. inner elaboration loop at bottom goal.
  10766. Retracting elaborate*copy-see-to-output-link
  10767. -->
  10768. (I3 ^see 1 +)
  10769. Retracting propose*predict-no
  10770. -->
  10771. (O1954 ^name predict-no +)
  10772. (S1 ^operator O1954 +)
  10773. Retracting propose*predict-yes
  10774. -->
  10775. (O1953 ^name predict-yes +)
  10776. (S1 ^operator O1953 +)
  10777. Retracting elaborate*reward*based*on*reward
  10778. -->
  10779. (R980 ^value 1 +)
  10780. (R1 ^reward R980 +)
  10781. Retracting elaborate*copy-dir-to-output-link
  10782. -->
  10783. (I3 ^dir R +)
  10784. Retracting rl*prefer*rvt*predict-no*H0*6
  10785. -->
  10786. (S1 ^operator O1954 = 0.9994824970933811)
  10787. Retracting rl*prefer*rvt*predict-yes*H0*5*H1*10
  10788. -->
  10789. (S1 ^operator O1953 = -0.2099933006338622)
  10790. Retracting rl*prefer*rvt*predict-yes*H0*5
  10791. -->
  10792. (S1 ^operator O1953 = 0.2239383613632431)
  10793. =>WM: (13701: S1 ^operator O1956 +)
  10794. =>WM: (13700: S1 ^operator O1955 +)
  10795. =>WM: (13699: I3 ^dir U)
  10796. =>WM: (13698: O1956 ^name predict-no)
  10797. =>WM: (13697: O1955 ^name predict-yes)
  10798. =>WM: (13696: R981 ^value 1)
  10799. =>WM: (13695: R1 ^reward R981)
  10800. =>WM: (13694: I3 ^see 0)
  10801. <=WM: (13685: S1 ^operator O1953 +)
  10802. <=WM: (13686: S1 ^operator O1954 +)
  10803. <=WM: (13687: S1 ^operator O1954)
  10804. <=WM: (13671: I3 ^dir R)
  10805. <=WM: (13681: R1 ^reward R980)
  10806. <=WM: (13666: I3 ^see 1)
  10807. <=WM: (13684: O1954 ^name predict-no)
  10808. <=WM: (13683: O1953 ^name predict-yes)
  10809. <=WM: (13682: R980 ^value 1)
  10810. --- Inner Elaboration Phase, active level 1 (S1) ---
  10811. Firing prefer*rvt*predict-yes*H0
  10812. -->
  10813. Firing rl*prefer*rvt*predict-yes*H0*3
  10814. -->
  10815. (S1 ^operator O1955 = 0.)
  10816. Firing prefer*rvt*predict-no*H0
  10817. -->
  10818. Firing rl*prefer*rvt*predict-no*H0*4
  10819. -->
  10820. (S1 ^operator O1956 = 1.)
  10821. inner elaboration loop at bottom goal.
  10822. Retracting rl*prefer*rvt*predict-no*H0*4
  10823. -->
  10824. (S1 ^operator O1954 = 1.)
  10825. Retracting rl*prefer*rvt*predict-yes*H0*3
  10826. -->
  10827. (S1 ^operator O1953 = 0.)
  10828. --- END Proposal Phase ---
  10829. --- Decision Phase ---
  10830. RL update rl*prefer*rvt*predict-no*H0*6 0.999482 0 0.999482 -> 0.999567 0 0.999567(R,m,v=1,0.859649,0.121362)
  10831. =>WM: (13702: S1 ^operator O1956)
  10832. 978: O: O1956 (predict-no)
  10833. --- END Decision Phase ---
  10834. --- Application Phase ---
  10835. --- Firing Productions (PE) For State At Depth 1 ---
  10836. --- Inner Elaboration Phase, active level 1 (S1) ---
  10837. Firing apply*operator
  10838. -->
  10839. (I3 ^predict-no N978 + :O )
  10840. Firing apply*operator*complete
  10841. -->
  10842. (I3 ^predict-no N977 - :O )
  10843. inner elaboration loop at bottom goal.
  10844. --- Change Working Memory (PE) ---
  10845. =>WM: (13703: I3 ^predict-no N978)
  10846. <=WM: (13689: N977 ^status complete)
  10847. <=WM: (13688: I3 ^predict-no N977)
  10848. --- Firing Productions (IE) For State At Depth 1 ---
  10849. --- Inner Elaboration Phase, active level 1 (S1) ---
  10850. Firing monitor*world
  10851. -->
  10852. I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
  10853. --- Change Working Memory (IE) ---
  10854. --- END Application Phase ---
  10855. --- Output Phase ---
  10856. ENV: Agent did: predict-no for direction U in state State-B
  10857. In State-B moving U
  10858. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  10859. predict error 0
  10860. dir: dir isU
  10861. --- END Output Phase ---
  10862. |\---- Input Phase ---
  10863. =>WM: (13707: I2 ^dir U)
  10864. =>WM: (13706: I2 ^reward 1)
  10865. =>WM: (13705: I2 ^see 0)
  10866. =>WM: (13704: N978 ^status complete)
  10867. <=WM: (13692: I2 ^dir U)
  10868. <=WM: (13691: I2 ^reward 1)
  10869. <=WM: (13690: I2 ^see 0)
  10870. =>WM: (13708: I2 ^level-1 R0-root)
  10871. <=WM: (13693: I2 ^level-1 R0-root)
  10872. --- END Input Phase ---
  10873. --- Proposal Phase ---
  10874. --- Inner Elaboration Phase, active level 1 (S1) ---
  10875. Firing elaborate*copy-see-to-output-link
  10876. -->
  10877. (I3 ^see 0 +)
  10878. Firing elaborate*reward*based*on*reward
  10879. -->
  10880. (R982 ^value 1 +)
  10881. (R1 ^reward R982 +)
  10882. Firing propose*predict-yes
  10883. -->
  10884. (O1957 ^name predict-yes +)
  10885. (S1 ^operator O1957 +)
  10886. Firing propose*predict-no
  10887. -->
  10888. (O1958 ^name predict-no +)
  10889. (S1 ^operator O1958 +)
  10890. Firing rl*prefer*rvt*predict-no*H0*4
  10891. -->
  10892. (S1 ^operator O1956 = 1.)
  10893. Firing rl*prefer*rvt*predict-yes*H0*3
  10894. -->
  10895. (S1 ^operator O1955 = 0.)
  10896. Firing prefer*rvt*predict-yes*H0
  10897. -->
  10898. Firing prefer*rvt*predict-no*H0
  10899. -->
  10900. Firing elaborate*copy-dir-to-output-link
  10901. -->
  10902. (I3 ^dir U +)
  10903. inner elaboration loop at bottom goal.
  10904. Retracting elaborate*copy-see-to-output-link
  10905. -->
  10906. (I3 ^see 0 +)
  10907. Retracting propose*predict-no
  10908. -->
  10909. (O1956 ^name predict-no +)
  10910. (S1 ^operator O1956 +)
  10911. Retracting propose*predict-yes
  10912. -->
  10913. (O1955 ^name predict-yes +)
  10914. (S1 ^operator O1955 +)
  10915. Retracting elaborate*reward*based*on*reward
  10916. -->
  10917. (R981 ^value 1 +)
  10918. (R1 ^reward R981 +)
  10919. Retracting elaborate*copy-dir-to-output-link
  10920. -->
  10921. (I3 ^dir U +)
  10922. Retracting rl*prefer*rvt*predict-no*H0*4
  10923. -->
  10924. (S1 ^operator O1956 = 1.)
  10925. Retracting rl*prefer*rvt*predict-yes*H0*3
  10926. -->
  10927. (S1 ^operator O1955 = 0.)
  10928. =>WM: (13714: S1 ^operator O1958 +)
  10929. =>WM: (13713: S1 ^operator O1957 +)
  10930. =>WM: (13712: O1958 ^name predict-no)
  10931. =>WM: (13711: O1957 ^name predict-yes)
  10932. =>WM: (13710: R982 ^value 1)
  10933. =>WM: (13709: R1 ^reward R982)
  10934. <=WM: (13700: S1 ^operator O1955 +)
  10935. <=WM: (13701: S1 ^operator O1956 +)
  10936. <=WM: (13702: S1 ^operator O1956)
  10937. <=WM: (13695: R1 ^reward R981)
  10938. <=WM: (13698: O1956 ^name predict-no)
  10939. <=WM: (13697: O1955 ^name predict-yes)
  10940. <=WM: (13696: R981 ^value 1)
  10941. --- Inner Elaboration Phase, active level 1 (S1) ---
  10942. Firing prefer*rvt*predict-yes*H0
  10943. -->
  10944. Firing rl*prefer*rvt*predict-yes*H0*3
  10945. -->
  10946. (S1 ^operator O1957 = 0.)
  10947. Firing prefer*rvt*predict-no*H0
  10948. -->
  10949. Firing rl*prefer*rvt*predict-no*H0*4
  10950. -->
  10951. (S1 ^operator O1958 = 1.)
  10952. inner elaboration loop at bottom goal.
  10953. Retracting rl*prefer*rvt*predict-no*H0*4
  10954. -->
  10955. (S1 ^operator O1956 = 1.)
  10956. Retracting rl*prefer*rvt*predict-yes*H0*3
  10957. -->
  10958. (S1 ^operator O1955 = 0.)
  10959. --- END Proposal Phase ---
  10960. --- Decision Phase ---
  10961. RL update rl*prefer*rvt*predict-no*H0*4 1 0 1 -> 1 0 1(R,m,v=1,1,0)
  10962. =>WM: (13715: S1 ^operator O1958)
  10963. 979: O: O1958 (predict-no)
  10964. --- END Decision Phase ---
  10965. --- Application Phase ---
  10966. --- Firing Productions (PE) For State At Depth 1 ---
  10967. --- Inner Elaboration Phase, active level 1 (S1) ---
  10968. Firing apply*operator
  10969. -->
  10970. (I3 ^predict-no N979 + :O )
  10971. Firing apply*operator*complete
  10972. -->
  10973. (I3 ^predict-no N978 - :O )
  10974. inner elaboration loop at bottom goal.
  10975. --- Change Working Memory (PE) ---
  10976. =>WM: (13716: I3 ^predict-no N979)
  10977. <=WM: (13704: N978 ^status complete)
  10978. <=WM: (13703: I3 ^predict-no N978)
  10979. --- Firing Productions (IE) For State At Depth 1 ---
  10980. --- Inner Elaboration Phase, active level 1 (S1) ---
  10981. Firing monitor*world
  10982. -->
  10983. I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
  10984. --- Change Working Memory (IE) ---
  10985. --- END Application Phase ---
  10986. --- Output Phase ---
  10987. ENV: Agent did: predict-no for direction U in state State-B
  10988. In State-B moving U
  10989. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  10990. predict error 0
  10991. dir: dir isL
  10992. --- END Output Phase ---
  10993. /|--- Input Phase ---
  10994. =>WM: (13720: I2 ^dir L)
  10995. =>WM: (13719: I2 ^reward 1)
  10996. =>WM: (13718: I2 ^see 0)
  10997. =>WM: (13717: N979 ^status complete)
  10998. <=WM: (13707: I2 ^dir U)
  10999. <=WM: (13706: I2 ^reward 1)
  11000. <=WM: (13705: I2 ^see 0)
  11001. =>WM: (13721: I2 ^level-1 R0-root)
  11002. <=WM: (13708: I2 ^level-1 R0-root)
  11003. --- END Input Phase ---
  11004. --- Proposal Phase ---
  11005. --- Inner Elaboration Phase, active level 1 (S1) ---
  11006. Firing rl*prefer*rvt*predict-no*H0*2*H1*12
  11007. -->
  11008. (S1 ^operator O1958 = -0.1359494083332169)
  11009. Firing rl*prefer*rvt*predict-yes*H0*1*H1*13
  11010. -->
  11011. (S1 ^operator O1957 = 0.6500789221022334)
  11012. Firing prefer*rvt*predict-no*H0*2*H1
  11013. -->
  11014. Firing prefer*rvt*predict-yes*H0*1*H1
  11015. -->
  11016. Firing elaborate*copy-see-to-output-link
  11017. -->
  11018. (I3 ^see 0 +)
  11019. Firing elaborate*reward*based*on*reward
  11020. -->
  11021. (R983 ^value 1 +)
  11022. (R1 ^reward R983 +)
  11023. Firing propose*predict-yes
  11024. -->
  11025. (O1959 ^name predict-yes +)
  11026. (S1 ^operator O1959 +)
  11027. Firing propose*predict-no
  11028. -->
  11029. (O1960 ^name predict-no +)
  11030. (S1 ^operator O1960 +)
  11031. Firing rl*prefer*rvt*predict-no*H0*2
  11032. -->
  11033. (S1 ^operator O1958 = 0.2381416323002802)
  11034. Firing rl*prefer*rvt*predict-yes*H0*1
  11035. -->
  11036. (S1 ^operator O1957 = 0.3499208208013597)
  11037. Firing prefer*rvt*predict-yes*H0
  11038. -->
  11039. Firing prefer*rvt*predict-no*H0
  11040. -->
  11041. Firing elaborate*copy-dir-to-output-link
  11042. -->
  11043. (I3 ^dir L +)
  11044. inner elaboration loop at bottom goal.
  11045. Retracting elaborate*copy-see-to-output-link
  11046. -->
  11047. (I3 ^see 0 +)
  11048. Retracting propose*predict-no
  11049. -->
  11050. (O1958 ^name predict-no +)
  11051. (S1 ^operator O1958 +)
  11052. Retracting propose*predict-yes
  11053. -->
  11054. (O1957 ^name predict-yes +)
  11055. (S1 ^operator O1957 +)
  11056. Retracting elaborate*reward*based*on*reward
  11057. -->
  11058. (R982 ^value 1 +)
  11059. (R1 ^reward R982 +)
  11060. Retracting elaborate*copy-dir-to-output-link
  11061. -->
  11062. (I3 ^dir U +)
  11063. Retracting rl*prefer*rvt*predict-no*H0*4
  11064. -->
  11065. (S1 ^operator O1958 = 1.)
  11066. Retracting rl*prefer*rvt*predict-yes*H0*3
  11067. -->
  11068. (S1 ^operator O1957 = 0.)
  11069. =>WM: (13728: S1 ^operator O1960 +)
  11070. =>WM: (13727: S1 ^operator O1959 +)
  11071. =>WM: (13726: I3 ^dir L)
  11072. =>WM: (13725: O1960 ^name predict-no)
  11073. =>WM: (13724: O1959 ^name predict-yes)
  11074. =>WM: (13723: R983 ^value 1)
  11075. =>WM: (13722: R1 ^reward R983)
  11076. <=WM: (13713: S1 ^operator O1957 +)
  11077. <=WM: (13714: S1 ^operator O1958 +)
  11078. <=WM: (13715: S1 ^operator O1958)
  11079. <=WM: (13699: I3 ^dir U)
  11080. <=WM: (13709: R1 ^reward R982)
  11081. <=WM: (13712: O1958 ^name predict-no)
  11082. <=WM: (13711: O1957 ^name predict-yes)
  11083. <=WM: (13710: R982 ^value 1)
  11084. --- Inner Elaboration Phase, active level 1 (S1) ---
  11085. Firing prefer*rvt*predict-yes*H0
  11086. -->
  11087. Firing rl*prefer*rvt*predict-yes*H0*1*H1*13
  11088. -->
  11089. (S1 ^operator O1959 = 0.6500789221022334)
  11090. Firing rl*prefer*rvt*predict-yes*H0*1
  11091. -->
  11092. (S1 ^operator O1959 = 0.3499208208013597)
  11093. Firing prefer*rvt*predict-yes*H0*1*H1
  11094. -->
  11095. Firing prefer*rvt*predict-no*H0
  11096. -->
  11097. Firing rl*prefer*rvt*predict-no*H0*2*H1*12
  11098. -->
  11099. (S1 ^operator O1960 = -0.1359494083332169)
  11100. Firing rl*prefer*rvt*predict-no*H0*2
  11101. -->
  11102. (S1 ^operator O1960 = 0.2381416323002802)
  11103. Firing prefer*rvt*predict-no*H0*2*H1
  11104. -->
  11105. inner elaboration loop at bottom goal.
  11106. Retracting rl*prefer*rvt*predict-no*H0*2
  11107. -->
  11108. (S1 ^operator O1958 = 0.2381416323002802)
  11109. Retracting rl*prefer*rvt*predict-no*H0*2*H1*12
  11110. -->
  11111. (S1 ^operator O1958 = -0.1359494083332169)
  11112. Retracting rl*prefer*rvt*predict-yes*H0*1
  11113. -->
  11114. (S1 ^operator O1957 = 0.3499208208013597)
  11115. Retracting rl*prefer*rvt*predict-yes*H0*1*H1*13
  11116. -->
  11117. (S1 ^operator O1957 = 0.6500789221022334)
  11118. --- END Proposal Phase ---
  11119. --- Decision Phase ---
  11120. RL update rl*prefer*rvt*predict-no*H0*4 1 0 1 -> 1 0 1(R,m,v=1,1,0)
  11121. =>WM: (13729: S1 ^operator O1959)
  11122. 980: O: O1959 (predict-yes)
  11123. --- END Decision Phase ---
  11124. --- Application Phase ---
  11125. --- Firing Productions (PE) For State At Depth 1 ---
  11126. --- Inner Elaboration Phase, active level 1 (S1) ---
  11127. Firing apply*operator
  11128. -->
  11129. (I3 ^predict-yes N980 + :O )
  11130. Firing apply*operator*complete
  11131. -->
  11132. (I3 ^predict-no N979 - :O )
  11133. inner elaboration loop at bottom goal.
  11134. --- Change Working Memory (PE) ---
  11135. =>WM: (13730: I3 ^predict-yes N980)
  11136. <=WM: (13717: N979 ^status complete)
  11137. <=WM: (13716: I3 ^predict-no N979)
  11138. --- Firing Productions (IE) For State At Depth 1 ---
  11139. --- Inner Elaboration Phase, active level 1 (S1) ---
  11140. Firing monitor*world
  11141. -->
  11142. I see 1 and I'm going to do: predict-yes inner elaboration loop at bottom goal.
  11143. --- Change Working Memory (IE) ---
  11144. --- END Application Phase ---
  11145. --- Output Phase ---
  11146. ENV: Agent did: predict-yes for direction L in state State-B
  11147. In State-B moving L
  11148. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  11149. predict error 0
  11150. dir: dir isR
  11151. --- END Output Phase ---
  11152. \-/--- Input Phase ---
  11153. =>WM: (13734: I2 ^dir R)
  11154. =>WM: (13733: I2 ^reward 1)
  11155. =>WM: (13732: I2 ^see 1)
  11156. =>WM: (13731: N980 ^status complete)
  11157. <=WM: (13720: I2 ^dir L)
  11158. <=WM: (13719: I2 ^reward 1)
  11159. <=WM: (13718: I2 ^see 0)
  11160. =>WM: (13735: I2 ^level-1 L1-root)
  11161. <=WM: (13721: I2 ^level-1 R0-root)
  11162. --- END Input Phase ---
  11163. --- Proposal Phase ---
  11164. --- Inner Elaboration Phase, active level 1 (S1) ---
  11165. Firing rl*prefer*rvt*predict-yes*H0*5*H1*9
  11166. -->
  11167. (S1 ^operator O1959 = 0.7762142992912291)
  11168. Firing prefer*rvt*predict-yes*H0*5*H1
  11169. -->
  11170. Firing elaborate*copy-see-to-output-link
  11171. -->
  11172. (I3 ^see 1 +)
  11173. Firing elaborate*reward*based*on*reward
  11174. -->
  11175. (R984 ^value 1 +)
  11176. (R1 ^reward R984 +)
  11177. Firing propose*predict-yes
  11178. -->
  11179. (O1961 ^name predict-yes +)
  11180. (S1 ^operator O1961 +)
  11181. Firing propose*predict-no
  11182. -->
  11183. (O1962 ^name predict-no +)
  11184. (S1 ^operator O1962 +)
  11185. Firing rl*prefer*rvt*predict-no*H0*6
  11186. -->
  11187. (S1 ^operator O1960 = 0.9995667581249172)
  11188. Firing rl*prefer*rvt*predict-yes*H0*5
  11189. -->
  11190. (S1 ^operator O1959 = 0.2239383613632431)
  11191. Firing prefer*rvt*predict-yes*H0
  11192. -->
  11193. Firing prefer*rvt*predict-no*H0
  11194. -->
  11195. Firing elaborate*copy-dir-to-output-link
  11196. -->
  11197. (I3 ^dir R +)
  11198. inner elaboration loop at bottom goal.
  11199. Retracting elaborate*copy-see-to-output-link
  11200. -->
  11201. (I3 ^see 0 +)
  11202. Retracting propose*predict-no
  11203. -->
  11204. (O1960 ^name predict-no +)
  11205. (S1 ^operator O1960 +)
  11206. Retracting propose*predict-yes
  11207. -->
  11208. (O1959 ^name predict-yes +)
  11209. (S1 ^operator O1959 +)
  11210. Retracting elaborate*reward*based*on*reward
  11211. -->
  11212. (R983 ^value 1 +)
  11213. (R1 ^reward R983 +)
  11214. Retracting elaborate*copy-dir-to-output-link
  11215. -->
  11216. (I3 ^dir L +)
  11217. Retracting rl*prefer*rvt*predict-no*H0*2
  11218. -->
  11219. (S1 ^operator O1960 = 0.2381416323002802)
  11220. Retracting rl*prefer*rvt*predict-no*H0*2*H1*12
  11221. -->
  11222. (S1 ^operator O1960 = -0.1359494083332169)
  11223. Retracting rl*prefer*rvt*predict-yes*H0*1
  11224. -->
  11225. (S1 ^operator O1959 = 0.3499208208013597)
  11226. Retracting rl*prefer*rvt*predict-yes*H0*1*H1*13
  11227. -->
  11228. (S1 ^operator O1959 = 0.6500789221022334)
  11229. =>WM: (13743: S1 ^operator O1962 +)
  11230. =>WM: (13742: S1 ^operator O1961 +)
  11231. =>WM: (13741: I3 ^dir R)
  11232. =>WM: (13740: O1962 ^name predict-no)
  11233. =>WM: (13739: O1961 ^name predict-yes)
  11234. =>WM: (13738: R984 ^value 1)
  11235. =>WM: (13737: R1 ^reward R984)
  11236. =>WM: (13736: I3 ^see 1)
  11237. <=WM: (13727: S1 ^operator O1959 +)
  11238. <=WM: (13729: S1 ^operator O1959)
  11239. <=WM: (13728: S1 ^operator O1960 +)
  11240. <=WM: (13726: I3 ^dir L)
  11241. <=WM: (13722: R1 ^reward R983)
  11242. <=WM: (13694: I3 ^see 0)
  11243. <=WM: (13725: O1960 ^name predict-no)
  11244. <=WM: (13724: O1959 ^name predict-yes)
  11245. <=WM: (13723: R983 ^value 1)
  11246. --- Inner Elaboration Phase, active level 1 (S1) ---
  11247. Firing prefer*rvt*predict-yes*H0
  11248. -->
  11249. Firing rl*prefer*rvt*predict-yes*H0*5
  11250. -->
  11251. (S1 ^operator O1961 = 0.2239383613632431)
  11252. Firing prefer*rvt*predict-yes*H0*5*H1
  11253. -->
  11254. Firing rl*prefer*rvt*predict-yes*H0*5*H1*9
  11255. -->
  11256. (S1 ^operator O1961 = 0.7762142992912291)
  11257. Firing prefer*rvt*predict-no*H0
  11258. -->
  11259. Firing rl*prefer*rvt*predict-no*H0*6
  11260. -->
  11261. (S1 ^operator O1962 = 0.9995667581249172)
  11262. inner elaboration loop at bottom goal.
  11263. Retracting rl*prefer*rvt*predict-no*H0*6
  11264. -->
  11265. (S1 ^operator O1960 = 0.9995667581249172)
  11266. Retracting rl*prefer*rvt*predict-yes*H0*5
  11267. -->
  11268. (S1 ^operator O1959 = 0.2239383613632431)
  11269. Retracting rl*prefer*rvt*predict-yes*H0*5*H1*9
  11270. -->
  11271. (S1 ^operator O1959 = 0.7762142992912291)
  11272. --- END Proposal Phase ---
  11273. --- Decision Phase ---
  11274. RL update rl*prefer*rvt*predict-yes*H0*1 0.407929 -0.0580081 0.349921 -> 0.407929 -0.0580077 0.349921(R,m,v=1,0.9,0.090604)
  11275. RL update rl*prefer*rvt*predict-yes*H0*1*H1*13 0.592076 0.0580031 0.650079 -> 0.592075 0.0580036 0.650079(R,m,v=1,1,0)
  11276. =>WM: (13744: S1 ^operator O1961)
  11277. 981: O: O1961 (predict-yes)
  11278. --- END Decision Phase ---
  11279. --- Application Phase ---
  11280. --- Firing Productions (PE) For State At Depth 1 ---
  11281. --- Inner Elaboration Phase, active level 1 (S1) ---
  11282. Firing apply*operator
  11283. -->
  11284. (I3 ^predict-yes N981 + :O )
  11285. Firing apply*operator*complete
  11286. -->
  11287. (I3 ^predict-yes N980 - :O )
  11288. inner elaboration loop at bottom goal.
  11289. --- Change Working Memory (PE) ---
  11290. =>WM: (13745: I3 ^predict-yes N981)
  11291. <=WM: (13731: N980 ^status complete)
  11292. <=WM: (13730: I3 ^predict-yes N980)
  11293. --- Firing Productions (IE) For State At Depth 1 ---
  11294. --- Inner Elaboration Phase, active level 1 (S1) ---
  11295. Firing monitor*world
  11296. -->
  11297. I see 1 and I'm going to do: predict-yes inner elaboration loop at bottom goal.
  11298. --- Change Working Memory (IE) ---
  11299. --- END Application Phase ---
  11300. --- Output Phase ---
  11301. ENV: Agent did: predict-yes for direction R in state State-A
  11302. In State-A moving R
  11303. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  11304. predict error 0
  11305. dir: dir isU
  11306. --- END Output Phase ---
  11307. |--- Input Phase ---
  11308. =>WM: (13749: I2 ^dir U)
  11309. =>WM: (13748: I2 ^reward 1)
  11310. =>WM: (13747: I2 ^see 1)
  11311. =>WM: (13746: N981 ^status complete)
  11312. <=WM: (13734: I2 ^dir R)
  11313. <=WM: (13733: I2 ^reward 1)
  11314. <=WM: (13732: I2 ^see 1)
  11315. =>WM: (13750: I2 ^level-1 R1-root)
  11316. <=WM: (13735: I2 ^level-1 L1-root)
  11317. --- END Input Phase ---
  11318. --- Proposal Phase ---
  11319. --- Inner Elaboration Phase, active level 1 (S1) ---
  11320. Firing elaborate*copy-see-to-output-link
  11321. -->
  11322. (I3 ^see 1 +)
  11323. Firing elaborate*reward*based*on*reward
  11324. -->
  11325. (R985 ^value 1 +)
  11326. (R1 ^reward R985 +)
  11327. Firing propose*predict-yes
  11328. -->
  11329. (O1963 ^name predict-yes +)
  11330. (S1 ^operator O1963 +)
  11331. Firing propose*predict-no
  11332. -->
  11333. (O1964 ^name predict-no +)
  11334. (S1 ^operator O1964 +)
  11335. Firing rl*prefer*rvt*predict-no*H0*4
  11336. -->
  11337. (S1 ^operator O1962 = 1.)
  11338. Firing rl*prefer*rvt*predict-yes*H0*3
  11339. -->
  11340. (S1 ^operator O1961 = 0.)
  11341. Firing prefer*rvt*predict-yes*H0
  11342. -->
  11343. Firing prefer*rvt*predict-no*H0
  11344. -->
  11345. Firing elaborate*copy-dir-to-output-link
  11346. -->
  11347. (I3 ^dir U +)
  11348. inner elaboration loop at bottom goal.
  11349. Retracting elaborate*copy-see-to-output-link
  11350. -->
  11351. (I3 ^see 1 +)
  11352. Retracting propose*predict-no
  11353. -->
  11354. (O1962 ^name predict-no +)
  11355. (S1 ^operator O1962 +)
  11356. Retracting propose*predict-yes
  11357. -->
  11358. (O1961 ^name predict-yes +)
  11359. (S1 ^operator O1961 +)
  11360. Retracting elaborate*reward*based*on*reward
  11361. -->
  11362. (R984 ^value 1 +)
  11363. (R1 ^reward R984 +)
  11364. Retracting elaborate*copy-dir-to-output-link
  11365. -->
  11366. (I3 ^dir R +)
  11367. Retracting rl*prefer*rvt*predict-no*H0*6
  11368. -->
  11369. (S1 ^operator O1962 = 0.9995667581249172)
  11370. Retracting rl*prefer*rvt*predict-yes*H0*5*H1*9
  11371. -->
  11372. (S1 ^operator O1961 = 0.7762142992912291)
  11373. Retracting rl*prefer*rvt*predict-yes*H0*5
  11374. -->
  11375. (S1 ^operator O1961 = 0.2239383613632431)
  11376. =>WM: (13757: S1 ^operator O1964 +)
  11377. =>WM: (13756: S1 ^operator O1963 +)
  11378. =>WM: (13755: I3 ^dir U)
  11379. =>WM: (13754: O1964 ^name predict-no)
  11380. =>WM: (13753: O1963 ^name predict-yes)
  11381. =>WM: (13752: R985 ^value 1)
  11382. =>WM: (13751: R1 ^reward R985)
  11383. <=WM: (13742: S1 ^operator O1961 +)
  11384. <=WM: (13744: S1 ^operator O1961)
  11385. <=WM: (13743: S1 ^operator O1962 +)
  11386. <=WM: (13741: I3 ^dir R)
  11387. <=WM: (13737: R1 ^reward R984)
  11388. <=WM: (13740: O1962 ^name predict-no)
  11389. <=WM: (13739: O1961 ^name predict-yes)
  11390. <=WM: (13738: R984 ^value 1)
  11391. --- Inner Elaboration Phase, active level 1 (S1) ---
  11392. Firing prefer*rvt*predict-yes*H0
  11393. -->
  11394. Firing rl*prefer*rvt*predict-yes*H0*3
  11395. -->
  11396. (S1 ^operator O1963 = 0.)
  11397. Firing prefer*rvt*predict-no*H0
  11398. -->
  11399. Firing rl*prefer*rvt*predict-no*H0*4
  11400. -->
  11401. (S1 ^operator O1964 = 1.)
  11402. inner elaboration loop at bottom goal.
  11403. Retracting rl*prefer*rvt*predict-no*H0*4
  11404. -->
  11405. (S1 ^operator O1962 = 1.)
  11406. Retracting rl*prefer*rvt*predict-yes*H0*3
  11407. -->
  11408. (S1 ^operator O1961 = 0.)
  11409. --- END Proposal Phase ---
  11410. --- Decision Phase ---
  11411. RL update rl*prefer*rvt*predict-yes*H0*5 0.55355 -0.329612 0.223938 -> 0.553538 -0.329612 0.223926(R,m,v=1,0.856209,0.123925)
  11412. RL update rl*prefer*rvt*predict-yes*H0*5*H1*9 0.446603 0.329612 0.776214 -> 0.446588 0.329612 0.7762(R,m,v=1,1,0)
  11413. =>WM: (13758: S1 ^operator O1964)
  11414. 982: O: O1964 (predict-no)
  11415. --- END Decision Phase ---
  11416. --- Application Phase ---
  11417. --- Firing Productions (PE) For State At Depth 1 ---
  11418. --- Inner Elaboration Phase, active level 1 (S1) ---
  11419. Firing apply*operator
  11420. -->
  11421. (I3 ^predict-no N982 + :O )
  11422. Firing apply*operator*complete
  11423. -->
  11424. (I3 ^predict-yes N981 - :O )
  11425. inner elaboration loop at bottom goal.
  11426. --- Change Working Memory (PE) ---
  11427. =>WM: (13759: I3 ^predict-no N982)
  11428. <=WM: (13746: N981 ^status complete)
  11429. <=WM: (13745: I3 ^predict-yes N981)
  11430. --- Firing Productions (IE) For State At Depth 1 ---
  11431. --- Inner Elaboration Phase, active level 1 (S1) ---
  11432. Firing monitor*world
  11433. -->
  11434. I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
  11435. --- Change Working Memory (IE) ---
  11436. --- END Application Phase ---
  11437. --- Output Phase ---
  11438. ENV: Agent did: predict-no for direction U in state State-B
  11439. In State-B moving U
  11440. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  11441. predict error 0
  11442. dir: dir isR
  11443. --- END Output Phase ---
  11444. \-/--- Input Phase ---
  11445. =>WM: (13763: I2 ^dir R)
  11446. =>WM: (13762: I2 ^reward 1)
  11447. =>WM: (13761: I2 ^see 0)
  11448. =>WM: (13760: N982 ^status complete)
  11449. <=WM: (13749: I2 ^dir U)
  11450. <=WM: (13748: I2 ^reward 1)
  11451. <=WM: (13747: I2 ^see 1)
  11452. =>WM: (13764: I2 ^level-1 R1-root)
  11453. <=WM: (13750: I2 ^level-1 R1-root)
  11454. --- END Input Phase ---
  11455. --- Proposal Phase ---
  11456. --- Inner Elaboration Phase, active level 1 (S1) ---
  11457. Firing rl*prefer*rvt*predict-yes*H0*5*H1*10
  11458. -->
  11459. (S1 ^operator O1963 = -0.2099933006338622)
  11460. Firing prefer*rvt*predict-yes*H0*5*H1
  11461. -->
  11462. Firing elaborate*copy-see-to-output-link
  11463. -->
  11464. (I3 ^see 0 +)
  11465. Firing elaborate*reward*based*on*reward
  11466. -->
  11467. (R986 ^value 1 +)
  11468. (R1 ^reward R986 +)
  11469. Firing propose*predict-yes
  11470. -->
  11471. (O1965 ^name predict-yes +)
  11472. (S1 ^operator O1965 +)
  11473. Firing propose*predict-no
  11474. -->
  11475. (O1966 ^name predict-no +)
  11476. (S1 ^operator O1966 +)
  11477. Firing rl*prefer*rvt*predict-no*H0*6
  11478. -->
  11479. (S1 ^operator O1964 = 0.9995667581249172)
  11480. Firing rl*prefer*rvt*predict-yes*H0*5
  11481. -->
  11482. (S1 ^operator O1963 = 0.2239257038534186)
  11483. Firing prefer*rvt*predict-yes*H0
  11484. -->
  11485. Firing prefer*rvt*predict-no*H0
  11486. -->
  11487. Firing elaborate*copy-dir-to-output-link
  11488. -->
  11489. (I3 ^dir R +)
  11490. inner elaboration loop at bottom goal.
  11491. Retracting elaborate*copy-see-to-output-link
  11492. -->
  11493. (I3 ^see 1 +)
  11494. Retracting propose*predict-no
  11495. -->
  11496. (O1964 ^name predict-no +)
  11497. (S1 ^operator O1964 +)
  11498. Retracting propose*predict-yes
  11499. -->
  11500. (O1963 ^name predict-yes +)
  11501. (S1 ^operator O1963 +)
  11502. Retracting elaborate*reward*based*on*reward
  11503. -->
  11504. (R985 ^value 1 +)
  11505. (R1 ^reward R985 +)
  11506. Retracting elaborate*copy-dir-to-output-link
  11507. -->
  11508. (I3 ^dir U +)
  11509. Retracting rl*prefer*rvt*predict-no*H0*4
  11510. -->
  11511. (S1 ^operator O1964 = 1.)
  11512. Retracting rl*prefer*rvt*predict-yes*H0*3
  11513. -->
  11514. (S1 ^operator O1963 = 0.)
  11515. =>WM: (13772: S1 ^operator O1966 +)
  11516. =>WM: (13771: S1 ^operator O1965 +)
  11517. =>WM: (13770: I3 ^dir R)
  11518. =>WM: (13769: O1966 ^name predict-no)
  11519. =>WM: (13768: O1965 ^name predict-yes)
  11520. =>WM: (13767: R986 ^value 1)
  11521. =>WM: (13766: R1 ^reward R986)
  11522. =>WM: (13765: I3 ^see 0)
  11523. <=WM: (13756: S1 ^operator O1963 +)
  11524. <=WM: (13757: S1 ^operator O1964 +)
  11525. <=WM: (13758: S1 ^operator O1964)
  11526. <=WM: (13755: I3 ^dir U)
  11527. <=WM: (13751: R1 ^reward R985)
  11528. <=WM: (13736: I3 ^see 1)
  11529. <=WM: (13754: O1964 ^name predict-no)
  11530. <=WM: (13753: O1963 ^name predict-yes)
  11531. <=WM: (13752: R985 ^value 1)
  11532. --- Inner Elaboration Phase, active level 1 (S1) ---
  11533. Firing prefer*rvt*predict-yes*H0
  11534. -->
  11535. Firing rl*prefer*rvt*predict-yes*H0*5*H1*10
  11536. -->
  11537. (S1 ^operator O1965 = -0.2099933006338622)
  11538. Firing rl*prefer*rvt*predict-yes*H0*5
  11539. -->
  11540. (S1 ^operator O1965 = 0.2239257038534186)
  11541. Firing prefer*rvt*predict-yes*H0*5*H1
  11542. -->
  11543. Firing prefer*rvt*predict-no*H0
  11544. -->
  11545. Firing rl*prefer*rvt*predict-no*H0*6
  11546. -->
  11547. (S1 ^operator O1966 = 0.9995667581249172)
  11548. inner elaboration loop at bottom goal.
  11549. Retracting rl*prefer*rvt*predict-no*H0*6
  11550. -->
  11551. (S1 ^operator O1964 = 0.9995667581249172)
  11552. Retracting rl*prefer*rvt*predict-yes*H0*5
  11553. -->
  11554. (S1 ^operator O1963 = 0.2239257038534186)
  11555. Retracting rl*prefer*rvt*predict-yes*H0*5*H1*10
  11556. -->
  11557. (S1 ^operator O1963 = -0.2099933006338622)
  11558. --- END Proposal Phase ---
  11559. --- Decision Phase ---
  11560. RL update rl*prefer*rvt*predict-no*H0*4 1 0 1 -> 1 0 1(R,m,v=1,1,0)
  11561. =>WM: (13773: S1 ^operator O1966)
  11562. 983: O: O1966 (predict-no)
  11563. --- END Decision Phase ---
  11564. --- Application Phase ---
  11565. --- Firing Productions (PE) For State At Depth 1 ---
  11566. --- Inner Elaboration Phase, active level 1 (S1) ---
  11567. Firing apply*operator
  11568. -->
  11569. (I3 ^predict-no N983 + :O )
  11570. Firing apply*operator*complete
  11571. -->
  11572. (I3 ^predict-no N982 - :O )
  11573. inner elaboration loop at bottom goal.
  11574. --- Change Working Memory (PE) ---
  11575. =>WM: (13774: I3 ^predict-no N983)
  11576. <=WM: (13760: N982 ^status complete)
  11577. <=WM: (13759: I3 ^predict-no N982)
  11578. --- Firing Productions (IE) For State At Depth 1 ---
  11579. --- Inner Elaboration Phase, active level 1 (S1) ---
  11580. Firing monitor*world
  11581. -->
  11582. I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
  11583. --- Change Working Memory (IE) ---
  11584. --- END Application Phase ---
  11585. --- Output Phase ---
  11586. ENV: Agent did: predict-no for direction R in state State-B
  11587. In State-B moving R
  11588. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  11589. predict error 0
  11590. dir: dir isL
  11591. --- END Output Phase ---
  11592. |\---- Input Phase ---
  11593. =>WM: (13778: I2 ^dir L)
  11594. =>WM: (13777: I2 ^reward 1)
  11595. =>WM: (13776: I2 ^see 0)
  11596. =>WM: (13775: N983 ^status complete)
  11597. <=WM: (13763: I2 ^dir R)
  11598. <=WM: (13762: I2 ^reward 1)
  11599. <=WM: (13761: I2 ^see 0)
  11600. =>WM: (13779: I2 ^level-1 R0-root)
  11601. <=WM: (13764: I2 ^level-1 R1-root)
  11602. --- END Input Phase ---
  11603. --- Proposal Phase ---
  11604. --- Inner Elaboration Phase, active level 1 (S1) ---
  11605. Firing rl*prefer*rvt*predict-no*H0*2*H1*12
  11606. -->
  11607. (S1 ^operator O1966 = -0.1359494083332169)
  11608. Firing rl*prefer*rvt*predict-yes*H0*1*H1*13
  11609. -->
  11610. (S1 ^operator O1965 = 0.6500789468007531)
  11611. Firing prefer*rvt*predict-no*H0*2*H1
  11612. -->
  11613. Firing prefer*rvt*predict-yes*H0*1*H1
  11614. -->
  11615. Firing elaborate*copy-see-to-output-link
  11616. -->
  11617. (I3 ^see 0 +)
  11618. Firing elaborate*reward*based*on*reward
  11619. -->
  11620. (R987 ^value 1 +)
  11621. (R1 ^reward R987 +)
  11622. Firing propose*predict-yes
  11623. -->
  11624. (O1967 ^name predict-yes +)
  11625. (S1 ^operator O1967 +)
  11626. Firing propose*predict-no
  11627. -->
  11628. (O1968 ^name predict-no +)
  11629. (S1 ^operator O1968 +)
  11630. Firing rl*prefer*rvt*predict-no*H0*2
  11631. -->
  11632. (S1 ^operator O1966 = 0.2381416323002802)
  11633. Firing rl*prefer*rvt*predict-yes*H0*1
  11634. -->
  11635. (S1 ^operator O1965 = 0.3499208421881511)
  11636. Firing prefer*rvt*predict-yes*H0
  11637. -->
  11638. Firing prefer*rvt*predict-no*H0
  11639. -->
  11640. Firing elaborate*copy-dir-to-output-link
  11641. -->
  11642. (I3 ^dir L +)
  11643. inner elaboration loop at bottom goal.
  11644. Retracting elaborate*copy-see-to-output-link
  11645. -->
  11646. (I3 ^see 0 +)
  11647. Retracting propose*predict-no
  11648. -->
  11649. (O1966 ^name predict-no +)
  11650. (S1 ^operator O1966 +)
  11651. Retracting propose*predict-yes
  11652. -->
  11653. (O1965 ^name predict-yes +)
  11654. (S1 ^operator O1965 +)
  11655. Retracting elaborate*reward*based*on*reward
  11656. -->
  11657. (R986 ^value 1 +)
  11658. (R1 ^reward R986 +)
  11659. Retracting elaborate*copy-dir-to-output-link
  11660. -->
  11661. (I3 ^dir R +)
  11662. Retracting rl*prefer*rvt*predict-no*H0*6
  11663. -->
  11664. (S1 ^operator O1966 = 0.9995667581249172)
  11665. Retracting rl*prefer*rvt*predict-yes*H0*5
  11666. -->
  11667. (S1 ^operator O1965 = 0.2239257038534186)
  11668. Retracting rl*prefer*rvt*predict-yes*H0*5*H1*10
  11669. -->
  11670. (S1 ^operator O1965 = -0.2099933006338622)
  11671. =>WM: (13786: S1 ^operator O1968 +)
  11672. =>WM: (13785: S1 ^operator O1967 +)
  11673. =>WM: (13784: I3 ^dir L)
  11674. =>WM: (13783: O1968 ^name predict-no)
  11675. =>WM: (13782: O1967 ^name predict-yes)
  11676. =>WM: (13781: R987 ^value 1)
  11677. =>WM: (13780: R1 ^reward R987)
  11678. <=WM: (13771: S1 ^operator O1965 +)
  11679. <=WM: (13772: S1 ^operator O1966 +)
  11680. <=WM: (13773: S1 ^operator O1966)
  11681. <=WM: (13770: I3 ^dir R)
  11682. <=WM: (13766: R1 ^reward R986)
  11683. <=WM: (13769: O1966 ^name predict-no)
  11684. <=WM: (13768: O1965 ^name predict-yes)
  11685. <=WM: (13767: R986 ^value 1)
  11686. --- Inner Elaboration Phase, active level 1 (S1) ---
  11687. Firing prefer*rvt*predict-yes*H0
  11688. -->
  11689. Firing rl*prefer*rvt*predict-yes*H0*1
  11690. -->
  11691. (S1 ^operator O1967 = 0.3499208421881511)
  11692. Firing prefer*rvt*predict-yes*H0*1*H1
  11693. -->
  11694. Firing rl*prefer*rvt*predict-yes*H0*1*H1*13
  11695. -->
  11696. (S1 ^operator O1967 = 0.6500789468007531)
  11697. Firing prefer*rvt*predict-no*H0
  11698. -->
  11699. Firing rl*prefer*rvt*predict-no*H0*2
  11700. -->
  11701. (S1 ^operator O1968 = 0.2381416323002802)
  11702. Firing prefer*rvt*predict-no*H0*2*H1
  11703. -->
  11704. Firing rl*prefer*rvt*predict-no*H0*2*H1*12
  11705. -->
  11706. (S1 ^operator O1968 = -0.1359494083332169)
  11707. inner elaboration loop at bottom goal.
  11708. Retracting rl*prefer*rvt*predict-no*H0*2
  11709. -->
  11710. (S1 ^operator O1966 = 0.2381416323002802)
  11711. Retracting rl*prefer*rvt*predict-no*H0*2*H1*12
  11712. -->
  11713. (S1 ^operator O1966 = -0.1359494083332169)
  11714. Retracting rl*prefer*rvt*predict-yes*H0*1
  11715. -->
  11716. (S1 ^operator O1965 = 0.3499208421881511)
  11717. Retracting rl*prefer*rvt*predict-yes*H0*1*H1*13
  11718. -->
  11719. (S1 ^operator O1965 = 0.6500789468007531)
  11720. --- END Proposal Phase ---
  11721. --- Decision Phase ---
  11722. RL update rl*prefer*rvt*predict-no*H0*6 0.999567 0 0.999567 -> 0.999637 0 0.999637(R,m,v=1,0.860465,0.120767)
  11723. =>WM: (13787: S1 ^operator O1967)
  11724. 984: O: O1967 (predict-yes)
  11725. --- END Decision Phase ---
  11726. --- Application Phase ---
  11727. --- Firing Productions (PE) For State At Depth 1 ---
  11728. --- Inner Elaboration Phase, active level 1 (S1) ---
  11729. Firing apply*operator
  11730. -->
  11731. (I3 ^predict-yes N984 + :O )
  11732. Firing apply*operator*complete
  11733. -->
  11734. (I3 ^predict-no N983 - :O )
  11735. inner elaboration loop at bottom goal.
  11736. --- Change Working Memory (PE) ---
  11737. =>WM: (13788: I3 ^predict-yes N984)
  11738. <=WM: (13775: N983 ^status complete)
  11739. <=WM: (13774: I3 ^predict-no N983)
  11740. --- Firing Productions (IE) For State At Depth 1 ---
  11741. --- Inner Elaboration Phase, active level 1 (S1) ---
  11742. Firing monitor*world
  11743. -->
  11744. I see 1 and I'm going to do: predict-yes inner elaboration loop at bottom goal.
  11745. --- Change Working Memory (IE) ---
  11746. --- END Application Phase ---
  11747. --- Output Phase ---
  11748. ENV: Agent did: predict-yes for direction L in state State-B
  11749. In State-B moving L
  11750. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  11751. predict error 0
  11752. dir: dir isU
  11753. --- END Output Phase ---
  11754. /|\--- Input Phase ---
  11755. =>WM: (13792: I2 ^dir U)
  11756. =>WM: (13791: I2 ^reward 1)
  11757. =>WM: (13790: I2 ^see 1)
  11758. =>WM: (13789: N984 ^status complete)
  11759. <=WM: (13778: I2 ^dir L)
  11760. <=WM: (13777: I2 ^reward 1)
  11761. <=WM: (13776: I2 ^see 0)
  11762. =>WM: (13793: I2 ^level-1 L1-root)
  11763. <=WM: (13779: I2 ^level-1 R0-root)
  11764. --- END Input Phase ---
  11765. --- Proposal Phase ---
  11766. --- Inner Elaboration Phase, active level 1 (S1) ---
  11767. Firing elaborate*copy-see-to-output-link
  11768. -->
  11769. (I3 ^see 1 +)
  11770. Firing elaborate*reward*based*on*reward
  11771. -->
  11772. (R988 ^value 1 +)
  11773. (R1 ^reward R988 +)
  11774. Firing propose*predict-yes
  11775. -->
  11776. (O1969 ^name predict-yes +)
  11777. (S1 ^operator O1969 +)
  11778. Firing propose*predict-no
  11779. -->
  11780. (O1970 ^name predict-no +)
  11781. (S1 ^operator O1970 +)
  11782. Firing rl*prefer*rvt*predict-no*H0*4
  11783. -->
  11784. (S1 ^operator O1968 = 1.)
  11785. Firing rl*prefer*rvt*predict-yes*H0*3
  11786. -->
  11787. (S1 ^operator O1967 = 0.)
  11788. Firing prefer*rvt*predict-yes*H0
  11789. -->
  11790. Firing prefer*rvt*predict-no*H0
  11791. -->
  11792. Firing elaborate*copy-dir-to-output-link
  11793. -->
  11794. (I3 ^dir U +)
  11795. inner elaboration loop at bottom goal.
  11796. Retracting elaborate*copy-see-to-output-link
  11797. -->
  11798. (I3 ^see 0 +)
  11799. Retracting propose*predict-no
  11800. -->
  11801. (O1968 ^name predict-no +)
  11802. (S1 ^operator O1968 +)
  11803. Retracting propose*predict-yes
  11804. -->
  11805. (O1967 ^name predict-yes +)
  11806. (S1 ^operator O1967 +)
  11807. Retracting elaborate*reward*based*on*reward
  11808. -->
  11809. (R987 ^value 1 +)
  11810. (R1 ^reward R987 +)
  11811. Retracting elaborate*copy-dir-to-output-link
  11812. -->
  11813. (I3 ^dir L +)
  11814. Retracting rl*prefer*rvt*predict-no*H0*2*H1*12
  11815. -->
  11816. (S1 ^operator O1968 = -0.1359494083332169)
  11817. Retracting rl*prefer*rvt*predict-no*H0*2
  11818. -->
  11819. (S1 ^operator O1968 = 0.2381416323002802)
  11820. Retracting rl*prefer*rvt*predict-yes*H0*1*H1*13
  11821. -->
  11822. (S1 ^operator O1967 = 0.6500789468007531)
  11823. Retracting rl*prefer*rvt*predict-yes*H0*1
  11824. -->
  11825. (S1 ^operator O1967 = 0.3499208421881511)
  11826. =>WM: (13801: S1 ^operator O1970 +)
  11827. =>WM: (13800: S1 ^operator O1969 +)
  11828. =>WM: (13799: I3 ^dir U)
  11829. =>WM: (13798: O1970 ^name predict-no)
  11830. =>WM: (13797: O1969 ^name predict-yes)
  11831. =>WM: (13796: R988 ^value 1)
  11832. =>WM: (13795: R1 ^reward R988)
  11833. =>WM: (13794: I3 ^see 1)
  11834. <=WM: (13785: S1 ^operator O1967 +)
  11835. <=WM: (13787: S1 ^operator O1967)
  11836. <=WM: (13786: S1 ^operator O1968 +)
  11837. <=WM: (13784: I3 ^dir L)
  11838. <=WM: (13780: R1 ^reward R987)
  11839. <=WM: (13765: I3 ^see 0)
  11840. <=WM: (13783: O1968 ^name predict-no)
  11841. <=WM: (13782: O1967 ^name predict-yes)
  11842. <=WM: (13781: R987 ^value 1)
  11843. --- Inner Elaboration Phase, active level 1 (S1) ---
  11844. Firing prefer*rvt*predict-yes*H0
  11845. -->
  11846. Firing rl*prefer*rvt*predict-yes*H0*3
  11847. -->
  11848. (S1 ^operator O1969 = 0.)
  11849. Firing prefer*rvt*predict-no*H0
  11850. -->
  11851. Firing rl*prefer*rvt*predict-no*H0*4
  11852. -->
  11853. (S1 ^operator O1970 = 1.)
  11854. inner elaboration loop at bottom goal.
  11855. Retracting rl*prefer*rvt*predict-no*H0*4
  11856. -->
  11857. (S1 ^operator O1968 = 1.)
  11858. Retracting rl*prefer*rvt*predict-yes*H0*3
  11859. -->
  11860. (S1 ^operator O1967 = 0.)
  11861. --- END Proposal Phase ---
  11862. --- Decision Phase ---
  11863. RL update rl*prefer*rvt*predict-yes*H0*1 0.407929 -0.0580077 0.349921 -> 0.407928 -0.0580073 0.349921(R,m,v=1,0.900662,0.0900662)
  11864. RL update rl*prefer*rvt*predict-yes*H0*1*H1*13 0.592075 0.0580036 0.650079 -> 0.592075 0.058004 0.650079(R,m,v=1,1,0)
  11865. =>WM: (13802: S1 ^operator O1970)
  11866. 985: O: O1970 (predict-no)
  11867. --- END Decision Phase ---
  11868. --- Application Phase ---
  11869. --- Firing Productions (PE) For State At Depth 1 ---
  11870. --- Inner Elaboration Phase, active level 1 (S1) ---
  11871. Firing apply*operator
  11872. -->
  11873. (I3 ^predict-no N985 + :O )
  11874. Firing apply*operator*complete
  11875. -->
  11876. (I3 ^predict-yes N984 - :O )
  11877. inner elaboration loop at bottom goal.
  11878. --- Change Working Memory (PE) ---
  11879. =>WM: (13803: I3 ^predict-no N985)
  11880. <=WM: (13789: N984 ^status complete)
  11881. <=WM: (13788: I3 ^predict-yes N984)
  11882. --- Firing Productions (IE) For State At Depth 1 ---
  11883. --- Inner Elaboration Phase, active level 1 (S1) ---
  11884. Firing monitor*world
  11885. -->
  11886. I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
  11887. --- Change Working Memory (IE) ---
  11888. --- END Application Phase ---
  11889. --- Output Phase ---
  11890. ENV: Agent did: predict-no for direction U in state State-A
  11891. In State-A moving U
  11892. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  11893. predict error 0
  11894. dir: dir isR
  11895. --- END Output Phase ---
  11896. -/|--- Input Phase ---
  11897. =>WM: (13807: I2 ^dir R)
  11898. =>WM: (13806: I2 ^reward 1)
  11899. =>WM: (13805: I2 ^see 0)
  11900. =>WM: (13804: N985 ^status complete)
  11901. <=WM: (13792: I2 ^dir U)
  11902. <=WM: (13791: I2 ^reward 1)
  11903. <=WM: (13790: I2 ^see 1)
  11904. =>WM: (13808: I2 ^level-1 L1-root)
  11905. <=WM: (13793: I2 ^level-1 L1-root)
  11906. --- END Input Phase ---
  11907. --- Proposal Phase ---
  11908. --- Inner Elaboration Phase, active level 1 (S1) ---
  11909. Firing rl*prefer*rvt*predict-yes*H0*5*H1*9
  11910. -->
  11911. (S1 ^operator O1969 = 0.7761995477229264)
  11912. Firing prefer*rvt*predict-yes*H0*5*H1
  11913. -->
  11914. Firing elaborate*copy-see-to-output-link
  11915. -->
  11916. (I3 ^see 0 +)
  11917. Firing elaborate*reward*based*on*reward
  11918. -->
  11919. (R989 ^value 1 +)
  11920. (R1 ^reward R989 +)
  11921. Firing propose*predict-yes
  11922. -->
  11923. (O1971 ^name predict-yes +)
  11924. (S1 ^operator O1971 +)
  11925. Firing propose*predict-no
  11926. -->
  11927. (O1972 ^name predict-no +)
  11928. (S1 ^operator O1972 +)
  11929. Firing rl*prefer*rvt*predict-no*H0*6
  11930. -->
  11931. (S1 ^operator O1970 = 0.9996372326697447)
  11932. Firing rl*prefer*rvt*predict-yes*H0*5
  11933. -->
  11934. (S1 ^operator O1969 = 0.2239257038534186)
  11935. Firing prefer*rvt*predict-yes*H0
  11936. -->
  11937. Firing prefer*rvt*predict-no*H0
  11938. -->
  11939. Firing elaborate*copy-dir-to-output-link
  11940. -->
  11941. (I3 ^dir R +)
  11942. inner elaboration loop at bottom goal.
  11943. Retracting elaborate*copy-see-to-output-link
  11944. -->
  11945. (I3 ^see 1 +)
  11946. Retracting propose*predict-no
  11947. -->
  11948. (O1970 ^name predict-no +)
  11949. (S1 ^operator O1970 +)
  11950. Retracting propose*predict-yes
  11951. -->
  11952. (O1969 ^name predict-yes +)
  11953. (S1 ^operator O1969 +)
  11954. Retracting elaborate*reward*based*on*reward
  11955. -->
  11956. (R988 ^value 1 +)
  11957. (R1 ^reward R988 +)
  11958. Retracting elaborate*copy-dir-to-output-link
  11959. -->
  11960. (I3 ^dir U +)
  11961. Retracting rl*prefer*rvt*predict-no*H0*4
  11962. -->
  11963. (S1 ^operator O1970 = 1.)
  11964. Retracting rl*prefer*rvt*predict-yes*H0*3
  11965. -->
  11966. (S1 ^operator O1969 = 0.)
  11967. =>WM: (13816: S1 ^operator O1972 +)
  11968. =>WM: (13815: S1 ^operator O1971 +)
  11969. =>WM: (13814: I3 ^dir R)
  11970. =>WM: (13813: O1972 ^name predict-no)
  11971. =>WM: (13812: O1971 ^name predict-yes)
  11972. =>WM: (13811: R989 ^value 1)
  11973. =>WM: (13810: R1 ^reward R989)
  11974. =>WM: (13809: I3 ^see 0)
  11975. <=WM: (13800: S1 ^operator O1969 +)
  11976. <=WM: (13801: S1 ^operator O1970 +)
  11977. <=WM: (13802: S1 ^operator O1970)
  11978. <=WM: (13799: I3 ^dir U)
  11979. <=WM: (13795: R1 ^reward R988)
  11980. <=WM: (13794: I3 ^see 1)
  11981. <=WM: (13798: O1970 ^name predict-no)
  11982. <=WM: (13797: O1969 ^name predict-yes)
  11983. <=WM: (13796: R988 ^value 1)
  11984. --- Inner Elaboration Phase, active level 1 (S1) ---
  11985. Firing prefer*rvt*predict-yes*H0
  11986. -->
  11987. Firing rl*prefer*rvt*predict-yes*H0*5*H1*9
  11988. -->
  11989. (S1 ^operator O1971 = 0.7761995477229264)
  11990. Firing rl*prefer*rvt*predict-yes*H0*5
  11991. -->
  11992. (S1 ^operator O1971 = 0.2239257038534186)
  11993. Firing prefer*rvt*predict-yes*H0*5*H1
  11994. -->
  11995. Firing prefer*rvt*predict-no*H0
  11996. -->
  11997. Firing rl*prefer*rvt*predict-no*H0*6
  11998. -->
  11999. (S1 ^operator O1972 = 0.9996372326697447)
  12000. inner elaboration loop at bottom goal.
  12001. Retracting rl*prefer*rvt*predict-no*H0*6
  12002. -->
  12003. (S1 ^operator O1970 = 0.9996372326697447)
  12004. Retracting rl*prefer*rvt*predict-yes*H0*5
  12005. -->
  12006. (S1 ^operator O1969 = 0.2239257038534186)
  12007. Retracting rl*prefer*rvt*predict-yes*H0*5*H1*9
  12008. -->
  12009. (S1 ^operator O1969 = 0.7761995477229264)
  12010. --- END Proposal Phase ---
  12011. --- Decision Phase ---
  12012. RL update rl*prefer*rvt*predict-no*H0*4 1 0 1 -> 1 0 1(R,m,v=1,1,0)
  12013. =>WM: (13817: S1 ^operator O1971)
  12014. 986: O: O1971 (predict-yes)
  12015. --- END Decision Phase ---
  12016. --- Application Phase ---
  12017. --- Firing Productions (PE) For State At Depth 1 ---
  12018. --- Inner Elaboration Phase, active level 1 (S1) ---
  12019. Firing apply*operator
  12020. -->
  12021. (I3 ^predict-yes N986 + :O )
  12022. Firing apply*operator*complete
  12023. -->
  12024. (I3 ^predict-no N985 - :O )
  12025. inner elaboration loop at bottom goal.
  12026. --- Change Working Memory (PE) ---
  12027. =>WM: (13818: I3 ^predict-yes N986)
  12028. <=WM: (13804: N985 ^status complete)
  12029. <=WM: (13803: I3 ^predict-no N985)
  12030. --- Firing Productions (IE) For State At Depth 1 ---
  12031. --- Inner Elaboration Phase, active level 1 (S1) ---
  12032. Firing monitor*world
  12033. -->
  12034. I see 1 and I'm going to do: predict-yes inner elaboration loop at bottom goal.
  12035. --- Change Working Memory (IE) ---
  12036. --- END Application Phase ---
  12037. --- Output Phase ---
  12038. ENV: Agent did: predict-yes for direction R in state State-A
  12039. In State-A moving R
  12040. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  12041. predict error 0
  12042. dir: dir isR
  12043. --- END Output Phase ---
  12044. \-/--- Input Phase ---
  12045. =>WM: (13822: I2 ^dir R)
  12046. =>WM: (13821: I2 ^reward 1)
  12047. =>WM: (13820: I2 ^see 1)
  12048. =>WM: (13819: N986 ^status complete)
  12049. <=WM: (13807: I2 ^dir R)
  12050. <=WM: (13806: I2 ^reward 1)
  12051. <=WM: (13805: I2 ^see 0)
  12052. =>WM: (13823: I2 ^level-1 R1-root)
  12053. <=WM: (13808: I2 ^level-1 L1-root)
  12054. --- END Input Phase ---
  12055. --- Proposal Phase ---
  12056. --- Inner Elaboration Phase, active level 1 (S1) ---
  12057. Firing rl*prefer*rvt*predict-yes*H0*5*H1*10
  12058. -->
  12059. (S1 ^operator O1971 = -0.2099933006338622)
  12060. Firing prefer*rvt*predict-yes*H0*5*H1
  12061. -->
  12062. Firing elaborate*copy-see-to-output-link
  12063. -->
  12064. (I3 ^see 1 +)
  12065. Firing elaborate*reward*based*on*reward
  12066. -->
  12067. (R990 ^value 1 +)
  12068. (R1 ^reward R990 +)
  12069. Firing propose*predict-yes
  12070. -->
  12071. (O1973 ^name predict-yes +)
  12072. (S1 ^operator O1973 +)
  12073. Firing propose*predict-no
  12074. -->
  12075. (O1974 ^name predict-no +)
  12076. (S1 ^operator O1974 +)
  12077. Firing rl*prefer*rvt*predict-no*H0*6
  12078. -->
  12079. (S1 ^operator O1972 = 0.9996372326697447)
  12080. Firing rl*prefer*rvt*predict-yes*H0*5
  12081. -->
  12082. (S1 ^operator O1971 = 0.2239257038534186)
  12083. Firing prefer*rvt*predict-yes*H0
  12084. -->
  12085. Firing prefer*rvt*predict-no*H0
  12086. -->
  12087. Firing elaborate*copy-dir-to-output-link
  12088. -->
  12089. (I3 ^dir R +)
  12090. inner elaboration loop at bottom goal.
  12091. Retracting elaborate*copy-see-to-output-link
  12092. -->
  12093. (I3 ^see 0 +)
  12094. Retracting propose*predict-no
  12095. -->
  12096. (O1972 ^name predict-no +)
  12097. (S1 ^operator O1972 +)
  12098. Retracting propose*predict-yes
  12099. -->
  12100. (O1971 ^name predict-yes +)
  12101. (S1 ^operator O1971 +)
  12102. Retracting elaborate*reward*based*on*reward
  12103. -->
  12104. (R989 ^value 1 +)
  12105. (R1 ^reward R989 +)
  12106. Retracting elaborate*copy-dir-to-output-link
  12107. -->
  12108. (I3 ^dir R +)
  12109. Retracting rl*prefer*rvt*predict-no*H0*6
  12110. -->
  12111. (S1 ^operator O1972 = 0.9996372326697447)
  12112. Retracting rl*prefer*rvt*predict-yes*H0*5
  12113. -->
  12114. (S1 ^operator O1971 = 0.2239257038534186)
  12115. Retracting rl*prefer*rvt*predict-yes*H0*5*H1*9
  12116. -->
  12117. (S1 ^operator O1971 = 0.7761995477229264)
  12118. =>WM: (13830: S1 ^operator O1974 +)
  12119. =>WM: (13829: S1 ^operator O1973 +)
  12120. =>WM: (13828: O1974 ^name predict-no)
  12121. =>WM: (13827: O1973 ^name predict-yes)
  12122. =>WM: (13826: R990 ^value 1)
  12123. =>WM: (13825: R1 ^reward R990)
  12124. =>WM: (13824: I3 ^see 1)
  12125. <=WM: (13815: S1 ^operator O1971 +)
  12126. <=WM: (13817: S1 ^operator O1971)
  12127. <=WM: (13816: S1 ^operator O1972 +)
  12128. <=WM: (13810: R1 ^reward R989)
  12129. <=WM: (13809: I3 ^see 0)
  12130. <=WM: (13813: O1972 ^name predict-no)
  12131. <=WM: (13812: O1971 ^name predict-yes)
  12132. <=WM: (13811: R989 ^value 1)
  12133. --- Inner Elaboration Phase, active level 1 (S1) ---
  12134. Firing prefer*rvt*predict-yes*H0
  12135. -->
  12136. Firing rl*prefer*rvt*predict-yes*H0*5
  12137. -->
  12138. (S1 ^operator O1973 = 0.2239257038534186)
  12139. Firing prefer*rvt*predict-yes*H0*5*H1
  12140. -->
  12141. Firing rl*prefer*rvt*predict-yes*H0*5*H1*10
  12142. -->
  12143. (S1 ^operator O1973 = -0.2099933006338622)
  12144. Firing prefer*rvt*predict-no*H0
  12145. -->
  12146. Firing rl*prefer*rvt*predict-no*H0*6
  12147. -->
  12148. (S1 ^operator O1974 = 0.9996372326697447)
  12149. inner elaboration loop at bottom goal.
  12150. Retracting rl*prefer*rvt*predict-no*H0*6
  12151. -->
  12152. (S1 ^operator O1972 = 0.9996372326697447)
  12153. Retracting rl*prefer*rvt*predict-yes*H0*5
  12154. -->
  12155. (S1 ^operator O1971 = 0.2239257038534186)
  12156. Retracting rl*prefer*rvt*predict-yes*H0*5*H1*10
  12157. -->
  12158. (S1 ^operator O1971 = -0.2099933006338622)
  12159. --- END Proposal Phase ---
  12160. --- Decision Phase ---
  12161. RL update rl*prefer*rvt*predict-yes*H0*5 0.553538 -0.329612 0.223926 -> 0.553527 -0.329612 0.223915(R,m,v=1,0.857143,0.123249)
  12162. RL update rl*prefer*rvt*predict-yes*H0*5*H1*9 0.446588 0.329612 0.7762 -> 0.446576 0.329612 0.776187(R,m,v=1,1,0)
  12163. =>WM: (13831: S1 ^operator O1974)
  12164. 987: O: O1974 (predict-no)
  12165. --- END Decision Phase ---
  12166. --- Application Phase ---
  12167. --- Firing Productions (PE) For State At Depth 1 ---
  12168. --- Inner Elaboration Phase, active level 1 (S1) ---
  12169. Firing apply*operator
  12170. -->
  12171. (I3 ^predict-no N987 + :O )
  12172. Firing apply*operator*complete
  12173. -->
  12174. (I3 ^predict-yes N986 - :O )
  12175. inner elaboration loop at bottom goal.
  12176. --- Change Working Memory (PE) ---
  12177. =>WM: (13832: I3 ^predict-no N987)
  12178. <=WM: (13819: N986 ^status complete)
  12179. <=WM: (13818: I3 ^predict-yes N986)
  12180. --- Firing Productions (IE) For State At Depth 1 ---
  12181. --- Inner Elaboration Phase, active level 1 (S1) ---
  12182. Firing monitor*world
  12183. -->
  12184. I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
  12185. --- Change Working Memory (IE) ---
  12186. --- END Application Phase ---
  12187. --- Output Phase ---
  12188. ENV: Agent did: predict-no for direction R in state State-B
  12189. In State-B moving R
  12190. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  12191. predict error 0
  12192. dir: dir isL
  12193. --- END Output Phase ---
  12194. |\---- Input Phase ---
  12195. =>WM: (13836: I2 ^dir L)
  12196. =>WM: (13835: I2 ^reward 1)
  12197. =>WM: (13834: I2 ^see 0)
  12198. =>WM: (13833: N987 ^status complete)
  12199. <=WM: (13822: I2 ^dir R)
  12200. <=WM: (13821: I2 ^reward 1)
  12201. <=WM: (13820: I2 ^see 1)
  12202. =>WM: (13837: I2 ^level-1 R0-root)
  12203. <=WM: (13823: I2 ^level-1 R1-root)
  12204. --- END Input Phase ---
  12205. --- Proposal Phase ---
  12206. --- Inner Elaboration Phase, active level 1 (S1) ---
  12207. Firing rl*prefer*rvt*predict-no*H0*2*H1*12
  12208. -->
  12209. (S1 ^operator O1974 = -0.1359494083332169)
  12210. Firing rl*prefer*rvt*predict-yes*H0*1*H1*13
  12211. -->
  12212. (S1 ^operator O1973 = 0.6500789670144502)
  12213. Firing prefer*rvt*predict-no*H0*2*H1
  12214. -->
  12215. Firing prefer*rvt*predict-yes*H0*1*H1
  12216. -->
  12217. Firing elaborate*copy-see-to-output-link
  12218. -->
  12219. (I3 ^see 0 +)
  12220. Firing elaborate*reward*based*on*reward
  12221. -->
  12222. (R991 ^value 1 +)
  12223. (R1 ^reward R991 +)
  12224. Firing propose*predict-yes
  12225. -->
  12226. (O1975 ^name predict-yes +)
  12227. (S1 ^operator O1975 +)
  12228. Firing propose*predict-no
  12229. -->
  12230. (O1976 ^name predict-no +)
  12231. (S1 ^operator O1976 +)
  12232. Firing rl*prefer*rvt*predict-no*H0*2
  12233. -->
  12234. (S1 ^operator O1974 = 0.2381416323002802)
  12235. Firing rl*prefer*rvt*predict-yes*H0*1
  12236. -->
  12237. (S1 ^operator O1973 = 0.3499208597219124)
  12238. Firing prefer*rvt*predict-yes*H0
  12239. -->
  12240. Firing prefer*rvt*predict-no*H0
  12241. -->
  12242. Firing elaborate*copy-dir-to-output-link
  12243. -->
  12244. (I3 ^dir L +)
  12245. inner elaboration loop at bottom goal.
  12246. Retracting elaborate*copy-see-to-output-link
  12247. -->
  12248. (I3 ^see 1 +)
  12249. Retracting propose*predict-no
  12250. -->
  12251. (O1974 ^name predict-no +)
  12252. (S1 ^operator O1974 +)
  12253. Retracting propose*predict-yes
  12254. -->
  12255. (O1973 ^name predict-yes +)
  12256. (S1 ^operator O1973 +)
  12257. Retracting elaborate*reward*based*on*reward
  12258. -->
  12259. (R990 ^value 1 +)
  12260. (R1 ^reward R990 +)
  12261. Retracting elaborate*copy-dir-to-output-link
  12262. -->
  12263. (I3 ^dir R +)
  12264. Retracting rl*prefer*rvt*predict-no*H0*6
  12265. -->
  12266. (S1 ^operator O1974 = 0.9996372326697447)
  12267. Retracting rl*prefer*rvt*predict-yes*H0*5*H1*10
  12268. -->
  12269. (S1 ^operator O1973 = -0.2099933006338622)
  12270. Retracting rl*prefer*rvt*predict-yes*H0*5
  12271. -->
  12272. (S1 ^operator O1973 = 0.2239153301115165)
  12273. =>WM: (13845: S1 ^operator O1976 +)
  12274. =>WM: (13844: S1 ^operator O1975 +)
  12275. =>WM: (13843: I3 ^dir L)
  12276. =>WM: (13842: O1976 ^name predict-no)
  12277. =>WM: (13841: O1975 ^name predict-yes)
  12278. =>WM: (13840: R991 ^value 1)
  12279. =>WM: (13839: R1 ^reward R991)
  12280. =>WM: (13838: I3 ^see 0)
  12281. <=WM: (13829: S1 ^operator O1973 +)
  12282. <=WM: (13830: S1 ^operator O1974 +)
  12283. <=WM: (13831: S1 ^operator O1974)
  12284. <=WM: (13814: I3 ^dir R)
  12285. <=WM: (13825: R1 ^reward R990)
  12286. <=WM: (13824: I3 ^see 1)
  12287. <=WM: (13828: O1974 ^name predict-no)
  12288. <=WM: (13827: O1973 ^name predict-yes)
  12289. <=WM: (13826: R990 ^value 1)
  12290. --- Inner Elaboration Phase, active level 1 (S1) ---
  12291. Firing prefer*rvt*predict-yes*H0
  12292. -->
  12293. Firing rl*prefer*rvt*predict-yes*H0*1
  12294. -->
  12295. (S1 ^operator O1975 = 0.3499208597219124)
  12296. Firing prefer*rvt*predict-yes*H0*1*H1
  12297. -->
  12298. Firing rl*prefer*rvt*predict-yes*H0*1*H1*13
  12299. -->
  12300. (S1 ^operator O1975 = 0.6500789670144502)
  12301. Firing prefer*rvt*predict-no*H0
  12302. -->
  12303. Firing rl*prefer*rvt*predict-no*H0*2
  12304. -->
  12305. (S1 ^operator O1976 = 0.2381416323002802)
  12306. Firing prefer*rvt*predict-no*H0*2*H1
  12307. -->
  12308. Firing rl*prefer*rvt*predict-no*H0*2*H1*12
  12309. -->
  12310. (S1 ^operator O1976 = -0.1359494083332169)
  12311. inner elaboration loop at bottom goal.
  12312. Retracting rl*prefer*rvt*predict-no*H0*2
  12313. -->
  12314. (S1 ^operator O1974 = 0.2381416323002802)
  12315. Retracting rl*prefer*rvt*predict-no*H0*2*H1*12
  12316. -->
  12317. (S1 ^operator O1974 = -0.1359494083332169)
  12318. Retracting rl*prefer*rvt*predict-yes*H0*1
  12319. -->
  12320. (S1 ^operator O1973 = 0.3499208597219124)
  12321. Retracting rl*prefer*rvt*predict-yes*H0*1*H1*13
  12322. -->
  12323. (S1 ^operator O1973 = 0.6500789670144502)
  12324. --- END Proposal Phase ---
  12325. --- Decision Phase ---
  12326. RL update rl*prefer*rvt*predict-no*H0*6 0.999637 0 0.999637 -> 0.999696 0 0.999696(R,m,v=1,0.861272,0.120177)
  12327. =>WM: (13846: S1 ^operator O1975)
  12328. 988: O: O1975 (predict-yes)
  12329. --- END Decision Phase ---
  12330. --- Application Phase ---
  12331. --- Firing Productions (PE) For State At Depth 1 ---
  12332. --- Inner Elaboration Phase, active level 1 (S1) ---
  12333. Firing apply*operator
  12334. -->
  12335. (I3 ^predict-yes N988 + :O )
  12336. Firing apply*operator*complete
  12337. -->
  12338. (I3 ^predict-no N987 - :O )
  12339. inner elaboration loop at bottom goal.
  12340. --- Change Working Memory (PE) ---
  12341. =>WM: (13847: I3 ^predict-yes N988)
  12342. <=WM: (13833: N987 ^status complete)
  12343. <=WM: (13832: I3 ^predict-no N987)
  12344. --- Firing Productions (IE) For State At Depth 1 ---
  12345. --- Inner Elaboration Phase, active level 1 (S1) ---
  12346. Firing monitor*world
  12347. -->
  12348. I see 1 and I'm going to do: predict-yes inner elaboration loop at bottom goal.
  12349. --- Change Working Memory (IE) ---
  12350. --- END Application Phase ---
  12351. --- Output Phase ---
  12352. ENV: Agent did: predict-yes for direction L in state State-B
  12353. In State-B moving L
  12354. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  12355. predict error 0
  12356. dir: dir isU
  12357. --- END Output Phase ---
  12358. /|\---- Input Phase ---
  12359. =>WM: (13851: I2 ^dir U)
  12360. =>WM: (13850: I2 ^reward 1)
  12361. =>WM: (13849: I2 ^see 1)
  12362. =>WM: (13848: N988 ^status complete)
  12363. <=WM: (13836: I2 ^dir L)
  12364. <=WM: (13835: I2 ^reward 1)
  12365. <=WM: (13834: I2 ^see 0)
  12366. =>WM: (13852: I2 ^level-1 L1-root)
  12367. <=WM: (13837: I2 ^level-1 R0-root)
  12368. --- END Input Phase ---
  12369. --- Proposal Phase ---
  12370. --- Inner Elaboration Phase, active level 1 (S1) ---
  12371. Firing elaborate*copy-see-to-output-link
  12372. -->
  12373. (I3 ^see 1 +)
  12374. Firing elaborate*reward*based*on*reward
  12375. -->
  12376. (R992 ^value 1 +)
  12377. (R1 ^reward R992 +)
  12378. Firing propose*predict-yes
  12379. -->
  12380. (O1977 ^name predict-yes +)
  12381. (S1 ^operator O1977 +)
  12382. Firing propose*predict-no
  12383. -->
  12384. (O1978 ^name predict-no +)
  12385. (S1 ^operator O1978 +)
  12386. Firing rl*prefer*rvt*predict-no*H0*4
  12387. -->
  12388. (S1 ^operator O1976 = 1.)
  12389. Firing rl*prefer*rvt*predict-yes*H0*3
  12390. -->
  12391. (S1 ^operator O1975 = 0.)
  12392. Firing prefer*rvt*predict-yes*H0
  12393. -->
  12394. Firing prefer*rvt*predict-no*H0
  12395. -->
  12396. Firing elaborate*copy-dir-to-output-link
  12397. -->
  12398. (I3 ^dir U +)
  12399. inner elaboration loop at bottom goal.
  12400. Retracting elaborate*copy-see-to-output-link
  12401. -->
  12402. (I3 ^see 0 +)
  12403. Retracting propose*predict-no
  12404. -->
  12405. (O1976 ^name predict-no +)
  12406. (S1 ^operator O1976 +)
  12407. Retracting propose*predict-yes
  12408. -->
  12409. (O1975 ^name predict-yes +)
  12410. (S1 ^operator O1975 +)
  12411. Retracting elaborate*reward*based*on*reward
  12412. -->
  12413. (R991 ^value 1 +)
  12414. (R1 ^reward R991 +)
  12415. Retracting elaborate*copy-dir-to-output-link
  12416. -->
  12417. (I3 ^dir L +)
  12418. Retracting rl*prefer*rvt*predict-no*H0*2*H1*12
  12419. -->
  12420. (S1 ^operator O1976 = -0.1359494083332169)
  12421. Retracting rl*prefer*rvt*predict-no*H0*2
  12422. -->
  12423. (S1 ^operator O1976 = 0.2381416323002802)
  12424. Retracting rl*prefer*rvt*predict-yes*H0*1*H1*13
  12425. -->
  12426. (S1 ^operator O1975 = 0.6500789670144502)
  12427. Retracting rl*prefer*rvt*predict-yes*H0*1
  12428. -->
  12429. (S1 ^operator O1975 = 0.3499208597219124)
  12430. =>WM: (13860: S1 ^operator O1978 +)
  12431. =>WM: (13859: S1 ^operator O1977 +)
  12432. =>WM: (13858: I3 ^dir U)
  12433. =>WM: (13857: O1978 ^name predict-no)
  12434. =>WM: (13856: O1977 ^name predict-yes)
  12435. =>WM: (13855: R992 ^value 1)
  12436. =>WM: (13854: R1 ^reward R992)
  12437. =>WM: (13853: I3 ^see 1)
  12438. <=WM: (13844: S1 ^operator O1975 +)
  12439. <=WM: (13846: S1 ^operator O1975)
  12440. <=WM: (13845: S1 ^operator O1976 +)
  12441. <=WM: (13843: I3 ^dir L)
  12442. <=WM: (13839: R1 ^reward R991)
  12443. <=WM: (13838: I3 ^see 0)
  12444. <=WM: (13842: O1976 ^name predict-no)
  12445. <=WM: (13841: O1975 ^name predict-yes)
  12446. <=WM: (13840: R991 ^value 1)
  12447. --- Inner Elaboration Phase, active level 1 (S1) ---
  12448. Firing prefer*rvt*predict-yes*H0
  12449. -->
  12450. Firing rl*prefer*rvt*predict-yes*H0*3
  12451. -->
  12452. (S1 ^operator O1977 = 0.)
  12453. Firing prefer*rvt*predict-no*H0
  12454. -->
  12455. Firing rl*prefer*rvt*predict-no*H0*4
  12456. -->
  12457. (S1 ^operator O1978 = 1.)
  12458. inner elaboration loop at bottom goal.
  12459. Retracting rl*prefer*rvt*predict-no*H0*4
  12460. -->
  12461. (S1 ^operator O1976 = 1.)
  12462. Retracting rl*prefer*rvt*predict-yes*H0*3
  12463. -->
  12464. (S1 ^operator O1975 = 0.)
  12465. --- END Proposal Phase ---
  12466. --- Decision Phase ---
  12467. RL update rl*prefer*rvt*predict-yes*H0*1 0.407928 -0.0580073 0.349921 -> 0.407928 -0.0580071 0.349921(R,m,v=1,0.901316,0.0895347)
  12468. RL update rl*prefer*rvt*predict-yes*H0*1*H1*13 0.592075 0.058004 0.650079 -> 0.592075 0.0580043 0.650079(R,m,v=1,1,0)
  12469. =>WM: (13861: S1 ^operator O1978)
  12470. 989: O: O1978 (predict-no)
  12471. --- END Decision Phase ---
  12472. --- Application Phase ---
  12473. --- Firing Productions (PE) For State At Depth 1 ---
  12474. --- Inner Elaboration Phase, active level 1 (S1) ---
  12475. Firing apply*operator
  12476. -->
  12477. (I3 ^predict-no N989 + :O )
  12478. Firing apply*operator*complete
  12479. -->
  12480. (I3 ^predict-yes N988 - :O )
  12481. inner elaboration loop at bottom goal.
  12482. --- Change Working Memory (PE) ---
  12483. =>WM: (13862: I3 ^predict-no N989)
  12484. <=WM: (13848: N988 ^status complete)
  12485. <=WM: (13847: I3 ^predict-yes N988)
  12486. --- Firing Productions (IE) For State At Depth 1 ---
  12487. --- Inner Elaboration Phase, active level 1 (S1) ---
  12488. Firing monitor*world
  12489. -->
  12490. I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
  12491. --- Change Working Memory (IE) ---
  12492. --- END Application Phase ---
  12493. --- Output Phase ---
  12494. ENV: Agent did: predict-no for direction U in state State-A
  12495. In State-A moving U
  12496. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  12497. predict error 0
  12498. dir: dir isR
  12499. --- END Output Phase ---
  12500. /|\--- Input Phase ---
  12501. =>WM: (13866: I2 ^dir R)
  12502. =>WM: (13865: I2 ^reward 1)
  12503. =>WM: (13864: I2 ^see 0)
  12504. =>WM: (13863: N989 ^status complete)
  12505. <=WM: (13851: I2 ^dir U)
  12506. <=WM: (13850: I2 ^reward 1)
  12507. <=WM: (13849: I2 ^see 1)
  12508. =>WM: (13867: I2 ^level-1 L1-root)
  12509. <=WM: (13852: I2 ^level-1 L1-root)
  12510. --- END Input Phase ---
  12511. --- Proposal Phase ---
  12512. --- Inner Elaboration Phase, active level 1 (S1) ---
  12513. Firing rl*prefer*rvt*predict-yes*H0*5*H1*9
  12514. -->
  12515. (S1 ^operator O1977 = 0.7761874802943043)
  12516. Firing prefer*rvt*predict-yes*H0*5*H1
  12517. -->
  12518. Firing elaborate*copy-see-to-output-link
  12519. -->
  12520. (I3 ^see 0 +)
  12521. Firing elaborate*reward*based*on*reward
  12522. -->
  12523. (R993 ^value 1 +)
  12524. (R1 ^reward R993 +)
  12525. Firing propose*predict-yes
  12526. -->
  12527. (O1979 ^name predict-yes +)
  12528. (S1 ^operator O1979 +)
  12529. Firing propose*predict-no
  12530. -->
  12531. (O1980 ^name predict-no +)
  12532. (S1 ^operator O1980 +)
  12533. Firing rl*prefer*rvt*predict-no*H0*6
  12534. -->
  12535. (S1 ^operator O1978 = 0.9996961876736941)
  12536. Firing rl*prefer*rvt*predict-yes*H0*5
  12537. -->
  12538. (S1 ^operator O1977 = 0.2239153301115165)
  12539. Firing prefer*rvt*predict-yes*H0
  12540. -->
  12541. Firing prefer*rvt*predict-no*H0
  12542. -->
  12543. Firing elaborate*copy-dir-to-output-link
  12544. -->
  12545. (I3 ^dir R +)
  12546. inner elaboration loop at bottom goal.
  12547. Retracting elaborate*copy-see-to-output-link
  12548. -->
  12549. (I3 ^see 1 +)
  12550. Retracting propose*predict-no
  12551. -->
  12552. (O1978 ^name predict-no +)
  12553. (S1 ^operator O1978 +)
  12554. Retracting propose*predict-yes
  12555. -->
  12556. (O1977 ^name predict-yes +)
  12557. (S1 ^operator O1977 +)
  12558. Retracting elaborate*reward*based*on*reward
  12559. -->
  12560. (R992 ^value 1 +)
  12561. (R1 ^reward R992 +)
  12562. Retracting elaborate*copy-dir-to-output-link
  12563. -->
  12564. (I3 ^dir U +)
  12565. Retracting rl*prefer*rvt*predict-no*H0*4
  12566. -->
  12567. (S1 ^operator O1978 = 1.)
  12568. Retracting rl*prefer*rvt*predict-yes*H0*3
  12569. -->
  12570. (S1 ^operator O1977 = 0.)
  12571. =>WM: (13875: S1 ^operator O1980 +)
  12572. =>WM: (13874: S1 ^operator O1979 +)
  12573. =>WM: (13873: I3 ^dir R)
  12574. =>WM: (13872: O1980 ^name predict-no)
  12575. =>WM: (13871: O1979 ^name predict-yes)
  12576. =>WM: (13870: R993 ^value 1)
  12577. =>WM: (13869: R1 ^reward R993)
  12578. =>WM: (13868: I3 ^see 0)
  12579. <=WM: (13859: S1 ^operator O1977 +)
  12580. <=WM: (13860: S1 ^operator O1978 +)
  12581. <=WM: (13861: S1 ^operator O1978)
  12582. <=WM: (13858: I3 ^dir U)
  12583. <=WM: (13854: R1 ^reward R992)
  12584. <=WM: (13853: I3 ^see 1)
  12585. <=WM: (13857: O1978 ^name predict-no)
  12586. <=WM: (13856: O1977 ^name predict-yes)
  12587. <=WM: (13855: R992 ^value 1)
  12588. --- Inner Elaboration Phase, active level 1 (S1) ---
  12589. Firing prefer*rvt*predict-yes*H0
  12590. -->
  12591. Firing rl*prefer*rvt*predict-yes*H0*5*H1*9
  12592. -->
  12593. (S1 ^operator O1979 = 0.7761874802943043)
  12594. Firing rl*prefer*rvt*predict-yes*H0*5
  12595. -->
  12596. (S1 ^operator O1979 = 0.2239153301115165)
  12597. Firing prefer*rvt*predict-yes*H0*5*H1
  12598. -->
  12599. Firing prefer*rvt*predict-no*H0
  12600. -->
  12601. Firing rl*prefer*rvt*predict-no*H0*6
  12602. -->
  12603. (S1 ^operator O1980 = 0.9996961876736941)
  12604. inner elaboration loop at bottom goal.
  12605. Retracting rl*prefer*rvt*predict-no*H0*6
  12606. -->
  12607. (S1 ^operator O1978 = 0.9996961876736941)
  12608. Retracting rl*prefer*rvt*predict-yes*H0*5
  12609. -->
  12610. (S1 ^operator O1977 = 0.2239153301115165)
  12611. Retracting rl*prefer*rvt*predict-yes*H0*5*H1*9
  12612. -->
  12613. (S1 ^operator O1977 = 0.7761874802943043)
  12614. --- END Proposal Phase ---
  12615. --- Decision Phase ---
  12616. RL update rl*prefer*rvt*predict-no*H0*4 1 0 1 -> 1 0 1(R,m,v=1,1,0)
  12617. =>WM: (13876: S1 ^operator O1979)
  12618. 990: O: O1979 (predict-yes)
  12619. --- END Decision Phase ---
  12620. --- Application Phase ---
  12621. --- Firing Productions (PE) For State At Depth 1 ---
  12622. --- Inner Elaboration Phase, active level 1 (S1) ---
  12623. Firing apply*operator
  12624. -->
  12625. (I3 ^predict-yes N990 + :O )
  12626. Firing apply*operator*complete
  12627. -->
  12628. (I3 ^predict-no N989 - :O )
  12629. inner elaboration loop at bottom goal.
  12630. --- Change Working Memory (PE) ---
  12631. =>WM: (13877: I3 ^predict-yes N990)
  12632. <=WM: (13863: N989 ^status complete)
  12633. <=WM: (13862: I3 ^predict-no N989)
  12634. --- Firing Productions (IE) For State At Depth 1 ---
  12635. --- Inner Elaboration Phase, active level 1 (S1) ---
  12636. Firing monitor*world
  12637. -->
  12638. I see 1 and I'm going to do: predict-yes inner elaboration loop at bottom goal.
  12639. --- Change Working Memory (IE) ---
  12640. --- END Application Phase ---
  12641. --- Output Phase ---
  12642. ENV: Agent did: predict-yes for direction R in state State-A
  12643. In State-A moving R
  12644. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  12645. predict error 0
  12646. dir: dir isU
  12647. --- END Output Phase ---
  12648. -/--- Input Phase ---
  12649. =>WM: (13881: I2 ^dir U)
  12650. =>WM: (13880: I2 ^reward 1)
  12651. =>WM: (13879: I2 ^see 1)
  12652. =>WM: (13878: N990 ^status complete)
  12653. <=WM: (13866: I2 ^dir R)
  12654. <=WM: (13865: I2 ^reward 1)
  12655. <=WM: (13864: I2 ^see 0)
  12656. =>WM: (13882: I2 ^level-1 R1-root)
  12657. <=WM: (13867: I2 ^level-1 L1-root)
  12658. --- END Input Phase ---
  12659. --- Proposal Phase ---
  12660. --- Inner Elaboration Phase, active level 1 (S1) ---
  12661. Firing elaborate*copy-see-to-output-link
  12662. -->
  12663. (I3 ^see 1 +)
  12664. Firing elaborate*reward*based*on*reward
  12665. -->
  12666. (R994 ^value 1 +)
  12667. (R1 ^reward R994 +)
  12668. Firing propose*predict-yes
  12669. -->
  12670. (O1981 ^name predict-yes +)
  12671. (S1 ^operator O1981 +)
  12672. Firing propose*predict-no
  12673. -->
  12674. (O1982 ^name predict-no +)
  12675. (S1 ^operator O1982 +)
  12676. Firing rl*prefer*rvt*predict-no*H0*4
  12677. -->
  12678. (S1 ^operator O1980 = 1.)
  12679. Firing rl*prefer*rvt*predict-yes*H0*3
  12680. -->
  12681. (S1 ^operator O1979 = 0.)
  12682. Firing prefer*rvt*predict-yes*H0
  12683. -->
  12684. Firing prefer*rvt*predict-no*H0
  12685. -->
  12686. Firing elaborate*copy-dir-to-output-link
  12687. -->
  12688. (I3 ^dir U +)
  12689. inner elaboration loop at bottom goal.
  12690. Retracting elaborate*copy-see-to-output-link
  12691. -->
  12692. (I3 ^see 0 +)
  12693. Retracting propose*predict-no
  12694. -->
  12695. (O1980 ^name predict-no +)
  12696. (S1 ^operator O1980 +)
  12697. Retracting propose*predict-yes
  12698. -->
  12699. (O1979 ^name predict-yes +)
  12700. (S1 ^operator O1979 +)
  12701. Retracting elaborate*reward*based*on*reward
  12702. -->
  12703. (R993 ^value 1 +)
  12704. (R1 ^reward R993 +)
  12705. Retracting elaborate*copy-dir-to-output-link
  12706. -->
  12707. (I3 ^dir R +)
  12708. Retracting rl*prefer*rvt*predict-no*H0*6
  12709. -->
  12710. (S1 ^operator O1980 = 0.9996961876736941)
  12711. Retracting rl*prefer*rvt*predict-yes*H0*5
  12712. -->
  12713. (S1 ^operator O1979 = 0.2239153301115165)
  12714. Retracting rl*prefer*rvt*predict-yes*H0*5*H1*9
  12715. -->
  12716. (S1 ^operator O1979 = 0.7761874802943043)
  12717. =>WM: (13890: S1 ^operator O1982 +)
  12718. =>WM: (13889: S1 ^operator O1981 +)
  12719. =>WM: (13888: I3 ^dir U)
  12720. =>WM: (13887: O1982 ^name predict-no)
  12721. =>WM: (13886: O1981 ^name predict-yes)
  12722. =>WM: (13885: R994 ^value 1)
  12723. =>WM: (13884: R1 ^reward R994)
  12724. =>WM: (13883: I3 ^see 1)
  12725. <=WM: (13874: S1 ^operator O1979 +)
  12726. <=WM: (13876: S1 ^operator O1979)
  12727. <=WM: (13875: S1 ^operator O1980 +)
  12728. <=WM: (13873: I3 ^dir R)
  12729. <=WM: (13869: R1 ^reward R993)
  12730. <=WM: (13868: I3 ^see 0)
  12731. <=WM: (13872: O1980 ^name predict-no)
  12732. <=WM: (13871: O1979 ^name predict-yes)
  12733. <=WM: (13870: R993 ^value 1)
  12734. --- Inner Elaboration Phase, active level 1 (S1) ---
  12735. Firing prefer*rvt*predict-yes*H0
  12736. -->
  12737. Firing rl*prefer*rvt*predict-yes*H0*3
  12738. -->
  12739. (S1 ^operator O1981 = 0.)
  12740. Firing prefer*rvt*predict-no*H0
  12741. -->
  12742. Firing rl*prefer*rvt*predict-no*H0*4
  12743. -->
  12744. (S1 ^operator O1982 = 1.)
  12745. inner elaboration loop at bottom goal.
  12746. Retracting rl*prefer*rvt*predict-no*H0*4
  12747. -->
  12748. (S1 ^operator O1980 = 1.)
  12749. Retracting rl*prefer*rvt*predict-yes*H0*3
  12750. -->
  12751. (S1 ^operator O1979 = 0.)
  12752. --- END Proposal Phase ---
  12753. --- Decision Phase ---
  12754. RL update rl*prefer*rvt*predict-yes*H0*5 0.553527 -0.329612 0.223915 -> 0.553519 -0.329612 0.223907(R,m,v=1,0.858065,0.122581)
  12755. RL update rl*prefer*rvt*predict-yes*H0*5*H1*9 0.446576 0.329612 0.776187 -> 0.446566 0.329612 0.776178(R,m,v=1,1,0)
  12756. =>WM: (13891: S1 ^operator O1982)
  12757. 991: O: O1982 (predict-no)
  12758. --- END Decision Phase ---
  12759. --- Application Phase ---
  12760. --- Firing Productions (PE) For State At Depth 1 ---
  12761. --- Inner Elaboration Phase, active level 1 (S1) ---
  12762. Firing apply*operator
  12763. -->
  12764. (I3 ^predict-no N991 + :O )
  12765. Firing apply*operator*complete
  12766. -->
  12767. (I3 ^predict-yes N990 - :O )
  12768. inner elaboration loop at bottom goal.
  12769. --- Change Working Memory (PE) ---
  12770. =>WM: (13892: I3 ^predict-no N991)
  12771. <=WM: (13878: N990 ^status complete)
  12772. <=WM: (13877: I3 ^predict-yes N990)
  12773. --- Firing Productions (IE) For State At Depth 1 ---
  12774. --- Inner Elaboration Phase, active level 1 (S1) ---
  12775. Firing monitor*world
  12776. -->
  12777. I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
  12778. --- Change Working Memory (IE) ---
  12779. --- END Application Phase ---
  12780. --- Output Phase ---
  12781. ENV: Agent did: predict-no for direction U in state State-B
  12782. In State-B moving U
  12783. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  12784. predict error 0
  12785. dir: dir isU
  12786. --- END Output Phase ---
  12787. |--- Input Phase ---
  12788. =>WM: (13896: I2 ^dir U)
  12789. =>WM: (13895: I2 ^reward 1)
  12790. =>WM: (13894: I2 ^see 0)
  12791. =>WM: (13893: N991 ^status complete)
  12792. <=WM: (13881: I2 ^dir U)
  12793. <=WM: (13880: I2 ^reward 1)
  12794. <=WM: (13879: I2 ^see 1)
  12795. =>WM: (13897: I2 ^level-1 R1-root)
  12796. <=WM: (13882: I2 ^level-1 R1-root)
  12797. --- END Input Phase ---
  12798. --- Proposal Phase ---
  12799. --- Inner Elaboration Phase, active level 1 (S1) ---
  12800. Firing elaborate*copy-see-to-output-link
  12801. -->
  12802. (I3 ^see 0 +)
  12803. Firing elaborate*reward*based*on*reward
  12804. -->
  12805. (R995 ^value 1 +)
  12806. (R1 ^reward R995 +)
  12807. Firing propose*predict-yes
  12808. -->
  12809. (O1983 ^name predict-yes +)
  12810. (S1 ^operator O1983 +)
  12811. Firing propose*predict-no
  12812. -->
  12813. (O1984 ^name predict-no +)
  12814. (S1 ^operator O1984 +)
  12815. Firing rl*prefer*rvt*predict-no*H0*4
  12816. -->
  12817. (S1 ^operator O1982 = 1.)
  12818. Firing rl*prefer*rvt*predict-yes*H0*3
  12819. -->
  12820. (S1 ^operator O1981 = 0.)
  12821. Firing prefer*rvt*predict-yes*H0
  12822. -->
  12823. Firing prefer*rvt*predict-no*H0
  12824. -->
  12825. Firing elaborate*copy-dir-to-output-link
  12826. -->
  12827. (I3 ^dir U +)
  12828. inner elaboration loop at bottom goal.
  12829. Retracting elaborate*copy-see-to-output-link
  12830. -->
  12831. (I3 ^see 1 +)
  12832. Retracting propose*predict-no
  12833. -->
  12834. (O1982 ^name predict-no +)
  12835. (S1 ^operator O1982 +)
  12836. Retracting propose*predict-yes
  12837. -->
  12838. (O1981 ^name predict-yes +)
  12839. (S1 ^operator O1981 +)
  12840. Retracting elaborate*reward*based*on*reward
  12841. -->
  12842. (R994 ^value 1 +)
  12843. (R1 ^reward R994 +)
  12844. Retracting elaborate*copy-dir-to-output-link
  12845. -->
  12846. (I3 ^dir U +)
  12847. Retracting rl*prefer*rvt*predict-no*H0*4
  12848. -->
  12849. (S1 ^operator O1982 = 1.)
  12850. Retracting rl*prefer*rvt*predict-yes*H0*3
  12851. -->
  12852. (S1 ^operator O1981 = 0.)
  12853. =>WM: (13904: S1 ^operator O1984 +)
  12854. =>WM: (13903: S1 ^operator O1983 +)
  12855. =>WM: (13902: O1984 ^name predict-no)
  12856. =>WM: (13901: O1983 ^name predict-yes)
  12857. =>WM: (13900: R995 ^value 1)
  12858. =>WM: (13899: R1 ^reward R995)
  12859. =>WM: (13898: I3 ^see 0)
  12860. <=WM: (13889: S1 ^operator O1981 +)
  12861. <=WM: (13890: S1 ^operator O1982 +)
  12862. <=WM: (13891: S1 ^operator O1982)
  12863. <=WM: (13884: R1 ^reward R994)
  12864. <=WM: (13883: I3 ^see 1)
  12865. <=WM: (13887: O1982 ^name predict-no)
  12866. <=WM: (13886: O1981 ^name predict-yes)
  12867. <=WM: (13885: R994 ^value 1)
  12868. --- Inner Elaboration Phase, active level 1 (S1) ---
  12869. Firing prefer*rvt*predict-yes*H0
  12870. -->
  12871. Firing rl*prefer*rvt*predict-yes*H0*3
  12872. -->
  12873. (S1 ^operator O1983 = 0.)
  12874. Firing prefer*rvt*predict-no*H0
  12875. -->
  12876. Firing rl*prefer*rvt*predict-no*H0*4
  12877. -->
  12878. (S1 ^operator O1984 = 1.)
  12879. inner elaboration loop at bottom goal.
  12880. Retracting rl*prefer*rvt*predict-no*H0*4
  12881. -->
  12882. (S1 ^operator O1982 = 1.)
  12883. Retracting rl*prefer*rvt*predict-yes*H0*3
  12884. -->
  12885. (S1 ^operator O1981 = 0.)
  12886. --- END Proposal Phase ---
  12887. --- Decision Phase ---
  12888. RL update rl*prefer*rvt*predict-no*H0*4 1 0 1 -> 1 0 1(R,m,v=1,1,0)
  12889. =>WM: (13905: S1 ^operator O1984)
  12890. 992: O: O1984 (predict-no)
  12891. --- END Decision Phase ---
  12892. --- Application Phase ---
  12893. --- Firing Productions (PE) For State At Depth 1 ---
  12894. --- Inner Elaboration Phase, active level 1 (S1) ---
  12895. Firing apply*operator
  12896. -->
  12897. (I3 ^predict-no N992 + :O )
  12898. Firing apply*operator*complete
  12899. -->
  12900. (I3 ^predict-no N991 - :O )
  12901. inner elaboration loop at bottom goal.
  12902. --- Change Working Memory (PE) ---
  12903. =>WM: (13906: I3 ^predict-no N992)
  12904. <=WM: (13893: N991 ^status complete)
  12905. <=WM: (13892: I3 ^predict-no N991)
  12906. --- Firing Productions (IE) For State At Depth 1 ---
  12907. --- Inner Elaboration Phase, active level 1 (S1) ---
  12908. Firing monitor*world
  12909. -->
  12910. I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
  12911. --- Change Working Memory (IE) ---
  12912. --- END Application Phase ---
  12913. --- Output Phase ---
  12914. ENV: Agent did: predict-no for direction U in state State-B
  12915. In State-B moving U
  12916. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  12917. predict error 0
  12918. dir: dir isL
  12919. --- END Output Phase ---
  12920. \---- Input Phase ---
  12921. =>WM: (13910: I2 ^dir L)
  12922. =>WM: (13909: I2 ^reward 1)
  12923. =>WM: (13908: I2 ^see 0)
  12924. =>WM: (13907: N992 ^status complete)
  12925. <=WM: (13896: I2 ^dir U)
  12926. <=WM: (13895: I2 ^reward 1)
  12927. <=WM: (13894: I2 ^see 0)
  12928. =>WM: (13911: I2 ^level-1 R1-root)
  12929. <=WM: (13897: I2 ^level-1 R1-root)
  12930. --- END Input Phase ---
  12931. --- Proposal Phase ---
  12932. --- Inner Elaboration Phase, active level 1 (S1) ---
  12933. Firing rl*prefer*rvt*predict-no*H0*2*H1*8
  12934. -->
  12935. (S1 ^operator O1984 = -0.1970449706966682)
  12936. Firing rl*prefer*rvt*predict-yes*H0*1*H1*7
  12937. -->
  12938. (S1 ^operator O1983 = 0.6500792769188249)
  12939. Firing prefer*rvt*predict-no*H0*2*H1
  12940. -->
  12941. Firing prefer*rvt*predict-yes*H0*1*H1
  12942. -->
  12943. Firing elaborate*copy-see-to-output-link
  12944. -->
  12945. (I3 ^see 0 +)
  12946. Firing elaborate*reward*based*on*reward
  12947. -->
  12948. (R996 ^value 1 +)
  12949. (R1 ^reward R996 +)
  12950. Firing propose*predict-yes
  12951. -->
  12952. (O1985 ^name predict-yes +)
  12953. (S1 ^operator O1985 +)
  12954. Firing propose*predict-no
  12955. -->
  12956. (O1986 ^name predict-no +)
  12957. (S1 ^operator O1986 +)
  12958. Firing rl*prefer*rvt*predict-no*H0*2
  12959. -->
  12960. (S1 ^operator O1984 = 0.2381416323002802)
  12961. Firing rl*prefer*rvt*predict-yes*H0*1
  12962. -->
  12963. (S1 ^operator O1983 = 0.3499208741033096)
  12964. Firing prefer*rvt*predict-yes*H0
  12965. -->
  12966. Firing prefer*rvt*predict-no*H0
  12967. -->
  12968. Firing elaborate*copy-dir-to-output-link
  12969. -->
  12970. (I3 ^dir L +)
  12971. inner elaboration loop at bottom goal.
  12972. Retracting elaborate*copy-see-to-output-link
  12973. -->
  12974. (I3 ^see 0 +)
  12975. Retracting propose*predict-no
  12976. -->
  12977. (O1984 ^name predict-no +)
  12978. (S1 ^operator O1984 +)
  12979. Retracting propose*predict-yes
  12980. -->
  12981. (O1983 ^name predict-yes +)
  12982. (S1 ^operator O1983 +)
  12983. Retracting elaborate*reward*based*on*reward
  12984. -->
  12985. (R995 ^value 1 +)
  12986. (R1 ^reward R995 +)
  12987. Retracting elaborate*copy-dir-to-output-link
  12988. -->
  12989. (I3 ^dir U +)
  12990. Retracting rl*prefer*rvt*predict-no*H0*4
  12991. -->
  12992. (S1 ^operator O1984 = 1.)
  12993. Retracting rl*prefer*rvt*predict-yes*H0*3
  12994. -->
  12995. (S1 ^operator O1983 = 0.)
  12996. =>WM: (13918: S1 ^operator O1986 +)
  12997. =>WM: (13917: S1 ^operator O1985 +)
  12998. =>WM: (13916: I3 ^dir L)
  12999. =>WM: (13915: O1986 ^name predict-no)
  13000. =>WM: (13914: O1985 ^name predict-yes)
  13001. =>WM: (13913: R996 ^value 1)
  13002. =>WM: (13912: R1 ^reward R996)
  13003. <=WM: (13903: S1 ^operator O1983 +)
  13004. <=WM: (13904: S1 ^operator O1984 +)
  13005. <=WM: (13905: S1 ^operator O1984)
  13006. <=WM: (13888: I3 ^dir U)
  13007. <=WM: (13899: R1 ^reward R995)
  13008. <=WM: (13902: O1984 ^name predict-no)
  13009. <=WM: (13901: O1983 ^name predict-yes)
  13010. <=WM: (13900: R995 ^value 1)
  13011. --- Inner Elaboration Phase, active level 1 (S1) ---
  13012. Firing prefer*rvt*predict-yes*H0
  13013. -->
  13014. Firing rl*prefer*rvt*predict-yes*H0*1*H1*7
  13015. -->
  13016. (S1 ^operator O1985 = 0.6500792769188249)
  13017. Firing rl*prefer*rvt*predict-yes*H0*1
  13018. -->
  13019. (S1 ^operator O1985 = 0.3499208741033096)
  13020. Firing prefer*rvt*predict-yes*H0*1*H1
  13021. -->
  13022. Firing prefer*rvt*predict-no*H0
  13023. -->
  13024. Firing rl*prefer*rvt*predict-no*H0*2*H1*8
  13025. -->
  13026. (S1 ^operator O1986 = -0.1970449706966682)
  13027. Firing rl*prefer*rvt*predict-no*H0*2
  13028. -->
  13029. (S1 ^operator O1986 = 0.2381416323002802)
  13030. Firing prefer*rvt*predict-no*H0*2*H1
  13031. -->
  13032. inner elaboration loop at bottom goal.
  13033. Retracting rl*prefer*rvt*predict-no*H0*2
  13034. -->
  13035. (S1 ^operator O1984 = 0.2381416323002802)
  13036. Retracting rl*prefer*rvt*predict-no*H0*2*H1*8
  13037. -->
  13038. (S1 ^operator O1984 = -0.1970449706966682)
  13039. Retracting rl*prefer*rvt*predict-yes*H0*1
  13040. -->
  13041. (S1 ^operator O1983 = 0.3499208741033096)
  13042. Retracting rl*prefer*rvt*predict-yes*H0*1*H1*7
  13043. -->
  13044. (S1 ^operator O1983 = 0.6500792769188249)
  13045. --- END Proposal Phase ---
  13046. --- Decision Phase ---
  13047. RL update rl*prefer*rvt*predict-no*H0*4 1 0 1 -> 1 0 1(R,m,v=1,1,0)
  13048. =>WM: (13919: S1 ^operator O1985)
  13049. 993: O: O1985 (predict-yes)
  13050. --- END Decision Phase ---
  13051. --- Application Phase ---
  13052. --- Firing Productions (PE) For State At Depth 1 ---
  13053. --- Inner Elaboration Phase, active level 1 (S1) ---
  13054. Firing apply*operator
  13055. -->
  13056. (I3 ^predict-yes N993 + :O )
  13057. Firing apply*operator*complete
  13058. -->
  13059. (I3 ^predict-no N992 - :O )
  13060. inner elaboration loop at bottom goal.
  13061. --- Change Working Memory (PE) ---
  13062. =>WM: (13920: I3 ^predict-yes N993)
  13063. <=WM: (13907: N992 ^status complete)
  13064. <=WM: (13906: I3 ^predict-no N992)
  13065. --- Firing Productions (IE) For State At Depth 1 ---
  13066. --- Inner Elaboration Phase, active level 1 (S1) ---
  13067. Firing monitor*world
  13068. -->
  13069. I see 1 and I'm going to do: predict-yes inner elaboration loop at bottom goal.
  13070. --- Change Working Memory (IE) ---
  13071. --- END Application Phase ---
  13072. --- Output Phase ---
  13073. ENV: Agent did: predict-yes for direction L in state State-B
  13074. In State-B moving L
  13075. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  13076. predict error 0
  13077. dir: dir isR
  13078. --- END Output Phase ---
  13079. /|--- Input Phase ---
  13080. =>WM: (13924: I2 ^dir R)
  13081. =>WM: (13923: I2 ^reward 1)
  13082. =>WM: (13922: I2 ^see 1)
  13083. =>WM: (13921: N993 ^status complete)
  13084. <=WM: (13910: I2 ^dir L)
  13085. <=WM: (13909: I2 ^reward 1)
  13086. <=WM: (13908: I2 ^see 0)
  13087. =>WM: (13925: I2 ^level-1 L1-root)
  13088. <=WM: (13911: I2 ^level-1 R1-root)
  13089. --- END Input Phase ---
  13090. --- Proposal Phase ---
  13091. --- Inner Elaboration Phase, active level 1 (S1) ---
  13092. Firing rl*prefer*rvt*predict-yes*H0*5*H1*9
  13093. -->
  13094. (S1 ^operator O1985 = 0.7761776035913615)
  13095. Firing prefer*rvt*predict-yes*H0*5*H1
  13096. -->
  13097. Firing elaborate*copy-see-to-output-link
  13098. -->
  13099. (I3 ^see 1 +)
  13100. Firing elaborate*reward*based*on*reward
  13101. -->
  13102. (R997 ^value 1 +)
  13103. (R1 ^reward R997 +)
  13104. Firing propose*predict-yes
  13105. -->
  13106. (O1987 ^name predict-yes +)
  13107. (S1 ^operator O1987 +)
  13108. Firing propose*predict-no
  13109. -->
  13110. (O1988 ^name predict-no +)
  13111. (S1 ^operator O1988 +)
  13112. Firing rl*prefer*rvt*predict-no*H0*6
  13113. -->
  13114. (S1 ^operator O1986 = 0.9996961876736941)
  13115. Firing rl*prefer*rvt*predict-yes*H0*5
  13116. -->
  13117. (S1 ^operator O1985 = 0.223906824139834)
  13118. Firing prefer*rvt*predict-yes*H0
  13119. -->
  13120. Firing prefer*rvt*predict-no*H0
  13121. -->
  13122. Firing elaborate*copy-dir-to-output-link
  13123. -->
  13124. (I3 ^dir R +)
  13125. inner elaboration loop at bottom goal.
  13126. Retracting elaborate*copy-see-to-output-link
  13127. -->
  13128. (I3 ^see 0 +)
  13129. Retracting propose*predict-no
  13130. -->
  13131. (O1986 ^name predict-no +)
  13132. (S1 ^operator O1986 +)
  13133. Retracting propose*predict-yes
  13134. -->
  13135. (O1985 ^name predict-yes +)
  13136. (S1 ^operator O1985 +)
  13137. Retracting elaborate*reward*based*on*reward
  13138. -->
  13139. (R996 ^value 1 +)
  13140. (R1 ^reward R996 +)
  13141. Retracting elaborate*copy-dir-to-output-link
  13142. -->
  13143. (I3 ^dir L +)
  13144. Retracting rl*prefer*rvt*predict-no*H0*2
  13145. -->
  13146. (S1 ^operator O1986 = 0.2381416323002802)
  13147. Retracting rl*prefer*rvt*predict-no*H0*2*H1*8
  13148. -->
  13149. (S1 ^operator O1986 = -0.1970449706966682)
  13150. Retracting rl*prefer*rvt*predict-yes*H0*1
  13151. -->
  13152. (S1 ^operator O1985 = 0.3499208741033096)
  13153. Retracting rl*prefer*rvt*predict-yes*H0*1*H1*7
  13154. -->
  13155. (S1 ^operator O1985 = 0.6500792769188249)
  13156. =>WM: (13933: S1 ^operator O1988 +)
  13157. =>WM: (13932: S1 ^operator O1987 +)
  13158. =>WM: (13931: I3 ^dir R)
  13159. =>WM: (13930: O1988 ^name predict-no)
  13160. =>WM: (13929: O1987 ^name predict-yes)
  13161. =>WM: (13928: R997 ^value 1)
  13162. =>WM: (13927: R1 ^reward R997)
  13163. =>WM: (13926: I3 ^see 1)
  13164. <=WM: (13917: S1 ^operator O1985 +)
  13165. <=WM: (13919: S1 ^operator O1985)
  13166. <=WM: (13918: S1 ^operator O1986 +)
  13167. <=WM: (13916: I3 ^dir L)
  13168. <=WM: (13912: R1 ^reward R996)
  13169. <=WM: (13898: I3 ^see 0)
  13170. <=WM: (13915: O1986 ^name predict-no)
  13171. <=WM: (13914: O1985 ^name predict-yes)
  13172. <=WM: (13913: R996 ^value 1)
  13173. --- Inner Elaboration Phase, active level 1 (S1) ---
  13174. Firing prefer*rvt*predict-yes*H0
  13175. -->
  13176. Firing rl*prefer*rvt*predict-yes*H0*5
  13177. -->
  13178. (S1 ^operator O1987 = 0.223906824139834)
  13179. Firing prefer*rvt*predict-yes*H0*5*H1
  13180. -->
  13181. Firing rl*prefer*rvt*predict-yes*H0*5*H1*9
  13182. -->
  13183. (S1 ^operator O1987 = 0.7761776035913615)
  13184. Firing prefer*rvt*predict-no*H0
  13185. -->
  13186. Firing rl*prefer*rvt*predict-no*H0*6
  13187. -->
  13188. (S1 ^operator O1988 = 0.9996961876736941)
  13189. inner elaboration loop at bottom goal.
  13190. Retracting rl*prefer*rvt*predict-no*H0*6
  13191. -->
  13192. (S1 ^operator O1986 = 0.9996961876736941)
  13193. Retracting rl*prefer*rvt*predict-yes*H0*5
  13194. -->
  13195. (S1 ^operator O1985 = 0.223906824139834)
  13196. Retracting rl*prefer*rvt*predict-yes*H0*5*H1*9
  13197. -->
  13198. (S1 ^operator O1985 = 0.7761776035913615)
  13199. --- END Proposal Phase ---
  13200. --- Decision Phase ---
  13201. RL update rl*prefer*rvt*predict-yes*H0*1 0.407928 -0.0580071 0.349921 -> 0.407928 -0.0580075 0.349921(R,m,v=1,0.901961,0.0890093)
  13202. RL update rl*prefer*rvt*predict-yes*H0*1*H1*7 0.592067 0.0580125 0.650079 -> 0.592067 0.058012 0.650079(R,m,v=1,1,0)
  13203. =>WM: (13934: S1 ^operator O1987)
  13204. 994: O: O1987 (predict-yes)
  13205. --- END Decision Phase ---
  13206. --- Application Phase ---
  13207. --- Firing Productions (PE) For State At Depth 1 ---
  13208. --- Inner Elaboration Phase, active level 1 (S1) ---
  13209. Firing apply*operator
  13210. -->
  13211. (I3 ^predict-yes N994 + :O )
  13212. Firing apply*operator*complete
  13213. -->
  13214. (I3 ^predict-yes N993 - :O )
  13215. inner elaboration loop at bottom goal.
  13216. --- Change Working Memory (PE) ---
  13217. =>WM: (13935: I3 ^predict-yes N994)
  13218. <=WM: (13921: N993 ^status complete)
  13219. <=WM: (13920: I3 ^predict-yes N993)
  13220. --- Firing Productions (IE) For State At Depth 1 ---
  13221. --- Inner Elaboration Phase, active level 1 (S1) ---
  13222. Firing monitor*world
  13223. -->
  13224. I see 1 and I'm going to do: predict-yes inner elaboration loop at bottom goal.
  13225. --- Change Working Memory (IE) ---
  13226. --- END Application Phase ---
  13227. --- Output Phase ---
  13228. ENV: Agent did: predict-yes for direction R in state State-A
  13229. In State-A moving R
  13230. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  13231. predict error 0
  13232. dir: dir isR
  13233. --- END Output Phase ---
  13234. \-/--- Input Phase ---
  13235. =>WM: (13939: I2 ^dir R)
  13236. =>WM: (13938: I2 ^reward 1)
  13237. =>WM: (13937: I2 ^see 1)
  13238. =>WM: (13936: N994 ^status complete)
  13239. <=WM: (13924: I2 ^dir R)
  13240. <=WM: (13923: I2 ^reward 1)
  13241. <=WM: (13922: I2 ^see 1)
  13242. =>WM: (13940: I2 ^level-1 R1-root)
  13243. <=WM: (13925: I2 ^level-1 L1-root)
  13244. --- END Input Phase ---
  13245. --- Proposal Phase ---
  13246. --- Inner Elaboration Phase, active level 1 (S1) ---
  13247. Firing rl*prefer*rvt*predict-yes*H0*5*H1*10
  13248. -->
  13249. (S1 ^operator O1987 = -0.2099933006338622)
  13250. Firing prefer*rvt*predict-yes*H0*5*H1
  13251. -->
  13252. Firing elaborate*copy-see-to-output-link
  13253. -->
  13254. (I3 ^see 1 +)
  13255. Firing elaborate*reward*based*on*reward
  13256. -->
  13257. (R998 ^value 1 +)
  13258. (R1 ^reward R998 +)
  13259. Firing propose*predict-yes
  13260. -->
  13261. (O1989 ^name predict-yes +)
  13262. (S1 ^operator O1989 +)
  13263. Firing propose*predict-no
  13264. -->
  13265. (O1990 ^name predict-no +)
  13266. (S1 ^operator O1990 +)
  13267. Firing rl*prefer*rvt*predict-no*H0*6
  13268. -->
  13269. (S1 ^operator O1988 = 0.9996961876736941)
  13270. Firing rl*prefer*rvt*predict-yes*H0*5
  13271. -->
  13272. (S1 ^operator O1987 = 0.223906824139834)
  13273. Firing prefer*rvt*predict-yes*H0
  13274. -->
  13275. Firing prefer*rvt*predict-no*H0
  13276. -->
  13277. Firing elaborate*copy-dir-to-output-link
  13278. -->
  13279. (I3 ^dir R +)
  13280. inner elaboration loop at bottom goal.
  13281. Retracting elaborate*copy-see-to-output-link
  13282. -->
  13283. (I3 ^see 1 +)
  13284. Retracting propose*predict-no
  13285. -->
  13286. (O1988 ^name predict-no +)
  13287. (S1 ^operator O1988 +)
  13288. Retracting propose*predict-yes
  13289. -->
  13290. (O1987 ^name predict-yes +)
  13291. (S1 ^operator O1987 +)
  13292. Retracting elaborate*reward*based*on*reward
  13293. -->
  13294. (R997 ^value 1 +)
  13295. (R1 ^reward R997 +)
  13296. Retracting elaborate*copy-dir-to-output-link
  13297. -->
  13298. (I3 ^dir R +)
  13299. Retracting rl*prefer*rvt*predict-no*H0*6
  13300. -->
  13301. (S1 ^operator O1988 = 0.9996961876736941)
  13302. Retracting rl*prefer*rvt*predict-yes*H0*5*H1*9
  13303. -->
  13304. (S1 ^operator O1987 = 0.7761776035913615)
  13305. Retracting rl*prefer*rvt*predict-yes*H0*5
  13306. -->
  13307. (S1 ^operator O1987 = 0.223906824139834)
  13308. =>WM: (13946: S1 ^operator O1990 +)
  13309. =>WM: (13945: S1 ^operator O1989 +)
  13310. =>WM: (13944: O1990 ^name predict-no)
  13311. =>WM: (13943: O1989 ^name predict-yes)
  13312. =>WM: (13942: R998 ^value 1)
  13313. =>WM: (13941: R1 ^reward R998)
  13314. <=WM: (13932: S1 ^operator O1987 +)
  13315. <=WM: (13934: S1 ^operator O1987)
  13316. <=WM: (13933: S1 ^operator O1988 +)
  13317. <=WM: (13927: R1 ^reward R997)
  13318. <=WM: (13930: O1988 ^name predict-no)
  13319. <=WM: (13929: O1987 ^name predict-yes)
  13320. <=WM: (13928: R997 ^value 1)
  13321. --- Inner Elaboration Phase, active level 1 (S1) ---
  13322. Firing prefer*rvt*predict-yes*H0
  13323. -->
  13324. Firing rl*prefer*rvt*predict-yes*H0*5
  13325. -->
  13326. (S1 ^operator O1989 = 0.223906824139834)
  13327. Firing prefer*rvt*predict-yes*H0*5*H1
  13328. -->
  13329. Firing rl*prefer*rvt*predict-yes*H0*5*H1*10
  13330. -->
  13331. (S1 ^operator O1989 = -0.2099933006338622)
  13332. Firing prefer*rvt*predict-no*H0
  13333. -->
  13334. Firing rl*prefer*rvt*predict-no*H0*6
  13335. -->
  13336. (S1 ^operator O1990 = 0.9996961876736941)
  13337. inner elaboration loop at bottom goal.
  13338. Retracting rl*prefer*rvt*predict-no*H0*6
  13339. -->
  13340. (S1 ^operator O1988 = 0.9996961876736941)
  13341. Retracting rl*prefer*rvt*predict-yes*H0*5
  13342. -->
  13343. (S1 ^operator O1987 = 0.223906824139834)
  13344. Retracting rl*prefer*rvt*predict-yes*H0*5*H1*10
  13345. -->
  13346. (S1 ^operator O1987 = -0.2099933006338622)
  13347. --- END Proposal Phase ---
  13348. --- Decision Phase ---
  13349. RL update rl*prefer*rvt*predict-yes*H0*5 0.553519 -0.329612 0.223907 -> 0.553512 -0.329612 0.2239(R,m,v=1,0.858974,0.121919)
  13350. RL update rl*prefer*rvt*predict-yes*H0*5*H1*9 0.446566 0.329612 0.776178 -> 0.446558 0.329612 0.77617(R,m,v=1,1,0)
  13351. =>WM: (13947: S1 ^operator O1990)
  13352. 995: O: O1990 (predict-no)
  13353. --- END Decision Phase ---
  13354. --- Application Phase ---
  13355. --- Firing Productions (PE) For State At Depth 1 ---
  13356. --- Inner Elaboration Phase, active level 1 (S1) ---
  13357. Firing apply*operator
  13358. -->
  13359. (I3 ^predict-no N995 + :O )
  13360. Firing apply*operator*complete
  13361. -->
  13362. (I3 ^predict-yes N994 - :O )
  13363. inner elaboration loop at bottom goal.
  13364. --- Change Working Memory (PE) ---
  13365. =>WM: (13948: I3 ^predict-no N995)
  13366. <=WM: (13936: N994 ^status complete)
  13367. <=WM: (13935: I3 ^predict-yes N994)
  13368. --- Firing Productions (IE) For State At Depth 1 ---
  13369. --- Inner Elaboration Phase, active level 1 (S1) ---
  13370. Firing monitor*world
  13371. -->
  13372. I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
  13373. --- Change Working Memory (IE) ---
  13374. --- END Application Phase ---
  13375. --- Output Phase ---
  13376. ENV: Agent did: predict-no for direction R in state State-B
  13377. In State-B moving R
  13378. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  13379. predict error 0
  13380. dir: dir isU
  13381. --- END Output Phase ---
  13382. |\--- Input Phase ---
  13383. =>WM: (13952: I2 ^dir U)
  13384. =>WM: (13951: I2 ^reward 1)
  13385. =>WM: (13950: I2 ^see 0)
  13386. =>WM: (13949: N995 ^status complete)
  13387. <=WM: (13939: I2 ^dir R)
  13388. <=WM: (13938: I2 ^reward 1)
  13389. <=WM: (13937: I2 ^see 1)
  13390. =>WM: (13953: I2 ^level-1 R0-root)
  13391. <=WM: (13940: I2 ^level-1 R1-root)
  13392. --- END Input Phase ---
  13393. --- Proposal Phase ---
  13394. --- Inner Elaboration Phase, active level 1 (S1) ---
  13395. Firing elaborate*copy-see-to-output-link
  13396. -->
  13397. (I3 ^see 0 +)
  13398. Firing elaborate*reward*based*on*reward
  13399. -->
  13400. (R999 ^value 1 +)
  13401. (R1 ^reward R999 +)
  13402. Firing propose*predict-yes
  13403. -->
  13404. (O1991 ^name predict-yes +)
  13405. (S1 ^operator O1991 +)
  13406. Firing propose*predict-no
  13407. -->
  13408. (O1992 ^name predict-no +)
  13409. (S1 ^operator O1992 +)
  13410. Firing rl*prefer*rvt*predict-no*H0*4
  13411. -->
  13412. (S1 ^operator O1990 = 1.)
  13413. Firing rl*prefer*rvt*predict-yes*H0*3
  13414. -->
  13415. (S1 ^operator O1989 = 0.)
  13416. Firing prefer*rvt*predict-yes*H0
  13417. -->
  13418. Firing prefer*rvt*predict-no*H0
  13419. -->
  13420. Firing elaborate*copy-dir-to-output-link
  13421. -->
  13422. (I3 ^dir U +)
  13423. inner elaboration loop at bottom goal.
  13424. Retracting elaborate*copy-see-to-output-link
  13425. -->
  13426. (I3 ^see 1 +)
  13427. Retracting propose*predict-no
  13428. -->
  13429. (O1990 ^name predict-no +)
  13430. (S1 ^operator O1990 +)
  13431. Retracting propose*predict-yes
  13432. -->
  13433. (O1989 ^name predict-yes +)
  13434. (S1 ^operator O1989 +)
  13435. Retracting elaborate*reward*based*on*reward
  13436. -->
  13437. (R998 ^value 1 +)
  13438. (R1 ^reward R998 +)
  13439. Retracting elaborate*copy-dir-to-output-link
  13440. -->
  13441. (I3 ^dir R +)
  13442. Retracting rl*prefer*rvt*predict-no*H0*6
  13443. -->
  13444. (S1 ^operator O1990 = 0.9996961876736941)
  13445. Retracting rl*prefer*rvt*predict-yes*H0*5*H1*10
  13446. -->
  13447. (S1 ^operator O1989 = -0.2099933006338622)
  13448. Retracting rl*prefer*rvt*predict-yes*H0*5
  13449. -->
  13450. (S1 ^operator O1989 = 0.2238998464753165)
  13451. =>WM: (13961: S1 ^operator O1992 +)
  13452. =>WM: (13960: S1 ^operator O1991 +)
  13453. =>WM: (13959: I3 ^dir U)
  13454. =>WM: (13958: O1992 ^name predict-no)
  13455. =>WM: (13957: O1991 ^name predict-yes)
  13456. =>WM: (13956: R999 ^value 1)
  13457. =>WM: (13955: R1 ^reward R999)
  13458. =>WM: (13954: I3 ^see 0)
  13459. <=WM: (13945: S1 ^operator O1989 +)
  13460. <=WM: (13946: S1 ^operator O1990 +)
  13461. <=WM: (13947: S1 ^operator O1990)
  13462. <=WM: (13931: I3 ^dir R)
  13463. <=WM: (13941: R1 ^reward R998)
  13464. <=WM: (13926: I3 ^see 1)
  13465. <=WM: (13944: O1990 ^name predict-no)
  13466. <=WM: (13943: O1989 ^name predict-yes)
  13467. <=WM: (13942: R998 ^value 1)
  13468. --- Inner Elaboration Phase, active level 1 (S1) ---
  13469. Firing prefer*rvt*predict-yes*H0
  13470. -->
  13471. Firing rl*prefer*rvt*predict-yes*H0*3
  13472. -->
  13473. (S1 ^operator O1991 = 0.)
  13474. Firing prefer*rvt*predict-no*H0
  13475. -->
  13476. Firing rl*prefer*rvt*predict-no*H0*4
  13477. -->
  13478. (S1 ^operator O1992 = 1.)
  13479. inner elaboration loop at bottom goal.
  13480. Retracting rl*prefer*rvt*predict-no*H0*4
  13481. -->
  13482. (S1 ^operator O1990 = 1.)
  13483. Retracting rl*prefer*rvt*predict-yes*H0*3
  13484. -->
  13485. (S1 ^operator O1989 = 0.)
  13486. --- END Proposal Phase ---
  13487. --- Decision Phase ---
  13488. RL update rl*prefer*rvt*predict-no*H0*6 0.999696 0 0.999696 -> 0.999746 0 0.999746(R,m,v=1,0.862069,0.119593)
  13489. =>WM: (13962: S1 ^operator O1992)
  13490. 996: O: O1992 (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 N996 + :O )
  13498. Firing apply*operator*complete
  13499. -->
  13500. (I3 ^predict-no N995 - :O )
  13501. inner elaboration loop at bottom goal.
  13502. --- Change Working Memory (PE) ---
  13503. =>WM: (13963: I3 ^predict-no N996)
  13504. <=WM: (13949: N995 ^status complete)
  13505. <=WM: (13948: I3 ^predict-no N995)
  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: (13967: I2 ^dir U)
  13522. =>WM: (13966: I2 ^reward 1)
  13523. =>WM: (13965: I2 ^see 0)
  13524. =>WM: (13964: N996 ^status complete)
  13525. <=WM: (13952: I2 ^dir U)
  13526. <=WM: (13951: I2 ^reward 1)
  13527. <=WM: (13950: I2 ^see 0)
  13528. =>WM: (13968: I2 ^level-1 R0-root)
  13529. <=WM: (13953: I2 ^level-1 R0-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. (R1000 ^value 1 +)
  13539. (R1 ^reward R1000 +)
  13540. Firing propose*predict-yes
  13541. -->
  13542. (O1993 ^name predict-yes +)
  13543. (S1 ^operator O1993 +)
  13544. Firing propose*predict-no
  13545. -->
  13546. (O1994 ^name predict-no +)
  13547. (S1 ^operator O1994 +)
  13548. Firing rl*prefer*rvt*predict-no*H0*4
  13549. -->
  13550. (S1 ^operator O1992 = 1.)
  13551. Firing rl*prefer*rvt*predict-yes*H0*3
  13552. -->
  13553. (S1 ^operator O1991 = 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 0 +)
  13565. Retracting propose*predict-no
  13566. -->
  13567. (O1992 ^name predict-no +)
  13568. (S1 ^operator O1992 +)
  13569. Retracting propose*predict-yes
  13570. -->
  13571. (O1991 ^name predict-yes +)
  13572. (S1 ^operator O1991 +)
  13573. Retracting elaborate*reward*based*on*reward
  13574. -->
  13575. (R999 ^value 1 +)
  13576. (R1 ^reward R999 +)
  13577. Retracting elaborate*copy-dir-to-output-link
  13578. -->
  13579. (I3 ^dir U +)
  13580. Retracting rl*prefer*rvt*predict-no*H0*4
  13581. -->
  13582. (S1 ^operator O1992 = 1.)
  13583. Retracting rl*prefer*rvt*predict-yes*H0*3
  13584. -->
  13585. (S1 ^operator O1991 = 0.)
  13586. =>WM: (13974: S1 ^operator O1994 +)
  13587. =>WM: (13973: S1 ^operator O1993 +)
  13588. =>WM: (13972: O1994 ^name predict-no)
  13589. =>WM: (13971: O1993 ^name predict-yes)
  13590. =>WM: (13970: R1000 ^value 1)
  13591. =>WM: (13969: R1 ^reward R1000)
  13592. <=WM: (13960: S1 ^operator O1991 +)
  13593. <=WM: (13961: S1 ^operator O1992 +)
  13594. <=WM: (13962: S1 ^operator O1992)
  13595. <=WM: (13955: R1 ^reward R999)
  13596. <=WM: (13958: O1992 ^name predict-no)
  13597. <=WM: (13957: O1991 ^name predict-yes)
  13598. <=WM: (13956: R999 ^value 1)
  13599. --- Inner Elaboration Phase, active level 1 (S1) ---
  13600. Firing prefer*rvt*predict-yes*H0
  13601. -->
  13602. Firing rl*prefer*rvt*predict-yes*H0*3
  13603. -->
  13604. (S1 ^operator O1993 = 0.)
  13605. Firing prefer*rvt*predict-no*H0
  13606. -->
  13607. Firing rl*prefer*rvt*predict-no*H0*4
  13608. -->
  13609. (S1 ^operator O1994 = 1.)
  13610. inner elaboration loop at bottom goal.
  13611. Retracting rl*prefer*rvt*predict-no*H0*4
  13612. -->
  13613. (S1 ^operator O1992 = 1.)
  13614. Retracting rl*prefer*rvt*predict-yes*H0*3
  13615. -->
  13616. (S1 ^operator O1991 = 0.)
  13617. --- END Proposal Phase ---
  13618. --- Decision Phase ---
  13619. RL update rl*prefer*rvt*predict-no*H0*4 1 0 1 -> 1 0 1(R,m,v=1,1,0)
  13620. =>WM: (13975: S1 ^operator O1994)
  13621. 997: O: O1994 (predict-no)
  13622. --- END Decision Phase ---
  13623. --- Application Phase ---
  13624. --- Firing Productions (PE) For State At Depth 1 ---
  13625. --- Inner Elaboration Phase, active level 1 (S1) ---
  13626. Firing apply*operator
  13627. -->
  13628. (I3 ^predict-no N997 + :O )
  13629. Firing apply*operator*complete
  13630. -->
  13631. (I3 ^predict-no N996 - :O )
  13632. inner elaboration loop at bottom goal.
  13633. --- Change Working Memory (PE) ---
  13634. =>WM: (13976: I3 ^predict-no N997)
  13635. <=WM: (13964: N996 ^status complete)
  13636. <=WM: (13963: I3 ^predict-no N996)
  13637. --- Firing Productions (IE) For State At Depth 1 ---
  13638. --- Inner Elaboration Phase, active level 1 (S1) ---
  13639. Firing monitor*world
  13640. -->
  13641. I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
  13642. --- Change Working Memory (IE) ---
  13643. --- END Application Phase ---
  13644. --- Output Phase ---
  13645. ENV: Agent did: predict-no for direction U in state State-B
  13646. In State-B moving U
  13647. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  13648. predict error 0
  13649. dir: dir isL
  13650. --- END Output Phase ---
  13651. |--- Input Phase ---
  13652. =>WM: (13980: I2 ^dir L)
  13653. =>WM: (13979: I2 ^reward 1)
  13654. =>WM: (13978: I2 ^see 0)
  13655. =>WM: (13977: N997 ^status complete)
  13656. <=WM: (13967: I2 ^dir U)
  13657. <=WM: (13966: I2 ^reward 1)
  13658. <=WM: (13965: I2 ^see 0)
  13659. =>WM: (13981: I2 ^level-1 R0-root)
  13660. <=WM: (13968: I2 ^level-1 R0-root)
  13661. --- END Input Phase ---
  13662. --- Proposal Phase ---
  13663. --- Inner Elaboration Phase, active level 1 (S1) ---
  13664. Firing rl*prefer*rvt*predict-no*H0*2*H1*12
  13665. -->
  13666. (S1 ^operator O1994 = -0.1359494083332169)
  13667. Firing rl*prefer*rvt*predict-yes*H0*1*H1*13
  13668. -->
  13669. (S1 ^operator O1993 = 0.6500789835658556)
  13670. Firing prefer*rvt*predict-no*H0*2*H1
  13671. -->
  13672. Firing prefer*rvt*predict-yes*H0*1*H1
  13673. -->
  13674. Firing elaborate*copy-see-to-output-link
  13675. -->
  13676. (I3 ^see 0 +)
  13677. Firing elaborate*reward*based*on*reward
  13678. -->
  13679. (R1001 ^value 1 +)
  13680. (R1 ^reward R1001 +)
  13681. Firing propose*predict-yes
  13682. -->
  13683. (O1995 ^name predict-yes +)
  13684. (S1 ^operator O1995 +)
  13685. Firing propose*predict-no
  13686. -->
  13687. (O1996 ^name predict-no +)
  13688. (S1 ^operator O1996 +)
  13689. Firing rl*prefer*rvt*predict-no*H0*2
  13690. -->
  13691. (S1 ^operator O1994 = 0.2381416323002802)
  13692. Firing rl*prefer*rvt*predict-yes*H0*1
  13693. -->
  13694. (S1 ^operator O1993 = 0.349920861581654)
  13695. Firing prefer*rvt*predict-yes*H0
  13696. -->
  13697. Firing prefer*rvt*predict-no*H0
  13698. -->
  13699. Firing elaborate*copy-dir-to-output-link
  13700. -->
  13701. (I3 ^dir L +)
  13702. inner elaboration loop at bottom goal.
  13703. Retracting elaborate*copy-see-to-output-link
  13704. -->
  13705. (I3 ^see 0 +)
  13706. Retracting propose*predict-no
  13707. -->
  13708. (O1994 ^name predict-no +)
  13709. (S1 ^operator O1994 +)
  13710. Retracting propose*predict-yes
  13711. -->
  13712. (O1993 ^name predict-yes +)
  13713. (S1 ^operator O1993 +)
  13714. Retracting elaborate*reward*based*on*reward
  13715. -->
  13716. (R1000 ^value 1 +)
  13717. (R1 ^reward R1000 +)
  13718. Retracting elaborate*copy-dir-to-output-link
  13719. -->
  13720. (I3 ^dir U +)
  13721. Retracting rl*prefer*rvt*predict-no*H0*4
  13722. -->
  13723. (S1 ^operator O1994 = 1.)
  13724. Retracting rl*prefer*rvt*predict-yes*H0*3
  13725. -->
  13726. (S1 ^operator O1993 = 0.)
  13727. =>WM: (13988: S1 ^operator O1996 +)
  13728. =>WM: (13987: S1 ^operator O1995 +)
  13729. =>WM: (13986: I3 ^dir L)
  13730. =>WM: (13985: O1996 ^name predict-no)
  13731. =>WM: (13984: O1995 ^name predict-yes)
  13732. =>WM: (13983: R1001 ^value 1)
  13733. =>WM: (13982: R1 ^reward R1001)
  13734. <=WM: (13973: S1 ^operator O1993 +)
  13735. <=WM: (13974: S1 ^operator O1994 +)
  13736. <=WM: (13975: S1 ^operator O1994)
  13737. <=WM: (13959: I3 ^dir U)
  13738. <=WM: (13969: R1 ^reward R1000)
  13739. <=WM: (13972: O1994 ^name predict-no)
  13740. <=WM: (13971: O1993 ^name predict-yes)
  13741. <=WM: (13970: R1000 ^value 1)
  13742. --- Inner Elaboration Phase, active level 1 (S1) ---
  13743. Firing prefer*rvt*predict-yes*H0
  13744. -->
  13745. Firing rl*prefer*rvt*predict-yes*H0*1*H1*13
  13746. -->
  13747. (S1 ^operator O1995 = 0.6500789835658556)
  13748. Firing rl*prefer*rvt*predict-yes*H0*1
  13749. -->
  13750. (S1 ^operator O1995 = 0.349920861581654)
  13751. Firing prefer*rvt*predict-yes*H0*1*H1
  13752. -->
  13753. Firing prefer*rvt*predict-no*H0
  13754. -->
  13755. Firing rl*prefer*rvt*predict-no*H0*2*H1*12
  13756. -->
  13757. (S1 ^operator O1996 = -0.1359494083332169)
  13758. Firing rl*prefer*rvt*predict-no*H0*2
  13759. -->
  13760. (S1 ^operator O1996 = 0.2381416323002802)
  13761. Firing prefer*rvt*predict-no*H0*2*H1
  13762. -->
  13763. inner elaboration loop at bottom goal.
  13764. Retracting rl*prefer*rvt*predict-no*H0*2
  13765. -->
  13766. (S1 ^operator O1994 = 0.2381416323002802)
  13767. Retracting rl*prefer*rvt*predict-no*H0*2*H1*12
  13768. -->
  13769. (S1 ^operator O1994 = -0.1359494083332169)
  13770. Retracting rl*prefer*rvt*predict-yes*H0*1
  13771. -->
  13772. (S1 ^operator O1993 = 0.349920861581654)
  13773. Retracting rl*prefer*rvt*predict-yes*H0*1*H1*13
  13774. -->
  13775. (S1 ^operator O1993 = 0.6500789835658556)
  13776. --- END Proposal Phase ---
  13777. --- Decision Phase ---
  13778. RL update rl*prefer*rvt*predict-no*H0*4 1 0 1 -> 1 0 1(R,m,v=1,1,0)
  13779. =>WM: (13989: S1 ^operator O1995)
  13780. 998: O: O1995 (predict-yes)
  13781. --- END Decision Phase ---
  13782. --- Application Phase ---
  13783. --- Firing Productions (PE) For State At Depth 1 ---
  13784. --- Inner Elaboration Phase, active level 1 (S1) ---
  13785. Firing apply*operator
  13786. -->
  13787. (I3 ^predict-yes N998 + :O )
  13788. Firing apply*operator*complete
  13789. -->
  13790. (I3 ^predict-no N997 - :O )
  13791. inner elaboration loop at bottom goal.
  13792. --- Change Working Memory (PE) ---
  13793. =>WM: (13990: I3 ^predict-yes N998)
  13794. <=WM: (13977: N997 ^status complete)
  13795. <=WM: (13976: I3 ^predict-no N997)
  13796. --- Firing Productions (IE) For State At Depth 1 ---
  13797. --- Inner Elaboration Phase, active level 1 (S1) ---
  13798. Firing monitor*world
  13799. -->
  13800. I see 1 and I'm going to do: predict-yes inner elaboration loop at bottom goal.
  13801. --- Change Working Memory (IE) ---
  13802. --- END Application Phase ---
  13803. --- Output Phase ---
  13804. ENV: Agent did: predict-yes for direction L in state State-B
  13805. In State-B moving L
  13806. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  13807. predict error 0
  13808. dir: dir isL
  13809. --- END Output Phase ---
  13810. \-/--- Input Phase ---
  13811. =>WM: (13994: I2 ^dir L)
  13812. =>WM: (13993: I2 ^reward 1)
  13813. =>WM: (13992: I2 ^see 1)
  13814. =>WM: (13991: N998 ^status complete)
  13815. <=WM: (13980: I2 ^dir L)
  13816. <=WM: (13979: I2 ^reward 1)
  13817. <=WM: (13978: I2 ^see 0)
  13818. =>WM: (13995: I2 ^level-1 L1-root)
  13819. <=WM: (13981: I2 ^level-1 R0-root)
  13820. --- END Input Phase ---
  13821. --- Proposal Phase ---
  13822. --- Inner Elaboration Phase, active level 1 (S1) ---
  13823. Firing rl*prefer*rvt*predict-no*H0*2*H1*14
  13824. -->
  13825. (S1 ^operator O1996 = 0.7618942170579377)
  13826. Firing rl*prefer*rvt*predict-yes*H0*1*H1*15
  13827. -->
  13828. (S1 ^operator O1995 = -0.2915346922215271)
  13829. Firing prefer*rvt*predict-no*H0*2*H1
  13830. -->
  13831. Firing prefer*rvt*predict-yes*H0*1*H1
  13832. -->
  13833. Firing elaborate*copy-see-to-output-link
  13834. -->
  13835. (I3 ^see 1 +)
  13836. Firing elaborate*reward*based*on*reward
  13837. -->
  13838. (R1002 ^value 1 +)
  13839. (R1 ^reward R1002 +)
  13840. Firing propose*predict-yes
  13841. -->
  13842. (O1997 ^name predict-yes +)
  13843. (S1 ^operator O1997 +)
  13844. Firing propose*predict-no
  13845. -->
  13846. (O1998 ^name predict-no +)
  13847. (S1 ^operator O1998 +)
  13848. Firing rl*prefer*rvt*predict-no*H0*2
  13849. -->
  13850. (S1 ^operator O1996 = 0.2381416323002802)
  13851. Firing rl*prefer*rvt*predict-yes*H0*1
  13852. -->
  13853. (S1 ^operator O1995 = 0.349920861581654)
  13854. Firing prefer*rvt*predict-yes*H0
  13855. -->
  13856. Firing prefer*rvt*predict-no*H0
  13857. -->
  13858. Firing elaborate*copy-dir-to-output-link
  13859. -->
  13860. (I3 ^dir L +)
  13861. inner elaboration loop at bottom goal.
  13862. Retracting elaborate*copy-see-to-output-link
  13863. -->
  13864. (I3 ^see 0 +)
  13865. Retracting propose*predict-no
  13866. -->
  13867. (O1996 ^name predict-no +)
  13868. (S1 ^operator O1996 +)
  13869. Retracting propose*predict-yes
  13870. -->
  13871. (O1995 ^name predict-yes +)
  13872. (S1 ^operator O1995 +)
  13873. Retracting elaborate*reward*based*on*reward
  13874. -->
  13875. (R1001 ^value 1 +)
  13876. (R1 ^reward R1001 +)
  13877. Retracting elaborate*copy-dir-to-output-link
  13878. -->
  13879. (I3 ^dir L +)
  13880. Retracting rl*prefer*rvt*predict-no*H0*2
  13881. -->
  13882. (S1 ^operator O1996 = 0.2381416323002802)
  13883. Retracting rl*prefer*rvt*predict-no*H0*2*H1*12
  13884. -->
  13885. (S1 ^operator O1996 = -0.1359494083332169)
  13886. Retracting rl*prefer*rvt*predict-yes*H0*1
  13887. -->
  13888. (S1 ^operator O1995 = 0.349920861581654)
  13889. Retracting rl*prefer*rvt*predict-yes*H0*1*H1*13
  13890. -->
  13891. (S1 ^operator O1995 = 0.6500789835658556)
  13892. =>WM: (14002: S1 ^operator O1998 +)
  13893. =>WM: (14001: S1 ^operator O1997 +)
  13894. =>WM: (14000: O1998 ^name predict-no)
  13895. =>WM: (13999: O1997 ^name predict-yes)
  13896. =>WM: (13998: R1002 ^value 1)
  13897. =>WM: (13997: R1 ^reward R1002)
  13898. =>WM: (13996: I3 ^see 1)
  13899. <=WM: (13987: S1 ^operator O1995 +)
  13900. <=WM: (13989: S1 ^operator O1995)
  13901. <=WM: (13988: S1 ^operator O1996 +)
  13902. <=WM: (13982: R1 ^reward R1001)
  13903. <=WM: (13954: I3 ^see 0)
  13904. <=WM: (13985: O1996 ^name predict-no)
  13905. <=WM: (13984: O1995 ^name predict-yes)
  13906. <=WM: (13983: R1001 ^value 1)
  13907. --- Inner Elaboration Phase, active level 1 (S1) ---
  13908. Firing prefer*rvt*predict-yes*H0
  13909. -->
  13910. Firing rl*prefer*rvt*predict-yes*H0*1
  13911. -->
  13912. (S1 ^operator O1997 = 0.349920861581654)
  13913. Firing prefer*rvt*predict-yes*H0*1*H1
  13914. -->
  13915. Firing rl*prefer*rvt*predict-yes*H0*1*H1*15
  13916. -->
  13917. (S1 ^operator O1997 = -0.2915346922215271)
  13918. Firing prefer*rvt*predict-no*H0
  13919. -->
  13920. Firing rl*prefer*rvt*predict-no*H0*2
  13921. -->
  13922. (S1 ^operator O1998 = 0.2381416323002802)
  13923. Firing prefer*rvt*predict-no*H0*2*H1
  13924. -->
  13925. Firing rl*prefer*rvt*predict-no*H0*2*H1*14
  13926. -->
  13927. (S1 ^operator O1998 = 0.7618942170579377)
  13928. inner elaboration loop at bottom goal.
  13929. Retracting rl*prefer*rvt*predict-no*H0*2
  13930. -->
  13931. (S1 ^operator O1996 = 0.2381416323002802)
  13932. Retracting rl*prefer*rvt*predict-no*H0*2*H1*14
  13933. -->
  13934. (S1 ^operator O1996 = 0.7618942170579377)
  13935. Retracting rl*prefer*rvt*predict-yes*H0*1
  13936. -->
  13937. (S1 ^operator O1995 = 0.349920861581654)
  13938. Retracting rl*prefer*rvt*predict-yes*H0*1*H1*15
  13939. -->
  13940. (S1 ^operator O1995 = -0.2915346922215271)
  13941. --- END Proposal Phase ---
  13942. --- Decision Phase ---
  13943. RL update rl*prefer*rvt*predict-yes*H0*1 0.407928 -0.0580075 0.349921 -> 0.407928 -0.0580072 0.349921(R,m,v=1,0.902597,0.0884899)
  13944. RL update rl*prefer*rvt*predict-yes*H0*1*H1*13 0.592075 0.0580043 0.650079 -> 0.592074 0.0580046 0.650079(R,m,v=1,1,0)
  13945. =>WM: (14003: S1 ^operator O1998)
  13946. 999: O: O1998 (predict-no)
  13947. --- END Decision Phase ---
  13948. --- Application Phase ---
  13949. --- Firing Productions (PE) For State At Depth 1 ---
  13950. --- Inner Elaboration Phase, active level 1 (S1) ---
  13951. Firing apply*operator
  13952. -->
  13953. (I3 ^predict-no N999 + :O )
  13954. Firing apply*operator*complete
  13955. -->
  13956. (I3 ^predict-yes N998 - :O )
  13957. inner elaboration loop at bottom goal.
  13958. --- Change Working Memory (PE) ---
  13959. =>WM: (14004: I3 ^predict-no N999)
  13960. <=WM: (13991: N998 ^status complete)
  13961. <=WM: (13990: I3 ^predict-yes N998)
  13962. --- Firing Productions (IE) For State At Depth 1 ---
  13963. --- Inner Elaboration Phase, active level 1 (S1) ---
  13964. Firing monitor*world
  13965. -->
  13966. I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
  13967. --- Change Working Memory (IE) ---
  13968. --- END Application Phase ---
  13969. --- Output Phase ---
  13970. ENV: Agent did: predict-no for direction L in state State-A
  13971. In State-A moving L
  13972. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  13973. predict error 0
  13974. dir: dir isU
  13975. --- END Output Phase ---
  13976. |\--- Input Phase ---
  13977. =>WM: (14008: I2 ^dir U)
  13978. =>WM: (14007: I2 ^reward 1)
  13979. =>WM: (14006: I2 ^see 0)
  13980. =>WM: (14005: N999 ^status complete)
  13981. <=WM: (13994: I2 ^dir L)
  13982. <=WM: (13993: I2 ^reward 1)
  13983. <=WM: (13992: I2 ^see 1)
  13984. =>WM: (14009: I2 ^level-1 L0-root)
  13985. <=WM: (13995: I2 ^level-1 L1-root)
  13986. --- END Input Phase ---
  13987. --- Proposal Phase ---
  13988. --- Inner Elaboration Phase, active level 1 (S1) ---
  13989. Firing elaborate*copy-see-to-output-link
  13990. -->
  13991. (I3 ^see 0 +)
  13992. Firing elaborate*reward*based*on*reward
  13993. -->
  13994. (R1003 ^value 1 +)
  13995. (R1 ^reward R1003 +)
  13996. Firing propose*predict-yes
  13997. -->
  13998. (O1999 ^name predict-yes +)
  13999. (S1 ^operator O1999 +)
  14000. Firing propose*predict-no
  14001. -->
  14002. (O2000 ^name predict-no +)
  14003. (S1 ^operator O2000 +)
  14004. Firing rl*prefer*rvt*predict-no*H0*4
  14005. -->
  14006. (S1 ^operator O1998 = 1.)
  14007. Firing rl*prefer*rvt*predict-yes*H0*3
  14008. -->
  14009. (S1 ^operator O1997 = 0.)
  14010. Firing prefer*rvt*predict-yes*H0
  14011. -->
  14012. Firing prefer*rvt*predict-no*H0
  14013. -->
  14014. Firing elaborate*copy-dir-to-output-link
  14015. -->
  14016. (I3 ^dir U +)
  14017. inner elaboration loop at bottom goal.
  14018. Retracting elaborate*copy-see-to-output-link
  14019. -->
  14020. (I3 ^see 1 +)
  14021. Retracting propose*predict-no
  14022. -->
  14023. (O1998 ^name predict-no +)
  14024. (S1 ^operator O1998 +)
  14025. Retracting propose*predict-yes
  14026. -->
  14027. (O1997 ^name predict-yes +)
  14028. (S1 ^operator O1997 +)
  14029. Retracting elaborate*reward*based*on*reward
  14030. -->
  14031. (R1002 ^value 1 +)
  14032. (R1 ^reward R1002 +)
  14033. Retracting elaborate*copy-dir-to-output-link
  14034. -->
  14035. (I3 ^dir L +)
  14036. Retracting rl*prefer*rvt*predict-no*H0*2*H1*14
  14037. -->
  14038. (S1 ^operator O1998 = 0.7618942170579377)
  14039. Retracting rl*prefer*rvt*predict-no*H0*2
  14040. -->
  14041. (S1 ^operator O1998 = 0.2381416323002802)
  14042. Retracting rl*prefer*rvt*predict-yes*H0*1*H1*15
  14043. -->
  14044. (S1 ^operator O1997 = -0.2915346922215271)
  14045. Retracting rl*prefer*rvt*predict-yes*H0*1
  14046. -->
  14047. (S1 ^operator O1997 = 0.3499208744070396)
  14048. =>WM: (14017: S1 ^operator O2000 +)
  14049. =>WM: (14016: S1 ^operator O1999 +)
  14050. =>WM: (14015: I3 ^dir U)
  14051. =>WM: (14014: O2000 ^name predict-no)
  14052. =>WM: (14013: O1999 ^name predict-yes)
  14053. =>WM: (14012: R1003 ^value 1)
  14054. =>WM: (14011: R1 ^reward R1003)
  14055. =>WM: (14010: I3 ^see 0)
  14056. <=WM: (14001: S1 ^operator O1997 +)
  14057. <=WM: (14002: S1 ^operator O1998 +)
  14058. <=WM: (14003: S1 ^operator O1998)
  14059. <=WM: (13986: I3 ^dir L)
  14060. <=WM: (13997: R1 ^reward R1002)
  14061. <=WM: (13996: I3 ^see 1)
  14062. <=WM: (14000: O1998 ^name predict-no)
  14063. <=WM: (13999: O1997 ^name predict-yes)
  14064. <=WM: (13998: R1002 ^value 1)
  14065. --- Inner Elaboration Phase, active level 1 (S1) ---
  14066. Firing prefer*rvt*predict-yes*H0
  14067. -->
  14068. Firing rl*prefer*rvt*predict-yes*H0*3
  14069. -->
  14070. (S1 ^operator O1999 = 0.)
  14071. Firing prefer*rvt*predict-no*H0
  14072. -->
  14073. Firing rl*prefer*rvt*predict-no*H0*4
  14074. -->
  14075. (S1 ^operator O2000 = 1.)
  14076. inner elaboration loop at bottom goal.
  14077. Retracting rl*prefer*rvt*predict-no*H0*4
  14078. -->
  14079. (S1 ^operator O1998 = 1.)
  14080. Retracting rl*prefer*rvt*predict-yes*H0*3
  14081. -->
  14082. (S1 ^operator O1997 = 0.)
  14083. --- END Proposal Phase ---
  14084. --- Decision Phase ---
  14085. RL update rl*prefer*rvt*predict-no*H0*2 0.569323 -0.331182 0.238142 -> 0.569318 -0.331179 0.238139(R,m,v=1,0.882716,0.104171)
  14086. RL update rl*prefer*rvt*predict-no*H0*2*H1*14 0.430739 0.331156 0.761894 -> 0.430733 0.331158 0.761891(R,m,v=1,1,0)
  14087. =>WM: (14018: S1 ^operator O2000)
  14088. 1000: O: O2000 (predict-no)
  14089. --- END Decision Phase ---
  14090. --- Application Phase ---
  14091. --- Firing Productions (PE) For State At Depth 1 ---
  14092. --- Inner Elaboration Phase, active level 1 (S1) ---
  14093. Firing apply*operator
  14094. -->
  14095. (I3 ^predict-no N1000 + :O )
  14096. Firing apply*operator*complete
  14097. -->
  14098. (I3 ^predict-no N999 - :O )
  14099. inner elaboration loop at bottom goal.
  14100. --- Change Working Memory (PE) ---
  14101. =>WM: (14019: I3 ^predict-no N1000)
  14102. <=WM: (14005: N999 ^status complete)
  14103. <=WM: (14004: I3 ^predict-no N999)
  14104. --- Firing Productions (IE) For State At Depth 1 ---
  14105. --- Inner Elaboration Phase, active level 1 (S1) ---
  14106. Firing monitor*world
  14107. -->
  14108. I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
  14109. --- Change Working Memory (IE) ---
  14110. --- END Application Phase ---
  14111. --- Output Phase ---
  14112. ENV: Agent did: predict-no for direction U in state State-A
  14113. In State-A moving U
  14114. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  14115. predict error 0
  14116. dir: dir isR
  14117. --- END Output Phase ---
  14118. -/|\-/|\-/--- Input Phase ---
  14119. =>WM: (14023: I2 ^dir R)
  14120. =>WM: (14022: I2 ^reward 1)
  14121. =>WM: (14021: I2 ^see 0)
  14122. =>WM: (14020: N1000 ^status complete)
  14123. <=WM: (14008: I2 ^dir U)
  14124. <=WM: (14007: I2 ^reward 1)
  14125. <=WM: (14006: I2 ^see 0)
  14126. =>WM: (14024: I2 ^level-1 L0-root)
  14127. <=WM: (14009: I2 ^level-1 L0-root)
  14128. --- END Input Phase ---
  14129. --- Proposal Phase ---
  14130. --- Inner Elaboration Phase, active level 1 (S1) ---
  14131. Firing rl*prefer*rvt*predict-yes*H0*5*H1*16
  14132. -->
  14133. (S1 ^operator O1999 = 0.7758187599628446)
  14134. Firing prefer*rvt*predict-yes*H0*5*H1
  14135. -->
  14136. Firing elaborate*copy-see-to-output-link
  14137. -->
  14138. (I3 ^see 0 +)
  14139. Firing elaborate*reward*based*on*reward
  14140. -->
  14141. (R1004 ^value 1 +)
  14142. (R1 ^reward R1004 +)
  14143. Firing propose*predict-yes
  14144. -->
  14145. (O2001 ^name predict-yes +)
  14146. (S1 ^operator O2001 +)
  14147. Firing propose*predict-no
  14148. -->
  14149. (O2002 ^name predict-no +)
  14150. (S1 ^operator O2002 +)
  14151. Firing rl*prefer*rvt*predict-no*H0*6
  14152. -->
  14153. (S1 ^operator O2000 = 0.9997455154214648)
  14154. Firing rl*prefer*rvt*predict-yes*H0*5
  14155. -->
  14156. (S1 ^operator O1999 = 0.2238998464753165)
  14157. Firing prefer*rvt*predict-yes*H0
  14158. -->
  14159. Firing prefer*rvt*predict-no*H0
  14160. -->
  14161. Firing elaborate*copy-dir-to-output-link
  14162. -->
  14163. (I3 ^dir R +)
  14164. inner elaboration loop at bottom goal.
  14165. Retracting elaborate*copy-see-to-output-link
  14166. -->
  14167. (I3 ^see 0 +)
  14168. Retracting propose*predict-no
  14169. -->
  14170. (O2000 ^name predict-no +)
  14171. (S1 ^operator O2000 +)
  14172. Retracting propose*predict-yes
  14173. -->
  14174. (O1999 ^name predict-yes +)
  14175. (S1 ^operator O1999 +)
  14176. Retracting elaborate*reward*based*on*reward
  14177. -->
  14178. (R1003 ^value 1 +)
  14179. (R1 ^reward R1003 +)
  14180. Retracting elaborate*copy-dir-to-output-link
  14181. -->
  14182. (I3 ^dir U +)
  14183. Retracting rl*prefer*rvt*predict-no*H0*4
  14184. -->
  14185. (S1 ^operator O2000 = 1.)
  14186. Retracting rl*prefer*rvt*predict-yes*H0*3
  14187. -->
  14188. (S1 ^operator O1999 = 0.)
  14189. =>WM: (14031: S1 ^operator O2002 +)
  14190. =>WM: (14030: S1 ^operator O2001 +)
  14191. =>WM: (14029: I3 ^dir R)
  14192. =>WM: (14028: O2002 ^name predict-no)
  14193. =>WM: (14027: O2001 ^name predict-yes)
  14194. =>WM: (14026: R1004 ^value 1)
  14195. =>WM: (14025: R1 ^reward R1004)
  14196. <=WM: (14016: S1 ^operator O1999 +)
  14197. <=WM: (14017: S1 ^operator O2000 +)
  14198. <=WM: (14018: S1 ^operator O2000)
  14199. <=WM: (14015: I3 ^dir U)
  14200. <=WM: (14011: R1 ^reward R1003)
  14201. <=WM: (14014: O2000 ^name predict-no)
  14202. <=WM: (14013: O1999 ^name predict-yes)
  14203. <=WM: (14012: R1003 ^value 1)
  14204. --- Inner Elaboration Phase, active level 1 (S1) ---
  14205. Firing prefer*rvt*predict-yes*H0
  14206. -->
  14207. Firing rl*prefer*rvt*predict-yes*H0*5*H1*16
  14208. -->
  14209. (S1 ^operator O2001 = 0.7758187599628446)
  14210. Firing rl*prefer*rvt*predict-yes*H0*5
  14211. -->
  14212. (S1 ^operator O2001 = 0.2238998464753165)
  14213. Firing prefer*rvt*predict-yes*H0*5*H1
  14214. -->
  14215. Firing prefer*rvt*predict-no*H0
  14216. -->
  14217. Firing rl*prefer*rvt*predict-no*H0*6
  14218. -->
  14219. (S1 ^operator O2002 = 0.9997455154214648)
  14220. inner elaboration loop at bottom goal.
  14221. Retracting rl*prefer*rvt*predict-no*H0*6
  14222. -->
  14223. (S1 ^operator O2000 = 0.9997455154214648)
  14224. Retracting rl*prefer*rvt*predict-yes*H0*5
  14225. -->
  14226. (S1 ^operator O1999 = 0.2238998464753165)
  14227. Retracting rl*prefer*rvt*predict-yes*H0*5*H1*16
  14228. -->
  14229. (S1 ^operator O1999 = 0.7758187599628446)
  14230. --- END Proposal Phase ---
  14231. --- Decision Phase ---
  14232. RL update rl*prefer*rvt*predict-no*H0*4 1 0 1 -> 1 0 1(R,m,v=1,1,0)
  14233. =>WM: (14032: S1 ^operator O2002)
  14234. 1001: O: O2002 (predict-no)
  14235. --- END Decision Phase ---
  14236. --- Application Phase ---
  14237. --- Firing Productions (PE) For State At Depth 1 ---
  14238. --- Inner Elaboration Phase, active level 1 (S1) ---
  14239. Firing apply*operator
  14240. -->
  14241. (I3 ^predict-no N1001 + :O )
  14242. Firing apply*operator*complete
  14243. -->
  14244. (I3 ^predict-no N1000 - :O )
  14245. inner elaboration loop at bottom goal.
  14246. --- Change Working Memory (PE) ---
  14247. =>WM: (14033: I3 ^predict-no N1001)
  14248. <=WM: (14020: N1000 ^status complete)
  14249. <=WM: (14019: I3 ^predict-no N1000)
  14250. --- Firing Productions (IE) For State At Depth 1 ---
  14251. --- Inner Elaboration Phase, active level 1 (S1) ---
  14252. Firing monitor*world
  14253. -->
  14254. I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
  14255. --- Change Working Memory (IE) ---
  14256. --- END Application Phase ---
  14257. --- Output Phase ---
  14258. ENV: Agent did: predict-no for direction R in state State-A
  14259. In State-A moving R
  14260. ENV: (next state, see, prediction correct?) = (State-B, 1, False)
  14261. predict error 1
  14262. dir: dir isL
  14263. --- END Output Phase ---
  14264. |--- Input Phase ---
  14265. =>WM: (14037: I2 ^dir L)
  14266. =>WM: (14036: I2 ^reward 0)
  14267. =>WM: (14035: I2 ^see 1)
  14268. =>WM: (14034: N1001 ^status complete)
  14269. <=WM: (14023: I2 ^dir R)
  14270. <=WM: (14022: I2 ^reward 1)
  14271. <=WM: (14021: I2 ^see 0)
  14272. =>WM: (14038: I2 ^level-1 R1-root)
  14273. <=WM: (14024: I2 ^level-1 L0-root)
  14274. --- END Input Phase ---
  14275. --- Proposal Phase ---
  14276. --- Inner Elaboration Phase, active level 1 (S1) ---
  14277. Firing rl*prefer*rvt*predict-no*H0*2*H1*8
  14278. -->
  14279. (S1 ^operator O2002 = -0.1970449706966682)
  14280. Firing rl*prefer*rvt*predict-yes*H0*1*H1*7
  14281. -->
  14282. (S1 ^operator O2001 = 0.6500792624517389)
  14283. Firing prefer*rvt*predict-no*H0*2*H1
  14284. -->
  14285. Firing prefer*rvt*predict-yes*H0*1*H1
  14286. -->
  14287. Firing elaborate*copy-see-to-output-link
  14288. -->
  14289. (I3 ^see 1 +)
  14290. Firing elaborate*reward*based*on*reward
  14291. -->
  14292. (R1005 ^value 0 +)
  14293. (R1 ^reward R1005 +)
  14294. Firing propose*predict-yes
  14295. -->
  14296. (O2003 ^name predict-yes +)
  14297. (S1 ^operator O2003 +)
  14298. Firing propose*predict-no
  14299. -->
  14300. (O2004 ^name predict-no +)
  14301. (S1 ^operator O2004 +)
  14302. Firing rl*prefer*rvt*predict-no*H0*2
  14303. -->
  14304. (S1 ^operator O2002 = 0.2381386878410681)
  14305. Firing rl*prefer*rvt*predict-yes*H0*1
  14306. -->
  14307. (S1 ^operator O2001 = 0.3499208744070396)
  14308. Firing prefer*rvt*predict-yes*H0
  14309. -->
  14310. Firing prefer*rvt*predict-no*H0
  14311. -->
  14312. Firing elaborate*copy-dir-to-output-link
  14313. -->
  14314. (I3 ^dir L +)
  14315. inner elaboration loop at bottom goal.
  14316. Retracting elaborate*copy-see-to-output-link
  14317. -->
  14318. (I3 ^see 0 +)
  14319. Retracting propose*predict-no
  14320. -->
  14321. (O2002 ^name predict-no +)
  14322. (S1 ^operator O2002 +)
  14323. Retracting propose*predict-yes
  14324. -->
  14325. (O2001 ^name predict-yes +)
  14326. (S1 ^operator O2001 +)
  14327. Retracting elaborate*reward*based*on*reward
  14328. -->
  14329. (R1004 ^value 1 +)
  14330. (R1 ^reward R1004 +)
  14331. Retracting elaborate*copy-dir-to-output-link
  14332. -->
  14333. (I3 ^dir R +)
  14334. Retracting rl*prefer*rvt*predict-no*H0*6
  14335. -->
  14336. (S1 ^operator O2002 = 0.9997455154214648)
  14337. Retracting rl*prefer*rvt*predict-yes*H0*5
  14338. -->
  14339. (S1 ^operator O2001 = 0.2238998464753165)
  14340. Retracting rl*prefer*rvt*predict-yes*H0*5*H1*16
  14341. -->
  14342. (S1 ^operator O2001 = 0.7758187599628446)
  14343. =>WM: (14046: S1 ^operator O2004 +)
  14344. =>WM: (14045: S1 ^operator O2003 +)
  14345. =>WM: (14044: I3 ^dir L)
  14346. =>WM: (14043: O2004 ^name predict-no)
  14347. =>WM: (14042: O2003 ^name predict-yes)
  14348. =>WM: (14041: R1005 ^value 0)
  14349. =>WM: (14040: R1 ^reward R1005)
  14350. =>WM: (14039: I3 ^see 1)
  14351. <=WM: (14030: S1 ^operator O2001 +)
  14352. <=WM: (14031: S1 ^operator O2002 +)
  14353. <=WM: (14032: S1 ^operator O2002)
  14354. <=WM: (14029: I3 ^dir R)
  14355. <=WM: (14025: R1 ^reward R1004)
  14356. <=WM: (14010: I3 ^see 0)
  14357. <=WM: (14028: O2002 ^name predict-no)
  14358. <=WM: (14027: O2001 ^name predict-yes)
  14359. <=WM: (14026: R1004 ^value 1)
  14360. --- Inner Elaboration Phase, active level 1 (S1) ---
  14361. Firing prefer*rvt*predict-yes*H0
  14362. -->
  14363. Firing rl*prefer*rvt*predict-yes*H0*1
  14364. -->
  14365. (S1 ^operator O2003 = 0.3499208744070396)
  14366. Firing prefer*rvt*predict-yes*H0*1*H1
  14367. -->
  14368. Firing rl*prefer*rvt*predict-yes*H0*1*H1*7
  14369. -->
  14370. (S1 ^operator O2003 = 0.6500792624517389)
  14371. Firing prefer*rvt*predict-no*H0
  14372. -->
  14373. Firing rl*prefer*rvt*predict-no*H0*2
  14374. -->
  14375. (S1 ^operator O2004 = 0.2381386878410681)
  14376. Firing prefer*rvt*predict-no*H0*2*H1
  14377. -->
  14378. Firing rl*prefer*rvt*predict-no*H0*2*H1*8
  14379. -->
  14380. (S1 ^operator O2004 = -0.1970449706966682)
  14381. inner elaboration loop at bottom goal.
  14382. Retracting rl*prefer*rvt*predict-no*H0*2
  14383. -->
  14384. (S1 ^operator O2002 = 0.2381386878410681)
  14385. Retracting rl*prefer*rvt*predict-no*H0*2*H1*8
  14386. -->
  14387. (S1 ^operator O2002 = -0.1970449706966682)
  14388. Retracting rl*prefer*rvt*predict-yes*H0*1
  14389. -->
  14390. (S1 ^operator O2001 = 0.3499208744070396)
  14391. Retracting rl*prefer*rvt*predict-yes*H0*1*H1*7
  14392. -->
  14393. (S1 ^operator O2001 = 0.6500792624517389)
  14394. --- END Proposal Phase ---
  14395. --- Decision Phase ---
  14396. RL update rl*prefer*rvt*predict-no*H0*6 0.999746 0 0.999746 -> 0.837575 0 0.837575(R,m,v=0,0.857143,0.123153)
  14397. =>WM: (14047: S1 ^operator O2003)
  14398. 1002: O: O2003 (predict-yes)
  14399. --- END Decision Phase ---
  14400. --- Application Phase ---
  14401. --- Firing Productions (PE) For State At Depth 1 ---
  14402. --- Inner Elaboration Phase, active level 1 (S1) ---
  14403. Firing apply*operator
  14404. -->
  14405. (I3 ^predict-yes N1002 + :O )
  14406. Firing apply*operator*complete
  14407. -->
  14408. (I3 ^predict-no N1001 - :O )
  14409. inner elaboration loop at bottom goal.
  14410. --- Change Working Memory (PE) ---
  14411. =>WM: (14048: I3 ^predict-yes N1002)
  14412. <=WM: (14034: N1001 ^status complete)
  14413. <=WM: (14033: I3 ^predict-no N1001)
  14414. --- Firing Productions (IE) For State At Depth 1 ---
  14415. --- Inner Elaboration Phase, active level 1 (S1) ---
  14416. Firing monitor*world
  14417. -->
  14418. I see 0 and I'm going to do: predict-yes inner elaboration loop at bottom goal.
  14419. --- Change Working Memory (IE) ---
  14420. --- END Application Phase ---
  14421. --- Output Phase ---
  14422. ENV: Agent did: predict-yes for direction L in state State-B
  14423. In State-B moving L
  14424. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  14425. predict error 0
  14426. dir: dir isL
  14427. --- END Output Phase ---
  14428. \-/--- Input Phase ---
  14429. =>WM: (14052: I2 ^dir L)
  14430. =>WM: (14051: I2 ^reward 1)
  14431. =>WM: (14050: I2 ^see 1)
  14432. =>WM: (14049: N1002 ^status complete)
  14433. <=WM: (14037: I2 ^dir L)
  14434. <=WM: (14036: I2 ^reward 0)
  14435. <=WM: (14035: I2 ^see 1)
  14436. =>WM: (14053: I2 ^level-1 L1-root)
  14437. <=WM: (14038: I2 ^level-1 R1-root)
  14438. --- END Input Phase ---
  14439. --- Proposal Phase ---
  14440. --- Inner Elaboration Phase, active level 1 (S1) ---
  14441. Firing rl*prefer*rvt*predict-no*H0*2*H1*14
  14442. -->
  14443. (S1 ^operator O2004 = 0.7618907924659671)
  14444. Firing rl*prefer*rvt*predict-yes*H0*1*H1*15
  14445. -->
  14446. (S1 ^operator O2003 = -0.2915346922215271)
  14447. Firing prefer*rvt*predict-no*H0*2*H1
  14448. -->
  14449. Firing prefer*rvt*predict-yes*H0*1*H1
  14450. -->
  14451. Firing elaborate*copy-see-to-output-link
  14452. -->
  14453. (I3 ^see 1 +)
  14454. Firing elaborate*reward*based*on*reward
  14455. -->
  14456. (R1006 ^value 1 +)
  14457. (R1 ^reward R1006 +)
  14458. Firing propose*predict-yes
  14459. -->
  14460. (O2005 ^name predict-yes +)
  14461. (S1 ^operator O2005 +)
  14462. Firing propose*predict-no
  14463. -->
  14464. (O2006 ^name predict-no +)
  14465. (S1 ^operator O2006 +)
  14466. Firing rl*prefer*rvt*predict-no*H0*2
  14467. -->
  14468. (S1 ^operator O2004 = 0.2381386878410681)
  14469. Firing rl*prefer*rvt*predict-yes*H0*1
  14470. -->
  14471. (S1 ^operator O2003 = 0.3499208744070396)
  14472. Firing prefer*rvt*predict-yes*H0
  14473. -->
  14474. Firing prefer*rvt*predict-no*H0
  14475. -->
  14476. Firing elaborate*copy-dir-to-output-link
  14477. -->
  14478. (I3 ^dir L +)
  14479. inner elaboration loop at bottom goal.
  14480. Retracting elaborate*copy-see-to-output-link
  14481. -->
  14482. (I3 ^see 1 +)
  14483. Retracting propose*predict-no
  14484. -->
  14485. (O2004 ^name predict-no +)
  14486. (S1 ^operator O2004 +)
  14487. Retracting propose*predict-yes
  14488. -->
  14489. (O2003 ^name predict-yes +)
  14490. (S1 ^operator O2003 +)
  14491. Retracting elaborate*reward*based*on*reward
  14492. -->
  14493. (R1005 ^value 0 +)
  14494. (R1 ^reward R1005 +)
  14495. Retracting elaborate*copy-dir-to-output-link
  14496. -->
  14497. (I3 ^dir L +)
  14498. Retracting rl*prefer*rvt*predict-no*H0*2*H1*8
  14499. -->
  14500. (S1 ^operator O2004 = -0.1970449706966682)
  14501. Retracting rl*prefer*rvt*predict-no*H0*2
  14502. -->
  14503. (S1 ^operator O2004 = 0.2381386878410681)
  14504. Retracting rl*prefer*rvt*predict-yes*H0*1*H1*7
  14505. -->
  14506. (S1 ^operator O2003 = 0.6500792624517389)
  14507. Retracting rl*prefer*rvt*predict-yes*H0*1
  14508. -->
  14509. (S1 ^operator O2003 = 0.3499208744070396)
  14510. =>WM: (14059: S1 ^operator O2006 +)
  14511. =>WM: (14058: S1 ^operator O2005 +)
  14512. =>WM: (14057: O2006 ^name predict-no)
  14513. =>WM: (14056: O2005 ^name predict-yes)
  14514. =>WM: (14055: R1006 ^value 1)
  14515. =>WM: (14054: R1 ^reward R1006)
  14516. <=WM: (14045: S1 ^operator O2003 +)
  14517. <=WM: (14047: S1 ^operator O2003)
  14518. <=WM: (14046: S1 ^operator O2004 +)
  14519. <=WM: (14040: R1 ^reward R1005)
  14520. <=WM: (14043: O2004 ^name predict-no)
  14521. <=WM: (14042: O2003 ^name predict-yes)
  14522. <=WM: (14041: R1005 ^value 0)
  14523. --- Inner Elaboration Phase, active level 1 (S1) ---
  14524. Firing prefer*rvt*predict-yes*H0
  14525. -->
  14526. Firing rl*prefer*rvt*predict-yes*H0*1
  14527. -->
  14528. (S1 ^operator O2005 = 0.3499208744070396)
  14529. Firing prefer*rvt*predict-yes*H0*1*H1
  14530. -->
  14531. Firing rl*prefer*rvt*predict-yes*H0*1*H1*15
  14532. -->
  14533. (S1 ^operator O2005 = -0.2915346922215271)
  14534. Firing prefer*rvt*predict-no*H0
  14535. -->
  14536. Firing rl*prefer*rvt*predict-no*H0*2
  14537. -->
  14538. (S1 ^operator O2006 = 0.2381386878410681)
  14539. Firing prefer*rvt*predict-no*H0*2*H1
  14540. -->
  14541. Firing rl*prefer*rvt*predict-no*H0*2*H1*14
  14542. -->
  14543. (S1 ^operator O2006 = 0.7618907924659671)
  14544. inner elaboration loop at bottom goal.
  14545. Retracting rl*prefer*rvt*predict-no*H0*2
  14546. -->
  14547. (S1 ^operator O2004 = 0.2381386878410681)
  14548. Retracting rl*prefer*rvt*predict-no*H0*2*H1*14
  14549. -->
  14550. (S1 ^operator O2004 = 0.7618907924659671)
  14551. Retracting rl*prefer*rvt*predict-yes*H0*1
  14552. -->
  14553. (S1 ^operator O2003 = 0.3499208744070396)
  14554. Retracting rl*prefer*rvt*predict-yes*H0*1*H1*15
  14555. -->
  14556. (S1 ^operator O2003 = -0.2915346922215271)
  14557. --- END Proposal Phase ---
  14558. --- Decision Phase ---
  14559. RL update rl*prefer*rvt*predict-yes*H0*1 0.407928 -0.0580072 0.349921 -> 0.407928 -0.0580076 0.349921(R,m,v=1,0.903226,0.0879765)
  14560. RL update rl*prefer*rvt*predict-yes*H0*1*H1*7 0.592067 0.058012 0.650079 -> 0.592068 0.0580115 0.650079(R,m,v=1,1,0)
  14561. =>WM: (14060: S1 ^operator O2006)
  14562. 1003: O: O2006 (predict-no)
  14563. --- END Decision Phase ---
  14564. --- Application Phase ---
  14565. --- Firing Productions (PE) For State At Depth 1 ---
  14566. --- Inner Elaboration Phase, active level 1 (S1) ---
  14567. Firing apply*operator
  14568. -->
  14569. (I3 ^predict-no N1003 + :O )
  14570. Firing apply*operator*complete
  14571. -->
  14572. (I3 ^predict-yes N1002 - :O )
  14573. inner elaboration loop at bottom goal.
  14574. --- Change Working Memory (PE) ---
  14575. =>WM: (14061: I3 ^predict-no N1003)
  14576. <=WM: (14049: N1002 ^status complete)
  14577. <=WM: (14048: I3 ^predict-yes N1002)
  14578. --- Firing Productions (IE) For State At Depth 1 ---
  14579. --- Inner Elaboration Phase, active level 1 (S1) ---
  14580. Firing monitor*world
  14581. -->
  14582. I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
  14583. --- Change Working Memory (IE) ---
  14584. --- END Application Phase ---
  14585. --- Output Phase ---
  14586. ENV: Agent did: predict-no for direction L in state State-A
  14587. In State-A moving L
  14588. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  14589. predict error 0
  14590. dir: dir isR
  14591. --- END Output Phase ---
  14592. |\---- Input Phase ---
  14593. =>WM: (14065: I2 ^dir R)
  14594. =>WM: (14064: I2 ^reward 1)
  14595. =>WM: (14063: I2 ^see 0)
  14596. =>WM: (14062: N1003 ^status complete)
  14597. <=WM: (14052: I2 ^dir L)
  14598. <=WM: (14051: I2 ^reward 1)
  14599. <=WM: (14050: I2 ^see 1)
  14600. =>WM: (14066: I2 ^level-1 L0-root)
  14601. <=WM: (14053: I2 ^level-1 L1-root)
  14602. --- END Input Phase ---
  14603. --- Proposal Phase ---
  14604. --- Inner Elaboration Phase, active level 1 (S1) ---
  14605. Firing rl*prefer*rvt*predict-yes*H0*5*H1*16
  14606. -->
  14607. (S1 ^operator O2005 = 0.7758187599628446)
  14608. Firing prefer*rvt*predict-yes*H0*5*H1
  14609. -->
  14610. Firing elaborate*copy-see-to-output-link
  14611. -->
  14612. (I3 ^see 0 +)
  14613. Firing elaborate*reward*based*on*reward
  14614. -->
  14615. (R1007 ^value 1 +)
  14616. (R1 ^reward R1007 +)
  14617. Firing propose*predict-yes
  14618. -->
  14619. (O2007 ^name predict-yes +)
  14620. (S1 ^operator O2007 +)
  14621. Firing propose*predict-no
  14622. -->
  14623. (O2008 ^name predict-no +)
  14624. (S1 ^operator O2008 +)
  14625. Firing rl*prefer*rvt*predict-no*H0*6
  14626. -->
  14627. (S1 ^operator O2006 = 0.8375751627684616)
  14628. Firing rl*prefer*rvt*predict-yes*H0*5
  14629. -->
  14630. (S1 ^operator O2005 = 0.2238998464753165)
  14631. Firing prefer*rvt*predict-yes*H0
  14632. -->
  14633. Firing prefer*rvt*predict-no*H0
  14634. -->
  14635. Firing elaborate*copy-dir-to-output-link
  14636. -->
  14637. (I3 ^dir R +)
  14638. inner elaboration loop at bottom goal.
  14639. Retracting elaborate*copy-see-to-output-link
  14640. -->
  14641. (I3 ^see 1 +)
  14642. Retracting propose*predict-no
  14643. -->
  14644. (O2006 ^name predict-no +)
  14645. (S1 ^operator O2006 +)
  14646. Retracting propose*predict-yes
  14647. -->
  14648. (O2005 ^name predict-yes +)
  14649. (S1 ^operator O2005 +)
  14650. Retracting elaborate*reward*based*on*reward
  14651. -->
  14652. (R1006 ^value 1 +)
  14653. (R1 ^reward R1006 +)
  14654. Retracting elaborate*copy-dir-to-output-link
  14655. -->
  14656. (I3 ^dir L +)
  14657. Retracting rl*prefer*rvt*predict-no*H0*2*H1*14
  14658. -->
  14659. (S1 ^operator O2006 = 0.7618907924659671)
  14660. Retracting rl*prefer*rvt*predict-no*H0*2
  14661. -->
  14662. (S1 ^operator O2006 = 0.2381386878410681)
  14663. Retracting rl*prefer*rvt*predict-yes*H0*1*H1*15
  14664. -->
  14665. (S1 ^operator O2005 = -0.2915346922215271)
  14666. Retracting rl*prefer*rvt*predict-yes*H0*1
  14667. -->
  14668. (S1 ^operator O2005 = 0.3499208630840915)
  14669. =>WM: (14074: S1 ^operator O2008 +)
  14670. =>WM: (14073: S1 ^operator O2007 +)
  14671. =>WM: (14072: I3 ^dir R)
  14672. =>WM: (14071: O2008 ^name predict-no)
  14673. =>WM: (14070: O2007 ^name predict-yes)
  14674. =>WM: (14069: R1007 ^value 1)
  14675. =>WM: (14068: R1 ^reward R1007)
  14676. =>WM: (14067: I3 ^see 0)
  14677. <=WM: (14058: S1 ^operator O2005 +)
  14678. <=WM: (14059: S1 ^operator O2006 +)
  14679. <=WM: (14060: S1 ^operator O2006)
  14680. <=WM: (14044: I3 ^dir L)
  14681. <=WM: (14054: R1 ^reward R1006)
  14682. <=WM: (14039: I3 ^see 1)
  14683. <=WM: (14057: O2006 ^name predict-no)
  14684. <=WM: (14056: O2005 ^name predict-yes)
  14685. <=WM: (14055: R1006 ^value 1)
  14686. --- Inner Elaboration Phase, active level 1 (S1) ---
  14687. Firing prefer*rvt*predict-yes*H0
  14688. -->
  14689. Firing rl*prefer*rvt*predict-yes*H0*5
  14690. -->
  14691. (S1 ^operator O2007 = 0.2238998464753165)
  14692. Firing prefer*rvt*predict-yes*H0*5*H1
  14693. -->
  14694. Firing rl*prefer*rvt*predict-yes*H0*5*H1*16
  14695. -->
  14696. (S1 ^operator O2007 = 0.7758187599628446)
  14697. Firing prefer*rvt*predict-no*H0
  14698. -->
  14699. Firing rl*prefer*rvt*predict-no*H0*6
  14700. -->
  14701. (S1 ^operator O2008 = 0.8375751627684616)
  14702. inner elaboration loop at bottom goal.
  14703. Retracting rl*prefer*rvt*predict-no*H0*6
  14704. -->
  14705. (S1 ^operator O2006 = 0.8375751627684616)
  14706. Retracting rl*prefer*rvt*predict-yes*H0*5
  14707. -->
  14708. (S1 ^operator O2005 = 0.2238998464753165)
  14709. Retracting rl*prefer*rvt*predict-yes*H0*5*H1*16
  14710. -->
  14711. (S1 ^operator O2005 = 0.7758187599628446)
  14712. --- END Proposal Phase ---
  14713. --- Decision Phase ---
  14714. RL update rl*prefer*rvt*predict-no*H0*2 0.569318 -0.331179 0.238139 -> 0.569314 -0.331178 0.238136(R,m,v=1,0.883436,0.103613)
  14715. RL update rl*prefer*rvt*predict-no*H0*2*H1*14 0.430733 0.331158 0.761891 -> 0.430728 0.33116 0.761888(R,m,v=1,1,0)
  14716. =>WM: (14075: S1 ^operator O2007)
  14717. 1004: O: O2007 (predict-yes)
  14718. --- END Decision Phase ---
  14719. --- Application Phase ---
  14720. --- Firing Productions (PE) For State At Depth 1 ---
  14721. --- Inner Elaboration Phase, active level 1 (S1) ---
  14722. Firing apply*operator
  14723. -->
  14724. (I3 ^predict-yes N1004 + :O )
  14725. Firing apply*operator*complete
  14726. -->
  14727. (I3 ^predict-no N1003 - :O )
  14728. inner elaboration loop at bottom goal.
  14729. --- Change Working Memory (PE) ---
  14730. =>WM: (14076: I3 ^predict-yes N1004)
  14731. <=WM: (14062: N1003 ^status complete)
  14732. <=WM: (14061: I3 ^predict-no N1003)
  14733. --- Firing Productions (IE) For State At Depth 1 ---
  14734. --- Inner Elaboration Phase, active level 1 (S1) ---
  14735. Firing monitor*world
  14736. -->
  14737. I see 1 and I'm going to do: predict-yes inner elaboration loop at bottom goal.
  14738. --- Change Working Memory (IE) ---
  14739. --- END Application Phase ---
  14740. --- Output Phase ---
  14741. ENV: Agent did: predict-yes for direction R in state State-A
  14742. In State-A moving R
  14743. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  14744. predict error 0
  14745. dir: dir isR
  14746. --- END Output Phase ---
  14747. /|\--- Input Phase ---
  14748. =>WM: (14080: I2 ^dir R)
  14749. =>WM: (14079: I2 ^reward 1)
  14750. =>WM: (14078: I2 ^see 1)
  14751. =>WM: (14077: N1004 ^status complete)
  14752. <=WM: (14065: I2 ^dir R)
  14753. <=WM: (14064: I2 ^reward 1)
  14754. <=WM: (14063: I2 ^see 0)
  14755. =>WM: (14081: I2 ^level-1 R1-root)
  14756. <=WM: (14066: I2 ^level-1 L0-root)
  14757. --- END Input Phase ---
  14758. --- Proposal Phase ---
  14759. --- Inner Elaboration Phase, active level 1 (S1) ---
  14760. Firing rl*prefer*rvt*predict-yes*H0*5*H1*10
  14761. -->
  14762. (S1 ^operator O2007 = -0.2099933006338622)
  14763. Firing prefer*rvt*predict-yes*H0*5*H1
  14764. -->
  14765. Firing elaborate*copy-see-to-output-link
  14766. -->
  14767. (I3 ^see 1 +)
  14768. Firing elaborate*reward*based*on*reward
  14769. -->
  14770. (R1008 ^value 1 +)
  14771. (R1 ^reward R1008 +)
  14772. Firing propose*predict-yes
  14773. -->
  14774. (O2009 ^name predict-yes +)
  14775. (S1 ^operator O2009 +)
  14776. Firing propose*predict-no
  14777. -->
  14778. (O2010 ^name predict-no +)
  14779. (S1 ^operator O2010 +)
  14780. Firing rl*prefer*rvt*predict-no*H0*6
  14781. -->
  14782. (S1 ^operator O2008 = 0.8375751627684616)
  14783. Firing rl*prefer*rvt*predict-yes*H0*5
  14784. -->
  14785. (S1 ^operator O2007 = 0.2238998464753165)
  14786. Firing prefer*rvt*predict-yes*H0
  14787. -->
  14788. Firing prefer*rvt*predict-no*H0
  14789. -->
  14790. Firing elaborate*copy-dir-to-output-link
  14791. -->
  14792. (I3 ^dir R +)
  14793. inner elaboration loop at bottom goal.
  14794. Retracting elaborate*copy-see-to-output-link
  14795. -->
  14796. (I3 ^see 0 +)
  14797. Retracting propose*predict-no
  14798. -->
  14799. (O2008 ^name predict-no +)
  14800. (S1 ^operator O2008 +)
  14801. Retracting propose*predict-yes
  14802. -->
  14803. (O2007 ^name predict-yes +)
  14804. (S1 ^operator O2007 +)
  14805. Retracting elaborate*reward*based*on*reward
  14806. -->
  14807. (R1007 ^value 1 +)
  14808. (R1 ^reward R1007 +)
  14809. Retracting elaborate*copy-dir-to-output-link
  14810. -->
  14811. (I3 ^dir R +)
  14812. Retracting rl*prefer*rvt*predict-no*H0*6
  14813. -->
  14814. (S1 ^operator O2008 = 0.8375751627684616)
  14815. Retracting rl*prefer*rvt*predict-yes*H0*5*H1*16
  14816. -->
  14817. (S1 ^operator O2007 = 0.7758187599628446)
  14818. Retracting rl*prefer*rvt*predict-yes*H0*5
  14819. -->
  14820. (S1 ^operator O2007 = 0.2238998464753165)
  14821. =>WM: (14088: S1 ^operator O2010 +)
  14822. =>WM: (14087: S1 ^operator O2009 +)
  14823. =>WM: (14086: O2010 ^name predict-no)
  14824. =>WM: (14085: O2009 ^name predict-yes)
  14825. =>WM: (14084: R1008 ^value 1)
  14826. =>WM: (14083: R1 ^reward R1008)
  14827. =>WM: (14082: I3 ^see 1)
  14828. <=WM: (14073: S1 ^operator O2007 +)
  14829. <=WM: (14075: S1 ^operator O2007)
  14830. <=WM: (14074: S1 ^operator O2008 +)
  14831. <=WM: (14068: R1 ^reward R1007)
  14832. <=WM: (14067: I3 ^see 0)
  14833. <=WM: (14071: O2008 ^name predict-no)
  14834. <=WM: (14070: O2007 ^name predict-yes)
  14835. <=WM: (14069: R1007 ^value 1)
  14836. --- Inner Elaboration Phase, active level 1 (S1) ---
  14837. Firing prefer*rvt*predict-yes*H0
  14838. -->
  14839. Firing rl*prefer*rvt*predict-yes*H0*5
  14840. -->
  14841. (S1 ^operator O2009 = 0.2238998464753165)
  14842. Firing prefer*rvt*predict-yes*H0*5*H1
  14843. -->
  14844. Firing rl*prefer*rvt*predict-yes*H0*5*H1*10
  14845. -->
  14846. (S1 ^operator O2009 = -0.2099933006338622)
  14847. Firing prefer*rvt*predict-no*H0
  14848. -->
  14849. Firing rl*prefer*rvt*predict-no*H0*6
  14850. -->
  14851. (S1 ^operator O2010 = 0.8375751627684616)
  14852. inner elaboration loop at bottom goal.
  14853. Retracting rl*prefer*rvt*predict-no*H0*6
  14854. -->
  14855. (S1 ^operator O2008 = 0.8375751627684616)
  14856. Retracting rl*prefer*rvt*predict-yes*H0*5
  14857. -->
  14858. (S1 ^operator O2007 = 0.2238998464753165)
  14859. Retracting rl*prefer*rvt*predict-yes*H0*5*H1*10
  14860. -->
  14861. (S1 ^operator O2007 = -0.2099933006338622)
  14862. --- END Proposal Phase ---
  14863. --- Decision Phase ---
  14864. RL update rl*prefer*rvt*predict-yes*H0*5 0.553512 -0.329612 0.2239 -> 0.553535 -0.329612 0.223923(R,m,v=1,0.859873,0.121264)
  14865. RL update rl*prefer*rvt*predict-yes*H0*5*H1*16 0.446202 0.329616 0.775819 -> 0.44623 0.329616 0.775846(R,m,v=1,1,0)
  14866. =>WM: (14089: S1 ^operator O2010)
  14867. 1005: O: O2010 (predict-no)
  14868. --- END Decision Phase ---
  14869. --- Application Phase ---
  14870. --- Firing Productions (PE) For State At Depth 1 ---
  14871. --- Inner Elaboration Phase, active level 1 (S1) ---
  14872. Firing apply*operator
  14873. -->
  14874. (I3 ^predict-no N1005 + :O )
  14875. Firing apply*operator*complete
  14876. -->
  14877. (I3 ^predict-yes N1004 - :O )
  14878. inner elaboration loop at bottom goal.
  14879. --- Change Working Memory (PE) ---
  14880. =>WM: (14090: I3 ^predict-no N1005)
  14881. <=WM: (14077: N1004 ^status complete)
  14882. <=WM: (14076: I3 ^predict-yes N1004)
  14883. --- Firing Productions (IE) For State At Depth 1 ---
  14884. --- Inner Elaboration Phase, active level 1 (S1) ---
  14885. Firing monitor*world
  14886. -->
  14887. I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
  14888. --- Change Working Memory (IE) ---
  14889. --- END Application Phase ---
  14890. --- Output Phase ---
  14891. ENV: Agent did: predict-no for direction R in state State-B
  14892. In State-B moving R
  14893. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  14894. predict error 0
  14895. dir: dir isU
  14896. --- END Output Phase ---
  14897. -/|--- Input Phase ---
  14898. =>WM: (14094: I2 ^dir U)
  14899. =>WM: (14093: I2 ^reward 1)
  14900. =>WM: (14092: I2 ^see 0)
  14901. =>WM: (14091: N1005 ^status complete)
  14902. <=WM: (14080: I2 ^dir R)
  14903. <=WM: (14079: I2 ^reward 1)
  14904. <=WM: (14078: I2 ^see 1)
  14905. =>WM: (14095: I2 ^level-1 R0-root)
  14906. <=WM: (14081: I2 ^level-1 R1-root)
  14907. --- END Input Phase ---
  14908. --- Proposal Phase ---
  14909. --- Inner Elaboration Phase, active level 1 (S1) ---
  14910. Firing elaborate*copy-see-to-output-link
  14911. -->
  14912. (I3 ^see 0 +)
  14913. Firing elaborate*reward*based*on*reward
  14914. -->
  14915. (R1009 ^value 1 +)
  14916. (R1 ^reward R1009 +)
  14917. Firing propose*predict-yes
  14918. -->
  14919. (O2011 ^name predict-yes +)
  14920. (S1 ^operator O2011 +)
  14921. Firing propose*predict-no
  14922. -->
  14923. (O2012 ^name predict-no +)
  14924. (S1 ^operator O2012 +)
  14925. Firing rl*prefer*rvt*predict-no*H0*4
  14926. -->
  14927. (S1 ^operator O2010 = 1.)
  14928. Firing rl*prefer*rvt*predict-yes*H0*3
  14929. -->
  14930. (S1 ^operator O2009 = 0.)
  14931. Firing prefer*rvt*predict-yes*H0
  14932. -->
  14933. Firing prefer*rvt*predict-no*H0
  14934. -->
  14935. Firing elaborate*copy-dir-to-output-link
  14936. -->
  14937. (I3 ^dir U +)
  14938. inner elaboration loop at bottom goal.
  14939. Retracting elaborate*copy-see-to-output-link
  14940. -->
  14941. (I3 ^see 1 +)
  14942. Retracting propose*predict-no
  14943. -->
  14944. (O2010 ^name predict-no +)
  14945. (S1 ^operator O2010 +)
  14946. Retracting propose*predict-yes
  14947. -->
  14948. (O2009 ^name predict-yes +)
  14949. (S1 ^operator O2009 +)
  14950. Retracting elaborate*reward*based*on*reward
  14951. -->
  14952. (R1008 ^value 1 +)
  14953. (R1 ^reward R1008 +)
  14954. Retracting elaborate*copy-dir-to-output-link
  14955. -->
  14956. (I3 ^dir R +)
  14957. Retracting rl*prefer*rvt*predict-no*H0*6
  14958. -->
  14959. (S1 ^operator O2010 = 0.8375751627684616)
  14960. Retracting rl*prefer*rvt*predict-yes*H0*5*H1*10
  14961. -->
  14962. (S1 ^operator O2009 = -0.2099933006338622)
  14963. Retracting rl*prefer*rvt*predict-yes*H0*5
  14964. -->
  14965. (S1 ^operator O2009 = 0.2239230781580192)
  14966. =>WM: (14103: S1 ^operator O2012 +)
  14967. =>WM: (14102: S1 ^operator O2011 +)
  14968. =>WM: (14101: I3 ^dir U)
  14969. =>WM: (14100: O2012 ^name predict-no)
  14970. =>WM: (14099: O2011 ^name predict-yes)
  14971. =>WM: (14098: R1009 ^value 1)
  14972. =>WM: (14097: R1 ^reward R1009)
  14973. =>WM: (14096: I3 ^see 0)
  14974. <=WM: (14087: S1 ^operator O2009 +)
  14975. <=WM: (14088: S1 ^operator O2010 +)
  14976. <=WM: (14089: S1 ^operator O2010)
  14977. <=WM: (14072: I3 ^dir R)
  14978. <=WM: (14083: R1 ^reward R1008)
  14979. <=WM: (14082: I3 ^see 1)
  14980. <=WM: (14086: O2010 ^name predict-no)
  14981. <=WM: (14085: O2009 ^name predict-yes)
  14982. <=WM: (14084: R1008 ^value 1)
  14983. --- Inner Elaboration Phase, active level 1 (S1) ---
  14984. Firing prefer*rvt*predict-yes*H0
  14985. -->
  14986. Firing rl*prefer*rvt*predict-yes*H0*3
  14987. -->
  14988. (S1 ^operator O2011 = 0.)
  14989. Firing prefer*rvt*predict-no*H0
  14990. -->
  14991. Firing rl*prefer*rvt*predict-no*H0*4
  14992. -->
  14993. (S1 ^operator O2012 = 1.)
  14994. inner elaboration loop at bottom goal.
  14995. Retracting rl*prefer*rvt*predict-no*H0*4
  14996. -->
  14997. (S1 ^operator O2010 = 1.)
  14998. Retracting rl*prefer*rvt*predict-yes*H0*3
  14999. -->
  15000. (S1 ^operator O2009 = 0.)
  15001. --- END Proposal Phase ---
  15002. --- Decision Phase ---
  15003. RL update rl*prefer*rvt*predict-no*H0*6 0.837575 0 0.837575 -> 0.863898 0 0.863898(R,m,v=1,0.857955,0.122565)
  15004. =>WM: (14104: S1 ^operator O2012)
  15005. 1006: O: O2012 (predict-no)
  15006. --- END Decision Phase ---
  15007. --- Application Phase ---
  15008. --- Firing Productions (PE) For State At Depth 1 ---
  15009. --- Inner Elaboration Phase, active level 1 (S1) ---
  15010. Firing apply*operator
  15011. -->
  15012. (I3 ^predict-no N1006 + :O )
  15013. Firing apply*operator*complete
  15014. -->
  15015. (I3 ^predict-no N1005 - :O )
  15016. inner elaboration loop at bottom goal.
  15017. --- Change Working Memory (PE) ---
  15018. =>WM: (14105: I3 ^predict-no N1006)
  15019. <=WM: (14091: N1005 ^status complete)
  15020. <=WM: (14090: I3 ^predict-no N1005)
  15021. --- Firing Productions (IE) For State At Depth 1 ---
  15022. --- Inner Elaboration Phase, active level 1 (S1) ---
  15023. Firing monitor*world
  15024. -->
  15025. I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
  15026. --- Change Working Memory (IE) ---
  15027. --- END Application Phase ---
  15028. --- Output Phase ---
  15029. ENV: Agent did: predict-no for direction U in state State-B
  15030. In State-B moving U
  15031. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  15032. predict error 0
  15033. dir: dir isR
  15034. --- END Output Phase ---
  15035. \-/--- Input Phase ---
  15036. =>WM: (14109: I2 ^dir R)
  15037. =>WM: (14108: I2 ^reward 1)
  15038. =>WM: (14107: I2 ^see 0)
  15039. =>WM: (14106: N1006 ^status complete)
  15040. <=WM: (14094: I2 ^dir U)
  15041. <=WM: (14093: I2 ^reward 1)
  15042. <=WM: (14092: I2 ^see 0)
  15043. =>WM: (14110: I2 ^level-1 R0-root)
  15044. <=WM: (14095: I2 ^level-1 R0-root)
  15045. --- END Input Phase ---
  15046. --- Proposal Phase ---
  15047. --- Inner Elaboration Phase, active level 1 (S1) ---
  15048. Firing rl*prefer*rvt*predict-yes*H0*5*H1*11
  15049. -->
  15050. (S1 ^operator O2011 = -0.1422200175486056)
  15051. Firing prefer*rvt*predict-yes*H0*5*H1
  15052. -->
  15053. Firing elaborate*copy-see-to-output-link
  15054. -->
  15055. (I3 ^see 0 +)
  15056. Firing elaborate*reward*based*on*reward
  15057. -->
  15058. (R1010 ^value 1 +)
  15059. (R1 ^reward R1010 +)
  15060. Firing propose*predict-yes
  15061. -->
  15062. (O2013 ^name predict-yes +)
  15063. (S1 ^operator O2013 +)
  15064. Firing propose*predict-no
  15065. -->
  15066. (O2014 ^name predict-no +)
  15067. (S1 ^operator O2014 +)
  15068. Firing rl*prefer*rvt*predict-no*H0*6
  15069. -->
  15070. (S1 ^operator O2012 = 0.8638980310170703)
  15071. Firing rl*prefer*rvt*predict-yes*H0*5
  15072. -->
  15073. (S1 ^operator O2011 = 0.2239230781580192)
  15074. Firing prefer*rvt*predict-yes*H0
  15075. -->
  15076. Firing prefer*rvt*predict-no*H0
  15077. -->
  15078. Firing elaborate*copy-dir-to-output-link
  15079. -->
  15080. (I3 ^dir R +)
  15081. inner elaboration loop at bottom goal.
  15082. Retracting elaborate*copy-see-to-output-link
  15083. -->
  15084. (I3 ^see 0 +)
  15085. Retracting propose*predict-no
  15086. -->
  15087. (O2012 ^name predict-no +)
  15088. (S1 ^operator O2012 +)
  15089. Retracting propose*predict-yes
  15090. -->
  15091. (O2011 ^name predict-yes +)
  15092. (S1 ^operator O2011 +)
  15093. Retracting elaborate*reward*based*on*reward
  15094. -->
  15095. (R1009 ^value 1 +)
  15096. (R1 ^reward R1009 +)
  15097. Retracting elaborate*copy-dir-to-output-link
  15098. -->
  15099. (I3 ^dir U +)
  15100. Retracting rl*prefer*rvt*predict-no*H0*4
  15101. -->
  15102. (S1 ^operator O2012 = 1.)
  15103. Retracting rl*prefer*rvt*predict-yes*H0*3
  15104. -->
  15105. (S1 ^operator O2011 = 0.)
  15106. =>WM: (14117: S1 ^operator O2014 +)
  15107. =>WM: (14116: S1 ^operator O2013 +)
  15108. =>WM: (14115: I3 ^dir R)
  15109. =>WM: (14114: O2014 ^name predict-no)
  15110. =>WM: (14113: O2013 ^name predict-yes)
  15111. =>WM: (14112: R1010 ^value 1)
  15112. =>WM: (14111: R1 ^reward R1010)
  15113. <=WM: (14102: S1 ^operator O2011 +)
  15114. <=WM: (14103: S1 ^operator O2012 +)
  15115. <=WM: (14104: S1 ^operator O2012)
  15116. <=WM: (14101: I3 ^dir U)
  15117. <=WM: (14097: R1 ^reward R1009)
  15118. <=WM: (14100: O2012 ^name predict-no)
  15119. <=WM: (14099: O2011 ^name predict-yes)
  15120. <=WM: (14098: R1009 ^value 1)
  15121. --- Inner Elaboration Phase, active level 1 (S1) ---
  15122. Firing prefer*rvt*predict-yes*H0
  15123. -->
  15124. Firing rl*prefer*rvt*predict-yes*H0*5*H1*11
  15125. -->
  15126. (S1 ^operator O2013 = -0.1422200175486056)
  15127. Firing rl*prefer*rvt*predict-yes*H0*5
  15128. -->
  15129. (S1 ^operator O2013 = 0.2239230781580192)
  15130. Firing prefer*rvt*predict-yes*H0*5*H1
  15131. -->
  15132. Firing prefer*rvt*predict-no*H0
  15133. -->
  15134. Firing rl*prefer*rvt*predict-no*H0*6
  15135. -->
  15136. (S1 ^operator O2014 = 0.8638980310170703)
  15137. inner elaboration loop at bottom goal.
  15138. Retracting rl*prefer*rvt*predict-no*H0*6
  15139. -->
  15140. (S1 ^operator O2012 = 0.8638980310170703)
  15141. Retracting rl*prefer*rvt*predict-yes*H0*5
  15142. -->
  15143. (S1 ^operator O2011 = 0.2239230781580192)
  15144. Retracting rl*prefer*rvt*predict-yes*H0*5*H1*11
  15145. -->
  15146. (S1 ^operator O2011 = -0.1422200175486056)
  15147. --- END Proposal Phase ---
  15148. --- Decision Phase ---
  15149. RL update rl*prefer*rvt*predict-no*H0*4 1 0 1 -> 1 0 1(R,m,v=1,1,0)
  15150. =>WM: (14118: S1 ^operator O2014)
  15151. 1007: O: O2014 (predict-no)
  15152. --- END Decision Phase ---
  15153. --- Application Phase ---
  15154. --- Firing Productions (PE) For State At Depth 1 ---
  15155. --- Inner Elaboration Phase, active level 1 (S1) ---
  15156. Firing apply*operator
  15157. -->
  15158. (I3 ^predict-no N1007 + :O )
  15159. Firing apply*operator*complete
  15160. -->
  15161. (I3 ^predict-no N1006 - :O )
  15162. inner elaboration loop at bottom goal.
  15163. --- Change Working Memory (PE) ---
  15164. =>WM: (14119: I3 ^predict-no N1007)
  15165. <=WM: (14106: N1006 ^status complete)
  15166. <=WM: (14105: I3 ^predict-no N1006)
  15167. --- Firing Productions (IE) For State At Depth 1 ---
  15168. --- Inner Elaboration Phase, active level 1 (S1) ---
  15169. Firing monitor*world
  15170. -->
  15171. I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
  15172. --- Change Working Memory (IE) ---
  15173. --- END Application Phase ---
  15174. --- Output Phase ---
  15175. ENV: Agent did: predict-no for direction R in state State-B
  15176. In State-B moving R
  15177. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  15178. predict error 0
  15179. dir: dir isR
  15180. --- END Output Phase ---
  15181. |\--- Input Phase ---
  15182. =>WM: (14123: I2 ^dir R)
  15183. =>WM: (14122: I2 ^reward 1)
  15184. =>WM: (14121: I2 ^see 0)
  15185. =>WM: (14120: N1007 ^status complete)
  15186. <=WM: (14109: I2 ^dir R)
  15187. <=WM: (14108: I2 ^reward 1)
  15188. <=WM: (14107: I2 ^see 0)
  15189. =>WM: (14124: I2 ^level-1 R0-root)
  15190. <=WM: (14110: I2 ^level-1 R0-root)
  15191. --- END Input Phase ---
  15192. --- Proposal Phase ---
  15193. --- Inner Elaboration Phase, active level 1 (S1) ---
  15194. Firing rl*prefer*rvt*predict-yes*H0*5*H1*11
  15195. -->
  15196. (S1 ^operator O2013 = -0.1422200175486056)
  15197. Firing prefer*rvt*predict-yes*H0*5*H1
  15198. -->
  15199. Firing elaborate*copy-see-to-output-link
  15200. -->
  15201. (I3 ^see 0 +)
  15202. Firing elaborate*reward*based*on*reward
  15203. -->
  15204. (R1011 ^value 1 +)
  15205. (R1 ^reward R1011 +)
  15206. Firing propose*predict-yes
  15207. -->
  15208. (O2015 ^name predict-yes +)
  15209. (S1 ^operator O2015 +)
  15210. Firing propose*predict-no
  15211. -->
  15212. (O2016 ^name predict-no +)
  15213. (S1 ^operator O2016 +)
  15214. Firing rl*prefer*rvt*predict-no*H0*6
  15215. -->
  15216. (S1 ^operator O2014 = 0.8638980310170703)
  15217. Firing rl*prefer*rvt*predict-yes*H0*5
  15218. -->
  15219. (S1 ^operator O2013 = 0.2239230781580192)
  15220. Firing prefer*rvt*predict-yes*H0
  15221. -->
  15222. Firing prefer*rvt*predict-no*H0
  15223. -->
  15224. Firing elaborate*copy-dir-to-output-link
  15225. -->
  15226. (I3 ^dir R +)
  15227. inner elaboration loop at bottom goal.
  15228. Retracting elaborate*copy-see-to-output-link
  15229. -->
  15230. (I3 ^see 0 +)
  15231. Retracting propose*predict-no
  15232. -->
  15233. (O2014 ^name predict-no +)
  15234. (S1 ^operator O2014 +)
  15235. Retracting propose*predict-yes
  15236. -->
  15237. (O2013 ^name predict-yes +)
  15238. (S1 ^operator O2013 +)
  15239. Retracting elaborate*reward*based*on*reward
  15240. -->
  15241. (R1010 ^value 1 +)
  15242. (R1 ^reward R1010 +)
  15243. Retracting elaborate*copy-dir-to-output-link
  15244. -->
  15245. (I3 ^dir R +)
  15246. Retracting rl*prefer*rvt*predict-no*H0*6
  15247. -->
  15248. (S1 ^operator O2014 = 0.8638980310170703)
  15249. Retracting rl*prefer*rvt*predict-yes*H0*5
  15250. -->
  15251. (S1 ^operator O2013 = 0.2239230781580192)
  15252. Retracting rl*prefer*rvt*predict-yes*H0*5*H1*11
  15253. -->
  15254. (S1 ^operator O2013 = -0.1422200175486056)
  15255. =>WM: (14130: S1 ^operator O2016 +)
  15256. =>WM: (14129: S1 ^operator O2015 +)
  15257. =>WM: (14128: O2016 ^name predict-no)
  15258. =>WM: (14127: O2015 ^name predict-yes)
  15259. =>WM: (14126: R1011 ^value 1)
  15260. =>WM: (14125: R1 ^reward R1011)
  15261. <=WM: (14116: S1 ^operator O2013 +)
  15262. <=WM: (14117: S1 ^operator O2014 +)
  15263. <=WM: (14118: S1 ^operator O2014)
  15264. <=WM: (14111: R1 ^reward R1010)
  15265. <=WM: (14114: O2014 ^name predict-no)
  15266. <=WM: (14113: O2013 ^name predict-yes)
  15267. <=WM: (14112: R1010 ^value 1)
  15268. --- Inner Elaboration Phase, active level 1 (S1) ---
  15269. Firing prefer*rvt*predict-yes*H0
  15270. -->
  15271. Firing rl*prefer*rvt*predict-yes*H0*5*H1*11
  15272. -->
  15273. (S1 ^operator O2015 = -0.1422200175486056)
  15274. Firing rl*prefer*rvt*predict-yes*H0*5
  15275. -->
  15276. (S1 ^operator O2015 = 0.2239230781580192)
  15277. Firing prefer*rvt*predict-yes*H0*5*H1
  15278. -->
  15279. Firing prefer*rvt*predict-no*H0
  15280. -->
  15281. Firing rl*prefer*rvt*predict-no*H0*6
  15282. -->
  15283. (S1 ^operator O2016 = 0.8638980310170703)
  15284. inner elaboration loop at bottom goal.
  15285. Retracting rl*prefer*rvt*predict-no*H0*6
  15286. -->
  15287. (S1 ^operator O2014 = 0.8638980310170703)
  15288. Retracting rl*prefer*rvt*predict-yes*H0*5
  15289. -->
  15290. (S1 ^operator O2013 = 0.2239230781580192)
  15291. Retracting rl*prefer*rvt*predict-yes*H0*5*H1*11
  15292. -->
  15293. (S1 ^operator O2013 = -0.1422200175486056)
  15294. --- END Proposal Phase ---
  15295. --- Decision Phase ---
  15296. RL update rl*prefer*rvt*predict-no*H0*6 0.863898 0 0.863898 -> 0.885935 0 0.885935(R,m,v=1,0.858757,0.121983)
  15297. =>WM: (14131: S1 ^operator O2016)
  15298. 1008: O: O2016 (predict-no)
  15299. --- END Decision Phase ---
  15300. --- Application Phase ---
  15301. --- Firing Productions (PE) For State At Depth 1 ---
  15302. --- Inner Elaboration Phase, active level 1 (S1) ---
  15303. Firing apply*operator
  15304. -->
  15305. (I3 ^predict-no N1008 + :O )
  15306. Firing apply*operator*complete
  15307. -->
  15308. (I3 ^predict-no N1007 - :O )
  15309. inner elaboration loop at bottom goal.
  15310. --- Change Working Memory (PE) ---
  15311. =>WM: (14132: I3 ^predict-no N1008)
  15312. <=WM: (14120: N1007 ^status complete)
  15313. <=WM: (14119: I3 ^predict-no N1007)
  15314. --- Firing Productions (IE) For State At Depth 1 ---
  15315. --- Inner Elaboration Phase, active level 1 (S1) ---
  15316. Firing monitor*world
  15317. -->
  15318. I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
  15319. --- Change Working Memory (IE) ---
  15320. --- END Application Phase ---
  15321. --- Output Phase ---
  15322. ENV: Agent did: predict-no for direction R in state State-B
  15323. In State-B moving R
  15324. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  15325. predict error 0
  15326. dir: dir isL
  15327. --- END Output Phase ---
  15328. -/|--- Input Phase ---
  15329. =>WM: (14136: I2 ^dir L)
  15330. =>WM: (14135: I2 ^reward 1)
  15331. =>WM: (14134: I2 ^see 0)
  15332. =>WM: (14133: N1008 ^status complete)
  15333. <=WM: (14123: I2 ^dir R)
  15334. <=WM: (14122: I2 ^reward 1)
  15335. <=WM: (14121: I2 ^see 0)
  15336. =>WM: (14137: I2 ^level-1 R0-root)
  15337. <=WM: (14124: I2 ^level-1 R0-root)
  15338. --- END Input Phase ---
  15339. --- Proposal Phase ---
  15340. --- Inner Elaboration Phase, active level 1 (S1) ---
  15341. Firing rl*prefer*rvt*predict-no*H0*2*H1*12
  15342. -->
  15343. (S1 ^operator O2016 = -0.1359494083332169)
  15344. Firing rl*prefer*rvt*predict-yes*H0*1*H1*13
  15345. -->
  15346. (S1 ^operator O2015 = 0.6500789983179401)
  15347. Firing prefer*rvt*predict-no*H0*2*H1
  15348. -->
  15349. Firing prefer*rvt*predict-yes*H0*1*H1
  15350. -->
  15351. Firing elaborate*copy-see-to-output-link
  15352. -->
  15353. (I3 ^see 0 +)
  15354. Firing elaborate*reward*based*on*reward
  15355. -->
  15356. (R1012 ^value 1 +)
  15357. (R1 ^reward R1012 +)
  15358. Firing propose*predict-yes
  15359. -->
  15360. (O2017 ^name predict-yes +)
  15361. (S1 ^operator O2017 +)
  15362. Firing propose*predict-no
  15363. -->
  15364. (O2018 ^name predict-no +)
  15365. (S1 ^operator O2018 +)
  15366. Firing rl*prefer*rvt*predict-no*H0*2
  15367. -->
  15368. (S1 ^operator O2016 = 0.2381362689441603)
  15369. Firing rl*prefer*rvt*predict-yes*H0*1
  15370. -->
  15371. (S1 ^operator O2015 = 0.3499208630840915)
  15372. Firing prefer*rvt*predict-yes*H0
  15373. -->
  15374. Firing prefer*rvt*predict-no*H0
  15375. -->
  15376. Firing elaborate*copy-dir-to-output-link
  15377. -->
  15378. (I3 ^dir L +)
  15379. inner elaboration loop at bottom goal.
  15380. Retracting elaborate*copy-see-to-output-link
  15381. -->
  15382. (I3 ^see 0 +)
  15383. Retracting propose*predict-no
  15384. -->
  15385. (O2016 ^name predict-no +)
  15386. (S1 ^operator O2016 +)
  15387. Retracting propose*predict-yes
  15388. -->
  15389. (O2015 ^name predict-yes +)
  15390. (S1 ^operator O2015 +)
  15391. Retracting elaborate*reward*based*on*reward
  15392. -->
  15393. (R1011 ^value 1 +)
  15394. (R1 ^reward R1011 +)
  15395. Retracting elaborate*copy-dir-to-output-link
  15396. -->
  15397. (I3 ^dir R +)
  15398. Retracting rl*prefer*rvt*predict-no*H0*6
  15399. -->
  15400. (S1 ^operator O2016 = 0.8859347326639087)
  15401. Retracting rl*prefer*rvt*predict-yes*H0*5
  15402. -->
  15403. (S1 ^operator O2015 = 0.2239230781580192)
  15404. Retracting rl*prefer*rvt*predict-yes*H0*5*H1*11
  15405. -->
  15406. (S1 ^operator O2015 = -0.1422200175486056)
  15407. =>WM: (14144: S1 ^operator O2018 +)
  15408. =>WM: (14143: S1 ^operator O2017 +)
  15409. =>WM: (14142: I3 ^dir L)
  15410. =>WM: (14141: O2018 ^name predict-no)
  15411. =>WM: (14140: O2017 ^name predict-yes)
  15412. =>WM: (14139: R1012 ^value 1)
  15413. =>WM: (14138: R1 ^reward R1012)
  15414. <=WM: (14129: S1 ^operator O2015 +)
  15415. <=WM: (14130: S1 ^operator O2016 +)
  15416. <=WM: (14131: S1 ^operator O2016)
  15417. <=WM: (14115: I3 ^dir R)
  15418. <=WM: (14125: R1 ^reward R1011)
  15419. <=WM: (14128: O2016 ^name predict-no)
  15420. <=WM: (14127: O2015 ^name predict-yes)
  15421. <=WM: (14126: R1011 ^value 1)
  15422. --- Inner Elaboration Phase, active level 1 (S1) ---
  15423. Firing prefer*rvt*predict-yes*H0
  15424. -->
  15425. Firing rl*prefer*rvt*predict-yes*H0*1*H1*13
  15426. -->
  15427. (S1 ^operator O2017 = 0.6500789983179401)
  15428. Firing rl*prefer*rvt*predict-yes*H0*1
  15429. -->
  15430. (S1 ^operator O2017 = 0.3499208630840915)
  15431. Firing prefer*rvt*predict-yes*H0*1*H1
  15432. -->
  15433. Firing prefer*rvt*predict-no*H0
  15434. -->
  15435. Firing rl*prefer*rvt*predict-no*H0*2*H1*12
  15436. -->
  15437. (S1 ^operator O2018 = -0.1359494083332169)
  15438. Firing rl*prefer*rvt*predict-no*H0*2
  15439. -->
  15440. (S1 ^operator O2018 = 0.2381362689441603)
  15441. Firing prefer*rvt*predict-no*H0*2*H1
  15442. -->
  15443. inner elaboration loop at bottom goal.
  15444. Retracting rl*prefer*rvt*predict-no*H0*2
  15445. -->
  15446. (S1 ^operator O2016 = 0.2381362689441603)
  15447. Retracting rl*prefer*rvt*predict-no*H0*2*H1*12
  15448. -->
  15449. (S1 ^operator O2016 = -0.1359494083332169)
  15450. Retracting rl*prefer*rvt*predict-yes*H0*1
  15451. -->
  15452. (S1 ^operator O2015 = 0.3499208630840915)
  15453. Retracting rl*prefer*rvt*predict-yes*H0*1*H1*13
  15454. -->
  15455. (S1 ^operator O2015 = 0.6500789983179401)
  15456. --- END Proposal Phase ---
  15457. --- Decision Phase ---
  15458. RL update rl*prefer*rvt*predict-no*H0*6 0.885935 0 0.885935 -> 0.904387 0 0.904387(R,m,v=1,0.859551,0.121405)
  15459. =>WM: (14145: S1 ^operator O2017)
  15460. 1009: O: O2017 (predict-yes)
  15461. --- END Decision Phase ---
  15462. --- Application Phase ---
  15463. --- Firing Productions (PE) For State At Depth 1 ---
  15464. --- Inner Elaboration Phase, active level 1 (S1) ---
  15465. Firing apply*operator
  15466. -->
  15467. (I3 ^predict-yes N1009 + :O )
  15468. Firing apply*operator*complete
  15469. -->
  15470. (I3 ^predict-no N1008 - :O )
  15471. inner elaboration loop at bottom goal.
  15472. --- Change Working Memory (PE) ---
  15473. =>WM: (14146: I3 ^predict-yes N1009)
  15474. <=WM: (14133: N1008 ^status complete)
  15475. <=WM: (14132: I3 ^predict-no N1008)
  15476. --- Firing Productions (IE) For State At Depth 1 ---
  15477. --- Inner Elaboration Phase, active level 1 (S1) ---
  15478. Firing monitor*world
  15479. -->
  15480. I see 1 and I'm going to do: predict-yes inner elaboration loop at bottom goal.
  15481. --- Change Working Memory (IE) ---
  15482. --- END Application Phase ---
  15483. --- Output Phase ---
  15484. ENV: Agent did: predict-yes for direction L in state State-B
  15485. In State-B moving L
  15486. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  15487. predict error 0
  15488. dir: dir isR
  15489. --- END Output Phase ---
  15490. \-/--- Input Phase ---
  15491. =>WM: (14150: I2 ^dir R)
  15492. =>WM: (14149: I2 ^reward 1)
  15493. =>WM: (14148: I2 ^see 1)
  15494. =>WM: (14147: N1009 ^status complete)
  15495. <=WM: (14136: I2 ^dir L)
  15496. <=WM: (14135: I2 ^reward 1)
  15497. <=WM: (14134: I2 ^see 0)
  15498. =>WM: (14151: I2 ^level-1 L1-root)
  15499. <=WM: (14137: I2 ^level-1 R0-root)
  15500. --- END Input Phase ---
  15501. --- Proposal Phase ---
  15502. --- Inner Elaboration Phase, active level 1 (S1) ---
  15503. Firing rl*prefer*rvt*predict-yes*H0*5*H1*9
  15504. -->
  15505. (S1 ^operator O2017 = 0.7761695158811823)
  15506. Firing prefer*rvt*predict-yes*H0*5*H1
  15507. -->
  15508. Firing elaborate*copy-see-to-output-link
  15509. -->
  15510. (I3 ^see 1 +)
  15511. Firing elaborate*reward*based*on*reward
  15512. -->
  15513. (R1013 ^value 1 +)
  15514. (R1 ^reward R1013 +)
  15515. Firing propose*predict-yes
  15516. -->
  15517. (O2019 ^name predict-yes +)
  15518. (S1 ^operator O2019 +)
  15519. Firing propose*predict-no
  15520. -->
  15521. (O2020 ^name predict-no +)
  15522. (S1 ^operator O2020 +)
  15523. Firing rl*prefer*rvt*predict-no*H0*6
  15524. -->
  15525. (S1 ^operator O2018 = 0.9043865704560459)
  15526. Firing rl*prefer*rvt*predict-yes*H0*5
  15527. -->
  15528. (S1 ^operator O2017 = 0.2239230781580192)
  15529. Firing prefer*rvt*predict-yes*H0
  15530. -->
  15531. Firing prefer*rvt*predict-no*H0
  15532. -->
  15533. Firing elaborate*copy-dir-to-output-link
  15534. -->
  15535. (I3 ^dir R +)
  15536. inner elaboration loop at bottom goal.
  15537. Retracting elaborate*copy-see-to-output-link
  15538. -->
  15539. (I3 ^see 0 +)
  15540. Retracting propose*predict-no
  15541. -->
  15542. (O2018 ^name predict-no +)
  15543. (S1 ^operator O2018 +)
  15544. Retracting propose*predict-yes
  15545. -->
  15546. (O2017 ^name predict-yes +)
  15547. (S1 ^operator O2017 +)
  15548. Retracting elaborate*reward*based*on*reward
  15549. -->
  15550. (R1012 ^value 1 +)
  15551. (R1 ^reward R1012 +)
  15552. Retracting elaborate*copy-dir-to-output-link
  15553. -->
  15554. (I3 ^dir L +)
  15555. Retracting rl*prefer*rvt*predict-no*H0*2
  15556. -->
  15557. (S1 ^operator O2018 = 0.2381362689441603)
  15558. Retracting rl*prefer*rvt*predict-no*H0*2*H1*12
  15559. -->
  15560. (S1 ^operator O2018 = -0.1359494083332169)
  15561. Retracting rl*prefer*rvt*predict-yes*H0*1
  15562. -->
  15563. (S1 ^operator O2017 = 0.3499208630840915)
  15564. Retracting rl*prefer*rvt*predict-yes*H0*1*H1*13
  15565. -->
  15566. (S1 ^operator O2017 = 0.6500789983179401)
  15567. =>WM: (14159: S1 ^operator O2020 +)
  15568. =>WM: (14158: S1 ^operator O2019 +)
  15569. =>WM: (14157: I3 ^dir R)
  15570. =>WM: (14156: O2020 ^name predict-no)
  15571. =>WM: (14155: O2019 ^name predict-yes)
  15572. =>WM: (14154: R1013 ^value 1)
  15573. =>WM: (14153: R1 ^reward R1013)
  15574. =>WM: (14152: I3 ^see 1)
  15575. <=WM: (14143: S1 ^operator O2017 +)
  15576. <=WM: (14145: S1 ^operator O2017)
  15577. <=WM: (14144: S1 ^operator O2018 +)
  15578. <=WM: (14142: I3 ^dir L)
  15579. <=WM: (14138: R1 ^reward R1012)
  15580. <=WM: (14096: I3 ^see 0)
  15581. <=WM: (14141: O2018 ^name predict-no)
  15582. <=WM: (14140: O2017 ^name predict-yes)
  15583. <=WM: (14139: R1012 ^value 1)
  15584. --- Inner Elaboration Phase, active level 1 (S1) ---
  15585. Firing prefer*rvt*predict-yes*H0
  15586. -->
  15587. Firing rl*prefer*rvt*predict-yes*H0*5
  15588. -->
  15589. (S1 ^operator O2019 = 0.2239230781580192)
  15590. Firing prefer*rvt*predict-yes*H0*5*H1
  15591. -->
  15592. Firing rl*prefer*rvt*predict-yes*H0*5*H1*9
  15593. -->
  15594. (S1 ^operator O2019 = 0.7761695158811823)
  15595. Firing prefer*rvt*predict-no*H0
  15596. -->
  15597. Firing rl*prefer*rvt*predict-no*H0*6
  15598. -->
  15599. (S1 ^operator O2020 = 0.9043865704560459)
  15600. inner elaboration loop at bottom goal.
  15601. Retracting rl*prefer*rvt*predict-no*H0*6
  15602. -->
  15603. (S1 ^operator O2018 = 0.9043865704560459)
  15604. Retracting rl*prefer*rvt*predict-yes*H0*5
  15605. -->
  15606. (S1 ^operator O2017 = 0.2239230781580192)
  15607. Retracting rl*prefer*rvt*predict-yes*H0*5*H1*9
  15608. -->
  15609. (S1 ^operator O2017 = 0.7761695158811823)
  15610. --- END Proposal Phase ---
  15611. --- Decision Phase ---
  15612. RL update rl*prefer*rvt*predict-yes*H0*1 0.407928 -0.0580076 0.349921 -> 0.407928 -0.0580074 0.349921(R,m,v=1,0.903846,0.087469)
  15613. RL update rl*prefer*rvt*predict-yes*H0*1*H1*13 0.592074 0.0580046 0.650079 -> 0.592074 0.0580049 0.650079(R,m,v=1,1,0)
  15614. =>WM: (14160: S1 ^operator O2019)
  15615. 1010: O: O2019 (predict-yes)
  15616. --- END Decision Phase ---
  15617. --- Application Phase ---
  15618. --- Firing Productions (PE) For State At Depth 1 ---
  15619. --- Inner Elaboration Phase, active level 1 (S1) ---
  15620. Firing apply*operator
  15621. -->
  15622. (I3 ^predict-yes N1010 + :O )
  15623. Firing apply*operator*complete
  15624. -->
  15625. (I3 ^predict-yes N1009 - :O )
  15626. inner elaboration loop at bottom goal.
  15627. --- Change Working Memory (PE) ---
  15628. =>WM: (14161: I3 ^predict-yes N1010)
  15629. <=WM: (14147: N1009 ^status complete)
  15630. <=WM: (14146: I3 ^predict-yes N1009)
  15631. --- Firing Productions (IE) For State At Depth 1 ---
  15632. --- Inner Elaboration Phase, active level 1 (S1) ---
  15633. Firing monitor*world
  15634. -->
  15635. I see 1 and I'm going to do: predict-yes inner elaboration loop at bottom goal.
  15636. --- Change Working Memory (IE) ---
  15637. --- END Application Phase ---
  15638. --- Output Phase ---
  15639. ENV: Agent did: predict-yes for direction R in state State-A
  15640. In State-A moving R
  15641. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  15642. predict error 0
  15643. dir: dir isL
  15644. --- END Output Phase ---
  15645. |\---- Input Phase ---
  15646. =>WM: (14165: I2 ^dir L)
  15647. =>WM: (14164: I2 ^reward 1)
  15648. =>WM: (14163: I2 ^see 1)
  15649. =>WM: (14162: N1010 ^status complete)
  15650. <=WM: (14150: I2 ^dir R)
  15651. <=WM: (14149: I2 ^reward 1)
  15652. <=WM: (14148: I2 ^see 1)
  15653. =>WM: (14166: I2 ^level-1 R1-root)
  15654. <=WM: (14151: I2 ^level-1 L1-root)
  15655. --- END Input Phase ---
  15656. --- Proposal Phase ---
  15657. --- Inner Elaboration Phase, active level 1 (S1) ---
  15658. Firing rl*prefer*rvt*predict-no*H0*2*H1*8
  15659. -->
  15660. (S1 ^operator O2020 = -0.1970449706966682)
  15661. Firing rl*prefer*rvt*predict-yes*H0*1*H1*7
  15662. -->
  15663. (S1 ^operator O2019 = 0.650079249377991)
  15664. Firing prefer*rvt*predict-no*H0*2*H1
  15665. -->
  15666. Firing prefer*rvt*predict-yes*H0*1*H1
  15667. -->
  15668. Firing elaborate*copy-see-to-output-link
  15669. -->
  15670. (I3 ^see 1 +)
  15671. Firing elaborate*reward*based*on*reward
  15672. -->
  15673. (R1014 ^value 1 +)
  15674. (R1 ^reward R1014 +)
  15675. Firing propose*predict-yes
  15676. -->
  15677. (O2021 ^name predict-yes +)
  15678. (S1 ^operator O2021 +)
  15679. Firing propose*predict-no
  15680. -->
  15681. (O2022 ^name predict-no +)
  15682. (S1 ^operator O2022 +)
  15683. Firing rl*prefer*rvt*predict-no*H0*2
  15684. -->
  15685. (S1 ^operator O2020 = 0.2381362689441603)
  15686. Firing rl*prefer*rvt*predict-yes*H0*1
  15687. -->
  15688. (S1 ^operator O2019 = 0.3499208745387417)
  15689. Firing prefer*rvt*predict-yes*H0
  15690. -->
  15691. Firing prefer*rvt*predict-no*H0
  15692. -->
  15693. Firing elaborate*copy-dir-to-output-link
  15694. -->
  15695. (I3 ^dir L +)
  15696. inner elaboration loop at bottom goal.
  15697. Retracting elaborate*copy-see-to-output-link
  15698. -->
  15699. (I3 ^see 1 +)
  15700. Retracting propose*predict-no
  15701. -->
  15702. (O2020 ^name predict-no +)
  15703. (S1 ^operator O2020 +)
  15704. Retracting propose*predict-yes
  15705. -->
  15706. (O2019 ^name predict-yes +)
  15707. (S1 ^operator O2019 +)
  15708. Retracting elaborate*reward*based*on*reward
  15709. -->
  15710. (R1013 ^value 1 +)
  15711. (R1 ^reward R1013 +)
  15712. Retracting elaborate*copy-dir-to-output-link
  15713. -->
  15714. (I3 ^dir R +)
  15715. Retracting rl*prefer*rvt*predict-no*H0*6
  15716. -->
  15717. (S1 ^operator O2020 = 0.9043865704560459)
  15718. Retracting rl*prefer*rvt*predict-yes*H0*5*H1*9
  15719. -->
  15720. (S1 ^operator O2019 = 0.7761695158811823)
  15721. Retracting rl*prefer*rvt*predict-yes*H0*5
  15722. -->
  15723. (S1 ^operator O2019 = 0.2239230781580192)
  15724. =>WM: (14173: S1 ^operator O2022 +)
  15725. =>WM: (14172: S1 ^operator O2021 +)
  15726. =>WM: (14171: I3 ^dir L)
  15727. =>WM: (14170: O2022 ^name predict-no)
  15728. =>WM: (14169: O2021 ^name predict-yes)
  15729. =>WM: (14168: R1014 ^value 1)
  15730. =>WM: (14167: R1 ^reward R1014)
  15731. <=WM: (14158: S1 ^operator O2019 +)
  15732. <=WM: (14160: S1 ^operator O2019)
  15733. <=WM: (14159: S1 ^operator O2020 +)
  15734. <=WM: (14157: I3 ^dir R)
  15735. <=WM: (14153: R1 ^reward R1013)
  15736. <=WM: (14156: O2020 ^name predict-no)
  15737. <=WM: (14155: O2019 ^name predict-yes)
  15738. <=WM: (14154: R1013 ^value 1)
  15739. --- Inner Elaboration Phase, active level 1 (S1) ---
  15740. Firing prefer*rvt*predict-yes*H0
  15741. -->
  15742. Firing rl*prefer*rvt*predict-yes*H0*1
  15743. -->
  15744. (S1 ^ope