PageRenderTime 143ms CodeModel.GetById 22ms RepoModel.GetById 0ms app.codeStats 1ms

/flipv2/20121112-101138-2.5K-ReLST-Evan/stdout-flip-2.5K_0.txt

https://bitbucket.org/evan13579b/soar-ziggurat
Plain Text | 16520 lines | 15742 code | 778 blank | 0 comment | 0 complexity | ced40955f45f159289b4215de1fd8824 MD5 | raw file
Possible License(s): BSD-3-Clause
  1. Seeding... 0
  2. dir: dir isU
  3. Python-Soar Flip environment.
  4. To accept commands from an external sml process, you'll need to
  5. type 'slave <log file> <n decisons>' at the prompt...
  6. sourcing 'flip_predict.soar'
  7. ***********
  8. Total: 11 productions sourced.
  9. seeding Soar with 0 ...
  10. soar> Entering slave mode:
  11. - log file 'rl-slave-2.5K_0.log'....
  12. - will exit slave mode after 2500 decisions
  13. waiting for commands from an externally connected sml process...
  14. -/|sleeping...
  15. \sleeping...
  16. -sleeping...
  17. /sleeping...
  18. |sleeping...
  19. \-/|\-/|\sleeping...
  20. -/|\-/|sleeping...
  21. \1: O: O1 (predict-yes)
  22. I see 0 and I'm going to do: predict-yes
  23. ENV: Agent did: predict-yes for direction U in state State-A
  24. In State-A moving U
  25. ENV: (next state, see, prediction correct?) = (State-A, 0, False)
  26. predict error 1
  27. dir: dir isU
  28. rule alias: '*'
  29. rule alias: '*'
  30. -/|\-/|\2: O: O4 (predict-no)
  31. I see 0 and I'm going to do: predict-no
  32. ENV: Agent did: predict-no for direction U in state State-A
  33. In State-A moving U
  34. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  35. predict error 0
  36. dir: dir isR
  37. -/|3: O: O5 (predict-yes)
  38. I see 1 and I'm going to do: predict-yes
  39. ENV: Agent did: predict-yes for direction R in state State-A
  40. In State-A moving R
  41. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  42. predict error 0
  43. dir: dir isL
  44. \-/4: O: O7 (predict-yes)
  45. I see 1 and I'm going to do: predict-yes
  46. ENV: Agent did: predict-yes for direction L in state State-B
  47. In State-B moving L
  48. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  49. predict error 0
  50. dir: dir isR
  51. |\-5: O: O9 (predict-yes)
  52. I see 1 and I'm going to do: predict-yes
  53. ENV: Agent did: predict-yes for direction R in state State-A
  54. In State-A moving R
  55. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  56. predict error 0
  57. dir: dir isR
  58. /|\6: O: O11 (predict-yes)
  59. I see 1 and I'm going to do: predict-yes
  60. ENV: Agent did: predict-yes for direction R in state State-B
  61. In State-B moving R
  62. ENV: (next state, see, prediction correct?) = (State-B, 0, False)
  63. predict error 1
  64. dir: dir isU
  65. -/|7: O: O14 (predict-no)
  66. I see 0 and I'm going to do: predict-no
  67. ENV: Agent did: predict-no for direction U in state State-B
  68. In State-B moving U
  69. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  70. predict error 0
  71. dir: dir isL
  72. \-/8: O: O15 (predict-yes)
  73. I see 1 and I'm going to do: predict-yes
  74. ENV: Agent did: predict-yes for direction L in state State-B
  75. In State-B moving L
  76. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  77. predict error 0
  78. dir: dir isR
  79. |\9: O: O17 (predict-yes)
  80. I see 1 and I'm going to do: predict-yes
  81. ENV: Agent did: predict-yes for direction R in state State-A
  82. In State-A moving R
  83. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  84. predict error 0
  85. dir: dir isR
  86. -10: O: O19 (predict-yes)
  87. I see 1 and I'm going to do: predict-yes
  88. ENV: Agent did: predict-yes for direction R in state State-B
  89. In State-B moving R
  90. ENV: (next state, see, prediction correct?) = (State-B, 0, False)
  91. predict error 1
  92. dir: dir isU
  93. /|\11: O: O22 (predict-no)
  94. I see 0 and I'm going to do: predict-no
  95. ENV: Agent did: predict-no for direction U in state State-B
  96. In State-B moving U
  97. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  98. predict error 0
  99. dir: dir isR
  100. rule alias: '*'
  101. rule alias: '*'
  102. rule alias: '*'
  103. rule alias: '*'
  104. -12: O: O24 (predict-no)
  105. I see 1 and I'm going to do: predict-no
  106. ENV: Agent did: predict-no for direction R in state State-B
  107. In State-B moving R
  108. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  109. predict error 0
  110. dir: dir isL
  111. /|\13: O: O26 (predict-no)
  112. I see 1 and I'm going to do: predict-no
  113. ENV: Agent did: predict-no for direction L in state State-B
  114. In State-B moving L
  115. ENV: (next state, see, prediction correct?) = (State-A, 1, False)
  116. predict error 1
  117. dir: dir isU
  118. -/|14: O: O28 (predict-no)
  119. I see 0 and I'm going to do: predict-no
  120. ENV: Agent did: predict-no for direction U in state State-A
  121. In State-A moving U
  122. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  123. predict error 0
  124. dir: dir isR
  125. \-/15: O: O30 (predict-no)
  126. I see 1 and I'm going to do: predict-no
  127. ENV: Agent did: predict-no for direction R in state State-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 isL
  132. |\-16: O: O31 (predict-yes)
  133. I see 0 and I'm going to do: predict-yes
  134. ENV: Agent did: predict-yes for direction L in state State-B
  135. In State-B moving L
  136. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  137. predict error 0
  138. dir: dir isU
  139. /|\17: O: O34 (predict-no)
  140. I see 1 and I'm going to do: predict-no
  141. ENV: Agent did: predict-no for direction U in state State-A
  142. In State-A moving U
  143. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  144. predict error 0
  145. dir: dir isU
  146. -/|18: O: O36 (predict-no)
  147. I see 1 and I'm going to do: predict-no
  148. ENV: Agent did: predict-no for direction U in state State-A
  149. In State-A moving U
  150. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  151. predict error 0
  152. dir: dir isU
  153. \-/19: O: O38 (predict-no)
  154. I see 1 and I'm going to do: predict-no
  155. ENV: Agent did: predict-no for direction U in state State-A
  156. In State-A moving U
  157. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  158. predict error 0
  159. dir: dir isU
  160. |\-20: O: O40 (predict-no)
  161. I see 1 and I'm going to do: predict-no
  162. ENV: Agent did: predict-no for direction U in state State-A
  163. In State-A moving U
  164. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  165. predict error 0
  166. dir: dir isL
  167. /|\21: O: O41 (predict-yes)
  168. I see 1 and I'm going to do: predict-yes
  169. ENV: Agent did: predict-yes for direction L in state State-A
  170. In State-A moving L
  171. ENV: (next state, see, prediction correct?) = (State-A, 0, False)
  172. predict error 1
  173. dir: dir isU
  174. -22: O: O44 (predict-no)
  175. I see 0 and I'm going to do: predict-no
  176. ENV: Agent did: predict-no for direction U in state State-A
  177. In State-A moving U
  178. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  179. predict error 0
  180. dir: dir isU
  181. /|\23: O: O46 (predict-no)
  182. I see 1 and I'm going to do: predict-no
  183. ENV: Agent did: predict-no for direction U in state State-A
  184. In State-A moving U
  185. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  186. predict error 0
  187. dir: dir isU
  188. -/|24: O: O48 (predict-no)
  189. I see 1 and I'm going to do: predict-no
  190. ENV: Agent did: predict-no for direction U in state State-A
  191. In State-A moving U
  192. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  193. predict error 0
  194. dir: dir isR
  195. \-25: O: O50 (predict-no)
  196. I see 1 and I'm going to do: predict-no
  197. ENV: Agent did: predict-no for direction R in state State-A
  198. In State-A moving R
  199. ENV: (next state, see, prediction correct?) = (State-B, 1, False)
  200. predict error 1
  201. dir: dir isL
  202. /|\26: O: O51 (predict-yes)
  203. I see 0 and I'm going to do: predict-yes
  204. ENV: Agent did: predict-yes for direction L in state State-B
  205. In State-B moving L
  206. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  207. predict error 0
  208. dir: dir isR
  209. -/|27: O: O53 (predict-yes)
  210. I see 1 and I'm going to do: predict-yes
  211. ENV: Agent did: predict-yes for direction R in state State-A
  212. In State-A moving R
  213. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  214. predict error 0
  215. dir: dir isR
  216. \-28: O: O55 (predict-yes)
  217. I see 1 and I'm going to do: predict-yes
  218. ENV: Agent did: predict-yes for direction R in state State-B
  219. In State-B moving R
  220. ENV: (next state, see, prediction correct?) = (State-B, 0, False)
  221. predict error 1
  222. dir: dir isU
  223. /|\29: O: O57 (predict-yes)
  224. I see 0 and I'm going to do: predict-yes
  225. ENV: Agent did: predict-yes for direction U in state State-B
  226. In State-B moving U
  227. ENV: (next state, see, prediction correct?) = (State-B, 0, False)
  228. predict error 1
  229. dir: dir isU
  230. -/|30: O: O60 (predict-no)
  231. I see 0 and I'm going to do: predict-no
  232. ENV: Agent did: predict-no for direction U in state State-B
  233. In State-B moving U
  234. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  235. predict error 0
  236. dir: dir isR
  237. \-/31: O: O61 (predict-yes)
  238. I see 1 and I'm going to do: predict-yes
  239. ENV: Agent did: predict-yes for direction R in state State-B
  240. In State-B moving R
  241. ENV: (next state, see, prediction correct?) = (State-B, 0, False)
  242. predict error 1
  243. dir: dir isU
  244. |32: O: O64 (predict-no)
  245. I see 0 and I'm going to do: predict-no
  246. ENV: Agent did: predict-no for direction U in state State-B
  247. In State-B moving U
  248. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  249. predict error 0
  250. dir: dir isL
  251. \-/33: O: O65 (predict-yes)
  252. I see 1 and I'm going to do: predict-yes
  253. ENV: Agent did: predict-yes for direction L in state State-B
  254. In State-B moving L
  255. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  256. predict error 0
  257. dir: dir isU
  258. |\-34: O: O68 (predict-no)
  259. I see 1 and I'm going to do: predict-no
  260. ENV: Agent did: predict-no for direction U in state State-A
  261. In State-A moving U
  262. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  263. predict error 0
  264. dir: dir isR
  265. /|\35: O: O69 (predict-yes)
  266. I see 1 and I'm going to do: predict-yes
  267. ENV: Agent did: predict-yes for direction R in state State-A
  268. In State-A moving R
  269. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  270. predict error 0
  271. dir: dir isL
  272. -/|36: O: O71 (predict-yes)
  273. I see 1 and I'm going to do: predict-yes
  274. ENV: Agent did: predict-yes for direction L in state State-B
  275. In State-B moving L
  276. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  277. predict error 0
  278. dir: dir isU
  279. \-/37: O: O74 (predict-no)
  280. I see 1 and I'm going to do: predict-no
  281. ENV: Agent did: predict-no for direction U in state State-A
  282. In State-A moving U
  283. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  284. predict error 0
  285. dir: dir isR
  286. |\38: O: O75 (predict-yes)
  287. I see 1 and I'm going to do: predict-yes
  288. ENV: Agent did: predict-yes for direction R in state State-A
  289. In State-A moving R
  290. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  291. predict error 0
  292. dir: dir isU
  293. -/|39: O: O77 (predict-yes)
  294. I see 1 and I'm going to do: predict-yes
  295. ENV: Agent did: predict-yes for direction U in state State-B
  296. In State-B moving U
  297. ENV: (next state, see, prediction correct?) = (State-B, 0, False)
  298. predict error 1
  299. dir: dir isU
  300. \-/40: O: O80 (predict-no)
  301. I see 0 and I'm going to do: predict-no
  302. ENV: Agent did: predict-no for direction U in state State-B
  303. In State-B moving U
  304. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  305. predict error 0
  306. dir: dir isL
  307. |\-41: O: O81 (predict-yes)
  308. I see 1 and I'm going to do: predict-yes
  309. ENV: Agent did: predict-yes for direction L in state State-B
  310. In State-B moving L
  311. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  312. predict error 0
  313. dir: dir isR
  314. /42: O: O83 (predict-yes)
  315. I see 1 and I'm going to do: predict-yes
  316. ENV: Agent did: predict-yes for direction R in state State-A
  317. In State-A moving R
  318. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  319. predict error 0
  320. dir: dir isU
  321. |\43: O: O86 (predict-no)
  322. I see 1 and I'm going to do: predict-no
  323. ENV: Agent did: predict-no for direction U in state State-B
  324. In State-B moving U
  325. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  326. predict error 0
  327. dir: dir isL
  328. -/44: O: O87 (predict-yes)
  329. I see 1 and I'm going to do: predict-yes
  330. ENV: Agent did: predict-yes for direction L in state State-B
  331. In State-B moving L
  332. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  333. predict error 0
  334. dir: dir isL
  335. |\-45: O: O89 (predict-yes)
  336. I see 1 and I'm going to do: predict-yes
  337. ENV: Agent did: predict-yes for direction L in state State-A
  338. In State-A moving L
  339. ENV: (next state, see, prediction correct?) = (State-A, 0, False)
  340. predict error 1
  341. dir: dir isU
  342. /|\46: O: O92 (predict-no)
  343. I see 0 and I'm going to do: predict-no
  344. ENV: Agent did: predict-no for direction U in state State-A
  345. In State-A moving U
  346. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  347. predict error 0
  348. dir: dir isL
  349. -/|47: O: O93 (predict-yes)
  350. I see 1 and I'm going to do: predict-yes
  351. ENV: Agent did: predict-yes for direction L in state State-A
  352. In State-A moving L
  353. ENV: (next state, see, prediction correct?) = (State-A, 0, False)
  354. predict error 1
  355. dir: dir isR
  356. \-/48: O: O96 (predict-no)
  357. I see 0 and I'm going to do: predict-no
  358. ENV: Agent did: predict-no for direction R in state State-A
  359. In State-A moving R
  360. ENV: (next state, see, prediction correct?) = (State-B, 1, False)
  361. predict error 1
  362. dir: dir isL
  363. |\-49: O: O97 (predict-yes)
  364. I see 0 and I'm going to do: predict-yes
  365. ENV: Agent did: predict-yes for direction L in state State-B
  366. In State-B moving L
  367. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  368. predict error 0
  369. dir: dir isU
  370. /|\50: O: O100 (predict-no)
  371. I see 1 and I'm going to do: predict-no
  372. ENV: Agent did: predict-no for direction U in state State-A
  373. In State-A moving U
  374. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  375. predict error 0
  376. dir: dir isU
  377. -/|\-/|sleeping...
  378. \sleeping...
  379. -51: O: O102 (predict-no)
  380. I see 1 and I'm going to do: predict-no
  381. ENV: Agent did: predict-no for direction U in state State-A
  382. In State-A moving U
  383. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  384. predict error 0
  385. dir: dir isR
  386. /52: O: O104 (predict-no)
  387. I see 1 and I'm going to do: predict-no
  388. ENV: Agent did: predict-no for direction R in state State-A
  389. In State-A moving R
  390. ENV: (next state, see, prediction correct?) = (State-B, 1, False)
  391. predict error 1
  392. dir: dir isL
  393. |\-53: O: O106 (predict-no)
  394. I see 0 and I'm going to do: predict-no
  395. ENV: Agent did: predict-no for direction L in state State-B
  396. In State-B moving L
  397. ENV: (next state, see, prediction correct?) = (State-A, 1, False)
  398. predict error 1
  399. dir: dir isL
  400. /|\54: O: O107 (predict-yes)
  401. I see 0 and I'm going to do: predict-yes
  402. ENV: Agent did: predict-yes for direction L in state State-A
  403. In State-A moving L
  404. ENV: (next state, see, prediction correct?) = (State-A, 0, False)
  405. predict error 1
  406. dir: dir isR
  407. -/55: O: O109 (predict-yes)
  408. I see 0 and I'm going to do: predict-yes
  409. ENV: Agent did: predict-yes for direction R in state State-A
  410. In State-A moving R
  411. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  412. predict error 0
  413. dir: dir isU
  414. |\-56: O: O112 (predict-no)
  415. I see 1 and I'm going to do: predict-no
  416. ENV: Agent did: predict-no for direction U in state State-B
  417. In State-B moving U
  418. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  419. predict error 0
  420. dir: dir isL
  421. /|\57: O: O114 (predict-no)
  422. I see 1 and I'm going to do: predict-no
  423. ENV: Agent did: predict-no for direction L in state State-B
  424. In State-B moving L
  425. ENV: (next state, see, prediction correct?) = (State-A, 1, False)
  426. predict error 1
  427. dir: dir isR
  428. -/|\58: O: O115 (predict-yes)
  429. I see 0 and I'm going to do: predict-yes
  430. ENV: Agent did: predict-yes for direction R in state State-A
  431. In State-A moving R
  432. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  433. predict error 0
  434. dir: dir isU
  435. -59: O: O118 (predict-no)
  436. I see 1 and I'm going to do: predict-no
  437. ENV: Agent did: predict-no for direction U in state State-B
  438. In State-B moving U
  439. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  440. predict error 0
  441. dir: dir isR
  442. /|60: O: O119 (predict-yes)
  443. I see 1 and I'm going to do: predict-yes
  444. ENV: Agent did: predict-yes for direction R in state State-B
  445. In State-B moving R
  446. ENV: (next state, see, prediction correct?) = (State-B, 0, False)
  447. predict error 1
  448. dir: dir isU
  449. \-61: O: O122 (predict-no)
  450. I see 0 and I'm going to do: predict-no
  451. ENV: Agent did: predict-no for direction U in state State-B
  452. In State-B moving U
  453. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  454. predict error 0
  455. dir: dir isR
  456. rule alias: '*'
  457. rule alias: '*'
  458. rule alias: '*'
  459. rule alias: '*'
  460. rule alias: '*'
  461. rule alias: '*'
  462. rule alias: '*'
  463. rule alias: '*'
  464. rule alias: '*'
  465. rule alias: '*'
  466. rule alias: '*'
  467. /62: O: O123 (predict-yes)
  468. I see 1 and I'm going to do: predict-yes
  469. ENV: Agent did: predict-yes for direction R in state State-B
  470. In State-B moving R
  471. ENV: (next state, see, prediction correct?) = (State-B, 0, False)
  472. predict error 1
  473. dir: dir isU
  474. |\-63: O: O126 (predict-no)
  475. I see 0 and I'm going to do: predict-no
  476. ENV: Agent did: predict-no for direction U in state State-B
  477. In State-B moving U
  478. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  479. predict error 0
  480. dir: dir isR
  481. /|64: O: O127 (predict-yes)
  482. I see 1 and I'm going to do: predict-yes
  483. ENV: Agent did: predict-yes for direction R in state State-B
  484. In State-B moving R
  485. ENV: (next state, see, prediction correct?) = (State-B, 0, False)
  486. predict error 1
  487. dir: dir isR
  488. \-65: O: O129 (predict-yes)
  489. I see 0 and I'm going to do: predict-yes
  490. ENV: Agent did: predict-yes for direction R in state State-B
  491. In State-B moving R
  492. ENV: (next state, see, prediction correct?) = (State-B, 0, False)
  493. predict error 1
  494. dir: dir isR
  495. /|66: O: O131 (predict-yes)
  496. I see 0 and I'm going to do: predict-yes
  497. ENV: Agent did: predict-yes for direction R in state State-B
  498. In State-B moving R
  499. ENV: (next state, see, prediction correct?) = (State-B, 0, False)
  500. predict error 1
  501. dir: dir isR
  502. \-/67: O: O133 (predict-yes)
  503. I see 0 and I'm going to do: predict-yes
  504. ENV: Agent did: predict-yes for direction R in state State-B
  505. In State-B moving R
  506. ENV: (next state, see, prediction correct?) = (State-B, 0, False)
  507. predict error 1
  508. dir: dir isR
  509. |\68: O: O135 (predict-yes)
  510. I see 0 and I'm going to do: predict-yes
  511. ENV: Agent did: predict-yes for direction R in state State-B
  512. In State-B moving R
  513. ENV: (next state, see, prediction correct?) = (State-B, 0, False)
  514. predict error 1
  515. dir: dir isR
  516. -/|69: O: O138 (predict-no)
  517. I see 0 and I'm going to do: predict-no
  518. ENV: Agent did: predict-no for direction R in state State-B
  519. In State-B moving R
  520. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  521. predict error 0
  522. dir: dir isL
  523. \-/70: O: O139 (predict-yes)
  524. I see 1 and I'm going to do: predict-yes
  525. ENV: Agent did: predict-yes for direction L in state State-B
  526. In State-B moving L
  527. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  528. predict error 0
  529. dir: dir isL
  530. |\71: O: O141 (predict-yes)
  531. I see 1 and I'm going to do: predict-yes
  532. ENV: Agent did: predict-yes for direction L in state State-A
  533. In State-A moving L
  534. ENV: (next state, see, prediction correct?) = (State-A, 0, False)
  535. predict error 1
  536. dir: dir isL
  537. rule alias: '*'
  538. rule alias: '*'
  539. rule alias: '*'
  540. rule alias: '*'
  541. rule alias: '*'
  542. -72: O: O143 (predict-yes)
  543. I see 0 and I'm going to do: predict-yes
  544. ENV: Agent did: predict-yes for direction L in state State-A
  545. In State-A moving L
  546. ENV: (next state, see, prediction correct?) = (State-A, 0, False)
  547. predict error 1
  548. dir: dir isR
  549. /|\73: O: O146 (predict-no)
  550. I see 0 and I'm going to do: predict-no
  551. ENV: Agent did: predict-no for direction R in state State-A
  552. In State-A moving R
  553. ENV: (next state, see, prediction correct?) = (State-B, 1, False)
  554. predict error 1
  555. dir: dir isR
  556. -/74: O: O147 (predict-yes)
  557. I see 0 and I'm going to do: predict-yes
  558. ENV: Agent did: predict-yes for direction R in state State-B
  559. In State-B moving R
  560. ENV: (next state, see, prediction correct?) = (State-B, 0, False)
  561. predict error 1
  562. dir: dir isR
  563. |\75: O: O150 (predict-no)
  564. I see 0 and I'm going to do: predict-no
  565. ENV: Agent did: predict-no for direction R in state State-B
  566. In State-B moving R
  567. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  568. predict error 0
  569. dir: dir isL
  570. -/|76: O: O151 (predict-yes)
  571. I see 1 and I'm going to do: predict-yes
  572. ENV: Agent did: predict-yes for direction L in state State-B
  573. In State-B moving L
  574. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  575. predict error 0
  576. dir: dir isU
  577. \-/77: O: O154 (predict-no)
  578. I see 1 and I'm going to do: predict-no
  579. ENV: Agent did: predict-no for direction U in state State-A
  580. In State-A moving U
  581. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  582. predict error 0
  583. dir: dir isU
  584. |\-78: O: O156 (predict-no)
  585. I see 1 and I'm going to do: predict-no
  586. ENV: Agent did: predict-no for direction U in state State-A
  587. In State-A moving U
  588. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  589. predict error 0
  590. dir: dir isU
  591. /|\79: O: O158 (predict-no)
  592. I see 1 and I'm going to do: predict-no
  593. ENV: Agent did: predict-no for direction U in state State-A
  594. In State-A moving U
  595. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  596. predict error 0
  597. dir: dir isU
  598. -80: O: O160 (predict-no)
  599. I see 1 and I'm going to do: predict-no
  600. ENV: Agent did: predict-no for direction U in state State-A
  601. In State-A moving U
  602. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  603. predict error 0
  604. dir: dir isU
  605. /|\81: O: O162 (predict-no)
  606. I see 1 and I'm going to do: predict-no
  607. ENV: Agent did: predict-no for direction U in state State-A
  608. In State-A moving U
  609. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  610. predict error 0
  611. dir: dir isU
  612. rule alias: '*'
  613. rule alias: '*'
  614. rule alias: '*'
  615. -82: O: O164 (predict-no)
  616. I see 1 and I'm going to do: predict-no
  617. ENV: Agent did: predict-no for direction U in state State-A
  618. In State-A moving U
  619. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  620. predict error 0
  621. dir: dir isR
  622. /|\83: O: O165 (predict-yes)
  623. I see 1 and I'm going to do: predict-yes
  624. ENV: Agent did: predict-yes for direction R in state State-A
  625. In State-A moving R
  626. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  627. predict error 0
  628. dir: dir isR
  629. -/84: O: O168 (predict-no)
  630. I see 1 and I'm going to do: predict-no
  631. ENV: Agent did: predict-no for direction R in state State-B
  632. In State-B moving R
  633. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  634. predict error 0
  635. dir: dir isU
  636. |\-85: O: O169 (predict-yes)
  637. I see 1 and I'm going to do: predict-yes
  638. ENV: Agent did: predict-yes for direction U in state State-B
  639. In State-B moving U
  640. ENV: (next state, see, prediction correct?) = (State-B, 0, False)
  641. predict error 1
  642. dir: dir isL
  643. /|\86: O: O172 (predict-no)
  644. I see 0 and I'm going to do: predict-no
  645. ENV: Agent did: predict-no for direction L in state State-B
  646. In State-B moving L
  647. ENV: (next state, see, prediction correct?) = (State-A, 1, False)
  648. predict error 1
  649. dir: dir isU
  650. -/|87: O: O174 (predict-no)
  651. I see 0 and I'm going to do: predict-no
  652. ENV: Agent did: predict-no for direction U in state State-A
  653. In State-A moving U
  654. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  655. predict error 0
  656. dir: dir isU
  657. \-88: O: O176 (predict-no)
  658. I see 1 and I'm going to do: predict-no
  659. ENV: Agent did: predict-no for direction U in state State-A
  660. In State-A moving U
  661. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  662. predict error 0
  663. dir: dir isU
  664. /|\89: O: O178 (predict-no)
  665. I see 1 and I'm going to do: predict-no
  666. ENV: Agent did: predict-no for direction U in state State-A
  667. In State-A moving U
  668. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  669. predict error 0
  670. dir: dir isR
  671. -/90: O: O180 (predict-no)
  672. I see 1 and I'm going to do: predict-no
  673. ENV: Agent did: predict-no for direction R in state State-A
  674. In State-A moving R
  675. ENV: (next state, see, prediction correct?) = (State-B, 1, False)
  676. predict error 1
  677. dir: dir isU
  678. |\-91: O: O182 (predict-no)
  679. I see 0 and I'm going to do: predict-no
  680. ENV: Agent did: predict-no for direction U in state State-B
  681. In State-B moving U
  682. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  683. predict error 0
  684. dir: dir isR
  685. rule alias: '*'
  686. rule alias: '*'
  687. rule alias: '*'
  688. /92: O: O184 (predict-no)
  689. I see 1 and I'm going to do: predict-no
  690. ENV: Agent did: predict-no for direction R in state State-B
  691. In State-B moving R
  692. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  693. predict error 0
  694. dir: dir isR
  695. |\-93: O: O186 (predict-no)
  696. I see 1 and I'm going to do: predict-no
  697. ENV: Agent did: predict-no for direction R in state State-B
  698. In State-B moving R
  699. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  700. predict error 0
  701. dir: dir isR
  702. /|\94: O: O187 (predict-yes)
  703. I see 1 and I'm going to do: predict-yes
  704. ENV: Agent did: predict-yes for direction R in state State-B
  705. In State-B moving R
  706. ENV: (next state, see, prediction correct?) = (State-B, 0, False)
  707. predict error 1
  708. dir: dir isU
  709. -/|95: O: O189 (predict-yes)
  710. I see 0 and I'm going to do: predict-yes
  711. ENV: Agent did: predict-yes for direction U in state State-B
  712. In State-B moving U
  713. ENV: (next state, see, prediction correct?) = (State-B, 0, False)
  714. predict error 1
  715. dir: dir isU
  716. \96: O: O192 (predict-no)
  717. I see 0 and I'm going to do: predict-no
  718. ENV: Agent did: predict-no for direction U in state State-B
  719. In State-B moving U
  720. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  721. predict error 0
  722. dir: dir isU
  723. -/|97: O: O194 (predict-no)
  724. I see 1 and I'm going to do: predict-no
  725. ENV: Agent did: predict-no for direction U in state State-B
  726. In State-B moving U
  727. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  728. predict error 0
  729. dir: dir isL
  730. \-98: O: O195 (predict-yes)
  731. I see 1 and I'm going to do: predict-yes
  732. ENV: Agent did: predict-yes for direction L in state State-B
  733. In State-B moving L
  734. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  735. predict error 0
  736. dir: dir isR
  737. /|\99: O: O197 (predict-yes)
  738. I see 1 and I'm going to do: predict-yes
  739. ENV: Agent did: predict-yes for direction R in state State-A
  740. In State-A moving R
  741. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  742. predict error 0
  743. dir: dir isR
  744. -/|100: O: O200 (predict-no)
  745. I see 1 and I'm going to do: predict-no
  746. ENV: Agent did: predict-no for direction R in state State-B
  747. In State-B moving R
  748. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  749. predict error 0
  750. dir: dir isR
  751. \-/101: O: O202 (predict-no)
  752. I see 1 and I'm going to do: predict-no
  753. ENV: Agent did: predict-no for direction R in state State-B
  754. In State-B moving R
  755. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  756. predict error 0
  757. dir: dir isU
  758. rule alias: '*'
  759. |\-/|\-/|\-/|\-/|\-/|\-/|\-/|\-/|sleeping...
  760. \102: O: O204 (predict-no)
  761. I see 1 and I'm going to do: predict-no
  762. ENV: Agent did: predict-no for direction U in state State-B
  763. In State-B moving U
  764. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  765. predict error 0
  766. dir: dir isL
  767. -/|103: O: O206 (predict-no)
  768. I see 1 and I'm going to do: predict-no
  769. ENV: Agent did: predict-no for direction L in state State-B
  770. In State-B moving L
  771. ENV: (next state, see, prediction correct?) = (State-A, 1, False)
  772. predict error 1
  773. dir: dir isU
  774. \-/104: O: O208 (predict-no)
  775. I see 0 and I'm going to do: predict-no
  776. ENV: Agent did: predict-no for direction U in state State-A
  777. In State-A moving U
  778. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  779. predict error 0
  780. dir: dir isL
  781. |\-105: O: O209 (predict-yes)
  782. I see 1 and I'm going to do: predict-yes
  783. ENV: Agent did: predict-yes for direction L in state State-A
  784. In State-A moving L
  785. ENV: (next state, see, prediction correct?) = (State-A, 0, False)
  786. predict error 1
  787. dir: dir isL
  788. /|\106: O: O211 (predict-yes)
  789. I see 0 and I'm going to do: predict-yes
  790. ENV: Agent did: predict-yes for direction L in state State-A
  791. In State-A moving L
  792. ENV: (next state, see, prediction correct?) = (State-A, 0, False)
  793. predict error 1
  794. dir: dir isU
  795. -/|107: O: O214 (predict-no)
  796. I see 0 and I'm going to do: predict-no
  797. ENV: Agent did: predict-no for direction U in state State-A
  798. In State-A moving U
  799. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  800. predict error 0
  801. dir: dir isL
  802. \-108: O: O215 (predict-yes)
  803. I see 1 and I'm going to do: predict-yes
  804. ENV: Agent did: predict-yes for direction L in state State-A
  805. In State-A moving L
  806. ENV: (next state, see, prediction correct?) = (State-A, 0, False)
  807. predict error 1
  808. dir: dir isU
  809. /|109: O: O218 (predict-no)
  810. I see 0 and I'm going to do: predict-no
  811. ENV: Agent did: predict-no for direction U in state State-A
  812. In State-A moving U
  813. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  814. predict error 0
  815. dir: dir isL
  816. \-/110: O: O219 (predict-yes)
  817. I see 1 and I'm going to do: predict-yes
  818. ENV: Agent did: predict-yes for direction L in state State-A
  819. In State-A moving L
  820. ENV: (next state, see, prediction correct?) = (State-A, 0, False)
  821. predict error 1
  822. dir: dir isL
  823. |\111: O: O221 (predict-yes)
  824. I see 0 and I'm going to do: predict-yes
  825. ENV: Agent did: predict-yes for direction L in state State-A
  826. In State-A moving L
  827. ENV: (next state, see, prediction correct?) = (State-A, 0, False)
  828. predict error 1
  829. dir: dir isU
  830. rule alias: '*'
  831. rule alias: '*'
  832. rule alias: '*'
  833. -112: O: O224 (predict-no)
  834. I see 0 and I'm going to do: predict-no
  835. ENV: Agent did: predict-no for direction U in state State-A
  836. In State-A moving U
  837. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  838. predict error 0
  839. dir: dir isL
  840. /|\113: O: O225 (predict-yes)
  841. I see 1 and I'm going to do: predict-yes
  842. ENV: Agent did: predict-yes for direction L in state State-A
  843. In State-A moving L
  844. ENV: (next state, see, prediction correct?) = (State-A, 0, False)
  845. predict error 1
  846. dir: dir isR
  847. -114: O: O228 (predict-no)
  848. I see 0 and I'm going to do: predict-no
  849. ENV: Agent did: predict-no for direction R in state State-A
  850. In State-A moving R
  851. ENV: (next state, see, prediction correct?) = (State-B, 1, False)
  852. predict error 1
  853. dir: dir isU
  854. /|\115: O: O230 (predict-no)
  855. I see 0 and I'm going to do: predict-no
  856. ENV: Agent did: predict-no for direction U in state State-B
  857. In State-B moving U
  858. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  859. predict error 0
  860. dir: dir isR
  861. -/116: O: O232 (predict-no)
  862. I see 1 and I'm going to do: predict-no
  863. ENV: Agent did: predict-no for direction R in state State-B
  864. In State-B moving R
  865. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  866. predict error 0
  867. dir: dir isU
  868. |117: O: O234 (predict-no)
  869. I see 1 and I'm going to do: predict-no
  870. ENV: Agent did: predict-no for direction U in state State-B
  871. In State-B moving U
  872. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  873. predict error 0
  874. dir: dir isL
  875. \-/118: O: O235 (predict-yes)
  876. I see 1 and I'm going to do: predict-yes
  877. ENV: Agent did: predict-yes for direction L in state State-B
  878. In State-B moving L
  879. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  880. predict error 0
  881. dir: dir isR
  882. |\119: O: O238 (predict-no)
  883. I see 1 and I'm going to do: predict-no
  884. ENV: Agent did: predict-no for direction R in state State-A
  885. In State-A moving R
  886. ENV: (next state, see, prediction correct?) = (State-B, 1, False)
  887. predict error 1
  888. dir: dir isR
  889. -/|120: O: O239 (predict-yes)
  890. I see 0 and I'm going to do: predict-yes
  891. ENV: Agent did: predict-yes for direction R in state State-B
  892. In State-B moving R
  893. ENV: (next state, see, prediction correct?) = (State-B, 0, False)
  894. predict error 1
  895. dir: dir isR
  896. \-121: O: O242 (predict-no)
  897. I see 0 and I'm going to do: predict-no
  898. ENV: Agent did: predict-no for direction R in state State-B
  899. In State-B moving R
  900. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  901. predict error 0
  902. dir: dir isR
  903. rule alias: '*'
  904. rule alias: '*'
  905. rule alias: '*'
  906. rule alias: '*'
  907. rule alias: '*'
  908. rule alias: '*'
  909. rule alias: '*'
  910. rule alias: '*'
  911. /122: O: O244 (predict-no)
  912. I see 1 and I'm going to do: predict-no
  913. ENV: Agent did: predict-no for direction R in state State-B
  914. In State-B moving R
  915. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  916. predict error 0
  917. dir: dir isR
  918. |\-/123: O: O245 (predict-yes)
  919. I see 1 and I'm going to do: predict-yes
  920. ENV: Agent did: predict-yes for direction R in state State-B
  921. In State-B moving R
  922. ENV: (next state, see, prediction correct?) = (State-B, 0, False)
  923. predict error 1
  924. dir: dir isU
  925. |\-124: O: O248 (predict-no)
  926. I see 0 and I'm going to do: predict-no
  927. ENV: Agent did: predict-no for direction U in state State-B
  928. In State-B moving U
  929. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  930. predict error 0
  931. dir: dir isL
  932. /|\125: O: O249 (predict-yes)
  933. I see 1 and I'm going to do: predict-yes
  934. ENV: Agent did: predict-yes for direction L in state State-B
  935. In State-B moving L
  936. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  937. predict error 0
  938. dir: dir isL
  939. -/|126: O: O251 (predict-yes)
  940. I see 1 and I'm going to do: predict-yes
  941. ENV: Agent did: predict-yes for direction L in state State-A
  942. In State-A moving L
  943. ENV: (next state, see, prediction correct?) = (State-A, 0, False)
  944. predict error 1
  945. dir: dir isU
  946. \-/127: O: O254 (predict-no)
  947. I see 0 and I'm going to do: predict-no
  948. ENV: Agent did: predict-no for direction U in state State-A
  949. In State-A moving U
  950. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  951. predict error 0
  952. dir: dir isL
  953. |\-128: O: O255 (predict-yes)
  954. I see 1 and I'm going to do: predict-yes
  955. ENV: Agent did: predict-yes for direction L in state State-A
  956. In State-A moving L
  957. ENV: (next state, see, prediction correct?) = (State-A, 0, False)
  958. predict error 1
  959. dir: dir isL
  960. /|129: O: O257 (predict-yes)
  961. I see 0 and I'm going to do: predict-yes
  962. ENV: Agent did: predict-yes for direction L in state State-A
  963. In State-A moving L
  964. ENV: (next state, see, prediction correct?) = (State-A, 0, False)
  965. predict error 1
  966. dir: dir isL
  967. \-/130: O: O259 (predict-yes)
  968. I see 0 and I'm going to do: predict-yes
  969. ENV: Agent did: predict-yes for direction L in state State-A
  970. In State-A moving L
  971. ENV: (next state, see, prediction correct?) = (State-A, 0, False)
  972. predict error 1
  973. dir: dir isU
  974. |\131: O: O262 (predict-no)
  975. I see 0 and I'm going to do: predict-no
  976. ENV: Agent did: predict-no for direction U in state State-A
  977. In State-A moving U
  978. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  979. predict error 0
  980. dir: dir isU
  981. -132: O: O264 (predict-no)
  982. I see 1 and I'm going to do: predict-no
  983. ENV: Agent did: predict-no for direction U in state State-A
  984. In State-A moving U
  985. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  986. predict error 0
  987. dir: dir isL
  988. /|\-133: O: O265 (predict-yes)
  989. I see 1 and I'm going to do: predict-yes
  990. ENV: Agent did: predict-yes for direction L in state State-A
  991. In State-A moving L
  992. ENV: (next state, see, prediction correct?) = (State-A, 0, False)
  993. predict error 1
  994. dir: dir isR
  995. /|\134: O: O268 (predict-no)
  996. I see 0 and I'm going to do: predict-no
  997. ENV: Agent did: predict-no for direction R in state State-A
  998. In State-A moving R
  999. ENV: (next state, see, prediction correct?) = (State-B, 1, False)
  1000. predict error 1
  1001. dir: dir isL
  1002. -/135: O: O269 (predict-yes)
  1003. I see 0 and I'm going to do: predict-yes
  1004. ENV: Agent did: predict-yes for direction L in state State-B
  1005. In State-B moving L
  1006. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  1007. predict error 0
  1008. dir: dir isL
  1009. |\-136: O: O271 (predict-yes)
  1010. I see 1 and I'm going to do: predict-yes
  1011. ENV: Agent did: predict-yes for direction L in state State-A
  1012. In State-A moving L
  1013. ENV: (next state, see, prediction correct?) = (State-A, 0, False)
  1014. predict error 1
  1015. dir: dir isL
  1016. /|\137: O: O274 (predict-no)
  1017. I see 0 and I'm going to do: predict-no
  1018. ENV: Agent did: predict-no for direction L in state State-A
  1019. In State-A moving L
  1020. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  1021. predict error 0
  1022. dir: dir isR
  1023. -/|138: O: O276 (predict-no)
  1024. I see 1 and I'm going to do: predict-no
  1025. ENV: Agent did: predict-no for direction R in state State-A
  1026. In State-A moving R
  1027. ENV: (next state, see, prediction correct?) = (State-B, 1, False)
  1028. predict error 1
  1029. dir: dir isR
  1030. \-/139: O: O278 (predict-no)
  1031. I see 0 and I'm going to do: predict-no
  1032. ENV: Agent did: predict-no for direction R in state State-B
  1033. In State-B moving R
  1034. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  1035. predict error 0
  1036. dir: dir isL
  1037. |\-140: O: O279 (predict-yes)
  1038. I see 1 and I'm going to do: predict-yes
  1039. ENV: Agent did: predict-yes for direction L in state State-B
  1040. In State-B moving L
  1041. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  1042. predict error 0
  1043. dir: dir isR
  1044. /|\141: O: O282 (predict-no)
  1045. I see 1 and I'm going to do: predict-no
  1046. ENV: Agent did: predict-no for direction R in state State-A
  1047. In State-A moving R
  1048. ENV: (next state, see, prediction correct?) = (State-B, 1, False)
  1049. predict error 1
  1050. dir: dir isL
  1051. rule alias: '*'
  1052. -142: O: O283 (predict-yes)
  1053. I see 0 and I'm going to do: predict-yes
  1054. ENV: Agent did: predict-yes for direction L in state State-B
  1055. In State-B moving L
  1056. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  1057. predict error 0
  1058. dir: dir isL
  1059. /|\-143: O: O286 (predict-no)
  1060. I see 1 and I'm going to do: predict-no
  1061. ENV: Agent did: predict-no for direction L in state State-A
  1062. In State-A moving L
  1063. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  1064. predict error 0
  1065. dir: dir isU
  1066. /|\144: O: O288 (predict-no)
  1067. I see 1 and I'm going to do: predict-no
  1068. ENV: Agent did: predict-no for direction U in state State-A
  1069. In State-A moving U
  1070. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  1071. predict error 0
  1072. dir: dir isL
  1073. -/|145: O: O290 (predict-no)
  1074. I see 1 and I'm going to do: predict-no
  1075. ENV: Agent did: predict-no for direction L in state State-A
  1076. In State-A moving L
  1077. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  1078. predict error 0
  1079. dir: dir isR
  1080. \-/146: O: O292 (predict-no)
  1081. I see 1 and I'm going to do: predict-no
  1082. ENV: Agent did: predict-no for direction R in state State-A
  1083. In State-A moving R
  1084. ENV: (next state, see, prediction correct?) = (State-B, 1, False)
  1085. predict error 1
  1086. dir: dir isU
  1087. |\-147: O: O294 (predict-no)
  1088. I see 0 and I'm going to do: predict-no
  1089. ENV: Agent did: predict-no for direction U in state State-B
  1090. In State-B moving U
  1091. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  1092. predict error 0
  1093. dir: dir isU
  1094. /|\148: O: O296 (predict-no)
  1095. I see 1 and I'm going to do: predict-no
  1096. ENV: Agent did: predict-no for direction U in state State-B
  1097. In State-B moving U
  1098. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  1099. predict error 0
  1100. dir: dir isU
  1101. -/|149: O: O298 (predict-no)
  1102. I see 1 and I'm going to do: predict-no
  1103. ENV: Agent did: predict-no for direction U in state State-B
  1104. In State-B moving U
  1105. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  1106. predict error 0
  1107. dir: dir isL
  1108. \-/150: O: O299 (predict-yes)
  1109. I see 1 and I'm going to do: predict-yes
  1110. ENV: Agent did: predict-yes for direction L in state State-B
  1111. In State-B moving L
  1112. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  1113. predict error 0
  1114. dir: dir isU
  1115. |\-151: O: O302 (predict-no)
  1116. I see 1 and I'm going to do: predict-no
  1117. ENV: Agent did: predict-no for direction U in state State-A
  1118. In State-A moving U
  1119. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  1120. predict error 0
  1121. dir: dir isU
  1122. /152: O: O304 (predict-no)
  1123. I see 1 and I'm going to do: predict-no
  1124. ENV: Agent did: predict-no for direction U in state State-A
  1125. In State-A moving U
  1126. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  1127. predict error 0
  1128. dir: dir isL
  1129. |\-153: O: O306 (predict-no)
  1130. I see 1 and I'm going to do: predict-no
  1131. ENV: Agent did: predict-no for direction L in state State-A
  1132. In State-A moving L
  1133. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  1134. predict error 0
  1135. dir: dir isU
  1136. /|154: O: O308 (predict-no)
  1137. I see 1 and I'm going to do: predict-no
  1138. ENV: Agent did: predict-no for direction U in state State-A
  1139. In State-A moving U
  1140. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  1141. predict error 0
  1142. dir: dir isU
  1143. \-/155: O: O310 (predict-no)
  1144. I see 1 and I'm going to do: predict-no
  1145. ENV: Agent did: predict-no for direction U in state State-A
  1146. In State-A moving U
  1147. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  1148. predict error 0
  1149. dir: dir isR
  1150. |\-/sleeping...
  1151. |156: O: O312 (predict-no)
  1152. I see 1 and I'm going to do: predict-no
  1153. ENV: Agent did: predict-no for direction R in state State-A
  1154. In State-A moving R
  1155. ENV: (next state, see, prediction correct?) = (State-B, 1, False)
  1156. predict error 1
  1157. dir: dir isL
  1158. \-/157: O: O313 (predict-yes)
  1159. I see 0 and I'm going to do: predict-yes
  1160. ENV: Agent did: predict-yes for direction L in state State-B
  1161. In State-B moving L
  1162. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  1163. predict error 0
  1164. dir: dir isR
  1165. |\-158: O: O316 (predict-no)
  1166. I see 1 and I'm going to do: predict-no
  1167. ENV: Agent did: predict-no for direction R in state State-A
  1168. In State-A moving R
  1169. ENV: (next state, see, prediction correct?) = (State-B, 1, False)
  1170. predict error 1
  1171. dir: dir isR
  1172. /|\159: O: O318 (predict-no)
  1173. I see 0 and I'm going to do: predict-no
  1174. ENV: Agent did: predict-no for direction R in state State-B
  1175. In State-B moving R
  1176. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  1177. predict error 0
  1178. dir: dir isL
  1179. -160: O: O319 (predict-yes)
  1180. I see 1 and I'm going to do: predict-yes
  1181. ENV: Agent did: predict-yes for direction L in state State-B
  1182. In State-B moving L
  1183. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  1184. predict error 0
  1185. dir: dir isR
  1186. /|\161: O: O322 (predict-no)
  1187. I see 1 and I'm going to do: predict-no
  1188. ENV: Agent did: predict-no for direction R in state State-A
  1189. In State-A moving R
  1190. ENV: (next state, see, prediction correct?) = (State-B, 1, False)
  1191. predict error 1
  1192. dir: dir isR
  1193. -162: O: O324 (predict-no)
  1194. I see 0 and I'm going to do: predict-no
  1195. ENV: Agent did: predict-no for direction R in state State-B
  1196. In State-B moving R
  1197. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  1198. predict error 0
  1199. dir: dir isR
  1200. /|163: O: O326 (predict-no)
  1201. I see 1 and I'm going to do: predict-no
  1202. ENV: Agent did: predict-no for direction R in state State-B
  1203. In State-B moving R
  1204. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  1205. predict error 0
  1206. dir: dir isR
  1207. \164: O: O328 (predict-no)
  1208. I see 1 and I'm going to do: predict-no
  1209. ENV: Agent did: predict-no for direction R in state State-B
  1210. In State-B moving R
  1211. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  1212. predict error 0
  1213. dir: dir isL
  1214. -/|165: O: O329 (predict-yes)
  1215. I see 1 and I'm going to do: predict-yes
  1216. ENV: Agent did: predict-yes for direction L in state State-B
  1217. In State-B moving L
  1218. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  1219. predict error 0
  1220. dir: dir isR
  1221. \-/166: O: O332 (predict-no)
  1222. I see 1 and I'm going to do: predict-no
  1223. ENV: Agent did: predict-no for direction R in state State-A
  1224. In State-A moving R
  1225. ENV: (next state, see, prediction correct?) = (State-B, 1, False)
  1226. predict error 1
  1227. dir: dir isU
  1228. |\-167: O: O334 (predict-no)
  1229. I see 0 and I'm going to do: predict-no
  1230. ENV: Agent did: predict-no for direction U in state State-B
  1231. In State-B moving U
  1232. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  1233. predict error 0
  1234. dir: dir isL
  1235. /|\168: O: O335 (predict-yes)
  1236. I see 1 and I'm going to do: predict-yes
  1237. ENV: Agent did: predict-yes for direction L in state State-B
  1238. In State-B moving L
  1239. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  1240. predict error 0
  1241. dir: dir isR
  1242. -/|169: O: O338 (predict-no)
  1243. I see 1 and I'm going to do: predict-no
  1244. ENV: Agent did: predict-no for direction R in state State-A
  1245. In State-A moving R
  1246. ENV: (next state, see, prediction correct?) = (State-B, 1, False)
  1247. predict error 1
  1248. dir: dir isL
  1249. \-170: O: O339 (predict-yes)
  1250. I see 0 and I'm going to do: predict-yes
  1251. ENV: Agent did: predict-yes for direction L in state State-B
  1252. In State-B moving L
  1253. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  1254. predict error 0
  1255. dir: dir isU
  1256. /|171: O: O342 (predict-no)
  1257. I see 1 and I'm going to do: predict-no
  1258. ENV: Agent did: predict-no for direction U in state State-A
  1259. In State-A moving U
  1260. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  1261. predict error 0
  1262. dir: dir isR
  1263. \172: O: O343 (predict-yes)
  1264. I see 1 and I'm going to do: predict-yes
  1265. ENV: Agent did: predict-yes for direction R in state State-A
  1266. In State-A moving R
  1267. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  1268. predict error 0
  1269. dir: dir isL
  1270. -/173: O: O345 (predict-yes)
  1271. I see 1 and I'm going to do: predict-yes
  1272. ENV: Agent did: predict-yes for direction L in state State-B
  1273. In State-B moving L
  1274. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  1275. predict error 0
  1276. dir: dir isL
  1277. |\-174: O: O348 (predict-no)
  1278. I see 1 and I'm going to do: predict-no
  1279. ENV: Agent did: predict-no for direction L in state State-A
  1280. In State-A moving L
  1281. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  1282. predict error 0
  1283. dir: dir isL
  1284. /|\175: O: O350 (predict-no)
  1285. I see 1 and I'm going to do: predict-no
  1286. ENV: Agent did: predict-no for direction L in state State-A
  1287. In State-A moving L
  1288. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  1289. predict error 0
  1290. dir: dir isU
  1291. -/|176: O: O352 (predict-no)
  1292. I see 1 and I'm going to do: predict-no
  1293. ENV: Agent did: predict-no for direction U in state State-A
  1294. In State-A moving U
  1295. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  1296. predict error 0
  1297. dir: dir isR
  1298. \-177: O: O353 (predict-yes)
  1299. I see 1 and I'm going to do: predict-yes
  1300. ENV: Agent did: predict-yes for direction R in state State-A
  1301. In State-A moving R
  1302. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  1303. predict error 0
  1304. dir: dir isL
  1305. /|\178: O: O355 (predict-yes)
  1306. I see 1 and I'm going to do: predict-yes
  1307. ENV: Agent did: predict-yes for direction L in state State-B
  1308. In State-B moving L
  1309. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  1310. predict error 0
  1311. dir: dir isR
  1312. -/|179: O: O357 (predict-yes)
  1313. I see 1 and I'm going to do: predict-yes
  1314. ENV: Agent did: predict-yes for direction R in state State-A
  1315. In State-A moving R
  1316. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  1317. predict error 0
  1318. dir: dir isU
  1319. \-/180: O: O360 (predict-no)
  1320. I see 1 and I'm going to do: predict-no
  1321. ENV: Agent did: predict-no for direction U in state State-B
  1322. In State-B moving U
  1323. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  1324. predict error 0
  1325. dir: dir isR
  1326. |\-181: O: O362 (predict-no)
  1327. I see 1 and I'm going to do: predict-no
  1328. ENV: Agent did: predict-no for direction R in state State-B
  1329. In State-B moving R
  1330. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  1331. predict error 0
  1332. dir: dir isR
  1333. /182: O: O364 (predict-no)
  1334. I see 1 and I'm going to do: predict-no
  1335. ENV: Agent did: predict-no for direction R in state State-B
  1336. In State-B moving R
  1337. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  1338. predict error 0
  1339. dir: dir isU
  1340. |\-183: O: O366 (predict-no)
  1341. I see 1 and I'm going to do: predict-no
  1342. ENV: Agent did: predict-no for direction U in state State-B
  1343. In State-B moving U
  1344. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  1345. predict error 0
  1346. dir: dir isR
  1347. /|\184: O: O368 (predict-no)
  1348. I see 1 and I'm going to do: predict-no
  1349. ENV: Agent did: predict-no for direction R in state State-B
  1350. In State-B moving R
  1351. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  1352. predict error 0
  1353. dir: dir isR
  1354. -/|185: O: O370 (predict-no)
  1355. I see 1 and I'm going to do: predict-no
  1356. ENV: Agent did: predict-no for direction R in state State-B
  1357. In State-B moving R
  1358. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  1359. predict error 0
  1360. dir: dir isR
  1361. \-/186: O: O372 (predict-no)
  1362. I see 1 and I'm going to do: predict-no
  1363. ENV: Agent did: predict-no for direction R in state State-B
  1364. In State-B moving R
  1365. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  1366. predict error 0
  1367. dir: dir isL
  1368. |\-187: O: O373 (predict-yes)
  1369. I see 1 and I'm going to do: predict-yes
  1370. ENV: Agent did: predict-yes for direction L in state State-B
  1371. In State-B moving L
  1372. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  1373. predict error 0
  1374. dir: dir isL
  1375. /|\188: O: O376 (predict-no)
  1376. I see 1 and I'm going to do: predict-no
  1377. ENV: Agent did: predict-no for direction L in state State-A
  1378. In State-A moving L
  1379. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  1380. predict error 0
  1381. dir: dir isR
  1382. -/|189: O: O377 (predict-yes)
  1383. I see 1 and I'm going to do: predict-yes
  1384. ENV: Agent did: predict-yes for direction R in state State-A
  1385. In State-A moving R
  1386. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  1387. predict error 0
  1388. dir: dir isL
  1389. \190: O: O379 (predict-yes)
  1390. I see 1 and I'm going to do: predict-yes
  1391. ENV: Agent did: predict-yes for direction L in state State-B
  1392. In State-B moving L
  1393. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  1394. predict error 0
  1395. dir: dir isR
  1396. -/|191: O: O381 (predict-yes)
  1397. I see 1 and I'm going to do: predict-yes
  1398. ENV: Agent did: predict-yes for direction R in state State-A
  1399. In State-A moving R
  1400. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  1401. predict error 0
  1402. dir: dir isR
  1403. \192: O: O384 (predict-no)
  1404. I see 1 and I'm going to do: predict-no
  1405. ENV: Agent did: predict-no for direction R in state State-B
  1406. In State-B moving R
  1407. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  1408. predict error 0
  1409. dir: dir isU
  1410. -/|193: O: O386 (predict-no)
  1411. I see 1 and I'm going to do: predict-no
  1412. ENV: Agent did: predict-no for direction U in state State-B
  1413. In State-B moving U
  1414. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  1415. predict error 0
  1416. dir: dir isR
  1417. \-194: O: O388 (predict-no)
  1418. I see 1 and I'm going to do: predict-no
  1419. ENV: Agent did: predict-no for direction R in state State-B
  1420. In State-B moving R
  1421. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  1422. predict error 0
  1423. dir: dir isR
  1424. /|\195: O: O390 (predict-no)
  1425. I see 1 and I'm going to do: predict-no
  1426. ENV: Agent did: predict-no for direction R in state State-B
  1427. In State-B moving R
  1428. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  1429. predict error 0
  1430. dir: dir isR
  1431. -/|196: O: O392 (predict-no)
  1432. I see 1 and I'm going to do: predict-no
  1433. ENV: Agent did: predict-no for direction R in state State-B
  1434. In State-B moving R
  1435. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  1436. predict error 0
  1437. dir: dir isU
  1438. \-/197: O: O394 (predict-no)
  1439. I see 1 and I'm going to do: predict-no
  1440. ENV: Agent did: predict-no for direction U in state State-B
  1441. In State-B moving U
  1442. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  1443. predict error 0
  1444. dir: dir isR
  1445. |198: O: O396 (predict-no)
  1446. I see 1 and I'm going to do: predict-no
  1447. ENV: Agent did: predict-no for direction R in state State-B
  1448. In State-B moving R
  1449. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  1450. predict error 0
  1451. dir: dir isR
  1452. \-/199: O: O398 (predict-no)
  1453. I see 1 and I'm going to do: predict-no
  1454. ENV: Agent did: predict-no for direction R in state State-B
  1455. In State-B moving R
  1456. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  1457. predict error 0
  1458. dir: dir isL
  1459. |\200: O: O399 (predict-yes)
  1460. I see 1 and I'm going to do: predict-yes
  1461. ENV: Agent did: predict-yes for direction L in state State-B
  1462. In State-B moving L
  1463. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  1464. predict error 0
  1465. dir: dir isR
  1466. -/|201: O: O401 (predict-yes)
  1467. I see 1 and I'm going to do: predict-yes
  1468. ENV: Agent did: predict-yes for direction R in state State-A
  1469. In State-A moving R
  1470. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  1471. predict error 0
  1472. dir: dir isL
  1473. \-202: O: O403 (predict-yes)
  1474. I see 1 and I'm going to do: predict-yes
  1475. ENV: Agent did: predict-yes for direction L in state State-B
  1476. In State-B moving L
  1477. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  1478. predict error 0
  1479. dir: dir isL
  1480. /|\203: O: O406 (predict-no)
  1481. I see 1 and I'm going to do: predict-no
  1482. ENV: Agent did: predict-no for direction L in state State-A
  1483. In State-A moving L
  1484. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  1485. predict error 0
  1486. dir: dir isR
  1487. -/|204: O: O407 (predict-yes)
  1488. I see 1 and I'm going to do: predict-yes
  1489. ENV: Agent did: predict-yes for direction R in state State-A
  1490. In State-A moving R
  1491. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  1492. predict error 0
  1493. dir: dir isR
  1494. \-/205: O: O410 (predict-no)
  1495. I see 1 and I'm going to do: predict-no
  1496. ENV: Agent did: predict-no for direction R in state State-B
  1497. In State-B moving R
  1498. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  1499. predict error 0
  1500. dir: dir isR
  1501. |\-206: O: O412 (predict-no)
  1502. I see 1 and I'm going to do: predict-no
  1503. ENV: Agent did: predict-no for direction R in state State-B
  1504. In State-B moving R
  1505. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  1506. predict error 0
  1507. dir: dir isU
  1508. /|\-207: O: O414 (predict-no)
  1509. I see 1 and I'm going to do: predict-no
  1510. ENV: Agent did: predict-no for direction U in state State-B
  1511. In State-B moving U
  1512. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  1513. predict error 0
  1514. dir: dir isU
  1515. /|\208: O: O416 (predict-no)
  1516. I see 1 and I'm going to do: predict-no
  1517. ENV: Agent did: predict-no for direction U in state State-B
  1518. In State-B moving U
  1519. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  1520. predict error 0
  1521. dir: dir isR
  1522. -/209: O: O418 (predict-no)
  1523. I see 1 and I'm going to do: predict-no
  1524. ENV: Agent did: predict-no for direction R in state State-B
  1525. In State-B moving R
  1526. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  1527. predict error 0
  1528. dir: dir isL
  1529. |\-/210: O: O419 (predict-yes)
  1530. I see 1 and I'm going to do: predict-yes
  1531. ENV: Agent did: predict-yes for direction L in state State-B
  1532. In State-B moving L
  1533. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  1534. predict error 0
  1535. dir: dir isR
  1536. |\-211: O: O421 (predict-yes)
  1537. I see 1 and I'm going to do: predict-yes
  1538. ENV: Agent did: predict-yes for direction R in state State-A
  1539. In State-A moving R
  1540. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  1541. predict error 0
  1542. dir: dir isU
  1543. /212: O: O424 (predict-no)
  1544. I see 1 and I'm going to do: predict-no
  1545. ENV: Agent did: predict-no for direction U in state State-B
  1546. In State-B moving U
  1547. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  1548. predict error 0
  1549. dir: dir isU
  1550. |\-213: O: O426 (predict-no)
  1551. I see 1 and I'm going to do: predict-no
  1552. ENV: Agent did: predict-no for direction U in state State-B
  1553. In State-B moving U
  1554. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  1555. predict error 0
  1556. dir: dir isU
  1557. /|\214: O: O428 (predict-no)
  1558. I see 1 and I'm going to do: predict-no
  1559. ENV: Agent did: predict-no for direction U in state State-B
  1560. In State-B moving U
  1561. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  1562. predict error 0
  1563. dir: dir isL
  1564. -/|215: O: O429 (predict-yes)
  1565. I see 1 and I'm going to do: predict-yes
  1566. ENV: Agent did: predict-yes for direction L in state State-B
  1567. In State-B moving L
  1568. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  1569. predict error 0
  1570. dir: dir isU
  1571. \-/216: O: O432 (predict-no)
  1572. I see 1 and I'm going to do: predict-no
  1573. ENV: Agent did: predict-no for direction U in state State-A
  1574. In State-A moving U
  1575. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  1576. predict error 0
  1577. dir: dir isR
  1578. |\-217: O: O433 (predict-yes)
  1579. I see 1 and I'm going to do: predict-yes
  1580. ENV: Agent did: predict-yes for direction R in state State-A
  1581. In State-A moving R
  1582. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  1583. predict error 0
  1584. dir: dir isL
  1585. /|\218: O: O435 (predict-yes)
  1586. I see 1 and I'm going to do: predict-yes
  1587. ENV: Agent did: predict-yes for direction L in state State-B
  1588. In State-B moving L
  1589. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  1590. predict error 0
  1591. dir: dir isU
  1592. -/219: O: O437 (predict-yes)
  1593. I see 1 and I'm going to do: predict-yes
  1594. ENV: Agent did: predict-yes for direction U in state State-A
  1595. In State-A moving U
  1596. ENV: (next state, see, prediction correct?) = (State-A, 0, False)
  1597. predict error 1
  1598. dir: dir isU
  1599. |\-220: O: O440 (predict-no)
  1600. I see 0 and I'm going to do: predict-no
  1601. ENV: Agent did: predict-no for direction U in state State-A
  1602. In State-A moving U
  1603. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  1604. predict error 0
  1605. dir: dir isR
  1606. /|\221: O: O441 (predict-yes)
  1607. I see 1 and I'm going to do: predict-yes
  1608. ENV: Agent did: predict-yes for direction R in state State-A
  1609. In State-A moving R
  1610. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  1611. predict error 0
  1612. dir: dir isU
  1613. -222: O: O444 (predict-no)
  1614. I see 1 and I'm going to do: predict-no
  1615. ENV: Agent did: predict-no for direction U in state State-B
  1616. In State-B moving U
  1617. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  1618. predict error 0
  1619. dir: dir isL
  1620. /|223: O: O445 (predict-yes)
  1621. I see 1 and I'm going to do: predict-yes
  1622. ENV: Agent did: predict-yes for direction L in state State-B
  1623. In State-B moving L
  1624. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  1625. predict error 0
  1626. dir: dir isL
  1627. \-224: O: O448 (predict-no)
  1628. I see 1 and I'm going to do: predict-no
  1629. ENV: Agent did: predict-no for direction L in state State-A
  1630. In State-A moving L
  1631. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  1632. predict error 0
  1633. dir: dir isU
  1634. /|\225: O: O450 (predict-no)
  1635. I see 1 and I'm going to do: predict-no
  1636. ENV: Agent did: predict-no for direction U in state State-A
  1637. In State-A moving U
  1638. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  1639. predict error 0
  1640. dir: dir isL
  1641. -226: O: O452 (predict-no)
  1642. I see 1 and I'm going to do: predict-no
  1643. ENV: Agent did: predict-no for direction L in state State-A
  1644. In State-A moving L
  1645. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  1646. predict error 0
  1647. dir: dir isU
  1648. /|\227: O: O454 (predict-no)
  1649. I see 1 and I'm going to do: predict-no
  1650. ENV: Agent did: predict-no for direction U in state State-A
  1651. In State-A moving U
  1652. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  1653. predict error 0
  1654. dir: dir isR
  1655. -/|228: O: O455 (predict-yes)
  1656. I see 1 and I'm going to do: predict-yes
  1657. ENV: Agent did: predict-yes for direction R in state State-A
  1658. In State-A moving R
  1659. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  1660. predict error 0
  1661. dir: dir isL
  1662. \-229: O: O457 (predict-yes)
  1663. I see 1 and I'm going to do: predict-yes
  1664. ENV: Agent did: predict-yes for direction L in state State-B
  1665. In State-B moving L
  1666. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  1667. predict error 0
  1668. dir: dir isL
  1669. /|\230: O: O460 (predict-no)
  1670. I see 1 and I'm going to do: predict-no
  1671. ENV: Agent did: predict-no for direction L in state State-A
  1672. In State-A moving L
  1673. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  1674. predict error 0
  1675. dir: dir isR
  1676. -/|231: O: O462 (predict-no)
  1677. I see 1 and I'm going to do: predict-no
  1678. ENV: Agent did: predict-no for direction R in state State-A
  1679. In State-A moving R
  1680. ENV: (next state, see, prediction correct?) = (State-B, 1, False)
  1681. predict error 1
  1682. dir: dir isU
  1683. \232: O: O464 (predict-no)
  1684. I see 0 and I'm going to do: predict-no
  1685. ENV: Agent did: predict-no for direction U in state State-B
  1686. In State-B moving U
  1687. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  1688. predict error 0
  1689. dir: dir isL
  1690. -/|233: O: O465 (predict-yes)
  1691. I see 1 and I'm going to do: predict-yes
  1692. ENV: Agent did: predict-yes for direction L in state State-B
  1693. In State-B moving L
  1694. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  1695. predict error 0
  1696. dir: dir isU
  1697. \-234: O: O468 (predict-no)
  1698. I see 1 and I'm going to do: predict-no
  1699. ENV: Agent did: predict-no for direction U in state State-A
  1700. In State-A moving U
  1701. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  1702. predict error 0
  1703. dir: dir isL
  1704. /|\235: O: O470 (predict-no)
  1705. I see 1 and I'm going to do: predict-no
  1706. ENV: Agent did: predict-no for direction L in state State-A
  1707. In State-A moving L
  1708. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  1709. predict error 0
  1710. dir: dir isU
  1711. -/|236: O: O472 (predict-no)
  1712. I see 1 and I'm going to do: predict-no
  1713. ENV: Agent did: predict-no for direction U in state State-A
  1714. In State-A moving U
  1715. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  1716. predict error 0
  1717. dir: dir isR
  1718. \-/|237: O: O473 (predict-yes)
  1719. I see 1 and I'm going to do: predict-yes
  1720. ENV: Agent did: predict-yes for direction R in state State-A
  1721. In State-A moving R
  1722. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  1723. predict error 0
  1724. dir: dir isL
  1725. \-/238: O: O475 (predict-yes)
  1726. I see 1 and I'm going to do: predict-yes
  1727. ENV: Agent did: predict-yes for direction L in state State-B
  1728. In State-B moving L
  1729. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  1730. predict error 0
  1731. dir: dir isL
  1732. |\-239: O: O478 (predict-no)
  1733. I see 1 and I'm going to do: predict-no
  1734. ENV: Agent did: predict-no for direction L in state State-A
  1735. In State-A moving L
  1736. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  1737. predict error 0
  1738. dir: dir isR
  1739. /|240: O: O479 (predict-yes)
  1740. I see 1 and I'm going to do: predict-yes
  1741. ENV: Agent did: predict-yes for direction R in state State-A
  1742. In State-A moving R
  1743. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  1744. predict error 0
  1745. dir: dir isU
  1746. \-/241: O: O482 (predict-no)
  1747. I see 1 and I'm going to do: predict-no
  1748. ENV: Agent did: predict-no for direction U in state State-B
  1749. In State-B moving U
  1750. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  1751. predict error 0
  1752. dir: dir isU
  1753. |242: O: O484 (predict-no)
  1754. I see 1 and I'm going to do: predict-no
  1755. ENV: Agent did: predict-no for direction U in state State-B
  1756. In State-B moving U
  1757. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  1758. predict error 0
  1759. dir: dir isL
  1760. \-/243: O: O485 (predict-yes)
  1761. I see 1 and I'm going to do: predict-yes
  1762. ENV: Agent did: predict-yes for direction L in state State-B
  1763. In State-B moving L
  1764. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  1765. predict error 0
  1766. dir: dir isR
  1767. |\244: O: O487 (predict-yes)
  1768. I see 1 and I'm going to do: predict-yes
  1769. ENV: Agent did: predict-yes for direction R in state State-A
  1770. In State-A moving R
  1771. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  1772. predict error 0
  1773. dir: dir isR
  1774. -/|245: O: O490 (predict-no)
  1775. I see 1 and I'm going to do: predict-no
  1776. ENV: Agent did: predict-no for direction R in state State-B
  1777. In State-B moving R
  1778. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  1779. predict error 0
  1780. dir: dir isR
  1781. \-/246: O: O492 (predict-no)
  1782. I see 1 and I'm going to do: predict-no
  1783. ENV: Agent did: predict-no for direction R in state State-B
  1784. In State-B moving R
  1785. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  1786. predict error 0
  1787. dir: dir isU
  1788. |\-247: O: O494 (predict-no)
  1789. I see 1 and I'm going to do: predict-no
  1790. ENV: Agent did: predict-no for direction U in state State-B
  1791. In State-B moving U
  1792. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  1793. predict error 0
  1794. dir: dir isL
  1795. /|\248: O: O495 (predict-yes)
  1796. I see 1 and I'm going to do: predict-yes
  1797. ENV: Agent did: predict-yes for direction L in state State-B
  1798. In State-B moving L
  1799. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  1800. predict error 0
  1801. dir: dir isL
  1802. -/|249: O: O498 (predict-no)
  1803. I see 1 and I'm going to do: predict-no
  1804. ENV: Agent did: predict-no for direction L in state State-A
  1805. In State-A moving L
  1806. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  1807. predict error 0
  1808. dir: dir isL
  1809. \-250: O: O500 (predict-no)
  1810. I see 1 and I'm going to do: predict-no
  1811. ENV: Agent did: predict-no for direction L in state State-A
  1812. In State-A moving L
  1813. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  1814. predict error 0
  1815. dir: dir isU
  1816. /|251: O: O502 (predict-no)
  1817. I see 1 and I'm going to do: predict-no
  1818. ENV: Agent did: predict-no for direction U in state State-A
  1819. In State-A moving U
  1820. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  1821. predict error 0
  1822. dir: dir isR
  1823. \252: O: O503 (predict-yes)
  1824. I see 1 and I'm going to do: predict-yes
  1825. ENV: Agent did: predict-yes for direction R in state State-A
  1826. In State-A moving R
  1827. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  1828. predict error 0
  1829. dir: dir isU
  1830. -/|253: O: O506 (predict-no)
  1831. I see 1 and I'm going to do: predict-no
  1832. ENV: Agent did: predict-no for direction U in state State-B
  1833. In State-B moving U
  1834. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  1835. predict error 0
  1836. dir: dir isU
  1837. \-/254: O: O508 (predict-no)
  1838. I see 1 and I'm going to do: predict-no
  1839. ENV: Agent did: predict-no for direction U in state State-B
  1840. In State-B moving U
  1841. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  1842. predict error 0
  1843. dir: dir isU
  1844. |\-255: O: O510 (predict-no)
  1845. I see 1 and I'm going to do: predict-no
  1846. ENV: Agent did: predict-no for direction U in state State-B
  1847. In State-B moving U
  1848. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  1849. predict error 0
  1850. dir: dir isL
  1851. /|\256: O: O511 (predict-yes)
  1852. I see 1 and I'm going to do: predict-yes
  1853. ENV: Agent did: predict-yes for direction L in state State-B
  1854. In State-B moving L
  1855. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  1856. predict error 0
  1857. dir: dir isU
  1858. -/|257: O: O514 (predict-no)
  1859. I see 1 and I'm going to do: predict-no
  1860. ENV: Agent did: predict-no for direction U in state State-A
  1861. In State-A moving U
  1862. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  1863. predict error 0
  1864. dir: dir isU
  1865. \-/258: O: O516 (predict-no)
  1866. I see 1 and I'm going to do: predict-no
  1867. ENV: Agent did: predict-no for direction U in state State-A
  1868. In State-A moving U
  1869. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  1870. predict error 0
  1871. dir: dir isR
  1872. |\259: O: O517 (predict-yes)
  1873. I see 1 and I'm going to do: predict-yes
  1874. ENV: Agent did: predict-yes for direction R in state State-A
  1875. In State-A moving R
  1876. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  1877. predict error 0
  1878. dir: dir isU
  1879. -/|260: O: O519 (predict-yes)
  1880. I see 1 and I'm going to do: predict-yes
  1881. ENV: Agent did: predict-yes for direction U in state State-B
  1882. In State-B moving U
  1883. ENV: (next state, see, prediction correct?) = (State-B, 0, False)
  1884. predict error 1
  1885. dir: dir isU
  1886. \-/261: O: O522 (predict-no)
  1887. I see 0 and I'm going to do: predict-no
  1888. ENV: Agent did: predict-no for direction U in state State-B
  1889. In State-B moving U
  1890. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  1891. predict error 0
  1892. dir: dir isR
  1893. |262: O: O524 (predict-no)
  1894. I see 1 and I'm going to do: predict-no
  1895. ENV: Agent did: predict-no for direction R in state State-B
  1896. In State-B moving R
  1897. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  1898. predict error 0
  1899. dir: dir isR
  1900. \-263: O: O526 (predict-no)
  1901. I see 1 and I'm going to do: predict-no
  1902. ENV: Agent did: predict-no for direction R in state State-B
  1903. In State-B moving R
  1904. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  1905. predict error 0
  1906. dir: dir isR
  1907. /|\264: O: O528 (predict-no)
  1908. I see 1 and I'm going to do: predict-no
  1909. ENV: Agent did: predict-no for direction R in state State-B
  1910. In State-B moving R
  1911. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  1912. predict error 0
  1913. dir: dir isL
  1914. -/|265: O: O529 (predict-yes)
  1915. I see 1 and I'm going to do: predict-yes
  1916. ENV: Agent did: predict-yes for direction L in state State-B
  1917. In State-B moving L
  1918. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  1919. predict error 0
  1920. dir: dir isR
  1921. \-/266: O: O531 (predict-yes)
  1922. I see 1 and I'm going to do: predict-yes
  1923. ENV: Agent did: predict-yes for direction R in state State-A
  1924. In State-A moving R
  1925. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  1926. predict error 0
  1927. dir: dir isL
  1928. |\267: O: O534 (predict-no)
  1929. I see 1 and I'm going to do: predict-no
  1930. ENV: Agent did: predict-no for direction L in state State-B
  1931. In State-B moving L
  1932. ENV: (next state, see, prediction correct?) = (State-A, 1, False)
  1933. predict error 1
  1934. dir: dir isL
  1935. -/268: O: O536 (predict-no)
  1936. I see 0 and I'm going to do: predict-no
  1937. ENV: Agent did: predict-no for direction L in state State-A
  1938. In State-A moving L
  1939. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  1940. predict error 0
  1941. dir: dir isR
  1942. |269: O: O537 (predict-yes)
  1943. I see 1 and I'm going to do: predict-yes
  1944. ENV: Agent did: predict-yes for direction R in state State-A
  1945. In State-A moving R
  1946. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  1947. predict error 0
  1948. dir: dir isU
  1949. \-/270: O: O540 (predict-no)
  1950. I see 1 and I'm going to do: predict-no
  1951. ENV: Agent did: predict-no for direction U in state State-B
  1952. In State-B moving U
  1953. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  1954. predict error 0
  1955. dir: dir isU
  1956. |\-271: O: O542 (predict-no)
  1957. I see 1 and I'm going to do: predict-no
  1958. ENV: Agent did: predict-no for direction U in state State-B
  1959. In State-B moving U
  1960. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  1961. predict error 0
  1962. dir: dir isR
  1963. /272: O: O543 (predict-yes)
  1964. I see 1 and I'm going to do: predict-yes
  1965. ENV: Agent did: predict-yes for direction R in state State-B
  1966. In State-B moving R
  1967. ENV: (next state, see, prediction correct?) = (State-B, 0, False)
  1968. predict error 1
  1969. dir: dir isR
  1970. |\-273: O: O546 (predict-no)
  1971. I see 0 and I'm going to do: predict-no
  1972. ENV: Agent did: predict-no for direction R in state State-B
  1973. In State-B moving R
  1974. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  1975. predict error 0
  1976. dir: dir isL
  1977. /|274: O: O547 (predict-yes)
  1978. I see 1 and I'm going to do: predict-yes
  1979. ENV: Agent did: predict-yes for direction L in state State-B
  1980. In State-B moving L
  1981. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  1982. predict error 0
  1983. dir: dir isL
  1984. \-/275: O: O550 (predict-no)
  1985. I see 1 and I'm going to do: predict-no
  1986. ENV: Agent did: predict-no for direction L in state State-A
  1987. In State-A moving L
  1988. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  1989. predict error 0
  1990. dir: dir isU
  1991. |\-276: O: O552 (predict-no)
  1992. I see 1 and I'm going to do: predict-no
  1993. ENV: Agent did: predict-no for direction U in state State-A
  1994. In State-A moving U
  1995. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  1996. predict error 0
  1997. dir: dir isL
  1998. /|\277: O: O554 (predict-no)
  1999. I see 1 and I'm going to do: predict-no
  2000. ENV: Agent did: predict-no for direction L in state State-A
  2001. In State-A moving L
  2002. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  2003. predict error 0
  2004. dir: dir isR
  2005. -/|278: O: O555 (predict-yes)
  2006. I see 1 and I'm going to do: predict-yes
  2007. ENV: Agent did: predict-yes for direction R in state State-A
  2008. In State-A moving R
  2009. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  2010. predict error 0
  2011. dir: dir isR
  2012. \-/279: O: O558 (predict-no)
  2013. I see 1 and I'm going to do: predict-no
  2014. ENV: Agent did: predict-no for direction R in state State-B
  2015. In State-B moving R
  2016. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2017. predict error 0
  2018. dir: dir isL
  2019. |\-280: O: O559 (predict-yes)
  2020. I see 1 and I'm going to do: predict-yes
  2021. ENV: Agent did: predict-yes for direction L in state State-B
  2022. In State-B moving L
  2023. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  2024. predict error 0
  2025. dir: dir isR
  2026. /281: O: O561 (predict-yes)
  2027. I see 1 and I'm going to do: predict-yes
  2028. ENV: Agent did: predict-yes for direction R in state State-A
  2029. In State-A moving R
  2030. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  2031. predict error 0
  2032. dir: dir isL
  2033. |282: O: O564 (predict-no)
  2034. I see 1 and I'm going to do: predict-no
  2035. ENV: Agent did: predict-no for direction L in state State-B
  2036. In State-B moving L
  2037. ENV: (next state, see, prediction correct?) = (State-A, 1, False)
  2038. predict error 1
  2039. dir: dir isL
  2040. \-/283: O: O565 (predict-yes)
  2041. I see 0 and I'm going to do: predict-yes
  2042. ENV: Agent did: predict-yes for direction L in state State-A
  2043. In State-A moving L
  2044. ENV: (next state, see, prediction correct?) = (State-A, 0, False)
  2045. predict error 1
  2046. dir: dir isL
  2047. |\284: O: O568 (predict-no)
  2048. I see 0 and I'm going to do: predict-no
  2049. ENV: Agent did: predict-no for direction L in state State-A
  2050. In State-A moving L
  2051. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  2052. predict error 0
  2053. dir: dir isR
  2054. -/|285: O: O569 (predict-yes)
  2055. I see 1 and I'm going to do: predict-yes
  2056. ENV: Agent did: predict-yes for direction R in state State-A
  2057. In State-A moving R
  2058. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  2059. predict error 0
  2060. dir: dir isL
  2061. \-/286: O: O571 (predict-yes)
  2062. I see 1 and I'm going to do: predict-yes
  2063. ENV: Agent did: predict-yes for direction L in state State-B
  2064. In State-B moving L
  2065. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  2066. predict error 0
  2067. dir: dir isR
  2068. |287: O: O573 (predict-yes)
  2069. I see 1 and I'm going to do: predict-yes
  2070. ENV: Agent did: predict-yes for direction R in state State-A
  2071. In State-A moving R
  2072. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  2073. predict error 0
  2074. dir: dir isL
  2075. \-/288: O: O575 (predict-yes)
  2076. I see 1 and I'm going to do: predict-yes
  2077. ENV: Agent did: predict-yes for direction L in state State-B
  2078. In State-B moving L
  2079. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  2080. predict error 0
  2081. dir: dir isR
  2082. |\289: O: O577 (predict-yes)
  2083. I see 1 and I'm going to do: predict-yes
  2084. ENV: Agent did: predict-yes for direction R in state State-A
  2085. In State-A moving R
  2086. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  2087. predict error 0
  2088. dir: dir isL
  2089. -/|290: O: O579 (predict-yes)
  2090. I see 1 and I'm going to do: predict-yes
  2091. ENV: Agent did: predict-yes for direction L in state State-B
  2092. In State-B moving L
  2093. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  2094. predict error 0
  2095. dir: dir isU
  2096. \-291: O: O582 (predict-no)
  2097. I see 1 and I'm going to do: predict-no
  2098. ENV: Agent did: predict-no for direction U in state State-A
  2099. In State-A moving U
  2100. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  2101. predict error 0
  2102. dir: dir isR
  2103. /292: O: O583 (predict-yes)
  2104. I see 1 and I'm going to do: predict-yes
  2105. ENV: Agent did: predict-yes for direction R in state State-A
  2106. In State-A moving R
  2107. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  2108. predict error 0
  2109. dir: dir isU
  2110. |\-293: O: O585 (predict-yes)
  2111. I see 1 and I'm going to do: predict-yes
  2112. ENV: Agent did: predict-yes for direction U in state State-B
  2113. In State-B moving U
  2114. ENV: (next state, see, prediction correct?) = (State-B, 0, False)
  2115. predict error 1
  2116. dir: dir isU
  2117. /|\294: O: O587 (predict-yes)
  2118. I see 0 and I'm going to do: predict-yes
  2119. ENV: Agent did: predict-yes for direction U in state State-B
  2120. In State-B moving U
  2121. ENV: (next state, see, prediction correct?) = (State-B, 0, False)
  2122. predict error 1
  2123. dir: dir isR
  2124. -/|295: O: O590 (predict-no)
  2125. I see 0 and I'm going to do: predict-no
  2126. ENV: Agent did: predict-no for direction R in state State-B
  2127. In State-B moving R
  2128. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2129. predict error 0
  2130. dir: dir isR
  2131. \-/296: O: O592 (predict-no)
  2132. I see 1 and I'm going to do: predict-no
  2133. ENV: Agent did: predict-no for direction R in state State-B
  2134. In State-B moving R
  2135. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2136. predict error 0
  2137. dir: dir isU
  2138. |\-297: O: O594 (predict-no)
  2139. I see 1 and I'm going to do: predict-no
  2140. ENV: Agent did: predict-no for direction U in state State-B
  2141. In State-B moving U
  2142. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2143. predict error 0
  2144. dir: dir isR
  2145. /|\298: O: O596 (predict-no)
  2146. I see 1 and I'm going to do: predict-no
  2147. ENV: Agent did: predict-no for direction R in state State-B
  2148. In State-B moving R
  2149. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2150. predict error 0
  2151. dir: dir isL
  2152. -/|299: O: O597 (predict-yes)
  2153. I see 1 and I'm going to do: predict-yes
  2154. ENV: Agent did: predict-yes for direction L in state State-B
  2155. In State-B moving L
  2156. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  2157. predict error 0
  2158. dir: dir isU
  2159. \-300: O: O600 (predict-no)
  2160. I see 1 and I'm going to do: predict-no
  2161. ENV: Agent did: predict-no for direction U in state State-A
  2162. In State-A moving U
  2163. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  2164. predict error 0
  2165. dir: dir isU
  2166. /|\-/|301: O: O602 (predict-no)
  2167. I see 1 and I'm going to do: predict-no
  2168. ENV: Agent did: predict-no for direction U in state State-A
  2169. In State-A moving U
  2170. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  2171. predict error 0
  2172. dir: dir isU
  2173. \302: O: O604 (predict-no)
  2174. I see 1 and I'm going to do: predict-no
  2175. ENV: Agent did: predict-no for direction U in state State-A
  2176. In State-A moving U
  2177. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  2178. predict error 0
  2179. dir: dir isR
  2180. -/|303: O: O605 (predict-yes)
  2181. I see 1 and I'm going to do: predict-yes
  2182. ENV: Agent did: predict-yes for direction R in state State-A
  2183. In State-A moving R
  2184. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  2185. predict error 0
  2186. dir: dir isR
  2187. \-/|304: O: O608 (predict-no)
  2188. I see 1 and I'm going to do: predict-no
  2189. ENV: Agent did: predict-no for direction R in state State-B
  2190. In State-B moving R
  2191. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2192. predict error 0
  2193. dir: dir isU
  2194. \305: O: O610 (predict-no)
  2195. I see 1 and I'm going to do: predict-no
  2196. ENV: Agent did: predict-no for direction U in state State-B
  2197. In State-B moving U
  2198. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2199. predict error 0
  2200. dir: dir isR
  2201. -/306: O: O612 (predict-no)
  2202. I see 1 and I'm going to do: predict-no
  2203. ENV: Agent did: predict-no for direction R in state State-B
  2204. In State-B moving R
  2205. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2206. predict error 0
  2207. dir: dir isL
  2208. |\307: O: O613 (predict-yes)
  2209. I see 1 and I'm going to do: predict-yes
  2210. ENV: Agent did: predict-yes for direction L in state State-B
  2211. In State-B moving L
  2212. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  2213. predict error 0
  2214. dir: dir isL
  2215. -/|308: O: O616 (predict-no)
  2216. I see 1 and I'm going to do: predict-no
  2217. ENV: Agent did: predict-no for direction L in state State-A
  2218. In State-A moving L
  2219. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  2220. predict error 0
  2221. dir: dir isU
  2222. \-/309: O: O618 (predict-no)
  2223. I see 1 and I'm going to do: predict-no
  2224. ENV: Agent did: predict-no for direction U in state State-A
  2225. In State-A moving U
  2226. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  2227. predict error 0
  2228. dir: dir isL
  2229. |\-310: O: O620 (predict-no)
  2230. I see 1 and I'm going to do: predict-no
  2231. ENV: Agent did: predict-no for direction L in state State-A
  2232. In State-A moving L
  2233. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  2234. predict error 0
  2235. dir: dir isL
  2236. /|\311: O: O622 (predict-no)
  2237. I see 1 and I'm going to do: predict-no
  2238. ENV: Agent did: predict-no for direction L in state State-A
  2239. In State-A moving L
  2240. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  2241. predict error 0
  2242. dir: dir isR
  2243. -312: O: O623 (predict-yes)
  2244. I see 1 and I'm going to do: predict-yes
  2245. ENV: Agent did: predict-yes for direction R in state State-A
  2246. In State-A moving R
  2247. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  2248. predict error 0
  2249. dir: dir isR
  2250. /|\313: O: O626 (predict-no)
  2251. I see 1 and I'm going to do: predict-no
  2252. ENV: Agent did: predict-no for direction R in state State-B
  2253. In State-B moving R
  2254. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2255. predict error 0
  2256. dir: dir isR
  2257. -/|314: O: O628 (predict-no)
  2258. I see 1 and I'm going to do: predict-no
  2259. ENV: Agent did: predict-no for direction R in state State-B
  2260. In State-B moving R
  2261. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2262. predict error 0
  2263. dir: dir isR
  2264. \-/|315: O: O630 (predict-no)
  2265. I see 1 and I'm going to do: predict-no
  2266. ENV: Agent did: predict-no for direction R in state State-B
  2267. In State-B moving R
  2268. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2269. predict error 0
  2270. dir: dir isR
  2271. \-/316: O: O632 (predict-no)
  2272. I see 1 and I'm going to do: predict-no
  2273. ENV: Agent did: predict-no for direction R in state State-B
  2274. In State-B moving R
  2275. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2276. predict error 0
  2277. dir: dir isU
  2278. |\-317: O: O634 (predict-no)
  2279. I see 1 and I'm going to do: predict-no
  2280. ENV: Agent did: predict-no for direction U in state State-B
  2281. In State-B moving U
  2282. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2283. predict error 0
  2284. dir: dir isR
  2285. /|\318: O: O636 (predict-no)
  2286. I see 1 and I'm going to do: predict-no
  2287. ENV: Agent did: predict-no for direction R in state State-B
  2288. In State-B moving R
  2289. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2290. predict error 0
  2291. dir: dir isR
  2292. -/319: O: O638 (predict-no)
  2293. I see 1 and I'm going to do: predict-no
  2294. ENV: Agent did: predict-no for direction R in state State-B
  2295. In State-B moving R
  2296. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2297. predict error 0
  2298. dir: dir isU
  2299. |\-320: O: O640 (predict-no)
  2300. I see 1 and I'm going to do: predict-no
  2301. ENV: Agent did: predict-no for direction U in state State-B
  2302. In State-B moving U
  2303. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2304. predict error 0
  2305. dir: dir isL
  2306. /|\321: O: O641 (predict-yes)
  2307. I see 1 and I'm going to do: predict-yes
  2308. ENV: Agent did: predict-yes for direction L in state State-B
  2309. In State-B moving L
  2310. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  2311. predict error 0
  2312. dir: dir isU
  2313. -322: O: O644 (predict-no)
  2314. I see 1 and I'm going to do: predict-no
  2315. ENV: Agent did: predict-no for direction U in state State-A
  2316. In State-A moving U
  2317. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  2318. predict error 0
  2319. dir: dir isR
  2320. /|\323: O: O645 (predict-yes)
  2321. I see 1 and I'm going to do: predict-yes
  2322. ENV: Agent did: predict-yes for direction R in state State-A
  2323. In State-A moving R
  2324. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  2325. predict error 0
  2326. dir: dir isR
  2327. -/|324: O: O648 (predict-no)
  2328. I see 1 and I'm going to do: predict-no
  2329. ENV: Agent did: predict-no for direction R in state State-B
  2330. In State-B moving R
  2331. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2332. predict error 0
  2333. dir: dir isL
  2334. \-/325: O: O649 (predict-yes)
  2335. I see 1 and I'm going to do: predict-yes
  2336. ENV: Agent did: predict-yes for direction L in state State-B
  2337. In State-B moving L
  2338. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  2339. predict error 0
  2340. dir: dir isU
  2341. |\-326: O: O652 (predict-no)
  2342. I see 1 and I'm going to do: predict-no
  2343. ENV: Agent did: predict-no for direction U in state State-A
  2344. In State-A moving U
  2345. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  2346. predict error 0
  2347. dir: dir isU
  2348. /|\327: O: O653 (predict-yes)
  2349. I see 1 and I'm going to do: predict-yes
  2350. ENV: Agent did: predict-yes for direction U in state State-A
  2351. In State-A moving U
  2352. ENV: (next state, see, prediction correct?) = (State-A, 0, False)
  2353. predict error 1
  2354. dir: dir isU
  2355. -/|328: O: O656 (predict-no)
  2356. I see 0 and I'm going to do: predict-no
  2357. ENV: Agent did: predict-no for direction U in state State-A
  2358. In State-A moving U
  2359. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  2360. predict error 0
  2361. dir: dir isR
  2362. \-/329: O: O657 (predict-yes)
  2363. I see 1 and I'm going to do: predict-yes
  2364. ENV: Agent did: predict-yes for direction R in state State-A
  2365. In State-A moving R
  2366. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  2367. predict error 0
  2368. dir: dir isU
  2369. |\-330: O: O660 (predict-no)
  2370. I see 1 and I'm going to do: predict-no
  2371. ENV: Agent did: predict-no for direction U in state State-B
  2372. In State-B moving U
  2373. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2374. predict error 0
  2375. dir: dir isL
  2376. /|\331: O: O661 (predict-yes)
  2377. I see 1 and I'm going to do: predict-yes
  2378. ENV: Agent did: predict-yes for direction L in state State-B
  2379. In State-B moving L
  2380. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  2381. predict error 0
  2382. dir: dir isR
  2383. -332: O: O663 (predict-yes)
  2384. I see 1 and I'm going to do: predict-yes
  2385. ENV: Agent did: predict-yes for direction R in state State-A
  2386. In State-A moving R
  2387. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  2388. predict error 0
  2389. dir: dir isL
  2390. /333: O: O665 (predict-yes)
  2391. I see 1 and I'm going to do: predict-yes
  2392. ENV: Agent did: predict-yes for direction L in state State-B
  2393. In State-B moving L
  2394. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  2395. predict error 0
  2396. dir: dir isL
  2397. |\-334: O: O668 (predict-no)
  2398. I see 1 and I'm going to do: predict-no
  2399. ENV: Agent did: predict-no for direction L in state State-A
  2400. In State-A moving L
  2401. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  2402. predict error 0
  2403. dir: dir isU
  2404. /|\335: O: O670 (predict-no)
  2405. I see 1 and I'm going to do: predict-no
  2406. ENV: Agent did: predict-no for direction U in state State-A
  2407. In State-A moving U
  2408. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  2409. predict error 0
  2410. dir: dir isL
  2411. -/|336: O: O672 (predict-no)
  2412. I see 1 and I'm going to do: predict-no
  2413. ENV: Agent did: predict-no for direction L in state State-A
  2414. In State-A moving L
  2415. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  2416. predict error 0
  2417. dir: dir isL
  2418. \-/337: O: O674 (predict-no)
  2419. I see 1 and I'm going to do: predict-no
  2420. ENV: Agent did: predict-no for direction L in state State-A
  2421. In State-A moving L
  2422. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  2423. predict error 0
  2424. dir: dir isL
  2425. |\-338: O: O676 (predict-no)
  2426. I see 1 and I'm going to do: predict-no
  2427. ENV: Agent did: predict-no for direction L in state State-A
  2428. In State-A moving L
  2429. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  2430. predict error 0
  2431. dir: dir isR
  2432. /|\339: O: O677 (predict-yes)
  2433. I see 1 and I'm going to do: predict-yes
  2434. ENV: Agent did: predict-yes for direction R in state State-A
  2435. In State-A moving R
  2436. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  2437. predict error 0
  2438. dir: dir isR
  2439. -/|340: O: O680 (predict-no)
  2440. I see 1 and I'm going to do: predict-no
  2441. ENV: Agent did: predict-no for direction R in state State-B
  2442. In State-B moving R
  2443. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2444. predict error 0
  2445. dir: dir isL
  2446. \-/341: O: O681 (predict-yes)
  2447. I see 1 and I'm going to do: predict-yes
  2448. ENV: Agent did: predict-yes for direction L in state State-B
  2449. In State-B moving L
  2450. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  2451. predict error 0
  2452. dir: dir isU
  2453. |342: O: O684 (predict-no)
  2454. I see 1 and I'm going to do: predict-no
  2455. ENV: Agent did: predict-no for direction U in state State-A
  2456. In State-A moving U
  2457. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  2458. predict error 0
  2459. dir: dir isU
  2460. \-/343: O: O686 (predict-no)
  2461. I see 1 and I'm going to do: predict-no
  2462. ENV: Agent did: predict-no for direction U in state State-A
  2463. In State-A moving U
  2464. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  2465. predict error 0
  2466. dir: dir isL
  2467. |\-/344: O: O688 (predict-no)
  2468. I see 1 and I'm going to do: predict-no
  2469. ENV: Agent did: predict-no for direction L in state State-A
  2470. In State-A moving L
  2471. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  2472. predict error 0
  2473. dir: dir isR
  2474. |\-345: O: O689 (predict-yes)
  2475. I see 1 and I'm going to do: predict-yes
  2476. ENV: Agent did: predict-yes for direction R in state State-A
  2477. In State-A moving R
  2478. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  2479. predict error 0
  2480. dir: dir isU
  2481. /|\346: O: O692 (predict-no)
  2482. I see 1 and I'm going to do: predict-no
  2483. ENV: Agent did: predict-no for direction U in state State-B
  2484. In State-B moving U
  2485. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2486. predict error 0
  2487. dir: dir isU
  2488. -347: O: O694 (predict-no)
  2489. I see 1 and I'm going to do: predict-no
  2490. ENV: Agent did: predict-no for direction U in state State-B
  2491. In State-B moving U
  2492. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2493. predict error 0
  2494. dir: dir isR
  2495. /|348: O: O696 (predict-no)
  2496. I see 1 and I'm going to do: predict-no
  2497. ENV: Agent did: predict-no for direction R in state State-B
  2498. In State-B moving R
  2499. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2500. predict error 0
  2501. dir: dir isU
  2502. \-/349: O: O698 (predict-no)
  2503. I see 1 and I'm going to do: predict-no
  2504. ENV: Agent did: predict-no for direction U in state State-B
  2505. In State-B moving U
  2506. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2507. predict error 0
  2508. dir: dir isL
  2509. |\-350: O: O699 (predict-yes)
  2510. I see 1 and I'm going to do: predict-yes
  2511. ENV: Agent did: predict-yes for direction L in state State-B
  2512. In State-B moving L
  2513. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  2514. predict error 0
  2515. dir: dir isR
  2516. /|351: O: O701 (predict-yes)
  2517. I see 1 and I'm going to do: predict-yes
  2518. ENV: Agent did: predict-yes for direction R in state State-A
  2519. In State-A moving R
  2520. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  2521. predict error 0
  2522. dir: dir isR
  2523. \352: O: O704 (predict-no)
  2524. I see 1 and I'm going to do: predict-no
  2525. ENV: Agent did: predict-no for direction R in state State-B
  2526. In State-B moving R
  2527. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2528. predict error 0
  2529. dir: dir isU
  2530. -353: O: O706 (predict-no)
  2531. I see 1 and I'm going to do: predict-no
  2532. ENV: Agent did: predict-no for direction U in state State-B
  2533. In State-B moving U
  2534. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2535. predict error 0
  2536. dir: dir isL
  2537. /|\354: O: O707 (predict-yes)
  2538. I see 1 and I'm going to do: predict-yes
  2539. ENV: Agent did: predict-yes for direction L in state State-B
  2540. In State-B moving L
  2541. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  2542. predict error 0
  2543. dir: dir isR
  2544. -/|355: O: O710 (predict-no)
  2545. I see 1 and I'm going to do: predict-no
  2546. ENV: Agent did: predict-no for direction R in state State-A
  2547. In State-A moving R
  2548. ENV: (next state, see, prediction correct?) = (State-B, 1, False)
  2549. predict error 1
  2550. dir: dir isL
  2551. \-/356: O: O711 (predict-yes)
  2552. I see 0 and I'm going to do: predict-yes
  2553. ENV: Agent did: predict-yes for direction L in state State-B
  2554. In State-B moving L
  2555. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  2556. predict error 0
  2557. dir: dir isR
  2558. |\-357: O: O713 (predict-yes)
  2559. I see 1 and I'm going to do: predict-yes
  2560. ENV: Agent did: predict-yes for direction R in state State-A
  2561. In State-A moving R
  2562. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  2563. predict error 0
  2564. dir: dir isU
  2565. /|\358: O: O716 (predict-no)
  2566. I see 1 and I'm going to do: predict-no
  2567. ENV: Agent did: predict-no for direction U in state State-B
  2568. In State-B moving U
  2569. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2570. predict error 0
  2571. dir: dir isU
  2572. -/|359: O: O718 (predict-no)
  2573. I see 1 and I'm going to do: predict-no
  2574. ENV: Agent did: predict-no for direction U in state State-B
  2575. In State-B moving U
  2576. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2577. predict error 0
  2578. dir: dir isU
  2579. \-/|360: O: O720 (predict-no)
  2580. I see 1 and I'm going to do: predict-no
  2581. ENV: Agent did: predict-no for direction U in state State-B
  2582. In State-B moving U
  2583. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2584. predict error 0
  2585. dir: dir isL
  2586. \-/361: O: O721 (predict-yes)
  2587. I see 1 and I'm going to do: predict-yes
  2588. ENV: Agent did: predict-yes for direction L in state State-B
  2589. In State-B moving L
  2590. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  2591. predict error 0
  2592. dir: dir isL
  2593. |362: O: O724 (predict-no)
  2594. I see 1 and I'm going to do: predict-no
  2595. ENV: Agent did: predict-no for direction L in state State-A
  2596. In State-A moving L
  2597. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  2598. predict error 0
  2599. dir: dir isL
  2600. \-/363: O: O726 (predict-no)
  2601. I see 1 and I'm going to do: predict-no
  2602. ENV: Agent did: predict-no for direction L in state State-A
  2603. In State-A moving L
  2604. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  2605. predict error 0
  2606. dir: dir isU
  2607. |\-364: O: O728 (predict-no)
  2608. I see 1 and I'm going to do: predict-no
  2609. ENV: Agent did: predict-no for direction U in state State-A
  2610. In State-A moving U
  2611. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  2612. predict error 0
  2613. dir: dir isU
  2614. /|\365: O: O730 (predict-no)
  2615. I see 1 and I'm going to do: predict-no
  2616. ENV: Agent did: predict-no for direction U in state State-A
  2617. In State-A moving U
  2618. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  2619. predict error 0
  2620. dir: dir isR
  2621. -/|366: O: O731 (predict-yes)
  2622. I see 1 and I'm going to do: predict-yes
  2623. ENV: Agent did: predict-yes for direction R in state State-A
  2624. In State-A moving R
  2625. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  2626. predict error 0
  2627. dir: dir isU
  2628. \-/367: O: O734 (predict-no)
  2629. I see 1 and I'm going to do: predict-no
  2630. ENV: Agent did: predict-no for direction U in state State-B
  2631. In State-B moving U
  2632. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2633. predict error 0
  2634. dir: dir isU
  2635. |\-368: O: O735 (predict-yes)
  2636. I see 1 and I'm going to do: predict-yes
  2637. ENV: Agent did: predict-yes for direction U in state State-B
  2638. In State-B moving U
  2639. ENV: (next state, see, prediction correct?) = (State-B, 0, False)
  2640. predict error 1
  2641. dir: dir isL
  2642. /|\369: O: O737 (predict-yes)
  2643. I see 0 and I'm going to do: predict-yes
  2644. ENV: Agent did: predict-yes for direction L in state State-B
  2645. In State-B moving L
  2646. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  2647. predict error 0
  2648. dir: dir isL
  2649. -/|370: O: O740 (predict-no)
  2650. I see 1 and I'm going to do: predict-no
  2651. ENV: Agent did: predict-no for direction L in state State-A
  2652. In State-A moving L
  2653. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  2654. predict error 0
  2655. dir: dir isU
  2656. \-/371: O: O742 (predict-no)
  2657. I see 1 and I'm going to do: predict-no
  2658. ENV: Agent did: predict-no for direction U in state State-A
  2659. In State-A moving U
  2660. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  2661. predict error 0
  2662. dir: dir isL
  2663. |372: O: O744 (predict-no)
  2664. I see 1 and I'm going to do: predict-no
  2665. ENV: Agent did: predict-no for direction L in state State-A
  2666. In State-A moving L
  2667. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  2668. predict error 0
  2669. dir: dir isL
  2670. \-/373: O: O746 (predict-no)
  2671. I see 1 and I'm going to do: predict-no
  2672. ENV: Agent did: predict-no for direction L in state State-A
  2673. In State-A moving L
  2674. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  2675. predict error 0
  2676. dir: dir isL
  2677. |\-374: O: O748 (predict-no)
  2678. I see 1 and I'm going to do: predict-no
  2679. ENV: Agent did: predict-no for direction L in state State-A
  2680. In State-A moving L
  2681. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  2682. predict error 0
  2683. dir: dir isL
  2684. /375: O: O750 (predict-no)
  2685. I see 1 and I'm going to do: predict-no
  2686. ENV: Agent did: predict-no for direction L in state State-A
  2687. In State-A moving L
  2688. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  2689. predict error 0
  2690. dir: dir isU
  2691. |\-376: O: O752 (predict-no)
  2692. I see 1 and I'm going to do: predict-no
  2693. ENV: Agent did: predict-no for direction U in state State-A
  2694. In State-A moving U
  2695. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  2696. predict error 0
  2697. dir: dir isL
  2698. /|377: O: O754 (predict-no)
  2699. I see 1 and I'm going to do: predict-no
  2700. ENV: Agent did: predict-no for direction L in state State-A
  2701. In State-A moving L
  2702. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  2703. predict error 0
  2704. dir: dir isL
  2705. \-/378: O: O756 (predict-no)
  2706. I see 1 and I'm going to do: predict-no
  2707. ENV: Agent did: predict-no for direction L in state State-A
  2708. In State-A moving L
  2709. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  2710. predict error 0
  2711. dir: dir isL
  2712. |\-379: O: O758 (predict-no)
  2713. I see 1 and I'm going to do: predict-no
  2714. ENV: Agent did: predict-no for direction L in state State-A
  2715. In State-A moving L
  2716. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  2717. predict error 0
  2718. dir: dir isR
  2719. /|\380: O: O759 (predict-yes)
  2720. I see 1 and I'm going to do: predict-yes
  2721. ENV: Agent did: predict-yes for direction R in state State-A
  2722. In State-A moving R
  2723. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  2724. predict error 0
  2725. dir: dir isU
  2726. -/|381: O: O762 (predict-no)
  2727. I see 1 and I'm going to do: predict-no
  2728. ENV: Agent did: predict-no for direction U in state State-B
  2729. In State-B moving U
  2730. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2731. predict error 0
  2732. dir: dir isR
  2733. \382: O: O764 (predict-no)
  2734. I see 1 and I'm going to do: predict-no
  2735. ENV: Agent did: predict-no for direction R in state State-B
  2736. In State-B moving R
  2737. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2738. predict error 0
  2739. dir: dir isU
  2740. -/|383: O: O766 (predict-no)
  2741. I see 1 and I'm going to do: predict-no
  2742. ENV: Agent did: predict-no for direction U in state State-B
  2743. In State-B moving U
  2744. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2745. predict error 0
  2746. dir: dir isR
  2747. \384: O: O768 (predict-no)
  2748. I see 1 and I'm going to do: predict-no
  2749. ENV: Agent did: predict-no for direction R in state State-B
  2750. In State-B moving R
  2751. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2752. predict error 0
  2753. dir: dir isR
  2754. -/385: O: O770 (predict-no)
  2755. I see 1 and I'm going to do: predict-no
  2756. ENV: Agent did: predict-no for direction R in state State-B
  2757. In State-B moving R
  2758. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2759. predict error 0
  2760. dir: dir isU
  2761. |\-386: O: O772 (predict-no)
  2762. I see 1 and I'm going to do: predict-no
  2763. ENV: Agent did: predict-no for direction U in state State-B
  2764. In State-B moving U
  2765. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2766. predict error 0
  2767. dir: dir isU
  2768. /|\387: O: O774 (predict-no)
  2769. I see 1 and I'm going to do: predict-no
  2770. ENV: Agent did: predict-no for direction U in state State-B
  2771. In State-B moving U
  2772. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2773. predict error 0
  2774. dir: dir isU
  2775. -/|388: O: O776 (predict-no)
  2776. I see 1 and I'm going to do: predict-no
  2777. ENV: Agent did: predict-no for direction U in state State-B
  2778. In State-B moving U
  2779. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2780. predict error 0
  2781. dir: dir isU
  2782. \-389: O: O778 (predict-no)
  2783. I see 1 and I'm going to do: predict-no
  2784. ENV: Agent did: predict-no for direction U in state State-B
  2785. In State-B moving U
  2786. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2787. predict error 0
  2788. dir: dir isU
  2789. /390: O: O780 (predict-no)
  2790. I see 1 and I'm going to do: predict-no
  2791. ENV: Agent did: predict-no for direction U in state State-B
  2792. In State-B moving U
  2793. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2794. predict error 0
  2795. dir: dir isU
  2796. |\-391: O: O782 (predict-no)
  2797. I see 1 and I'm going to do: predict-no
  2798. ENV: Agent did: predict-no for direction U in state State-B
  2799. In State-B moving U
  2800. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2801. predict error 0
  2802. dir: dir isL
  2803. /392: O: O784 (predict-no)
  2804. I see 1 and I'm going to do: predict-no
  2805. ENV: Agent did: predict-no for direction L in state State-B
  2806. In State-B moving L
  2807. ENV: (next state, see, prediction correct?) = (State-A, 1, False)
  2808. predict error 1
  2809. dir: dir isR
  2810. |\-393: O: O785 (predict-yes)
  2811. I see 0 and I'm going to do: predict-yes
  2812. ENV: Agent did: predict-yes for direction R in state State-A
  2813. In State-A moving R
  2814. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  2815. predict error 0
  2816. dir: dir isR
  2817. /|\394: O: O788 (predict-no)
  2818. I see 1 and I'm going to do: predict-no
  2819. ENV: Agent did: predict-no for direction R in state State-B
  2820. In State-B moving R
  2821. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2822. predict error 0
  2823. dir: dir isU
  2824. -/|395: O: O790 (predict-no)
  2825. I see 1 and I'm going to do: predict-no
  2826. ENV: Agent did: predict-no for direction U in state State-B
  2827. In State-B moving U
  2828. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2829. predict error 0
  2830. dir: dir isR
  2831. \-396: O: O792 (predict-no)
  2832. I see 1 and I'm going to do: predict-no
  2833. ENV: Agent did: predict-no for direction R in state State-B
  2834. In State-B moving R
  2835. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2836. predict error 0
  2837. dir: dir isU
  2838. /|\397: O: O794 (predict-no)
  2839. I see 1 and I'm going to do: predict-no
  2840. ENV: Agent did: predict-no for direction U in state State-B
  2841. In State-B moving U
  2842. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2843. predict error 0
  2844. dir: dir isR
  2845. -/|398: O: O796 (predict-no)
  2846. I see 1 and I'm going to do: predict-no
  2847. ENV: Agent did: predict-no for direction R in state State-B
  2848. In State-B moving R
  2849. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2850. predict error 0
  2851. dir: dir isR
  2852. \-/399: O: O798 (predict-no)
  2853. I see 1 and I'm going to do: predict-no
  2854. ENV: Agent did: predict-no for direction R in state State-B
  2855. In State-B moving R
  2856. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2857. predict error 0
  2858. dir: dir isU
  2859. |\-400: O: O800 (predict-no)
  2860. I see 1 and I'm going to do: predict-no
  2861. ENV: Agent did: predict-no for direction U in state State-B
  2862. In State-B moving U
  2863. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2864. predict error 0
  2865. dir: dir isU
  2866. /|\401: O: O802 (predict-no)
  2867. I see 1 and I'm going to do: predict-no
  2868. ENV: Agent did: predict-no for direction U in state State-B
  2869. In State-B moving U
  2870. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2871. predict error 0
  2872. dir: dir isR
  2873. -402: O: O804 (predict-no)
  2874. I see 1 and I'm going to do: predict-no
  2875. ENV: Agent did: predict-no for direction R in state State-B
  2876. In State-B moving R
  2877. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2878. predict error 0
  2879. dir: dir isL
  2880. /|\403: O: O805 (predict-yes)
  2881. I see 1 and I'm going to do: predict-yes
  2882. ENV: Agent did: predict-yes for direction L in state State-B
  2883. In State-B moving L
  2884. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  2885. predict error 0
  2886. dir: dir isL
  2887. -/404: O: O808 (predict-no)
  2888. I see 1 and I'm going to do: predict-no
  2889. ENV: Agent did: predict-no for direction L in state State-A
  2890. In State-A moving L
  2891. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  2892. predict error 0
  2893. dir: dir isR
  2894. |\405: O: O809 (predict-yes)
  2895. I see 1 and I'm going to do: predict-yes
  2896. ENV: Agent did: predict-yes for direction R in state State-A
  2897. In State-A moving R
  2898. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  2899. predict error 0
  2900. dir: dir isL
  2901. -/|406: O: O811 (predict-yes)
  2902. I see 1 and I'm going to do: predict-yes
  2903. ENV: Agent did: predict-yes for direction L in state State-B
  2904. In State-B moving L
  2905. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  2906. predict error 0
  2907. dir: dir isL
  2908. \-407: O: O813 (predict-yes)
  2909. I see 1 and I'm going to do: predict-yes
  2910. ENV: Agent did: predict-yes for direction L in state State-A
  2911. In State-A moving L
  2912. ENV: (next state, see, prediction correct?) = (State-A, 0, False)
  2913. predict error 1
  2914. dir: dir isU
  2915. /|408: O: O816 (predict-no)
  2916. I see 0 and I'm going to do: predict-no
  2917. ENV: Agent did: predict-no for direction U in state State-A
  2918. In State-A moving U
  2919. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  2920. predict error 0
  2921. dir: dir isU
  2922. \-/409: O: O818 (predict-no)
  2923. I see 1 and I'm going to do: predict-no
  2924. ENV: Agent did: predict-no for direction U in state State-A
  2925. In State-A moving U
  2926. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  2927. predict error 0
  2928. dir: dir isL
  2929. |\-410: O: O820 (predict-no)
  2930. I see 1 and I'm going to do: predict-no
  2931. ENV: Agent did: predict-no for direction L in state State-A
  2932. In State-A moving L
  2933. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  2934. predict error 0
  2935. dir: dir isR
  2936. /|411: O: O821 (predict-yes)
  2937. I see 1 and I'm going to do: predict-yes
  2938. ENV: Agent did: predict-yes for direction R in state State-A
  2939. In State-A moving R
  2940. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  2941. predict error 0
  2942. dir: dir isU
  2943. \412: O: O824 (predict-no)
  2944. I see 1 and I'm going to do: predict-no
  2945. ENV: Agent did: predict-no for direction U in state State-B
  2946. In State-B moving U
  2947. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2948. predict error 0
  2949. dir: dir isL
  2950. -/|413: O: O825 (predict-yes)
  2951. I see 1 and I'm going to do: predict-yes
  2952. ENV: Agent did: predict-yes for direction L in state State-B
  2953. In State-B moving L
  2954. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  2955. predict error 0
  2956. dir: dir isR
  2957. \-/414: O: O827 (predict-yes)
  2958. I see 1 and I'm going to do: predict-yes
  2959. ENV: Agent did: predict-yes for direction R in state State-A
  2960. In State-A moving R
  2961. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  2962. predict error 0
  2963. dir: dir isL
  2964. |\-415: O: O829 (predict-yes)
  2965. I see 1 and I'm going to do: predict-yes
  2966. ENV: Agent did: predict-yes for direction L in state State-B
  2967. In State-B moving L
  2968. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  2969. predict error 0
  2970. dir: dir isL
  2971. /|\416: O: O832 (predict-no)
  2972. I see 1 and I'm going to do: predict-no
  2973. ENV: Agent did: predict-no for direction L in state State-A
  2974. In State-A moving L
  2975. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  2976. predict error 0
  2977. dir: dir isU
  2978. -/|417: O: O834 (predict-no)
  2979. I see 1 and I'm going to do: predict-no
  2980. ENV: Agent did: predict-no for direction U in state State-A
  2981. In State-A moving U
  2982. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  2983. predict error 0
  2984. dir: dir isL
  2985. \-/418: O: O836 (predict-no)
  2986. I see 1 and I'm going to do: predict-no
  2987. ENV: Agent did: predict-no for direction L in state State-A
  2988. In State-A moving L
  2989. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  2990. predict error 0
  2991. dir: dir isL
  2992. |\-419: O: O838 (predict-no)
  2993. I see 1 and I'm going to do: predict-no
  2994. ENV: Agent did: predict-no for direction L in state State-A
  2995. In State-A moving L
  2996. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  2997. predict error 0
  2998. dir: dir isR
  2999. /|\420: O: O839 (predict-yes)
  3000. I see 1 and I'm going to do: predict-yes
  3001. ENV: Agent did: predict-yes for direction R in state State-A
  3002. In State-A moving R
  3003. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  3004. predict error 0
  3005. dir: dir isR
  3006. -/421: O: O842 (predict-no)
  3007. I see 1 and I'm going to do: predict-no
  3008. ENV: Agent did: predict-no for direction R in state State-B
  3009. In State-B moving R
  3010. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3011. predict error 0
  3012. dir: dir isU
  3013. |422: O: O843 (predict-yes)
  3014. I see 1 and I'm going to do: predict-yes
  3015. ENV: Agent did: predict-yes for direction U in state State-B
  3016. In State-B moving U
  3017. ENV: (next state, see, prediction correct?) = (State-B, 0, False)
  3018. predict error 1
  3019. dir: dir isU
  3020. \-/423: O: O846 (predict-no)
  3021. I see 0 and I'm going to do: predict-no
  3022. ENV: Agent did: predict-no for direction U in state State-B
  3023. In State-B moving U
  3024. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3025. predict error 0
  3026. dir: dir isU
  3027. |\-424: O: O848 (predict-no)
  3028. I see 1 and I'm going to do: predict-no
  3029. ENV: Agent did: predict-no for direction U in state State-B
  3030. In State-B moving U
  3031. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3032. predict error 0
  3033. dir: dir isL
  3034. /|\425: O: O850 (predict-no)
  3035. I see 1 and I'm going to do: predict-no
  3036. ENV: Agent did: predict-no for direction L in state State-B
  3037. In State-B moving L
  3038. ENV: (next state, see, prediction correct?) = (State-A, 1, False)
  3039. predict error 1
  3040. dir: dir isU
  3041. -/|426: O: O852 (predict-no)
  3042. I see 0 and I'm going to do: predict-no
  3043. ENV: Agent did: predict-no for direction U in state State-A
  3044. In State-A moving U
  3045. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3046. predict error 0
  3047. dir: dir isR
  3048. \-427: O: O853 (predict-yes)
  3049. I see 1 and I'm going to do: predict-yes
  3050. ENV: Agent did: predict-yes for direction R in state State-A
  3051. In State-A moving R
  3052. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  3053. predict error 0
  3054. dir: dir isR
  3055. /|428: O: O856 (predict-no)
  3056. I see 1 and I'm going to do: predict-no
  3057. ENV: Agent did: predict-no for direction R in state State-B
  3058. In State-B moving R
  3059. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3060. predict error 0
  3061. dir: dir isR
  3062. \-429: O: O858 (predict-no)
  3063. I see 1 and I'm going to do: predict-no
  3064. ENV: Agent did: predict-no for direction R in state State-B
  3065. In State-B moving R
  3066. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3067. predict error 0
  3068. dir: dir isL
  3069. /|\430: O: O860 (predict-no)
  3070. I see 1 and I'm going to do: predict-no
  3071. ENV: Agent did: predict-no for direction L in state State-B
  3072. In State-B moving L
  3073. ENV: (next state, see, prediction correct?) = (State-A, 1, False)
  3074. predict error 1
  3075. dir: dir isR
  3076. -/|431: O: O861 (predict-yes)
  3077. I see 0 and I'm going to do: predict-yes
  3078. ENV: Agent did: predict-yes for direction R in state State-A
  3079. In State-A moving R
  3080. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  3081. predict error 0
  3082. dir: dir isL
  3083. \432: O: O863 (predict-yes)
  3084. I see 1 and I'm going to do: predict-yes
  3085. ENV: Agent did: predict-yes for direction L in state State-B
  3086. In State-B moving L
  3087. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  3088. predict error 0
  3089. dir: dir isL
  3090. -/|433: O: O866 (predict-no)
  3091. I see 1 and I'm going to do: predict-no
  3092. ENV: Agent did: predict-no for direction L in state State-A
  3093. In State-A moving L
  3094. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3095. predict error 0
  3096. dir: dir isR
  3097. \-434: O: O868 (predict-no)
  3098. I see 1 and I'm going to do: predict-no
  3099. ENV: Agent did: predict-no for direction R in state State-A
  3100. In State-A moving R
  3101. ENV: (next state, see, prediction correct?) = (State-B, 1, False)
  3102. predict error 1
  3103. dir: dir isR
  3104. /|435: O: O870 (predict-no)
  3105. I see 0 and I'm going to do: predict-no
  3106. ENV: Agent did: predict-no for direction R in state State-B
  3107. In State-B moving R
  3108. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3109. predict error 0
  3110. dir: dir isL
  3111. \-/436: O: O871 (predict-yes)
  3112. I see 1 and I'm going to do: predict-yes
  3113. ENV: Agent did: predict-yes for direction L in state State-B
  3114. In State-B moving L
  3115. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  3116. predict error 0
  3117. dir: dir isR
  3118. |\-437: O: O873 (predict-yes)
  3119. I see 1 and I'm going to do: predict-yes
  3120. ENV: Agent did: predict-yes for direction R in state State-A
  3121. In State-A moving R
  3122. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  3123. predict error 0
  3124. dir: dir isR
  3125. /|438: O: O876 (predict-no)
  3126. I see 1 and I'm going to do: predict-no
  3127. ENV: Agent did: predict-no for direction R in state State-B
  3128. In State-B moving R
  3129. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3130. predict error 0
  3131. dir: dir isR
  3132. \-/439: O: O878 (predict-no)
  3133. I see 1 and I'm going to do: predict-no
  3134. ENV: Agent did: predict-no for direction R in state State-B
  3135. In State-B moving R
  3136. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3137. predict error 0
  3138. dir: dir isU
  3139. |\-440: O: O879 (predict-yes)
  3140. I see 1 and I'm going to do: predict-yes
  3141. ENV: Agent did: predict-yes for direction U in state State-B
  3142. In State-B moving U
  3143. ENV: (next state, see, prediction correct?) = (State-B, 0, False)
  3144. predict error 1
  3145. dir: dir isR
  3146. /|\441: O: O882 (predict-no)
  3147. I see 0 and I'm going to do: predict-no
  3148. ENV: Agent did: predict-no for direction R in state State-B
  3149. In State-B moving R
  3150. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3151. predict error 0
  3152. dir: dir isU
  3153. -442: O: O884 (predict-no)
  3154. I see 1 and I'm going to do: predict-no
  3155. ENV: Agent did: predict-no for direction U in state State-B
  3156. In State-B moving U
  3157. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3158. predict error 0
  3159. dir: dir isR
  3160. /|\443: O: O886 (predict-no)
  3161. I see 1 and I'm going to do: predict-no
  3162. ENV: Agent did: predict-no for direction R in state State-B
  3163. In State-B moving R
  3164. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3165. predict error 0
  3166. dir: dir isR
  3167. -/|444: O: O888 (predict-no)
  3168. I see 1 and I'm going to do: predict-no
  3169. ENV: Agent did: predict-no for direction R in state State-B
  3170. In State-B moving R
  3171. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3172. predict error 0
  3173. dir: dir isR
  3174. \-445: O: O890 (predict-no)
  3175. I see 1 and I'm going to do: predict-no
  3176. ENV: Agent did: predict-no for direction R in state State-B
  3177. In State-B moving R
  3178. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3179. predict error 0
  3180. dir: dir isR
  3181. /|\446: O: O892 (predict-no)
  3182. I see 1 and I'm going to do: predict-no
  3183. ENV: Agent did: predict-no for direction R in state State-B
  3184. In State-B moving R
  3185. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3186. predict error 0
  3187. dir: dir isL
  3188. -/|447: O: O893 (predict-yes)
  3189. I see 1 and I'm going to do: predict-yes
  3190. ENV: Agent did: predict-yes for direction L in state State-B
  3191. In State-B moving L
  3192. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  3193. predict error 0
  3194. dir: dir isU
  3195. \-/448: O: O896 (predict-no)
  3196. I see 1 and I'm going to do: predict-no
  3197. ENV: Agent did: predict-no for direction U in state State-A
  3198. In State-A moving U
  3199. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3200. predict error 0
  3201. dir: dir isR
  3202. |\-/449: O: O897 (predict-yes)
  3203. I see 1 and I'm going to do: predict-yes
  3204. ENV: Agent did: predict-yes for direction R in state State-A
  3205. In State-A moving R
  3206. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  3207. predict error 0
  3208. dir: dir isU
  3209. |\-450: O: O900 (predict-no)
  3210. I see 1 and I'm going to do: predict-no
  3211. ENV: Agent did: predict-no for direction U in state State-B
  3212. In State-B moving U
  3213. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3214. predict error 0
  3215. dir: dir isL
  3216. /|\451: O: O901 (predict-yes)
  3217. I see 1 and I'm going to do: predict-yes
  3218. ENV: Agent did: predict-yes for direction L in state State-B
  3219. In State-B moving L
  3220. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  3221. predict error 0
  3222. dir: dir isU
  3223. -452: O: O904 (predict-no)
  3224. I see 1 and I'm going to do: predict-no
  3225. ENV: Agent did: predict-no for direction U in state State-A
  3226. In State-A moving U
  3227. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3228. predict error 0
  3229. dir: dir isU
  3230. /|\453: O: O906 (predict-no)
  3231. I see 1 and I'm going to do: predict-no
  3232. ENV: Agent did: predict-no for direction U in state State-A
  3233. In State-A moving U
  3234. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3235. predict error 0
  3236. dir: dir isU
  3237. -/454: O: O908 (predict-no)
  3238. I see 1 and I'm going to do: predict-no
  3239. ENV: Agent did: predict-no for direction U in state State-A
  3240. In State-A moving U
  3241. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3242. predict error 0
  3243. dir: dir isU
  3244. |\-455: O: O910 (predict-no)
  3245. I see 1 and I'm going to do: predict-no
  3246. ENV: Agent did: predict-no for direction U in state State-A
  3247. In State-A moving U
  3248. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3249. predict error 0
  3250. dir: dir isU
  3251. /|\456: O: O912 (predict-no)
  3252. I see 1 and I'm going to do: predict-no
  3253. ENV: Agent did: predict-no for direction U in state State-A
  3254. In State-A moving U
  3255. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3256. predict error 0
  3257. dir: dir isU
  3258. -/457: O: O914 (predict-no)
  3259. I see 1 and I'm going to do: predict-no
  3260. ENV: Agent did: predict-no for direction U in state State-A
  3261. In State-A moving U
  3262. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3263. predict error 0
  3264. dir: dir isR
  3265. |458: O: O915 (predict-yes)
  3266. I see 1 and I'm going to do: predict-yes
  3267. ENV: Agent did: predict-yes for direction R in state State-A
  3268. In State-A moving R
  3269. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  3270. predict error 0
  3271. dir: dir isU
  3272. \-/459: O: O918 (predict-no)
  3273. I see 1 and I'm going to do: predict-no
  3274. ENV: Agent did: predict-no for direction U in state State-B
  3275. In State-B moving U
  3276. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3277. predict error 0
  3278. dir: dir isL
  3279. |\-460: O: O919 (predict-yes)
  3280. I see 1 and I'm going to do: predict-yes
  3281. ENV: Agent did: predict-yes for direction L in state State-B
  3282. In State-B moving L
  3283. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  3284. predict error 0
  3285. dir: dir isU
  3286. /|\461: O: O922 (predict-no)
  3287. I see 1 and I'm going to do: predict-no
  3288. ENV: Agent did: predict-no for direction U in state State-A
  3289. In State-A moving U
  3290. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3291. predict error 0
  3292. dir: dir isR
  3293. -462: O: O923 (predict-yes)
  3294. I see 1 and I'm going to do: predict-yes
  3295. ENV: Agent did: predict-yes for direction R in state State-A
  3296. In State-A moving R
  3297. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  3298. predict error 0
  3299. dir: dir isU
  3300. /|463: O: O926 (predict-no)
  3301. I see 1 and I'm going to do: predict-no
  3302. ENV: Agent did: predict-no for direction U in state State-B
  3303. In State-B moving U
  3304. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3305. predict error 0
  3306. dir: dir isR
  3307. \-/464: O: O928 (predict-no)
  3308. I see 1 and I'm going to do: predict-no
  3309. ENV: Agent did: predict-no for direction R in state State-B
  3310. In State-B moving R
  3311. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3312. predict error 0
  3313. dir: dir isU
  3314. |\465: O: O930 (predict-no)
  3315. I see 1 and I'm going to do: predict-no
  3316. ENV: Agent did: predict-no for direction U in state State-B
  3317. In State-B moving U
  3318. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3319. predict error 0
  3320. dir: dir isL
  3321. -/|466: O: O931 (predict-yes)
  3322. I see 1 and I'm going to do: predict-yes
  3323. ENV: Agent did: predict-yes for direction L in state State-B
  3324. In State-B moving L
  3325. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  3326. predict error 0
  3327. dir: dir isL
  3328. \-/467: O: O934 (predict-no)
  3329. I see 1 and I'm going to do: predict-no
  3330. ENV: Agent did: predict-no for direction L in state State-A
  3331. In State-A moving L
  3332. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3333. predict error 0
  3334. dir: dir isU
  3335. |\-468: O: O936 (predict-no)
  3336. I see 1 and I'm going to do: predict-no
  3337. ENV: Agent did: predict-no for direction U in state State-A
  3338. In State-A moving U
  3339. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3340. predict error 0
  3341. dir: dir isR
  3342. /|\469: O: O937 (predict-yes)
  3343. I see 1 and I'm going to do: predict-yes
  3344. ENV: Agent did: predict-yes for direction R in state State-A
  3345. In State-A moving R
  3346. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  3347. predict error 0
  3348. dir: dir isU
  3349. -/470: O: O940 (predict-no)
  3350. I see 1 and I'm going to do: predict-no
  3351. ENV: Agent did: predict-no for direction U in state State-B
  3352. In State-B moving U
  3353. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3354. predict error 0
  3355. dir: dir isU
  3356. |\471: O: O942 (predict-no)
  3357. I see 1 and I'm going to do: predict-no
  3358. ENV: Agent did: predict-no for direction U in state State-B
  3359. In State-B moving U
  3360. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3361. predict error 0
  3362. dir: dir isR
  3363. -472: O: O944 (predict-no)
  3364. I see 1 and I'm going to do: predict-no
  3365. ENV: Agent did: predict-no for direction R in state State-B
  3366. In State-B moving R
  3367. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3368. predict error 0
  3369. dir: dir isR
  3370. /|\473: O: O946 (predict-no)
  3371. I see 1 and I'm going to do: predict-no
  3372. ENV: Agent did: predict-no for direction R in state State-B
  3373. In State-B moving R
  3374. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3375. predict error 0
  3376. dir: dir isL
  3377. -/|474: O: O947 (predict-yes)
  3378. I see 1 and I'm going to do: predict-yes
  3379. ENV: Agent did: predict-yes for direction L in state State-B
  3380. In State-B moving L
  3381. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  3382. predict error 0
  3383. dir: dir isL
  3384. \-/475: O: O950 (predict-no)
  3385. I see 1 and I'm going to do: predict-no
  3386. ENV: Agent did: predict-no for direction L in state State-A
  3387. In State-A moving L
  3388. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3389. predict error 0
  3390. dir: dir isU
  3391. |\476: O: O952 (predict-no)
  3392. I see 1 and I'm going to do: predict-no
  3393. ENV: Agent did: predict-no for direction U in state State-A
  3394. In State-A moving U
  3395. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3396. predict error 0
  3397. dir: dir isU
  3398. -/|477: O: O954 (predict-no)
  3399. I see 1 and I'm going to do: predict-no
  3400. ENV: Agent did: predict-no for direction U in state State-A
  3401. In State-A moving U
  3402. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3403. predict error 0
  3404. dir: dir isU
  3405. \-/478: O: O956 (predict-no)
  3406. I see 1 and I'm going to do: predict-no
  3407. ENV: Agent did: predict-no for direction U in state State-A
  3408. In State-A moving U
  3409. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3410. predict error 0
  3411. dir: dir isU
  3412. |\479: O: O958 (predict-no)
  3413. I see 1 and I'm going to do: predict-no
  3414. ENV: Agent did: predict-no for direction U in state State-A
  3415. In State-A moving U
  3416. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3417. predict error 0
  3418. dir: dir isR
  3419. -/480: O: O959 (predict-yes)
  3420. I see 1 and I'm going to do: predict-yes
  3421. ENV: Agent did: predict-yes for direction R in state State-A
  3422. In State-A moving R
  3423. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  3424. predict error 0
  3425. dir: dir isL
  3426. |481: O: O961 (predict-yes)
  3427. I see 1 and I'm going to do: predict-yes
  3428. ENV: Agent did: predict-yes for direction L in state State-B
  3429. In State-B moving L
  3430. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  3431. predict error 0
  3432. dir: dir isL
  3433. \482: O: O964 (predict-no)
  3434. I see 1 and I'm going to do: predict-no
  3435. ENV: Agent did: predict-no for direction L in state State-A
  3436. In State-A moving L
  3437. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3438. predict error 0
  3439. dir: dir isR
  3440. -/|483: O: O965 (predict-yes)
  3441. I see 1 and I'm going to do: predict-yes
  3442. ENV: Agent did: predict-yes for direction R in state State-A
  3443. In State-A moving R
  3444. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  3445. predict error 0
  3446. dir: dir isR
  3447. \-/484: O: O968 (predict-no)
  3448. I see 1 and I'm going to do: predict-no
  3449. ENV: Agent did: predict-no for direction R in state State-B
  3450. In State-B moving R
  3451. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3452. predict error 0
  3453. dir: dir isU
  3454. |\-485: O: O970 (predict-no)
  3455. I see 1 and I'm going to do: predict-no
  3456. ENV: Agent did: predict-no for direction U in state State-B
  3457. In State-B moving U
  3458. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3459. predict error 0
  3460. dir: dir isU
  3461. /|\-486: O: O972 (predict-no)
  3462. I see 1 and I'm going to do: predict-no
  3463. ENV: Agent did: predict-no for direction U in state State-B
  3464. In State-B moving U
  3465. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3466. predict error 0
  3467. dir: dir isR
  3468. /|487: O: O974 (predict-no)
  3469. I see 1 and I'm going to do: predict-no
  3470. ENV: Agent did: predict-no for direction R in state State-B
  3471. In State-B moving R
  3472. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3473. predict error 0
  3474. dir: dir isL
  3475. \-488: O: O975 (predict-yes)
  3476. I see 1 and I'm going to do: predict-yes
  3477. ENV: Agent did: predict-yes for direction L in state State-B
  3478. In State-B moving L
  3479. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  3480. predict error 0
  3481. dir: dir isU
  3482. /|\489: O: O978 (predict-no)
  3483. I see 1 and I'm going to do: predict-no
  3484. ENV: Agent did: predict-no for direction U in state State-A
  3485. In State-A moving U
  3486. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3487. predict error 0
  3488. dir: dir isU
  3489. -/|490: O: O979 (predict-yes)
  3490. I see 1 and I'm going to do: predict-yes
  3491. ENV: Agent did: predict-yes for direction U in state State-A
  3492. In State-A moving U
  3493. ENV: (next state, see, prediction correct?) = (State-A, 0, False)
  3494. predict error 1
  3495. dir: dir isL
  3496. \-/491: O: O982 (predict-no)
  3497. I see 0 and I'm going to do: predict-no
  3498. ENV: Agent did: predict-no for direction L in state State-A
  3499. In State-A moving L
  3500. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3501. predict error 0
  3502. dir: dir isR
  3503. |492: O: O983 (predict-yes)
  3504. I see 1 and I'm going to do: predict-yes
  3505. ENV: Agent did: predict-yes for direction R in state State-A
  3506. In State-A moving R
  3507. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  3508. predict error 0
  3509. dir: dir isU
  3510. \-/493: O: O986 (predict-no)
  3511. I see 1 and I'm going to do: predict-no
  3512. ENV: Agent did: predict-no for direction U in state State-B
  3513. In State-B moving U
  3514. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3515. predict error 0
  3516. dir: dir isL
  3517. |494: O: O987 (predict-yes)
  3518. I see 1 and I'm going to do: predict-yes
  3519. ENV: Agent did: predict-yes for direction L in state State-B
  3520. In State-B moving L
  3521. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  3522. predict error 0
  3523. dir: dir isU
  3524. \-/495: O: O990 (predict-no)
  3525. I see 1 and I'm going to do: predict-no
  3526. ENV: Agent did: predict-no for direction U in state State-A
  3527. In State-A moving U
  3528. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3529. predict error 0
  3530. dir: dir isU
  3531. |\-496: O: O992 (predict-no)
  3532. I see 1 and I'm going to do: predict-no
  3533. ENV: Agent did: predict-no for direction U in state State-A
  3534. In State-A moving U
  3535. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3536. predict error 0
  3537. dir: dir isU
  3538. /|\497: O: O994 (predict-no)
  3539. I see 1 and I'm going to do: predict-no
  3540. ENV: Agent did: predict-no for direction U in state State-A
  3541. In State-A moving U
  3542. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3543. predict error 0
  3544. dir: dir isL
  3545. -/|498: O: O996 (predict-no)
  3546. I see 1 and I'm going to do: predict-no
  3547. ENV: Agent did: predict-no for direction L in state State-A
  3548. In State-A moving L
  3549. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3550. predict error 0
  3551. dir: dir isL
  3552. \-/499: O: O998 (predict-no)
  3553. I see 1 and I'm going to do: predict-no
  3554. ENV: Agent did: predict-no for direction L in state State-A
  3555. In State-A moving L
  3556. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3557. predict error 0
  3558. dir: dir isR
  3559. |\-500: O: O999 (predict-yes)
  3560. I see 1 and I'm going to do: predict-yes
  3561. ENV: Agent did: predict-yes for direction R in state State-A
  3562. In State-A moving R
  3563. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  3564. predict error 0
  3565. dir: dir isL
  3566. /|\-/|\501: O: O1001 (predict-yes)
  3567. I see 1 and I'm going to do: predict-yes
  3568. ENV: Agent did: predict-yes for direction L in state State-B
  3569. In State-B moving L
  3570. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  3571. predict error 0
  3572. dir: dir isR
  3573. -502: O: O1003 (predict-yes)
  3574. I see 1 and I'm going to do: predict-yes
  3575. ENV: Agent did: predict-yes for direction R in state State-A
  3576. In State-A moving R
  3577. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  3578. predict error 0
  3579. dir: dir isL
  3580. /|\503: O: O1005 (predict-yes)
  3581. I see 1 and I'm going to do: predict-yes
  3582. ENV: Agent did: predict-yes for direction L in state State-B
  3583. In State-B moving L
  3584. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  3585. predict error 0
  3586. dir: dir isU
  3587. -504: O: O1008 (predict-no)
  3588. I see 1 and I'm going to do: predict-no
  3589. ENV: Agent did: predict-no for direction U in state State-A
  3590. In State-A moving U
  3591. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3592. predict error 0
  3593. dir: dir isU
  3594. /|505: O: O1010 (predict-no)
  3595. I see 1 and I'm going to do: predict-no
  3596. ENV: Agent did: predict-no for direction U in state State-A
  3597. In State-A moving U
  3598. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3599. predict error 0
  3600. dir: dir isL
  3601. \-506: O: O1012 (predict-no)
  3602. I see 1 and I'm going to do: predict-no
  3603. ENV: Agent did: predict-no for direction L in state State-A
  3604. In State-A moving L
  3605. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3606. predict error 0
  3607. dir: dir isU
  3608. /507: O: O1014 (predict-no)
  3609. I see 1 and I'm going to do: predict-no
  3610. ENV: Agent did: predict-no for direction U in state State-A
  3611. In State-A moving U
  3612. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3613. predict error 0
  3614. dir: dir isL
  3615. |\-508: O: O1016 (predict-no)
  3616. I see 1 and I'm going to do: predict-no
  3617. ENV: Agent did: predict-no for direction L in state State-A
  3618. In State-A moving L
  3619. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3620. predict error 0
  3621. dir: dir isL
  3622. /|\509: O: O1018 (predict-no)
  3623. I see 1 and I'm going to do: predict-no
  3624. ENV: Agent did: predict-no for direction L in state State-A
  3625. In State-A moving L
  3626. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3627. predict error 0
  3628. dir: dir isU
  3629. -/|510: O: O1020 (predict-no)
  3630. I see 1 and I'm going to do: predict-no
  3631. ENV: Agent did: predict-no for direction U in state State-A
  3632. In State-A moving U
  3633. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3634. predict error 0
  3635. dir: dir isU
  3636. \-511: O: O1022 (predict-no)
  3637. I see 1 and I'm going to do: predict-no
  3638. ENV: Agent did: predict-no for direction U in state State-A
  3639. In State-A moving U
  3640. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3641. predict error 0
  3642. dir: dir isL
  3643. /512: O: O1024 (predict-no)
  3644. I see 1 and I'm going to do: predict-no
  3645. ENV: Agent did: predict-no for direction L in state State-A
  3646. In State-A moving L
  3647. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3648. predict error 0
  3649. dir: dir isL
  3650. |\-513: O: O1026 (predict-no)
  3651. I see 1 and I'm going to do: predict-no
  3652. ENV: Agent did: predict-no for direction L in state State-A
  3653. In State-A moving L
  3654. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3655. predict error 0
  3656. dir: dir isR
  3657. /|\514: O: O1027 (predict-yes)
  3658. I see 1 and I'm going to do: predict-yes
  3659. ENV: Agent did: predict-yes for direction R in state State-A
  3660. In State-A moving R
  3661. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  3662. predict error 0
  3663. dir: dir isL
  3664. -/|515: O: O1029 (predict-yes)
  3665. I see 1 and I'm going to do: predict-yes
  3666. ENV: Agent did: predict-yes for direction L in state State-B
  3667. In State-B moving L
  3668. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  3669. predict error 0
  3670. dir: dir isR
  3671. \-/516: O: O1031 (predict-yes)
  3672. I see 1 and I'm going to do: predict-yes
  3673. ENV: Agent did: predict-yes for direction R in state State-A
  3674. In State-A moving R
  3675. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  3676. predict error 0
  3677. dir: dir isU
  3678. |\-517: O: O1034 (predict-no)
  3679. I see 1 and I'm going to do: predict-no
  3680. ENV: Agent did: predict-no for direction U in state State-B
  3681. In State-B moving U
  3682. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3683. predict error 0
  3684. dir: dir isL
  3685. /|\518: O: O1035 (predict-yes)
  3686. I see 1 and I'm going to do: predict-yes
  3687. ENV: Agent did: predict-yes for direction L in state State-B
  3688. In State-B moving L
  3689. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  3690. predict error 0
  3691. dir: dir isL
  3692. -/|519: O: O1038 (predict-no)
  3693. I see 1 and I'm going to do: predict-no
  3694. ENV: Agent did: predict-no for direction L in state State-A
  3695. In State-A moving L
  3696. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3697. predict error 0
  3698. dir: dir isR
  3699. \-520: O: O1039 (predict-yes)
  3700. I see 1 and I'm going to do: predict-yes
  3701. ENV: Agent did: predict-yes for direction R in state State-A
  3702. In State-A moving R
  3703. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  3704. predict error 0
  3705. dir: dir isU
  3706. /|\521: O: O1042 (predict-no)
  3707. I see 1 and I'm going to do: predict-no
  3708. ENV: Agent did: predict-no for direction U in state State-B
  3709. In State-B moving U
  3710. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3711. predict error 0
  3712. dir: dir isL
  3713. -522: O: O1043 (predict-yes)
  3714. I see 1 and I'm going to do: predict-yes
  3715. ENV: Agent did: predict-yes for direction L in state State-B
  3716. In State-B moving L
  3717. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  3718. predict error 0
  3719. dir: dir isU
  3720. /|\523: O: O1046 (predict-no)
  3721. I see 1 and I'm going to do: predict-no
  3722. ENV: Agent did: predict-no for direction U in state State-A
  3723. In State-A moving U
  3724. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3725. predict error 0
  3726. dir: dir isR
  3727. -/524: O: O1048 (predict-no)
  3728. I see 1 and I'm going to do: predict-no
  3729. ENV: Agent did: predict-no for direction R in state State-A
  3730. In State-A moving R
  3731. ENV: (next state, see, prediction correct?) = (State-B, 1, False)
  3732. predict error 1
  3733. dir: dir isR
  3734. |\-525: O: O1050 (predict-no)
  3735. I see 0 and I'm going to do: predict-no
  3736. ENV: Agent did: predict-no for direction R in state State-B
  3737. In State-B moving R
  3738. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3739. predict error 0
  3740. dir: dir isL
  3741. /|526: O: O1052 (predict-no)
  3742. I see 1 and I'm going to do: predict-no
  3743. ENV: Agent did: predict-no for direction L in state State-B
  3744. In State-B moving L
  3745. ENV: (next state, see, prediction correct?) = (State-A, 1, False)
  3746. predict error 1
  3747. dir: dir isU
  3748. \-/527: O: O1054 (predict-no)
  3749. I see 0 and I'm going to do: predict-no
  3750. ENV: Agent did: predict-no for direction U in state State-A
  3751. In State-A moving U
  3752. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3753. predict error 0
  3754. dir: dir isU
  3755. |\528: O: O1056 (predict-no)
  3756. I see 1 and I'm going to do: predict-no
  3757. ENV: Agent did: predict-no for direction U in state State-A
  3758. In State-A moving U
  3759. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3760. predict error 0
  3761. dir: dir isR
  3762. -/|529: O: O1057 (predict-yes)
  3763. I see 1 and I'm going to do: predict-yes
  3764. ENV: Agent did: predict-yes for direction R in state State-A
  3765. In State-A moving R
  3766. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  3767. predict error 0
  3768. dir: dir isL
  3769. \-/530: O: O1059 (predict-yes)
  3770. I see 1 and I'm going to do: predict-yes
  3771. ENV: Agent did: predict-yes for direction L in state State-B
  3772. In State-B moving L
  3773. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  3774. predict error 0
  3775. dir: dir isU
  3776. |\-531: O: O1062 (predict-no)
  3777. I see 1 and I'm going to do: predict-no
  3778. ENV: Agent did: predict-no for direction U in state State-A
  3779. In State-A moving U
  3780. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3781. predict error 0
  3782. dir: dir isL
  3783. /532: O: O1063 (predict-yes)
  3784. I see 1 and I'm going to do: predict-yes
  3785. ENV: Agent did: predict-yes for direction L in state State-A
  3786. In State-A moving L
  3787. ENV: (next state, see, prediction correct?) = (State-A, 0, False)
  3788. predict error 1
  3789. dir: dir isR
  3790. |\533: O: O1065 (predict-yes)
  3791. I see 0 and I'm going to do: predict-yes
  3792. ENV: Agent did: predict-yes for direction R in state State-A
  3793. In State-A moving R
  3794. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  3795. predict error 0
  3796. dir: dir isL
  3797. -/|534: O: O1067 (predict-yes)
  3798. I see 1 and I'm going to do: predict-yes
  3799. ENV: Agent did: predict-yes for direction L in state State-B
  3800. In State-B moving L
  3801. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  3802. predict error 0
  3803. dir: dir isU
  3804. \-/535: O: O1070 (predict-no)
  3805. I see 1 and I'm going to do: predict-no
  3806. ENV: Agent did: predict-no for direction U in state State-A
  3807. In State-A moving U
  3808. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3809. predict error 0
  3810. dir: dir isU
  3811. |\-536: O: O1072 (predict-no)
  3812. I see 1 and I'm going to do: predict-no
  3813. ENV: Agent did: predict-no for direction U in state State-A
  3814. In State-A moving U
  3815. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3816. predict error 0
  3817. dir: dir isU
  3818. /|537: O: O1074 (predict-no)
  3819. I see 1 and I'm going to do: predict-no
  3820. ENV: Agent did: predict-no for direction U in state State-A
  3821. In State-A moving U
  3822. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3823. predict error 0
  3824. dir: dir isL
  3825. \-538: O: O1076 (predict-no)
  3826. I see 1 and I'm going to do: predict-no
  3827. ENV: Agent did: predict-no for direction L in state State-A
  3828. In State-A moving L
  3829. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3830. predict error 0
  3831. dir: dir isL
  3832. /|\539: O: O1078 (predict-no)
  3833. I see 1 and I'm going to do: predict-no
  3834. ENV: Agent did: predict-no for direction L in state State-A
  3835. In State-A moving L
  3836. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3837. predict error 0
  3838. dir: dir isU
  3839. -/|540: O: O1080 (predict-no)
  3840. I see 1 and I'm going to do: predict-no
  3841. ENV: Agent did: predict-no for direction U in state State-A
  3842. In State-A moving U
  3843. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3844. predict error 0
  3845. dir: dir isL
  3846. \-541: O: O1082 (predict-no)
  3847. I see 1 and I'm going to do: predict-no
  3848. ENV: Agent did: predict-no for direction L in state State-A
  3849. In State-A moving L
  3850. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3851. predict error 0
  3852. dir: dir isR
  3853. /542: O: O1083 (predict-yes)
  3854. I see 1 and I'm going to do: predict-yes
  3855. ENV: Agent did: predict-yes for direction R in state State-A
  3856. In State-A moving R
  3857. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  3858. predict error 0
  3859. dir: dir isL
  3860. |\-543: O: O1085 (predict-yes)
  3861. I see 1 and I'm going to do: predict-yes
  3862. ENV: Agent did: predict-yes for direction L in state State-B
  3863. In State-B moving L
  3864. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  3865. predict error 0
  3866. dir: dir isL
  3867. /|\544: O: O1088 (predict-no)
  3868. I see 1 and I'm going to do: predict-no
  3869. ENV: Agent did: predict-no for direction L in state State-A
  3870. In State-A moving L
  3871. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3872. predict error 0
  3873. dir: dir isL
  3874. -/|545: O: O1090 (predict-no)
  3875. I see 1 and I'm going to do: predict-no
  3876. ENV: Agent did: predict-no for direction L in state State-A
  3877. In State-A moving L
  3878. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3879. predict error 0
  3880. dir: dir isL
  3881. \-/546: O: O1092 (predict-no)
  3882. I see 1 and I'm going to do: predict-no
  3883. ENV: Agent did: predict-no for direction L in state State-A
  3884. In State-A moving L
  3885. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3886. predict error 0
  3887. dir: dir isL
  3888. |\547: O: O1094 (predict-no)
  3889. I see 1 and I'm going to do: predict-no
  3890. ENV: Agent did: predict-no for direction L in state State-A
  3891. In State-A moving L
  3892. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3893. predict error 0
  3894. dir: dir isR
  3895. -/548: O: O1095 (predict-yes)
  3896. I see 1 and I'm going to do: predict-yes
  3897. ENV: Agent did: predict-yes for direction R in state State-A
  3898. In State-A moving R
  3899. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  3900. predict error 0
  3901. dir: dir isR
  3902. |\-/549: O: O1098 (predict-no)
  3903. I see 1 and I'm going to do: predict-no
  3904. ENV: Agent did: predict-no for direction R in state State-B
  3905. In State-B moving R
  3906. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3907. predict error 0
  3908. dir: dir isU
  3909. |\-550: O: O1100 (predict-no)
  3910. I see 1 and I'm going to do: predict-no
  3911. ENV: Agent did: predict-no for direction U in state State-B
  3912. In State-B moving U
  3913. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3914. predict error 0
  3915. dir: dir isL
  3916. /|\551: O: O1102 (predict-no)
  3917. I see 1 and I'm going to do: predict-no
  3918. ENV: Agent did: predict-no for direction L in state State-B
  3919. In State-B moving L
  3920. ENV: (next state, see, prediction correct?) = (State-A, 1, False)
  3921. predict error 1
  3922. dir: dir isR
  3923. -552: O: O1103 (predict-yes)
  3924. I see 0 and I'm going to do: predict-yes
  3925. ENV: Agent did: predict-yes for direction R in state State-A
  3926. In State-A moving R
  3927. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  3928. predict error 0
  3929. dir: dir isR
  3930. /|\553: O: O1106 (predict-no)
  3931. I see 1 and I'm going to do: predict-no
  3932. ENV: Agent did: predict-no for direction R in state State-B
  3933. In State-B moving R
  3934. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3935. predict error 0
  3936. dir: dir isL
  3937. -/554: O: O1107 (predict-yes)
  3938. I see 1 and I'm going to do: predict-yes
  3939. ENV: Agent did: predict-yes for direction L in state State-B
  3940. In State-B moving L
  3941. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  3942. predict error 0
  3943. dir: dir isR
  3944. |\-555: O: O1109 (predict-yes)
  3945. I see 1 and I'm going to do: predict-yes
  3946. ENV: Agent did: predict-yes for direction R in state State-A
  3947. In State-A moving R
  3948. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  3949. predict error 0
  3950. dir: dir isR
  3951. /|\556: O: O1112 (predict-no)
  3952. I see 1 and I'm going to do: predict-no
  3953. ENV: Agent did: predict-no for direction R in state State-B
  3954. In State-B moving R
  3955. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3956. predict error 0
  3957. dir: dir isU
  3958. -/|557: O: O1114 (predict-no)
  3959. I see 1 and I'm going to do: predict-no
  3960. ENV: Agent did: predict-no for direction U in state State-B
  3961. In State-B moving U
  3962. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3963. predict error 0
  3964. dir: dir isL
  3965. \-/558: O: O1115 (predict-yes)
  3966. I see 1 and I'm going to do: predict-yes
  3967. ENV: Agent did: predict-yes for direction L in state State-B
  3968. In State-B moving L
  3969. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  3970. predict error 0
  3971. dir: dir isR
  3972. |\559: O: O1117 (predict-yes)
  3973. I see 1 and I'm going to do: predict-yes
  3974. ENV: Agent did: predict-yes for direction R in state State-A
  3975. In State-A moving R
  3976. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  3977. predict error 0
  3978. dir: dir isR
  3979. -/|560: O: O1120 (predict-no)
  3980. I see 1 and I'm going to do: predict-no
  3981. ENV: Agent did: predict-no for direction R in state State-B
  3982. In State-B moving R
  3983. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3984. predict error 0
  3985. dir: dir isU
  3986. \-561: O: O1122 (predict-no)
  3987. I see 1 and I'm going to do: predict-no
  3988. ENV: Agent did: predict-no for direction U in state State-B
  3989. In State-B moving U
  3990. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3991. predict error 0
  3992. dir: dir isL
  3993. /562: O: O1123 (predict-yes)
  3994. I see 1 and I'm going to do: predict-yes
  3995. ENV: Agent did: predict-yes for direction L in state State-B
  3996. In State-B moving L
  3997. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  3998. predict error 0
  3999. dir: dir isL
  4000. |\-563: O: O1126 (predict-no)
  4001. I see 1 and I'm going to do: predict-no
  4002. ENV: Agent did: predict-no for direction L in state State-A
  4003. In State-A moving L
  4004. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4005. predict error 0
  4006. dir: dir isL
  4007. /|\564: O: O1128 (predict-no)
  4008. I see 1 and I'm going to do: predict-no
  4009. ENV: Agent did: predict-no for direction L in state State-A
  4010. In State-A moving L
  4011. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4012. predict error 0
  4013. dir: dir isR
  4014. -/|565: O: O1129 (predict-yes)
  4015. I see 1 and I'm going to do: predict-yes
  4016. ENV: Agent did: predict-yes for direction R in state State-A
  4017. In State-A moving R
  4018. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  4019. predict error 0
  4020. dir: dir isU
  4021. \-/566: O: O1132 (predict-no)
  4022. I see 1 and I'm going to do: predict-no
  4023. ENV: Agent did: predict-no for direction U in state State-B
  4024. In State-B moving U
  4025. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4026. predict error 0
  4027. dir: dir isU
  4028. |\-567: O: O1134 (predict-no)
  4029. I see 1 and I'm going to do: predict-no
  4030. ENV: Agent did: predict-no for direction U in state State-B
  4031. In State-B moving U
  4032. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4033. predict error 0
  4034. dir: dir isL
  4035. /|568: O: O1135 (predict-yes)
  4036. I see 1 and I'm going to do: predict-yes
  4037. ENV: Agent did: predict-yes for direction L in state State-B
  4038. In State-B moving L
  4039. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  4040. predict error 0
  4041. dir: dir isR
  4042. \-/569: O: O1137 (predict-yes)
  4043. I see 1 and I'm going to do: predict-yes
  4044. ENV: Agent did: predict-yes for direction R in state State-A
  4045. In State-A moving R
  4046. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  4047. predict error 0
  4048. dir: dir isU
  4049. |\-570: O: O1140 (predict-no)
  4050. I see 1 and I'm going to do: predict-no
  4051. ENV: Agent did: predict-no for direction U in state State-B
  4052. In State-B moving U
  4053. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4054. predict error 0
  4055. dir: dir isU
  4056. /|571: O: O1142 (predict-no)
  4057. I see 1 and I'm going to do: predict-no
  4058. ENV: Agent did: predict-no for direction U in state State-B
  4059. In State-B moving U
  4060. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4061. predict error 0
  4062. dir: dir isR
  4063. \572: O: O1144 (predict-no)
  4064. I see 1 and I'm going to do: predict-no
  4065. ENV: Agent did: predict-no for direction R in state State-B
  4066. In State-B moving R
  4067. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4068. predict error 0
  4069. dir: dir isR
  4070. -/|573: O: O1146 (predict-no)
  4071. I see 1 and I'm going to do: predict-no
  4072. ENV: Agent did: predict-no for direction R in state State-B
  4073. In State-B moving R
  4074. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4075. predict error 0
  4076. dir: dir isU
  4077. \-/574: O: O1148 (predict-no)
  4078. I see 1 and I'm going to do: predict-no
  4079. ENV: Agent did: predict-no for direction U in state State-B
  4080. In State-B moving U
  4081. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4082. predict error 0
  4083. dir: dir isR
  4084. |\-575: O: O1150 (predict-no)
  4085. I see 1 and I'm going to do: predict-no
  4086. ENV: Agent did: predict-no for direction R in state State-B
  4087. In State-B moving R
  4088. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4089. predict error 0
  4090. dir: dir isL
  4091. /|\576: O: O1151 (predict-yes)
  4092. I see 1 and I'm going to do: predict-yes
  4093. ENV: Agent did: predict-yes for direction L in state State-B
  4094. In State-B moving L
  4095. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  4096. predict error 0
  4097. dir: dir isR
  4098. -/|577: O: O1153 (predict-yes)
  4099. I see 1 and I'm going to do: predict-yes
  4100. ENV: Agent did: predict-yes for direction R in state State-A
  4101. In State-A moving R
  4102. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  4103. predict error 0
  4104. dir: dir isU
  4105. \-/|sleeping...
  4106. \578: O: O1156 (predict-no)
  4107. I see 1 and I'm going to do: predict-no
  4108. ENV: Agent did: predict-no for direction U in state State-B
  4109. In State-B moving U
  4110. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4111. predict error 0
  4112. dir: dir isL
  4113. -/|579: O: O1157 (predict-yes)
  4114. I see 1 and I'm going to do: predict-yes
  4115. ENV: Agent did: predict-yes for direction L in state State-B
  4116. In State-B moving L
  4117. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  4118. predict error 0
  4119. dir: dir isR
  4120. \-/580: O: O1159 (predict-yes)
  4121. I see 1 and I'm going to do: predict-yes
  4122. ENV: Agent did: predict-yes for direction R in state State-A
  4123. In State-A moving R
  4124. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  4125. predict error 0
  4126. dir: dir isR
  4127. |\-581: O: O1162 (predict-no)
  4128. I see 1 and I'm going to do: predict-no
  4129. ENV: Agent did: predict-no for direction R in state State-B
  4130. In State-B moving R
  4131. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4132. predict error 0
  4133. dir: dir isR
  4134. /582: O: O1163 (predict-yes)
  4135. I see 1 and I'm going to do: predict-yes
  4136. ENV: Agent did: predict-yes for direction R in state State-B
  4137. In State-B moving R
  4138. ENV: (next state, see, prediction correct?) = (State-B, 0, False)
  4139. predict error 1
  4140. dir: dir isL
  4141. |\-583: O: O1165 (predict-yes)
  4142. I see 0 and I'm going to do: predict-yes
  4143. ENV: Agent did: predict-yes for direction L in state State-B
  4144. In State-B moving L
  4145. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  4146. predict error 0
  4147. dir: dir isL
  4148. /|\584: O: O1168 (predict-no)
  4149. I see 1 and I'm going to do: predict-no
  4150. ENV: Agent did: predict-no for direction L in state State-A
  4151. In State-A moving L
  4152. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4153. predict error 0
  4154. dir: dir isU
  4155. -/585: O: O1170 (predict-no)
  4156. I see 1 and I'm going to do: predict-no
  4157. ENV: Agent did: predict-no for direction U in state State-A
  4158. In State-A moving U
  4159. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4160. predict error 0
  4161. dir: dir isR
  4162. |\-586: O: O1171 (predict-yes)
  4163. I see 1 and I'm going to do: predict-yes
  4164. ENV: Agent did: predict-yes for direction R in state State-A
  4165. In State-A moving R
  4166. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  4167. predict error 0
  4168. dir: dir isL
  4169. /|\587: O: O1173 (predict-yes)
  4170. I see 1 and I'm going to do: predict-yes
  4171. ENV: Agent did: predict-yes for direction L in state State-B
  4172. In State-B moving L
  4173. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  4174. predict error 0
  4175. dir: dir isL
  4176. -/|588: O: O1176 (predict-no)
  4177. I see 1 and I'm going to do: predict-no
  4178. ENV: Agent did: predict-no for direction L in state State-A
  4179. In State-A moving L
  4180. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4181. predict error 0
  4182. dir: dir isU
  4183. \-589: O: O1178 (predict-no)
  4184. I see 1 and I'm going to do: predict-no
  4185. ENV: Agent did: predict-no for direction U in state State-A
  4186. In State-A moving U
  4187. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4188. predict error 0
  4189. dir: dir isR
  4190. /590: O: O1179 (predict-yes)
  4191. I see 1 and I'm going to do: predict-yes
  4192. ENV: Agent did: predict-yes for direction R in state State-A
  4193. In State-A moving R
  4194. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  4195. predict error 0
  4196. dir: dir isR
  4197. |\-591: O: O1182 (predict-no)
  4198. I see 1 and I'm going to do: predict-no
  4199. ENV: Agent did: predict-no for direction R in state State-B
  4200. In State-B moving R
  4201. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4202. predict error 0
  4203. dir: dir isL
  4204. /592: O: O1183 (predict-yes)
  4205. I see 1 and I'm going to do: predict-yes
  4206. ENV: Agent did: predict-yes for direction L in state State-B
  4207. In State-B moving L
  4208. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  4209. predict error 0
  4210. dir: dir isU
  4211. |\-593: O: O1186 (predict-no)
  4212. I see 1 and I'm going to do: predict-no
  4213. ENV: Agent did: predict-no for direction U in state State-A
  4214. In State-A moving U
  4215. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4216. predict error 0
  4217. dir: dir isR
  4218. /|\594: O: O1187 (predict-yes)
  4219. I see 1 and I'm going to do: predict-yes
  4220. ENV: Agent did: predict-yes for direction R in state State-A
  4221. In State-A moving R
  4222. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  4223. predict error 0
  4224. dir: dir isU
  4225. -/|595: O: O1190 (predict-no)
  4226. I see 1 and I'm going to do: predict-no
  4227. ENV: Agent did: predict-no for direction U in state State-B
  4228. In State-B moving U
  4229. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4230. predict error 0
  4231. dir: dir isU
  4232. \596: O: O1192 (predict-no)
  4233. I see 1 and I'm going to do: predict-no
  4234. ENV: Agent did: predict-no for direction U in state State-B
  4235. In State-B moving U
  4236. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4237. predict error 0
  4238. dir: dir isL
  4239. -/|597: O: O1193 (predict-yes)
  4240. I see 1 and I'm going to do: predict-yes
  4241. ENV: Agent did: predict-yes for direction L in state State-B
  4242. In State-B moving L
  4243. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  4244. predict error 0
  4245. dir: dir isU
  4246. \-/598: O: O1196 (predict-no)
  4247. I see 1 and I'm going to do: predict-no
  4248. ENV: Agent did: predict-no for direction U in state State-A
  4249. In State-A moving U
  4250. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4251. predict error 0
  4252. dir: dir isL
  4253. |\-599: O: O1198 (predict-no)
  4254. I see 1 and I'm going to do: predict-no
  4255. ENV: Agent did: predict-no for direction L in state State-A
  4256. In State-A moving L
  4257. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4258. predict error 0
  4259. dir: dir isU
  4260. /600: O: O1200 (predict-no)
  4261. I see 1 and I'm going to do: predict-no
  4262. ENV: Agent did: predict-no for direction U in state State-A
  4263. In State-A moving U
  4264. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4265. predict error 0
  4266. dir: dir isL
  4267. |601: O: O1202 (predict-no)
  4268. I see 1 and I'm going to do: predict-no
  4269. ENV: Agent did: predict-no for direction L in state State-A
  4270. In State-A moving L
  4271. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4272. predict error 0
  4273. dir: dir isU
  4274. \602: O: O1204 (predict-no)
  4275. I see 1 and I'm going to do: predict-no
  4276. ENV: Agent did: predict-no for direction U in state State-A
  4277. In State-A moving U
  4278. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4279. predict error 0
  4280. dir: dir isL
  4281. -/|\603: O: O1206 (predict-no)
  4282. I see 1 and I'm going to do: predict-no
  4283. ENV: Agent did: predict-no for direction L in state State-A
  4284. In State-A moving L
  4285. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4286. predict error 0
  4287. dir: dir isL
  4288. -/|604: O: O1208 (predict-no)
  4289. I see 1 and I'm going to do: predict-no
  4290. ENV: Agent did: predict-no for direction L in state State-A
  4291. In State-A moving L
  4292. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4293. predict error 0
  4294. dir: dir isR
  4295. \-/605: O: O1209 (predict-yes)
  4296. I see 1 and I'm going to do: predict-yes
  4297. ENV: Agent did: predict-yes for direction R in state State-A
  4298. In State-A moving R
  4299. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  4300. predict error 0
  4301. dir: dir isR
  4302. |\-606: O: O1212 (predict-no)
  4303. I see 1 and I'm going to do: predict-no
  4304. ENV: Agent did: predict-no for direction R in state State-B
  4305. In State-B moving R
  4306. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4307. predict error 0
  4308. dir: dir isR
  4309. /|607: O: O1214 (predict-no)
  4310. I see 1 and I'm going to do: predict-no
  4311. ENV: Agent did: predict-no for direction R in state State-B
  4312. In State-B moving R
  4313. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4314. predict error 0
  4315. dir: dir isL
  4316. \-/608: O: O1215 (predict-yes)
  4317. I see 1 and I'm going to do: predict-yes
  4318. ENV: Agent did: predict-yes for direction L in state State-B
  4319. In State-B moving L
  4320. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  4321. predict error 0
  4322. dir: dir isL
  4323. |\-609: O: O1218 (predict-no)
  4324. I see 1 and I'm going to do: predict-no
  4325. ENV: Agent did: predict-no for direction L in state State-A
  4326. In State-A moving L
  4327. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4328. predict error 0
  4329. dir: dir isL
  4330. /|\610: O: O1220 (predict-no)
  4331. I see 1 and I'm going to do: predict-no
  4332. ENV: Agent did: predict-no for direction L in state State-A
  4333. In State-A moving L
  4334. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4335. predict error 0
  4336. dir: dir isU
  4337. -/611: O: O1222 (predict-no)
  4338. I see 1 and I'm going to do: predict-no
  4339. ENV: Agent did: predict-no for direction U in state State-A
  4340. In State-A moving U
  4341. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4342. predict error 0
  4343. dir: dir isU
  4344. |612: O: O1224 (predict-no)
  4345. I see 1 and I'm going to do: predict-no
  4346. ENV: Agent did: predict-no for direction U in state State-A
  4347. In State-A moving U
  4348. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4349. predict error 0
  4350. dir: dir isR
  4351. \-/613: O: O1225 (predict-yes)
  4352. I see 1 and I'm going to do: predict-yes
  4353. ENV: Agent did: predict-yes for direction R in state State-A
  4354. In State-A moving R
  4355. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  4356. predict error 0
  4357. dir: dir isL
  4358. |\-/614: O: O1227 (predict-yes)
  4359. I see 1 and I'm going to do: predict-yes
  4360. ENV: Agent did: predict-yes for direction L in state State-B
  4361. In State-B moving L
  4362. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  4363. predict error 0
  4364. dir: dir isU
  4365. |\-615: O: O1230 (predict-no)
  4366. I see 1 and I'm going to do: predict-no
  4367. ENV: Agent did: predict-no for direction U in state State-A
  4368. In State-A moving U
  4369. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4370. predict error 0
  4371. dir: dir isL
  4372. /|\616: O: O1232 (predict-no)
  4373. I see 1 and I'm going to do: predict-no
  4374. ENV: Agent did: predict-no for direction L in state State-A
  4375. In State-A moving L
  4376. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4377. predict error 0
  4378. dir: dir isR
  4379. -/|617: O: O1233 (predict-yes)
  4380. I see 1 and I'm going to do: predict-yes
  4381. ENV: Agent did: predict-yes for direction R in state State-A
  4382. In State-A moving R
  4383. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  4384. predict error 0
  4385. dir: dir isR
  4386. \618: O: O1236 (predict-no)
  4387. I see 1 and I'm going to do: predict-no
  4388. ENV: Agent did: predict-no for direction R in state State-B
  4389. In State-B moving R
  4390. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4391. predict error 0
  4392. dir: dir isL
  4393. -/|619: O: O1237 (predict-yes)
  4394. I see 1 and I'm going to do: predict-yes
  4395. ENV: Agent did: predict-yes for direction L in state State-B
  4396. In State-B moving L
  4397. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  4398. predict error 0
  4399. dir: dir isU
  4400. \-/620: O: O1240 (predict-no)
  4401. I see 1 and I'm going to do: predict-no
  4402. ENV: Agent did: predict-no for direction U in state State-A
  4403. In State-A moving U
  4404. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4405. predict error 0
  4406. dir: dir isL
  4407. |\-621: O: O1242 (predict-no)
  4408. I see 1 and I'm going to do: predict-no
  4409. ENV: Agent did: predict-no for direction L in state State-A
  4410. In State-A moving L
  4411. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4412. predict error 0
  4413. dir: dir isR
  4414. /622: O: O1243 (predict-yes)
  4415. I see 1 and I'm going to do: predict-yes
  4416. ENV: Agent did: predict-yes for direction R in state State-A
  4417. In State-A moving R
  4418. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  4419. predict error 0
  4420. dir: dir isL
  4421. |\-623: O: O1245 (predict-yes)
  4422. I see 1 and I'm going to do: predict-yes
  4423. ENV: Agent did: predict-yes for direction L in state State-B
  4424. In State-B moving L
  4425. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  4426. predict error 0
  4427. dir: dir isR
  4428. /|\624: O: O1247 (predict-yes)
  4429. I see 1 and I'm going to do: predict-yes
  4430. ENV: Agent did: predict-yes for direction R in state State-A
  4431. In State-A moving R
  4432. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  4433. predict error 0
  4434. dir: dir isR
  4435. -/|625: O: O1250 (predict-no)
  4436. I see 1 and I'm going to do: predict-no
  4437. ENV: Agent did: predict-no for direction R in state State-B
  4438. In State-B moving R
  4439. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4440. predict error 0
  4441. dir: dir isR
  4442. \-/626: O: O1252 (predict-no)
  4443. I see 1 and I'm going to do: predict-no
  4444. ENV: Agent did: predict-no for direction R in state State-B
  4445. In State-B moving R
  4446. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4447. predict error 0
  4448. dir: dir isR
  4449. |\-627: O: O1254 (predict-no)
  4450. I see 1 and I'm going to do: predict-no
  4451. ENV: Agent did: predict-no for direction R in state State-B
  4452. In State-B moving R
  4453. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4454. predict error 0
  4455. dir: dir isR
  4456. /|\628: O: O1256 (predict-no)
  4457. I see 1 and I'm going to do: predict-no
  4458. ENV: Agent did: predict-no for direction R in state State-B
  4459. In State-B moving R
  4460. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4461. predict error 0
  4462. dir: dir isR
  4463. -/|629: O: O1258 (predict-no)
  4464. I see 1 and I'm going to do: predict-no
  4465. ENV: Agent did: predict-no for direction R in state State-B
  4466. In State-B moving R
  4467. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4468. predict error 0
  4469. dir: dir isR
  4470. \-/630: O: O1260 (predict-no)
  4471. I see 1 and I'm going to do: predict-no
  4472. ENV: Agent did: predict-no for direction R in state State-B
  4473. In State-B moving R
  4474. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4475. predict error 0
  4476. dir: dir isU
  4477. |\-/631: O: O1262 (predict-no)
  4478. I see 1 and I'm going to do: predict-no
  4479. ENV: Agent did: predict-no for direction U in state State-B
  4480. In State-B moving U
  4481. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4482. predict error 0
  4483. dir: dir isU
  4484. |632: O: O1264 (predict-no)
  4485. I see 1 and I'm going to do: predict-no
  4486. ENV: Agent did: predict-no for direction U in state State-B
  4487. In State-B moving U
  4488. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4489. predict error 0
  4490. dir: dir isL
  4491. \-/633: O: O1265 (predict-yes)
  4492. I see 1 and I'm going to do: predict-yes
  4493. ENV: Agent did: predict-yes for direction L in state State-B
  4494. In State-B moving L
  4495. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  4496. predict error 0
  4497. dir: dir isR
  4498. |\634: O: O1267 (predict-yes)
  4499. I see 1 and I'm going to do: predict-yes
  4500. ENV: Agent did: predict-yes for direction R in state State-A
  4501. In State-A moving R
  4502. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  4503. predict error 0
  4504. dir: dir isR
  4505. -/635: O: O1270 (predict-no)
  4506. I see 1 and I'm going to do: predict-no
  4507. ENV: Agent did: predict-no for direction R in state State-B
  4508. In State-B moving R
  4509. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4510. predict error 0
  4511. dir: dir isL
  4512. |\-636: O: O1271 (predict-yes)
  4513. I see 1 and I'm going to do: predict-yes
  4514. ENV: Agent did: predict-yes for direction L in state State-B
  4515. In State-B moving L
  4516. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  4517. predict error 0
  4518. dir: dir isU
  4519. /|\637: O: O1274 (predict-no)
  4520. I see 1 and I'm going to do: predict-no
  4521. ENV: Agent did: predict-no for direction U in state State-A
  4522. In State-A moving U
  4523. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4524. predict error 0
  4525. dir: dir isR
  4526. -/|638: O: O1275 (predict-yes)
  4527. I see 1 and I'm going to do: predict-yes
  4528. ENV: Agent did: predict-yes for direction R in state State-A
  4529. In State-A moving R
  4530. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  4531. predict error 0
  4532. dir: dir isR
  4533. \-/639: O: O1278 (predict-no)
  4534. I see 1 and I'm going to do: predict-no
  4535. ENV: Agent did: predict-no for direction R in state State-B
  4536. In State-B moving R
  4537. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4538. predict error 0
  4539. dir: dir isL
  4540. |\-640: O: O1279 (predict-yes)
  4541. I see 1 and I'm going to do: predict-yes
  4542. ENV: Agent did: predict-yes for direction L in state State-B
  4543. In State-B moving L
  4544. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  4545. predict error 0
  4546. dir: dir isU
  4547. /|\641: O: O1282 (predict-no)
  4548. I see 1 and I'm going to do: predict-no
  4549. ENV: Agent did: predict-no for direction U in state State-A
  4550. In State-A moving U
  4551. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4552. predict error 0
  4553. dir: dir isR
  4554. -642: O: O1283 (predict-yes)
  4555. I see 1 and I'm going to do: predict-yes
  4556. ENV: Agent did: predict-yes for direction R in state State-A
  4557. In State-A moving R
  4558. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  4559. predict error 0
  4560. dir: dir isR
  4561. /|\643: O: O1286 (predict-no)
  4562. I see 1 and I'm going to do: predict-no
  4563. ENV: Agent did: predict-no for direction R in state State-B
  4564. In State-B moving R
  4565. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4566. predict error 0
  4567. dir: dir isR
  4568. -/|644: O: O1288 (predict-no)
  4569. I see 1 and I'm going to do: predict-no
  4570. ENV: Agent did: predict-no for direction R in state State-B
  4571. In State-B moving R
  4572. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4573. predict error 0
  4574. dir: dir isR
  4575. \-/645: O: O1290 (predict-no)
  4576. I see 1 and I'm going to do: predict-no
  4577. ENV: Agent did: predict-no for direction R in state State-B
  4578. In State-B moving R
  4579. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4580. predict error 0
  4581. dir: dir isU
  4582. |\-646: O: O1292 (predict-no)
  4583. I see 1 and I'm going to do: predict-no
  4584. ENV: Agent did: predict-no for direction U in state State-B
  4585. In State-B moving U
  4586. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4587. predict error 0
  4588. dir: dir isL
  4589. /|\647: O: O1294 (predict-no)
  4590. I see 1 and I'm going to do: predict-no
  4591. ENV: Agent did: predict-no for direction L in state State-B
  4592. In State-B moving L
  4593. ENV: (next state, see, prediction correct?) = (State-A, 1, False)
  4594. predict error 1
  4595. dir: dir isR
  4596. -/|648: O: O1295 (predict-yes)
  4597. I see 0 and I'm going to do: predict-yes
  4598. ENV: Agent did: predict-yes for direction R in state State-A
  4599. In State-A moving R
  4600. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  4601. predict error 0
  4602. dir: dir isL
  4603. \-/|649: O: O1297 (predict-yes)
  4604. I see 1 and I'm going to do: predict-yes
  4605. ENV: Agent did: predict-yes for direction L in state State-B
  4606. In State-B moving L
  4607. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  4608. predict error 0
  4609. dir: dir isL
  4610. \-/650: O: O1300 (predict-no)
  4611. I see 1 and I'm going to do: predict-no
  4612. ENV: Agent did: predict-no for direction L in state State-A
  4613. In State-A moving L
  4614. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4615. predict error 0
  4616. dir: dir isU
  4617. |\-651: O: O1302 (predict-no)
  4618. I see 1 and I'm going to do: predict-no
  4619. ENV: Agent did: predict-no for direction U in state State-A
  4620. In State-A moving U
  4621. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4622. predict error 0
  4623. dir: dir isL
  4624. /652: O: O1303 (predict-yes)
  4625. I see 1 and I'm going to do: predict-yes
  4626. ENV: Agent did: predict-yes for direction L in state State-A
  4627. In State-A moving L
  4628. ENV: (next state, see, prediction correct?) = (State-A, 0, False)
  4629. predict error 1
  4630. dir: dir isR
  4631. |\-653: O: O1305 (predict-yes)
  4632. I see 0 and I'm going to do: predict-yes
  4633. ENV: Agent did: predict-yes for direction R in state State-A
  4634. In State-A moving R
  4635. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  4636. predict error 0
  4637. dir: dir isL
  4638. /|\654: O: O1307 (predict-yes)
  4639. I see 1 and I'm going to do: predict-yes
  4640. ENV: Agent did: predict-yes for direction L in state State-B
  4641. In State-B moving L
  4642. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  4643. predict error 0
  4644. dir: dir isR
  4645. -/|655: O: O1309 (predict-yes)
  4646. I see 1 and I'm going to do: predict-yes
  4647. ENV: Agent did: predict-yes for direction R in state State-A
  4648. In State-A moving R
  4649. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  4650. predict error 0
  4651. dir: dir isU
  4652. \-/656: O: O1312 (predict-no)
  4653. I see 1 and I'm going to do: predict-no
  4654. ENV: Agent did: predict-no for direction U in state State-B
  4655. In State-B moving U
  4656. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4657. predict error 0
  4658. dir: dir isL
  4659. |\-657: O: O1313 (predict-yes)
  4660. I see 1 and I'm going to do: predict-yes
  4661. ENV: Agent did: predict-yes for direction L in state State-B
  4662. In State-B moving L
  4663. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  4664. predict error 0
  4665. dir: dir isR
  4666. /|\658: O: O1315 (predict-yes)
  4667. I see 1 and I'm going to do: predict-yes
  4668. ENV: Agent did: predict-yes for direction R in state State-A
  4669. In State-A moving R
  4670. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  4671. predict error 0
  4672. dir: dir isL
  4673. -/|659: O: O1317 (predict-yes)
  4674. I see 1 and I'm going to do: predict-yes
  4675. ENV: Agent did: predict-yes for direction L in state State-B
  4676. In State-B moving L
  4677. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  4678. predict error 0
  4679. dir: dir isU
  4680. \-660: O: O1320 (predict-no)
  4681. I see 1 and I'm going to do: predict-no
  4682. ENV: Agent did: predict-no for direction U in state State-A
  4683. In State-A moving U
  4684. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4685. predict error 0
  4686. dir: dir isU
  4687. /|\-661: O: O1322 (predict-no)
  4688. I see 1 and I'm going to do: predict-no
  4689. ENV: Agent did: predict-no for direction U in state State-A
  4690. In State-A moving U
  4691. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4692. predict error 0
  4693. dir: dir isU
  4694. /662: O: O1324 (predict-no)
  4695. I see 1 and I'm going to do: predict-no
  4696. ENV: Agent did: predict-no for direction U in state State-A
  4697. In State-A moving U
  4698. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4699. predict error 0
  4700. dir: dir isU
  4701. |\-663: O: O1326 (predict-no)
  4702. I see 1 and I'm going to do: predict-no
  4703. ENV: Agent did: predict-no for direction U in state State-A
  4704. In State-A moving U
  4705. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4706. predict error 0
  4707. dir: dir isL
  4708. /|\664: O: O1328 (predict-no)
  4709. I see 1 and I'm going to do: predict-no
  4710. ENV: Agent did: predict-no for direction L in state State-A
  4711. In State-A moving L
  4712. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4713. predict error 0
  4714. dir: dir isL
  4715. -/|665: O: O1330 (predict-no)
  4716. I see 1 and I'm going to do: predict-no
  4717. ENV: Agent did: predict-no for direction L in state State-A
  4718. In State-A moving L
  4719. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4720. predict error 0
  4721. dir: dir isR
  4722. \-/666: O: O1331 (predict-yes)
  4723. I see 1 and I'm going to do: predict-yes
  4724. ENV: Agent did: predict-yes for direction R in state State-A
  4725. In State-A moving R
  4726. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  4727. predict error 0
  4728. dir: dir isU
  4729. |\-667: O: O1334 (predict-no)
  4730. I see 1 and I'm going to do: predict-no
  4731. ENV: Agent did: predict-no for direction U in state State-B
  4732. In State-B moving U
  4733. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4734. predict error 0
  4735. dir: dir isU
  4736. /|668: O: O1336 (predict-no)
  4737. I see 1 and I'm going to do: predict-no
  4738. ENV: Agent did: predict-no for direction U in state State-B
  4739. In State-B moving U
  4740. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4741. predict error 0
  4742. dir: dir isU
  4743. \-/669: O: O1338 (predict-no)
  4744. I see 1 and I'm going to do: predict-no
  4745. ENV: Agent did: predict-no for direction U in state State-B
  4746. In State-B moving U
  4747. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4748. predict error 0
  4749. dir: dir isU
  4750. |\-670: O: O1340 (predict-no)
  4751. I see 1 and I'm going to do: predict-no
  4752. ENV: Agent did: predict-no for direction U in state State-B
  4753. In State-B moving U
  4754. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4755. predict error 0
  4756. dir: dir isL
  4757. /|\671: O: O1341 (predict-yes)
  4758. I see 1 and I'm going to do: predict-yes
  4759. ENV: Agent did: predict-yes for direction L in state State-B
  4760. In State-B moving L
  4761. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  4762. predict error 0
  4763. dir: dir isU
  4764. -672: O: O1344 (predict-no)
  4765. I see 1 and I'm going to do: predict-no
  4766. ENV: Agent did: predict-no for direction U in state State-A
  4767. In State-A moving U
  4768. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4769. predict error 0
  4770. dir: dir isL
  4771. /|673: O: O1346 (predict-no)
  4772. I see 1 and I'm going to do: predict-no
  4773. ENV: Agent did: predict-no for direction L in state State-A
  4774. In State-A moving L
  4775. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4776. predict error 0
  4777. dir: dir isL
  4778. \-674: O: O1348 (predict-no)
  4779. I see 1 and I'm going to do: predict-no
  4780. ENV: Agent did: predict-no for direction L in state State-A
  4781. In State-A moving L
  4782. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4783. predict error 0
  4784. dir: dir isR
  4785. /|\675: O: O1349 (predict-yes)
  4786. I see 1 and I'm going to do: predict-yes
  4787. ENV: Agent did: predict-yes for direction R in state State-A
  4788. In State-A moving R
  4789. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  4790. predict error 0
  4791. dir: dir isL
  4792. -/|676: O: O1351 (predict-yes)
  4793. I see 1 and I'm going to do: predict-yes
  4794. ENV: Agent did: predict-yes for direction L in state State-B
  4795. In State-B moving L
  4796. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  4797. predict error 0
  4798. dir: dir isL
  4799. \-/677: O: O1354 (predict-no)
  4800. I see 1 and I'm going to do: predict-no
  4801. ENV: Agent did: predict-no for direction L in state State-A
  4802. In State-A moving L
  4803. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4804. predict error 0
  4805. dir: dir isR
  4806. |\-678: O: O1355 (predict-yes)
  4807. I see 1 and I'm going to do: predict-yes
  4808. ENV: Agent did: predict-yes for direction R in state State-A
  4809. In State-A moving R
  4810. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  4811. predict error 0
  4812. dir: dir isU
  4813. /|\679: O: O1358 (predict-no)
  4814. I see 1 and I'm going to do: predict-no
  4815. ENV: Agent did: predict-no for direction U in state State-B
  4816. In State-B moving U
  4817. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4818. predict error 0
  4819. dir: dir isR
  4820. -/|680: O: O1360 (predict-no)
  4821. I see 1 and I'm going to do: predict-no
  4822. ENV: Agent did: predict-no for direction R in state State-B
  4823. In State-B moving R
  4824. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4825. predict error 0
  4826. dir: dir isR
  4827. \-/681: O: O1362 (predict-no)
  4828. I see 1 and I'm going to do: predict-no
  4829. ENV: Agent did: predict-no for direction R in state State-B
  4830. In State-B moving R
  4831. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4832. predict error 0
  4833. dir: dir isU
  4834. |682: O: O1364 (predict-no)
  4835. I see 1 and I'm going to do: predict-no
  4836. ENV: Agent did: predict-no for direction U in state State-B
  4837. In State-B moving U
  4838. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4839. predict error 0
  4840. dir: dir isR
  4841. \-/683: O: O1366 (predict-no)
  4842. I see 1 and I'm going to do: predict-no
  4843. ENV: Agent did: predict-no for direction R in state State-B
  4844. In State-B moving R
  4845. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4846. predict error 0
  4847. dir: dir isL
  4848. |\-684: O: O1367 (predict-yes)
  4849. I see 1 and I'm going to do: predict-yes
  4850. ENV: Agent did: predict-yes for direction L in state State-B
  4851. In State-B moving L
  4852. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  4853. predict error 0
  4854. dir: dir isU
  4855. /|\685: O: O1370 (predict-no)
  4856. I see 1 and I'm going to do: predict-no
  4857. ENV: Agent did: predict-no for direction U in state State-A
  4858. In State-A moving U
  4859. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4860. predict error 0
  4861. dir: dir isR
  4862. -/|686: O: O1371 (predict-yes)
  4863. I see 1 and I'm going to do: predict-yes
  4864. ENV: Agent did: predict-yes for direction R in state State-A
  4865. In State-A moving R
  4866. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  4867. predict error 0
  4868. dir: dir isU
  4869. \-/687: O: O1374 (predict-no)
  4870. I see 1 and I'm going to do: predict-no
  4871. ENV: Agent did: predict-no for direction U in state State-B
  4872. In State-B moving U
  4873. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4874. predict error 0
  4875. dir: dir isR
  4876. |\-688: O: O1376 (predict-no)
  4877. I see 1 and I'm going to do: predict-no
  4878. ENV: Agent did: predict-no for direction R in state State-B
  4879. In State-B moving R
  4880. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4881. predict error 0
  4882. dir: dir isU
  4883. /|\689: O: O1378 (predict-no)
  4884. I see 1 and I'm going to do: predict-no
  4885. ENV: Agent did: predict-no for direction U in state State-B
  4886. In State-B moving U
  4887. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4888. predict error 0
  4889. dir: dir isR
  4890. -/|690: O: O1380 (predict-no)
  4891. I see 1 and I'm going to do: predict-no
  4892. ENV: Agent did: predict-no for direction R in state State-B
  4893. In State-B moving R
  4894. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4895. predict error 0
  4896. dir: dir isL
  4897. \-/691: O: O1381 (predict-yes)
  4898. I see 1 and I'm going to do: predict-yes
  4899. ENV: Agent did: predict-yes for direction L in state State-B
  4900. In State-B moving L
  4901. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  4902. predict error 0
  4903. dir: dir isL
  4904. |692: O: O1384 (predict-no)
  4905. I see 1 and I'm going to do: predict-no
  4906. ENV: Agent did: predict-no for direction L in state State-A
  4907. In State-A moving L
  4908. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4909. predict error 0
  4910. dir: dir isU
  4911. \-693: O: O1386 (predict-no)
  4912. I see 1 and I'm going to do: predict-no
  4913. ENV: Agent did: predict-no for direction U in state State-A
  4914. In State-A moving U
  4915. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4916. predict error 0
  4917. dir: dir isR
  4918. /|\694: O: O1387 (predict-yes)
  4919. I see 1 and I'm going to do: predict-yes
  4920. ENV: Agent did: predict-yes for direction R in state State-A
  4921. In State-A moving R
  4922. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  4923. predict error 0
  4924. dir: dir isL
  4925. -/|695: O: O1389 (predict-yes)
  4926. I see 1 and I'm going to do: predict-yes
  4927. ENV: Agent did: predict-yes for direction L in state State-B
  4928. In State-B moving L
  4929. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  4930. predict error 0
  4931. dir: dir isR
  4932. \-/696: O: O1391 (predict-yes)
  4933. I see 1 and I'm going to do: predict-yes
  4934. ENV: Agent did: predict-yes for direction R in state State-A
  4935. In State-A moving R
  4936. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  4937. predict error 0
  4938. dir: dir isL
  4939. |\-697: O: O1393 (predict-yes)
  4940. I see 1 and I'm going to do: predict-yes
  4941. ENV: Agent did: predict-yes for direction L in state State-B
  4942. In State-B moving L
  4943. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  4944. predict error 0
  4945. dir: dir isL
  4946. /|698: O: O1396 (predict-no)
  4947. I see 1 and I'm going to do: predict-no
  4948. ENV: Agent did: predict-no for direction L in state State-A
  4949. In State-A moving L
  4950. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4951. predict error 0
  4952. dir: dir isL
  4953. \-699: O: O1398 (predict-no)
  4954. I see 1 and I'm going to do: predict-no
  4955. ENV: Agent did: predict-no for direction L in state State-A
  4956. In State-A moving L
  4957. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4958. predict error 0
  4959. dir: dir isL
  4960. /700: O: O1400 (predict-no)
  4961. I see 1 and I'm going to do: predict-no
  4962. ENV: Agent did: predict-no for direction L in state State-A
  4963. In State-A moving L
  4964. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4965. predict error 0
  4966. dir: dir isR
  4967. |\-701: O: O1401 (predict-yes)
  4968. I see 1 and I'm going to do: predict-yes
  4969. ENV: Agent did: predict-yes for direction R in state State-A
  4970. In State-A moving R
  4971. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  4972. predict error 0
  4973. dir: dir isL
  4974. /702: O: O1403 (predict-yes)
  4975. I see 1 and I'm going to do: predict-yes
  4976. ENV: Agent did: predict-yes for direction L in state State-B
  4977. In State-B moving L
  4978. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  4979. predict error 0
  4980. dir: dir isR
  4981. |\-703: O: O1405 (predict-yes)
  4982. I see 1 and I'm going to do: predict-yes
  4983. ENV: Agent did: predict-yes for direction R in state State-A
  4984. In State-A moving R
  4985. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  4986. predict error 0
  4987. dir: dir isR
  4988. /|704: O: O1408 (predict-no)
  4989. I see 1 and I'm going to do: predict-no
  4990. ENV: Agent did: predict-no for direction R in state State-B
  4991. In State-B moving R
  4992. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4993. predict error 0
  4994. dir: dir isU
  4995. \-/705: O: O1410 (predict-no)
  4996. I see 1 and I'm going to do: predict-no
  4997. ENV: Agent did: predict-no for direction U in state State-B
  4998. In State-B moving U
  4999. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5000. predict error 0
  5001. dir: dir isR
  5002. |\-706: O: O1412 (predict-no)
  5003. I see 1 and I'm going to do: predict-no
  5004. ENV: Agent did: predict-no for direction R in state State-B
  5005. In State-B moving R
  5006. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5007. predict error 0
  5008. dir: dir isL
  5009. /|\707: O: O1413 (predict-yes)
  5010. I see 1 and I'm going to do: predict-yes
  5011. ENV: Agent did: predict-yes for direction L in state State-B
  5012. In State-B moving L
  5013. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  5014. predict error 0
  5015. dir: dir isU
  5016. -/|708: O: O1416 (predict-no)
  5017. I see 1 and I'm going to do: predict-no
  5018. ENV: Agent did: predict-no for direction U in state State-A
  5019. In State-A moving U
  5020. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  5021. predict error 0
  5022. dir: dir isR
  5023. \-/709: O: O1417 (predict-yes)
  5024. I see 1 and I'm going to do: predict-yes
  5025. ENV: Agent did: predict-yes for direction R in state State-A
  5026. In State-A moving R
  5027. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  5028. predict error 0
  5029. dir: dir isR
  5030. |\-710: O: O1420 (predict-no)
  5031. I see 1 and I'm going to do: predict-no
  5032. ENV: Agent did: predict-no for direction R in state State-B
  5033. In State-B moving R
  5034. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5035. predict error 0
  5036. dir: dir isR
  5037. /|\711: O: O1422 (predict-no)
  5038. I see 1 and I'm going to do: predict-no
  5039. ENV: Agent did: predict-no for direction R in state State-B
  5040. In State-B moving R
  5041. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5042. predict error 0
  5043. dir: dir isR
  5044. -712: O: O1424 (predict-no)
  5045. I see 1 and I'm going to do: predict-no
  5046. ENV: Agent did: predict-no for direction R in state State-B
  5047. In State-B moving R
  5048. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5049. predict error 0
  5050. dir: dir isU
  5051. /|\713: O: O1426 (predict-no)
  5052. I see 1 and I'm going to do: predict-no
  5053. ENV: Agent did: predict-no for direction U in state State-B
  5054. In State-B moving U
  5055. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5056. predict error 0
  5057. dir: dir isU
  5058. -/|714: O: O1428 (predict-no)
  5059. I see 1 and I'm going to do: predict-no
  5060. ENV: Agent did: predict-no for direction U in state State-B
  5061. In State-B moving U
  5062. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5063. predict error 0
  5064. dir: dir isU
  5065. \-715: O: O1430 (predict-no)
  5066. I see 1 and I'm going to do: predict-no
  5067. ENV: Agent did: predict-no for direction U in state State-B
  5068. In State-B moving U
  5069. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5070. predict error 0
  5071. dir: dir isU
  5072. /|\716: O: O1432 (predict-no)
  5073. I see 1 and I'm going to do: predict-no
  5074. ENV: Agent did: predict-no for direction U in state State-B
  5075. In State-B moving U
  5076. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5077. predict error 0
  5078. dir: dir isR
  5079. -/|717: O: O1434 (predict-no)
  5080. I see 1 and I'm going to do: predict-no
  5081. ENV: Agent did: predict-no for direction R in state State-B
  5082. In State-B moving R
  5083. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5084. predict error 0
  5085. dir: dir isR
  5086. \-718: O: O1436 (predict-no)
  5087. I see 1 and I'm going to do: predict-no
  5088. ENV: Agent did: predict-no for direction R in state State-B
  5089. In State-B moving R
  5090. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5091. predict error 0
  5092. dir: dir isU
  5093. /|\719: O: O1438 (predict-no)
  5094. I see 1 and I'm going to do: predict-no
  5095. ENV: Agent did: predict-no for direction U in state State-B
  5096. In State-B moving U
  5097. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5098. predict error 0
  5099. dir: dir isL
  5100. -720: O: O1439 (predict-yes)
  5101. I see 1 and I'm going to do: predict-yes
  5102. ENV: Agent did: predict-yes for direction L in state State-B
  5103. In State-B moving L
  5104. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  5105. predict error 0
  5106. dir: dir isL
  5107. /|\721: O: O1442 (predict-no)
  5108. I see 1 and I'm going to do: predict-no
  5109. ENV: Agent did: predict-no for direction L in state State-A
  5110. In State-A moving L
  5111. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  5112. predict error 0
  5113. dir: dir isL
  5114. -722: O: O1444 (predict-no)
  5115. I see 1 and I'm going to do: predict-no
  5116. ENV: Agent did: predict-no for direction L in state State-A
  5117. In State-A moving L
  5118. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  5119. predict error 0
  5120. dir: dir isL
  5121. /|\723: O: O1446 (predict-no)
  5122. I see 1 and I'm going to do: predict-no
  5123. ENV: Agent did: predict-no for direction L in state State-A
  5124. In State-A moving L
  5125. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  5126. predict error 0
  5127. dir: dir isL
  5128. -/|724: O: O1448 (predict-no)
  5129. I see 1 and I'm going to do: predict-no
  5130. ENV: Agent did: predict-no for direction L in state State-A
  5131. In State-A moving L
  5132. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  5133. predict error 0
  5134. dir: dir isR
  5135. \-/725: O: O1449 (predict-yes)
  5136. I see 1 and I'm going to do: predict-yes
  5137. ENV: Agent did: predict-yes for direction R in state State-A
  5138. In State-A moving R
  5139. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  5140. predict error 0
  5141. dir: dir isL
  5142. |\-726: O: O1451 (predict-yes)
  5143. I see 1 and I'm going to do: predict-yes
  5144. ENV: Agent did: predict-yes for direction L in state State-B
  5145. In State-B moving L
  5146. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  5147. predict error 0
  5148. dir: dir isU
  5149. /|\727: O: O1454 (predict-no)
  5150. I see 1 and I'm going to do: predict-no
  5151. ENV: Agent did: predict-no for direction U in state State-A
  5152. In State-A moving U
  5153. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  5154. predict error 0
  5155. dir: dir isU
  5156. -/|728: O: O1456 (predict-no)
  5157. I see 1 and I'm going to do: predict-no
  5158. ENV: Agent did: predict-no for direction U in state State-A
  5159. In State-A moving U
  5160. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  5161. predict error 0
  5162. dir: dir isU
  5163. \-729: O: O1458 (predict-no)
  5164. I see 1 and I'm going to do: predict-no
  5165. ENV: Agent did: predict-no for direction U in state State-A
  5166. In State-A moving U
  5167. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  5168. predict error 0
  5169. dir: dir isR
  5170. /730: O: O1459 (predict-yes)
  5171. I see 1 and I'm going to do: predict-yes
  5172. ENV: Agent did: predict-yes for direction R in state State-A
  5173. In State-A moving R
  5174. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  5175. predict error 0
  5176. dir: dir isU
  5177. |\-731: O: O1462 (predict-no)
  5178. I see 1 and I'm going to do: predict-no
  5179. ENV: Agent did: predict-no for direction U in state State-B
  5180. In State-B moving U
  5181. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5182. predict error 0
  5183. dir: dir isR
  5184. /732: O: O1464 (predict-no)
  5185. I see 1 and I'm going to do: predict-no
  5186. ENV: Agent did: predict-no for direction R in state State-B
  5187. In State-B moving R
  5188. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5189. predict error 0
  5190. dir: dir isR
  5191. |\-733: O: O1466 (predict-no)
  5192. I see 1 and I'm going to do: predict-no
  5193. ENV: Agent did: predict-no for direction R in state State-B
  5194. In State-B moving R
  5195. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5196. predict error 0
  5197. dir: dir isL
  5198. /|734: O: O1467 (predict-yes)
  5199. I see 1 and I'm going to do: predict-yes
  5200. ENV: Agent did: predict-yes for direction L in state State-B
  5201. In State-B moving L
  5202. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  5203. predict error 0
  5204. dir: dir isU
  5205. \-735: O: O1470 (predict-no)
  5206. I see 1 and I'm going to do: predict-no
  5207. ENV: Agent did: predict-no for direction U in state State-A
  5208. In State-A moving U
  5209. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  5210. predict error 0
  5211. dir: dir isU
  5212. /|\736: O: O1472 (predict-no)
  5213. I see 1 and I'm going to do: predict-no
  5214. ENV: Agent did: predict-no for direction U in state State-A
  5215. In State-A moving U
  5216. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  5217. predict error 0
  5218. dir: dir isL
  5219. -/|737: O: O1474 (predict-no)
  5220. I see 1 and I'm going to do: predict-no
  5221. ENV: Agent did: predict-no for direction L in state State-A
  5222. In State-A moving L
  5223. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  5224. predict error 0
  5225. dir: dir isR
  5226. \-738: O: O1475 (predict-yes)
  5227. I see 1 and I'm going to do: predict-yes
  5228. ENV: Agent did: predict-yes for direction R in state State-A
  5229. In State-A moving R
  5230. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  5231. predict error 0
  5232. dir: dir isL
  5233. /|739: O: O1477 (predict-yes)
  5234. I see 1 and I'm going to do: predict-yes
  5235. ENV: Agent did: predict-yes for direction L in state State-B
  5236. In State-B moving L
  5237. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  5238. predict error 0
  5239. dir: dir isL
  5240. \-/740: O: O1480 (predict-no)
  5241. I see 1 and I'm going to do: predict-no
  5242. ENV: Agent did: predict-no for direction L in state State-A
  5243. In State-A moving L
  5244. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  5245. predict error 0
  5246. dir: dir isL
  5247. |\741: O: O1482 (predict-no)
  5248. I see 1 and I'm going to do: predict-no
  5249. ENV: Agent did: predict-no for direction L in state State-A
  5250. In State-A moving L
  5251. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  5252. predict error 0
  5253. dir: dir isR
  5254. -742: O: O1483 (predict-yes)
  5255. I see 1 and I'm going to do: predict-yes
  5256. ENV: Agent did: predict-yes for direction R in state State-A
  5257. In State-A moving R
  5258. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  5259. predict error 0
  5260. dir: dir isL
  5261. /|\743: O: O1485 (predict-yes)
  5262. I see 1 and I'm going to do: predict-yes
  5263. ENV: Agent did: predict-yes for direction L in state State-B
  5264. In State-B moving L
  5265. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  5266. predict error 0
  5267. dir: dir isR
  5268. -/|744: O: O1487 (predict-yes)
  5269. I see 1 and I'm going to do: predict-yes
  5270. ENV: Agent did: predict-yes for direction R in state State-A
  5271. In State-A moving R
  5272. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  5273. predict error 0
  5274. dir: dir isL
  5275. \-/745: O: O1489 (predict-yes)
  5276. I see 1 and I'm going to do: predict-yes
  5277. ENV: Agent did: predict-yes for direction L in state State-B
  5278. In State-B moving L
  5279. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  5280. predict error 0
  5281. dir: dir isL
  5282. |\-746: O: O1492 (predict-no)
  5283. I see 1 and I'm going to do: predict-no
  5284. ENV: Agent did: predict-no for direction L in state State-A
  5285. In State-A moving L
  5286. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  5287. predict error 0
  5288. dir: dir isU
  5289. /|\747: O: O1494 (predict-no)
  5290. I see 1 and I'm going to do: predict-no
  5291. ENV: Agent did: predict-no for direction U in state State-A
  5292. In State-A moving U
  5293. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  5294. predict error 0
  5295. dir: dir isU
  5296. -748: O: O1496 (predict-no)
  5297. I see 1 and I'm going to do: predict-no
  5298. ENV: Agent did: predict-no for direction U in state State-A
  5299. In State-A moving U
  5300. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  5301. predict error 0
  5302. dir: dir isL
  5303. /|\749: O: O1498 (predict-no)
  5304. I see 1 and I'm going to do: predict-no
  5305. ENV: Agent did: predict-no for direction L in state State-A
  5306. In State-A moving L
  5307. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  5308. predict error 0
  5309. dir: dir isU
  5310. -/|750: O: O1500 (predict-no)
  5311. I see 1 and I'm going to do: predict-no
  5312. ENV: Agent did: predict-no for direction U in state State-A
  5313. In State-A moving U
  5314. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  5315. predict error 0
  5316. dir: dir isL
  5317. \-751: O: O1502 (predict-no)
  5318. I see 1 and I'm going to do: predict-no
  5319. ENV: Agent did: predict-no for direction L in state State-A
  5320. In State-A moving L
  5321. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  5322. predict error 0
  5323. dir: dir isR
  5324. /752: O: O1503 (predict-yes)
  5325. I see 1 and I'm going to do: predict-yes
  5326. ENV: Agent did: predict-yes for direction R in state State-A
  5327. In State-A moving R
  5328. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  5329. predict error 0
  5330. dir: dir isU
  5331. |\-753: O: O1506 (predict-no)
  5332. I see 1 and I'm going to do: predict-no
  5333. ENV: Agent did: predict-no for direction U in state State-B
  5334. In State-B moving U
  5335. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5336. predict error 0
  5337. dir: dir isL
  5338. /|754: O: O1507 (predict-yes)
  5339. I see 1 and I'm going to do: predict-yes
  5340. ENV: Agent did: predict-yes for direction L in state State-B
  5341. In State-B moving L
  5342. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  5343. predict error 0
  5344. dir: dir isU
  5345. \-/755: O: O1510 (predict-no)
  5346. I see 1 and I'm going to do: predict-no
  5347. ENV: Agent did: predict-no for direction U in state State-A
  5348. In State-A moving U
  5349. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  5350. predict error 0
  5351. dir: dir isL
  5352. |\-756: O: O1512 (predict-no)
  5353. I see 1 and I'm going to do: predict-no
  5354. ENV: Agent did: predict-no for direction L in state State-A
  5355. In State-A moving L
  5356. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  5357. predict error 0
  5358. dir: dir isR
  5359. /|\757: O: O1513 (predict-yes)
  5360. I see 1 and I'm going to do: predict-yes
  5361. ENV: Agent did: predict-yes for direction R in state State-A
  5362. In State-A moving R
  5363. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  5364. predict error 0
  5365. dir: dir isU
  5366. -/758: O: O1516 (predict-no)
  5367. I see 1 and I'm going to do: predict-no
  5368. ENV: Agent did: predict-no for direction U in state State-B
  5369. In State-B moving U
  5370. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5371. predict error 0
  5372. dir: dir isL
  5373. |\-759: O: O1517 (predict-yes)
  5374. I see 1 and I'm going to do: predict-yes
  5375. ENV: Agent did: predict-yes for direction L in state State-B
  5376. In State-B moving L
  5377. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  5378. predict error 0
  5379. dir: dir isU
  5380. /|\760: O: O1520 (predict-no)
  5381. I see 1 and I'm going to do: predict-no
  5382. ENV: Agent did: predict-no for direction U in state State-A
  5383. In State-A moving U
  5384. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  5385. predict error 0
  5386. dir: dir isU
  5387. -/|761: O: O1522 (predict-no)
  5388. I see 1 and I'm going to do: predict-no
  5389. ENV: Agent did: predict-no for direction U in state State-A
  5390. In State-A moving U
  5391. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  5392. predict error 0
  5393. dir: dir isR
  5394. \762: O: O1523 (predict-yes)
  5395. I see 1 and I'm going to do: predict-yes
  5396. ENV: Agent did: predict-yes for direction R in state State-A
  5397. In State-A moving R
  5398. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  5399. predict error 0
  5400. dir: dir isL
  5401. -/|763: O: O1525 (predict-yes)
  5402. I see 1 and I'm going to do: predict-yes
  5403. ENV: Agent did: predict-yes for direction L in state State-B
  5404. In State-B moving L
  5405. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  5406. predict error 0
  5407. dir: dir isL
  5408. \-/764: O: O1528 (predict-no)
  5409. I see 1 and I'm going to do: predict-no
  5410. ENV: Agent did: predict-no for direction L in state State-A
  5411. In State-A moving L
  5412. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  5413. predict error 0
  5414. dir: dir isL
  5415. |\-765: O: O1530 (predict-no)
  5416. I see 1 and I'm going to do: predict-no
  5417. ENV: Agent did: predict-no for direction L in state State-A
  5418. In State-A moving L
  5419. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  5420. predict error 0
  5421. dir: dir isU
  5422. /|\766: O: O1532 (predict-no)
  5423. I see 1 and I'm going to do: predict-no
  5424. ENV: Agent did: predict-no for direction U in state State-A
  5425. In State-A moving U
  5426. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  5427. predict error 0
  5428. dir: dir isR
  5429. -/|767: O: O1533 (predict-yes)
  5430. I see 1 and I'm going to do: predict-yes
  5431. ENV: Agent did: predict-yes for direction R in state State-A
  5432. In State-A moving R
  5433. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  5434. predict error 0
  5435. dir: dir isU
  5436. \-768: O: O1536 (predict-no)
  5437. I see 1 and I'm going to do: predict-no
  5438. ENV: Agent did: predict-no for direction U in state State-B
  5439. In State-B moving U
  5440. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5441. predict error 0
  5442. dir: dir isR
  5443. /|\769: O: O1538 (predict-no)
  5444. I see 1 and I'm going to do: predict-no
  5445. ENV: Agent did: predict-no for direction R in state State-B
  5446. In State-B moving R
  5447. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5448. predict error 0
  5449. dir: dir isL
  5450. -/|\770: O: O1540 (predict-no)
  5451. I see 1 and I'm going to do: predict-no
  5452. ENV: Agent did: predict-no for direction L in state State-B
  5453. In State-B moving L
  5454. ENV: (next state, see, prediction correct?) = (State-A, 1, False)
  5455. predict error 1
  5456. dir: dir isR
  5457. -/|771: O: O1541 (predict-yes)
  5458. I see 0 and I'm going to do: predict-yes
  5459. ENV: Agent did: predict-yes for direction R in state State-A
  5460. In State-A moving R
  5461. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  5462. predict error 0
  5463. dir: dir isU
  5464. \772: O: O1544 (predict-no)
  5465. I see 1 and I'm going to do: predict-no
  5466. ENV: Agent did: predict-no for direction U in state State-B
  5467. In State-B moving U
  5468. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5469. predict error 0
  5470. dir: dir isU
  5471. -/|773: O: O1546 (predict-no)
  5472. I see 1 and I'm going to do: predict-no
  5473. ENV: Agent did: predict-no for direction U in state State-B
  5474. In State-B moving U
  5475. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5476. predict error 0
  5477. dir: dir isL
  5478. \-/774: O: O1547 (predict-yes)
  5479. I see 1 and I'm going to do: predict-yes
  5480. ENV: Agent did: predict-yes for direction L in state State-B
  5481. In State-B moving L
  5482. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  5483. predict error 0
  5484. dir: dir isL
  5485. |\-/775: O: O1550 (predict-no)
  5486. I see 1 and I'm going to do: predict-no
  5487. ENV: Agent did: predict-no for direction L in state State-A
  5488. In State-A moving L
  5489. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  5490. predict error 0
  5491. dir: dir isR
  5492. |\-776: O: O1551 (predict-yes)
  5493. I see 1 and I'm going to do: predict-yes
  5494. ENV: Agent did: predict-yes for direction R in state State-A
  5495. In State-A moving R
  5496. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  5497. predict error 0
  5498. dir: dir isL
  5499. /|\777: O: O1553 (predict-yes)
  5500. I see 1 and I'm going to do: predict-yes
  5501. ENV: Agent did: predict-yes for direction L in state State-B
  5502. In State-B moving L
  5503. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  5504. predict error 0
  5505. dir: dir isU
  5506. -/|778: O: O1556 (predict-no)
  5507. I see 1 and I'm going to do: predict-no
  5508. ENV: Agent did: predict-no for direction U in state State-A
  5509. In State-A moving U
  5510. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  5511. predict error 0
  5512. dir: dir isU
  5513. \-/779: O: O1558 (predict-no)
  5514. I see 1 and I'm going to do: predict-no
  5515. ENV: Agent did: predict-no for direction U in state State-A
  5516. In State-A moving U
  5517. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  5518. predict error 0
  5519. dir: dir isL
  5520. |\780: O: O1560 (predict-no)
  5521. I see 1 and I'm going to do: predict-no
  5522. ENV: Agent did: predict-no for direction L in state State-A
  5523. In State-A moving L
  5524. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  5525. predict error 0
  5526. dir: dir isR
  5527. -/781: O: O1561 (predict-yes)
  5528. I see 1 and I'm going to do: predict-yes
  5529. ENV: Agent did: predict-yes for direction R in state State-A
  5530. In State-A moving R
  5531. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  5532. predict error 0
  5533. dir: dir isR
  5534. |782: O: O1564 (predict-no)
  5535. I see 1 and I'm going to do: predict-no
  5536. ENV: Agent did: predict-no for direction R in state State-B
  5537. In State-B moving R
  5538. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5539. predict error 0
  5540. dir: dir isL
  5541. \-/783: O: O1565 (predict-yes)
  5542. I see 1 and I'm going to do: predict-yes
  5543. ENV: Agent did: predict-yes for direction L in state State-B
  5544. In State-B moving L
  5545. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  5546. predict error 0
  5547. dir: dir isR
  5548. |\-784: O: O1567 (predict-yes)
  5549. I see 1 and I'm going to do: predict-yes
  5550. ENV: Agent did: predict-yes for direction R in state State-A
  5551. In State-A moving R
  5552. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  5553. predict error 0
  5554. dir: dir isL
  5555. /|\785: O: O1569 (predict-yes)
  5556. I see 1 and I'm going to do: predict-yes
  5557. ENV: Agent did: predict-yes for direction L in state State-B
  5558. In State-B moving L
  5559. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  5560. predict error 0
  5561. dir: dir isL
  5562. -/|786: O: O1572 (predict-no)
  5563. I see 1 and I'm going to do: predict-no
  5564. ENV: Agent did: predict-no for direction L in state State-A
  5565. In State-A moving L
  5566. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  5567. predict error 0
  5568. dir: dir isR
  5569. \-/787: O: O1573 (predict-yes)
  5570. I see 1 and I'm going to do: predict-yes
  5571. ENV: Agent did: predict-yes for direction R in state State-A
  5572. In State-A moving R
  5573. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  5574. predict error 0
  5575. dir: dir isR
  5576. |\-788: O: O1576 (predict-no)
  5577. I see 1 and I'm going to do: predict-no
  5578. ENV: Agent did: predict-no for direction R in state State-B
  5579. In State-B moving R
  5580. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5581. predict error 0
  5582. dir: dir isR
  5583. /|789: O: O1578 (predict-no)
  5584. I see 1 and I'm going to do: predict-no
  5585. ENV: Agent did: predict-no for direction R in state State-B
  5586. In State-B moving R
  5587. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5588. predict error 0
  5589. dir: dir isL
  5590. \-/790: O: O1579 (predict-yes)
  5591. I see 1 and I'm going to do: predict-yes
  5592. ENV: Agent did: predict-yes for direction L in state State-B
  5593. In State-B moving L
  5594. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  5595. predict error 0
  5596. dir: dir isL
  5597. |\-791: O: O1582 (predict-no)
  5598. I see 1 and I'm going to do: predict-no
  5599. ENV: Agent did: predict-no for direction L in state State-A
  5600. In State-A moving L
  5601. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  5602. predict error 0
  5603. dir: dir isL
  5604. /792: O: O1584 (predict-no)
  5605. I see 1 and I'm going to do: predict-no
  5606. ENV: Agent did: predict-no for direction L in state State-A
  5607. In State-A moving L
  5608. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  5609. predict error 0
  5610. dir: dir isU
  5611. |\-793: O: O1586 (predict-no)
  5612. I see 1 and I'm going to do: predict-no
  5613. ENV: Agent did: predict-no for direction U in state State-A
  5614. In State-A moving U
  5615. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  5616. predict error 0
  5617. dir: dir isL
  5618. /|\794: O: O1588 (predict-no)
  5619. I see 1 and I'm going to do: predict-no
  5620. ENV: Agent did: predict-no for direction L in state State-A
  5621. In State-A moving L
  5622. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  5623. predict error 0
  5624. dir: dir isU
  5625. -/|795: O: O1590 (predict-no)
  5626. I see 1 and I'm going to do: predict-no
  5627. ENV: Agent did: predict-no for direction U in state State-A
  5628. In State-A moving U
  5629. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  5630. predict error 0
  5631. dir: dir isL
  5632. \-/796: O: O1592 (predict-no)
  5633. I see 1 and I'm going to do: predict-no
  5634. ENV: Agent did: predict-no for direction L in state State-A
  5635. In State-A moving L
  5636. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  5637. predict error 0
  5638. dir: dir isL
  5639. |\-797: O: O1594 (predict-no)
  5640. I see 1 and I'm going to do: predict-no
  5641. ENV: Agent did: predict-no for direction L in state State-A
  5642. In State-A moving L
  5643. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  5644. predict error 0
  5645. dir: dir isU
  5646. /|\798: O: O1596 (predict-no)
  5647. I see 1 and I'm going to do: predict-no
  5648. ENV: Agent did: predict-no for direction U in state State-A
  5649. In State-A moving U
  5650. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  5651. predict error 0
  5652. dir: dir isR
  5653. -/|799: O: O1597 (predict-yes)
  5654. I see 1 and I'm going to do: predict-yes
  5655. ENV: Agent did: predict-yes for direction R in state State-A
  5656. In State-A moving R
  5657. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  5658. predict error 0
  5659. dir: dir isU
  5660. \800: O: O1600 (predict-no)
  5661. I see 1 and I'm going to do: predict-no
  5662. ENV: Agent did: predict-no for direction U in state State-B
  5663. In State-B moving U
  5664. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5665. predict error 0
  5666. dir: dir isR
  5667. -/|801: O: O1602 (predict-no)
  5668. I see 1 and I'm going to do: predict-no
  5669. ENV: Agent did: predict-no for direction R in state State-B
  5670. In State-B moving R
  5671. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5672. predict error 0
  5673. dir: dir isU
  5674. \802: O: O1604 (predict-no)
  5675. I see 1 and I'm going to do: predict-no
  5676. ENV: Agent did: predict-no for direction U in state State-B
  5677. In State-B moving U
  5678. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5679. predict error 0
  5680. dir: dir isL
  5681. -/|803: O: O1605 (predict-yes)
  5682. I see 1 and I'm going to do: predict-yes
  5683. ENV: Agent did: predict-yes for direction L in state State-B
  5684. In State-B moving L
  5685. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  5686. predict error 0
  5687. dir: dir isR
  5688. \-/804: O: O1607 (predict-yes)
  5689. I see 1 and I'm going to do: predict-yes
  5690. ENV: Agent did: predict-yes for direction R in state State-A
  5691. In State-A moving R
  5692. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  5693. predict error 0
  5694. dir: dir isL
  5695. |\-805: O: O1609 (predict-yes)
  5696. I see 1 and I'm going to do: predict-yes
  5697. ENV: Agent did: predict-yes for direction L in state State-B
  5698. In State-B moving L
  5699. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  5700. predict error 0
  5701. dir: dir isU
  5702. /|\806: O: O1612 (predict-no)
  5703. I see 1 and I'm going to do: predict-no
  5704. ENV: Agent did: predict-no for direction U in state State-A
  5705. In State-A moving U
  5706. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  5707. predict error 0
  5708. dir: dir isR
  5709. -/|807: O: O1613 (predict-yes)
  5710. I see 1 and I'm going to do: predict-yes
  5711. ENV: Agent did: predict-yes for direction R in state State-A
  5712. In State-A moving R
  5713. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  5714. predict error 0
  5715. dir: dir isU
  5716. \-/808: O: O1616 (predict-no)
  5717. I see 1 and I'm going to do: predict-no
  5718. ENV: Agent did: predict-no for direction U in state State-B
  5719. In State-B moving U
  5720. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5721. predict error 0
  5722. dir: dir isU
  5723. |\809: O: O1618 (predict-no)
  5724. I see 1 and I'm going to do: predict-no
  5725. ENV: Agent did: predict-no for direction U in state State-B
  5726. In State-B moving U
  5727. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5728. predict error 0
  5729. dir: dir isR
  5730. -/|810: O: O1620 (predict-no)
  5731. I see 1 and I'm going to do: predict-no
  5732. ENV: Agent did: predict-no for direction R in state State-B
  5733. In State-B moving R
  5734. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5735. predict error 0
  5736. dir: dir isL
  5737. \-/811: O: O1621 (predict-yes)
  5738. I see 1 and I'm going to do: predict-yes
  5739. ENV: Agent did: predict-yes for direction L in state State-B
  5740. In State-B moving L
  5741. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  5742. predict error 0
  5743. dir: dir isU
  5744. |812: O: O1624 (predict-no)
  5745. I see 1 and I'm going to do: predict-no
  5746. ENV: Agent did: predict-no for direction U in state State-A
  5747. In State-A moving U
  5748. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  5749. predict error 0
  5750. dir: dir isL
  5751. \-813: O: O1626 (predict-no)
  5752. I see 1 and I'm going to do: predict-no
  5753. ENV: Agent did: predict-no for direction L in state State-A
  5754. In State-A moving L
  5755. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  5756. predict error 0
  5757. dir: dir isR
  5758. /|814: O: O1627 (predict-yes)
  5759. I see 1 and I'm going to do: predict-yes
  5760. ENV: Agent did: predict-yes for direction R in state State-A
  5761. In State-A moving R
  5762. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  5763. predict error 0
  5764. dir: dir isU
  5765. \-/815: O: O1630 (predict-no)
  5766. I see 1 and I'm going to do: predict-no
  5767. ENV: Agent did: predict-no for direction U in state State-B
  5768. In State-B moving U
  5769. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5770. predict error 0
  5771. dir: dir isL
  5772. |\-816: O: O1631 (predict-yes)
  5773. I see 1 and I'm going to do: predict-yes
  5774. ENV: Agent did: predict-yes for direction L in state State-B
  5775. In State-B moving L
  5776. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  5777. predict error 0
  5778. dir: dir isR
  5779. /|\817: O: O1633 (predict-yes)
  5780. I see 1 and I'm going to do: predict-yes
  5781. ENV: Agent did: predict-yes for direction R in state State-A
  5782. In State-A moving R
  5783. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  5784. predict error 0
  5785. dir: dir isL
  5786. -/|\818: O: O1635 (predict-yes)
  5787. I see 1 and I'm going to do: predict-yes
  5788. ENV: Agent did: predict-yes for direction L in state State-B
  5789. In State-B moving L
  5790. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  5791. predict error 0
  5792. dir: dir isL
  5793. -/|819: O: O1638 (predict-no)
  5794. I see 1 and I'm going to do: predict-no
  5795. ENV: Agent did: predict-no for direction L in state State-A
  5796. In State-A moving L
  5797. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  5798. predict error 0
  5799. dir: dir isU
  5800. \-/820: O: O1640 (predict-no)
  5801. I see 1 and I'm going to do: predict-no
  5802. ENV: Agent did: predict-no for direction U in state State-A
  5803. In State-A moving U
  5804. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  5805. predict error 0
  5806. dir: dir isR
  5807. |\-821: O: O1641 (predict-yes)
  5808. I see 1 and I'm going to do: predict-yes
  5809. ENV: Agent did: predict-yes for direction R in state State-A
  5810. In State-A moving R
  5811. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  5812. predict error 0
  5813. dir: dir isL
  5814. /822: O: O1643 (predict-yes)
  5815. I see 1 and I'm going to do: predict-yes
  5816. ENV: Agent did: predict-yes for direction L in state State-B
  5817. In State-B moving L
  5818. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  5819. predict error 0
  5820. dir: dir isR
  5821. |\-823: O: O1645 (predict-yes)
  5822. I see 1 and I'm going to do: predict-yes
  5823. ENV: Agent did: predict-yes for direction R in state State-A
  5824. In State-A moving R
  5825. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  5826. predict error 0
  5827. dir: dir isL
  5828. /|\-824: O: O1647 (predict-yes)
  5829. I see 1 and I'm going to do: predict-yes
  5830. ENV: Agent did: predict-yes for direction L in state State-B
  5831. In State-B moving L
  5832. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  5833. predict error 0
  5834. dir: dir isL
  5835. /|\825: O: O1650 (predict-no)
  5836. I see 1 and I'm going to do: predict-no
  5837. ENV: Agent did: predict-no for direction L in state State-A
  5838. In State-A moving L
  5839. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  5840. predict error 0
  5841. dir: dir isR
  5842. -/|826: O: O1651 (predict-yes)
  5843. I see 1 and I'm going to do: predict-yes
  5844. ENV: Agent did: predict-yes for direction R in state State-A
  5845. In State-A moving R
  5846. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  5847. predict error 0
  5848. dir: dir isU
  5849. \-827: O: O1654 (predict-no)
  5850. I see 1 and I'm going to do: predict-no
  5851. ENV: Agent did: predict-no for direction U in state State-B
  5852. In State-B moving U
  5853. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5854. predict error 0
  5855. dir: dir isR
  5856. /|\828: O: O1656 (predict-no)
  5857. I see 1 and I'm going to do: predict-no
  5858. ENV: Agent did: predict-no for direction R in state State-B
  5859. In State-B moving R
  5860. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5861. predict error 0
  5862. dir: dir isL
  5863. -/829: O: O1657 (predict-yes)
  5864. I see 1 and I'm going to do: predict-yes
  5865. ENV: Agent did: predict-yes for direction L in state State-B
  5866. In State-B moving L
  5867. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  5868. predict error 0
  5869. dir: dir isU
  5870. |\-830: O: O1660 (predict-no)
  5871. I see 1 and I'm going to do: predict-no
  5872. ENV: Agent did: predict-no for direction U in state State-A
  5873. In State-A moving U
  5874. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  5875. predict error 0
  5876. dir: dir isU
  5877. /|\831: O: O1662 (predict-no)
  5878. I see 1 and I'm going to do: predict-no
  5879. ENV: Agent did: predict-no for direction U in state State-A
  5880. In State-A moving U
  5881. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  5882. predict error 0
  5883. dir: dir isU
  5884. -832: O: O1664 (predict-no)
  5885. I see 1 and I'm going to do: predict-no
  5886. ENV: Agent did: predict-no for direction U in state State-A
  5887. In State-A moving U
  5888. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  5889. predict error 0
  5890. dir: dir isR
  5891. /|\833: O: O1665 (predict-yes)
  5892. I see 1 and I'm going to do: predict-yes
  5893. ENV: Agent did: predict-yes for direction R in state State-A
  5894. In State-A moving R
  5895. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  5896. predict error 0
  5897. dir: dir isU
  5898. -/|834: O: O1668 (predict-no)
  5899. I see 1 and I'm going to do: predict-no
  5900. ENV: Agent did: predict-no for direction U in state State-B
  5901. In State-B moving U
  5902. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5903. predict error 0
  5904. dir: dir isL
  5905. \-/835: O: O1669 (predict-yes)
  5906. I see 1 and I'm going to do: predict-yes
  5907. ENV: Agent did: predict-yes for direction L in state State-B
  5908. In State-B moving L
  5909. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  5910. predict error 0
  5911. dir: dir isU
  5912. |\-836: O: O1672 (predict-no)
  5913. I see 1 and I'm going to do: predict-no
  5914. ENV: Agent did: predict-no for direction U in state State-A
  5915. In State-A moving U
  5916. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  5917. predict error 0
  5918. dir: dir isU
  5919. /|\837: O: O1674 (predict-no)
  5920. I see 1 and I'm going to do: predict-no
  5921. ENV: Agent did: predict-no for direction U in state State-A
  5922. In State-A moving U
  5923. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  5924. predict error 0
  5925. dir: dir isU
  5926. -/838: O: O1676 (predict-no)
  5927. I see 1 and I'm going to do: predict-no
  5928. ENV: Agent did: predict-no for direction U in state State-A
  5929. In State-A moving U
  5930. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  5931. predict error 0
  5932. dir: dir isR
  5933. |\-839: O: O1677 (predict-yes)
  5934. I see 1 and I'm going to do: predict-yes
  5935. ENV: Agent did: predict-yes for direction R in state State-A
  5936. In State-A moving R
  5937. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  5938. predict error 0
  5939. dir: dir isR
  5940. /|\840: O: O1680 (predict-no)
  5941. I see 1 and I'm going to do: predict-no
  5942. ENV: Agent did: predict-no for direction R in state State-B
  5943. In State-B moving R
  5944. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5945. predict error 0
  5946. dir: dir isR
  5947. -/|841: O: O1682 (predict-no)
  5948. I see 1 and I'm going to do: predict-no
  5949. ENV: Agent did: predict-no for direction R in state State-B
  5950. In State-B moving R
  5951. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5952. predict error 0
  5953. dir: dir isU
  5954. \842: O: O1684 (predict-no)
  5955. I see 1 and I'm going to do: predict-no
  5956. ENV: Agent did: predict-no for direction U in state State-B
  5957. In State-B moving U
  5958. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5959. predict error 0
  5960. dir: dir isL
  5961. -/|843: O: O1685 (predict-yes)
  5962. I see 1 and I'm going to do: predict-yes
  5963. ENV: Agent did: predict-yes for direction L in state State-B
  5964. In State-B moving L
  5965. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  5966. predict error 0
  5967. dir: dir isU
  5968. \-/844: O: O1688 (predict-no)
  5969. I see 1 and I'm going to do: predict-no
  5970. ENV: Agent did: predict-no for direction U in state State-A
  5971. In State-A moving U
  5972. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  5973. predict error 0
  5974. dir: dir isR
  5975. |\-845: O: O1689 (predict-yes)
  5976. I see 1 and I'm going to do: predict-yes
  5977. ENV: Agent did: predict-yes for direction R in state State-A
  5978. In State-A moving R
  5979. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  5980. predict error 0
  5981. dir: dir isR
  5982. /846: O: O1692 (predict-no)
  5983. I see 1 and I'm going to do: predict-no
  5984. ENV: Agent did: predict-no for direction R in state State-B
  5985. In State-B moving R
  5986. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5987. predict error 0
  5988. dir: dir isR
  5989. |\-847: O: O1694 (predict-no)
  5990. I see 1 and I'm going to do: predict-no
  5991. ENV: Agent did: predict-no for direction R in state State-B
  5992. In State-B moving R
  5993. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5994. predict error 0
  5995. dir: dir isL
  5996. /|\848: O: O1695 (predict-yes)
  5997. I see 1 and I'm going to do: predict-yes
  5998. ENV: Agent did: predict-yes for direction L in state State-B
  5999. In State-B moving L
  6000. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  6001. predict error 0
  6002. dir: dir isL
  6003. -/|849: O: O1698 (predict-no)
  6004. I see 1 and I'm going to do: predict-no
  6005. ENV: Agent did: predict-no for direction L in state State-A
  6006. In State-A moving L
  6007. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  6008. predict error 0
  6009. dir: dir isR
  6010. \-/850: O: O1699 (predict-yes)
  6011. I see 1 and I'm going to do: predict-yes
  6012. ENV: Agent did: predict-yes for direction R in state State-A
  6013. In State-A moving R
  6014. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  6015. predict error 0
  6016. dir: dir isR
  6017. |\-851: O: O1702 (predict-no)
  6018. I see 1 and I'm going to do: predict-no
  6019. ENV: Agent did: predict-no for direction R in state State-B
  6020. In State-B moving R
  6021. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  6022. predict error 0
  6023. dir: dir isR
  6024. /852: O: O1704 (predict-no)
  6025. I see 1 and I'm going to do: predict-no
  6026. ENV: Agent did: predict-no for direction R in state State-B
  6027. In State-B moving R
  6028. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  6029. predict error 0
  6030. dir: dir isU
  6031. |\853: O: O1706 (predict-no)
  6032. I see 1 and I'm going to do: predict-no
  6033. ENV: Agent did: predict-no for direction U in state State-B
  6034. In State-B moving U
  6035. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  6036. predict error 0
  6037. dir: dir isR
  6038. -/854: O: O1708 (predict-no)
  6039. I see 1 and I'm going to do: predict-no
  6040. ENV: Agent did: predict-no for direction R in state State-B
  6041. In State-B moving R
  6042. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  6043. predict error 0
  6044. dir: dir isL
  6045. |\-855: O: O1709 (predict-yes)
  6046. I see 1 and I'm going to do: predict-yes
  6047. ENV: Agent did: predict-yes for direction L in state State-B
  6048. In State-B moving L
  6049. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  6050. predict error 0
  6051. dir: dir isU
  6052. /|\856: O: O1712 (predict-no)
  6053. I see 1 and I'm going to do: predict-no
  6054. ENV: Agent did: predict-no for direction U in state State-A
  6055. In State-A moving U
  6056. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  6057. predict error 0
  6058. dir: dir isL
  6059. -857: O: O1714 (predict-no)
  6060. I see 1 and I'm going to do: predict-no
  6061. ENV: Agent did: predict-no for direction L in state State-A
  6062. In State-A moving L
  6063. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  6064. predict error 0
  6065. dir: dir isR
  6066. /|\858: O: O1715 (predict-yes)
  6067. I see 1 and I'm going to do: predict-yes
  6068. ENV: Agent did: predict-yes for direction R in state State-A
  6069. In State-A moving R
  6070. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  6071. predict error 0
  6072. dir: dir isU
  6073. -/859: O: O1718 (predict-no)
  6074. I see 1 and I'm going to do: predict-no
  6075. ENV: Agent did: predict-no for direction U in state State-B
  6076. In State-B moving U
  6077. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  6078. predict error 0
  6079. dir: dir isU
  6080. |\-860: O: O1720 (predict-no)
  6081. I see 1 and I'm going to do: predict-no
  6082. ENV: Agent did: predict-no for direction U in state State-B
  6083. In State-B moving U
  6084. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  6085. predict error 0
  6086. dir: dir isU
  6087. /|\861: O: O1722 (predict-no)
  6088. I see 1 and I'm going to do: predict-no
  6089. ENV: Agent did: predict-no for direction U in state State-B
  6090. In State-B moving U
  6091. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  6092. predict error 0
  6093. dir: dir isR
  6094. -862: O: O1724 (predict-no)
  6095. I see 1 and I'm going to do: predict-no
  6096. ENV: Agent did: predict-no for direction R in state State-B
  6097. In State-B moving R
  6098. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  6099. predict error 0
  6100. dir: dir isL
  6101. /|863: O: O1725 (predict-yes)
  6102. I see 1 and I'm going to do: predict-yes
  6103. ENV: Agent did: predict-yes for direction L in state State-B
  6104. In State-B moving L
  6105. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  6106. predict error 0
  6107. dir: dir isL
  6108. \864: O: O1728 (predict-no)
  6109. I see 1 and I'm going to do: predict-no
  6110. ENV: Agent did: predict-no for direction L in state State-A
  6111. In State-A moving L
  6112. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  6113. predict error 0
  6114. dir: dir isU
  6115. -/|865: O: O1730 (predict-no)
  6116. I see 1 and I'm going to do: predict-no
  6117. ENV: Agent did: predict-no for direction U in state State-A
  6118. In State-A moving U
  6119. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  6120. predict error 0
  6121. dir: dir isU
  6122. \-/866: O: O1732 (predict-no)
  6123. I see 1 and I'm going to do: predict-no
  6124. ENV: Agent did: predict-no for direction U in state State-A
  6125. In State-A moving U
  6126. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  6127. predict error 0
  6128. dir: dir isR
  6129. |\-867: O: O1733 (predict-yes)
  6130. I see 1 and I'm going to do: predict-yes
  6131. ENV: Agent did: predict-yes for direction R in state State-A
  6132. In State-A moving R
  6133. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  6134. predict error 0
  6135. dir: dir isR
  6136. /|\868: O: O1736 (predict-no)
  6137. I see 1 and I'm going to do: predict-no
  6138. ENV: Agent did: predict-no for direction R in state State-B
  6139. In State-B moving R
  6140. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  6141. predict error 0
  6142. dir: dir isU
  6143. -/|869: O: O1738 (predict-no)
  6144. I see 1 and I'm going to do: predict-no
  6145. ENV: Agent did: predict-no for direction U in state State-B
  6146. In State-B moving U
  6147. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  6148. predict error 0
  6149. dir: dir isR
  6150. \-/870: O: O1740 (predict-no)
  6151. I see 1 and I'm going to do: predict-no
  6152. ENV: Agent did: predict-no for direction R in state State-B
  6153. In State-B moving R
  6154. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  6155. predict error 0
  6156. dir: dir isL
  6157. |\-871: O: O1741 (predict-yes)
  6158. I see 1 and I'm going to do: predict-yes
  6159. ENV: Agent did: predict-yes for direction L in state State-B
  6160. In State-B moving L
  6161. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  6162. predict error 0
  6163. dir: dir isU
  6164. /872: O: O1744 (predict-no)
  6165. I see 1 and I'm going to do: predict-no
  6166. ENV: Agent did: predict-no for direction U in state State-A
  6167. In State-A moving U
  6168. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  6169. predict error 0
  6170. dir: dir isL
  6171. |\-873: O: O1746 (predict-no)
  6172. I see 1 and I'm going to do: predict-no
  6173. ENV: Agent did: predict-no for direction L in state State-A
  6174. In State-A moving L
  6175. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  6176. predict error 0
  6177. dir: dir isR
  6178. /|\-874: O: O1747 (predict-yes)
  6179. I see 1 and I'm going to do: predict-yes
  6180. ENV: Agent did: predict-yes for direction R in state State-A
  6181. In State-A moving R
  6182. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  6183. predict error 0
  6184. dir: dir isR
  6185. /|\-875: O: O1750 (predict-no)
  6186. I see 1 and I'm going to do: predict-no
  6187. ENV: Agent did: predict-no for direction R in state State-B
  6188. In State-B moving R
  6189. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  6190. predict error 0
  6191. dir: dir isU
  6192. /|876: O: O1752 (predict-no)
  6193. I see 1 and I'm going to do: predict-no
  6194. ENV: Agent did: predict-no for direction U in state State-B
  6195. In State-B moving U
  6196. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  6197. predict error 0
  6198. dir: dir isL
  6199. \-/877: O: O1753 (predict-yes)
  6200. I see 1 and I'm going to do: predict-yes
  6201. ENV: Agent did: predict-yes for direction L in state State-B
  6202. In State-B moving L
  6203. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  6204. predict error 0
  6205. dir: dir isL
  6206. |\878: O: O1756 (predict-no)
  6207. I see 1 and I'm going to do: predict-no
  6208. ENV: Agent did: predict-no for direction L in state State-A
  6209. In State-A moving L
  6210. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  6211. predict error 0
  6212. dir: dir isR
  6213. -/|879: O: O1757 (predict-yes)
  6214. I see 1 and I'm going to do: predict-yes
  6215. ENV: Agent did: predict-yes for direction R in state State-A
  6216. In State-A moving R
  6217. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  6218. predict error 0
  6219. dir: dir isL
  6220. \-/|880: O: O1759 (predict-yes)
  6221. I see 1 and I'm going to do: predict-yes
  6222. ENV: Agent did: predict-yes for direction L in state State-B
  6223. In State-B moving L
  6224. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  6225. predict error 0
  6226. dir: dir isL
  6227. \-/881: O: O1762 (predict-no)
  6228. I see 1 and I'm going to do: predict-no
  6229. ENV: Agent did: predict-no for direction L in state State-A
  6230. In State-A moving L
  6231. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  6232. predict error 0
  6233. dir: dir isL
  6234. |882: O: O1764 (predict-no)
  6235. I see 1 and I'm going to do: predict-no
  6236. ENV: Agent did: predict-no for direction L in state State-A
  6237. In State-A moving L
  6238. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  6239. predict error 0
  6240. dir: dir isR
  6241. \-/883: O: O1765 (predict-yes)
  6242. I see 1 and I'm going to do: predict-yes
  6243. ENV: Agent did: predict-yes for direction R in state State-A
  6244. In State-A moving R
  6245. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  6246. predict error 0
  6247. dir: dir isL
  6248. |\884: O: O1767 (predict-yes)
  6249. I see 1 and I'm going to do: predict-yes
  6250. ENV: Agent did: predict-yes for direction L in state State-B
  6251. In State-B moving L
  6252. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  6253. predict error 0
  6254. dir: dir isL
  6255. -/|885: O: O1770 (predict-no)
  6256. I see 1 and I'm going to do: predict-no
  6257. ENV: Agent did: predict-no for direction L in state State-A
  6258. In State-A moving L
  6259. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  6260. predict error 0
  6261. dir: dir isU
  6262. \-/886: O: O1772 (predict-no)
  6263. I see 1 and I'm going to do: predict-no
  6264. ENV: Agent did: predict-no for direction U in state State-A
  6265. In State-A moving U
  6266. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  6267. predict error 0
  6268. dir: dir isR
  6269. |\-887: O: O1773 (predict-yes)
  6270. I see 1 and I'm going to do: predict-yes
  6271. ENV: Agent did: predict-yes for direction R in state State-A
  6272. In State-A moving R
  6273. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  6274. predict error 0
  6275. dir: dir isU
  6276. /|\888: O: O1776 (predict-no)
  6277. I see 1 and I'm going to do: predict-no
  6278. ENV: Agent did: predict-no for direction U in state State-B
  6279. In State-B moving U
  6280. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  6281. predict error 0
  6282. dir: dir isL
  6283. -/889: O: O1777 (predict-yes)
  6284. I see 1 and I'm going to do: predict-yes
  6285. ENV: Agent did: predict-yes for direction L in state State-B
  6286. In State-B moving L
  6287. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  6288. predict error 0
  6289. dir: dir isR
  6290. |\-890: O: O1779 (predict-yes)
  6291. I see 1 and I'm going to do: predict-yes
  6292. ENV: Agent did: predict-yes for direction R in state State-A
  6293. In State-A moving R
  6294. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  6295. predict error 0
  6296. dir: dir isR
  6297. /|\891: O: O1782 (predict-no)
  6298. I see 1 and I'm going to do: predict-no
  6299. ENV: Agent did: predict-no for direction R in state State-B
  6300. In State-B moving R
  6301. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  6302. predict error 0
  6303. dir: dir isL
  6304. -892: O: O1783 (predict-yes)
  6305. I see 1 and I'm going to do: predict-yes
  6306. ENV: Agent did: predict-yes for direction L in state State-B
  6307. In State-B moving L
  6308. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  6309. predict error 0
  6310. dir: dir isL
  6311. /|893: O: O1786 (predict-no)
  6312. I see 1 and I'm going to do: predict-no
  6313. ENV: Agent did: predict-no for direction L in state State-A
  6314. In State-A moving L
  6315. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  6316. predict error 0
  6317. dir: dir isU
  6318. \-/894: O: O1788 (predict-no)
  6319. I see 1 and I'm going to do: predict-no
  6320. ENV: Agent did: predict-no for direction U in state State-A
  6321. In State-A moving U
  6322. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  6323. predict error 0
  6324. dir: dir isU
  6325. |\895: O: O1790 (predict-no)
  6326. I see 1 and I'm going to do: predict-no
  6327. ENV: Agent did: predict-no for direction U in state State-A
  6328. In State-A moving U
  6329. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  6330. predict error 0
  6331. dir: dir isR
  6332. -/|896: O: O1791 (predict-yes)
  6333. I see 1 and I'm going to do: predict-yes
  6334. ENV: Agent did: predict-yes for direction R in state State-A
  6335. In State-A moving R
  6336. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  6337. predict error 0
  6338. dir: dir isR
  6339. \-/|897: O: O1794 (predict-no)
  6340. I see 1 and I'm going to do: predict-no
  6341. ENV: Agent did: predict-no for direction R in state State-B
  6342. In State-B moving R
  6343. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  6344. predict error 0
  6345. dir: dir isL
  6346. \-/898: O: O1795 (predict-yes)
  6347. I see 1 and I'm going to do: predict-yes
  6348. ENV: Agent did: predict-yes for direction L in state State-B
  6349. In State-B moving L
  6350. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  6351. predict error 0
  6352. dir: dir isR
  6353. |\-899: O: O1797 (predict-yes)
  6354. I see 1 and I'm going to do: predict-yes
  6355. ENV: Agent did: predict-yes for direction R in state State-A
  6356. In State-A moving R
  6357. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  6358. predict error 0
  6359. dir: dir isU
  6360. /|\900: O: O1800 (predict-no)
  6361. I see 1 and I'm going to do: predict-no
  6362. ENV: Agent did: predict-no for direction U in state State-B
  6363. In State-B moving U
  6364. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  6365. predict error 0
  6366. dir: dir isU
  6367. -/|901: O: O1802 (predict-no)
  6368. I see 1 and I'm going to do: predict-no
  6369. ENV: Agent did: predict-no for direction U in state State-B
  6370. In State-B moving U
  6371. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  6372. predict error 0
  6373. dir: dir isR
  6374. \902: O: O1804 (predict-no)
  6375. I see 1 and I'm going to do: predict-no
  6376. ENV: Agent did: predict-no for direction R in state State-B
  6377. In State-B moving R
  6378. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  6379. predict error 0
  6380. dir: dir isL
  6381. -/|903: O: O1805 (predict-yes)
  6382. I see 1 and I'm going to do: predict-yes
  6383. ENV: Agent did: predict-yes for direction L in state State-B
  6384. In State-B moving L
  6385. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  6386. predict error 0
  6387. dir: dir isU
  6388. \-/904: O: O1808 (predict-no)
  6389. I see 1 and I'm going to do: predict-no
  6390. ENV: Agent did: predict-no for direction U in state State-A
  6391. In State-A moving U
  6392. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  6393. predict error 0
  6394. dir: dir isR
  6395. |\-905: O: O1809 (predict-yes)
  6396. I see 1 and I'm going to do: predict-yes
  6397. ENV: Agent did: predict-yes for direction R in state State-A
  6398. In State-A moving R
  6399. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  6400. predict error 0
  6401. dir: dir isR
  6402. /|\906: O: O1812 (predict-no)
  6403. I see 1 and I'm going to do: predict-no
  6404. ENV: Agent did: predict-no for direction R in state State-B
  6405. In State-B moving R
  6406. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  6407. predict error 0
  6408. dir: dir isL
  6409. -/|907: O: O1813 (predict-yes)
  6410. I see 1 and I'm going to do: predict-yes
  6411. ENV: Agent did: predict-yes for direction L in state State-B
  6412. In State-B moving L
  6413. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  6414. predict error 0
  6415. dir: dir isL
  6416. \-/908: O: O1816 (predict-no)
  6417. I see 1 and I'm going to do: predict-no
  6418. ENV: Agent did: predict-no for direction L in state State-A
  6419. In State-A moving L
  6420. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  6421. predict error 0
  6422. dir: dir isU
  6423. |\-909: O: O1818 (predict-no)
  6424. I see 1 and I'm going to do: predict-no
  6425. ENV: Agent did: predict-no for direction U in state State-A
  6426. In State-A moving U
  6427. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  6428. predict error 0
  6429. dir: dir isR
  6430. /|\910: O: O1819 (predict-yes)
  6431. I see 1 and I'm going to do: predict-yes
  6432. ENV: Agent did: predict-yes for direction R in state State-A
  6433. In State-A moving R
  6434. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  6435. predict error 0
  6436. dir: dir isU
  6437. -911: O: O1822 (predict-no)
  6438. I see 1 and I'm going to do: predict-no
  6439. ENV: Agent did: predict-no for direction U in state State-B
  6440. In State-B moving U
  6441. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  6442. predict error 0
  6443. dir: dir isL
  6444. /912: O: O1823 (predict-yes)
  6445. I see 1 and I'm going to do: predict-yes
  6446. ENV: Agent did: predict-yes for direction L in state State-B
  6447. In State-B moving L
  6448. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  6449. predict error 0
  6450. dir: dir isL
  6451. |\-913: O: O1826 (predict-no)
  6452. I see 1 and I'm going to do: predict-no
  6453. ENV: Agent did: predict-no for direction L in state State-A
  6454. In State-A moving L
  6455. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  6456. predict error 0
  6457. dir: dir isU
  6458. /|914: O: O1828 (predict-no)
  6459. I see 1 and I'm going to do: predict-no
  6460. ENV: Agent did: predict-no for direction U in state State-A
  6461. In State-A moving U
  6462. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  6463. predict error 0
  6464. dir: dir isU
  6465. \-915: O: O1830 (predict-no)
  6466. I see 1 and I'm going to do: predict-no
  6467. ENV: Agent did: predict-no for direction U in state State-A
  6468. In State-A moving U
  6469. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  6470. predict error 0
  6471. dir: dir isL
  6472. /|916: O: O1832 (predict-no)
  6473. I see 1 and I'm going to do: predict-no
  6474. ENV: Agent did: predict-no for direction L in state State-A
  6475. In State-A moving L
  6476. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  6477. predict error 0
  6478. dir: dir isL
  6479. \-/917: O: O1834 (predict-no)
  6480. I see 1 and I'm going to do: predict-no
  6481. ENV: Agent did: predict-no for direction L in state State-A
  6482. In State-A moving L
  6483. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  6484. predict error 0
  6485. dir: dir isU
  6486. |\-918: O: O1836 (predict-no)
  6487. I see 1 and I'm going to do: predict-no
  6488. ENV: Agent did: predict-no for direction U in state State-A
  6489. In State-A moving U
  6490. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  6491. predict error 0
  6492. dir: dir isL
  6493. /|\919: O: O1838 (predict-no)
  6494. I see 1 and I'm going to do: predict-no
  6495. ENV: Agent did: predict-no for direction L in state State-A
  6496. In State-A moving L
  6497. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  6498. predict error 0
  6499. dir: dir isU
  6500. -/|920: O: O1840 (predict-no)
  6501. I see 1 and I'm going to do: predict-no
  6502. ENV: Agent did: predict-no for direction U in state State-A
  6503. In State-A moving U
  6504. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  6505. predict error 0
  6506. dir: dir isU
  6507. \-/921: O: O1842 (predict-no)
  6508. I see 1 and I'm going to do: predict-no
  6509. ENV: Agent did: predict-no for direction U in state State-A
  6510. In State-A moving U
  6511. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  6512. predict error 0
  6513. dir: dir isL
  6514. |922: O: O1844 (predict-no)
  6515. I see 1 and I'm going to do: predict-no
  6516. ENV: Agent did: predict-no for direction L in state State-A
  6517. In State-A moving L
  6518. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  6519. predict error 0
  6520. dir: dir isL
  6521. \-/923: O: O1846 (predict-no)
  6522. I see 1 and I'm going to do: predict-no
  6523. ENV: Agent did: predict-no for direction L in state State-A
  6524. In State-A moving L
  6525. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  6526. predict error 0
  6527. dir: dir isU
  6528. |\-924: O: O1848 (predict-no)
  6529. I see 1 and I'm going to do: predict-no
  6530. ENV: Agent did: predict-no for direction U in state State-A
  6531. In State-A moving U
  6532. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  6533. predict error 0
  6534. dir: dir isR
  6535. /|\-925: O: O1849 (predict-yes)
  6536. I see 1 and I'm going to do: predict-yes
  6537. ENV: Agent did: predict-yes for direction R in state State-A
  6538. In State-A moving R
  6539. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  6540. predict error 0
  6541. dir: dir isR
  6542. /|\926: O: O1852 (predict-no)
  6543. I see 1 and I'm going to do: predict-no
  6544. ENV: Agent did: predict-no for direction R in state State-B
  6545. In State-B moving R
  6546. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  6547. predict error 0
  6548. dir: dir isR
  6549. -927: O: O1854 (predict-no)
  6550. I see 1 and I'm going to do: predict-no
  6551. ENV: Agent did: predict-no for direction R in state State-B
  6552. In State-B moving R
  6553. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  6554. predict error 0
  6555. dir: dir isL
  6556. /|928: O: O1855 (predict-yes)
  6557. I see 1 and I'm going to do: predict-yes
  6558. ENV: Agent did: predict-yes for direction L in state State-B
  6559. In State-B moving L
  6560. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  6561. predict error 0
  6562. dir: dir isR
  6563. \-/|929: O: O1857 (predict-yes)
  6564. I see 1 and I'm going to do: predict-yes
  6565. ENV: Agent did: predict-yes for direction R in state State-A
  6566. In State-A moving R
  6567. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  6568. predict error 0
  6569. dir: dir isL
  6570. \-/930: O: O1859 (predict-yes)
  6571. I see 1 and I'm going to do: predict-yes
  6572. ENV: Agent did: predict-yes for direction L in state State-B
  6573. In State-B moving L
  6574. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  6575. predict error 0
  6576. dir: dir isU
  6577. |\-931: O: O1862 (predict-no)
  6578. I see 1 and I'm going to do: predict-no
  6579. ENV: Agent did: predict-no for direction U in state State-A
  6580. In State-A moving U
  6581. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  6582. predict error 0
  6583. dir: dir isU
  6584. /932: O: O1864 (predict-no)
  6585. I see 1 and I'm going to do: predict-no
  6586. ENV: Agent did: predict-no for direction U in state State-A
  6587. In State-A moving U
  6588. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  6589. predict error 0
  6590. dir: dir isL
  6591. |\933: O: O1866 (predict-no)
  6592. I see 1 and I'm going to do: predict-no
  6593. ENV: Agent did: predict-no for direction L in state State-A
  6594. In State-A moving L
  6595. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  6596. predict error 0
  6597. dir: dir isU
  6598. -/|934: O: O1868 (predict-no)
  6599. I see 1 and I'm going to do: predict-no
  6600. ENV: Agent did: predict-no for direction U in state State-A
  6601. In State-A moving U
  6602. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  6603. predict error 0
  6604. dir: dir isL
  6605. \-/935: O: O1870 (predict-no)
  6606. I see 1 and I'm going to do: predict-no
  6607. ENV: Agent did: predict-no for direction L in state State-A
  6608. In State-A moving L
  6609. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  6610. predict error 0
  6611. dir: dir isL
  6612. |\936: O: O1872 (predict-no)
  6613. I see 1 and I'm going to do: predict-no
  6614. ENV: Agent did: predict-no for direction L in state State-A
  6615. In State-A moving L
  6616. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  6617. predict error 0
  6618. dir: dir isL
  6619. -/|\937: O: O1874 (predict-no)
  6620. I see 1 and I'm going to do: predict-no
  6621. ENV: Agent did: predict-no for direction L in state State-A
  6622. In State-A moving L
  6623. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  6624. predict error 0
  6625. dir: dir isL
  6626. -/938: O: O1876 (predict-no)
  6627. I see 1 and I'm going to do: predict-no
  6628. ENV: Agent did: predict-no for direction L in state State-A
  6629. In State-A moving L
  6630. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  6631. predict error 0
  6632. dir: dir isL
  6633. |\-/939: O: O1878 (predict-no)
  6634. I see 1 and I'm going to do: predict-no
  6635. ENV: Agent did: predict-no for direction L in state State-A
  6636. In State-A moving L
  6637. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  6638. predict error 0
  6639. dir: dir isR
  6640. |\-940: O: O1879 (predict-yes)
  6641. I see 1 and I'm going to do: predict-yes
  6642. ENV: Agent did: predict-yes for direction R in state State-A
  6643. In State-A moving R
  6644. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  6645. predict error 0
  6646. dir: dir isU
  6647. /|\941: O: O1882 (predict-no)
  6648. I see 1 and I'm going to do: predict-no
  6649. ENV: Agent did: predict-no for direction U in state State-B
  6650. In State-B moving U
  6651. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  6652. predict error 0
  6653. dir: dir isR
  6654. -942: O: O1884 (predict-no)
  6655. I see 1 and I'm going to do: predict-no
  6656. ENV: Agent did: predict-no for direction R in state State-B
  6657. In State-B moving R
  6658. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  6659. predict error 0
  6660. dir: dir isL
  6661. /|\943: O: O1885 (predict-yes)
  6662. I see 1 and I'm going to do: predict-yes
  6663. ENV: Agent did: predict-yes for direction L in state State-B
  6664. In State-B moving L
  6665. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  6666. predict error 0
  6667. dir: dir isR
  6668. -944: O: O1887 (predict-yes)
  6669. I see 1 and I'm going to do: predict-yes
  6670. ENV: Agent did: predict-yes for direction R in state State-A
  6671. In State-A moving R
  6672. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  6673. predict error 0
  6674. dir: dir isR
  6675. /|\945: O: O1890 (predict-no)
  6676. I see 1 and I'm going to do: predict-no
  6677. ENV: Agent did: predict-no for direction R in state State-B
  6678. In State-B moving R
  6679. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  6680. predict error 0
  6681. dir: dir isL
  6682. -/|946: O: O1891 (predict-yes)
  6683. I see 1 and I'm going to do: predict-yes
  6684. ENV: Agent did: predict-yes for direction L in state State-B
  6685. In State-B moving L
  6686. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  6687. predict error 0
  6688. dir: dir isU
  6689. \-/947: O: O1894 (predict-no)
  6690. I see 1 and I'm going to do: predict-no
  6691. ENV: Agent did: predict-no for direction U in state State-A
  6692. In State-A moving U
  6693. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  6694. predict error 0
  6695. dir: dir isR
  6696. |\-948: O: O1895 (predict-yes)
  6697. I see 1 and I'm going to do: predict-yes
  6698. ENV: Agent did: predict-yes for direction R in state State-A
  6699. In State-A moving R
  6700. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  6701. predict error 0
  6702. dir: dir isU
  6703. /|\949: O: O1898 (predict-no)
  6704. I see 1 and I'm going to do: predict-no
  6705. ENV: Agent did: predict-no for direction U in state State-B
  6706. In State-B moving U
  6707. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  6708. predict error 0
  6709. dir: dir isU
  6710. -/|950: O: O1900 (predict-no)
  6711. I see 1 and I'm going to do: predict-no
  6712. ENV: Agent did: predict-no for direction U in state State-B
  6713. In State-B moving U
  6714. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  6715. predict error 0
  6716. dir: dir isR
  6717. \-/|\-/|\-/--- Input Phase ---
  6718. =>WM: (13382: I2 ^dir R)
  6719. =>WM: (13381: I2 ^reward 1)
  6720. =>WM: (13380: I2 ^see 0)
  6721. =>WM: (13379: N950 ^status complete)
  6722. <=WM: (13368: I2 ^dir U)
  6723. <=WM: (13367: I2 ^reward 1)
  6724. <=WM: (13366: I2 ^see 0)
  6725. =>WM: (13383: I2 ^level-1 R1-root)
  6726. <=WM: (13369: I2 ^level-1 R1-root)
  6727. --- END Input Phase ---
  6728. --- Proposal Phase ---
  6729. --- Inner Elaboration Phase, active level 1 (S1) ---
  6730. Firing rl*prefer*rvt*predict-yes*H0*3*v1*H1*36
  6731. -->
  6732. (S1 ^operator O1899 = -0.1070236389116304)
  6733. Firing rl*prefer*rvt*predict-no*H0*4*v1*H1*35
  6734. -->
  6735. (S1 ^operator O1900 = 0.66025212945601)
  6736. Firing prefer*rvt*predict-no*H0*4*v1*H1
  6737. -->
  6738. Firing prefer*rvt*predict-yes*H0*3*v1*H1
  6739. -->
  6740. Firing elaborate*copy-see-to-output-link
  6741. -->
  6742. (I3 ^see 0 +)
  6743. Firing elaborate*reward*based*on*reward
  6744. -->
  6745. (R954 ^value 1 +)
  6746. (R1 ^reward R954 +)
  6747. Firing propose*predict-yes
  6748. -->
  6749. (O1901 ^name predict-yes +)
  6750. (S1 ^operator O1901 +)
  6751. Firing propose*predict-no
  6752. -->
  6753. (O1902 ^name predict-no +)
  6754. (S1 ^operator O1902 +)
  6755. Firing rl*prefer*rvt*predict-no*H0*4
  6756. -->
  6757. (S1 ^operator O1900 = 0.3397665963572414)
  6758. Firing rl*prefer*rvt*predict-yes*H0*3
  6759. -->
  6760. (S1 ^operator O1899 = 0.3377110766337923)
  6761. Firing prefer*rvt*predict-yes*H0
  6762. -->
  6763. Firing prefer*rvt*predict-no*H0
  6764. -->
  6765. Firing elaborate*copy-dir-to-output-link
  6766. -->
  6767. (I3 ^dir R +)
  6768. inner elaboration loop at bottom goal.
  6769. Retracting elaborate*copy-see-to-output-link
  6770. -->
  6771. (I3 ^see 0 +)
  6772. Retracting propose*predict-no
  6773. -->
  6774. (O1900 ^name predict-no +)
  6775. (S1 ^operator O1900 +)
  6776. Retracting propose*predict-yes
  6777. -->
  6778. (O1899 ^name predict-yes +)
  6779. (S1 ^operator O1899 +)
  6780. Retracting elaborate*reward*based*on*reward
  6781. -->
  6782. (R953 ^value 1 +)
  6783. (R1 ^reward R953 +)
  6784. Retracting elaborate*copy-dir-to-output-link
  6785. -->
  6786. (I3 ^dir U +)
  6787. Retracting rl*prefer*rvt*predict-no*H0*2
  6788. -->
  6789. (S1 ^operator O1900 = 1.)
  6790. Retracting rl*prefer*rvt*predict-yes*H0*1
  6791. -->
  6792. (S1 ^operator O1899 = 0.)
  6793. =>WM: (13390: S1 ^operator O1902 +)
  6794. =>WM: (13389: S1 ^operator O1901 +)
  6795. =>WM: (13388: I3 ^dir R)
  6796. =>WM: (13387: O1902 ^name predict-no)
  6797. =>WM: (13386: O1901 ^name predict-yes)
  6798. =>WM: (13385: R954 ^value 1)
  6799. =>WM: (13384: R1 ^reward R954)
  6800. <=WM: (13375: S1 ^operator O1899 +)
  6801. <=WM: (13376: S1 ^operator O1900 +)
  6802. <=WM: (13377: S1 ^operator O1900)
  6803. <=WM: (13360: I3 ^dir U)
  6804. <=WM: (13371: R1 ^reward R953)
  6805. <=WM: (13374: O1900 ^name predict-no)
  6806. <=WM: (13373: O1899 ^name predict-yes)
  6807. <=WM: (13372: R953 ^value 1)
  6808. --- Inner Elaboration Phase, active level 1 (S1) ---
  6809. Firing prefer*rvt*predict-yes*H0
  6810. -->
  6811. Firing rl*prefer*rvt*predict-yes*H0*3*v1*H1*36
  6812. -->
  6813. (S1 ^operator O1901 = -0.1070236389116304)
  6814. Firing rl*prefer*rvt*predict-yes*H0*3
  6815. -->
  6816. (S1 ^operator O1901 = 0.3377110766337923)
  6817. Firing prefer*rvt*predict-yes*H0*3*v1*H1
  6818. -->
  6819. Firing prefer*rvt*predict-no*H0
  6820. -->
  6821. Firing rl*prefer*rvt*predict-no*H0*4*v1*H1*35
  6822. -->
  6823. (S1 ^operator O1902 = 0.66025212945601)
  6824. Firing rl*prefer*rvt*predict-no*H0*4
  6825. -->
  6826. (S1 ^operator O1902 = 0.3397665963572414)
  6827. Firing prefer*rvt*predict-no*H0*4*v1*H1
  6828. -->
  6829. inner elaboration loop at bottom goal.
  6830. Retracting rl*prefer*rvt*predict-no*H0*4
  6831. -->
  6832. (S1 ^operator O1900 = 0.3397665963572414)
  6833. Retracting rl*prefer*rvt*predict-no*H0*4*v1*H1*35
  6834. -->
  6835. (S1 ^operator O1900 = 0.66025212945601)
  6836. Retracting rl*prefer*rvt*predict-yes*H0*3
  6837. -->
  6838. (S1 ^operator O1899 = 0.3377110766337923)
  6839. Retracting rl*prefer*rvt*predict-yes*H0*3*v1*H1*36
  6840. -->
  6841. (S1 ^operator O1899 = -0.1070236389116304)
  6842. --- END Proposal Phase ---
  6843. --- Decision Phase ---
  6844. RL update rl*prefer*rvt*predict-no*H0*2 1 0 1 -> 1 0 1(R,m,v=1,1,0)
  6845. =>WM: (13391: S1 ^operator O1902)
  6846. 951: O: O1902 (predict-no)
  6847. --- END Decision Phase ---
  6848. --- Application Phase ---
  6849. --- Firing Productions (PE) For State At Depth 1 ---
  6850. --- Inner Elaboration Phase, active level 1 (S1) ---
  6851. Firing apply*operator
  6852. -->
  6853. (I3 ^predict-no N951 + :O )
  6854. Firing apply*operator*complete
  6855. -->
  6856. (I3 ^predict-no N950 - :O )
  6857. inner elaboration loop at bottom goal.
  6858. --- Change Working Memory (PE) ---
  6859. =>WM: (13392: I3 ^predict-no N951)
  6860. <=WM: (13379: N950 ^status complete)
  6861. <=WM: (13378: I3 ^predict-no N950)
  6862. --- Firing Productions (IE) For State At Depth 1 ---
  6863. --- Inner Elaboration Phase, active level 1 (S1) ---
  6864. Firing monitor*world
  6865. -->
  6866. I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
  6867. --- Change Working Memory (IE) ---
  6868. --- END Application Phase ---
  6869. --- Output Phase ---
  6870. ENV: Agent did: predict-no for direction R in state State-B
  6871. In State-B moving R
  6872. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  6873. predict error 0
  6874. dir: dir isL
  6875. --- END Output Phase ---
  6876. |--- Input Phase ---
  6877. =>WM: (13396: I2 ^dir L)
  6878. =>WM: (13395: I2 ^reward 1)
  6879. =>WM: (13394: I2 ^see 0)
  6880. =>WM: (13393: N951 ^status complete)
  6881. <=WM: (13382: I2 ^dir R)
  6882. <=WM: (13381: I2 ^reward 1)
  6883. <=WM: (13380: I2 ^see 0)
  6884. =>WM: (13397: I2 ^level-1 R0-root)
  6885. <=WM: (13383: I2 ^level-1 R1-root)
  6886. --- END Input Phase ---
  6887. --- Proposal Phase ---
  6888. --- Inner Elaboration Phase, active level 1 (S1) ---
  6889. Firing rl*prefer*rvt*predict-yes*H0*5*v1*H1*30
  6890. -->
  6891. (S1 ^operator O1901 = 0.735786774178754)
  6892. Firing prefer*rvt*predict-yes*H0*5*v1*H1
  6893. -->
  6894. Firing elaborate*copy-see-to-output-link
  6895. -->
  6896. (I3 ^see 0 +)
  6897. Firing elaborate*reward*based*on*reward
  6898. -->
  6899. (R955 ^value 1 +)
  6900. (R1 ^reward R955 +)
  6901. Firing propose*predict-yes
  6902. -->
  6903. (O1903 ^name predict-yes +)
  6904. (S1 ^operator O1903 +)
  6905. Firing propose*predict-no
  6906. -->
  6907. (O1904 ^name predict-no +)
  6908. (S1 ^operator O1904 +)
  6909. Firing rl*prefer*rvt*predict-no*H0*6
  6910. -->
  6911. (S1 ^operator O1902 = 0.9996367744406318)
  6912. Firing rl*prefer*rvt*predict-yes*H0*5
  6913. -->
  6914. (S1 ^operator O1901 = 0.2640533371018167)
  6915. Firing prefer*rvt*predict-yes*H0
  6916. -->
  6917. Firing prefer*rvt*predict-no*H0
  6918. -->
  6919. Firing elaborate*copy-dir-to-output-link
  6920. -->
  6921. (I3 ^dir L +)
  6922. inner elaboration loop at bottom goal.
  6923. Retracting elaborate*copy-see-to-output-link
  6924. -->
  6925. (I3 ^see 0 +)
  6926. Retracting propose*predict-no
  6927. -->
  6928. (O1902 ^name predict-no +)
  6929. (S1 ^operator O1902 +)
  6930. Retracting propose*predict-yes
  6931. -->
  6932. (O1901 ^name predict-yes +)
  6933. (S1 ^operator O1901 +)
  6934. Retracting elaborate*reward*based*on*reward
  6935. -->
  6936. (R954 ^value 1 +)
  6937. (R1 ^reward R954 +)
  6938. Retracting elaborate*copy-dir-to-output-link
  6939. -->
  6940. (I3 ^dir R +)
  6941. Retracting rl*prefer*rvt*predict-no*H0*4
  6942. -->
  6943. (S1 ^operator O1902 = 0.3397665963572414)
  6944. Retracting rl*prefer*rvt*predict-no*H0*4*v1*H1*35
  6945. -->
  6946. (S1 ^operator O1902 = 0.66025212945601)
  6947. Retracting rl*prefer*rvt*predict-yes*H0*3
  6948. -->
  6949. (S1 ^operator O1901 = 0.3377110766337923)
  6950. Retracting rl*prefer*rvt*predict-yes*H0*3*v1*H1*36
  6951. -->
  6952. (S1 ^operator O1901 = -0.1070236389116304)
  6953. =>WM: (13404: S1 ^operator O1904 +)
  6954. =>WM: (13403: S1 ^operator O1903 +)
  6955. =>WM: (13402: I3 ^dir L)
  6956. =>WM: (13401: O1904 ^name predict-no)
  6957. =>WM: (13400: O1903 ^name predict-yes)
  6958. =>WM: (13399: R955 ^value 1)
  6959. =>WM: (13398: R1 ^reward R955)
  6960. <=WM: (13389: S1 ^operator O1901 +)
  6961. <=WM: (13390: S1 ^operator O1902 +)
  6962. <=WM: (13391: S1 ^operator O1902)
  6963. <=WM: (13388: I3 ^dir R)
  6964. <=WM: (13384: R1 ^reward R954)
  6965. <=WM: (13387: O1902 ^name predict-no)
  6966. <=WM: (13386: O1901 ^name predict-yes)
  6967. <=WM: (13385: R954 ^value 1)
  6968. --- Inner Elaboration Phase, active level 1 (S1) ---
  6969. Firing prefer*rvt*predict-yes*H0
  6970. -->
  6971. Firing rl*prefer*rvt*predict-yes*H0*5
  6972. -->
  6973. (S1 ^operator O1903 = 0.2640533371018167)
  6974. Firing prefer*rvt*predict-yes*H0*5*v1*H1
  6975. -->
  6976. Firing rl*prefer*rvt*predict-yes*H0*5*v1*H1*30
  6977. -->
  6978. (S1 ^operator O1903 = 0.735786774178754)
  6979. Firing prefer*rvt*predict-no*H0
  6980. -->
  6981. Firing rl*prefer*rvt*predict-no*H0*6
  6982. -->
  6983. (S1 ^operator O1904 = 0.9996367744406318)
  6984. inner elaboration loop at bottom goal.
  6985. Retracting rl*prefer*rvt*predict-no*H0*6
  6986. -->
  6987. (S1 ^operator O1902 = 0.9996367744406318)
  6988. Retracting rl*prefer*rvt*predict-yes*H0*5
  6989. -->
  6990. (S1 ^operator O1901 = 0.2640533371018167)
  6991. Retracting rl*prefer*rvt*predict-yes*H0*5*v1*H1*30
  6992. -->
  6993. (S1 ^operator O1901 = 0.735786774178754)
  6994. --- END Proposal Phase ---
  6995. --- Decision Phase ---
  6996. RL update rl*prefer*rvt*predict-no*H0*4 0.57025 -0.230483 0.339767 -> 0.570248 -0.230483 0.339765(R,m,v=1,0.87037,0.113527)
  6997. RL update rl*prefer*rvt*predict-no*H0*4*v1*H1*35 0.42977 0.230482 0.660252 -> 0.429768 0.230482 0.66025(R,m,v=1,1,0)
  6998. =>WM: (13405: S1 ^operator O1903)
  6999. 952: O: O1903 (predict-yes)
  7000. --- END Decision Phase ---
  7001. --- Application Phase ---
  7002. --- Firing Productions (PE) For State At Depth 1 ---
  7003. --- Inner Elaboration Phase, active level 1 (S1) ---
  7004. Firing apply*operator
  7005. -->
  7006. (I3 ^predict-yes N952 + :O )
  7007. Firing apply*operator*complete
  7008. -->
  7009. (I3 ^predict-no N951 - :O )
  7010. inner elaboration loop at bottom goal.
  7011. --- Change Working Memory (PE) ---
  7012. =>WM: (13406: I3 ^predict-yes N952)
  7013. <=WM: (13393: N951 ^status complete)
  7014. <=WM: (13392: I3 ^predict-no N951)
  7015. --- Firing Productions (IE) For State At Depth 1 ---
  7016. --- Inner Elaboration Phase, active level 1 (S1) ---
  7017. Firing monitor*world
  7018. -->
  7019. I see 1 and I'm going to do: predict-yes inner elaboration loop at bottom goal.
  7020. --- Change Working Memory (IE) ---
  7021. --- END Application Phase ---
  7022. --- Output Phase ---
  7023. ENV: Agent did: predict-yes for direction L in state State-B
  7024. In State-B moving L
  7025. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  7026. predict error 0
  7027. dir: dir isU
  7028. --- END Output Phase ---
  7029. \-/--- Input Phase ---
  7030. =>WM: (13410: I2 ^dir U)
  7031. =>WM: (13409: I2 ^reward 1)
  7032. =>WM: (13408: I2 ^see 1)
  7033. =>WM: (13407: N952 ^status complete)
  7034. <=WM: (13396: I2 ^dir L)
  7035. <=WM: (13395: I2 ^reward 1)
  7036. <=WM: (13394: I2 ^see 0)
  7037. =>WM: (13411: I2 ^level-1 L1-root)
  7038. <=WM: (13397: I2 ^level-1 R0-root)
  7039. --- END Input Phase ---
  7040. --- Proposal Phase ---
  7041. --- Inner Elaboration Phase, active level 1 (S1) ---
  7042. Firing elaborate*copy-see-to-output-link
  7043. -->
  7044. (I3 ^see 1 +)
  7045. Firing elaborate*reward*based*on*reward
  7046. -->
  7047. (R956 ^value 1 +)
  7048. (R1 ^reward R956 +)
  7049. Firing propose*predict-yes
  7050. -->
  7051. (O1905 ^name predict-yes +)
  7052. (S1 ^operator O1905 +)
  7053. Firing propose*predict-no
  7054. -->
  7055. (O1906 ^name predict-no +)
  7056. (S1 ^operator O1906 +)
  7057. Firing rl*prefer*rvt*predict-no*H0*2
  7058. -->
  7059. (S1 ^operator O1904 = 1.)
  7060. Firing rl*prefer*rvt*predict-yes*H0*1
  7061. -->
  7062. (S1 ^operator O1903 = 0.)
  7063. Firing prefer*rvt*predict-yes*H0
  7064. -->
  7065. Firing prefer*rvt*predict-no*H0
  7066. -->
  7067. Firing elaborate*copy-dir-to-output-link
  7068. -->
  7069. (I3 ^dir U +)
  7070. inner elaboration loop at bottom goal.
  7071. Retracting elaborate*copy-see-to-output-link
  7072. -->
  7073. (I3 ^see 0 +)
  7074. Retracting propose*predict-no
  7075. -->
  7076. (O1904 ^name predict-no +)
  7077. (S1 ^operator O1904 +)
  7078. Retracting propose*predict-yes
  7079. -->
  7080. (O1903 ^name predict-yes +)
  7081. (S1 ^operator O1903 +)
  7082. Retracting elaborate*reward*based*on*reward
  7083. -->
  7084. (R955 ^value 1 +)
  7085. (R1 ^reward R955 +)
  7086. Retracting elaborate*copy-dir-to-output-link
  7087. -->
  7088. (I3 ^dir L +)
  7089. Retracting rl*prefer*rvt*predict-no*H0*6
  7090. -->
  7091. (S1 ^operator O1904 = 0.9996367744406318)
  7092. Retracting rl*prefer*rvt*predict-yes*H0*5*v1*H1*30
  7093. -->
  7094. (S1 ^operator O1903 = 0.735786774178754)
  7095. Retracting rl*prefer*rvt*predict-yes*H0*5
  7096. -->
  7097. (S1 ^operator O1903 = 0.2640533371018167)
  7098. =>WM: (13419: S1 ^operator O1906 +)
  7099. =>WM: (13418: S1 ^operator O1905 +)
  7100. =>WM: (13417: I3 ^dir U)
  7101. =>WM: (13416: O1906 ^name predict-no)
  7102. =>WM: (13415: O1905 ^name predict-yes)
  7103. =>WM: (13414: R956 ^value 1)
  7104. =>WM: (13413: R1 ^reward R956)
  7105. =>WM: (13412: I3 ^see 1)
  7106. <=WM: (13403: S1 ^operator O1903 +)
  7107. <=WM: (13405: S1 ^operator O1903)
  7108. <=WM: (13404: S1 ^operator O1904 +)
  7109. <=WM: (13402: I3 ^dir L)
  7110. <=WM: (13398: R1 ^reward R955)
  7111. <=WM: (13370: I3 ^see 0)
  7112. <=WM: (13401: O1904 ^name predict-no)
  7113. <=WM: (13400: O1903 ^name predict-yes)
  7114. <=WM: (13399: R955 ^value 1)
  7115. --- Inner Elaboration Phase, active level 1 (S1) ---
  7116. Firing prefer*rvt*predict-yes*H0
  7117. -->
  7118. Firing rl*prefer*rvt*predict-yes*H0*1
  7119. -->
  7120. (S1 ^operator O1905 = 0.)
  7121. Firing prefer*rvt*predict-no*H0
  7122. -->
  7123. Firing rl*prefer*rvt*predict-no*H0*2
  7124. -->
  7125. (S1 ^operator O1906 = 1.)
  7126. inner elaboration loop at bottom goal.
  7127. Retracting rl*prefer*rvt*predict-no*H0*2
  7128. -->
  7129. (S1 ^operator O1904 = 1.)
  7130. Retracting rl*prefer*rvt*predict-yes*H0*1
  7131. -->
  7132. (S1 ^operator O1903 = 0.)
  7133. --- END Proposal Phase ---
  7134. --- Decision Phase ---
  7135. RL update rl*prefer*rvt*predict-yes*H0*5 0.554438 -0.290385 0.264053 -> 0.554451 -0.290385 0.264066(R,m,v=1,0.872093,0.112199)
  7136. RL update rl*prefer*rvt*predict-yes*H0*5*v1*H1*30 0.445404 0.290382 0.735787 -> 0.44542 0.290383 0.735802(R,m,v=1,1,0)
  7137. =>WM: (13420: S1 ^operator O1906)
  7138. 953: O: O1906 (predict-no)
  7139. --- END Decision Phase ---
  7140. --- Application Phase ---
  7141. --- Firing Productions (PE) For State At Depth 1 ---
  7142. --- Inner Elaboration Phase, active level 1 (S1) ---
  7143. Firing apply*operator
  7144. -->
  7145. (I3 ^predict-no N953 + :O )
  7146. Firing apply*operator*complete
  7147. -->
  7148. (I3 ^predict-yes N952 - :O )
  7149. inner elaboration loop at bottom goal.
  7150. --- Change Working Memory (PE) ---
  7151. =>WM: (13421: I3 ^predict-no N953)
  7152. <=WM: (13407: N952 ^status complete)
  7153. <=WM: (13406: I3 ^predict-yes N952)
  7154. --- Firing Productions (IE) For State At Depth 1 ---
  7155. --- Inner Elaboration Phase, active level 1 (S1) ---
  7156. Firing monitor*world
  7157. -->
  7158. I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
  7159. --- Change Working Memory (IE) ---
  7160. --- END Application Phase ---
  7161. --- Output Phase ---
  7162. ENV: Agent did: predict-no for direction U in state State-A
  7163. In State-A moving U
  7164. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  7165. predict error 0
  7166. dir: dir isR
  7167. --- END Output Phase ---
  7168. |\---- Input Phase ---
  7169. =>WM: (13425: I2 ^dir R)
  7170. =>WM: (13424: I2 ^reward 1)
  7171. =>WM: (13423: I2 ^see 0)
  7172. =>WM: (13422: N953 ^status complete)
  7173. <=WM: (13410: I2 ^dir U)
  7174. <=WM: (13409: I2 ^reward 1)
  7175. <=WM: (13408: I2 ^see 1)
  7176. =>WM: (13426: I2 ^level-1 L1-root)
  7177. <=WM: (13411: I2 ^level-1 L1-root)
  7178. --- END Input Phase ---
  7179. --- Proposal Phase ---
  7180. --- Inner Elaboration Phase, active level 1 (S1) ---
  7181. Firing rl*prefer*rvt*predict-no*H0*4*v1*H1*37
  7182. -->
  7183. (S1 ^operator O1906 = -0.2714224023553999)
  7184. Firing rl*prefer*rvt*predict-yes*H0*3*v1*H1*38
  7185. -->
  7186. (S1 ^operator O1905 = 0.6621942993402632)
  7187. Firing prefer*rvt*predict-no*H0*4*v1*H1
  7188. -->
  7189. Firing prefer*rvt*predict-yes*H0*3*v1*H1
  7190. -->
  7191. Firing elaborate*copy-see-to-output-link
  7192. -->
  7193. (I3 ^see 0 +)
  7194. Firing elaborate*reward*based*on*reward
  7195. -->
  7196. (R957 ^value 1 +)
  7197. (R1 ^reward R957 +)
  7198. Firing propose*predict-yes
  7199. -->
  7200. (O1907 ^name predict-yes +)
  7201. (S1 ^operator O1907 +)
  7202. Firing propose*predict-no
  7203. -->
  7204. (O1908 ^name predict-no +)
  7205. (S1 ^operator O1908 +)
  7206. Firing rl*prefer*rvt*predict-no*H0*4
  7207. -->
  7208. (S1 ^operator O1906 = 0.3397650583271044)
  7209. Firing rl*prefer*rvt*predict-yes*H0*3
  7210. -->
  7211. (S1 ^operator O1905 = 0.3377110766337923)
  7212. Firing prefer*rvt*predict-yes*H0
  7213. -->
  7214. Firing prefer*rvt*predict-no*H0
  7215. -->
  7216. Firing elaborate*copy-dir-to-output-link
  7217. -->
  7218. (I3 ^dir R +)
  7219. inner elaboration loop at bottom goal.
  7220. Retracting elaborate*copy-see-to-output-link
  7221. -->
  7222. (I3 ^see 1 +)
  7223. Retracting propose*predict-no
  7224. -->
  7225. (O1906 ^name predict-no +)
  7226. (S1 ^operator O1906 +)
  7227. Retracting propose*predict-yes
  7228. -->
  7229. (O1905 ^name predict-yes +)
  7230. (S1 ^operator O1905 +)
  7231. Retracting elaborate*reward*based*on*reward
  7232. -->
  7233. (R956 ^value 1 +)
  7234. (R1 ^reward R956 +)
  7235. Retracting elaborate*copy-dir-to-output-link
  7236. -->
  7237. (I3 ^dir U +)
  7238. Retracting rl*prefer*rvt*predict-no*H0*2
  7239. -->
  7240. (S1 ^operator O1906 = 1.)
  7241. Retracting rl*prefer*rvt*predict-yes*H0*1
  7242. -->
  7243. (S1 ^operator O1905 = 0.)
  7244. =>WM: (13434: S1 ^operator O1908 +)
  7245. =>WM: (13433: S1 ^operator O1907 +)
  7246. =>WM: (13432: I3 ^dir R)
  7247. =>WM: (13431: O1908 ^name predict-no)
  7248. =>WM: (13430: O1907 ^name predict-yes)
  7249. =>WM: (13429: R957 ^value 1)
  7250. =>WM: (13428: R1 ^reward R957)
  7251. =>WM: (13427: I3 ^see 0)
  7252. <=WM: (13418: S1 ^operator O1905 +)
  7253. <=WM: (13419: S1 ^operator O1906 +)
  7254. <=WM: (13420: S1 ^operator O1906)
  7255. <=WM: (13417: I3 ^dir U)
  7256. <=WM: (13413: R1 ^reward R956)
  7257. <=WM: (13412: I3 ^see 1)
  7258. <=WM: (13416: O1906 ^name predict-no)
  7259. <=WM: (13415: O1905 ^name predict-yes)
  7260. <=WM: (13414: R956 ^value 1)
  7261. --- Inner Elaboration Phase, active level 1 (S1) ---
  7262. Firing prefer*rvt*predict-yes*H0
  7263. -->
  7264. Firing rl*prefer*rvt*predict-yes*H0*3*v1*H1*38
  7265. -->
  7266. (S1 ^operator O1907 = 0.6621942993402632)
  7267. Firing rl*prefer*rvt*predict-yes*H0*3
  7268. -->
  7269. (S1 ^operator O1907 = 0.3377110766337923)
  7270. Firing prefer*rvt*predict-yes*H0*3*v1*H1
  7271. -->
  7272. Firing prefer*rvt*predict-no*H0
  7273. -->
  7274. Firing rl*prefer*rvt*predict-no*H0*4*v1*H1*37
  7275. -->
  7276. (S1 ^operator O1908 = -0.2714224023553999)
  7277. Firing rl*prefer*rvt*predict-no*H0*4
  7278. -->
  7279. (S1 ^operator O1908 = 0.3397650583271044)
  7280. Firing prefer*rvt*predict-no*H0*4*v1*H1
  7281. -->
  7282. inner elaboration loop at bottom goal.
  7283. Retracting rl*prefer*rvt*predict-no*H0*4
  7284. -->
  7285. (S1 ^operator O1906 = 0.3397650583271044)
  7286. Retracting rl*prefer*rvt*predict-no*H0*4*v1*H1*37
  7287. -->
  7288. (S1 ^operator O1906 = -0.2714224023553999)
  7289. Retracting rl*prefer*rvt*predict-yes*H0*3
  7290. -->
  7291. (S1 ^operator O1905 = 0.3377110766337923)
  7292. Retracting rl*prefer*rvt*predict-yes*H0*3*v1*H1*38
  7293. -->
  7294. (S1 ^operator O1905 = 0.6621942993402632)
  7295. --- END Proposal Phase ---
  7296. --- Decision Phase ---
  7297. RL update rl*prefer*rvt*predict-no*H0*2 1 0 1 -> 1 0 1(R,m,v=1,1,0)
  7298. =>WM: (13435: S1 ^operator O1907)
  7299. 954: O: O1907 (predict-yes)
  7300. --- END Decision Phase ---
  7301. --- Application Phase ---
  7302. --- Firing Productions (PE) For State At Depth 1 ---
  7303. --- Inner Elaboration Phase, active level 1 (S1) ---
  7304. Firing apply*operator
  7305. -->
  7306. (I3 ^predict-yes N954 + :O )
  7307. Firing apply*operator*complete
  7308. -->
  7309. (I3 ^predict-no N953 - :O )
  7310. inner elaboration loop at bottom goal.
  7311. --- Change Working Memory (PE) ---
  7312. =>WM: (13436: I3 ^predict-yes N954)
  7313. <=WM: (13422: N953 ^status complete)
  7314. <=WM: (13421: I3 ^predict-no N953)
  7315. --- Firing Productions (IE) For State At Depth 1 ---
  7316. --- Inner Elaboration Phase, active level 1 (S1) ---
  7317. Firing monitor*world
  7318. -->
  7319. I see 1 and I'm going to do: predict-yes inner elaboration loop at bottom goal.
  7320. --- Change Working Memory (IE) ---
  7321. --- END Application Phase ---
  7322. --- Output Phase ---
  7323. ENV: Agent did: predict-yes for direction R in state State-A
  7324. In State-A moving R
  7325. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  7326. predict error 0
  7327. dir: dir isU
  7328. --- END Output Phase ---
  7329. /|\---- Input Phase ---
  7330. =>WM: (13440: I2 ^dir U)
  7331. =>WM: (13439: I2 ^reward 1)
  7332. =>WM: (13438: I2 ^see 1)
  7333. =>WM: (13437: N954 ^status complete)
  7334. <=WM: (13425: I2 ^dir R)
  7335. <=WM: (13424: I2 ^reward 1)
  7336. <=WM: (13423: I2 ^see 0)
  7337. =>WM: (13441: I2 ^level-1 R1-root)
  7338. <=WM: (13426: I2 ^level-1 L1-root)
  7339. --- END Input Phase ---
  7340. --- Proposal Phase ---
  7341. --- Inner Elaboration Phase, active level 1 (S1) ---
  7342. Firing elaborate*copy-see-to-output-link
  7343. -->
  7344. (I3 ^see 1 +)
  7345. Firing elaborate*reward*based*on*reward
  7346. -->
  7347. (R958 ^value 1 +)
  7348. (R1 ^reward R958 +)
  7349. Firing propose*predict-yes
  7350. -->
  7351. (O1909 ^name predict-yes +)
  7352. (S1 ^operator O1909 +)
  7353. Firing propose*predict-no
  7354. -->
  7355. (O1910 ^name predict-no +)
  7356. (S1 ^operator O1910 +)
  7357. Firing rl*prefer*rvt*predict-no*H0*2
  7358. -->
  7359. (S1 ^operator O1908 = 1.)
  7360. Firing rl*prefer*rvt*predict-yes*H0*1
  7361. -->
  7362. (S1 ^operator O1907 = 0.)
  7363. Firing prefer*rvt*predict-yes*H0
  7364. -->
  7365. Firing prefer*rvt*predict-no*H0
  7366. -->
  7367. Firing elaborate*copy-dir-to-output-link
  7368. -->
  7369. (I3 ^dir U +)
  7370. inner elaboration loop at bottom goal.
  7371. Retracting elaborate*copy-see-to-output-link
  7372. -->
  7373. (I3 ^see 0 +)
  7374. Retracting propose*predict-no
  7375. -->
  7376. (O1908 ^name predict-no +)
  7377. (S1 ^operator O1908 +)
  7378. Retracting propose*predict-yes
  7379. -->
  7380. (O1907 ^name predict-yes +)
  7381. (S1 ^operator O1907 +)
  7382. Retracting elaborate*reward*based*on*reward
  7383. -->
  7384. (R957 ^value 1 +)
  7385. (R1 ^reward R957 +)
  7386. Retracting elaborate*copy-dir-to-output-link
  7387. -->
  7388. (I3 ^dir R +)
  7389. Retracting rl*prefer*rvt*predict-no*H0*4
  7390. -->
  7391. (S1 ^operator O1908 = 0.3397650583271044)
  7392. Retracting rl*prefer*rvt*predict-no*H0*4*v1*H1*37
  7393. -->
  7394. (S1 ^operator O1908 = -0.2714224023553999)
  7395. Retracting rl*prefer*rvt*predict-yes*H0*3
  7396. -->
  7397. (S1 ^operator O1907 = 0.3377110766337923)
  7398. Retracting rl*prefer*rvt*predict-yes*H0*3*v1*H1*38
  7399. -->
  7400. (S1 ^operator O1907 = 0.6621942993402632)
  7401. =>WM: (13449: S1 ^operator O1910 +)
  7402. =>WM: (13448: S1 ^operator O1909 +)
  7403. =>WM: (13447: I3 ^dir U)
  7404. =>WM: (13446: O1910 ^name predict-no)
  7405. =>WM: (13445: O1909 ^name predict-yes)
  7406. =>WM: (13444: R958 ^value 1)
  7407. =>WM: (13443: R1 ^reward R958)
  7408. =>WM: (13442: I3 ^see 1)
  7409. <=WM: (13433: S1 ^operator O1907 +)
  7410. <=WM: (13435: S1 ^operator O1907)
  7411. <=WM: (13434: S1 ^operator O1908 +)
  7412. <=WM: (13432: I3 ^dir R)
  7413. <=WM: (13428: R1 ^reward R957)
  7414. <=WM: (13427: I3 ^see 0)
  7415. <=WM: (13431: O1908 ^name predict-no)
  7416. <=WM: (13430: O1907 ^name predict-yes)
  7417. <=WM: (13429: R957 ^value 1)
  7418. --- Inner Elaboration Phase, active level 1 (S1) ---
  7419. Firing prefer*rvt*predict-yes*H0
  7420. -->
  7421. Firing rl*prefer*rvt*predict-yes*H0*1
  7422. -->
  7423. (S1 ^operator O1909 = 0.)
  7424. Firing prefer*rvt*predict-no*H0
  7425. -->
  7426. Firing rl*prefer*rvt*predict-no*H0*2
  7427. -->
  7428. (S1 ^operator O1910 = 1.)
  7429. inner elaboration loop at bottom goal.
  7430. Retracting rl*prefer*rvt*predict-no*H0*2
  7431. -->
  7432. (S1 ^operator O1908 = 1.)
  7433. Retracting rl*prefer*rvt*predict-yes*H0*1
  7434. -->
  7435. (S1 ^operator O1907 = 0.)
  7436. --- END Proposal Phase ---
  7437. --- Decision Phase ---
  7438. RL update rl*prefer*rvt*predict-yes*H0*3 0.590111 -0.2524 0.337711 -> 0.59012 -0.252401 0.337719(R,m,v=1,0.89441,0.0950311)
  7439. RL update rl*prefer*rvt*predict-yes*H0*3*v1*H1*38 0.40978 0.252415 0.662194 -> 0.40979 0.252413 0.662203(R,m,v=1,1,0)
  7440. =>WM: (13450: S1 ^operator O1910)
  7441. 955: O: O1910 (predict-no)
  7442. --- END Decision Phase ---
  7443. --- Application Phase ---
  7444. --- Firing Productions (PE) For State At Depth 1 ---
  7445. --- Inner Elaboration Phase, active level 1 (S1) ---
  7446. Firing apply*operator
  7447. -->
  7448. (I3 ^predict-no N955 + :O )
  7449. Firing apply*operator*complete
  7450. -->
  7451. (I3 ^predict-yes N954 - :O )
  7452. inner elaboration loop at bottom goal.
  7453. --- Change Working Memory (PE) ---
  7454. =>WM: (13451: I3 ^predict-no N955)
  7455. <=WM: (13437: N954 ^status complete)
  7456. <=WM: (13436: I3 ^predict-yes N954)
  7457. --- Firing Productions (IE) For State At Depth 1 ---
  7458. --- Inner Elaboration Phase, active level 1 (S1) ---
  7459. Firing monitor*world
  7460. -->
  7461. I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
  7462. --- Change Working Memory (IE) ---
  7463. --- END Application Phase ---
  7464. --- Output Phase ---
  7465. ENV: Agent did: predict-no for direction U in state State-B
  7466. In State-B moving U
  7467. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  7468. predict error 0
  7469. dir: dir isR
  7470. --- END Output Phase ---
  7471. /|\--- Input Phase ---
  7472. =>WM: (13455: I2 ^dir R)
  7473. =>WM: (13454: I2 ^reward 1)
  7474. =>WM: (13453: I2 ^see 0)
  7475. =>WM: (13452: N955 ^status complete)
  7476. <=WM: (13440: I2 ^dir U)
  7477. <=WM: (13439: I2 ^reward 1)
  7478. <=WM: (13438: I2 ^see 1)
  7479. =>WM: (13456: I2 ^level-1 R1-root)
  7480. <=WM: (13441: I2 ^level-1 R1-root)
  7481. --- END Input Phase ---
  7482. --- Proposal Phase ---
  7483. --- Inner Elaboration Phase, active level 1 (S1) ---
  7484. Firing rl*prefer*rvt*predict-yes*H0*3*v1*H1*36
  7485. -->
  7486. (S1 ^operator O1909 = -0.1070236389116304)
  7487. Firing rl*prefer*rvt*predict-no*H0*4*v1*H1*35
  7488. -->
  7489. (S1 ^operator O1910 = 0.6602503199844459)
  7490. Firing prefer*rvt*predict-no*H0*4*v1*H1
  7491. -->
  7492. Firing prefer*rvt*predict-yes*H0*3*v1*H1
  7493. -->
  7494. Firing elaborate*copy-see-to-output-link
  7495. -->
  7496. (I3 ^see 0 +)
  7497. Firing elaborate*reward*based*on*reward
  7498. -->
  7499. (R959 ^value 1 +)
  7500. (R1 ^reward R959 +)
  7501. Firing propose*predict-yes
  7502. -->
  7503. (O1911 ^name predict-yes +)
  7504. (S1 ^operator O1911 +)
  7505. Firing propose*predict-no
  7506. -->
  7507. (O1912 ^name predict-no +)
  7508. (S1 ^operator O1912 +)
  7509. Firing rl*prefer*rvt*predict-no*H0*4
  7510. -->
  7511. (S1 ^operator O1910 = 0.3397650583271044)
  7512. Firing rl*prefer*rvt*predict-yes*H0*3
  7513. -->
  7514. (S1 ^operator O1909 = 0.3377188564178903)
  7515. Firing prefer*rvt*predict-yes*H0
  7516. -->
  7517. Firing prefer*rvt*predict-no*H0
  7518. -->
  7519. Firing elaborate*copy-dir-to-output-link
  7520. -->
  7521. (I3 ^dir R +)
  7522. inner elaboration loop at bottom goal.
  7523. Retracting elaborate*copy-see-to-output-link
  7524. -->
  7525. (I3 ^see 1 +)
  7526. Retracting propose*predict-no
  7527. -->
  7528. (O1910 ^name predict-no +)
  7529. (S1 ^operator O1910 +)
  7530. Retracting propose*predict-yes
  7531. -->
  7532. (O1909 ^name predict-yes +)
  7533. (S1 ^operator O1909 +)
  7534. Retracting elaborate*reward*based*on*reward
  7535. -->
  7536. (R958 ^value 1 +)
  7537. (R1 ^reward R958 +)
  7538. Retracting elaborate*copy-dir-to-output-link
  7539. -->
  7540. (I3 ^dir U +)
  7541. Retracting rl*prefer*rvt*predict-no*H0*2
  7542. -->
  7543. (S1 ^operator O1910 = 1.)
  7544. Retracting rl*prefer*rvt*predict-yes*H0*1
  7545. -->
  7546. (S1 ^operator O1909 = 0.)
  7547. =>WM: (13464: S1 ^operator O1912 +)
  7548. =>WM: (13463: S1 ^operator O1911 +)
  7549. =>WM: (13462: I3 ^dir R)
  7550. =>WM: (13461: O1912 ^name predict-no)
  7551. =>WM: (13460: O1911 ^name predict-yes)
  7552. =>WM: (13459: R959 ^value 1)
  7553. =>WM: (13458: R1 ^reward R959)
  7554. =>WM: (13457: I3 ^see 0)
  7555. <=WM: (13448: S1 ^operator O1909 +)
  7556. <=WM: (13449: S1 ^operator O1910 +)
  7557. <=WM: (13450: S1 ^operator O1910)
  7558. <=WM: (13447: I3 ^dir U)
  7559. <=WM: (13443: R1 ^reward R958)
  7560. <=WM: (13442: I3 ^see 1)
  7561. <=WM: (13446: O1910 ^name predict-no)
  7562. <=WM: (13445: O1909 ^name predict-yes)
  7563. <=WM: (13444: R958 ^value 1)
  7564. --- Inner Elaboration Phase, active level 1 (S1) ---
  7565. Firing prefer*rvt*predict-yes*H0
  7566. -->
  7567. Firing rl*prefer*rvt*predict-yes*H0*3*v1*H1*36
  7568. -->
  7569. (S1 ^operator O1911 = -0.1070236389116304)
  7570. Firing rl*prefer*rvt*predict-yes*H0*3
  7571. -->
  7572. (S1 ^operator O1911 = 0.3377188564178903)
  7573. Firing prefer*rvt*predict-yes*H0*3*v1*H1
  7574. -->
  7575. Firing prefer*rvt*predict-no*H0
  7576. -->
  7577. Firing rl*prefer*rvt*predict-no*H0*4*v1*H1*35
  7578. -->
  7579. (S1 ^operator O1912 = 0.6602503199844459)
  7580. Firing rl*prefer*rvt*predict-no*H0*4
  7581. -->
  7582. (S1 ^operator O1912 = 0.3397650583271044)
  7583. Firing prefer*rvt*predict-no*H0*4*v1*H1
  7584. -->
  7585. inner elaboration loop at bottom goal.
  7586. Retracting rl*prefer*rvt*predict-no*H0*4
  7587. -->
  7588. (S1 ^operator O1910 = 0.3397650583271044)
  7589. Retracting rl*prefer*rvt*predict-no*H0*4*v1*H1*35
  7590. -->
  7591. (S1 ^operator O1910 = 0.6602503199844459)
  7592. Retracting rl*prefer*rvt*predict-yes*H0*3
  7593. -->
  7594. (S1 ^operator O1909 = 0.3377188564178903)
  7595. Retracting rl*prefer*rvt*predict-yes*H0*3*v1*H1*36
  7596. -->
  7597. (S1 ^operator O1909 = -0.1070236389116304)
  7598. --- END Proposal Phase ---
  7599. --- Decision Phase ---
  7600. RL update rl*prefer*rvt*predict-no*H0*2 1 0 1 -> 1 0 1(R,m,v=1,1,0)
  7601. =>WM: (13465: S1 ^operator O1912)
  7602. 956: O: O1912 (predict-no)
  7603. --- END Decision Phase ---
  7604. --- Application Phase ---
  7605. --- Firing Productions (PE) For State At Depth 1 ---
  7606. --- Inner Elaboration Phase, active level 1 (S1) ---
  7607. Firing apply*operator
  7608. -->
  7609. (I3 ^predict-no N956 + :O )
  7610. Firing apply*operator*complete
  7611. -->
  7612. (I3 ^predict-no N955 - :O )
  7613. inner elaboration loop at bottom goal.
  7614. --- Change Working Memory (PE) ---
  7615. =>WM: (13466: I3 ^predict-no N956)
  7616. <=WM: (13452: N955 ^status complete)
  7617. <=WM: (13451: I3 ^predict-no N955)
  7618. --- Firing Productions (IE) For State At Depth 1 ---
  7619. --- Inner Elaboration Phase, active level 1 (S1) ---
  7620. Firing monitor*world
  7621. -->
  7622. I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
  7623. --- Change Working Memory (IE) ---
  7624. --- END Application Phase ---
  7625. --- Output Phase ---
  7626. ENV: Agent did: predict-no for direction R in state State-B
  7627. In State-B moving R
  7628. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  7629. predict error 0
  7630. dir: dir isR
  7631. --- END Output Phase ---
  7632. -/--- Input Phase ---
  7633. =>WM: (13470: I2 ^dir R)
  7634. =>WM: (13469: I2 ^reward 1)
  7635. =>WM: (13468: I2 ^see 0)
  7636. =>WM: (13467: N956 ^status complete)
  7637. <=WM: (13455: I2 ^dir R)
  7638. <=WM: (13454: I2 ^reward 1)
  7639. <=WM: (13453: I2 ^see 0)
  7640. =>WM: (13471: I2 ^level-1 R0-root)
  7641. <=WM: (13456: I2 ^level-1 R1-root)
  7642. --- END Input Phase ---
  7643. --- Proposal Phase ---
  7644. --- Inner Elaboration Phase, active level 1 (S1) ---
  7645. Firing rl*prefer*rvt*predict-no*H0*4*v1*H1*39
  7646. -->
  7647. (S1 ^operator O1912 = 0.6601435952544124)
  7648. Firing rl*prefer*rvt*predict-yes*H0*3*v1*H1*40
  7649. -->
  7650. (S1 ^operator O1911 = -0.1028953566115423)
  7651. Firing prefer*rvt*predict-no*H0*4*v1*H1
  7652. -->
  7653. Firing prefer*rvt*predict-yes*H0*3*v1*H1
  7654. -->
  7655. Firing elaborate*copy-see-to-output-link
  7656. -->
  7657. (I3 ^see 0 +)
  7658. Firing elaborate*reward*based*on*reward
  7659. -->
  7660. (R960 ^value 1 +)
  7661. (R1 ^reward R960 +)
  7662. Firing propose*predict-yes
  7663. -->
  7664. (O1913 ^name predict-yes +)
  7665. (S1 ^operator O1913 +)
  7666. Firing propose*predict-no
  7667. -->
  7668. (O1914 ^name predict-no +)
  7669. (S1 ^operator O1914 +)
  7670. Firing rl*prefer*rvt*predict-no*H0*4
  7671. -->
  7672. (S1 ^operator O1912 = 0.3397650583271044)
  7673. Firing rl*prefer*rvt*predict-yes*H0*3
  7674. -->
  7675. (S1 ^operator O1911 = 0.3377188564178903)
  7676. Firing prefer*rvt*predict-yes*H0
  7677. -->
  7678. Firing prefer*rvt*predict-no*H0
  7679. -->
  7680. Firing elaborate*copy-dir-to-output-link
  7681. -->
  7682. (I3 ^dir R +)
  7683. inner elaboration loop at bottom goal.
  7684. Retracting elaborate*copy-see-to-output-link
  7685. -->
  7686. (I3 ^see 0 +)
  7687. Retracting propose*predict-no
  7688. -->
  7689. (O1912 ^name predict-no +)
  7690. (S1 ^operator O1912 +)
  7691. Retracting propose*predict-yes
  7692. -->
  7693. (O1911 ^name predict-yes +)
  7694. (S1 ^operator O1911 +)
  7695. Retracting elaborate*reward*based*on*reward
  7696. -->
  7697. (R959 ^value 1 +)
  7698. (R1 ^reward R959 +)
  7699. Retracting elaborate*copy-dir-to-output-link
  7700. -->
  7701. (I3 ^dir R +)
  7702. Retracting rl*prefer*rvt*predict-no*H0*4
  7703. -->
  7704. (S1 ^operator O1912 = 0.3397650583271044)
  7705. Retracting rl*prefer*rvt*predict-no*H0*4*v1*H1*35
  7706. -->
  7707. (S1 ^operator O1912 = 0.6602503199844459)
  7708. Retracting rl*prefer*rvt*predict-yes*H0*3
  7709. -->
  7710. (S1 ^operator O1911 = 0.3377188564178903)
  7711. Retracting rl*prefer*rvt*predict-yes*H0*3*v1*H1*36
  7712. -->
  7713. (S1 ^operator O1911 = -0.1070236389116304)
  7714. =>WM: (13477: S1 ^operator O1914 +)
  7715. =>WM: (13476: S1 ^operator O1913 +)
  7716. =>WM: (13475: O1914 ^name predict-no)
  7717. =>WM: (13474: O1913 ^name predict-yes)
  7718. =>WM: (13473: R960 ^value 1)
  7719. =>WM: (13472: R1 ^reward R960)
  7720. <=WM: (13463: S1 ^operator O1911 +)
  7721. <=WM: (13464: S1 ^operator O1912 +)
  7722. <=WM: (13465: S1 ^operator O1912)
  7723. <=WM: (13458: R1 ^reward R959)
  7724. <=WM: (13461: O1912 ^name predict-no)
  7725. <=WM: (13460: O1911 ^name predict-yes)
  7726. <=WM: (13459: R959 ^value 1)
  7727. --- Inner Elaboration Phase, active level 1 (S1) ---
  7728. Firing prefer*rvt*predict-yes*H0
  7729. -->
  7730. Firing rl*prefer*rvt*predict-yes*H0*3
  7731. -->
  7732. (S1 ^operator O1913 = 0.3377188564178903)
  7733. Firing prefer*rvt*predict-yes*H0*3*v1*H1
  7734. -->
  7735. Firing rl*prefer*rvt*predict-yes*H0*3*v1*H1*40
  7736. -->
  7737. (S1 ^operator O1913 = -0.1028953566115423)
  7738. Firing prefer*rvt*predict-no*H0
  7739. -->
  7740. Firing rl*prefer*rvt*predict-no*H0*4
  7741. -->
  7742. (S1 ^operator O1914 = 0.3397650583271044)
  7743. Firing prefer*rvt*predict-no*H0*4*v1*H1
  7744. -->
  7745. Firing rl*prefer*rvt*predict-no*H0*4*v1*H1*39
  7746. -->
  7747. (S1 ^operator O1914 = 0.6601435952544124)
  7748. inner elaboration loop at bottom goal.
  7749. Retracting rl*prefer*rvt*predict-no*H0*4
  7750. -->
  7751. (S1 ^operator O1912 = 0.3397650583271044)
  7752. Retracting rl*prefer*rvt*predict-no*H0*4*v1*H1*39
  7753. -->
  7754. (S1 ^operator O1912 = 0.6601435952544124)
  7755. Retracting rl*prefer*rvt*predict-yes*H0*3
  7756. -->
  7757. (S1 ^operator O1911 = 0.3377188564178903)
  7758. Retracting rl*prefer*rvt*predict-yes*H0*3*v1*H1*40
  7759. -->
  7760. (S1 ^operator O1911 = -0.1028953566115423)
  7761. --- END Proposal Phase ---
  7762. --- Decision Phase ---
  7763. RL update rl*prefer*rvt*predict-no*H0*4 0.570248 -0.230483 0.339765 -> 0.570247 -0.230483 0.339764(R,m,v=1,0.871166,0.112929)
  7764. RL update rl*prefer*rvt*predict-no*H0*4*v1*H1*35 0.429768 0.230482 0.66025 -> 0.429766 0.230483 0.660249(R,m,v=1,1,0)
  7765. =>WM: (13478: S1 ^operator O1914)
  7766. 957: O: O1914 (predict-no)
  7767. --- END Decision Phase ---
  7768. --- Application Phase ---
  7769. --- Firing Productions (PE) For State At Depth 1 ---
  7770. --- Inner Elaboration Phase, active level 1 (S1) ---
  7771. Firing apply*operator
  7772. -->
  7773. (I3 ^predict-no N957 + :O )
  7774. Firing apply*operator*complete
  7775. -->
  7776. (I3 ^predict-no N956 - :O )
  7777. inner elaboration loop at bottom goal.
  7778. --- Change Working Memory (PE) ---
  7779. =>WM: (13479: I3 ^predict-no N957)
  7780. <=WM: (13467: N956 ^status complete)
  7781. <=WM: (13466: I3 ^predict-no N956)
  7782. --- Firing Productions (IE) For State At Depth 1 ---
  7783. --- Inner Elaboration Phase, active level 1 (S1) ---
  7784. Firing monitor*world
  7785. -->
  7786. I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
  7787. --- Change Working Memory (IE) ---
  7788. --- END Application Phase ---
  7789. --- Output Phase ---
  7790. ENV: Agent did: predict-no for direction R in state State-B
  7791. In State-B moving R
  7792. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  7793. predict error 0
  7794. dir: dir isL
  7795. --- END Output Phase ---
  7796. |\---- Input Phase ---
  7797. =>WM: (13483: I2 ^dir L)
  7798. =>WM: (13482: I2 ^reward 1)
  7799. =>WM: (13481: I2 ^see 0)
  7800. =>WM: (13480: N957 ^status complete)
  7801. <=WM: (13470: I2 ^dir R)
  7802. <=WM: (13469: I2 ^reward 1)
  7803. <=WM: (13468: I2 ^see 0)
  7804. =>WM: (13484: I2 ^level-1 R0-root)
  7805. <=WM: (13471: I2 ^level-1 R0-root)
  7806. --- END Input Phase ---
  7807. --- Proposal Phase ---
  7808. --- Inner Elaboration Phase, active level 1 (S1) ---
  7809. Firing rl*prefer*rvt*predict-yes*H0*5*v1*H1*30
  7810. -->
  7811. (S1 ^operator O1913 = 0.7358024669452599)
  7812. Firing prefer*rvt*predict-yes*H0*5*v1*H1
  7813. -->
  7814. Firing elaborate*copy-see-to-output-link
  7815. -->
  7816. (I3 ^see 0 +)
  7817. Firing elaborate*reward*based*on*reward
  7818. -->
  7819. (R961 ^value 1 +)
  7820. (R1 ^reward R961 +)
  7821. Firing propose*predict-yes
  7822. -->
  7823. (O1915 ^name predict-yes +)
  7824. (S1 ^operator O1915 +)
  7825. Firing propose*predict-no
  7826. -->
  7827. (O1916 ^name predict-no +)
  7828. (S1 ^operator O1916 +)
  7829. Firing rl*prefer*rvt*predict-no*H0*6
  7830. -->
  7831. (S1 ^operator O1914 = 0.9996367744406318)
  7832. Firing rl*prefer*rvt*predict-yes*H0*5
  7833. -->
  7834. (S1 ^operator O1913 = 0.2640663414827097)
  7835. Firing prefer*rvt*predict-yes*H0
  7836. -->
  7837. Firing prefer*rvt*predict-no*H0
  7838. -->
  7839. Firing elaborate*copy-dir-to-output-link
  7840. -->
  7841. (I3 ^dir L +)
  7842. inner elaboration loop at bottom goal.
  7843. Retracting elaborate*copy-see-to-output-link
  7844. -->
  7845. (I3 ^see 0 +)
  7846. Retracting propose*predict-no
  7847. -->
  7848. (O1914 ^name predict-no +)
  7849. (S1 ^operator O1914 +)
  7850. Retracting propose*predict-yes
  7851. -->
  7852. (O1913 ^name predict-yes +)
  7853. (S1 ^operator O1913 +)
  7854. Retracting elaborate*reward*based*on*reward
  7855. -->
  7856. (R960 ^value 1 +)
  7857. (R1 ^reward R960 +)
  7858. Retracting elaborate*copy-dir-to-output-link
  7859. -->
  7860. (I3 ^dir R +)
  7861. Retracting rl*prefer*rvt*predict-no*H0*4*v1*H1*39
  7862. -->
  7863. (S1 ^operator O1914 = 0.6601435952544124)
  7864. Retracting rl*prefer*rvt*predict-no*H0*4
  7865. -->
  7866. (S1 ^operator O1914 = 0.3397637965169674)
  7867. Retracting rl*prefer*rvt*predict-yes*H0*3*v1*H1*40
  7868. -->
  7869. (S1 ^operator O1913 = -0.1028953566115423)
  7870. Retracting rl*prefer*rvt*predict-yes*H0*3
  7871. -->
  7872. (S1 ^operator O1913 = 0.3377188564178903)
  7873. =>WM: (13491: S1 ^operator O1916 +)
  7874. =>WM: (13490: S1 ^operator O1915 +)
  7875. =>WM: (13489: I3 ^dir L)
  7876. =>WM: (13488: O1916 ^name predict-no)
  7877. =>WM: (13487: O1915 ^name predict-yes)
  7878. =>WM: (13486: R961 ^value 1)
  7879. =>WM: (13485: R1 ^reward R961)
  7880. <=WM: (13476: S1 ^operator O1913 +)
  7881. <=WM: (13477: S1 ^operator O1914 +)
  7882. <=WM: (13478: S1 ^operator O1914)
  7883. <=WM: (13462: I3 ^dir R)
  7884. <=WM: (13472: R1 ^reward R960)
  7885. <=WM: (13475: O1914 ^name predict-no)
  7886. <=WM: (13474: O1913 ^name predict-yes)
  7887. <=WM: (13473: R960 ^value 1)
  7888. --- Inner Elaboration Phase, active level 1 (S1) ---
  7889. Firing prefer*rvt*predict-yes*H0
  7890. -->
  7891. Firing rl*prefer*rvt*predict-yes*H0*5*v1*H1*30
  7892. -->
  7893. (S1 ^operator O1915 = 0.7358024669452599)
  7894. Firing rl*prefer*rvt*predict-yes*H0*5
  7895. -->
  7896. (S1 ^operator O1915 = 0.2640663414827097)
  7897. Firing prefer*rvt*predict-yes*H0*5*v1*H1
  7898. -->
  7899. Firing prefer*rvt*predict-no*H0
  7900. -->
  7901. Firing rl*prefer*rvt*predict-no*H0*6
  7902. -->
  7903. (S1 ^operator O1916 = 0.9996367744406318)
  7904. inner elaboration loop at bottom goal.
  7905. Retracting rl*prefer*rvt*predict-no*H0*6
  7906. -->
  7907. (S1 ^operator O1914 = 0.9996367744406318)
  7908. Retracting rl*prefer*rvt*predict-yes*H0*5
  7909. -->
  7910. (S1 ^operator O1913 = 0.2640663414827097)
  7911. Retracting rl*prefer*rvt*predict-yes*H0*5*v1*H1*30
  7912. -->
  7913. (S1 ^operator O1913 = 0.7358024669452599)
  7914. --- END Proposal Phase ---
  7915. --- Decision Phase ---
  7916. RL update rl*prefer*rvt*predict-no*H0*4 0.570247 -0.230483 0.339764 -> 0.570255 -0.230484 0.339771(R,m,v=1,0.871951,0.112337)
  7917. RL update rl*prefer*rvt*predict-no*H0*4*v1*H1*39 0.429656 0.230488 0.660144 -> 0.429665 0.230487 0.660152(R,m,v=1,1,0)
  7918. =>WM: (13492: S1 ^operator O1915)
  7919. 958: O: O1915 (predict-yes)
  7920. --- END Decision Phase ---
  7921. --- Application Phase ---
  7922. --- Firing Productions (PE) For State At Depth 1 ---
  7923. --- Inner Elaboration Phase, active level 1 (S1) ---
  7924. Firing apply*operator
  7925. -->
  7926. (I3 ^predict-yes N958 + :O )
  7927. Firing apply*operator*complete
  7928. -->
  7929. (I3 ^predict-no N957 - :O )
  7930. inner elaboration loop at bottom goal.
  7931. --- Change Working Memory (PE) ---
  7932. =>WM: (13493: I3 ^predict-yes N958)
  7933. <=WM: (13480: N957 ^status complete)
  7934. <=WM: (13479: I3 ^predict-no N957)
  7935. --- Firing Productions (IE) For State At Depth 1 ---
  7936. --- Inner Elaboration Phase, active level 1 (S1) ---
  7937. Firing monitor*world
  7938. -->
  7939. I see 1 and I'm going to do: predict-yes inner elaboration loop at bottom goal.
  7940. --- Change Working Memory (IE) ---
  7941. --- END Application Phase ---
  7942. --- Output Phase ---
  7943. ENV: Agent did: predict-yes for direction L in state State-B
  7944. In State-B moving L
  7945. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  7946. predict error 0
  7947. dir: dir isU
  7948. --- END Output Phase ---
  7949. /|\--- Input Phase ---
  7950. =>WM: (13497: I2 ^dir U)
  7951. =>WM: (13496: I2 ^reward 1)
  7952. =>WM: (13495: I2 ^see 1)
  7953. =>WM: (13494: N958 ^status complete)
  7954. <=WM: (13483: I2 ^dir L)
  7955. <=WM: (13482: I2 ^reward 1)
  7956. <=WM: (13481: I2 ^see 0)
  7957. =>WM: (13498: I2 ^level-1 L1-root)
  7958. <=WM: (13484: I2 ^level-1 R0-root)
  7959. --- END Input Phase ---
  7960. --- Proposal Phase ---
  7961. --- Inner Elaboration Phase, active level 1 (S1) ---
  7962. Firing elaborate*copy-see-to-output-link
  7963. -->
  7964. (I3 ^see 1 +)
  7965. Firing elaborate*reward*based*on*reward
  7966. -->
  7967. (R962 ^value 1 +)
  7968. (R1 ^reward R962 +)
  7969. Firing propose*predict-yes
  7970. -->
  7971. (O1917 ^name predict-yes +)
  7972. (S1 ^operator O1917 +)
  7973. Firing propose*predict-no
  7974. -->
  7975. (O1918 ^name predict-no +)
  7976. (S1 ^operator O1918 +)
  7977. Firing rl*prefer*rvt*predict-no*H0*2
  7978. -->
  7979. (S1 ^operator O1916 = 1.)
  7980. Firing rl*prefer*rvt*predict-yes*H0*1
  7981. -->
  7982. (S1 ^operator O1915 = 0.)
  7983. Firing prefer*rvt*predict-yes*H0
  7984. -->
  7985. Firing prefer*rvt*predict-no*H0
  7986. -->
  7987. Firing elaborate*copy-dir-to-output-link
  7988. -->
  7989. (I3 ^dir U +)
  7990. inner elaboration loop at bottom goal.
  7991. Retracting elaborate*copy-see-to-output-link
  7992. -->
  7993. (I3 ^see 0 +)
  7994. Retracting propose*predict-no
  7995. -->
  7996. (O1916 ^name predict-no +)
  7997. (S1 ^operator O1916 +)
  7998. Retracting propose*predict-yes
  7999. -->
  8000. (O1915 ^name predict-yes +)
  8001. (S1 ^operator O1915 +)
  8002. Retracting elaborate*reward*based*on*reward
  8003. -->
  8004. (R961 ^value 1 +)
  8005. (R1 ^reward R961 +)
  8006. Retracting elaborate*copy-dir-to-output-link
  8007. -->
  8008. (I3 ^dir L +)
  8009. Retracting rl*prefer*rvt*predict-no*H0*6
  8010. -->
  8011. (S1 ^operator O1916 = 0.9996367744406318)
  8012. Retracting rl*prefer*rvt*predict-yes*H0*5
  8013. -->
  8014. (S1 ^operator O1915 = 0.2640663414827097)
  8015. Retracting rl*prefer*rvt*predict-yes*H0*5*v1*H1*30
  8016. -->
  8017. (S1 ^operator O1915 = 0.7358024669452599)
  8018. =>WM: (13506: S1 ^operator O1918 +)
  8019. =>WM: (13505: S1 ^operator O1917 +)
  8020. =>WM: (13504: I3 ^dir U)
  8021. =>WM: (13503: O1918 ^name predict-no)
  8022. =>WM: (13502: O1917 ^name predict-yes)
  8023. =>WM: (13501: R962 ^value 1)
  8024. =>WM: (13500: R1 ^reward R962)
  8025. =>WM: (13499: I3 ^see 1)
  8026. <=WM: (13490: S1 ^operator O1915 +)
  8027. <=WM: (13492: S1 ^operator O1915)
  8028. <=WM: (13491: S1 ^operator O1916 +)
  8029. <=WM: (13489: I3 ^dir L)
  8030. <=WM: (13485: R1 ^reward R961)
  8031. <=WM: (13457: I3 ^see 0)
  8032. <=WM: (13488: O1916 ^name predict-no)
  8033. <=WM: (13487: O1915 ^name predict-yes)
  8034. <=WM: (13486: R961 ^value 1)
  8035. --- Inner Elaboration Phase, active level 1 (S1) ---
  8036. Firing prefer*rvt*predict-yes*H0
  8037. -->
  8038. Firing rl*prefer*rvt*predict-yes*H0*1
  8039. -->
  8040. (S1 ^operator O1917 = 0.)
  8041. Firing prefer*rvt*predict-no*H0
  8042. -->
  8043. Firing rl*prefer*rvt*predict-no*H0*2
  8044. -->
  8045. (S1 ^operator O1918 = 1.)
  8046. inner elaboration loop at bottom goal.
  8047. Retracting rl*prefer*rvt*predict-no*H0*2
  8048. -->
  8049. (S1 ^operator O1916 = 1.)
  8050. Retracting rl*prefer*rvt*predict-yes*H0*1
  8051. -->
  8052. (S1 ^operator O1915 = 0.)
  8053. --- END Proposal Phase ---
  8054. --- Decision Phase ---
  8055. RL update rl*prefer*rvt*predict-yes*H0*5 0.554451 -0.290385 0.264066 -> 0.554462 -0.290385 0.264077(R,m,v=1,0.872832,0.111641)
  8056. RL update rl*prefer*rvt*predict-yes*H0*5*v1*H1*30 0.44542 0.290383 0.735802 -> 0.445432 0.290383 0.735815(R,m,v=1,1,0)
  8057. =>WM: (13507: S1 ^operator O1918)
  8058. 959: O: O1918 (predict-no)
  8059. --- END Decision Phase ---
  8060. --- Application Phase ---
  8061. --- Firing Productions (PE) For State At Depth 1 ---
  8062. --- Inner Elaboration Phase, active level 1 (S1) ---
  8063. Firing apply*operator
  8064. -->
  8065. (I3 ^predict-no N959 + :O )
  8066. Firing apply*operator*complete
  8067. -->
  8068. (I3 ^predict-yes N958 - :O )
  8069. inner elaboration loop at bottom goal.
  8070. --- Change Working Memory (PE) ---
  8071. =>WM: (13508: I3 ^predict-no N959)
  8072. <=WM: (13494: N958 ^status complete)
  8073. <=WM: (13493: I3 ^predict-yes N958)
  8074. --- Firing Productions (IE) For State At Depth 1 ---
  8075. --- Inner Elaboration Phase, active level 1 (S1) ---
  8076. Firing monitor*world
  8077. -->
  8078. I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
  8079. --- Change Working Memory (IE) ---
  8080. --- END Application Phase ---
  8081. --- Output Phase ---
  8082. ENV: Agent did: predict-no for direction U in state State-A
  8083. In State-A moving U
  8084. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  8085. predict error 0
  8086. dir: dir isL
  8087. --- END Output Phase ---
  8088. -/--- Input Phase ---
  8089. =>WM: (13512: I2 ^dir L)
  8090. =>WM: (13511: I2 ^reward 1)
  8091. =>WM: (13510: I2 ^see 0)
  8092. =>WM: (13509: N959 ^status complete)
  8093. <=WM: (13497: I2 ^dir U)
  8094. <=WM: (13496: I2 ^reward 1)
  8095. <=WM: (13495: I2 ^see 1)
  8096. =>WM: (13513: I2 ^level-1 L1-root)
  8097. <=WM: (13498: I2 ^level-1 L1-root)
  8098. --- END Input Phase ---
  8099. --- Proposal Phase ---
  8100. --- Inner Elaboration Phase, active level 1 (S1) ---
  8101. Firing rl*prefer*rvt*predict-yes*H0*5*v1*H1*31
  8102. -->
  8103. (S1 ^operator O1917 = -0.181727099742844)
  8104. Firing prefer*rvt*predict-yes*H0*5*v1*H1
  8105. -->
  8106. Firing elaborate*copy-see-to-output-link
  8107. -->
  8108. (I3 ^see 0 +)
  8109. Firing elaborate*reward*based*on*reward
  8110. -->
  8111. (R963 ^value 1 +)
  8112. (R1 ^reward R963 +)
  8113. Firing propose*predict-yes
  8114. -->
  8115. (O1919 ^name predict-yes +)
  8116. (S1 ^operator O1919 +)
  8117. Firing propose*predict-no
  8118. -->
  8119. (O1920 ^name predict-no +)
  8120. (S1 ^operator O1920 +)
  8121. Firing rl*prefer*rvt*predict-no*H0*6
  8122. -->
  8123. (S1 ^operator O1918 = 0.9996367744406318)
  8124. Firing rl*prefer*rvt*predict-yes*H0*5
  8125. -->
  8126. (S1 ^operator O1917 = 0.2640770017585976)
  8127. Firing prefer*rvt*predict-yes*H0
  8128. -->
  8129. Firing prefer*rvt*predict-no*H0
  8130. -->
  8131. Firing elaborate*copy-dir-to-output-link
  8132. -->
  8133. (I3 ^dir L +)
  8134. inner elaboration loop at bottom goal.
  8135. Retracting elaborate*copy-see-to-output-link
  8136. -->
  8137. (I3 ^see 1 +)
  8138. Retracting propose*predict-no
  8139. -->
  8140. (O1918 ^name predict-no +)
  8141. (S1 ^operator O1918 +)
  8142. Retracting propose*predict-yes
  8143. -->
  8144. (O1917 ^name predict-yes +)
  8145. (S1 ^operator O1917 +)
  8146. Retracting elaborate*reward*based*on*reward
  8147. -->
  8148. (R962 ^value 1 +)
  8149. (R1 ^reward R962 +)
  8150. Retracting elaborate*copy-dir-to-output-link
  8151. -->
  8152. (I3 ^dir U +)
  8153. Retracting rl*prefer*rvt*predict-no*H0*2
  8154. -->
  8155. (S1 ^operator O1918 = 1.)
  8156. Retracting rl*prefer*rvt*predict-yes*H0*1
  8157. -->
  8158. (S1 ^operator O1917 = 0.)
  8159. =>WM: (13521: S1 ^operator O1920 +)
  8160. =>WM: (13520: S1 ^operator O1919 +)
  8161. =>WM: (13519: I3 ^dir L)
  8162. =>WM: (13518: O1920 ^name predict-no)
  8163. =>WM: (13517: O1919 ^name predict-yes)
  8164. =>WM: (13516: R963 ^value 1)
  8165. =>WM: (13515: R1 ^reward R963)
  8166. =>WM: (13514: I3 ^see 0)
  8167. <=WM: (13505: S1 ^operator O1917 +)
  8168. <=WM: (13506: S1 ^operator O1918 +)
  8169. <=WM: (13507: S1 ^operator O1918)
  8170. <=WM: (13504: I3 ^dir U)
  8171. <=WM: (13500: R1 ^reward R962)
  8172. <=WM: (13499: I3 ^see 1)
  8173. <=WM: (13503: O1918 ^name predict-no)
  8174. <=WM: (13502: O1917 ^name predict-yes)
  8175. <=WM: (13501: R962 ^value 1)
  8176. --- Inner Elaboration Phase, active level 1 (S1) ---
  8177. Firing prefer*rvt*predict-yes*H0
  8178. -->
  8179. Firing rl*prefer*rvt*predict-yes*H0*5*v1*H1*31
  8180. -->
  8181. (S1 ^operator O1919 = -0.181727099742844)
  8182. Firing rl*prefer*rvt*predict-yes*H0*5
  8183. -->
  8184. (S1 ^operator O1919 = 0.2640770017585976)
  8185. Firing prefer*rvt*predict-yes*H0*5*v1*H1
  8186. -->
  8187. Firing prefer*rvt*predict-no*H0
  8188. -->
  8189. Firing rl*prefer*rvt*predict-no*H0*6
  8190. -->
  8191. (S1 ^operator O1920 = 0.9996367744406318)
  8192. inner elaboration loop at bottom goal.
  8193. Retracting rl*prefer*rvt*predict-no*H0*6
  8194. -->
  8195. (S1 ^operator O1918 = 0.9996367744406318)
  8196. Retracting rl*prefer*rvt*predict-yes*H0*5
  8197. -->
  8198. (S1 ^operator O1917 = 0.2640770017585976)
  8199. Retracting rl*prefer*rvt*predict-yes*H0*5*v1*H1*31
  8200. -->
  8201. (S1 ^operator O1917 = -0.181727099742844)
  8202. --- END Proposal Phase ---
  8203. --- Decision Phase ---
  8204. RL update rl*prefer*rvt*predict-no*H0*2 1 0 1 -> 1 0 1(R,m,v=1,1,0)
  8205. =>WM: (13522: S1 ^operator O1920)
  8206. 960: O: O1920 (predict-no)
  8207. --- END Decision Phase ---
  8208. --- Application Phase ---
  8209. --- Firing Productions (PE) For State At Depth 1 ---
  8210. --- Inner Elaboration Phase, active level 1 (S1) ---
  8211. Firing apply*operator
  8212. -->
  8213. (I3 ^predict-no N960 + :O )
  8214. Firing apply*operator*complete
  8215. -->
  8216. (I3 ^predict-no N959 - :O )
  8217. inner elaboration loop at bottom goal.
  8218. --- Change Working Memory (PE) ---
  8219. =>WM: (13523: I3 ^predict-no N960)
  8220. <=WM: (13509: N959 ^status complete)
  8221. <=WM: (13508: I3 ^predict-no N959)
  8222. --- Firing Productions (IE) For State At Depth 1 ---
  8223. --- Inner Elaboration Phase, active level 1 (S1) ---
  8224. Firing monitor*world
  8225. -->
  8226. I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
  8227. --- Change Working Memory (IE) ---
  8228. --- END Application Phase ---
  8229. --- Output Phase ---
  8230. ENV: Agent did: predict-no for direction L in state State-A
  8231. In State-A moving L
  8232. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  8233. predict error 0
  8234. dir: dir isU
  8235. --- END Output Phase ---
  8236. |\---- Input Phase ---
  8237. =>WM: (13527: I2 ^dir U)
  8238. =>WM: (13526: I2 ^reward 1)
  8239. =>WM: (13525: I2 ^see 0)
  8240. =>WM: (13524: N960 ^status complete)
  8241. <=WM: (13512: I2 ^dir L)
  8242. <=WM: (13511: I2 ^reward 1)
  8243. <=WM: (13510: I2 ^see 0)
  8244. =>WM: (13528: I2 ^level-1 L0-root)
  8245. <=WM: (13513: I2 ^level-1 L1-root)
  8246. --- END Input Phase ---
  8247. --- Proposal Phase ---
  8248. --- Inner Elaboration Phase, active level 1 (S1) ---
  8249. Firing elaborate*copy-see-to-output-link
  8250. -->
  8251. (I3 ^see 0 +)
  8252. Firing elaborate*reward*based*on*reward
  8253. -->
  8254. (R964 ^value 1 +)
  8255. (R1 ^reward R964 +)
  8256. Firing propose*predict-yes
  8257. -->
  8258. (O1921 ^name predict-yes +)
  8259. (S1 ^operator O1921 +)
  8260. Firing propose*predict-no
  8261. -->
  8262. (O1922 ^name predict-no +)
  8263. (S1 ^operator O1922 +)
  8264. Firing rl*prefer*rvt*predict-no*H0*2
  8265. -->
  8266. (S1 ^operator O1920 = 1.)
  8267. Firing rl*prefer*rvt*predict-yes*H0*1
  8268. -->
  8269. (S1 ^operator O1919 = 0.)
  8270. Firing prefer*rvt*predict-yes*H0
  8271. -->
  8272. Firing prefer*rvt*predict-no*H0
  8273. -->
  8274. Firing elaborate*copy-dir-to-output-link
  8275. -->
  8276. (I3 ^dir U +)
  8277. inner elaboration loop at bottom goal.
  8278. Retracting elaborate*copy-see-to-output-link
  8279. -->
  8280. (I3 ^see 0 +)
  8281. Retracting propose*predict-no
  8282. -->
  8283. (O1920 ^name predict-no +)
  8284. (S1 ^operator O1920 +)
  8285. Retracting propose*predict-yes
  8286. -->
  8287. (O1919 ^name predict-yes +)
  8288. (S1 ^operator O1919 +)
  8289. Retracting elaborate*reward*based*on*reward
  8290. -->
  8291. (R963 ^value 1 +)
  8292. (R1 ^reward R963 +)
  8293. Retracting elaborate*copy-dir-to-output-link
  8294. -->
  8295. (I3 ^dir L +)
  8296. Retracting rl*prefer*rvt*predict-no*H0*6
  8297. -->
  8298. (S1 ^operator O1920 = 0.9996367744406318)
  8299. Retracting rl*prefer*rvt*predict-yes*H0*5
  8300. -->
  8301. (S1 ^operator O1919 = 0.2640770017585976)
  8302. Retracting rl*prefer*rvt*predict-yes*H0*5*v1*H1*31
  8303. -->
  8304. (S1 ^operator O1919 = -0.181727099742844)
  8305. =>WM: (13535: S1 ^operator O1922 +)
  8306. =>WM: (13534: S1 ^operator O1921 +)
  8307. =>WM: (13533: I3 ^dir U)
  8308. =>WM: (13532: O1922 ^name predict-no)
  8309. =>WM: (13531: O1921 ^name predict-yes)
  8310. =>WM: (13530: R964 ^value 1)
  8311. =>WM: (13529: R1 ^reward R964)
  8312. <=WM: (13520: S1 ^operator O1919 +)
  8313. <=WM: (13521: S1 ^operator O1920 +)
  8314. <=WM: (13522: S1 ^operator O1920)
  8315. <=WM: (13519: I3 ^dir L)
  8316. <=WM: (13515: R1 ^reward R963)
  8317. <=WM: (13518: O1920 ^name predict-no)
  8318. <=WM: (13517: O1919 ^name predict-yes)
  8319. <=WM: (13516: R963 ^value 1)
  8320. --- Inner Elaboration Phase, active level 1 (S1) ---
  8321. Firing prefer*rvt*predict-yes*H0
  8322. -->
  8323. Firing rl*prefer*rvt*predict-yes*H0*1
  8324. -->
  8325. (S1 ^operator O1921 = 0.)
  8326. Firing prefer*rvt*predict-no*H0
  8327. -->
  8328. Firing rl*prefer*rvt*predict-no*H0*2
  8329. -->
  8330. (S1 ^operator O1922 = 1.)
  8331. inner elaboration loop at bottom goal.
  8332. Retracting rl*prefer*rvt*predict-no*H0*2
  8333. -->
  8334. (S1 ^operator O1920 = 1.)
  8335. Retracting rl*prefer*rvt*predict-yes*H0*1
  8336. -->
  8337. (S1 ^operator O1919 = 0.)
  8338. --- END Proposal Phase ---
  8339. --- Decision Phase ---
  8340. RL update rl*prefer*rvt*predict-no*H0*6 0.999637 0 0.999637 -> 0.999698 0 0.999698(R,m,v=1,0.903448,0.0878352)
  8341. =>WM: (13536: S1 ^operator O1922)
  8342. 961: O: O1922 (predict-no)
  8343. --- END Decision Phase ---
  8344. --- Application Phase ---
  8345. --- Firing Productions (PE) For State At Depth 1 ---
  8346. --- Inner Elaboration Phase, active level 1 (S1) ---
  8347. Firing apply*operator
  8348. -->
  8349. (I3 ^predict-no N961 + :O )
  8350. Firing apply*operator*complete
  8351. -->
  8352. (I3 ^predict-no N960 - :O )
  8353. inner elaboration loop at bottom goal.
  8354. --- Change Working Memory (PE) ---
  8355. =>WM: (13537: I3 ^predict-no N961)
  8356. <=WM: (13524: N960 ^status complete)
  8357. <=WM: (13523: I3 ^predict-no N960)
  8358. --- Firing Productions (IE) For State At Depth 1 ---
  8359. --- Inner Elaboration Phase, active level 1 (S1) ---
  8360. Firing monitor*world
  8361. -->
  8362. I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
  8363. --- Change Working Memory (IE) ---
  8364. --- END Application Phase ---
  8365. --- Output Phase ---
  8366. ENV: Agent did: predict-no for direction U in state State-A
  8367. In State-A moving U
  8368. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  8369. predict error 0
  8370. dir: dir isR
  8371. --- END Output Phase ---
  8372. /--- Input Phase ---
  8373. =>WM: (13541: I2 ^dir R)
  8374. =>WM: (13540: I2 ^reward 1)
  8375. =>WM: (13539: I2 ^see 0)
  8376. =>WM: (13538: N961 ^status complete)
  8377. <=WM: (13527: I2 ^dir U)
  8378. <=WM: (13526: I2 ^reward 1)
  8379. <=WM: (13525: I2 ^see 0)
  8380. =>WM: (13542: I2 ^level-1 L0-root)
  8381. <=WM: (13528: I2 ^level-1 L0-root)
  8382. --- END Input Phase ---
  8383. --- Proposal Phase ---
  8384. --- Inner Elaboration Phase, active level 1 (S1) ---
  8385. Firing rl*prefer*rvt*predict-no*H0*4*v1*H1*33
  8386. -->
  8387. (S1 ^operator O1922 = -0.2817060109291377)
  8388. Firing rl*prefer*rvt*predict-yes*H0*3*v1*H1*34
  8389. -->
  8390. (S1 ^operator O1921 = 0.6623767743575877)
  8391. Firing prefer*rvt*predict-no*H0*4*v1*H1
  8392. -->
  8393. Firing prefer*rvt*predict-yes*H0*3*v1*H1
  8394. -->
  8395. Firing elaborate*copy-see-to-output-link
  8396. -->
  8397. (I3 ^see 0 +)
  8398. Firing elaborate*reward*based*on*reward
  8399. -->
  8400. (R965 ^value 1 +)
  8401. (R1 ^reward R965 +)
  8402. Firing propose*predict-yes
  8403. -->
  8404. (O1923 ^name predict-yes +)
  8405. (S1 ^operator O1923 +)
  8406. Firing propose*predict-no
  8407. -->
  8408. (O1924 ^name predict-no +)
  8409. (S1 ^operator O1924 +)
  8410. Firing rl*prefer*rvt*predict-no*H0*4
  8411. -->
  8412. (S1 ^operator O1922 = 0.3397713875215998)
  8413. Firing rl*prefer*rvt*predict-yes*H0*3
  8414. -->
  8415. (S1 ^operator O1921 = 0.3377188564178903)
  8416. Firing prefer*rvt*predict-yes*H0
  8417. -->
  8418. Firing prefer*rvt*predict-no*H0
  8419. -->
  8420. Firing elaborate*copy-dir-to-output-link
  8421. -->
  8422. (I3 ^dir R +)
  8423. inner elaboration loop at bottom goal.
  8424. Retracting elaborate*copy-see-to-output-link
  8425. -->
  8426. (I3 ^see 0 +)
  8427. Retracting propose*predict-no
  8428. -->
  8429. (O1922 ^name predict-no +)
  8430. (S1 ^operator O1922 +)
  8431. Retracting propose*predict-yes
  8432. -->
  8433. (O1921 ^name predict-yes +)
  8434. (S1 ^operator O1921 +)
  8435. Retracting elaborate*reward*based*on*reward
  8436. -->
  8437. (R964 ^value 1 +)
  8438. (R1 ^reward R964 +)
  8439. Retracting elaborate*copy-dir-to-output-link
  8440. -->
  8441. (I3 ^dir U +)
  8442. Retracting rl*prefer*rvt*predict-no*H0*2
  8443. -->
  8444. (S1 ^operator O1922 = 1.)
  8445. Retracting rl*prefer*rvt*predict-yes*H0*1
  8446. -->
  8447. (S1 ^operator O1921 = 0.)
  8448. =>WM: (13549: S1 ^operator O1924 +)
  8449. =>WM: (13548: S1 ^operator O1923 +)
  8450. =>WM: (13547: I3 ^dir R)
  8451. =>WM: (13546: O1924 ^name predict-no)
  8452. =>WM: (13545: O1923 ^name predict-yes)
  8453. =>WM: (13544: R965 ^value 1)
  8454. =>WM: (13543: R1 ^reward R965)
  8455. <=WM: (13534: S1 ^operator O1921 +)
  8456. <=WM: (13535: S1 ^operator O1922 +)
  8457. <=WM: (13536: S1 ^operator O1922)
  8458. <=WM: (13533: I3 ^dir U)
  8459. <=WM: (13529: R1 ^reward R964)
  8460. <=WM: (13532: O1922 ^name predict-no)
  8461. <=WM: (13531: O1921 ^name predict-yes)
  8462. <=WM: (13530: R964 ^value 1)
  8463. --- Inner Elaboration Phase, active level 1 (S1) ---
  8464. Firing prefer*rvt*predict-yes*H0
  8465. -->
  8466. Firing rl*prefer*rvt*predict-yes*H0*3*v1*H1*34
  8467. -->
  8468. (S1 ^operator O1923 = 0.6623767743575877)
  8469. Firing rl*prefer*rvt*predict-yes*H0*3
  8470. -->
  8471. (S1 ^operator O1923 = 0.3377188564178903)
  8472. Firing prefer*rvt*predict-yes*H0*3*v1*H1
  8473. -->
  8474. Firing prefer*rvt*predict-no*H0
  8475. -->
  8476. Firing rl*prefer*rvt*predict-no*H0*4*v1*H1*33
  8477. -->
  8478. (S1 ^operator O1924 = -0.2817060109291377)
  8479. Firing rl*prefer*rvt*predict-no*H0*4
  8480. -->
  8481. (S1 ^operator O1924 = 0.3397713875215998)
  8482. Firing prefer*rvt*predict-no*H0*4*v1*H1
  8483. -->
  8484. inner elaboration loop at bottom goal.
  8485. Retracting rl*prefer*rvt*predict-no*H0*4
  8486. -->
  8487. (S1 ^operator O1922 = 0.3397713875215998)
  8488. Retracting rl*prefer*rvt*predict-no*H0*4*v1*H1*33
  8489. -->
  8490. (S1 ^operator O1922 = -0.2817060109291377)
  8491. Retracting rl*prefer*rvt*predict-yes*H0*3
  8492. -->
  8493. (S1 ^operator O1921 = 0.3377188564178903)
  8494. Retracting rl*prefer*rvt*predict-yes*H0*3*v1*H1*34
  8495. -->
  8496. (S1 ^operator O1921 = 0.6623767743575877)
  8497. --- END Proposal Phase ---
  8498. --- Decision Phase ---
  8499. RL update rl*prefer*rvt*predict-no*H0*2 1 0 1 -> 1 0 1(R,m,v=1,1,0)
  8500. =>WM: (13550: S1 ^operator O1923)
  8501. 962: O: O1923 (predict-yes)
  8502. --- END Decision Phase ---
  8503. --- Application Phase ---
  8504. --- Firing Productions (PE) For State At Depth 1 ---
  8505. --- Inner Elaboration Phase, active level 1 (S1) ---
  8506. Firing apply*operator
  8507. -->
  8508. (I3 ^predict-yes N962 + :O )
  8509. Firing apply*operator*complete
  8510. -->
  8511. (I3 ^predict-no N961 - :O )
  8512. inner elaboration loop at bottom goal.
  8513. --- Change Working Memory (PE) ---
  8514. =>WM: (13551: I3 ^predict-yes N962)
  8515. <=WM: (13538: N961 ^status complete)
  8516. <=WM: (13537: I3 ^predict-no N961)
  8517. --- Firing Productions (IE) For State At Depth 1 ---
  8518. --- Inner Elaboration Phase, active level 1 (S1) ---
  8519. Firing monitor*world
  8520. -->
  8521. I see 1 and I'm going to do: predict-yes inner elaboration loop at bottom goal.
  8522. --- Change Working Memory (IE) ---
  8523. --- END Application Phase ---
  8524. --- Output Phase ---
  8525. ENV: Agent did: predict-yes for direction R in state State-A
  8526. In State-A moving R
  8527. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  8528. predict error 0
  8529. dir: dir isU
  8530. --- END Output Phase ---
  8531. |\--- Input Phase ---
  8532. =>WM: (13555: I2 ^dir U)
  8533. =>WM: (13554: I2 ^reward 1)
  8534. =>WM: (13553: I2 ^see 1)
  8535. =>WM: (13552: N962 ^status complete)
  8536. <=WM: (13541: I2 ^dir R)
  8537. <=WM: (13540: I2 ^reward 1)
  8538. <=WM: (13539: I2 ^see 0)
  8539. =>WM: (13556: I2 ^level-1 R1-root)
  8540. <=WM: (13542: I2 ^level-1 L0-root)
  8541. --- END Input Phase ---
  8542. --- Proposal Phase ---
  8543. --- Inner Elaboration Phase, active level 1 (S1) ---
  8544. Firing elaborate*copy-see-to-output-link
  8545. -->
  8546. (I3 ^see 1 +)
  8547. Firing elaborate*reward*based*on*reward
  8548. -->
  8549. (R966 ^value 1 +)
  8550. (R1 ^reward R966 +)
  8551. Firing propose*predict-yes
  8552. -->
  8553. (O1925 ^name predict-yes +)
  8554. (S1 ^operator O1925 +)
  8555. Firing propose*predict-no
  8556. -->
  8557. (O1926 ^name predict-no +)
  8558. (S1 ^operator O1926 +)
  8559. Firing rl*prefer*rvt*predict-no*H0*2
  8560. -->
  8561. (S1 ^operator O1924 = 1.)
  8562. Firing rl*prefer*rvt*predict-yes*H0*1
  8563. -->
  8564. (S1 ^operator O1923 = 0.)
  8565. Firing prefer*rvt*predict-yes*H0
  8566. -->
  8567. Firing prefer*rvt*predict-no*H0
  8568. -->
  8569. Firing elaborate*copy-dir-to-output-link
  8570. -->
  8571. (I3 ^dir U +)
  8572. inner elaboration loop at bottom goal.
  8573. Retracting elaborate*copy-see-to-output-link
  8574. -->
  8575. (I3 ^see 0 +)
  8576. Retracting propose*predict-no
  8577. -->
  8578. (O1924 ^name predict-no +)
  8579. (S1 ^operator O1924 +)
  8580. Retracting propose*predict-yes
  8581. -->
  8582. (O1923 ^name predict-yes +)
  8583. (S1 ^operator O1923 +)
  8584. Retracting elaborate*reward*based*on*reward
  8585. -->
  8586. (R965 ^value 1 +)
  8587. (R1 ^reward R965 +)
  8588. Retracting elaborate*copy-dir-to-output-link
  8589. -->
  8590. (I3 ^dir R +)
  8591. Retracting rl*prefer*rvt*predict-no*H0*4
  8592. -->
  8593. (S1 ^operator O1924 = 0.3397713875215998)
  8594. Retracting rl*prefer*rvt*predict-no*H0*4*v1*H1*33
  8595. -->
  8596. (S1 ^operator O1924 = -0.2817060109291377)
  8597. Retracting rl*prefer*rvt*predict-yes*H0*3
  8598. -->
  8599. (S1 ^operator O1923 = 0.3377188564178903)
  8600. Retracting rl*prefer*rvt*predict-yes*H0*3*v1*H1*34
  8601. -->
  8602. (S1 ^operator O1923 = 0.6623767743575877)
  8603. =>WM: (13564: S1 ^operator O1926 +)
  8604. =>WM: (13563: S1 ^operator O1925 +)
  8605. =>WM: (13562: I3 ^dir U)
  8606. =>WM: (13561: O1926 ^name predict-no)
  8607. =>WM: (13560: O1925 ^name predict-yes)
  8608. =>WM: (13559: R966 ^value 1)
  8609. =>WM: (13558: R1 ^reward R966)
  8610. =>WM: (13557: I3 ^see 1)
  8611. <=WM: (13548: S1 ^operator O1923 +)
  8612. <=WM: (13550: S1 ^operator O1923)
  8613. <=WM: (13549: S1 ^operator O1924 +)
  8614. <=WM: (13547: I3 ^dir R)
  8615. <=WM: (13543: R1 ^reward R965)
  8616. <=WM: (13514: I3 ^see 0)
  8617. <=WM: (13546: O1924 ^name predict-no)
  8618. <=WM: (13545: O1923 ^name predict-yes)
  8619. <=WM: (13544: R965 ^value 1)
  8620. --- Inner Elaboration Phase, active level 1 (S1) ---
  8621. Firing prefer*rvt*predict-yes*H0
  8622. -->
  8623. Firing rl*prefer*rvt*predict-yes*H0*1
  8624. -->
  8625. (S1 ^operator O1925 = 0.)
  8626. Firing prefer*rvt*predict-no*H0
  8627. -->
  8628. Firing rl*prefer*rvt*predict-no*H0*2
  8629. -->
  8630. (S1 ^operator O1926 = 1.)
  8631. inner elaboration loop at bottom goal.
  8632. Retracting rl*prefer*rvt*predict-no*H0*2
  8633. -->
  8634. (S1 ^operator O1924 = 1.)
  8635. Retracting rl*prefer*rvt*predict-yes*H0*1
  8636. -->
  8637. (S1 ^operator O1923 = 0.)
  8638. --- END Proposal Phase ---
  8639. --- Decision Phase ---
  8640. RL update rl*prefer*rvt*predict-yes*H0*3 0.59012 -0.252401 0.337719 -> 0.590111 -0.2524 0.337711(R,m,v=1,0.895062,0.0945096)
  8641. RL update rl*prefer*rvt*predict-yes*H0*3*v1*H1*34 0.40999 0.252387 0.662377 -> 0.409979 0.252388 0.662368(R,m,v=1,1,0)
  8642. =>WM: (13565: S1 ^operator O1926)
  8643. 963: O: O1926 (predict-no)
  8644. --- END Decision Phase ---
  8645. --- Application Phase ---
  8646. --- Firing Productions (PE) For State At Depth 1 ---
  8647. --- Inner Elaboration Phase, active level 1 (S1) ---
  8648. Firing apply*operator
  8649. -->
  8650. (I3 ^predict-no N963 + :O )
  8651. Firing apply*operator*complete
  8652. -->
  8653. (I3 ^predict-yes N962 - :O )
  8654. inner elaboration loop at bottom goal.
  8655. --- Change Working Memory (PE) ---
  8656. =>WM: (13566: I3 ^predict-no N963)
  8657. <=WM: (13552: N962 ^status complete)
  8658. <=WM: (13551: I3 ^predict-yes N962)
  8659. --- Firing Productions (IE) For State At Depth 1 ---
  8660. --- Inner Elaboration Phase, active level 1 (S1) ---
  8661. Firing monitor*world
  8662. -->
  8663. I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
  8664. --- Change Working Memory (IE) ---
  8665. --- END Application Phase ---
  8666. --- Output Phase ---
  8667. ENV: Agent did: predict-no for direction U in state State-B
  8668. In State-B moving U
  8669. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  8670. predict error 0
  8671. dir: dir isL
  8672. --- END Output Phase ---
  8673. -/|--- Input Phase ---
  8674. =>WM: (13570: I2 ^dir L)
  8675. =>WM: (13569: I2 ^reward 1)
  8676. =>WM: (13568: I2 ^see 0)
  8677. =>WM: (13567: N963 ^status complete)
  8678. <=WM: (13555: I2 ^dir U)
  8679. <=WM: (13554: I2 ^reward 1)
  8680. <=WM: (13553: I2 ^see 1)
  8681. =>WM: (13571: I2 ^level-1 R1-root)
  8682. <=WM: (13556: I2 ^level-1 R1-root)
  8683. --- END Input Phase ---
  8684. --- Proposal Phase ---
  8685. --- Inner Elaboration Phase, active level 1 (S1) ---
  8686. Firing rl*prefer*rvt*predict-yes*H0*5*v1*H1*41
  8687. -->
  8688. (S1 ^operator O1925 = 0.7363235474336447)
  8689. Firing prefer*rvt*predict-yes*H0*5*v1*H1
  8690. -->
  8691. Firing elaborate*copy-see-to-output-link
  8692. -->
  8693. (I3 ^see 0 +)
  8694. Firing elaborate*reward*based*on*reward
  8695. -->
  8696. (R967 ^value 1 +)
  8697. (R1 ^reward R967 +)
  8698. Firing propose*predict-yes
  8699. -->
  8700. (O1927 ^name predict-yes +)
  8701. (S1 ^operator O1927 +)
  8702. Firing propose*predict-no
  8703. -->
  8704. (O1928 ^name predict-no +)
  8705. (S1 ^operator O1928 +)
  8706. Firing rl*prefer*rvt*predict-no*H0*6
  8707. -->
  8708. (S1 ^operator O1926 = 0.9996975476948911)
  8709. Firing rl*prefer*rvt*predict-yes*H0*5
  8710. -->
  8711. (S1 ^operator O1925 = 0.2640770017585976)
  8712. Firing prefer*rvt*predict-yes*H0
  8713. -->
  8714. Firing prefer*rvt*predict-no*H0
  8715. -->
  8716. Firing elaborate*copy-dir-to-output-link
  8717. -->
  8718. (I3 ^dir L +)
  8719. inner elaboration loop at bottom goal.
  8720. Retracting elaborate*copy-see-to-output-link
  8721. -->
  8722. (I3 ^see 1 +)
  8723. Retracting propose*predict-no
  8724. -->
  8725. (O1926 ^name predict-no +)
  8726. (S1 ^operator O1926 +)
  8727. Retracting propose*predict-yes
  8728. -->
  8729. (O1925 ^name predict-yes +)
  8730. (S1 ^operator O1925 +)
  8731. Retracting elaborate*reward*based*on*reward
  8732. -->
  8733. (R966 ^value 1 +)
  8734. (R1 ^reward R966 +)
  8735. Retracting elaborate*copy-dir-to-output-link
  8736. -->
  8737. (I3 ^dir U +)
  8738. Retracting rl*prefer*rvt*predict-no*H0*2
  8739. -->
  8740. (S1 ^operator O1926 = 1.)
  8741. Retracting rl*prefer*rvt*predict-yes*H0*1
  8742. -->
  8743. (S1 ^operator O1925 = 0.)
  8744. =>WM: (13579: S1 ^operator O1928 +)
  8745. =>WM: (13578: S1 ^operator O1927 +)
  8746. =>WM: (13577: I3 ^dir L)
  8747. =>WM: (13576: O1928 ^name predict-no)
  8748. =>WM: (13575: O1927 ^name predict-yes)
  8749. =>WM: (13574: R967 ^value 1)
  8750. =>WM: (13573: R1 ^reward R967)
  8751. =>WM: (13572: I3 ^see 0)
  8752. <=WM: (13563: S1 ^operator O1925 +)
  8753. <=WM: (13564: S1 ^operator O1926 +)
  8754. <=WM: (13565: S1 ^operator O1926)
  8755. <=WM: (13562: I3 ^dir U)
  8756. <=WM: (13558: R1 ^reward R966)
  8757. <=WM: (13557: I3 ^see 1)
  8758. <=WM: (13561: O1926 ^name predict-no)
  8759. <=WM: (13560: O1925 ^name predict-yes)
  8760. <=WM: (13559: R966 ^value 1)
  8761. --- Inner Elaboration Phase, active level 1 (S1) ---
  8762. Firing prefer*rvt*predict-yes*H0
  8763. -->
  8764. Firing rl*prefer*rvt*predict-yes*H0*5*v1*H1*41
  8765. -->
  8766. (S1 ^operator O1927 = 0.7363235474336447)
  8767. Firing rl*prefer*rvt*predict-yes*H0*5
  8768. -->
  8769. (S1 ^operator O1927 = 0.2640770017585976)
  8770. Firing prefer*rvt*predict-yes*H0*5*v1*H1
  8771. -->
  8772. Firing prefer*rvt*predict-no*H0
  8773. -->
  8774. Firing rl*prefer*rvt*predict-no*H0*6
  8775. -->
  8776. (S1 ^operator O1928 = 0.9996975476948911)
  8777. inner elaboration loop at bottom goal.
  8778. Retracting rl*prefer*rvt*predict-no*H0*6
  8779. -->
  8780. (S1 ^operator O1926 = 0.9996975476948911)
  8781. Retracting rl*prefer*rvt*predict-yes*H0*5
  8782. -->
  8783. (S1 ^operator O1925 = 0.2640770017585976)
  8784. Retracting rl*prefer*rvt*predict-yes*H0*5*v1*H1*41
  8785. -->
  8786. (S1 ^operator O1925 = 0.7363235474336447)
  8787. --- END Proposal Phase ---
  8788. --- Decision Phase ---
  8789. RL update rl*prefer*rvt*predict-no*H0*2 1 0 1 -> 1 0 1(R,m,v=1,1,0)
  8790. =>WM: (13580: S1 ^operator O1927)
  8791. 964: O: O1927 (predict-yes)
  8792. --- END Decision Phase ---
  8793. --- Application Phase ---
  8794. --- Firing Productions (PE) For State At Depth 1 ---
  8795. --- Inner Elaboration Phase, active level 1 (S1) ---
  8796. Firing apply*operator
  8797. -->
  8798. (I3 ^predict-yes N964 + :O )
  8799. Firing apply*operator*complete
  8800. -->
  8801. (I3 ^predict-no N963 - :O )
  8802. inner elaboration loop at bottom goal.
  8803. --- Change Working Memory (PE) ---
  8804. =>WM: (13581: I3 ^predict-yes N964)
  8805. <=WM: (13567: N963 ^status complete)
  8806. <=WM: (13566: I3 ^predict-no N963)
  8807. --- Firing Productions (IE) For State At Depth 1 ---
  8808. --- Inner Elaboration Phase, active level 1 (S1) ---
  8809. Firing monitor*world
  8810. -->
  8811. I see 1 and I'm going to do: predict-yes inner elaboration loop at bottom goal.
  8812. --- Change Working Memory (IE) ---
  8813. --- END Application Phase ---
  8814. --- Output Phase ---
  8815. ENV: Agent did: predict-yes for direction L in state State-B
  8816. In State-B moving L
  8817. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  8818. predict error 0
  8819. dir: dir isU
  8820. --- END Output Phase ---
  8821. \-/--- Input Phase ---
  8822. =>WM: (13585: I2 ^dir U)
  8823. =>WM: (13584: I2 ^reward 1)
  8824. =>WM: (13583: I2 ^see 1)
  8825. =>WM: (13582: N964 ^status complete)
  8826. <=WM: (13570: I2 ^dir L)
  8827. <=WM: (13569: I2 ^reward 1)
  8828. <=WM: (13568: I2 ^see 0)
  8829. =>WM: (13586: I2 ^level-1 L1-root)
  8830. <=WM: (13571: I2 ^level-1 R1-root)
  8831. --- END Input Phase ---
  8832. --- Proposal Phase ---
  8833. --- Inner Elaboration Phase, active level 1 (S1) ---
  8834. Firing elaborate*copy-see-to-output-link
  8835. -->
  8836. (I3 ^see 1 +)
  8837. Firing elaborate*reward*based*on*reward
  8838. -->
  8839. (R968 ^value 1 +)
  8840. (R1 ^reward R968 +)
  8841. Firing propose*predict-yes
  8842. -->
  8843. (O1929 ^name predict-yes +)
  8844. (S1 ^operator O1929 +)
  8845. Firing propose*predict-no
  8846. -->
  8847. (O1930 ^name predict-no +)
  8848. (S1 ^operator O1930 +)
  8849. Firing rl*prefer*rvt*predict-no*H0*2
  8850. -->
  8851. (S1 ^operator O1928 = 1.)
  8852. Firing rl*prefer*rvt*predict-yes*H0*1
  8853. -->
  8854. (S1 ^operator O1927 = 0.)
  8855. Firing prefer*rvt*predict-yes*H0
  8856. -->
  8857. Firing prefer*rvt*predict-no*H0
  8858. -->
  8859. Firing elaborate*copy-dir-to-output-link
  8860. -->
  8861. (I3 ^dir U +)
  8862. inner elaboration loop at bottom goal.
  8863. Retracting elaborate*copy-see-to-output-link
  8864. -->
  8865. (I3 ^see 0 +)
  8866. Retracting propose*predict-no
  8867. -->
  8868. (O1928 ^name predict-no +)
  8869. (S1 ^operator O1928 +)
  8870. Retracting propose*predict-yes
  8871. -->
  8872. (O1927 ^name predict-yes +)
  8873. (S1 ^operator O1927 +)
  8874. Retracting elaborate*reward*based*on*reward
  8875. -->
  8876. (R967 ^value 1 +)
  8877. (R1 ^reward R967 +)
  8878. Retracting elaborate*copy-dir-to-output-link
  8879. -->
  8880. (I3 ^dir L +)
  8881. Retracting rl*prefer*rvt*predict-no*H0*6
  8882. -->
  8883. (S1 ^operator O1928 = 0.9996975476948911)
  8884. Retracting rl*prefer*rvt*predict-yes*H0*5
  8885. -->
  8886. (S1 ^operator O1927 = 0.2640770017585976)
  8887. Retracting rl*prefer*rvt*predict-yes*H0*5*v1*H1*41
  8888. -->
  8889. (S1 ^operator O1927 = 0.7363235474336447)
  8890. =>WM: (13594: S1 ^operator O1930 +)
  8891. =>WM: (13593: S1 ^operator O1929 +)
  8892. =>WM: (13592: I3 ^dir U)
  8893. =>WM: (13591: O1930 ^name predict-no)
  8894. =>WM: (13590: O1929 ^name predict-yes)
  8895. =>WM: (13589: R968 ^value 1)
  8896. =>WM: (13588: R1 ^reward R968)
  8897. =>WM: (13587: I3 ^see 1)
  8898. <=WM: (13578: S1 ^operator O1927 +)
  8899. <=WM: (13580: S1 ^operator O1927)
  8900. <=WM: (13579: S1 ^operator O1928 +)
  8901. <=WM: (13577: I3 ^dir L)
  8902. <=WM: (13573: R1 ^reward R967)
  8903. <=WM: (13572: I3 ^see 0)
  8904. <=WM: (13576: O1928 ^name predict-no)
  8905. <=WM: (13575: O1927 ^name predict-yes)
  8906. <=WM: (13574: R967 ^value 1)
  8907. --- Inner Elaboration Phase, active level 1 (S1) ---
  8908. Firing prefer*rvt*predict-yes*H0
  8909. -->
  8910. Firing rl*prefer*rvt*predict-yes*H0*1
  8911. -->
  8912. (S1 ^operator O1929 = 0.)
  8913. Firing prefer*rvt*predict-no*H0
  8914. -->
  8915. Firing rl*prefer*rvt*predict-no*H0*2
  8916. -->
  8917. (S1 ^operator O1930 = 1.)
  8918. inner elaboration loop at bottom goal.
  8919. Retracting rl*prefer*rvt*predict-no*H0*2
  8920. -->
  8921. (S1 ^operator O1928 = 1.)
  8922. Retracting rl*prefer*rvt*predict-yes*H0*1
  8923. -->
  8924. (S1 ^operator O1927 = 0.)
  8925. --- END Proposal Phase ---
  8926. --- Decision Phase ---
  8927. RL update rl*prefer*rvt*predict-yes*H0*5 0.554462 -0.290385 0.264077 -> 0.55443 -0.290385 0.264044(R,m,v=1,0.873563,0.111089)
  8928. RL update rl*prefer*rvt*predict-yes*H0*5*v1*H1*41 0.445932 0.290392 0.736324 -> 0.445895 0.290391 0.736286(R,m,v=1,1,0)
  8929. =>WM: (13595: S1 ^operator O1930)
  8930. 965: O: O1930 (predict-no)
  8931. --- END Decision Phase ---
  8932. --- Application Phase ---
  8933. --- Firing Productions (PE) For State At Depth 1 ---
  8934. --- Inner Elaboration Phase, active level 1 (S1) ---
  8935. Firing apply*operator
  8936. -->
  8937. (I3 ^predict-no N965 + :O )
  8938. Firing apply*operator*complete
  8939. -->
  8940. (I3 ^predict-yes N964 - :O )
  8941. inner elaboration loop at bottom goal.
  8942. --- Change Working Memory (PE) ---
  8943. =>WM: (13596: I3 ^predict-no N965)
  8944. <=WM: (13582: N964 ^status complete)
  8945. <=WM: (13581: I3 ^predict-yes N964)
  8946. --- Firing Productions (IE) For State At Depth 1 ---
  8947. --- Inner Elaboration Phase, active level 1 (S1) ---
  8948. Firing monitor*world
  8949. -->
  8950. I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
  8951. --- Change Working Memory (IE) ---
  8952. --- END Application Phase ---
  8953. --- Output Phase ---
  8954. ENV: Agent did: predict-no for direction U in state State-A
  8955. In State-A moving U
  8956. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  8957. predict error 0
  8958. dir: dir isL
  8959. --- END Output Phase ---
  8960. |\--- Input Phase ---
  8961. =>WM: (13600: I2 ^dir L)
  8962. =>WM: (13599: I2 ^reward 1)
  8963. =>WM: (13598: I2 ^see 0)
  8964. =>WM: (13597: N965 ^status complete)
  8965. <=WM: (13585: I2 ^dir U)
  8966. <=WM: (13584: I2 ^reward 1)
  8967. <=WM: (13583: I2 ^see 1)
  8968. =>WM: (13601: I2 ^level-1 L1-root)
  8969. <=WM: (13586: I2 ^level-1 L1-root)
  8970. --- END Input Phase ---
  8971. --- Proposal Phase ---
  8972. --- Inner Elaboration Phase, active level 1 (S1) ---
  8973. Firing rl*prefer*rvt*predict-yes*H0*5*v1*H1*31
  8974. -->
  8975. (S1 ^operator O1929 = -0.181727099742844)
  8976. Firing prefer*rvt*predict-yes*H0*5*v1*H1
  8977. -->
  8978. Firing elaborate*copy-see-to-output-link
  8979. -->
  8980. (I3 ^see 0 +)
  8981. Firing elaborate*reward*based*on*reward
  8982. -->
  8983. (R969 ^value 1 +)
  8984. (R1 ^reward R969 +)
  8985. Firing propose*predict-yes
  8986. -->
  8987. (O1931 ^name predict-yes +)
  8988. (S1 ^operator O1931 +)
  8989. Firing propose*predict-no
  8990. -->
  8991. (O1932 ^name predict-no +)
  8992. (S1 ^operator O1932 +)
  8993. Firing rl*prefer*rvt*predict-no*H0*6
  8994. -->
  8995. (S1 ^operator O1930 = 0.9996975476948911)
  8996. Firing rl*prefer*rvt*predict-yes*H0*5
  8997. -->
  8998. (S1 ^operator O1929 = 0.2640444846619989)
  8999. Firing prefer*rvt*predict-yes*H0
  9000. -->
  9001. Firing prefer*rvt*predict-no*H0
  9002. -->
  9003. Firing elaborate*copy-dir-to-output-link
  9004. -->
  9005. (I3 ^dir L +)
  9006. inner elaboration loop at bottom goal.
  9007. Retracting elaborate*copy-see-to-output-link
  9008. -->
  9009. (I3 ^see 1 +)
  9010. Retracting propose*predict-no
  9011. -->
  9012. (O1930 ^name predict-no +)
  9013. (S1 ^operator O1930 +)
  9014. Retracting propose*predict-yes
  9015. -->
  9016. (O1929 ^name predict-yes +)
  9017. (S1 ^operator O1929 +)
  9018. Retracting elaborate*reward*based*on*reward
  9019. -->
  9020. (R968 ^value 1 +)
  9021. (R1 ^reward R968 +)
  9022. Retracting elaborate*copy-dir-to-output-link
  9023. -->
  9024. (I3 ^dir U +)
  9025. Retracting rl*prefer*rvt*predict-no*H0*2
  9026. -->
  9027. (S1 ^operator O1930 = 1.)
  9028. Retracting rl*prefer*rvt*predict-yes*H0*1
  9029. -->
  9030. (S1 ^operator O1929 = 0.)
  9031. =>WM: (13609: S1 ^operator O1932 +)
  9032. =>WM: (13608: S1 ^operator O1931 +)
  9033. =>WM: (13607: I3 ^dir L)
  9034. =>WM: (13606: O1932 ^name predict-no)
  9035. =>WM: (13605: O1931 ^name predict-yes)
  9036. =>WM: (13604: R969 ^value 1)
  9037. =>WM: (13603: R1 ^reward R969)
  9038. =>WM: (13602: I3 ^see 0)
  9039. <=WM: (13593: S1 ^operator O1929 +)
  9040. <=WM: (13594: S1 ^operator O1930 +)
  9041. <=WM: (13595: S1 ^operator O1930)
  9042. <=WM: (13592: I3 ^dir U)
  9043. <=WM: (13588: R1 ^reward R968)
  9044. <=WM: (13587: I3 ^see 1)
  9045. <=WM: (13591: O1930 ^name predict-no)
  9046. <=WM: (13590: O1929 ^name predict-yes)
  9047. <=WM: (13589: R968 ^value 1)
  9048. --- Inner Elaboration Phase, active level 1 (S1) ---
  9049. Firing prefer*rvt*predict-yes*H0
  9050. -->
  9051. Firing rl*prefer*rvt*predict-yes*H0*5*v1*H1*31
  9052. -->
  9053. (S1 ^operator O1931 = -0.181727099742844)
  9054. Firing rl*prefer*rvt*predict-yes*H0*5
  9055. -->
  9056. (S1 ^operator O1931 = 0.2640444846619989)
  9057. Firing prefer*rvt*predict-yes*H0*5*v1*H1
  9058. -->
  9059. Firing prefer*rvt*predict-no*H0
  9060. -->
  9061. Firing rl*prefer*rvt*predict-no*H0*6
  9062. -->
  9063. (S1 ^operator O1932 = 0.9996975476948911)
  9064. inner elaboration loop at bottom goal.
  9065. Retracting rl*prefer*rvt*predict-no*H0*6
  9066. -->
  9067. (S1 ^operator O1930 = 0.9996975476948911)
  9068. Retracting rl*prefer*rvt*predict-yes*H0*5
  9069. -->
  9070. (S1 ^operator O1929 = 0.2640444846619989)
  9071. Retracting rl*prefer*rvt*predict-yes*H0*5*v1*H1*31
  9072. -->
  9073. (S1 ^operator O1929 = -0.181727099742844)
  9074. --- END Proposal Phase ---
  9075. --- Decision Phase ---
  9076. RL update rl*prefer*rvt*predict-no*H0*2 1 0 1 -> 1 0 1(R,m,v=1,1,0)
  9077. =>WM: (13610: S1 ^operator O1932)
  9078. 966: O: O1932 (predict-no)
  9079. --- END Decision Phase ---
  9080. --- Application Phase ---
  9081. --- Firing Productions (PE) For State At Depth 1 ---
  9082. --- Inner Elaboration Phase, active level 1 (S1) ---
  9083. Firing apply*operator
  9084. -->
  9085. (I3 ^predict-no N966 + :O )
  9086. Firing apply*operator*complete
  9087. -->
  9088. (I3 ^predict-no N965 - :O )
  9089. inner elaboration loop at bottom goal.
  9090. --- Change Working Memory (PE) ---
  9091. =>WM: (13611: I3 ^predict-no N966)
  9092. <=WM: (13597: N965 ^status complete)
  9093. <=WM: (13596: I3 ^predict-no N965)
  9094. --- Firing Productions (IE) For State At Depth 1 ---
  9095. --- Inner Elaboration Phase, active level 1 (S1) ---
  9096. Firing monitor*world
  9097. -->
  9098. I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
  9099. --- Change Working Memory (IE) ---
  9100. --- END Application Phase ---
  9101. --- Output Phase ---
  9102. ENV: Agent did: predict-no for direction L in state State-A
  9103. In State-A moving L
  9104. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  9105. predict error 0
  9106. dir: dir isR
  9107. --- END Output Phase ---
  9108. -/|--- Input Phase ---
  9109. =>WM: (13615: I2 ^dir R)
  9110. =>WM: (13614: I2 ^reward 1)
  9111. =>WM: (13613: I2 ^see 0)
  9112. =>WM: (13612: N966 ^status complete)
  9113. <=WM: (13600: I2 ^dir L)
  9114. <=WM: (13599: I2 ^reward 1)
  9115. <=WM: (13598: I2 ^see 0)
  9116. =>WM: (13616: I2 ^level-1 L0-root)
  9117. <=WM: (13601: I2 ^level-1 L1-root)
  9118. --- END Input Phase ---
  9119. --- Proposal Phase ---
  9120. --- Inner Elaboration Phase, active level 1 (S1) ---
  9121. Firing rl*prefer*rvt*predict-no*H0*4*v1*H1*33
  9122. -->
  9123. (S1 ^operator O1932 = -0.2817060109291377)
  9124. Firing rl*prefer*rvt*predict-yes*H0*3*v1*H1*34
  9125. -->
  9126. (S1 ^operator O1931 = 0.6623675607605151)
  9127. Firing prefer*rvt*predict-no*H0*4*v1*H1
  9128. -->
  9129. Firing prefer*rvt*predict-yes*H0*3*v1*H1
  9130. -->
  9131. Firing elaborate*copy-see-to-output-link
  9132. -->
  9133. (I3 ^see 0 +)
  9134. Firing elaborate*reward*based*on*reward
  9135. -->
  9136. (R970 ^value 1 +)
  9137. (R1 ^reward R970 +)
  9138. Firing propose*predict-yes
  9139. -->
  9140. (O1933 ^name predict-yes +)
  9141. (S1 ^operator O1933 +)
  9142. Firing propose*predict-no
  9143. -->
  9144. (O1934 ^name predict-no +)
  9145. (S1 ^operator O1934 +)
  9146. Firing rl*prefer*rvt*predict-no*H0*4
  9147. -->
  9148. (S1 ^operator O1932 = 0.3397713875215998)
  9149. Firing rl*prefer*rvt*predict-yes*H0*3
  9150. -->
  9151. (S1 ^operator O1931 = 0.3377110018583719)
  9152. Firing prefer*rvt*predict-yes*H0
  9153. -->
  9154. Firing prefer*rvt*predict-no*H0
  9155. -->
  9156. Firing elaborate*copy-dir-to-output-link
  9157. -->
  9158. (I3 ^dir R +)
  9159. inner elaboration loop at bottom goal.
  9160. Retracting elaborate*copy-see-to-output-link
  9161. -->
  9162. (I3 ^see 0 +)
  9163. Retracting propose*predict-no
  9164. -->
  9165. (O1932 ^name predict-no +)
  9166. (S1 ^operator O1932 +)
  9167. Retracting propose*predict-yes
  9168. -->
  9169. (O1931 ^name predict-yes +)
  9170. (S1 ^operator O1931 +)
  9171. Retracting elaborate*reward*based*on*reward
  9172. -->
  9173. (R969 ^value 1 +)
  9174. (R1 ^reward R969 +)
  9175. Retracting elaborate*copy-dir-to-output-link
  9176. -->
  9177. (I3 ^dir L +)
  9178. Retracting rl*prefer*rvt*predict-no*H0*6
  9179. -->
  9180. (S1 ^operator O1932 = 0.9996975476948911)
  9181. Retracting rl*prefer*rvt*predict-yes*H0*5
  9182. -->
  9183. (S1 ^operator O1931 = 0.2640444846619989)
  9184. Retracting rl*prefer*rvt*predict-yes*H0*5*v1*H1*31
  9185. -->
  9186. (S1 ^operator O1931 = -0.181727099742844)
  9187. =>WM: (13623: S1 ^operator O1934 +)
  9188. =>WM: (13622: S1 ^operator O1933 +)
  9189. =>WM: (13621: I3 ^dir R)
  9190. =>WM: (13620: O1934 ^name predict-no)
  9191. =>WM: (13619: O1933 ^name predict-yes)
  9192. =>WM: (13618: R970 ^value 1)
  9193. =>WM: (13617: R1 ^reward R970)
  9194. <=WM: (13608: S1 ^operator O1931 +)
  9195. <=WM: (13609: S1 ^operator O1932 +)
  9196. <=WM: (13610: S1 ^operator O1932)
  9197. <=WM: (13607: I3 ^dir L)
  9198. <=WM: (13603: R1 ^reward R969)
  9199. <=WM: (13606: O1932 ^name predict-no)
  9200. <=WM: (13605: O1931 ^name predict-yes)
  9201. <=WM: (13604: R969 ^value 1)
  9202. --- Inner Elaboration Phase, active level 1 (S1) ---
  9203. Firing prefer*rvt*predict-yes*H0
  9204. -->
  9205. Firing rl*prefer*rvt*predict-yes*H0*3
  9206. -->
  9207. (S1 ^operator O1933 = 0.3377110018583719)
  9208. Firing prefer*rvt*predict-yes*H0*3*v1*H1
  9209. -->
  9210. Firing rl*prefer*rvt*predict-yes*H0*3*v1*H1*34
  9211. -->
  9212. (S1 ^operator O1933 = 0.6623675607605151)
  9213. Firing prefer*rvt*predict-no*H0
  9214. -->
  9215. Firing rl*prefer*rvt*predict-no*H0*4
  9216. -->
  9217. (S1 ^operator O1934 = 0.3397713875215998)
  9218. Firing prefer*rvt*predict-no*H0*4*v1*H1
  9219. -->
  9220. Firing rl*prefer*rvt*predict-no*H0*4*v1*H1*33
  9221. -->
  9222. (S1 ^operator O1934 = -0.2817060109291377)
  9223. inner elaboration loop at bottom goal.
  9224. Retracting rl*prefer*rvt*predict-no*H0*4
  9225. -->
  9226. (S1 ^operator O1932 = 0.3397713875215998)
  9227. Retracting rl*prefer*rvt*predict-no*H0*4*v1*H1*33
  9228. -->
  9229. (S1 ^operator O1932 = -0.2817060109291377)
  9230. Retracting rl*prefer*rvt*predict-yes*H0*3
  9231. -->
  9232. (S1 ^operator O1931 = 0.3377110018583719)
  9233. Retracting rl*prefer*rvt*predict-yes*H0*3*v1*H1*34
  9234. -->
  9235. (S1 ^operator O1931 = 0.6623675607605151)
  9236. --- END Proposal Phase ---
  9237. --- Decision Phase ---
  9238. RL update rl*prefer*rvt*predict-no*H0*6 0.999698 0 0.999698 -> 0.999748 0 0.999748(R,m,v=1,0.90411,0.0872933)
  9239. =>WM: (13624: S1 ^operator O1933)
  9240. 967: O: O1933 (predict-yes)
  9241. --- END Decision Phase ---
  9242. --- Application Phase ---
  9243. --- Firing Productions (PE) For State At Depth 1 ---
  9244. --- Inner Elaboration Phase, active level 1 (S1) ---
  9245. Firing apply*operator
  9246. -->
  9247. (I3 ^predict-yes N967 + :O )
  9248. Firing apply*operator*complete
  9249. -->
  9250. (I3 ^predict-no N966 - :O )
  9251. inner elaboration loop at bottom goal.
  9252. --- Change Working Memory (PE) ---
  9253. =>WM: (13625: I3 ^predict-yes N967)
  9254. <=WM: (13612: N966 ^status complete)
  9255. <=WM: (13611: I3 ^predict-no N966)
  9256. --- Firing Productions (IE) For State At Depth 1 ---
  9257. --- Inner Elaboration Phase, active level 1 (S1) ---
  9258. Firing monitor*world
  9259. -->
  9260. I see 1 and I'm going to do: predict-yes inner elaboration loop at bottom goal.
  9261. --- Change Working Memory (IE) ---
  9262. --- END Application Phase ---
  9263. --- Output Phase ---
  9264. ENV: Agent did: predict-yes for direction R in state State-A
  9265. In State-A moving R
  9266. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  9267. predict error 0
  9268. dir: dir isR
  9269. --- END Output Phase ---
  9270. \-/--- Input Phase ---
  9271. =>WM: (13629: I2 ^dir R)
  9272. =>WM: (13628: I2 ^reward 1)
  9273. =>WM: (13627: I2 ^see 1)
  9274. =>WM: (13626: N967 ^status complete)
  9275. <=WM: (13615: I2 ^dir R)
  9276. <=WM: (13614: I2 ^reward 1)
  9277. <=WM: (13613: I2 ^see 0)
  9278. =>WM: (13630: I2 ^level-1 R1-root)
  9279. <=WM: (13616: I2 ^level-1 L0-root)
  9280. --- END Input Phase ---
  9281. --- Proposal Phase ---
  9282. --- Inner Elaboration Phase, active level 1 (S1) ---
  9283. Firing rl*prefer*rvt*predict-yes*H0*3*v1*H1*36
  9284. -->
  9285. (S1 ^operator O1933 = -0.1070236389116304)
  9286. Firing rl*prefer*rvt*predict-no*H0*4*v1*H1*35
  9287. -->
  9288. (S1 ^operator O1934 = 0.6602488383529777)
  9289. Firing prefer*rvt*predict-no*H0*4*v1*H1
  9290. -->
  9291. Firing prefer*rvt*predict-yes*H0*3*v1*H1
  9292. -->
  9293. Firing elaborate*copy-see-to-output-link
  9294. -->
  9295. (I3 ^see 1 +)
  9296. Firing elaborate*reward*based*on*reward
  9297. -->
  9298. (R971 ^value 1 +)
  9299. (R1 ^reward R971 +)
  9300. Firing propose*predict-yes
  9301. -->
  9302. (O1935 ^name predict-yes +)
  9303. (S1 ^operator O1935 +)
  9304. Firing propose*predict-no
  9305. -->
  9306. (O1936 ^name predict-no +)
  9307. (S1 ^operator O1936 +)
  9308. Firing rl*prefer*rvt*predict-no*H0*4
  9309. -->
  9310. (S1 ^operator O1934 = 0.3397713875215998)
  9311. Firing rl*prefer*rvt*predict-yes*H0*3
  9312. -->
  9313. (S1 ^operator O1933 = 0.3377110018583719)
  9314. Firing prefer*rvt*predict-yes*H0
  9315. -->
  9316. Firing prefer*rvt*predict-no*H0
  9317. -->
  9318. Firing elaborate*copy-dir-to-output-link
  9319. -->
  9320. (I3 ^dir R +)
  9321. inner elaboration loop at bottom goal.
  9322. Retracting elaborate*copy-see-to-output-link
  9323. -->
  9324. (I3 ^see 0 +)
  9325. Retracting propose*predict-no
  9326. -->
  9327. (O1934 ^name predict-no +)
  9328. (S1 ^operator O1934 +)
  9329. Retracting propose*predict-yes
  9330. -->
  9331. (O1933 ^name predict-yes +)
  9332. (S1 ^operator O1933 +)
  9333. Retracting elaborate*reward*based*on*reward
  9334. -->
  9335. (R970 ^value 1 +)
  9336. (R1 ^reward R970 +)
  9337. Retracting elaborate*copy-dir-to-output-link
  9338. -->
  9339. (I3 ^dir R +)
  9340. Retracting rl*prefer*rvt*predict-no*H0*4*v1*H1*33
  9341. -->
  9342. (S1 ^operator O1934 = -0.2817060109291377)
  9343. Retracting rl*prefer*rvt*predict-no*H0*4
  9344. -->
  9345. (S1 ^operator O1934 = 0.3397713875215998)
  9346. Retracting rl*prefer*rvt*predict-yes*H0*3*v1*H1*34
  9347. -->
  9348. (S1 ^operator O1933 = 0.6623675607605151)
  9349. Retracting rl*prefer*rvt*predict-yes*H0*3
  9350. -->
  9351. (S1 ^operator O1933 = 0.3377110018583719)
  9352. =>WM: (13637: S1 ^operator O1936 +)
  9353. =>WM: (13636: S1 ^operator O1935 +)
  9354. =>WM: (13635: O1936 ^name predict-no)
  9355. =>WM: (13634: O1935 ^name predict-yes)
  9356. =>WM: (13633: R971 ^value 1)
  9357. =>WM: (13632: R1 ^reward R971)
  9358. =>WM: (13631: I3 ^see 1)
  9359. <=WM: (13622: S1 ^operator O1933 +)
  9360. <=WM: (13624: S1 ^operator O1933)
  9361. <=WM: (13623: S1 ^operator O1934 +)
  9362. <=WM: (13617: R1 ^reward R970)
  9363. <=WM: (13602: I3 ^see 0)
  9364. <=WM: (13620: O1934 ^name predict-no)
  9365. <=WM: (13619: O1933 ^name predict-yes)
  9366. <=WM: (13618: R970 ^value 1)
  9367. --- Inner Elaboration Phase, active level 1 (S1) ---
  9368. Firing prefer*rvt*predict-yes*H0
  9369. -->
  9370. Firing rl*prefer*rvt*predict-yes*H0*3
  9371. -->
  9372. (S1 ^operator O1935 = 0.3377110018583719)
  9373. Firing prefer*rvt*predict-yes*H0*3*v1*H1
  9374. -->
  9375. Firing rl*prefer*rvt*predict-yes*H0*3*v1*H1*36
  9376. -->
  9377. (S1 ^operator O1935 = -0.1070236389116304)
  9378. Firing prefer*rvt*predict-no*H0
  9379. -->
  9380. Firing rl*prefer*rvt*predict-no*H0*4
  9381. -->
  9382. (S1 ^operator O1936 = 0.3397713875215998)
  9383. Firing prefer*rvt*predict-no*H0*4*v1*H1
  9384. -->
  9385. Firing rl*prefer*rvt*predict-no*H0*4*v1*H1*35
  9386. -->
  9387. (S1 ^operator O1936 = 0.6602488383529777)
  9388. inner elaboration loop at bottom goal.
  9389. Retracting rl*prefer*rvt*predict-no*H0*4
  9390. -->
  9391. (S1 ^operator O1934 = 0.3397713875215998)
  9392. Retracting rl*prefer*rvt*predict-no*H0*4*v1*H1*35
  9393. -->
  9394. (S1 ^operator O1934 = 0.6602488383529777)
  9395. Retracting rl*prefer*rvt*predict-yes*H0*3
  9396. -->
  9397. (S1 ^operator O1933 = 0.3377110018583719)
  9398. Retracting rl*prefer*rvt*predict-yes*H0*3*v1*H1*36
  9399. -->
  9400. (S1 ^operator O1933 = -0.1070236389116304)
  9401. --- END Proposal Phase ---
  9402. --- Decision Phase ---
  9403. RL update rl*prefer*rvt*predict-yes*H0*3 0.590111 -0.2524 0.337711 -> 0.590104 -0.252399 0.337705(R,m,v=1,0.895706,0.0939938)
  9404. RL update rl*prefer*rvt*predict-yes*H0*3*v1*H1*34 0.409979 0.252388 0.662368 -> 0.409971 0.252389 0.66236(R,m,v=1,1,0)
  9405. =>WM: (13638: S1 ^operator O1936)
  9406. 968: O: O1936 (predict-no)
  9407. --- END Decision Phase ---
  9408. --- Application Phase ---
  9409. --- Firing Productions (PE) For State At Depth 1 ---
  9410. --- Inner Elaboration Phase, active level 1 (S1) ---
  9411. Firing apply*operator
  9412. -->
  9413. (I3 ^predict-no N968 + :O )
  9414. Firing apply*operator*complete
  9415. -->
  9416. (I3 ^predict-yes N967 - :O )
  9417. inner elaboration loop at bottom goal.
  9418. --- Change Working Memory (PE) ---
  9419. =>WM: (13639: I3 ^predict-no N968)
  9420. <=WM: (13626: N967 ^status complete)
  9421. <=WM: (13625: I3 ^predict-yes N967)
  9422. --- Firing Productions (IE) For State At Depth 1 ---
  9423. --- Inner Elaboration Phase, active level 1 (S1) ---
  9424. Firing monitor*world
  9425. -->
  9426. I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
  9427. --- Change Working Memory (IE) ---
  9428. --- END Application Phase ---
  9429. --- Output Phase ---
  9430. ENV: Agent did: predict-no for direction R in state State-B
  9431. In State-B moving R
  9432. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  9433. predict error 0
  9434. dir: dir isU
  9435. --- END Output Phase ---
  9436. |\--- Input Phase ---
  9437. =>WM: (13643: I2 ^dir U)
  9438. =>WM: (13642: I2 ^reward 1)
  9439. =>WM: (13641: I2 ^see 0)
  9440. =>WM: (13640: N968 ^status complete)
  9441. <=WM: (13629: I2 ^dir R)
  9442. <=WM: (13628: I2 ^reward 1)
  9443. <=WM: (13627: I2 ^see 1)
  9444. =>WM: (13644: I2 ^level-1 R0-root)
  9445. <=WM: (13630: I2 ^level-1 R1-root)
  9446. --- END Input Phase ---
  9447. --- Proposal Phase ---
  9448. --- Inner Elaboration Phase, active level 1 (S1) ---
  9449. Firing elaborate*copy-see-to-output-link
  9450. -->
  9451. (I3 ^see 0 +)
  9452. Firing elaborate*reward*based*on*reward
  9453. -->
  9454. (R972 ^value 1 +)
  9455. (R1 ^reward R972 +)
  9456. Firing propose*predict-yes
  9457. -->
  9458. (O1937 ^name predict-yes +)
  9459. (S1 ^operator O1937 +)
  9460. Firing propose*predict-no
  9461. -->
  9462. (O1938 ^name predict-no +)
  9463. (S1 ^operator O1938 +)
  9464. Firing rl*prefer*rvt*predict-no*H0*2
  9465. -->
  9466. (S1 ^operator O1936 = 1.)
  9467. Firing rl*prefer*rvt*predict-yes*H0*1
  9468. -->
  9469. (S1 ^operator O1935 = 0.)
  9470. Firing prefer*rvt*predict-yes*H0
  9471. -->
  9472. Firing prefer*rvt*predict-no*H0
  9473. -->
  9474. Firing elaborate*copy-dir-to-output-link
  9475. -->
  9476. (I3 ^dir U +)
  9477. inner elaboration loop at bottom goal.
  9478. Retracting elaborate*copy-see-to-output-link
  9479. -->
  9480. (I3 ^see 1 +)
  9481. Retracting propose*predict-no
  9482. -->
  9483. (O1936 ^name predict-no +)
  9484. (S1 ^operator O1936 +)
  9485. Retracting propose*predict-yes
  9486. -->
  9487. (O1935 ^name predict-yes +)
  9488. (S1 ^operator O1935 +)
  9489. Retracting elaborate*reward*based*on*reward
  9490. -->
  9491. (R971 ^value 1 +)
  9492. (R1 ^reward R971 +)
  9493. Retracting elaborate*copy-dir-to-output-link
  9494. -->
  9495. (I3 ^dir R +)
  9496. Retracting rl*prefer*rvt*predict-no*H0*4*v1*H1*35
  9497. -->
  9498. (S1 ^operator O1936 = 0.6602488383529777)
  9499. Retracting rl*prefer*rvt*predict-no*H0*4
  9500. -->
  9501. (S1 ^operator O1936 = 0.3397713875215998)
  9502. Retracting rl*prefer*rvt*predict-yes*H0*3*v1*H1*36
  9503. -->
  9504. (S1 ^operator O1935 = -0.1070236389116304)
  9505. Retracting rl*prefer*rvt*predict-yes*H0*3
  9506. -->
  9507. (S1 ^operator O1935 = 0.3377045556949833)
  9508. =>WM: (13652: S1 ^operator O1938 +)
  9509. =>WM: (13651: S1 ^operator O1937 +)
  9510. =>WM: (13650: I3 ^dir U)
  9511. =>WM: (13649: O1938 ^name predict-no)
  9512. =>WM: (13648: O1937 ^name predict-yes)
  9513. =>WM: (13647: R972 ^value 1)
  9514. =>WM: (13646: R1 ^reward R972)
  9515. =>WM: (13645: I3 ^see 0)
  9516. <=WM: (13636: S1 ^operator O1935 +)
  9517. <=WM: (13637: S1 ^operator O1936 +)
  9518. <=WM: (13638: S1 ^operator O1936)
  9519. <=WM: (13621: I3 ^dir R)
  9520. <=WM: (13632: R1 ^reward R971)
  9521. <=WM: (13631: I3 ^see 1)
  9522. <=WM: (13635: O1936 ^name predict-no)
  9523. <=WM: (13634: O1935 ^name predict-yes)
  9524. <=WM: (13633: R971 ^value 1)
  9525. --- Inner Elaboration Phase, active level 1 (S1) ---
  9526. Firing prefer*rvt*predict-yes*H0
  9527. -->
  9528. Firing rl*prefer*rvt*predict-yes*H0*1
  9529. -->
  9530. (S1 ^operator O1937 = 0.)
  9531. Firing prefer*rvt*predict-no*H0
  9532. -->
  9533. Firing rl*prefer*rvt*predict-no*H0*2
  9534. -->
  9535. (S1 ^operator O1938 = 1.)
  9536. inner elaboration loop at bottom goal.
  9537. Retracting rl*prefer*rvt*predict-no*H0*2
  9538. -->
  9539. (S1 ^operator O1936 = 1.)
  9540. Retracting rl*prefer*rvt*predict-yes*H0*1
  9541. -->
  9542. (S1 ^operator O1935 = 0.)
  9543. --- END Proposal Phase ---
  9544. --- Decision Phase ---
  9545. RL update rl*prefer*rvt*predict-no*H0*4 0.570255 -0.230484 0.339771 -> 0.570253 -0.230483 0.33977(R,m,v=1,0.872727,0.111752)
  9546. RL update rl*prefer*rvt*predict-no*H0*4*v1*H1*35 0.429766 0.230483 0.660249 -> 0.429764 0.230483 0.660247(R,m,v=1,1,0)
  9547. =>WM: (13653: S1 ^operator O1938)
  9548. 969: O: O1938 (predict-no)
  9549. --- END Decision Phase ---
  9550. --- Application Phase ---
  9551. --- Firing Productions (PE) For State At Depth 1 ---
  9552. --- Inner Elaboration Phase, active level 1 (S1) ---
  9553. Firing apply*operator
  9554. -->
  9555. (I3 ^predict-no N969 + :O )
  9556. Firing apply*operator*complete
  9557. -->
  9558. (I3 ^predict-no N968 - :O )
  9559. inner elaboration loop at bottom goal.
  9560. --- Change Working Memory (PE) ---
  9561. =>WM: (13654: I3 ^predict-no N969)
  9562. <=WM: (13640: N968 ^status complete)
  9563. <=WM: (13639: I3 ^predict-no N968)
  9564. --- Firing Productions (IE) For State At Depth 1 ---
  9565. --- Inner Elaboration Phase, active level 1 (S1) ---
  9566. Firing monitor*world
  9567. -->
  9568. I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
  9569. --- Change Working Memory (IE) ---
  9570. --- END Application Phase ---
  9571. --- Output Phase ---
  9572. ENV: Agent did: predict-no for direction U in state State-B
  9573. In State-B moving U
  9574. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  9575. predict error 0
  9576. dir: dir isU
  9577. --- END Output Phase ---
  9578. -/|--- Input Phase ---
  9579. =>WM: (13658: I2 ^dir U)
  9580. =>WM: (13657: I2 ^reward 1)
  9581. =>WM: (13656: I2 ^see 0)
  9582. =>WM: (13655: N969 ^status complete)
  9583. <=WM: (13643: I2 ^dir U)
  9584. <=WM: (13642: I2 ^reward 1)
  9585. <=WM: (13641: I2 ^see 0)
  9586. =>WM: (13659: I2 ^level-1 R0-root)
  9587. <=WM: (13644: I2 ^level-1 R0-root)
  9588. --- END Input Phase ---
  9589. --- Proposal Phase ---
  9590. --- Inner Elaboration Phase, active level 1 (S1) ---
  9591. Firing elaborate*copy-see-to-output-link
  9592. -->
  9593. (I3 ^see 0 +)
  9594. Firing elaborate*reward*based*on*reward
  9595. -->
  9596. (R973 ^value 1 +)
  9597. (R1 ^reward R973 +)
  9598. Firing propose*predict-yes
  9599. -->
  9600. (O1939 ^name predict-yes +)
  9601. (S1 ^operator O1939 +)
  9602. Firing propose*predict-no
  9603. -->
  9604. (O1940 ^name predict-no +)
  9605. (S1 ^operator O1940 +)
  9606. Firing rl*prefer*rvt*predict-no*H0*2
  9607. -->
  9608. (S1 ^operator O1938 = 1.)
  9609. Firing rl*prefer*rvt*predict-yes*H0*1
  9610. -->
  9611. (S1 ^operator O1937 = 0.)
  9612. Firing prefer*rvt*predict-yes*H0
  9613. -->
  9614. Firing prefer*rvt*predict-no*H0
  9615. -->
  9616. Firing elaborate*copy-dir-to-output-link
  9617. -->
  9618. (I3 ^dir U +)
  9619. inner elaboration loop at bottom goal.
  9620. Retracting elaborate*copy-see-to-output-link
  9621. -->
  9622. (I3 ^see 0 +)
  9623. Retracting propose*predict-no
  9624. -->
  9625. (O1938 ^name predict-no +)
  9626. (S1 ^operator O1938 +)
  9627. Retracting propose*predict-yes
  9628. -->
  9629. (O1937 ^name predict-yes +)
  9630. (S1 ^operator O1937 +)
  9631. Retracting elaborate*reward*based*on*reward
  9632. -->
  9633. (R972 ^value 1 +)
  9634. (R1 ^reward R972 +)
  9635. Retracting elaborate*copy-dir-to-output-link
  9636. -->
  9637. (I3 ^dir U +)
  9638. Retracting rl*prefer*rvt*predict-no*H0*2
  9639. -->
  9640. (S1 ^operator O1938 = 1.)
  9641. Retracting rl*prefer*rvt*predict-yes*H0*1
  9642. -->
  9643. (S1 ^operator O1937 = 0.)
  9644. =>WM: (13665: S1 ^operator O1940 +)
  9645. =>WM: (13664: S1 ^operator O1939 +)
  9646. =>WM: (13663: O1940 ^name predict-no)
  9647. =>WM: (13662: O1939 ^name predict-yes)
  9648. =>WM: (13661: R973 ^value 1)
  9649. =>WM: (13660: R1 ^reward R973)
  9650. <=WM: (13651: S1 ^operator O1937 +)
  9651. <=WM: (13652: S1 ^operator O1938 +)
  9652. <=WM: (13653: S1 ^operator O1938)
  9653. <=WM: (13646: R1 ^reward R972)
  9654. <=WM: (13649: O1938 ^name predict-no)
  9655. <=WM: (13648: O1937 ^name predict-yes)
  9656. <=WM: (13647: R972 ^value 1)
  9657. --- Inner Elaboration Phase, active level 1 (S1) ---
  9658. Firing prefer*rvt*predict-yes*H0
  9659. -->
  9660. Firing rl*prefer*rvt*predict-yes*H0*1
  9661. -->
  9662. (S1 ^operator O1939 = 0.)
  9663. Firing prefer*rvt*predict-no*H0
  9664. -->
  9665. Firing rl*prefer*rvt*predict-no*H0*2
  9666. -->
  9667. (S1 ^operator O1940 = 1.)
  9668. inner elaboration loop at bottom goal.
  9669. Retracting rl*prefer*rvt*predict-no*H0*2
  9670. -->
  9671. (S1 ^operator O1938 = 1.)
  9672. Retracting rl*prefer*rvt*predict-yes*H0*1
  9673. -->
  9674. (S1 ^operator O1937 = 0.)
  9675. --- END Proposal Phase ---
  9676. --- Decision Phase ---
  9677. RL update rl*prefer*rvt*predict-no*H0*2 1 0 1 -> 1 0 1(R,m,v=1,1,0)
  9678. =>WM: (13666: S1 ^operator O1940)
  9679. 970: O: O1940 (predict-no)
  9680. --- END Decision Phase ---
  9681. --- Application Phase ---
  9682. --- Firing Productions (PE) For State At Depth 1 ---
  9683. --- Inner Elaboration Phase, active level 1 (S1) ---
  9684. Firing apply*operator
  9685. -->
  9686. (I3 ^predict-no N970 + :O )
  9687. Firing apply*operator*complete
  9688. -->
  9689. (I3 ^predict-no N969 - :O )
  9690. inner elaboration loop at bottom goal.
  9691. --- Change Working Memory (PE) ---
  9692. =>WM: (13667: I3 ^predict-no N970)
  9693. <=WM: (13655: N969 ^status complete)
  9694. <=WM: (13654: I3 ^predict-no N969)
  9695. --- Firing Productions (IE) For State At Depth 1 ---
  9696. --- Inner Elaboration Phase, active level 1 (S1) ---
  9697. Firing monitor*world
  9698. -->
  9699. I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
  9700. --- Change Working Memory (IE) ---
  9701. --- END Application Phase ---
  9702. --- Output Phase ---
  9703. ENV: Agent did: predict-no for direction U in state State-B
  9704. In State-B moving U
  9705. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  9706. predict error 0
  9707. dir: dir isL
  9708. --- END Output Phase ---
  9709. \---- Input Phase ---
  9710. =>WM: (13671: I2 ^dir L)
  9711. =>WM: (13670: I2 ^reward 1)
  9712. =>WM: (13669: I2 ^see 0)
  9713. =>WM: (13668: N970 ^status complete)
  9714. <=WM: (13658: I2 ^dir U)
  9715. <=WM: (13657: I2 ^reward 1)
  9716. <=WM: (13656: I2 ^see 0)
  9717. =>WM: (13672: I2 ^level-1 R0-root)
  9718. <=WM: (13659: I2 ^level-1 R0-root)
  9719. --- END Input Phase ---
  9720. --- Proposal Phase ---
  9721. --- Inner Elaboration Phase, active level 1 (S1) ---
  9722. Firing rl*prefer*rvt*predict-yes*H0*5*v1*H1*30
  9723. -->
  9724. (S1 ^operator O1939 = 0.735815301499146)
  9725. Firing prefer*rvt*predict-yes*H0*5*v1*H1
  9726. -->
  9727. Firing elaborate*copy-see-to-output-link
  9728. -->
  9729. (I3 ^see 0 +)
  9730. Firing elaborate*reward*based*on*reward
  9731. -->
  9732. (R974 ^value 1 +)
  9733. (R1 ^reward R974 +)
  9734. Firing propose*predict-yes
  9735. -->
  9736. (O1941 ^name predict-yes +)
  9737. (S1 ^operator O1941 +)
  9738. Firing propose*predict-no
  9739. -->
  9740. (O1942 ^name predict-no +)
  9741. (S1 ^operator O1942 +)
  9742. Firing rl*prefer*rvt*predict-no*H0*6
  9743. -->
  9744. (S1 ^operator O1940 = 0.9997480945179411)
  9745. Firing rl*prefer*rvt*predict-yes*H0*5
  9746. -->
  9747. (S1 ^operator O1939 = 0.2640444846619989)
  9748. Firing prefer*rvt*predict-yes*H0
  9749. -->
  9750. Firing prefer*rvt*predict-no*H0
  9751. -->
  9752. Firing elaborate*copy-dir-to-output-link
  9753. -->
  9754. (I3 ^dir L +)
  9755. inner elaboration loop at bottom goal.
  9756. Retracting elaborate*copy-see-to-output-link
  9757. -->
  9758. (I3 ^see 0 +)
  9759. Retracting propose*predict-no
  9760. -->
  9761. (O1940 ^name predict-no +)
  9762. (S1 ^operator O1940 +)
  9763. Retracting propose*predict-yes
  9764. -->
  9765. (O1939 ^name predict-yes +)
  9766. (S1 ^operator O1939 +)
  9767. Retracting elaborate*reward*based*on*reward
  9768. -->
  9769. (R973 ^value 1 +)
  9770. (R1 ^reward R973 +)
  9771. Retracting elaborate*copy-dir-to-output-link
  9772. -->
  9773. (I3 ^dir U +)
  9774. Retracting rl*prefer*rvt*predict-no*H0*2
  9775. -->
  9776. (S1 ^operator O1940 = 1.)
  9777. Retracting rl*prefer*rvt*predict-yes*H0*1
  9778. -->
  9779. (S1 ^operator O1939 = 0.)
  9780. =>WM: (13679: S1 ^operator O1942 +)
  9781. =>WM: (13678: S1 ^operator O1941 +)
  9782. =>WM: (13677: I3 ^dir L)
  9783. =>WM: (13676: O1942 ^name predict-no)
  9784. =>WM: (13675: O1941 ^name predict-yes)
  9785. =>WM: (13674: R974 ^value 1)
  9786. =>WM: (13673: R1 ^reward R974)
  9787. <=WM: (13664: S1 ^operator O1939 +)
  9788. <=WM: (13665: S1 ^operator O1940 +)
  9789. <=WM: (13666: S1 ^operator O1940)
  9790. <=WM: (13650: I3 ^dir U)
  9791. <=WM: (13660: R1 ^reward R973)
  9792. <=WM: (13663: O1940 ^name predict-no)
  9793. <=WM: (13662: O1939 ^name predict-yes)
  9794. <=WM: (13661: R973 ^value 1)
  9795. --- Inner Elaboration Phase, active level 1 (S1) ---
  9796. Firing prefer*rvt*predict-yes*H0
  9797. -->
  9798. Firing rl*prefer*rvt*predict-yes*H0*5*v1*H1*30
  9799. -->
  9800. (S1 ^operator O1941 = 0.735815301499146)
  9801. Firing rl*prefer*rvt*predict-yes*H0*5
  9802. -->
  9803. (S1 ^operator O1941 = 0.2640444846619989)
  9804. Firing prefer*rvt*predict-yes*H0*5*v1*H1
  9805. -->
  9806. Firing prefer*rvt*predict-no*H0
  9807. -->
  9808. Firing rl*prefer*rvt*predict-no*H0*6
  9809. -->
  9810. (S1 ^operator O1942 = 0.9997480945179411)
  9811. inner elaboration loop at bottom goal.
  9812. Retracting rl*prefer*rvt*predict-no*H0*6
  9813. -->
  9814. (S1 ^operator O1940 = 0.9997480945179411)
  9815. Retracting rl*prefer*rvt*predict-yes*H0*5
  9816. -->
  9817. (S1 ^operator O1939 = 0.2640444846619989)
  9818. Retracting rl*prefer*rvt*predict-yes*H0*5*v1*H1*30
  9819. -->
  9820. (S1 ^operator O1939 = 0.735815301499146)
  9821. --- END Proposal Phase ---
  9822. --- Decision Phase ---
  9823. RL update rl*prefer*rvt*predict-no*H0*2 1 0 1 -> 1 0 1(R,m,v=1,1,0)
  9824. =>WM: (13680: S1 ^operator O1941)
  9825. 971: O: O1941 (predict-yes)
  9826. --- END Decision Phase ---
  9827. --- Application Phase ---
  9828. --- Firing Productions (PE) For State At Depth 1 ---
  9829. --- Inner Elaboration Phase, active level 1 (S1) ---
  9830. Firing apply*operator
  9831. -->
  9832. (I3 ^predict-yes N971 + :O )
  9833. Firing apply*operator*complete
  9834. -->
  9835. (I3 ^predict-no N970 - :O )
  9836. inner elaboration loop at bottom goal.
  9837. --- Change Working Memory (PE) ---
  9838. =>WM: (13681: I3 ^predict-yes N971)
  9839. <=WM: (13668: N970 ^status complete)
  9840. <=WM: (13667: I3 ^predict-no N970)
  9841. --- Firing Productions (IE) For State At Depth 1 ---
  9842. --- Inner Elaboration Phase, active level 1 (S1) ---
  9843. Firing monitor*world
  9844. -->
  9845. I see 1 and I'm going to do: predict-yes inner elaboration loop at bottom goal.
  9846. --- Change Working Memory (IE) ---
  9847. --- END Application Phase ---
  9848. --- Output Phase ---
  9849. ENV: Agent did: predict-yes for direction L in state State-B
  9850. In State-B moving L
  9851. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  9852. predict error 0
  9853. dir: dir isR
  9854. --- END Output Phase ---
  9855. /--- Input Phase ---
  9856. =>WM: (13685: I2 ^dir R)
  9857. =>WM: (13684: I2 ^reward 1)
  9858. =>WM: (13683: I2 ^see 1)
  9859. =>WM: (13682: N971 ^status complete)
  9860. <=WM: (13671: I2 ^dir L)
  9861. <=WM: (13670: I2 ^reward 1)
  9862. <=WM: (13669: I2 ^see 0)
  9863. =>WM: (13686: I2 ^level-1 L1-root)
  9864. <=WM: (13672: I2 ^level-1 R0-root)
  9865. --- END Input Phase ---
  9866. --- Proposal Phase ---
  9867. --- Inner Elaboration Phase, active level 1 (S1) ---
  9868. Firing rl*prefer*rvt*predict-no*H0*4*v1*H1*37
  9869. -->
  9870. (S1 ^operator O1942 = -0.2714224023553999)
  9871. Firing rl*prefer*rvt*predict-yes*H0*3*v1*H1*38
  9872. -->
  9873. (S1 ^operator O1941 = 0.6622033637991441)
  9874. Firing prefer*rvt*predict-no*H0*4*v1*H1
  9875. -->
  9876. Firing prefer*rvt*predict-yes*H0*3*v1*H1
  9877. -->
  9878. Firing elaborate*copy-see-to-output-link
  9879. -->
  9880. (I3 ^see 1 +)
  9881. Firing elaborate*reward*based*on*reward
  9882. -->
  9883. (R975 ^value 1 +)
  9884. (R1 ^reward R975 +)
  9885. Firing propose*predict-yes
  9886. -->
  9887. (O1943 ^name predict-yes +)
  9888. (S1 ^operator O1943 +)
  9889. Firing propose*predict-no
  9890. -->
  9891. (O1944 ^name predict-no +)
  9892. (S1 ^operator O1944 +)
  9893. Firing rl*prefer*rvt*predict-no*H0*4
  9894. -->
  9895. (S1 ^operator O1942 = 0.339769731277316)
  9896. Firing rl*prefer*rvt*predict-yes*H0*3
  9897. -->
  9898. (S1 ^operator O1941 = 0.3377045556949833)
  9899. Firing prefer*rvt*predict-yes*H0
  9900. -->
  9901. Firing prefer*rvt*predict-no*H0
  9902. -->
  9903. Firing elaborate*copy-dir-to-output-link
  9904. -->
  9905. (I3 ^dir R +)
  9906. inner elaboration loop at bottom goal.
  9907. Retracting elaborate*copy-see-to-output-link
  9908. -->
  9909. (I3 ^see 0 +)
  9910. Retracting propose*predict-no
  9911. -->
  9912. (O1942 ^name predict-no +)
  9913. (S1 ^operator O1942 +)
  9914. Retracting propose*predict-yes
  9915. -->
  9916. (O1941 ^name predict-yes +)
  9917. (S1 ^operator O1941 +)
  9918. Retracting elaborate*reward*based*on*reward
  9919. -->
  9920. (R974 ^value 1 +)
  9921. (R1 ^reward R974 +)
  9922. Retracting elaborate*copy-dir-to-output-link
  9923. -->
  9924. (I3 ^dir L +)
  9925. Retracting rl*prefer*rvt*predict-no*H0*6
  9926. -->
  9927. (S1 ^operator O1942 = 0.9997480945179411)
  9928. Retracting rl*prefer*rvt*predict-yes*H0*5
  9929. -->
  9930. (S1 ^operator O1941 = 0.2640444846619989)
  9931. Retracting rl*prefer*rvt*predict-yes*H0*5*v1*H1*30
  9932. -->
  9933. (S1 ^operator O1941 = 0.735815301499146)
  9934. =>WM: (13694: S1 ^operator O1944 +)
  9935. =>WM: (13693: S1 ^operator O1943 +)
  9936. =>WM: (13692: I3 ^dir R)
  9937. =>WM: (13691: O1944 ^name predict-no)
  9938. =>WM: (13690: O1943 ^name predict-yes)
  9939. =>WM: (13689: R975 ^value 1)
  9940. =>WM: (13688: R1 ^reward R975)
  9941. =>WM: (13687: I3 ^see 1)
  9942. <=WM: (13678: S1 ^operator O1941 +)
  9943. <=WM: (13680: S1 ^operator O1941)
  9944. <=WM: (13679: S1 ^operator O1942 +)
  9945. <=WM: (13677: I3 ^dir L)
  9946. <=WM: (13673: R1 ^reward R974)
  9947. <=WM: (13645: I3 ^see 0)
  9948. <=WM: (13676: O1942 ^name predict-no)
  9949. <=WM: (13675: O1941 ^name predict-yes)
  9950. <=WM: (13674: R974 ^value 1)
  9951. --- Inner Elaboration Phase, active level 1 (S1) ---
  9952. Firing prefer*rvt*predict-yes*H0
  9953. -->
  9954. Firing rl*prefer*rvt*predict-yes*H0*3
  9955. -->
  9956. (S1 ^operator O1943 = 0.3377045556949833)
  9957. Firing prefer*rvt*predict-yes*H0*3*v1*H1
  9958. -->
  9959. Firing rl*prefer*rvt*predict-yes*H0*3*v1*H1*38
  9960. -->
  9961. (S1 ^operator O1943 = 0.6622033637991441)
  9962. Firing prefer*rvt*predict-no*H0
  9963. -->
  9964. Firing rl*prefer*rvt*predict-no*H0*4
  9965. -->
  9966. (S1 ^operator O1944 = 0.339769731277316)
  9967. Firing prefer*rvt*predict-no*H0*4*v1*H1
  9968. -->
  9969. Firing rl*prefer*rvt*predict-no*H0*4*v1*H1*37
  9970. -->
  9971. (S1 ^operator O1944 = -0.2714224023553999)
  9972. inner elaboration loop at bottom goal.
  9973. Retracting rl*prefer*rvt*predict-no*H0*4
  9974. -->
  9975. (S1 ^operator O1942 = 0.339769731277316)
  9976. Retracting rl*prefer*rvt*predict-no*H0*4*v1*H1*37
  9977. -->
  9978. (S1 ^operator O1942 = -0.2714224023553999)
  9979. Retracting rl*prefer*rvt*predict-yes*H0*3
  9980. -->
  9981. (S1 ^operator O1941 = 0.3377045556949833)
  9982. Retracting rl*prefer*rvt*predict-yes*H0*3*v1*H1*38
  9983. -->
  9984. (S1 ^operator O1941 = 0.6622033637991441)
  9985. --- END Proposal Phase ---
  9986. --- Decision Phase ---
  9987. RL update rl*prefer*rvt*predict-yes*H0*5 0.55443 -0.290385 0.264044 -> 0.554441 -0.290385 0.264056(R,m,v=1,0.874286,0.110542)
  9988. RL update rl*prefer*rvt*predict-yes*H0*5*v1*H1*30 0.445432 0.290383 0.735815 -> 0.445446 0.290383 0.735829(R,m,v=1,1,0)
  9989. =>WM: (13695: S1 ^operator O1943)
  9990. 972: O: O1943 (predict-yes)
  9991. --- END Decision Phase ---
  9992. --- Application Phase ---
  9993. --- Firing Productions (PE) For State At Depth 1 ---
  9994. --- Inner Elaboration Phase, active level 1 (S1) ---
  9995. Firing apply*operator
  9996. -->
  9997. (I3 ^predict-yes N972 + :O )
  9998. Firing apply*operator*complete
  9999. -->
  10000. (I3 ^predict-yes N971 - :O )
  10001. inner elaboration loop at bottom goal.
  10002. --- Change Working Memory (PE) ---
  10003. =>WM: (13696: I3 ^predict-yes N972)
  10004. <=WM: (13682: N971 ^status complete)
  10005. <=WM: (13681: I3 ^predict-yes N971)
  10006. --- Firing Productions (IE) For State At Depth 1 ---
  10007. --- Inner Elaboration Phase, active level 1 (S1) ---
  10008. Firing monitor*world
  10009. -->
  10010. I see 1 and I'm going to do: predict-yes inner elaboration loop at bottom goal.
  10011. --- Change Working Memory (IE) ---
  10012. --- END Application Phase ---
  10013. --- Output Phase ---
  10014. ENV: Agent did: predict-yes for direction R in state State-A
  10015. In State-A moving R
  10016. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  10017. predict error 0
  10018. dir: dir isL
  10019. --- END Output Phase ---
  10020. |\---- Input Phase ---
  10021. =>WM: (13700: I2 ^dir L)
  10022. =>WM: (13699: I2 ^reward 1)
  10023. =>WM: (13698: I2 ^see 1)
  10024. =>WM: (13697: N972 ^status complete)
  10025. <=WM: (13685: I2 ^dir R)
  10026. <=WM: (13684: I2 ^reward 1)
  10027. <=WM: (13683: I2 ^see 1)
  10028. =>WM: (13701: I2 ^level-1 R1-root)
  10029. <=WM: (13686: I2 ^level-1 L1-root)
  10030. --- END Input Phase ---
  10031. --- Proposal Phase ---
  10032. --- Inner Elaboration Phase, active level 1 (S1) ---
  10033. Firing rl*prefer*rvt*predict-yes*H0*5*v1*H1*41
  10034. -->
  10035. (S1 ^operator O1943 = 0.7362862485154646)
  10036. Firing prefer*rvt*predict-yes*H0*5*v1*H1
  10037. -->
  10038. Firing elaborate*copy-see-to-output-link
  10039. -->
  10040. (I3 ^see 1 +)
  10041. Firing elaborate*reward*based*on*reward
  10042. -->
  10043. (R976 ^value 1 +)
  10044. (R1 ^reward R976 +)
  10045. Firing propose*predict-yes
  10046. -->
  10047. (O1945 ^name predict-yes +)
  10048. (S1 ^operator O1945 +)
  10049. Firing propose*predict-no
  10050. -->
  10051. (O1946 ^name predict-no +)
  10052. (S1 ^operator O1946 +)
  10053. Firing rl*prefer*rvt*predict-no*H0*6
  10054. -->
  10055. (S1 ^operator O1944 = 0.9997480945179411)
  10056. Firing rl*prefer*rvt*predict-yes*H0*5
  10057. -->
  10058. (S1 ^operator O1943 = 0.2640558568198847)
  10059. Firing prefer*rvt*predict-yes*H0
  10060. -->
  10061. Firing prefer*rvt*predict-no*H0
  10062. -->
  10063. Firing elaborate*copy-dir-to-output-link
  10064. -->
  10065. (I3 ^dir L +)
  10066. inner elaboration loop at bottom goal.
  10067. Retracting elaborate*copy-see-to-output-link
  10068. -->
  10069. (I3 ^see 1 +)
  10070. Retracting propose*predict-no
  10071. -->
  10072. (O1944 ^name predict-no +)
  10073. (S1 ^operator O1944 +)
  10074. Retracting propose*predict-yes
  10075. -->
  10076. (O1943 ^name predict-yes +)
  10077. (S1 ^operator O1943 +)
  10078. Retracting elaborate*reward*based*on*reward
  10079. -->
  10080. (R975 ^value 1 +)
  10081. (R1 ^reward R975 +)
  10082. Retracting elaborate*copy-dir-to-output-link
  10083. -->
  10084. (I3 ^dir R +)
  10085. Retracting rl*prefer*rvt*predict-no*H0*4*v1*H1*37
  10086. -->
  10087. (S1 ^operator O1944 = -0.2714224023553999)
  10088. Retracting rl*prefer*rvt*predict-no*H0*4
  10089. -->
  10090. (S1 ^operator O1944 = 0.339769731277316)
  10091. Retracting rl*prefer*rvt*predict-yes*H0*3*v1*H1*38
  10092. -->
  10093. (S1 ^operator O1943 = 0.6622033637991441)
  10094. Retracting rl*prefer*rvt*predict-yes*H0*3
  10095. -->
  10096. (S1 ^operator O1943 = 0.3377045556949833)
  10097. =>WM: (13708: S1 ^operator O1946 +)
  10098. =>WM: (13707: S1 ^operator O1945 +)
  10099. =>WM: (13706: I3 ^dir L)
  10100. =>WM: (13705: O1946 ^name predict-no)
  10101. =>WM: (13704: O1945 ^name predict-yes)
  10102. =>WM: (13703: R976 ^value 1)
  10103. =>WM: (13702: R1 ^reward R976)
  10104. <=WM: (13693: S1 ^operator O1943 +)
  10105. <=WM: (13695: S1 ^operator O1943)
  10106. <=WM: (13694: S1 ^operator O1944 +)
  10107. <=WM: (13692: I3 ^dir R)
  10108. <=WM: (13688: R1 ^reward R975)
  10109. <=WM: (13691: O1944 ^name predict-no)
  10110. <=WM: (13690: O1943 ^name predict-yes)
  10111. <=WM: (13689: R975 ^value 1)
  10112. --- Inner Elaboration Phase, active level 1 (S1) ---
  10113. Firing prefer*rvt*predict-yes*H0
  10114. -->
  10115. Firing rl*prefer*rvt*predict-yes*H0*5
  10116. -->
  10117. (S1 ^operator O1945 = 0.2640558568198847)
  10118. Firing prefer*rvt*predict-yes*H0*5*v1*H1
  10119. -->
  10120. Firing rl*prefer*rvt*predict-yes*H0*5*v1*H1*41
  10121. -->
  10122. (S1 ^operator O1945 = 0.7362862485154646)
  10123. Firing prefer*rvt*predict-no*H0
  10124. -->
  10125. Firing rl*prefer*rvt*predict-no*H0*6
  10126. -->
  10127. (S1 ^operator O1946 = 0.9997480945179411)
  10128. inner elaboration loop at bottom goal.
  10129. Retracting rl*prefer*rvt*predict-no*H0*6
  10130. -->
  10131. (S1 ^operator O1944 = 0.9997480945179411)
  10132. Retracting rl*prefer*rvt*predict-yes*H0*5
  10133. -->
  10134. (S1 ^operator O1943 = 0.2640558568198847)
  10135. Retracting rl*prefer*rvt*predict-yes*H0*5*v1*H1*41
  10136. -->
  10137. (S1 ^operator O1943 = 0.7362862485154646)
  10138. --- END Proposal Phase ---
  10139. --- Decision Phase ---
  10140. RL update rl*prefer*rvt*predict-yes*H0*3 0.590104 -0.252399 0.337705 -> 0.590112 -0.2524 0.337712(R,m,v=1,0.896341,0.0934835)
  10141. RL update rl*prefer*rvt*predict-yes*H0*3*v1*H1*38 0.40979 0.252413 0.662203 -> 0.4098 0.252412 0.662212(R,m,v=1,1,0)
  10142. =>WM: (13709: S1 ^operator O1945)
  10143. 973: O: O1945 (predict-yes)
  10144. --- END Decision Phase ---
  10145. --- Application Phase ---
  10146. --- Firing Productions (PE) For State At Depth 1 ---
  10147. --- Inner Elaboration Phase, active level 1 (S1) ---
  10148. Firing apply*operator
  10149. -->
  10150. (I3 ^predict-yes N973 + :O )
  10151. Firing apply*operator*complete
  10152. -->
  10153. (I3 ^predict-yes N972 - :O )
  10154. inner elaboration loop at bottom goal.
  10155. --- Change Working Memory (PE) ---
  10156. =>WM: (13710: I3 ^predict-yes N973)
  10157. <=WM: (13697: N972 ^status complete)
  10158. <=WM: (13696: I3 ^predict-yes N972)
  10159. --- Firing Productions (IE) For State At Depth 1 ---
  10160. --- Inner Elaboration Phase, active level 1 (S1) ---
  10161. Firing monitor*world
  10162. -->
  10163. I see 1 and I'm going to do: predict-yes inner elaboration loop at bottom goal.
  10164. --- Change Working Memory (IE) ---
  10165. --- END Application Phase ---
  10166. --- Output Phase ---
  10167. ENV: Agent did: predict-yes for direction L in state State-B
  10168. In State-B moving L
  10169. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  10170. predict error 0
  10171. dir: dir isU
  10172. --- END Output Phase ---
  10173. /|\--- Input Phase ---
  10174. =>WM: (13714: I2 ^dir U)
  10175. =>WM: (13713: I2 ^reward 1)
  10176. =>WM: (13712: I2 ^see 1)
  10177. =>WM: (13711: N973 ^status complete)
  10178. <=WM: (13700: I2 ^dir L)
  10179. <=WM: (13699: I2 ^reward 1)
  10180. <=WM: (13698: I2 ^see 1)
  10181. =>WM: (13715: I2 ^level-1 L1-root)
  10182. <=WM: (13701: I2 ^level-1 R1-root)
  10183. --- END Input Phase ---
  10184. --- Proposal Phase ---
  10185. --- Inner Elaboration Phase, active level 1 (S1) ---
  10186. Firing elaborate*copy-see-to-output-link
  10187. -->
  10188. (I3 ^see 1 +)
  10189. Firing elaborate*reward*based*on*reward
  10190. -->
  10191. (R977 ^value 1 +)
  10192. (R1 ^reward R977 +)
  10193. Firing propose*predict-yes
  10194. -->
  10195. (O1947 ^name predict-yes +)
  10196. (S1 ^operator O1947 +)
  10197. Firing propose*predict-no
  10198. -->
  10199. (O1948 ^name predict-no +)
  10200. (S1 ^operator O1948 +)
  10201. Firing rl*prefer*rvt*predict-no*H0*2
  10202. -->
  10203. (S1 ^operator O1946 = 1.)
  10204. Firing rl*prefer*rvt*predict-yes*H0*1
  10205. -->
  10206. (S1 ^operator O1945 = 0.)
  10207. Firing prefer*rvt*predict-yes*H0
  10208. -->
  10209. Firing prefer*rvt*predict-no*H0
  10210. -->
  10211. Firing elaborate*copy-dir-to-output-link
  10212. -->
  10213. (I3 ^dir U +)
  10214. inner elaboration loop at bottom goal.
  10215. Retracting elaborate*copy-see-to-output-link
  10216. -->
  10217. (I3 ^see 1 +)
  10218. Retracting propose*predict-no
  10219. -->
  10220. (O1946 ^name predict-no +)
  10221. (S1 ^operator O1946 +)
  10222. Retracting propose*predict-yes
  10223. -->
  10224. (O1945 ^name predict-yes +)
  10225. (S1 ^operator O1945 +)
  10226. Retracting elaborate*reward*based*on*reward
  10227. -->
  10228. (R976 ^value 1 +)
  10229. (R1 ^reward R976 +)
  10230. Retracting elaborate*copy-dir-to-output-link
  10231. -->
  10232. (I3 ^dir L +)
  10233. Retracting rl*prefer*rvt*predict-no*H0*6
  10234. -->
  10235. (S1 ^operator O1946 = 0.9997480945179411)
  10236. Retracting rl*prefer*rvt*predict-yes*H0*5*v1*H1*41
  10237. -->
  10238. (S1 ^operator O1945 = 0.7362862485154646)
  10239. Retracting rl*prefer*rvt*predict-yes*H0*5
  10240. -->
  10241. (S1 ^operator O1945 = 0.2640558568198847)
  10242. =>WM: (13722: S1 ^operator O1948 +)
  10243. =>WM: (13721: S1 ^operator O1947 +)
  10244. =>WM: (13720: I3 ^dir U)
  10245. =>WM: (13719: O1948 ^name predict-no)
  10246. =>WM: (13718: O1947 ^name predict-yes)
  10247. =>WM: (13717: R977 ^value 1)
  10248. =>WM: (13716: R1 ^reward R977)
  10249. <=WM: (13707: S1 ^operator O1945 +)
  10250. <=WM: (13709: S1 ^operator O1945)
  10251. <=WM: (13708: S1 ^operator O1946 +)
  10252. <=WM: (13706: I3 ^dir L)
  10253. <=WM: (13702: R1 ^reward R976)
  10254. <=WM: (13705: O1946 ^name predict-no)
  10255. <=WM: (13704: O1945 ^name predict-yes)
  10256. <=WM: (13703: R976 ^value 1)
  10257. --- Inner Elaboration Phase, active level 1 (S1) ---
  10258. Firing prefer*rvt*predict-yes*H0
  10259. -->
  10260. Firing rl*prefer*rvt*predict-yes*H0*1
  10261. -->
  10262. (S1 ^operator O1947 = 0.)
  10263. Firing prefer*rvt*predict-no*H0
  10264. -->
  10265. Firing rl*prefer*rvt*predict-no*H0*2
  10266. -->
  10267. (S1 ^operator O1948 = 1.)
  10268. inner elaboration loop at bottom goal.
  10269. Retracting rl*prefer*rvt*predict-no*H0*2
  10270. -->
  10271. (S1 ^operator O1946 = 1.)
  10272. Retracting rl*prefer*rvt*predict-yes*H0*1
  10273. -->
  10274. (S1 ^operator O1945 = 0.)
  10275. --- END Proposal Phase ---
  10276. --- Decision Phase ---
  10277. RL update rl*prefer*rvt*predict-yes*H0*5 0.554441 -0.290385 0.264056 -> 0.554414 -0.290386 0.264028(R,m,v=1,0.875,0.11)
  10278. RL update rl*prefer*rvt*predict-yes*H0*5*v1*H1*41 0.445895 0.290391 0.736286 -> 0.445864 0.29039 0.736254(R,m,v=1,1,0)
  10279. =>WM: (13723: S1 ^operator O1948)
  10280. 974: O: O1948 (predict-no)
  10281. --- END Decision Phase ---
  10282. --- Application Phase ---
  10283. --- Firing Productions (PE) For State At Depth 1 ---
  10284. --- Inner Elaboration Phase, active level 1 (S1) ---
  10285. Firing apply*operator
  10286. -->
  10287. (I3 ^predict-no N974 + :O )
  10288. Firing apply*operator*complete
  10289. -->
  10290. (I3 ^predict-yes N973 - :O )
  10291. inner elaboration loop at bottom goal.
  10292. --- Change Working Memory (PE) ---
  10293. =>WM: (13724: I3 ^predict-no N974)
  10294. <=WM: (13711: N973 ^status complete)
  10295. <=WM: (13710: I3 ^predict-yes N973)
  10296. --- Firing Productions (IE) For State At Depth 1 ---
  10297. --- Inner Elaboration Phase, active level 1 (S1) ---
  10298. Firing monitor*world
  10299. -->
  10300. I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
  10301. --- Change Working Memory (IE) ---
  10302. --- END Application Phase ---
  10303. --- Output Phase ---
  10304. ENV: Agent did: predict-no for direction U in state State-A
  10305. In State-A moving U
  10306. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  10307. predict error 0
  10308. dir: dir isU
  10309. --- END Output Phase ---
  10310. -/|--- Input Phase ---
  10311. =>WM: (13728: I2 ^dir U)
  10312. =>WM: (13727: I2 ^reward 1)
  10313. =>WM: (13726: I2 ^see 0)
  10314. =>WM: (13725: N974 ^status complete)
  10315. <=WM: (13714: I2 ^dir U)
  10316. <=WM: (13713: I2 ^reward 1)
  10317. <=WM: (13712: I2 ^see 1)
  10318. =>WM: (13729: I2 ^level-1 L1-root)
  10319. <=WM: (13715: I2 ^level-1 L1-root)
  10320. --- END Input Phase ---
  10321. --- Proposal Phase ---
  10322. --- Inner Elaboration Phase, active level 1 (S1) ---
  10323. Firing elaborate*copy-see-to-output-link
  10324. -->
  10325. (I3 ^see 0 +)
  10326. Firing elaborate*reward*based*on*reward
  10327. -->
  10328. (R978 ^value 1 +)
  10329. (R1 ^reward R978 +)
  10330. Firing propose*predict-yes
  10331. -->
  10332. (O1949 ^name predict-yes +)
  10333. (S1 ^operator O1949 +)
  10334. Firing propose*predict-no
  10335. -->
  10336. (O1950 ^name predict-no +)
  10337. (S1 ^operator O1950 +)
  10338. Firing rl*prefer*rvt*predict-no*H0*2
  10339. -->
  10340. (S1 ^operator O1948 = 1.)
  10341. Firing rl*prefer*rvt*predict-yes*H0*1
  10342. -->
  10343. (S1 ^operator O1947 = 0.)
  10344. Firing prefer*rvt*predict-yes*H0
  10345. -->
  10346. Firing prefer*rvt*predict-no*H0
  10347. -->
  10348. Firing elaborate*copy-dir-to-output-link
  10349. -->
  10350. (I3 ^dir U +)
  10351. inner elaboration loop at bottom goal.
  10352. Retracting elaborate*copy-see-to-output-link
  10353. -->
  10354. (I3 ^see 1 +)
  10355. Retracting propose*predict-no
  10356. -->
  10357. (O1948 ^name predict-no +)
  10358. (S1 ^operator O1948 +)
  10359. Retracting propose*predict-yes
  10360. -->
  10361. (O1947 ^name predict-yes +)
  10362. (S1 ^operator O1947 +)
  10363. Retracting elaborate*reward*based*on*reward
  10364. -->
  10365. (R977 ^value 1 +)
  10366. (R1 ^reward R977 +)
  10367. Retracting elaborate*copy-dir-to-output-link
  10368. -->
  10369. (I3 ^dir U +)
  10370. Retracting rl*prefer*rvt*predict-no*H0*2
  10371. -->
  10372. (S1 ^operator O1948 = 1.)
  10373. Retracting rl*prefer*rvt*predict-yes*H0*1
  10374. -->
  10375. (S1 ^operator O1947 = 0.)
  10376. =>WM: (13736: S1 ^operator O1950 +)
  10377. =>WM: (13735: S1 ^operator O1949 +)
  10378. =>WM: (13734: O1950 ^name predict-no)
  10379. =>WM: (13733: O1949 ^name predict-yes)
  10380. =>WM: (13732: R978 ^value 1)
  10381. =>WM: (13731: R1 ^reward R978)
  10382. =>WM: (13730: I3 ^see 0)
  10383. <=WM: (13721: S1 ^operator O1947 +)
  10384. <=WM: (13722: S1 ^operator O1948 +)
  10385. <=WM: (13723: S1 ^operator O1948)
  10386. <=WM: (13716: R1 ^reward R977)
  10387. <=WM: (13687: I3 ^see 1)
  10388. <=WM: (13719: O1948 ^name predict-no)
  10389. <=WM: (13718: O1947 ^name predict-yes)
  10390. <=WM: (13717: R977 ^value 1)
  10391. --- Inner Elaboration Phase, active level 1 (S1) ---
  10392. Firing prefer*rvt*predict-yes*H0
  10393. -->
  10394. Firing rl*prefer*rvt*predict-yes*H0*1
  10395. -->
  10396. (S1 ^operator O1949 = 0.)
  10397. Firing prefer*rvt*predict-no*H0
  10398. -->
  10399. Firing rl*prefer*rvt*predict-no*H0*2
  10400. -->
  10401. (S1 ^operator O1950 = 1.)
  10402. inner elaboration loop at bottom goal.
  10403. Retracting rl*prefer*rvt*predict-no*H0*2
  10404. -->
  10405. (S1 ^operator O1948 = 1.)
  10406. Retracting rl*prefer*rvt*predict-yes*H0*1
  10407. -->
  10408. (S1 ^operator O1947 = 0.)
  10409. --- END Proposal Phase ---
  10410. --- Decision Phase ---
  10411. RL update rl*prefer*rvt*predict-no*H0*2 1 0 1 -> 1 0 1(R,m,v=1,1,0)
  10412. =>WM: (13737: S1 ^operator O1950)
  10413. 975: O: O1950 (predict-no)
  10414. --- END Decision Phase ---
  10415. --- Application Phase ---
  10416. --- Firing Productions (PE) For State At Depth 1 ---
  10417. --- Inner Elaboration Phase, active level 1 (S1) ---
  10418. Firing apply*operator
  10419. -->
  10420. (I3 ^predict-no N975 + :O )
  10421. Firing apply*operator*complete
  10422. -->
  10423. (I3 ^predict-no N974 - :O )
  10424. inner elaboration loop at bottom goal.
  10425. --- Change Working Memory (PE) ---
  10426. =>WM: (13738: I3 ^predict-no N975)
  10427. <=WM: (13725: N974 ^status complete)
  10428. <=WM: (13724: I3 ^predict-no N974)
  10429. --- Firing Productions (IE) For State At Depth 1 ---
  10430. --- Inner Elaboration Phase, active level 1 (S1) ---
  10431. Firing monitor*world
  10432. -->
  10433. I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
  10434. --- Change Working Memory (IE) ---
  10435. --- END Application Phase ---
  10436. --- Output Phase ---
  10437. ENV: Agent did: predict-no for direction U in state State-A
  10438. In State-A moving U
  10439. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  10440. predict error 0
  10441. dir: dir isR
  10442. --- END Output Phase ---
  10443. \-/--- Input Phase ---
  10444. =>WM: (13742: I2 ^dir R)
  10445. =>WM: (13741: I2 ^reward 1)
  10446. =>WM: (13740: I2 ^see 0)
  10447. =>WM: (13739: N975 ^status complete)
  10448. <=WM: (13728: I2 ^dir U)
  10449. <=WM: (13727: I2 ^reward 1)
  10450. <=WM: (13726: I2 ^see 0)
  10451. =>WM: (13743: I2 ^level-1 L1-root)
  10452. <=WM: (13729: I2 ^level-1 L1-root)
  10453. --- END Input Phase ---
  10454. --- Proposal Phase ---
  10455. --- Inner Elaboration Phase, active level 1 (S1) ---
  10456. Firing rl*prefer*rvt*predict-no*H0*4*v1*H1*37
  10457. -->
  10458. (S1 ^operator O1950 = -0.2714224023553999)
  10459. Firing rl*prefer*rvt*predict-yes*H0*3*v1*H1*38
  10460. -->
  10461. (S1 ^operator O1949 = 0.6622121600001568)
  10462. Firing prefer*rvt*predict-no*H0*4*v1*H1
  10463. -->
  10464. Firing prefer*rvt*predict-yes*H0*3*v1*H1
  10465. -->
  10466. Firing elaborate*copy-see-to-output-link
  10467. -->
  10468. (I3 ^see 0 +)
  10469. Firing elaborate*reward*based*on*reward
  10470. -->
  10471. (R979 ^value 1 +)
  10472. (R1 ^reward R979 +)
  10473. Firing propose*predict-yes
  10474. -->
  10475. (O1951 ^name predict-yes +)
  10476. (S1 ^operator O1951 +)
  10477. Firing propose*predict-no
  10478. -->
  10479. (O1952 ^name predict-no +)
  10480. (S1 ^operator O1952 +)
  10481. Firing rl*prefer*rvt*predict-no*H0*4
  10482. -->
  10483. (S1 ^operator O1950 = 0.339769731277316)
  10484. Firing rl*prefer*rvt*predict-yes*H0*3
  10485. -->
  10486. (S1 ^operator O1949 = 0.3377121034427055)
  10487. Firing prefer*rvt*predict-yes*H0
  10488. -->
  10489. Firing prefer*rvt*predict-no*H0
  10490. -->
  10491. Firing elaborate*copy-dir-to-output-link
  10492. -->
  10493. (I3 ^dir R +)
  10494. inner elaboration loop at bottom goal.
  10495. Retracting elaborate*copy-see-to-output-link
  10496. -->
  10497. (I3 ^see 0 +)
  10498. Retracting propose*predict-no
  10499. -->
  10500. (O1950 ^name predict-no +)
  10501. (S1 ^operator O1950 +)
  10502. Retracting propose*predict-yes
  10503. -->
  10504. (O1949 ^name predict-yes +)
  10505. (S1 ^operator O1949 +)
  10506. Retracting elaborate*reward*based*on*reward
  10507. -->
  10508. (R978 ^value 1 +)
  10509. (R1 ^reward R978 +)
  10510. Retracting elaborate*copy-dir-to-output-link
  10511. -->
  10512. (I3 ^dir U +)
  10513. Retracting rl*prefer*rvt*predict-no*H0*2
  10514. -->
  10515. (S1 ^operator O1950 = 1.)
  10516. Retracting rl*prefer*rvt*predict-yes*H0*1
  10517. -->
  10518. (S1 ^operator O1949 = 0.)
  10519. =>WM: (13750: S1 ^operator O1952 +)
  10520. =>WM: (13749: S1 ^operator O1951 +)
  10521. =>WM: (13748: I3 ^dir R)
  10522. =>WM: (13747: O1952 ^name predict-no)
  10523. =>WM: (13746: O1951 ^name predict-yes)
  10524. =>WM: (13745: R979 ^value 1)
  10525. =>WM: (13744: R1 ^reward R979)
  10526. <=WM: (13735: S1 ^operator O1949 +)
  10527. <=WM: (13736: S1 ^operator O1950 +)
  10528. <=WM: (13737: S1 ^operator O1950)
  10529. <=WM: (13720: I3 ^dir U)
  10530. <=WM: (13731: R1 ^reward R978)
  10531. <=WM: (13734: O1950 ^name predict-no)
  10532. <=WM: (13733: O1949 ^name predict-yes)
  10533. <=WM: (13732: R978 ^value 1)
  10534. --- Inner Elaboration Phase, active level 1 (S1) ---
  10535. Firing prefer*rvt*predict-yes*H0
  10536. -->
  10537. Firing rl*prefer*rvt*predict-yes*H0*3*v1*H1*38
  10538. -->
  10539. (S1 ^operator O1951 = 0.6622121600001568)
  10540. Firing rl*prefer*rvt*predict-yes*H0*3
  10541. -->
  10542. (S1 ^operator O1951 = 0.3377121034427055)
  10543. Firing prefer*rvt*predict-yes*H0*3*v1*H1
  10544. -->
  10545. Firing prefer*rvt*predict-no*H0
  10546. -->
  10547. Firing rl*prefer*rvt*predict-no*H0*4*v1*H1*37
  10548. -->
  10549. (S1 ^operator O1952 = -0.2714224023553999)
  10550. Firing rl*prefer*rvt*predict-no*H0*4
  10551. -->
  10552. (S1 ^operator O1952 = 0.339769731277316)
  10553. Firing prefer*rvt*predict-no*H0*4*v1*H1
  10554. -->
  10555. inner elaboration loop at bottom goal.
  10556. Retracting rl*prefer*rvt*predict-no*H0*4
  10557. -->
  10558. (S1 ^operator O1950 = 0.339769731277316)
  10559. Retracting rl*prefer*rvt*predict-no*H0*4*v1*H1*37
  10560. -->
  10561. (S1 ^operator O1950 = -0.2714224023553999)
  10562. Retracting rl*prefer*rvt*predict-yes*H0*3
  10563. -->
  10564. (S1 ^operator O1949 = 0.3377121034427055)
  10565. Retracting rl*prefer*rvt*predict-yes*H0*3*v1*H1*38
  10566. -->
  10567. (S1 ^operator O1949 = 0.6622121600001568)
  10568. --- END Proposal Phase ---
  10569. --- Decision Phase ---
  10570. RL update rl*prefer*rvt*predict-no*H0*2 1 0 1 -> 1 0 1(R,m,v=1,1,0)
  10571. =>WM: (13751: S1 ^operator O1951)
  10572. 976: O: O1951 (predict-yes)
  10573. --- END Decision Phase ---
  10574. --- Application Phase ---
  10575. --- Firing Productions (PE) For State At Depth 1 ---
  10576. --- Inner Elaboration Phase, active level 1 (S1) ---
  10577. Firing apply*operator
  10578. -->
  10579. (I3 ^predict-yes N976 + :O )
  10580. Firing apply*operator*complete
  10581. -->
  10582. (I3 ^predict-no N975 - :O )
  10583. inner elaboration loop at bottom goal.
  10584. --- Change Working Memory (PE) ---
  10585. =>WM: (13752: I3 ^predict-yes N976)
  10586. <=WM: (13739: N975 ^status complete)
  10587. <=WM: (13738: I3 ^predict-no N975)
  10588. --- Firing Productions (IE) For State At Depth 1 ---
  10589. --- Inner Elaboration Phase, active level 1 (S1) ---
  10590. Firing monitor*world
  10591. -->
  10592. I see 1 and I'm going to do: predict-yes inner elaboration loop at bottom goal.
  10593. --- Change Working Memory (IE) ---
  10594. --- END Application Phase ---
  10595. --- Output Phase ---
  10596. ENV: Agent did: predict-yes for direction R in state State-A
  10597. In State-A moving R
  10598. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  10599. predict error 0
  10600. dir: dir isU
  10601. --- END Output Phase ---
  10602. |\---- Input Phase ---
  10603. =>WM: (13756: I2 ^dir U)
  10604. =>WM: (13755: I2 ^reward 1)
  10605. =>WM: (13754: I2 ^see 1)
  10606. =>WM: (13753: N976 ^status complete)
  10607. <=WM: (13742: I2 ^dir R)
  10608. <=WM: (13741: I2 ^reward 1)
  10609. <=WM: (13740: I2 ^see 0)
  10610. =>WM: (13757: I2 ^level-1 R1-root)
  10611. <=WM: (13743: I2 ^level-1 L1-root)
  10612. --- END Input Phase ---
  10613. --- Proposal Phase ---
  10614. --- Inner Elaboration Phase, active level 1 (S1) ---
  10615. Firing elaborate*copy-see-to-output-link
  10616. -->
  10617. (I3 ^see 1 +)
  10618. Firing elaborate*reward*based*on*reward
  10619. -->
  10620. (R980 ^value 1 +)
  10621. (R1 ^reward R980 +)
  10622. Firing propose*predict-yes
  10623. -->
  10624. (O1953 ^name predict-yes +)
  10625. (S1 ^operator O1953 +)
  10626. Firing propose*predict-no
  10627. -->
  10628. (O1954 ^name predict-no +)
  10629. (S1 ^operator O1954 +)
  10630. Firing rl*prefer*rvt*predict-no*H0*2
  10631. -->
  10632. (S1 ^operator O1952 = 1.)
  10633. Firing rl*prefer*rvt*predict-yes*H0*1
  10634. -->
  10635. (S1 ^operator O1951 = 0.)
  10636. Firing prefer*rvt*predict-yes*H0
  10637. -->
  10638. Firing prefer*rvt*predict-no*H0
  10639. -->
  10640. Firing elaborate*copy-dir-to-output-link
  10641. -->
  10642. (I3 ^dir U +)
  10643. inner elaboration loop at bottom goal.
  10644. Retracting elaborate*copy-see-to-output-link
  10645. -->
  10646. (I3 ^see 0 +)
  10647. Retracting propose*predict-no
  10648. -->
  10649. (O1952 ^name predict-no +)
  10650. (S1 ^operator O1952 +)
  10651. Retracting propose*predict-yes
  10652. -->
  10653. (O1951 ^name predict-yes +)
  10654. (S1 ^operator O1951 +)
  10655. Retracting elaborate*reward*based*on*reward
  10656. -->
  10657. (R979 ^value 1 +)
  10658. (R1 ^reward R979 +)
  10659. Retracting elaborate*copy-dir-to-output-link
  10660. -->
  10661. (I3 ^dir R +)
  10662. Retracting rl*prefer*rvt*predict-no*H0*4
  10663. -->
  10664. (S1 ^operator O1952 = 0.339769731277316)
  10665. Retracting rl*prefer*rvt*predict-no*H0*4*v1*H1*37
  10666. -->
  10667. (S1 ^operator O1952 = -0.2714224023553999)
  10668. Retracting rl*prefer*rvt*predict-yes*H0*3
  10669. -->
  10670. (S1 ^operator O1951 = 0.3377121034427055)
  10671. Retracting rl*prefer*rvt*predict-yes*H0*3*v1*H1*38
  10672. -->
  10673. (S1 ^operator O1951 = 0.6622121600001568)
  10674. =>WM: (13765: S1 ^operator O1954 +)
  10675. =>WM: (13764: S1 ^operator O1953 +)
  10676. =>WM: (13763: I3 ^dir U)
  10677. =>WM: (13762: O1954 ^name predict-no)
  10678. =>WM: (13761: O1953 ^name predict-yes)
  10679. =>WM: (13760: R980 ^value 1)
  10680. =>WM: (13759: R1 ^reward R980)
  10681. =>WM: (13758: I3 ^see 1)
  10682. <=WM: (13749: S1 ^operator O1951 +)
  10683. <=WM: (13751: S1 ^operator O1951)
  10684. <=WM: (13750: S1 ^operator O1952 +)
  10685. <=WM: (13748: I3 ^dir R)
  10686. <=WM: (13744: R1 ^reward R979)
  10687. <=WM: (13730: I3 ^see 0)
  10688. <=WM: (13747: O1952 ^name predict-no)
  10689. <=WM: (13746: O1951 ^name predict-yes)
  10690. <=WM: (13745: R979 ^value 1)
  10691. --- Inner Elaboration Phase, active level 1 (S1) ---
  10692. Firing prefer*rvt*predict-yes*H0
  10693. -->
  10694. Firing rl*prefer*rvt*predict-yes*H0*1
  10695. -->
  10696. (S1 ^operator O1953 = 0.)
  10697. Firing prefer*rvt*predict-no*H0
  10698. -->
  10699. Firing rl*prefer*rvt*predict-no*H0*2
  10700. -->
  10701. (S1 ^operator O1954 = 1.)
  10702. inner elaboration loop at bottom goal.
  10703. Retracting rl*prefer*rvt*predict-no*H0*2
  10704. -->
  10705. (S1 ^operator O1952 = 1.)
  10706. Retracting rl*prefer*rvt*predict-yes*H0*1
  10707. -->
  10708. (S1 ^operator O1951 = 0.)
  10709. --- END Proposal Phase ---
  10710. --- Decision Phase ---
  10711. RL update rl*prefer*rvt*predict-yes*H0*3 0.590112 -0.2524 0.337712 -> 0.59012 -0.252401 0.337718(R,m,v=1,0.89697,0.0929786)
  10712. RL update rl*prefer*rvt*predict-yes*H0*3*v1*H1*38 0.4098 0.252412 0.662212 -> 0.409809 0.252411 0.662219(R,m,v=1,1,0)
  10713. =>WM: (13766: S1 ^operator O1954)
  10714. 977: O: O1954 (predict-no)
  10715. --- END Decision Phase ---
  10716. --- Application Phase ---
  10717. --- Firing Productions (PE) For State At Depth 1 ---
  10718. --- Inner Elaboration Phase, active level 1 (S1) ---
  10719. Firing apply*operator
  10720. -->
  10721. (I3 ^predict-no N977 + :O )
  10722. Firing apply*operator*complete
  10723. -->
  10724. (I3 ^predict-yes N976 - :O )
  10725. inner elaboration loop at bottom goal.
  10726. --- Change Working Memory (PE) ---
  10727. =>WM: (13767: I3 ^predict-no N977)
  10728. <=WM: (13753: N976 ^status complete)
  10729. <=WM: (13752: I3 ^predict-yes N976)
  10730. --- Firing Productions (IE) For State At Depth 1 ---
  10731. --- Inner Elaboration Phase, active level 1 (S1) ---
  10732. Firing monitor*world
  10733. -->
  10734. I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
  10735. --- Change Working Memory (IE) ---
  10736. --- END Application Phase ---
  10737. --- Output Phase ---
  10738. ENV: Agent did: predict-no for direction U in state State-B
  10739. In State-B moving U
  10740. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  10741. predict error 0
  10742. dir: dir isU
  10743. --- END Output Phase ---
  10744. /|\--- Input Phase ---
  10745. =>WM: (13771: I2 ^dir U)
  10746. =>WM: (13770: I2 ^reward 1)
  10747. =>WM: (13769: I2 ^see 0)
  10748. =>WM: (13768: N977 ^status complete)
  10749. <=WM: (13756: I2 ^dir U)
  10750. <=WM: (13755: I2 ^reward 1)
  10751. <=WM: (13754: I2 ^see 1)
  10752. =>WM: (13772: I2 ^level-1 R1-root)
  10753. <=WM: (13757: I2 ^level-1 R1-root)
  10754. --- END Input Phase ---
  10755. --- Proposal Phase ---
  10756. --- Inner Elaboration Phase, active level 1 (S1) ---
  10757. Firing elaborate*copy-see-to-output-link
  10758. -->
  10759. (I3 ^see 0 +)
  10760. Firing elaborate*reward*based*on*reward
  10761. -->
  10762. (R981 ^value 1 +)
  10763. (R1 ^reward R981 +)
  10764. Firing propose*predict-yes
  10765. -->
  10766. (O1955 ^name predict-yes +)
  10767. (S1 ^operator O1955 +)
  10768. Firing propose*predict-no
  10769. -->
  10770. (O1956 ^name predict-no +)
  10771. (S1 ^operator O1956 +)
  10772. Firing rl*prefer*rvt*predict-no*H0*2
  10773. -->
  10774. (S1 ^operator O1954 = 1.)
  10775. Firing rl*prefer*rvt*predict-yes*H0*1
  10776. -->
  10777. (S1 ^operator O1953 = 0.)
  10778. Firing prefer*rvt*predict-yes*H0
  10779. -->
  10780. Firing prefer*rvt*predict-no*H0
  10781. -->
  10782. Firing elaborate*copy-dir-to-output-link
  10783. -->
  10784. (I3 ^dir U +)
  10785. inner elaboration loop at bottom goal.
  10786. Retracting elaborate*copy-see-to-output-link
  10787. -->
  10788. (I3 ^see 1 +)
  10789. Retracting propose*predict-no
  10790. -->
  10791. (O1954 ^name predict-no +)
  10792. (S1 ^operator O1954 +)
  10793. Retracting propose*predict-yes
  10794. -->
  10795. (O1953 ^name predict-yes +)
  10796. (S1 ^operator O1953 +)
  10797. Retracting elaborate*reward*based*on*reward
  10798. -->
  10799. (R980 ^value 1 +)
  10800. (R1 ^reward R980 +)
  10801. Retracting elaborate*copy-dir-to-output-link
  10802. -->
  10803. (I3 ^dir U +)
  10804. Retracting rl*prefer*rvt*predict-no*H0*2
  10805. -->
  10806. (S1 ^operator O1954 = 1.)
  10807. Retracting rl*prefer*rvt*predict-yes*H0*1
  10808. -->
  10809. (S1 ^operator O1953 = 0.)
  10810. =>WM: (13779: S1 ^operator O1956 +)
  10811. =>WM: (13778: S1 ^operator O1955 +)
  10812. =>WM: (13777: O1956 ^name predict-no)
  10813. =>WM: (13776: O1955 ^name predict-yes)
  10814. =>WM: (13775: R981 ^value 1)
  10815. =>WM: (13774: R1 ^reward R981)
  10816. =>WM: (13773: I3 ^see 0)
  10817. <=WM: (13764: S1 ^operator O1953 +)
  10818. <=WM: (13765: S1 ^operator O1954 +)
  10819. <=WM: (13766: S1 ^operator O1954)
  10820. <=WM: (13759: R1 ^reward R980)
  10821. <=WM: (13758: I3 ^see 1)
  10822. <=WM: (13762: O1954 ^name predict-no)
  10823. <=WM: (13761: O1953 ^name predict-yes)
  10824. <=WM: (13760: R980 ^value 1)
  10825. --- Inner Elaboration Phase, active level 1 (S1) ---
  10826. Firing prefer*rvt*predict-yes*H0
  10827. -->
  10828. Firing rl*prefer*rvt*predict-yes*H0*1
  10829. -->
  10830. (S1 ^operator O1955 = 0.)
  10831. Firing prefer*rvt*predict-no*H0
  10832. -->
  10833. Firing rl*prefer*rvt*predict-no*H0*2
  10834. -->
  10835. (S1 ^operator O1956 = 1.)
  10836. inner elaboration loop at bottom goal.
  10837. Retracting rl*prefer*rvt*predict-no*H0*2
  10838. -->
  10839. (S1 ^operator O1954 = 1.)
  10840. Retracting rl*prefer*rvt*predict-yes*H0*1
  10841. -->
  10842. (S1 ^operator O1953 = 0.)
  10843. --- END Proposal Phase ---
  10844. --- Decision Phase ---
  10845. RL update rl*prefer*rvt*predict-no*H0*2 1 0 1 -> 1 0 1(R,m,v=1,1,0)
  10846. =>WM: (13780: S1 ^operator O1956)
  10847. 978: O: O1956 (predict-no)
  10848. --- END Decision Phase ---
  10849. --- Application Phase ---
  10850. --- Firing Productions (PE) For State At Depth 1 ---
  10851. --- Inner Elaboration Phase, active level 1 (S1) ---
  10852. Firing apply*operator
  10853. -->
  10854. (I3 ^predict-no N978 + :O )
  10855. Firing apply*operator*complete
  10856. -->
  10857. (I3 ^predict-no N977 - :O )
  10858. inner elaboration loop at bottom goal.
  10859. --- Change Working Memory (PE) ---
  10860. =>WM: (13781: I3 ^predict-no N978)
  10861. <=WM: (13768: N977 ^status complete)
  10862. <=WM: (13767: I3 ^predict-no N977)
  10863. --- Firing Productions (IE) For State At Depth 1 ---
  10864. --- Inner Elaboration Phase, active level 1 (S1) ---
  10865. Firing monitor*world
  10866. -->
  10867. I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
  10868. --- Change Working Memory (IE) ---
  10869. --- END Application Phase ---
  10870. --- Output Phase ---
  10871. ENV: Agent did: predict-no for direction U in state State-B
  10872. In State-B moving U
  10873. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  10874. predict error 0
  10875. dir: dir isR
  10876. --- END Output Phase ---
  10877. -/|--- Input Phase ---
  10878. =>WM: (13785: I2 ^dir R)
  10879. =>WM: (13784: I2 ^reward 1)
  10880. =>WM: (13783: I2 ^see 0)
  10881. =>WM: (13782: N978 ^status complete)
  10882. <=WM: (13771: I2 ^dir U)
  10883. <=WM: (13770: I2 ^reward 1)
  10884. <=WM: (13769: I2 ^see 0)
  10885. =>WM: (13786: I2 ^level-1 R1-root)
  10886. <=WM: (13772: I2 ^level-1 R1-root)
  10887. --- END Input Phase ---
  10888. --- Proposal Phase ---
  10889. --- Inner Elaboration Phase, active level 1 (S1) ---
  10890. Firing rl*prefer*rvt*predict-yes*H0*3*v1*H1*36
  10891. -->
  10892. (S1 ^operator O1955 = -0.1070236389116304)
  10893. Firing rl*prefer*rvt*predict-no*H0*4*v1*H1*35
  10894. -->
  10895. (S1 ^operator O1956 = 0.6602468953107985)
  10896. Firing prefer*rvt*predict-no*H0*4*v1*H1
  10897. -->
  10898. Firing prefer*rvt*predict-yes*H0*3*v1*H1
  10899. -->
  10900. Firing elaborate*copy-see-to-output-link
  10901. -->
  10902. (I3 ^see 0 +)
  10903. Firing elaborate*reward*based*on*reward
  10904. -->
  10905. (R982 ^value 1 +)
  10906. (R1 ^reward R982 +)
  10907. Firing propose*predict-yes
  10908. -->
  10909. (O1957 ^name predict-yes +)
  10910. (S1 ^operator O1957 +)
  10911. Firing propose*predict-no
  10912. -->
  10913. (O1958 ^name predict-no +)
  10914. (S1 ^operator O1958 +)
  10915. Firing rl*prefer*rvt*predict-no*H0*4
  10916. -->
  10917. (S1 ^operator O1956 = 0.339769731277316)
  10918. Firing rl*prefer*rvt*predict-yes*H0*3
  10919. -->
  10920. (S1 ^operator O1955 = 0.3377183053124619)
  10921. Firing prefer*rvt*predict-yes*H0
  10922. -->
  10923. Firing prefer*rvt*predict-no*H0
  10924. -->
  10925. Firing elaborate*copy-dir-to-output-link
  10926. -->
  10927. (I3 ^dir R +)
  10928. inner elaboration loop at bottom goal.
  10929. Retracting elaborate*copy-see-to-output-link
  10930. -->
  10931. (I3 ^see 0 +)
  10932. Retracting propose*predict-no
  10933. -->
  10934. (O1956 ^name predict-no +)
  10935. (S1 ^operator O1956 +)
  10936. Retracting propose*predict-yes
  10937. -->
  10938. (O1955 ^name predict-yes +)
  10939. (S1 ^operator O1955 +)
  10940. Retracting elaborate*reward*based*on*reward
  10941. -->
  10942. (R981 ^value 1 +)
  10943. (R1 ^reward R981 +)
  10944. Retracting elaborate*copy-dir-to-output-link
  10945. -->
  10946. (I3 ^dir U +)
  10947. Retracting rl*prefer*rvt*predict-no*H0*2
  10948. -->
  10949. (S1 ^operator O1956 = 1.)
  10950. Retracting rl*prefer*rvt*predict-yes*H0*1
  10951. -->
  10952. (S1 ^operator O1955 = 0.)
  10953. =>WM: (13793: S1 ^operator O1958 +)
  10954. =>WM: (13792: S1 ^operator O1957 +)
  10955. =>WM: (13791: I3 ^dir R)
  10956. =>WM: (13790: O1958 ^name predict-no)
  10957. =>WM: (13789: O1957 ^name predict-yes)
  10958. =>WM: (13788: R982 ^value 1)
  10959. =>WM: (13787: R1 ^reward R982)
  10960. <=WM: (13778: S1 ^operator O1955 +)
  10961. <=WM: (13779: S1 ^operator O1956 +)
  10962. <=WM: (13780: S1 ^operator O1956)
  10963. <=WM: (13763: I3 ^dir U)
  10964. <=WM: (13774: R1 ^reward R981)
  10965. <=WM: (13777: O1956 ^name predict-no)
  10966. <=WM: (13776: O1955 ^name predict-yes)
  10967. <=WM: (13775: R981 ^value 1)
  10968. --- Inner Elaboration Phase, active level 1 (S1) ---
  10969. Firing prefer*rvt*predict-yes*H0
  10970. -->
  10971. Firing rl*prefer*rvt*predict-yes*H0*3*v1*H1*36
  10972. -->
  10973. (S1 ^operator O1957 = -0.1070236389116304)
  10974. Firing rl*prefer*rvt*predict-yes*H0*3
  10975. -->
  10976. (S1 ^operator O1957 = 0.3377183053124619)
  10977. Firing prefer*rvt*predict-yes*H0*3*v1*H1
  10978. -->
  10979. Firing prefer*rvt*predict-no*H0
  10980. -->
  10981. Firing rl*prefer*rvt*predict-no*H0*4*v1*H1*35
  10982. -->
  10983. (S1 ^operator O1958 = 0.6602468953107985)
  10984. Firing rl*prefer*rvt*predict-no*H0*4
  10985. -->
  10986. (S1 ^operator O1958 = 0.339769731277316)
  10987. Firing prefer*rvt*predict-no*H0*4*v1*H1
  10988. -->
  10989. inner elaboration loop at bottom goal.
  10990. Retracting rl*prefer*rvt*predict-no*H0*4
  10991. -->
  10992. (S1 ^operator O1956 = 0.339769731277316)
  10993. Retracting rl*prefer*rvt*predict-no*H0*4*v1*H1*35
  10994. -->
  10995. (S1 ^operator O1956 = 0.6602468953107985)
  10996. Retracting rl*prefer*rvt*predict-yes*H0*3
  10997. -->
  10998. (S1 ^operator O1955 = 0.3377183053124619)
  10999. Retracting rl*prefer*rvt*predict-yes*H0*3*v1*H1*36
  11000. -->
  11001. (S1 ^operator O1955 = -0.1070236389116304)
  11002. --- END Proposal Phase ---
  11003. --- Decision Phase ---
  11004. RL update rl*prefer*rvt*predict-no*H0*2 1 0 1 -> 1 0 1(R,m,v=1,1,0)
  11005. =>WM: (13794: S1 ^operator O1958)
  11006. 979: O: O1958 (predict-no)
  11007. --- END Decision Phase ---
  11008. --- Application Phase ---
  11009. --- Firing Productions (PE) For State At Depth 1 ---
  11010. --- Inner Elaboration Phase, active level 1 (S1) ---
  11011. Firing apply*operator
  11012. -->
  11013. (I3 ^predict-no N979 + :O )
  11014. Firing apply*operator*complete
  11015. -->
  11016. (I3 ^predict-no N978 - :O )
  11017. inner elaboration loop at bottom goal.
  11018. --- Change Working Memory (PE) ---
  11019. =>WM: (13795: I3 ^predict-no N979)
  11020. <=WM: (13782: N978 ^status complete)
  11021. <=WM: (13781: I3 ^predict-no N978)
  11022. --- Firing Productions (IE) For State At Depth 1 ---
  11023. --- Inner Elaboration Phase, active level 1 (S1) ---
  11024. Firing monitor*world
  11025. -->
  11026. I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
  11027. --- Change Working Memory (IE) ---
  11028. --- END Application Phase ---
  11029. --- Output Phase ---
  11030. ENV: Agent did: predict-no for direction R in state State-B
  11031. In State-B moving R
  11032. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  11033. predict error 0
  11034. dir: dir isU
  11035. --- END Output Phase ---
  11036. \-/--- Input Phase ---
  11037. =>WM: (13799: I2 ^dir U)
  11038. =>WM: (13798: I2 ^reward 1)
  11039. =>WM: (13797: I2 ^see 0)
  11040. =>WM: (13796: N979 ^status complete)
  11041. <=WM: (13785: I2 ^dir R)
  11042. <=WM: (13784: I2 ^reward 1)
  11043. <=WM: (13783: I2 ^see 0)
  11044. =>WM: (13800: I2 ^level-1 R0-root)
  11045. <=WM: (13786: I2 ^level-1 R1-root)
  11046. --- END Input Phase ---
  11047. --- Proposal Phase ---
  11048. --- Inner Elaboration Phase, active level 1 (S1) ---
  11049. Firing elaborate*copy-see-to-output-link
  11050. -->
  11051. (I3 ^see 0 +)
  11052. Firing elaborate*reward*based*on*reward
  11053. -->
  11054. (R983 ^value 1 +)
  11055. (R1 ^reward R983 +)
  11056. Firing propose*predict-yes
  11057. -->
  11058. (O1959 ^name predict-yes +)
  11059. (S1 ^operator O1959 +)
  11060. Firing propose*predict-no
  11061. -->
  11062. (O1960 ^name predict-no +)
  11063. (S1 ^operator O1960 +)
  11064. Firing rl*prefer*rvt*predict-no*H0*2
  11065. -->
  11066. (S1 ^operator O1958 = 1.)
  11067. Firing rl*prefer*rvt*predict-yes*H0*1
  11068. -->
  11069. (S1 ^operator O1957 = 0.)
  11070. Firing prefer*rvt*predict-yes*H0
  11071. -->
  11072. Firing prefer*rvt*predict-no*H0
  11073. -->
  11074. Firing elaborate*copy-dir-to-output-link
  11075. -->
  11076. (I3 ^dir U +)
  11077. inner elaboration loop at bottom goal.
  11078. Retracting elaborate*copy-see-to-output-link
  11079. -->
  11080. (I3 ^see 0 +)
  11081. Retracting propose*predict-no
  11082. -->
  11083. (O1958 ^name predict-no +)
  11084. (S1 ^operator O1958 +)
  11085. Retracting propose*predict-yes
  11086. -->
  11087. (O1957 ^name predict-yes +)
  11088. (S1 ^operator O1957 +)
  11089. Retracting elaborate*reward*based*on*reward
  11090. -->
  11091. (R982 ^value 1 +)
  11092. (R1 ^reward R982 +)
  11093. Retracting elaborate*copy-dir-to-output-link
  11094. -->
  11095. (I3 ^dir R +)
  11096. Retracting rl*prefer*rvt*predict-no*H0*4
  11097. -->
  11098. (S1 ^operator O1958 = 0.339769731277316)
  11099. Retracting rl*prefer*rvt*predict-no*H0*4*v1*H1*35
  11100. -->
  11101. (S1 ^operator O1958 = 0.6602468953107985)
  11102. Retracting rl*prefer*rvt*predict-yes*H0*3
  11103. -->
  11104. (S1 ^operator O1957 = 0.3377183053124619)
  11105. Retracting rl*prefer*rvt*predict-yes*H0*3*v1*H1*36
  11106. -->
  11107. (S1 ^operator O1957 = -0.1070236389116304)
  11108. =>WM: (13807: S1 ^operator O1960 +)
  11109. =>WM: (13806: S1 ^operator O1959 +)
  11110. =>WM: (13805: I3 ^dir U)
  11111. =>WM: (13804: O1960 ^name predict-no)
  11112. =>WM: (13803: O1959 ^name predict-yes)
  11113. =>WM: (13802: R983 ^value 1)
  11114. =>WM: (13801: R1 ^reward R983)
  11115. <=WM: (13792: S1 ^operator O1957 +)
  11116. <=WM: (13793: S1 ^operator O1958 +)
  11117. <=WM: (13794: S1 ^operator O1958)
  11118. <=WM: (13791: I3 ^dir R)
  11119. <=WM: (13787: R1 ^reward R982)
  11120. <=WM: (13790: O1958 ^name predict-no)
  11121. <=WM: (13789: O1957 ^name predict-yes)
  11122. <=WM: (13788: R982 ^value 1)
  11123. --- Inner Elaboration Phase, active level 1 (S1) ---
  11124. Firing prefer*rvt*predict-yes*H0
  11125. -->
  11126. Firing rl*prefer*rvt*predict-yes*H0*1
  11127. -->
  11128. (S1 ^operator O1959 = 0.)
  11129. Firing prefer*rvt*predict-no*H0
  11130. -->
  11131. Firing rl*prefer*rvt*predict-no*H0*2
  11132. -->
  11133. (S1 ^operator O1960 = 1.)
  11134. inner elaboration loop at bottom goal.
  11135. Retracting rl*prefer*rvt*predict-no*H0*2
  11136. -->
  11137. (S1 ^operator O1958 = 1.)
  11138. Retracting rl*prefer*rvt*predict-yes*H0*1
  11139. -->
  11140. (S1 ^operator O1957 = 0.)
  11141. --- END Proposal Phase ---
  11142. --- Decision Phase ---
  11143. RL update rl*prefer*rvt*predict-no*H0*4 0.570253 -0.230483 0.33977 -> 0.570252 -0.230483 0.339768(R,m,v=1,0.873494,0.111172)
  11144. RL update rl*prefer*rvt*predict-no*H0*4*v1*H1*35 0.429764 0.230483 0.660247 -> 0.429763 0.230483 0.660245(R,m,v=1,1,0)
  11145. =>WM: (13808: S1 ^operator O1960)
  11146. 980: O: O1960 (predict-no)
  11147. --- END Decision Phase ---
  11148. --- Application Phase ---
  11149. --- Firing Productions (PE) For State At Depth 1 ---
  11150. --- Inner Elaboration Phase, active level 1 (S1) ---
  11151. Firing apply*operator
  11152. -->
  11153. (I3 ^predict-no N980 + :O )
  11154. Firing apply*operator*complete
  11155. -->
  11156. (I3 ^predict-no N979 - :O )
  11157. inner elaboration loop at bottom goal.
  11158. --- Change Working Memory (PE) ---
  11159. =>WM: (13809: I3 ^predict-no N980)
  11160. <=WM: (13796: N979 ^status complete)
  11161. <=WM: (13795: I3 ^predict-no N979)
  11162. --- Firing Productions (IE) For State At Depth 1 ---
  11163. --- Inner Elaboration Phase, active level 1 (S1) ---
  11164. Firing monitor*world
  11165. -->
  11166. I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
  11167. --- Change Working Memory (IE) ---
  11168. --- END Application Phase ---
  11169. --- Output Phase ---
  11170. ENV: Agent did: predict-no for direction U in state State-B
  11171. In State-B moving U
  11172. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  11173. predict error 0
  11174. dir: dir isU
  11175. --- END Output Phase ---
  11176. |\--- Input Phase ---
  11177. =>WM: (13813: I2 ^dir U)
  11178. =>WM: (13812: I2 ^reward 1)
  11179. =>WM: (13811: I2 ^see 0)
  11180. =>WM: (13810: N980 ^status complete)
  11181. <=WM: (13799: I2 ^dir U)
  11182. <=WM: (13798: I2 ^reward 1)
  11183. <=WM: (13797: I2 ^see 0)
  11184. =>WM: (13814: I2 ^level-1 R0-root)
  11185. <=WM: (13800: I2 ^level-1 R0-root)
  11186. --- END Input Phase ---
  11187. --- Proposal Phase ---
  11188. --- Inner Elaboration Phase, active level 1 (S1) ---
  11189. Firing elaborate*copy-see-to-output-link
  11190. -->
  11191. (I3 ^see 0 +)
  11192. Firing elaborate*reward*based*on*reward
  11193. -->
  11194. (R984 ^value 1 +)
  11195. (R1 ^reward R984 +)
  11196. Firing propose*predict-yes
  11197. -->
  11198. (O1961 ^name predict-yes +)
  11199. (S1 ^operator O1961 +)
  11200. Firing propose*predict-no
  11201. -->
  11202. (O1962 ^name predict-no +)
  11203. (S1 ^operator O1962 +)
  11204. Firing rl*prefer*rvt*predict-no*H0*2
  11205. -->
  11206. (S1 ^operator O1960 = 1.)
  11207. Firing rl*prefer*rvt*predict-yes*H0*1
  11208. -->
  11209. (S1 ^operator O1959 = 0.)
  11210. Firing prefer*rvt*predict-yes*H0
  11211. -->
  11212. Firing prefer*rvt*predict-no*H0
  11213. -->
  11214. Firing elaborate*copy-dir-to-output-link
  11215. -->
  11216. (I3 ^dir U +)
  11217. inner elaboration loop at bottom goal.
  11218. Retracting elaborate*copy-see-to-output-link
  11219. -->
  11220. (I3 ^see 0 +)
  11221. Retracting propose*predict-no
  11222. -->
  11223. (O1960 ^name predict-no +)
  11224. (S1 ^operator O1960 +)
  11225. Retracting propose*predict-yes
  11226. -->
  11227. (O1959 ^name predict-yes +)
  11228. (S1 ^operator O1959 +)
  11229. Retracting elaborate*reward*based*on*reward
  11230. -->
  11231. (R983 ^value 1 +)
  11232. (R1 ^reward R983 +)
  11233. Retracting elaborate*copy-dir-to-output-link
  11234. -->
  11235. (I3 ^dir U +)
  11236. Retracting rl*prefer*rvt*predict-no*H0*2
  11237. -->
  11238. (S1 ^operator O1960 = 1.)
  11239. Retracting rl*prefer*rvt*predict-yes*H0*1
  11240. -->
  11241. (S1 ^operator O1959 = 0.)
  11242. =>WM: (13820: S1 ^operator O1962 +)
  11243. =>WM: (13819: S1 ^operator O1961 +)
  11244. =>WM: (13818: O1962 ^name predict-no)
  11245. =>WM: (13817: O1961 ^name predict-yes)
  11246. =>WM: (13816: R984 ^value 1)
  11247. =>WM: (13815: R1 ^reward R984)
  11248. <=WM: (13806: S1 ^operator O1959 +)
  11249. <=WM: (13807: S1 ^operator O1960 +)
  11250. <=WM: (13808: S1 ^operator O1960)
  11251. <=WM: (13801: R1 ^reward R983)
  11252. <=WM: (13804: O1960 ^name predict-no)
  11253. <=WM: (13803: O1959 ^name predict-yes)
  11254. <=WM: (13802: R983 ^value 1)
  11255. --- Inner Elaboration Phase, active level 1 (S1) ---
  11256. Firing prefer*rvt*predict-yes*H0
  11257. -->
  11258. Firing rl*prefer*rvt*predict-yes*H0*1
  11259. -->
  11260. (S1 ^operator O1961 = 0.)
  11261. Firing prefer*rvt*predict-no*H0
  11262. -->
  11263. Firing rl*prefer*rvt*predict-no*H0*2
  11264. -->
  11265. (S1 ^operator O1962 = 1.)
  11266. inner elaboration loop at bottom goal.
  11267. Retracting rl*prefer*rvt*predict-no*H0*2
  11268. -->
  11269. (S1 ^operator O1960 = 1.)
  11270. Retracting rl*prefer*rvt*predict-yes*H0*1
  11271. -->
  11272. (S1 ^operator O1959 = 0.)
  11273. --- END Proposal Phase ---
  11274. --- Decision Phase ---
  11275. RL update rl*prefer*rvt*predict-no*H0*2 1 0 1 -> 1 0 1(R,m,v=1,1,0)
  11276. =>WM: (13821: S1 ^operator O1962)
  11277. 981: O: O1962 (predict-no)
  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-no N981 + :O )
  11285. Firing apply*operator*complete
  11286. -->
  11287. (I3 ^predict-no N980 - :O )
  11288. inner elaboration loop at bottom goal.
  11289. --- Change Working Memory (PE) ---
  11290. =>WM: (13822: I3 ^predict-no N981)
  11291. <=WM: (13810: N980 ^status complete)
  11292. <=WM: (13809: I3 ^predict-no 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-no inner elaboration loop at bottom goal.
  11298. --- Change Working Memory (IE) ---
  11299. --- END Application Phase ---
  11300. --- Output Phase ---
  11301. ENV: Agent did: predict-no for direction U in state State-B
  11302. In State-B moving U
  11303. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  11304. predict error 0
  11305. dir: dir isL
  11306. --- END Output Phase ---
  11307. ---- Input Phase ---
  11308. =>WM: (13826: I2 ^dir L)
  11309. =>WM: (13825: I2 ^reward 1)
  11310. =>WM: (13824: I2 ^see 0)
  11311. =>WM: (13823: N981 ^status complete)
  11312. <=WM: (13813: I2 ^dir U)
  11313. <=WM: (13812: I2 ^reward 1)
  11314. <=WM: (13811: I2 ^see 0)
  11315. =>WM: (13827: I2 ^level-1 R0-root)
  11316. <=WM: (13814: I2 ^level-1 R0-root)
  11317. --- END Input Phase ---
  11318. --- Proposal Phase ---
  11319. --- Inner Elaboration Phase, active level 1 (S1) ---
  11320. Firing rl*prefer*rvt*predict-yes*H0*5*v1*H1*30
  11321. -->
  11322. (S1 ^operator O1961 = 0.7358289752034343)
  11323. Firing prefer*rvt*predict-yes*H0*5*v1*H1
  11324. -->
  11325. Firing elaborate*copy-see-to-output-link
  11326. -->
  11327. (I3 ^see 0 +)
  11328. Firing elaborate*reward*based*on*reward
  11329. -->
  11330. (R985 ^value 1 +)
  11331. (R1 ^reward R985 +)
  11332. Firing propose*predict-yes
  11333. -->
  11334. (O1963 ^name predict-yes +)
  11335. (S1 ^operator O1963 +)
  11336. Firing propose*predict-no
  11337. -->
  11338. (O1964 ^name predict-no +)
  11339. (S1 ^operator O1964 +)
  11340. Firing rl*prefer*rvt*predict-no*H0*6
  11341. -->
  11342. (S1 ^operator O1962 = 0.9997480945179411)
  11343. Firing rl*prefer*rvt*predict-yes*H0*5
  11344. -->
  11345. (S1 ^operator O1961 = 0.2640281357095451)
  11346. Firing prefer*rvt*predict-yes*H0
  11347. -->
  11348. Firing prefer*rvt*predict-no*H0
  11349. -->
  11350. Firing elaborate*copy-dir-to-output-link
  11351. -->
  11352. (I3 ^dir L +)
  11353. inner elaboration loop at bottom goal.
  11354. Retracting elaborate*copy-see-to-output-link
  11355. -->
  11356. (I3 ^see 0 +)
  11357. Retracting propose*predict-no
  11358. -->
  11359. (O1962 ^name predict-no +)
  11360. (S1 ^operator O1962 +)
  11361. Retracting propose*predict-yes
  11362. -->
  11363. (O1961 ^name predict-yes +)
  11364. (S1 ^operator O1961 +)
  11365. Retracting elaborate*reward*based*on*reward
  11366. -->
  11367. (R984 ^value 1 +)
  11368. (R1 ^reward R984 +)
  11369. Retracting elaborate*copy-dir-to-output-link
  11370. -->
  11371. (I3 ^dir U +)
  11372. Retracting rl*prefer*rvt*predict-no*H0*2
  11373. -->
  11374. (S1 ^operator O1962 = 1.)
  11375. Retracting rl*prefer*rvt*predict-yes*H0*1
  11376. -->
  11377. (S1 ^operator O1961 = 0.)
  11378. =>WM: (13834: S1 ^operator O1964 +)
  11379. =>WM: (13833: S1 ^operator O1963 +)
  11380. =>WM: (13832: I3 ^dir L)
  11381. =>WM: (13831: O1964 ^name predict-no)
  11382. =>WM: (13830: O1963 ^name predict-yes)
  11383. =>WM: (13829: R985 ^value 1)
  11384. =>WM: (13828: R1 ^reward R985)
  11385. <=WM: (13819: S1 ^operator O1961 +)
  11386. <=WM: (13820: S1 ^operator O1962 +)
  11387. <=WM: (13821: S1 ^operator O1962)
  11388. <=WM: (13805: I3 ^dir U)
  11389. <=WM: (13815: R1 ^reward R984)
  11390. <=WM: (13818: O1962 ^name predict-no)
  11391. <=WM: (13817: O1961 ^name predict-yes)
  11392. <=WM: (13816: R984 ^value 1)
  11393. --- Inner Elaboration Phase, active level 1 (S1) ---
  11394. Firing prefer*rvt*predict-yes*H0
  11395. -->
  11396. Firing rl*prefer*rvt*predict-yes*H0*5*v1*H1*30
  11397. -->
  11398. (S1 ^operator O1963 = 0.7358289752034343)
  11399. Firing rl*prefer*rvt*predict-yes*H0*5
  11400. -->
  11401. (S1 ^operator O1963 = 0.2640281357095451)
  11402. Firing prefer*rvt*predict-yes*H0*5*v1*H1
  11403. -->
  11404. Firing prefer*rvt*predict-no*H0
  11405. -->
  11406. Firing rl*prefer*rvt*predict-no*H0*6
  11407. -->
  11408. (S1 ^operator O1964 = 0.9997480945179411)
  11409. inner elaboration loop at bottom goal.
  11410. Retracting rl*prefer*rvt*predict-no*H0*6
  11411. -->
  11412. (S1 ^operator O1962 = 0.9997480945179411)
  11413. Retracting rl*prefer*rvt*predict-yes*H0*5
  11414. -->
  11415. (S1 ^operator O1961 = 0.2640281357095451)
  11416. Retracting rl*prefer*rvt*predict-yes*H0*5*v1*H1*30
  11417. -->
  11418. (S1 ^operator O1961 = 0.7358289752034343)
  11419. --- END Proposal Phase ---
  11420. --- Decision Phase ---
  11421. RL update rl*prefer*rvt*predict-no*H0*2 1 0 1 -> 1 0 1(R,m,v=1,1,0)
  11422. =>WM: (13835: S1 ^operator O1963)
  11423. 982: O: O1963 (predict-yes)
  11424. --- END Decision Phase ---
  11425. --- Application Phase ---
  11426. --- Firing Productions (PE) For State At Depth 1 ---
  11427. --- Inner Elaboration Phase, active level 1 (S1) ---
  11428. Firing apply*operator
  11429. -->
  11430. (I3 ^predict-yes N982 + :O )
  11431. Firing apply*operator*complete
  11432. -->
  11433. (I3 ^predict-no N981 - :O )
  11434. inner elaboration loop at bottom goal.
  11435. --- Change Working Memory (PE) ---
  11436. =>WM: (13836: I3 ^predict-yes N982)
  11437. <=WM: (13823: N981 ^status complete)
  11438. <=WM: (13822: I3 ^predict-no N981)
  11439. --- Firing Productions (IE) For State At Depth 1 ---
  11440. --- Inner Elaboration Phase, active level 1 (S1) ---
  11441. Firing monitor*world
  11442. -->
  11443. I see 1 and I'm going to do: predict-yes inner elaboration loop at bottom goal.
  11444. --- Change Working Memory (IE) ---
  11445. --- END Application Phase ---
  11446. --- Output Phase ---
  11447. ENV: Agent did: predict-yes for direction L in state State-B
  11448. In State-B moving L
  11449. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  11450. predict error 0
  11451. dir: dir isU
  11452. --- END Output Phase ---
  11453. /|\--- Input Phase ---
  11454. =>WM: (13840: I2 ^dir U)
  11455. =>WM: (13839: I2 ^reward 1)
  11456. =>WM: (13838: I2 ^see 1)
  11457. =>WM: (13837: N982 ^status complete)
  11458. <=WM: (13826: I2 ^dir L)
  11459. <=WM: (13825: I2 ^reward 1)
  11460. <=WM: (13824: I2 ^see 0)
  11461. =>WM: (13841: I2 ^level-1 L1-root)
  11462. <=WM: (13827: I2 ^level-1 R0-root)
  11463. --- END Input Phase ---
  11464. --- Proposal Phase ---
  11465. --- Inner Elaboration Phase, active level 1 (S1) ---
  11466. Firing elaborate*copy-see-to-output-link
  11467. -->
  11468. (I3 ^see 1 +)
  11469. Firing elaborate*reward*based*on*reward
  11470. -->
  11471. (R986 ^value 1 +)
  11472. (R1 ^reward R986 +)
  11473. Firing propose*predict-yes
  11474. -->
  11475. (O1965 ^name predict-yes +)
  11476. (S1 ^operator O1965 +)
  11477. Firing propose*predict-no
  11478. -->
  11479. (O1966 ^name predict-no +)
  11480. (S1 ^operator O1966 +)
  11481. Firing rl*prefer*rvt*predict-no*H0*2
  11482. -->
  11483. (S1 ^operator O1964 = 1.)
  11484. Firing rl*prefer*rvt*predict-yes*H0*1
  11485. -->
  11486. (S1 ^operator O1963 = 0.)
  11487. Firing prefer*rvt*predict-yes*H0
  11488. -->
  11489. Firing prefer*rvt*predict-no*H0
  11490. -->
  11491. Firing elaborate*copy-dir-to-output-link
  11492. -->
  11493. (I3 ^dir U +)
  11494. inner elaboration loop at bottom goal.
  11495. Retracting elaborate*copy-see-to-output-link
  11496. -->
  11497. (I3 ^see 0 +)
  11498. Retracting propose*predict-no
  11499. -->
  11500. (O1964 ^name predict-no +)
  11501. (S1 ^operator O1964 +)
  11502. Retracting propose*predict-yes
  11503. -->
  11504. (O1963 ^name predict-yes +)
  11505. (S1 ^operator O1963 +)
  11506. Retracting elaborate*reward*based*on*reward
  11507. -->
  11508. (R985 ^value 1 +)
  11509. (R1 ^reward R985 +)
  11510. Retracting elaborate*copy-dir-to-output-link
  11511. -->
  11512. (I3 ^dir L +)
  11513. Retracting rl*prefer*rvt*predict-no*H0*6
  11514. -->
  11515. (S1 ^operator O1964 = 0.9997480945179411)
  11516. Retracting rl*prefer*rvt*predict-yes*H0*5
  11517. -->
  11518. (S1 ^operator O1963 = 0.2640281357095451)
  11519. Retracting rl*prefer*rvt*predict-yes*H0*5*v1*H1*30
  11520. -->
  11521. (S1 ^operator O1963 = 0.7358289752034343)
  11522. =>WM: (13849: S1 ^operator O1966 +)
  11523. =>WM: (13848: S1 ^operator O1965 +)
  11524. =>WM: (13847: I3 ^dir U)
  11525. =>WM: (13846: O1966 ^name predict-no)
  11526. =>WM: (13845: O1965 ^name predict-yes)
  11527. =>WM: (13844: R986 ^value 1)
  11528. =>WM: (13843: R1 ^reward R986)
  11529. =>WM: (13842: I3 ^see 1)
  11530. <=WM: (13833: S1 ^operator O1963 +)
  11531. <=WM: (13835: S1 ^operator O1963)
  11532. <=WM: (13834: S1 ^operator O1964 +)
  11533. <=WM: (13832: I3 ^dir L)
  11534. <=WM: (13828: R1 ^reward R985)
  11535. <=WM: (13773: I3 ^see 0)
  11536. <=WM: (13831: O1964 ^name predict-no)
  11537. <=WM: (13830: O1963 ^name predict-yes)
  11538. <=WM: (13829: R985 ^value 1)
  11539. --- Inner Elaboration Phase, active level 1 (S1) ---
  11540. Firing prefer*rvt*predict-yes*H0
  11541. -->
  11542. Firing rl*prefer*rvt*predict-yes*H0*1
  11543. -->
  11544. (S1 ^operator O1965 = 0.)
  11545. Firing prefer*rvt*predict-no*H0
  11546. -->
  11547. Firing rl*prefer*rvt*predict-no*H0*2
  11548. -->
  11549. (S1 ^operator O1966 = 1.)
  11550. inner elaboration loop at bottom goal.
  11551. Retracting rl*prefer*rvt*predict-no*H0*2
  11552. -->
  11553. (S1 ^operator O1964 = 1.)
  11554. Retracting rl*prefer*rvt*predict-yes*H0*1
  11555. -->
  11556. (S1 ^operator O1963 = 0.)
  11557. --- END Proposal Phase ---
  11558. --- Decision Phase ---
  11559. RL update rl*prefer*rvt*predict-yes*H0*5 0.554414 -0.290386 0.264028 -> 0.554425 -0.290385 0.26404(R,m,v=1,0.875706,0.109463)
  11560. RL update rl*prefer*rvt*predict-yes*H0*5*v1*H1*30 0.445446 0.290383 0.735829 -> 0.44546 0.290383 0.735843(R,m,v=1,1,0)
  11561. =>WM: (13850: 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-yes N982 - :O )
  11573. inner elaboration loop at bottom goal.
  11574. --- Change Working Memory (PE) ---
  11575. =>WM: (13851: I3 ^predict-no N983)
  11576. <=WM: (13837: N982 ^status complete)
  11577. <=WM: (13836: I3 ^predict-yes 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 U in state State-A
  11587. In State-A moving U
  11588. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  11589. predict error 0
  11590. dir: dir isL
  11591. --- END Output Phase ---
  11592. -/|--- Input Phase ---
  11593. =>WM: (13855: I2 ^dir L)
  11594. =>WM: (13854: I2 ^reward 1)
  11595. =>WM: (13853: I2 ^see 0)
  11596. =>WM: (13852: N983 ^status complete)
  11597. <=WM: (13840: I2 ^dir U)
  11598. <=WM: (13839: I2 ^reward 1)
  11599. <=WM: (13838: I2 ^see 1)
  11600. =>WM: (13856: I2 ^level-1 L1-root)
  11601. <=WM: (13841: I2 ^level-1 L1-root)
  11602. --- END Input Phase ---
  11603. --- Proposal Phase ---
  11604. --- Inner Elaboration Phase, active level 1 (S1) ---
  11605. Firing rl*prefer*rvt*predict-yes*H0*5*v1*H1*31
  11606. -->
  11607. (S1 ^operator O1965 = -0.181727099742844)
  11608. Firing prefer*rvt*predict-yes*H0*5*v1*H1
  11609. -->
  11610. Firing elaborate*copy-see-to-output-link
  11611. -->
  11612. (I3 ^see 0 +)
  11613. Firing elaborate*reward*based*on*reward
  11614. -->
  11615. (R987 ^value 1 +)
  11616. (R1 ^reward R987 +)
  11617. Firing propose*predict-yes
  11618. -->
  11619. (O1967 ^name predict-yes +)
  11620. (S1 ^operator O1967 +)
  11621. Firing propose*predict-no
  11622. -->
  11623. (O1968 ^name predict-no +)
  11624. (S1 ^operator O1968 +)
  11625. Firing rl*prefer*rvt*predict-no*H0*6
  11626. -->
  11627. (S1 ^operator O1966 = 0.9997480945179411)
  11628. Firing rl*prefer*rvt*predict-yes*H0*5
  11629. -->
  11630. (S1 ^operator O1965 = 0.264039703522277)
  11631. Firing prefer*rvt*predict-yes*H0
  11632. -->
  11633. Firing prefer*rvt*predict-no*H0
  11634. -->
  11635. Firing elaborate*copy-dir-to-output-link
  11636. -->
  11637. (I3 ^dir L +)
  11638. inner elaboration loop at bottom goal.
  11639. Retracting elaborate*copy-see-to-output-link
  11640. -->
  11641. (I3 ^see 1 +)
  11642. Retracting propose*predict-no
  11643. -->
  11644. (O1966 ^name predict-no +)
  11645. (S1 ^operator O1966 +)
  11646. Retracting propose*predict-yes
  11647. -->
  11648. (O1965 ^name predict-yes +)
  11649. (S1 ^operator O1965 +)
  11650. Retracting elaborate*reward*based*on*reward
  11651. -->
  11652. (R986 ^value 1 +)
  11653. (R1 ^reward R986 +)
  11654. Retracting elaborate*copy-dir-to-output-link
  11655. -->
  11656. (I3 ^dir U +)
  11657. Retracting rl*prefer*rvt*predict-no*H0*2
  11658. -->
  11659. (S1 ^operator O1966 = 1.)
  11660. Retracting rl*prefer*rvt*predict-yes*H0*1
  11661. -->
  11662. (S1 ^operator O1965 = 0.)
  11663. =>WM: (13864: S1 ^operator O1968 +)
  11664. =>WM: (13863: S1 ^operator O1967 +)
  11665. =>WM: (13862: I3 ^dir L)
  11666. =>WM: (13861: O1968 ^name predict-no)
  11667. =>WM: (13860: O1967 ^name predict-yes)
  11668. =>WM: (13859: R987 ^value 1)
  11669. =>WM: (13858: R1 ^reward R987)
  11670. =>WM: (13857: I3 ^see 0)
  11671. <=WM: (13848: S1 ^operator O1965 +)
  11672. <=WM: (13849: S1 ^operator O1966 +)
  11673. <=WM: (13850: S1 ^operator O1966)
  11674. <=WM: (13847: I3 ^dir U)
  11675. <=WM: (13843: R1 ^reward R986)
  11676. <=WM: (13842: I3 ^see 1)
  11677. <=WM: (13846: O1966 ^name predict-no)
  11678. <=WM: (13845: O1965 ^name predict-yes)
  11679. <=WM: (13844: R986 ^value 1)
  11680. --- Inner Elaboration Phase, active level 1 (S1) ---
  11681. Firing prefer*rvt*predict-yes*H0
  11682. -->
  11683. Firing rl*prefer*rvt*predict-yes*H0*5*v1*H1*31
  11684. -->
  11685. (S1 ^operator O1967 = -0.181727099742844)
  11686. Firing rl*prefer*rvt*predict-yes*H0*5
  11687. -->
  11688. (S1 ^operator O1967 = 0.264039703522277)
  11689. Firing prefer*rvt*predict-yes*H0*5*v1*H1
  11690. -->
  11691. Firing prefer*rvt*predict-no*H0
  11692. -->
  11693. Firing rl*prefer*rvt*predict-no*H0*6
  11694. -->
  11695. (S1 ^operator O1968 = 0.9997480945179411)
  11696. inner elaboration loop at bottom goal.
  11697. Retracting rl*prefer*rvt*predict-no*H0*6
  11698. -->
  11699. (S1 ^operator O1966 = 0.9997480945179411)
  11700. Retracting rl*prefer*rvt*predict-yes*H0*5
  11701. -->
  11702. (S1 ^operator O1965 = 0.264039703522277)
  11703. Retracting rl*prefer*rvt*predict-yes*H0*5*v1*H1*31
  11704. -->
  11705. (S1 ^operator O1965 = -0.181727099742844)
  11706. --- END Proposal Phase ---
  11707. --- Decision Phase ---
  11708. RL update rl*prefer*rvt*predict-no*H0*2 1 0 1 -> 1 0 1(R,m,v=1,1,0)
  11709. =>WM: (13865: S1 ^operator O1968)
  11710. 984: O: O1968 (predict-no)
  11711. --- END Decision Phase ---
  11712. --- Application Phase ---
  11713. --- Firing Productions (PE) For State At Depth 1 ---
  11714. --- Inner Elaboration Phase, active level 1 (S1) ---
  11715. Firing apply*operator
  11716. -->
  11717. (I3 ^predict-no N984 + :O )
  11718. Firing apply*operator*complete
  11719. -->
  11720. (I3 ^predict-no N983 - :O )
  11721. inner elaboration loop at bottom goal.
  11722. --- Change Working Memory (PE) ---
  11723. =>WM: (13866: I3 ^predict-no N984)
  11724. <=WM: (13852: N983 ^status complete)
  11725. <=WM: (13851: I3 ^predict-no N983)
  11726. --- Firing Productions (IE) For State At Depth 1 ---
  11727. --- Inner Elaboration Phase, active level 1 (S1) ---
  11728. Firing monitor*world
  11729. -->
  11730. I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
  11731. --- Change Working Memory (IE) ---
  11732. --- END Application Phase ---
  11733. --- Output Phase ---
  11734. ENV: Agent did: predict-no for direction L in state State-A
  11735. In State-A moving L
  11736. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  11737. predict error 0
  11738. dir: dir isU
  11739. --- END Output Phase ---
  11740. \-/--- Input Phase ---
  11741. =>WM: (13870: I2 ^dir U)
  11742. =>WM: (13869: I2 ^reward 1)
  11743. =>WM: (13868: I2 ^see 0)
  11744. =>WM: (13867: N984 ^status complete)
  11745. <=WM: (13855: I2 ^dir L)
  11746. <=WM: (13854: I2 ^reward 1)
  11747. <=WM: (13853: I2 ^see 0)
  11748. =>WM: (13871: I2 ^level-1 L0-root)
  11749. <=WM: (13856: I2 ^level-1 L1-root)
  11750. --- END Input Phase ---
  11751. --- Proposal Phase ---
  11752. --- Inner Elaboration Phase, active level 1 (S1) ---
  11753. Firing elaborate*copy-see-to-output-link
  11754. -->
  11755. (I3 ^see 0 +)
  11756. Firing elaborate*reward*based*on*reward
  11757. -->
  11758. (R988 ^value 1 +)
  11759. (R1 ^reward R988 +)
  11760. Firing propose*predict-yes
  11761. -->
  11762. (O1969 ^name predict-yes +)
  11763. (S1 ^operator O1969 +)
  11764. Firing propose*predict-no
  11765. -->
  11766. (O1970 ^name predict-no +)
  11767. (S1 ^operator O1970 +)
  11768. Firing rl*prefer*rvt*predict-no*H0*2
  11769. -->
  11770. (S1 ^operator O1968 = 1.)
  11771. Firing rl*prefer*rvt*predict-yes*H0*1
  11772. -->
  11773. (S1 ^operator O1967 = 0.)
  11774. Firing prefer*rvt*predict-yes*H0
  11775. -->
  11776. Firing prefer*rvt*predict-no*H0
  11777. -->
  11778. Firing elaborate*copy-dir-to-output-link
  11779. -->
  11780. (I3 ^dir U +)
  11781. inner elaboration loop at bottom goal.
  11782. Retracting elaborate*copy-see-to-output-link
  11783. -->
  11784. (I3 ^see 0 +)
  11785. Retracting propose*predict-no
  11786. -->
  11787. (O1968 ^name predict-no +)
  11788. (S1 ^operator O1968 +)
  11789. Retracting propose*predict-yes
  11790. -->
  11791. (O1967 ^name predict-yes +)
  11792. (S1 ^operator O1967 +)
  11793. Retracting elaborate*reward*based*on*reward
  11794. -->
  11795. (R987 ^value 1 +)
  11796. (R1 ^reward R987 +)
  11797. Retracting elaborate*copy-dir-to-output-link
  11798. -->
  11799. (I3 ^dir L +)
  11800. Retracting rl*prefer*rvt*predict-no*H0*6
  11801. -->
  11802. (S1 ^operator O1968 = 0.9997480945179411)
  11803. Retracting rl*prefer*rvt*predict-yes*H0*5
  11804. -->
  11805. (S1 ^operator O1967 = 0.264039703522277)
  11806. Retracting rl*prefer*rvt*predict-yes*H0*5*v1*H1*31
  11807. -->
  11808. (S1 ^operator O1967 = -0.181727099742844)
  11809. =>WM: (13878: S1 ^operator O1970 +)
  11810. =>WM: (13877: S1 ^operator O1969 +)
  11811. =>WM: (13876: I3 ^dir U)
  11812. =>WM: (13875: O1970 ^name predict-no)
  11813. =>WM: (13874: O1969 ^name predict-yes)
  11814. =>WM: (13873: R988 ^value 1)
  11815. =>WM: (13872: R1 ^reward R988)
  11816. <=WM: (13863: S1 ^operator O1967 +)
  11817. <=WM: (13864: S1 ^operator O1968 +)
  11818. <=WM: (13865: S1 ^operator O1968)
  11819. <=WM: (13862: I3 ^dir L)
  11820. <=WM: (13858: R1 ^reward R987)
  11821. <=WM: (13861: O1968 ^name predict-no)
  11822. <=WM: (13860: O1967 ^name predict-yes)
  11823. <=WM: (13859: R987 ^value 1)
  11824. --- Inner Elaboration Phase, active level 1 (S1) ---
  11825. Firing prefer*rvt*predict-yes*H0
  11826. -->
  11827. Firing rl*prefer*rvt*predict-yes*H0*1
  11828. -->
  11829. (S1 ^operator O1969 = 0.)
  11830. Firing prefer*rvt*predict-no*H0
  11831. -->
  11832. Firing rl*prefer*rvt*predict-no*H0*2
  11833. -->
  11834. (S1 ^operator O1970 = 1.)
  11835. inner elaboration loop at bottom goal.
  11836. Retracting rl*prefer*rvt*predict-no*H0*2
  11837. -->
  11838. (S1 ^operator O1968 = 1.)
  11839. Retracting rl*prefer*rvt*predict-yes*H0*1
  11840. -->
  11841. (S1 ^operator O1967 = 0.)
  11842. --- END Proposal Phase ---
  11843. --- Decision Phase ---
  11844. RL update rl*prefer*rvt*predict-no*H0*6 0.999748 0 0.999748 -> 0.99979 0 0.99979(R,m,v=1,0.904762,0.086758)
  11845. =>WM: (13879: S1 ^operator O1970)
  11846. 985: O: O1970 (predict-no)
  11847. --- END Decision Phase ---
  11848. --- Application Phase ---
  11849. --- Firing Productions (PE) For State At Depth 1 ---
  11850. --- Inner Elaboration Phase, active level 1 (S1) ---
  11851. Firing apply*operator
  11852. -->
  11853. (I3 ^predict-no N985 + :O )
  11854. Firing apply*operator*complete
  11855. -->
  11856. (I3 ^predict-no N984 - :O )
  11857. inner elaboration loop at bottom goal.
  11858. --- Change Working Memory (PE) ---
  11859. =>WM: (13880: I3 ^predict-no N985)
  11860. <=WM: (13867: N984 ^status complete)
  11861. <=WM: (13866: I3 ^predict-no N984)
  11862. --- Firing Productions (IE) For State At Depth 1 ---
  11863. --- Inner Elaboration Phase, active level 1 (S1) ---
  11864. Firing monitor*world
  11865. -->
  11866. I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
  11867. --- Change Working Memory (IE) ---
  11868. --- END Application Phase ---
  11869. --- Output Phase ---
  11870. ENV: Agent did: predict-no for direction U in state State-A
  11871. In State-A moving U
  11872. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  11873. predict error 0
  11874. dir: dir isR
  11875. --- END Output Phase ---
  11876. |\---- Input Phase ---
  11877. =>WM: (13884: I2 ^dir R)
  11878. =>WM: (13883: I2 ^reward 1)
  11879. =>WM: (13882: I2 ^see 0)
  11880. =>WM: (13881: N985 ^status complete)
  11881. <=WM: (13870: I2 ^dir U)
  11882. <=WM: (13869: I2 ^reward 1)
  11883. <=WM: (13868: I2 ^see 0)
  11884. =>WM: (13885: I2 ^level-1 L0-root)
  11885. <=WM: (13871: I2 ^level-1 L0-root)
  11886. --- END Input Phase ---
  11887. --- Proposal Phase ---
  11888. --- Inner Elaboration Phase, active level 1 (S1) ---
  11889. Firing rl*prefer*rvt*predict-no*H0*4*v1*H1*33
  11890. -->
  11891. (S1 ^operator O1970 = -0.2817060109291377)
  11892. Firing rl*prefer*rvt*predict-yes*H0*3*v1*H1*34
  11893. -->
  11894. (S1 ^operator O1969 = 0.6623600134734193)
  11895. Firing prefer*rvt*predict-no*H0*4*v1*H1
  11896. -->
  11897. Firing prefer*rvt*predict-yes*H0*3*v1*H1
  11898. -->
  11899. Firing elaborate*copy-see-to-output-link
  11900. -->
  11901. (I3 ^see 0 +)
  11902. Firing elaborate*reward*based*on*reward
  11903. -->
  11904. (R989 ^value 1 +)
  11905. (R1 ^reward R989 +)
  11906. Firing propose*predict-yes
  11907. -->
  11908. (O1971 ^name predict-yes +)
  11909. (S1 ^operator O1971 +)
  11910. Firing propose*predict-no
  11911. -->
  11912. (O1972 ^name predict-no +)
  11913. (S1 ^operator O1972 +)
  11914. Firing rl*prefer*rvt*predict-no*H0*4
  11915. -->
  11916. (S1 ^operator O1970 = 0.3397683711152304)
  11917. Firing rl*prefer*rvt*predict-yes*H0*3
  11918. -->
  11919. (S1 ^operator O1969 = 0.3377183053124619)
  11920. Firing prefer*rvt*predict-yes*H0
  11921. -->
  11922. Firing prefer*rvt*predict-no*H0
  11923. -->
  11924. Firing elaborate*copy-dir-to-output-link
  11925. -->
  11926. (I3 ^dir R +)
  11927. inner elaboration loop at bottom goal.
  11928. Retracting elaborate*copy-see-to-output-link
  11929. -->
  11930. (I3 ^see 0 +)
  11931. Retracting propose*predict-no
  11932. -->
  11933. (O1970 ^name predict-no +)
  11934. (S1 ^operator O1970 +)
  11935. Retracting propose*predict-yes
  11936. -->
  11937. (O1969 ^name predict-yes +)
  11938. (S1 ^operator O1969 +)
  11939. Retracting elaborate*reward*based*on*reward
  11940. -->
  11941. (R988 ^value 1 +)
  11942. (R1 ^reward R988 +)
  11943. Retracting elaborate*copy-dir-to-output-link
  11944. -->
  11945. (I3 ^dir U +)
  11946. Retracting rl*prefer*rvt*predict-no*H0*2
  11947. -->
  11948. (S1 ^operator O1970 = 1.)
  11949. Retracting rl*prefer*rvt*predict-yes*H0*1
  11950. -->
  11951. (S1 ^operator O1969 = 0.)
  11952. =>WM: (13892: S1 ^operator O1972 +)
  11953. =>WM: (13891: S1 ^operator O1971 +)
  11954. =>WM: (13890: I3 ^dir R)
  11955. =>WM: (13889: O1972 ^name predict-no)
  11956. =>WM: (13888: O1971 ^name predict-yes)
  11957. =>WM: (13887: R989 ^value 1)
  11958. =>WM: (13886: R1 ^reward R989)
  11959. <=WM: (13877: S1 ^operator O1969 +)
  11960. <=WM: (13878: S1 ^operator O1970 +)
  11961. <=WM: (13879: S1 ^operator O1970)
  11962. <=WM: (13876: I3 ^dir U)
  11963. <=WM: (13872: R1 ^reward R988)
  11964. <=WM: (13875: O1970 ^name predict-no)
  11965. <=WM: (13874: O1969 ^name predict-yes)
  11966. <=WM: (13873: R988 ^value 1)
  11967. --- Inner Elaboration Phase, active level 1 (S1) ---
  11968. Firing prefer*rvt*predict-yes*H0
  11969. -->
  11970. Firing rl*prefer*rvt*predict-yes*H0*3*v1*H1*34
  11971. -->
  11972. (S1 ^operator O1971 = 0.6623600134734193)
  11973. Firing rl*prefer*rvt*predict-yes*H0*3
  11974. -->
  11975. (S1 ^operator O1971 = 0.3377183053124619)
  11976. Firing prefer*rvt*predict-yes*H0*3*v1*H1
  11977. -->
  11978. Firing prefer*rvt*predict-no*H0
  11979. -->
  11980. Firing rl*prefer*rvt*predict-no*H0*4*v1*H1*33
  11981. -->
  11982. (S1 ^operator O1972 = -0.2817060109291377)
  11983. Firing rl*prefer*rvt*predict-no*H0*4
  11984. -->
  11985. (S1 ^operator O1972 = 0.3397683711152304)
  11986. Firing prefer*rvt*predict-no*H0*4*v1*H1
  11987. -->
  11988. inner elaboration loop at bottom goal.
  11989. Retracting rl*prefer*rvt*predict-no*H0*4
  11990. -->
  11991. (S1 ^operator O1970 = 0.3397683711152304)
  11992. Retracting rl*prefer*rvt*predict-no*H0*4*v1*H1*33
  11993. -->
  11994. (S1 ^operator O1970 = -0.2817060109291377)
  11995. Retracting rl*prefer*rvt*predict-yes*H0*3
  11996. -->
  11997. (S1 ^operator O1969 = 0.3377183053124619)
  11998. Retracting rl*prefer*rvt*predict-yes*H0*3*v1*H1*34
  11999. -->
  12000. (S1 ^operator O1969 = 0.6623600134734193)
  12001. --- END Proposal Phase ---
  12002. --- Decision Phase ---
  12003. RL update rl*prefer*rvt*predict-no*H0*2 1 0 1 -> 1 0 1(R,m,v=1,1,0)
  12004. =>WM: (13893: S1 ^operator O1971)
  12005. 986: O: O1971 (predict-yes)
  12006. --- END Decision Phase ---
  12007. --- Application Phase ---
  12008. --- Firing Productions (PE) For State At Depth 1 ---
  12009. --- Inner Elaboration Phase, active level 1 (S1) ---
  12010. Firing apply*operator
  12011. -->
  12012. (I3 ^predict-yes N986 + :O )
  12013. Firing apply*operator*complete
  12014. -->
  12015. (I3 ^predict-no N985 - :O )
  12016. inner elaboration loop at bottom goal.
  12017. --- Change Working Memory (PE) ---
  12018. =>WM: (13894: I3 ^predict-yes N986)
  12019. <=WM: (13881: N985 ^status complete)
  12020. <=WM: (13880: I3 ^predict-no N985)
  12021. --- Firing Productions (IE) For State At Depth 1 ---
  12022. --- Inner Elaboration Phase, active level 1 (S1) ---
  12023. Firing monitor*world
  12024. -->
  12025. I see 1 and I'm going to do: predict-yes inner elaboration loop at bottom goal.
  12026. --- Change Working Memory (IE) ---
  12027. --- END Application Phase ---
  12028. --- Output Phase ---
  12029. ENV: Agent did: predict-yes for direction R in state State-A
  12030. In State-A moving R
  12031. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  12032. predict error 0
  12033. dir: dir isU
  12034. --- END Output Phase ---
  12035. /|\--- Input Phase ---
  12036. =>WM: (13898: I2 ^dir U)
  12037. =>WM: (13897: I2 ^reward 1)
  12038. =>WM: (13896: I2 ^see 1)
  12039. =>WM: (13895: N986 ^status complete)
  12040. <=WM: (13884: I2 ^dir R)
  12041. <=WM: (13883: I2 ^reward 1)
  12042. <=WM: (13882: I2 ^see 0)
  12043. =>WM: (13899: I2 ^level-1 R1-root)
  12044. <=WM: (13885: I2 ^level-1 L0-root)
  12045. --- END Input Phase ---
  12046. --- Proposal Phase ---
  12047. --- Inner Elaboration Phase, active level 1 (S1) ---
  12048. Firing elaborate*copy-see-to-output-link
  12049. -->
  12050. (I3 ^see 1 +)
  12051. Firing elaborate*reward*based*on*reward
  12052. -->
  12053. (R990 ^value 1 +)
  12054. (R1 ^reward R990 +)
  12055. Firing propose*predict-yes
  12056. -->
  12057. (O1973 ^name predict-yes +)
  12058. (S1 ^operator O1973 +)
  12059. Firing propose*predict-no
  12060. -->
  12061. (O1974 ^name predict-no +)
  12062. (S1 ^operator O1974 +)
  12063. Firing rl*prefer*rvt*predict-no*H0*2
  12064. -->
  12065. (S1 ^operator O1972 = 1.)
  12066. Firing rl*prefer*rvt*predict-yes*H0*1
  12067. -->
  12068. (S1 ^operator O1971 = 0.)
  12069. Firing prefer*rvt*predict-yes*H0
  12070. -->
  12071. Firing prefer*rvt*predict-no*H0
  12072. -->
  12073. Firing elaborate*copy-dir-to-output-link
  12074. -->
  12075. (I3 ^dir U +)
  12076. inner elaboration loop at bottom goal.
  12077. Retracting elaborate*copy-see-to-output-link
  12078. -->
  12079. (I3 ^see 0 +)
  12080. Retracting propose*predict-no
  12081. -->
  12082. (O1972 ^name predict-no +)
  12083. (S1 ^operator O1972 +)
  12084. Retracting propose*predict-yes
  12085. -->
  12086. (O1971 ^name predict-yes +)
  12087. (S1 ^operator O1971 +)
  12088. Retracting elaborate*reward*based*on*reward
  12089. -->
  12090. (R989 ^value 1 +)
  12091. (R1 ^reward R989 +)
  12092. Retracting elaborate*copy-dir-to-output-link
  12093. -->
  12094. (I3 ^dir R +)
  12095. Retracting rl*prefer*rvt*predict-no*H0*4
  12096. -->
  12097. (S1 ^operator O1972 = 0.3397683711152304)
  12098. Retracting rl*prefer*rvt*predict-no*H0*4*v1*H1*33
  12099. -->
  12100. (S1 ^operator O1972 = -0.2817060109291377)
  12101. Retracting rl*prefer*rvt*predict-yes*H0*3
  12102. -->
  12103. (S1 ^operator O1971 = 0.3377183053124619)
  12104. Retracting rl*prefer*rvt*predict-yes*H0*3*v1*H1*34
  12105. -->
  12106. (S1 ^operator O1971 = 0.6623600134734193)
  12107. =>WM: (13907: S1 ^operator O1974 +)
  12108. =>WM: (13906: S1 ^operator O1973 +)
  12109. =>WM: (13905: I3 ^dir U)
  12110. =>WM: (13904: O1974 ^name predict-no)
  12111. =>WM: (13903: O1973 ^name predict-yes)
  12112. =>WM: (13902: R990 ^value 1)
  12113. =>WM: (13901: R1 ^reward R990)
  12114. =>WM: (13900: I3 ^see 1)
  12115. <=WM: (13891: S1 ^operator O1971 +)
  12116. <=WM: (13893: S1 ^operator O1971)
  12117. <=WM: (13892: S1 ^operator O1972 +)
  12118. <=WM: (13890: I3 ^dir R)
  12119. <=WM: (13886: R1 ^reward R989)
  12120. <=WM: (13857: I3 ^see 0)
  12121. <=WM: (13889: O1972 ^name predict-no)
  12122. <=WM: (13888: O1971 ^name predict-yes)
  12123. <=WM: (13887: R989 ^value 1)
  12124. --- Inner Elaboration Phase, active level 1 (S1) ---
  12125. Firing prefer*rvt*predict-yes*H0
  12126. -->
  12127. Firing rl*prefer*rvt*predict-yes*H0*1
  12128. -->
  12129. (S1 ^operator O1973 = 0.)
  12130. Firing prefer*rvt*predict-no*H0
  12131. -->
  12132. Firing rl*prefer*rvt*predict-no*H0*2
  12133. -->
  12134. (S1 ^operator O1974 = 1.)
  12135. inner elaboration loop at bottom goal.
  12136. Retracting rl*prefer*rvt*predict-no*H0*2
  12137. -->
  12138. (S1 ^operator O1972 = 1.)
  12139. Retracting rl*prefer*rvt*predict-yes*H0*1
  12140. -->
  12141. (S1 ^operator O1971 = 0.)
  12142. --- END Proposal Phase ---
  12143. --- Decision Phase ---
  12144. RL update rl*prefer*rvt*predict-yes*H0*3 0.59012 -0.252401 0.337718 -> 0.590112 -0.2524 0.337712(R,m,v=1,0.89759,0.092479)
  12145. RL update rl*prefer*rvt*predict-yes*H0*3*v1*H1*34 0.409971 0.252389 0.66236 -> 0.409962 0.25239 0.662353(R,m,v=1,1,0)
  12146. =>WM: (13908: S1 ^operator O1974)
  12147. 987: O: O1974 (predict-no)
  12148. --- END Decision Phase ---
  12149. --- Application Phase ---
  12150. --- Firing Productions (PE) For State At Depth 1 ---
  12151. --- Inner Elaboration Phase, active level 1 (S1) ---
  12152. Firing apply*operator
  12153. -->
  12154. (I3 ^predict-no N987 + :O )
  12155. Firing apply*operator*complete
  12156. -->
  12157. (I3 ^predict-yes N986 - :O )
  12158. inner elaboration loop at bottom goal.
  12159. --- Change Working Memory (PE) ---
  12160. =>WM: (13909: I3 ^predict-no N987)
  12161. <=WM: (13895: N986 ^status complete)
  12162. <=WM: (13894: I3 ^predict-yes N986)
  12163. --- Firing Productions (IE) For State At Depth 1 ---
  12164. --- Inner Elaboration Phase, active level 1 (S1) ---
  12165. Firing monitor*world
  12166. -->
  12167. I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
  12168. --- Change Working Memory (IE) ---
  12169. --- END Application Phase ---
  12170. --- Output Phase ---
  12171. ENV: Agent did: predict-no for direction U in state State-B
  12172. In State-B moving U
  12173. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  12174. predict error 0
  12175. dir: dir isR
  12176. --- END Output Phase ---
  12177. -/|--- Input Phase ---
  12178. =>WM: (13913: I2 ^dir R)
  12179. =>WM: (13912: I2 ^reward 1)
  12180. =>WM: (13911: I2 ^see 0)
  12181. =>WM: (13910: N987 ^status complete)
  12182. <=WM: (13898: I2 ^dir U)
  12183. <=WM: (13897: I2 ^reward 1)
  12184. <=WM: (13896: I2 ^see 1)
  12185. =>WM: (13914: I2 ^level-1 R1-root)
  12186. <=WM: (13899: I2 ^level-1 R1-root)
  12187. --- END Input Phase ---
  12188. --- Proposal Phase ---
  12189. --- Inner Elaboration Phase, active level 1 (S1) ---
  12190. Firing rl*prefer*rvt*predict-yes*H0*3*v1*H1*36
  12191. -->
  12192. (S1 ^operator O1973 = -0.1070236389116304)
  12193. Firing rl*prefer*rvt*predict-no*H0*4*v1*H1*35
  12194. -->
  12195. (S1 ^operator O1974 = 0.6602453025755203)
  12196. Firing prefer*rvt*predict-no*H0*4*v1*H1
  12197. -->
  12198. Firing prefer*rvt*predict-yes*H0*3*v1*H1
  12199. -->
  12200. Firing elaborate*copy-see-to-output-link
  12201. -->
  12202. (I3 ^see 0 +)
  12203. Firing elaborate*reward*based*on*reward
  12204. -->
  12205. (R991 ^value 1 +)
  12206. (R1 ^reward R991 +)
  12207. Firing propose*predict-yes
  12208. -->
  12209. (O1975 ^name predict-yes +)
  12210. (S1 ^operator O1975 +)
  12211. Firing propose*predict-no
  12212. -->
  12213. (O1976 ^name predict-no +)
  12214. (S1 ^operator O1976 +)
  12215. Firing rl*prefer*rvt*predict-no*H0*4
  12216. -->
  12217. (S1 ^operator O1974 = 0.3397683711152304)
  12218. Firing rl*prefer*rvt*predict-yes*H0*3
  12219. -->
  12220. (S1 ^operator O1973 = 0.3377118983309207)
  12221. Firing prefer*rvt*predict-yes*H0
  12222. -->
  12223. Firing prefer*rvt*predict-no*H0
  12224. -->
  12225. Firing elaborate*copy-dir-to-output-link
  12226. -->
  12227. (I3 ^dir R +)
  12228. inner elaboration loop at bottom goal.
  12229. Retracting elaborate*copy-see-to-output-link
  12230. -->
  12231. (I3 ^see 1 +)
  12232. Retracting propose*predict-no
  12233. -->
  12234. (O1974 ^name predict-no +)
  12235. (S1 ^operator O1974 +)
  12236. Retracting propose*predict-yes
  12237. -->
  12238. (O1973 ^name predict-yes +)
  12239. (S1 ^operator O1973 +)
  12240. Retracting elaborate*reward*based*on*reward
  12241. -->
  12242. (R990 ^value 1 +)
  12243. (R1 ^reward R990 +)
  12244. Retracting elaborate*copy-dir-to-output-link
  12245. -->
  12246. (I3 ^dir U +)
  12247. Retracting rl*prefer*rvt*predict-no*H0*2
  12248. -->
  12249. (S1 ^operator O1974 = 1.)
  12250. Retracting rl*prefer*rvt*predict-yes*H0*1
  12251. -->
  12252. (S1 ^operator O1973 = 0.)
  12253. =>WM: (13922: S1 ^operator O1976 +)
  12254. =>WM: (13921: S1 ^operator O1975 +)
  12255. =>WM: (13920: I3 ^dir R)
  12256. =>WM: (13919: O1976 ^name predict-no)
  12257. =>WM: (13918: O1975 ^name predict-yes)
  12258. =>WM: (13917: R991 ^value 1)
  12259. =>WM: (13916: R1 ^reward R991)
  12260. =>WM: (13915: I3 ^see 0)
  12261. <=WM: (13906: S1 ^operator O1973 +)
  12262. <=WM: (13907: S1 ^operator O1974 +)
  12263. <=WM: (13908: S1 ^operator O1974)
  12264. <=WM: (13905: I3 ^dir U)
  12265. <=WM: (13901: R1 ^reward R990)
  12266. <=WM: (13900: I3 ^see 1)
  12267. <=WM: (13904: O1974 ^name predict-no)
  12268. <=WM: (13903: O1973 ^name predict-yes)
  12269. <=WM: (13902: R990 ^value 1)
  12270. --- Inner Elaboration Phase, active level 1 (S1) ---
  12271. Firing prefer*rvt*predict-yes*H0
  12272. -->
  12273. Firing rl*prefer*rvt*predict-yes*H0*3*v1*H1*36
  12274. -->
  12275. (S1 ^operator O1975 = -0.1070236389116304)
  12276. Firing rl*prefer*rvt*predict-yes*H0*3
  12277. -->
  12278. (S1 ^operator O1975 = 0.3377118983309207)
  12279. Firing prefer*rvt*predict-yes*H0*3*v1*H1
  12280. -->
  12281. Firing prefer*rvt*predict-no*H0
  12282. -->
  12283. Firing rl*prefer*rvt*predict-no*H0*4*v1*H1*35
  12284. -->
  12285. (S1 ^operator O1976 = 0.6602453025755203)
  12286. Firing rl*prefer*rvt*predict-no*H0*4
  12287. -->
  12288. (S1 ^operator O1976 = 0.3397683711152304)
  12289. Firing prefer*rvt*predict-no*H0*4*v1*H1
  12290. -->
  12291. inner elaboration loop at bottom goal.
  12292. Retracting rl*prefer*rvt*predict-no*H0*4
  12293. -->
  12294. (S1 ^operator O1974 = 0.3397683711152304)
  12295. Retracting rl*prefer*rvt*predict-no*H0*4*v1*H1*35
  12296. -->
  12297. (S1 ^operator O1974 = 0.6602453025755203)
  12298. Retracting rl*prefer*rvt*predict-yes*H0*3
  12299. -->
  12300. (S1 ^operator O1973 = 0.3377118983309207)
  12301. Retracting rl*prefer*rvt*predict-yes*H0*3*v1*H1*36
  12302. -->
  12303. (S1 ^operator O1973 = -0.1070236389116304)
  12304. --- END Proposal Phase ---
  12305. --- Decision Phase ---
  12306. RL update rl*prefer*rvt*predict-no*H0*2 1 0 1 -> 1 0 1(R,m,v=1,1,0)
  12307. =>WM: (13923: S1 ^operator O1976)
  12308. 988: O: O1976 (predict-no)
  12309. --- END Decision Phase ---
  12310. --- Application Phase ---
  12311. --- Firing Productions (PE) For State At Depth 1 ---
  12312. --- Inner Elaboration Phase, active level 1 (S1) ---
  12313. Firing apply*operator
  12314. -->
  12315. (I3 ^predict-no N988 + :O )
  12316. Firing apply*operator*complete
  12317. -->
  12318. (I3 ^predict-no N987 - :O )
  12319. inner elaboration loop at bottom goal.
  12320. --- Change Working Memory (PE) ---
  12321. =>WM: (13924: I3 ^predict-no N988)
  12322. <=WM: (13910: N987 ^status complete)
  12323. <=WM: (13909: I3 ^predict-no N987)
  12324. --- Firing Productions (IE) For State At Depth 1 ---
  12325. --- Inner Elaboration Phase, active level 1 (S1) ---
  12326. Firing monitor*world
  12327. -->
  12328. I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
  12329. --- Change Working Memory (IE) ---
  12330. --- END Application Phase ---
  12331. --- Output Phase ---
  12332. ENV: Agent did: predict-no for direction R in state State-B
  12333. In State-B moving R
  12334. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  12335. predict error 0
  12336. dir: dir isR
  12337. --- END Output Phase ---
  12338. \-/--- Input Phase ---
  12339. =>WM: (13928: I2 ^dir R)
  12340. =>WM: (13927: I2 ^reward 1)
  12341. =>WM: (13926: I2 ^see 0)
  12342. =>WM: (13925: N988 ^status complete)
  12343. <=WM: (13913: I2 ^dir R)
  12344. <=WM: (13912: I2 ^reward 1)
  12345. <=WM: (13911: I2 ^see 0)
  12346. =>WM: (13929: I2 ^level-1 R0-root)
  12347. <=WM: (13914: I2 ^level-1 R1-root)
  12348. --- END Input Phase ---
  12349. --- Proposal Phase ---
  12350. --- Inner Elaboration Phase, active level 1 (S1) ---
  12351. Firing rl*prefer*rvt*predict-no*H0*4*v1*H1*39
  12352. -->
  12353. (S1 ^operator O1976 = 0.660152441867348)
  12354. Firing rl*prefer*rvt*predict-yes*H0*3*v1*H1*40
  12355. -->
  12356. (S1 ^operator O1975 = -0.1028953566115423)
  12357. Firing prefer*rvt*predict-no*H0*4*v1*H1
  12358. -->
  12359. Firing prefer*rvt*predict-yes*H0*3*v1*H1
  12360. -->
  12361. Firing elaborate*copy-see-to-output-link
  12362. -->
  12363. (I3 ^see 0 +)
  12364. Firing elaborate*reward*based*on*reward
  12365. -->
  12366. (R992 ^value 1 +)
  12367. (R1 ^reward R992 +)
  12368. Firing propose*predict-yes
  12369. -->
  12370. (O1977 ^name predict-yes +)
  12371. (S1 ^operator O1977 +)
  12372. Firing propose*predict-no
  12373. -->
  12374. (O1978 ^name predict-no +)
  12375. (S1 ^operator O1978 +)
  12376. Firing rl*prefer*rvt*predict-no*H0*4
  12377. -->
  12378. (S1 ^operator O1976 = 0.3397683711152304)
  12379. Firing rl*prefer*rvt*predict-yes*H0*3
  12380. -->
  12381. (S1 ^operator O1975 = 0.3377118983309207)
  12382. Firing prefer*rvt*predict-yes*H0
  12383. -->
  12384. Firing prefer*rvt*predict-no*H0
  12385. -->
  12386. Firing elaborate*copy-dir-to-output-link
  12387. -->
  12388. (I3 ^dir R +)
  12389. inner elaboration loop at bottom goal.
  12390. Retracting elaborate*copy-see-to-output-link
  12391. -->
  12392. (I3 ^see 0 +)
  12393. Retracting propose*predict-no
  12394. -->
  12395. (O1976 ^name predict-no +)
  12396. (S1 ^operator O1976 +)
  12397. Retracting propose*predict-yes
  12398. -->
  12399. (O1975 ^name predict-yes +)
  12400. (S1 ^operator O1975 +)
  12401. Retracting elaborate*reward*based*on*reward
  12402. -->
  12403. (R991 ^value 1 +)
  12404. (R1 ^reward R991 +)
  12405. Retracting elaborate*copy-dir-to-output-link
  12406. -->
  12407. (I3 ^dir R +)
  12408. Retracting rl*prefer*rvt*predict-no*H0*4
  12409. -->
  12410. (S1 ^operator O1976 = 0.3397683711152304)
  12411. Retracting rl*prefer*rvt*predict-no*H0*4*v1*H1*35
  12412. -->
  12413. (S1 ^operator O1976 = 0.6602453025755203)
  12414. Retracting rl*prefer*rvt*predict-yes*H0*3
  12415. -->
  12416. (S1 ^operator O1975 = 0.3377118983309207)
  12417. Retracting rl*prefer*rvt*predict-yes*H0*3*v1*H1*36
  12418. -->
  12419. (S1 ^operator O1975 = -0.1070236389116304)
  12420. =>WM: (13935: S1 ^operator O1978 +)
  12421. =>WM: (13934: S1 ^operator O1977 +)
  12422. =>WM: (13933: O1978 ^name predict-no)
  12423. =>WM: (13932: O1977 ^name predict-yes)
  12424. =>WM: (13931: R992 ^value 1)
  12425. =>WM: (13930: R1 ^reward R992)
  12426. <=WM: (13921: S1 ^operator O1975 +)
  12427. <=WM: (13922: S1 ^operator O1976 +)
  12428. <=WM: (13923: S1 ^operator O1976)
  12429. <=WM: (13916: R1 ^reward R991)
  12430. <=WM: (13919: O1976 ^name predict-no)
  12431. <=WM: (13918: O1975 ^name predict-yes)
  12432. <=WM: (13917: R991 ^value 1)
  12433. --- Inner Elaboration Phase, active level 1 (S1) ---
  12434. Firing prefer*rvt*predict-yes*H0
  12435. -->
  12436. Firing rl*prefer*rvt*predict-yes*H0*3
  12437. -->
  12438. (S1 ^operator O1977 = 0.3377118983309207)
  12439. Firing prefer*rvt*predict-yes*H0*3*v1*H1
  12440. -->
  12441. Firing rl*prefer*rvt*predict-yes*H0*3*v1*H1*40
  12442. -->
  12443. (S1 ^operator O1977 = -0.1028953566115423)
  12444. Firing prefer*rvt*predict-no*H0
  12445. -->
  12446. Firing rl*prefer*rvt*predict-no*H0*4
  12447. -->
  12448. (S1 ^operator O1978 = 0.3397683711152304)
  12449. Firing prefer*rvt*predict-no*H0*4*v1*H1
  12450. -->
  12451. Firing rl*prefer*rvt*predict-no*H0*4*v1*H1*39
  12452. -->
  12453. (S1 ^operator O1978 = 0.660152441867348)
  12454. inner elaboration loop at bottom goal.
  12455. Retracting rl*prefer*rvt*predict-no*H0*4
  12456. -->
  12457. (S1 ^operator O1976 = 0.3397683711152304)
  12458. Retracting rl*prefer*rvt*predict-no*H0*4*v1*H1*39
  12459. -->
  12460. (S1 ^operator O1976 = 0.660152441867348)
  12461. Retracting rl*prefer*rvt*predict-yes*H0*3
  12462. -->
  12463. (S1 ^operator O1975 = 0.3377118983309207)
  12464. Retracting rl*prefer*rvt*predict-yes*H0*3*v1*H1*40
  12465. -->
  12466. (S1 ^operator O1975 = -0.1028953566115423)
  12467. --- END Proposal Phase ---
  12468. --- Decision Phase ---
  12469. RL update rl*prefer*rvt*predict-no*H0*4 0.570252 -0.230483 0.339768 -> 0.570251 -0.230483 0.339767(R,m,v=1,0.874251,0.110598)
  12470. RL update rl*prefer*rvt*predict-no*H0*4*v1*H1*35 0.429763 0.230483 0.660245 -> 0.429761 0.230483 0.660244(R,m,v=1,1,0)
  12471. =>WM: (13936: S1 ^operator O1978)
  12472. 989: O: O1978 (predict-no)
  12473. --- END Decision Phase ---
  12474. --- Application Phase ---
  12475. --- Firing Productions (PE) For State At Depth 1 ---
  12476. --- Inner Elaboration Phase, active level 1 (S1) ---
  12477. Firing apply*operator
  12478. -->
  12479. (I3 ^predict-no N989 + :O )
  12480. Firing apply*operator*complete
  12481. -->
  12482. (I3 ^predict-no N988 - :O )
  12483. inner elaboration loop at bottom goal.
  12484. --- Change Working Memory (PE) ---
  12485. =>WM: (13937: I3 ^predict-no N989)
  12486. <=WM: (13925: N988 ^status complete)
  12487. <=WM: (13924: I3 ^predict-no N988)
  12488. --- Firing Productions (IE) For State At Depth 1 ---
  12489. --- Inner Elaboration Phase, active level 1 (S1) ---
  12490. Firing monitor*world
  12491. -->
  12492. I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
  12493. --- Change Working Memory (IE) ---
  12494. --- END Application Phase ---
  12495. --- Output Phase ---
  12496. ENV: Agent did: predict-no for direction R in state State-B
  12497. In State-B moving R
  12498. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  12499. predict error 0
  12500. dir: dir isL
  12501. --- END Output Phase ---
  12502. |\---- Input Phase ---
  12503. =>WM: (13941: I2 ^dir L)
  12504. =>WM: (13940: I2 ^reward 1)
  12505. =>WM: (13939: I2 ^see 0)
  12506. =>WM: (13938: N989 ^status complete)
  12507. <=WM: (13928: I2 ^dir R)
  12508. <=WM: (13927: I2 ^reward 1)
  12509. <=WM: (13926: I2 ^see 0)
  12510. =>WM: (13942: I2 ^level-1 R0-root)
  12511. <=WM: (13929: I2 ^level-1 R0-root)
  12512. --- END Input Phase ---
  12513. --- Proposal Phase ---
  12514. --- Inner Elaboration Phase, active level 1 (S1) ---
  12515. Firing rl*prefer*rvt*predict-yes*H0*5*v1*H1*30
  12516. -->
  12517. (S1 ^operator O1977 = 0.7358428664482317)
  12518. Firing prefer*rvt*predict-yes*H0*5*v1*H1
  12519. -->
  12520. Firing elaborate*copy-see-to-output-link
  12521. -->
  12522. (I3 ^see 0 +)
  12523. Firing elaborate*reward*based*on*reward
  12524. -->
  12525. (R993 ^value 1 +)
  12526. (R1 ^reward R993 +)
  12527. Firing propose*predict-yes
  12528. -->
  12529. (O1979 ^name predict-yes +)
  12530. (S1 ^operator O1979 +)
  12531. Firing propose*predict-no
  12532. -->
  12533. (O1980 ^name predict-no +)
  12534. (S1 ^operator O1980 +)
  12535. Firing rl*prefer*rvt*predict-no*H0*6
  12536. -->
  12537. (S1 ^operator O1978 = 0.999790145818646)
  12538. Firing rl*prefer*rvt*predict-yes*H0*5
  12539. -->
  12540. (S1 ^operator O1977 = 0.264039703522277)
  12541. Firing prefer*rvt*predict-yes*H0
  12542. -->
  12543. Firing prefer*rvt*predict-no*H0
  12544. -->
  12545. Firing elaborate*copy-dir-to-output-link
  12546. -->
  12547. (I3 ^dir L +)
  12548. inner elaboration loop at bottom goal.
  12549. Retracting elaborate*copy-see-to-output-link
  12550. -->
  12551. (I3 ^see 0 +)
  12552. Retracting propose*predict-no
  12553. -->
  12554. (O1978 ^name predict-no +)
  12555. (S1 ^operator O1978 +)
  12556. Retracting propose*predict-yes
  12557. -->
  12558. (O1977 ^name predict-yes +)
  12559. (S1 ^operator O1977 +)
  12560. Retracting elaborate*reward*based*on*reward
  12561. -->
  12562. (R992 ^value 1 +)
  12563. (R1 ^reward R992 +)
  12564. Retracting elaborate*copy-dir-to-output-link
  12565. -->
  12566. (I3 ^dir R +)
  12567. Retracting rl*prefer*rvt*predict-no*H0*4*v1*H1*39
  12568. -->
  12569. (S1 ^operator O1978 = 0.660152441867348)
  12570. Retracting rl*prefer*rvt*predict-no*H0*4
  12571. -->
  12572. (S1 ^operator O1978 = 0.339767253617308)
  12573. Retracting rl*prefer*rvt*predict-yes*H0*3*v1*H1*40
  12574. -->
  12575. (S1 ^operator O1977 = -0.1028953566115423)
  12576. Retracting rl*prefer*rvt*predict-yes*H0*3
  12577. -->
  12578. (S1 ^operator O1977 = 0.3377118983309207)
  12579. =>WM: (13949: S1 ^operator O1980 +)
  12580. =>WM: (13948: S1 ^operator O1979 +)
  12581. =>WM: (13947: I3 ^dir L)
  12582. =>WM: (13946: O1980 ^name predict-no)
  12583. =>WM: (13945: O1979 ^name predict-yes)
  12584. =>WM: (13944: R993 ^value 1)
  12585. =>WM: (13943: R1 ^reward R993)
  12586. <=WM: (13934: S1 ^operator O1977 +)
  12587. <=WM: (13935: S1 ^operator O1978 +)
  12588. <=WM: (13936: S1 ^operator O1978)
  12589. <=WM: (13920: I3 ^dir R)
  12590. <=WM: (13930: R1 ^reward R992)
  12591. <=WM: (13933: O1978 ^name predict-no)
  12592. <=WM: (13932: O1977 ^name predict-yes)
  12593. <=WM: (13931: R992 ^value 1)
  12594. --- Inner Elaboration Phase, active level 1 (S1) ---
  12595. Firing prefer*rvt*predict-yes*H0
  12596. -->
  12597. Firing rl*prefer*rvt*predict-yes*H0*5*v1*H1*30
  12598. -->
  12599. (S1 ^operator O1979 = 0.7358428664482317)
  12600. Firing rl*prefer*rvt*predict-yes*H0*5
  12601. -->
  12602. (S1 ^operator O1979 = 0.264039703522277)
  12603. Firing prefer*rvt*predict-yes*H0*5*v1*H1
  12604. -->
  12605. Firing prefer*rvt*predict-no*H0
  12606. -->
  12607. Firing rl*prefer*rvt*predict-no*H0*6
  12608. -->
  12609. (S1 ^operator O1980 = 0.999790145818646)
  12610. inner elaboration loop at bottom goal.
  12611. Retracting rl*prefer*rvt*predict-no*H0*6
  12612. -->
  12613. (S1 ^operator O1978 = 0.999790145818646)
  12614. Retracting rl*prefer*rvt*predict-yes*H0*5
  12615. -->
  12616. (S1 ^operator O1977 = 0.264039703522277)
  12617. Retracting rl*prefer*rvt*predict-yes*H0*5*v1*H1*30
  12618. -->
  12619. (S1 ^operator O1977 = 0.7358428664482317)
  12620. --- END Proposal Phase ---
  12621. --- Decision Phase ---
  12622. RL update rl*prefer*rvt*predict-no*H0*4 0.570251 -0.230483 0.339767 -> 0.570257 -0.230484 0.339774(R,m,v=1,0.875,0.11003)
  12623. RL update rl*prefer*rvt*predict-no*H0*4*v1*H1*39 0.429665 0.230487 0.660152 -> 0.429673 0.230487 0.66016(R,m,v=1,1,0)
  12624. =>WM: (13950: S1 ^operator O1979)
  12625. 990: O: O1979 (predict-yes)
  12626. --- END Decision Phase ---
  12627. --- Application Phase ---
  12628. --- Firing Productions (PE) For State At Depth 1 ---
  12629. --- Inner Elaboration Phase, active level 1 (S1) ---
  12630. Firing apply*operator
  12631. -->
  12632. (I3 ^predict-yes N990 + :O )
  12633. Firing apply*operator*complete
  12634. -->
  12635. (I3 ^predict-no N989 - :O )
  12636. inner elaboration loop at bottom goal.
  12637. --- Change Working Memory (PE) ---
  12638. =>WM: (13951: I3 ^predict-yes N990)
  12639. <=WM: (13938: N989 ^status complete)
  12640. <=WM: (13937: I3 ^predict-no N989)
  12641. --- Firing Productions (IE) For State At Depth 1 ---
  12642. --- Inner Elaboration Phase, active level 1 (S1) ---
  12643. Firing monitor*world
  12644. -->
  12645. I see 1 and I'm going to do: predict-yes inner elaboration loop at bottom goal.
  12646. --- Change Working Memory (IE) ---
  12647. --- END Application Phase ---
  12648. --- Output Phase ---
  12649. ENV: Agent did: predict-yes for direction L in state State-B
  12650. In State-B moving L
  12651. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  12652. predict error 0
  12653. dir: dir isU
  12654. --- END Output Phase ---
  12655. /|\--- Input Phase ---
  12656. =>WM: (13955: I2 ^dir U)
  12657. =>WM: (13954: I2 ^reward 1)
  12658. =>WM: (13953: I2 ^see 1)
  12659. =>WM: (13952: N990 ^status complete)
  12660. <=WM: (13941: I2 ^dir L)
  12661. <=WM: (13940: I2 ^reward 1)
  12662. <=WM: (13939: I2 ^see 0)
  12663. =>WM: (13956: I2 ^level-1 L1-root)
  12664. <=WM: (13942: I2 ^level-1 R0-root)
  12665. --- END Input Phase ---
  12666. --- Proposal Phase ---
  12667. --- Inner Elaboration Phase, active level 1 (S1) ---
  12668. Firing elaborate*copy-see-to-output-link
  12669. -->
  12670. (I3 ^see 1 +)
  12671. Firing elaborate*reward*based*on*reward
  12672. -->
  12673. (R994 ^value 1 +)
  12674. (R1 ^reward R994 +)
  12675. Firing propose*predict-yes
  12676. -->
  12677. (O1981 ^name predict-yes +)
  12678. (S1 ^operator O1981 +)
  12679. Firing propose*predict-no
  12680. -->
  12681. (O1982 ^name predict-no +)
  12682. (S1 ^operator O1982 +)
  12683. Firing rl*prefer*rvt*predict-no*H0*2
  12684. -->
  12685. (S1 ^operator O1980 = 1.)
  12686. Firing rl*prefer*rvt*predict-yes*H0*1
  12687. -->
  12688. (S1 ^operator O1979 = 0.)
  12689. Firing prefer*rvt*predict-yes*H0
  12690. -->
  12691. Firing prefer*rvt*predict-no*H0
  12692. -->
  12693. Firing elaborate*copy-dir-to-output-link
  12694. -->
  12695. (I3 ^dir U +)
  12696. inner elaboration loop at bottom goal.
  12697. Retracting elaborate*copy-see-to-output-link
  12698. -->
  12699. (I3 ^see 0 +)
  12700. Retracting propose*predict-no
  12701. -->
  12702. (O1980 ^name predict-no +)
  12703. (S1 ^operator O1980 +)
  12704. Retracting propose*predict-yes
  12705. -->
  12706. (O1979 ^name predict-yes +)
  12707. (S1 ^operator O1979 +)
  12708. Retracting elaborate*reward*based*on*reward
  12709. -->
  12710. (R993 ^value 1 +)
  12711. (R1 ^reward R993 +)
  12712. Retracting elaborate*copy-dir-to-output-link
  12713. -->
  12714. (I3 ^dir L +)
  12715. Retracting rl*prefer*rvt*predict-no*H0*6
  12716. -->
  12717. (S1 ^operator O1980 = 0.999790145818646)
  12718. Retracting rl*prefer*rvt*predict-yes*H0*5
  12719. -->
  12720. (S1 ^operator O1979 = 0.264039703522277)
  12721. Retracting rl*prefer*rvt*predict-yes*H0*5*v1*H1*30
  12722. -->
  12723. (S1 ^operator O1979 = 0.7358428664482317)
  12724. =>WM: (13964: S1 ^operator O1982 +)
  12725. =>WM: (13963: S1 ^operator O1981 +)
  12726. =>WM: (13962: I3 ^dir U)
  12727. =>WM: (13961: O1982 ^name predict-no)
  12728. =>WM: (13960: O1981 ^name predict-yes)
  12729. =>WM: (13959: R994 ^value 1)
  12730. =>WM: (13958: R1 ^reward R994)
  12731. =>WM: (13957: I3 ^see 1)
  12732. <=WM: (13948: S1 ^operator O1979 +)
  12733. <=WM: (13950: S1 ^operator O1979)
  12734. <=WM: (13949: S1 ^operator O1980 +)
  12735. <=WM: (13947: I3 ^dir L)
  12736. <=WM: (13943: R1 ^reward R993)
  12737. <=WM: (13915: I3 ^see 0)
  12738. <=WM: (13946: O1980 ^name predict-no)
  12739. <=WM: (13945: O1979 ^name predict-yes)
  12740. <=WM: (13944: R993 ^value 1)
  12741. --- Inner Elaboration Phase, active level 1 (S1) ---
  12742. Firing prefer*rvt*predict-yes*H0
  12743. -->
  12744. Firing rl*prefer*rvt*predict-yes*H0*1
  12745. -->
  12746. (S1 ^operator O1981 = 0.)
  12747. Firing prefer*rvt*predict-no*H0
  12748. -->
  12749. Firing rl*prefer*rvt*predict-no*H0*2
  12750. -->
  12751. (S1 ^operator O1982 = 1.)
  12752. inner elaboration loop at bottom goal.
  12753. Retracting rl*prefer*rvt*predict-no*H0*2
  12754. -->
  12755. (S1 ^operator O1980 = 1.)
  12756. Retracting rl*prefer*rvt*predict-yes*H0*1
  12757. -->
  12758. (S1 ^operator O1979 = 0.)
  12759. --- END Proposal Phase ---
  12760. --- Decision Phase ---
  12761. RL update rl*prefer*rvt*predict-yes*H0*5 0.554425 -0.290385 0.26404 -> 0.554434 -0.290385 0.264049(R,m,v=1,0.876404,0.108932)
  12762. RL update rl*prefer*rvt*predict-yes*H0*5*v1*H1*30 0.44546 0.290383 0.735843 -> 0.445471 0.290384 0.735854(R,m,v=1,1,0)
  12763. =>WM: (13965: S1 ^operator O1982)
  12764. 991: O: O1982 (predict-no)
  12765. --- END Decision Phase ---
  12766. --- Application Phase ---
  12767. --- Firing Productions (PE) For State At Depth 1 ---
  12768. --- Inner Elaboration Phase, active level 1 (S1) ---
  12769. Firing apply*operator
  12770. -->
  12771. (I3 ^predict-no N991 + :O )
  12772. Firing apply*operator*complete
  12773. -->
  12774. (I3 ^predict-yes N990 - :O )
  12775. inner elaboration loop at bottom goal.
  12776. --- Change Working Memory (PE) ---
  12777. =>WM: (13966: I3 ^predict-no N991)
  12778. <=WM: (13952: N990 ^status complete)
  12779. <=WM: (13951: I3 ^predict-yes N990)
  12780. --- Firing Productions (IE) For State At Depth 1 ---
  12781. --- Inner Elaboration Phase, active level 1 (S1) ---
  12782. Firing monitor*world
  12783. -->
  12784. I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
  12785. --- Change Working Memory (IE) ---
  12786. --- END Application Phase ---
  12787. --- Output Phase ---
  12788. ENV: Agent did: predict-no for direction U in state State-A
  12789. In State-A moving U
  12790. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  12791. predict error 0
  12792. dir: dir isR
  12793. --- END Output Phase ---
  12794. ---- Input Phase ---
  12795. =>WM: (13970: I2 ^dir R)
  12796. =>WM: (13969: I2 ^reward 1)
  12797. =>WM: (13968: I2 ^see 0)
  12798. =>WM: (13967: N991 ^status complete)
  12799. <=WM: (13955: I2 ^dir U)
  12800. <=WM: (13954: I2 ^reward 1)
  12801. <=WM: (13953: I2 ^see 1)
  12802. =>WM: (13971: I2 ^level-1 L1-root)
  12803. <=WM: (13956: I2 ^level-1 L1-root)
  12804. --- END Input Phase ---
  12805. --- Proposal Phase ---
  12806. --- Inner Elaboration Phase, active level 1 (S1) ---
  12807. Firing rl*prefer*rvt*predict-no*H0*4*v1*H1*37
  12808. -->
  12809. (S1 ^operator O1982 = -0.2714224023553999)
  12810. Firing rl*prefer*rvt*predict-yes*H0*3*v1*H1*38
  12811. -->
  12812. (S1 ^operator O1981 = 0.662219375073587)
  12813. Firing prefer*rvt*predict-no*H0*4*v1*H1
  12814. -->
  12815. Firing prefer*rvt*predict-yes*H0*3*v1*H1
  12816. -->
  12817. Firing elaborate*copy-see-to-output-link
  12818. -->
  12819. (I3 ^see 0 +)
  12820. Firing elaborate*reward*based*on*reward
  12821. -->
  12822. (R995 ^value 1 +)
  12823. (R1 ^reward R995 +)
  12824. Firing propose*predict-yes
  12825. -->
  12826. (O1983 ^name predict-yes +)
  12827. (S1 ^operator O1983 +)
  12828. Firing propose*predict-no
  12829. -->
  12830. (O1984 ^name predict-no +)
  12831. (S1 ^operator O1984 +)
  12832. Firing rl*prefer*rvt*predict-no*H0*4
  12833. -->
  12834. (S1 ^operator O1982 = 0.339773810196969)
  12835. Firing rl*prefer*rvt*predict-yes*H0*3
  12836. -->
  12837. (S1 ^operator O1981 = 0.3377118983309207)
  12838. Firing prefer*rvt*predict-yes*H0
  12839. -->
  12840. Firing prefer*rvt*predict-no*H0
  12841. -->
  12842. Firing elaborate*copy-dir-to-output-link
  12843. -->
  12844. (I3 ^dir R +)
  12845. inner elaboration loop at bottom goal.
  12846. Retracting elaborate*copy-see-to-output-link
  12847. -->
  12848. (I3 ^see 1 +)
  12849. Retracting propose*predict-no
  12850. -->
  12851. (O1982 ^name predict-no +)
  12852. (S1 ^operator O1982 +)
  12853. Retracting propose*predict-yes
  12854. -->
  12855. (O1981 ^name predict-yes +)
  12856. (S1 ^operator O1981 +)
  12857. Retracting elaborate*reward*based*on*reward
  12858. -->
  12859. (R994 ^value 1 +)
  12860. (R1 ^reward R994 +)
  12861. Retracting elaborate*copy-dir-to-output-link
  12862. -->
  12863. (I3 ^dir U +)
  12864. Retracting rl*prefer*rvt*predict-no*H0*2
  12865. -->
  12866. (S1 ^operator O1982 = 1.)
  12867. Retracting rl*prefer*rvt*predict-yes*H0*1
  12868. -->
  12869. (S1 ^operator O1981 = 0.)
  12870. =>WM: (13979: S1 ^operator O1984 +)
  12871. =>WM: (13978: S1 ^operator O1983 +)
  12872. =>WM: (13977: I3 ^dir R)
  12873. =>WM: (13976: O1984 ^name predict-no)
  12874. =>WM: (13975: O1983 ^name predict-yes)
  12875. =>WM: (13974: R995 ^value 1)
  12876. =>WM: (13973: R1 ^reward R995)
  12877. =>WM: (13972: I3 ^see 0)
  12878. <=WM: (13963: S1 ^operator O1981 +)
  12879. <=WM: (13964: S1 ^operator O1982 +)
  12880. <=WM: (13965: S1 ^operator O1982)
  12881. <=WM: (13962: I3 ^dir U)
  12882. <=WM: (13958: R1 ^reward R994)
  12883. <=WM: (13957: I3 ^see 1)
  12884. <=WM: (13961: O1982 ^name predict-no)
  12885. <=WM: (13960: O1981 ^name predict-yes)
  12886. <=WM: (13959: R994 ^value 1)
  12887. --- Inner Elaboration Phase, active level 1 (S1) ---
  12888. Firing prefer*rvt*predict-yes*H0
  12889. -->
  12890. Firing rl*prefer*rvt*predict-yes*H0*3*v1*H1*38
  12891. -->
  12892. (S1 ^operator O1983 = 0.662219375073587)
  12893. Firing rl*prefer*rvt*predict-yes*H0*3
  12894. -->
  12895. (S1 ^operator O1983 = 0.3377118983309207)
  12896. Firing prefer*rvt*predict-yes*H0*3*v1*H1
  12897. -->
  12898. Firing prefer*rvt*predict-no*H0
  12899. -->
  12900. Firing rl*prefer*rvt*predict-no*H0*4*v1*H1*37
  12901. -->
  12902. (S1 ^operator O1984 = -0.2714224023553999)
  12903. Firing rl*prefer*rvt*predict-no*H0*4
  12904. -->
  12905. (S1 ^operator O1984 = 0.339773810196969)
  12906. Firing prefer*rvt*predict-no*H0*4*v1*H1
  12907. -->
  12908. inner elaboration loop at bottom goal.
  12909. Retracting rl*prefer*rvt*predict-no*H0*4
  12910. -->
  12911. (S1 ^operator O1982 = 0.339773810196969)
  12912. Retracting rl*prefer*rvt*predict-no*H0*4*v1*H1*37
  12913. -->
  12914. (S1 ^operator O1982 = -0.2714224023553999)
  12915. Retracting rl*prefer*rvt*predict-yes*H0*3
  12916. -->
  12917. (S1 ^operator O1981 = 0.3377118983309207)
  12918. Retracting rl*prefer*rvt*predict-yes*H0*3*v1*H1*38
  12919. -->
  12920. (S1 ^operator O1981 = 0.662219375073587)
  12921. --- END Proposal Phase ---
  12922. --- Decision Phase ---
  12923. RL update rl*prefer*rvt*predict-no*H0*2 1 0 1 -> 1 0 1(R,m,v=1,1,0)
  12924. =>WM: (13980: S1 ^operator O1983)
  12925. 992: O: O1983 (predict-yes)
  12926. --- END Decision Phase ---
  12927. --- Application Phase ---
  12928. --- Firing Productions (PE) For State At Depth 1 ---
  12929. --- Inner Elaboration Phase, active level 1 (S1) ---
  12930. Firing apply*operator
  12931. -->
  12932. (I3 ^predict-yes N992 + :O )
  12933. Firing apply*operator*complete
  12934. -->
  12935. (I3 ^predict-no N991 - :O )
  12936. inner elaboration loop at bottom goal.
  12937. --- Change Working Memory (PE) ---
  12938. =>WM: (13981: I3 ^predict-yes N992)
  12939. <=WM: (13967: N991 ^status complete)
  12940. <=WM: (13966: I3 ^predict-no N991)
  12941. --- Firing Productions (IE) For State At Depth 1 ---
  12942. --- Inner Elaboration Phase, active level 1 (S1) ---
  12943. Firing monitor*world
  12944. -->
  12945. I see 1 and I'm going to do: predict-yes inner elaboration loop at bottom goal.
  12946. --- Change Working Memory (IE) ---
  12947. --- END Application Phase ---
  12948. --- Output Phase ---
  12949. ENV: Agent did: predict-yes for direction R in state State-A
  12950. In State-A moving R
  12951. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  12952. predict error 0
  12953. dir: dir isU
  12954. --- END Output Phase ---
  12955. /|--- Input Phase ---
  12956. =>WM: (13985: I2 ^dir U)
  12957. =>WM: (13984: I2 ^reward 1)
  12958. =>WM: (13983: I2 ^see 1)
  12959. =>WM: (13982: N992 ^status complete)
  12960. <=WM: (13970: I2 ^dir R)
  12961. <=WM: (13969: I2 ^reward 1)
  12962. <=WM: (13968: I2 ^see 0)
  12963. =>WM: (13986: I2 ^level-1 R1-root)
  12964. <=WM: (13971: I2 ^level-1 L1-root)
  12965. --- END Input Phase ---
  12966. --- Proposal Phase ---
  12967. --- Inner Elaboration Phase, active level 1 (S1) ---
  12968. Firing elaborate*copy-see-to-output-link
  12969. -->
  12970. (I3 ^see 1 +)
  12971. Firing elaborate*reward*based*on*reward
  12972. -->
  12973. (R996 ^value 1 +)
  12974. (R1 ^reward R996 +)
  12975. Firing propose*predict-yes
  12976. -->
  12977. (O1985 ^name predict-yes +)
  12978. (S1 ^operator O1985 +)
  12979. Firing propose*predict-no
  12980. -->
  12981. (O1986 ^name predict-no +)
  12982. (S1 ^operator O1986 +)
  12983. Firing rl*prefer*rvt*predict-no*H0*2
  12984. -->
  12985. (S1 ^operator O1984 = 1.)
  12986. Firing rl*prefer*rvt*predict-yes*H0*1
  12987. -->
  12988. (S1 ^operator O1983 = 0.)
  12989. Firing prefer*rvt*predict-yes*H0
  12990. -->
  12991. Firing prefer*rvt*predict-no*H0
  12992. -->
  12993. Firing elaborate*copy-dir-to-output-link
  12994. -->
  12995. (I3 ^dir U +)
  12996. inner elaboration loop at bottom goal.
  12997. Retracting elaborate*copy-see-to-output-link
  12998. -->
  12999. (I3 ^see 0 +)
  13000. Retracting propose*predict-no
  13001. -->
  13002. (O1984 ^name predict-no +)
  13003. (S1 ^operator O1984 +)
  13004. Retracting propose*predict-yes
  13005. -->
  13006. (O1983 ^name predict-yes +)
  13007. (S1 ^operator O1983 +)
  13008. Retracting elaborate*reward*based*on*reward
  13009. -->
  13010. (R995 ^value 1 +)
  13011. (R1 ^reward R995 +)
  13012. Retracting elaborate*copy-dir-to-output-link
  13013. -->
  13014. (I3 ^dir R +)
  13015. Retracting rl*prefer*rvt*predict-no*H0*4
  13016. -->
  13017. (S1 ^operator O1984 = 0.339773810196969)
  13018. Retracting rl*prefer*rvt*predict-no*H0*4*v1*H1*37
  13019. -->
  13020. (S1 ^operator O1984 = -0.2714224023553999)
  13021. Retracting rl*prefer*rvt*predict-yes*H0*3
  13022. -->
  13023. (S1 ^operator O1983 = 0.3377118983309207)
  13024. Retracting rl*prefer*rvt*predict-yes*H0*3*v1*H1*38
  13025. -->
  13026. (S1 ^operator O1983 = 0.662219375073587)
  13027. =>WM: (13994: S1 ^operator O1986 +)
  13028. =>WM: (13993: S1 ^operator O1985 +)
  13029. =>WM: (13992: I3 ^dir U)
  13030. =>WM: (13991: O1986 ^name predict-no)
  13031. =>WM: (13990: O1985 ^name predict-yes)
  13032. =>WM: (13989: R996 ^value 1)
  13033. =>WM: (13988: R1 ^reward R996)
  13034. =>WM: (13987: I3 ^see 1)
  13035. <=WM: (13978: S1 ^operator O1983 +)
  13036. <=WM: (13980: S1 ^operator O1983)
  13037. <=WM: (13979: S1 ^operator O1984 +)
  13038. <=WM: (13977: I3 ^dir R)
  13039. <=WM: (13973: R1 ^reward R995)
  13040. <=WM: (13972: I3 ^see 0)
  13041. <=WM: (13976: O1984 ^name predict-no)
  13042. <=WM: (13975: O1983 ^name predict-yes)
  13043. <=WM: (13974: R995 ^value 1)
  13044. --- Inner Elaboration Phase, active level 1 (S1) ---
  13045. Firing prefer*rvt*predict-yes*H0
  13046. -->
  13047. Firing rl*prefer*rvt*predict-yes*H0*1
  13048. -->
  13049. (S1 ^operator O1985 = 0.)
  13050. Firing prefer*rvt*predict-no*H0
  13051. -->
  13052. Firing rl*prefer*rvt*predict-no*H0*2
  13053. -->
  13054. (S1 ^operator O1986 = 1.)
  13055. inner elaboration loop at bottom goal.
  13056. Retracting rl*prefer*rvt*predict-no*H0*2
  13057. -->
  13058. (S1 ^operator O1984 = 1.)
  13059. Retracting rl*prefer*rvt*predict-yes*H0*1
  13060. -->
  13061. (S1 ^operator O1983 = 0.)
  13062. --- END Proposal Phase ---
  13063. --- Decision Phase ---
  13064. RL update rl*prefer*rvt*predict-yes*H0*3 0.590112 -0.2524 0.337712 -> 0.590119 -0.252401 0.337718(R,m,v=1,0.898204,0.0919847)
  13065. RL update rl*prefer*rvt*predict-yes*H0*3*v1*H1*38 0.409809 0.252411 0.662219 -> 0.409816 0.25241 0.662226(R,m,v=1,1,0)
  13066. =>WM: (13995: S1 ^operator O1986)
  13067. 993: O: O1986 (predict-no)
  13068. --- END Decision Phase ---
  13069. --- Application Phase ---
  13070. --- Firing Productions (PE) For State At Depth 1 ---
  13071. --- Inner Elaboration Phase, active level 1 (S1) ---
  13072. Firing apply*operator
  13073. -->
  13074. (I3 ^predict-no N993 + :O )
  13075. Firing apply*operator*complete
  13076. -->
  13077. (I3 ^predict-yes N992 - :O )
  13078. inner elaboration loop at bottom goal.
  13079. --- Change Working Memory (PE) ---
  13080. =>WM: (13996: I3 ^predict-no N993)
  13081. <=WM: (13982: N992 ^status complete)
  13082. <=WM: (13981: I3 ^predict-yes N992)
  13083. --- Firing Productions (IE) For State At Depth 1 ---
  13084. --- Inner Elaboration Phase, active level 1 (S1) ---
  13085. Firing monitor*world
  13086. -->
  13087. I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
  13088. --- Change Working Memory (IE) ---
  13089. --- END Application Phase ---
  13090. --- Output Phase ---
  13091. ENV: Agent did: predict-no for direction U in state State-B
  13092. In State-B moving U
  13093. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  13094. predict error 0
  13095. dir: dir isL
  13096. --- END Output Phase ---
  13097. \-/--- Input Phase ---
  13098. =>WM: (14000: I2 ^dir L)
  13099. =>WM: (13999: I2 ^reward 1)
  13100. =>WM: (13998: I2 ^see 0)
  13101. =>WM: (13997: N993 ^status complete)
  13102. <=WM: (13985: I2 ^dir U)
  13103. <=WM: (13984: I2 ^reward 1)
  13104. <=WM: (13983: I2 ^see 1)
  13105. =>WM: (14001: I2 ^level-1 R1-root)
  13106. <=WM: (13986: I2 ^level-1 R1-root)
  13107. --- END Input Phase ---
  13108. --- Proposal Phase ---
  13109. --- Inner Elaboration Phase, active level 1 (S1) ---
  13110. Firing rl*prefer*rvt*predict-yes*H0*5*v1*H1*41
  13111. -->
  13112. (S1 ^operator O1985 = 0.7362544663116062)
  13113. Firing prefer*rvt*predict-yes*H0*5*v1*H1
  13114. -->
  13115. Firing elaborate*copy-see-to-output-link
  13116. -->
  13117. (I3 ^see 0 +)
  13118. Firing elaborate*reward*based*on*reward
  13119. -->
  13120. (R997 ^value 1 +)
  13121. (R1 ^reward R997 +)
  13122. Firing propose*predict-yes
  13123. -->
  13124. (O1987 ^name predict-yes +)
  13125. (S1 ^operator O1987 +)
  13126. Firing propose*predict-no
  13127. -->
  13128. (O1988 ^name predict-no +)
  13129. (S1 ^operator O1988 +)
  13130. Firing rl*prefer*rvt*predict-no*H0*6
  13131. -->
  13132. (S1 ^operator O1986 = 0.999790145818646)
  13133. Firing rl*prefer*rvt*predict-yes*H0*5
  13134. -->
  13135. (S1 ^operator O1985 = 0.2640492015925779)
  13136. Firing prefer*rvt*predict-yes*H0
  13137. -->
  13138. Firing prefer*rvt*predict-no*H0
  13139. -->
  13140. Firing elaborate*copy-dir-to-output-link
  13141. -->
  13142. (I3 ^dir L +)
  13143. inner elaboration loop at bottom goal.
  13144. Retracting elaborate*copy-see-to-output-link
  13145. -->
  13146. (I3 ^see 1 +)
  13147. Retracting propose*predict-no
  13148. -->
  13149. (O1986 ^name predict-no +)
  13150. (S1 ^operator O1986 +)
  13151. Retracting propose*predict-yes
  13152. -->
  13153. (O1985 ^name predict-yes +)
  13154. (S1 ^operator O1985 +)
  13155. Retracting elaborate*reward*based*on*reward
  13156. -->
  13157. (R996 ^value 1 +)
  13158. (R1 ^reward R996 +)
  13159. Retracting elaborate*copy-dir-to-output-link
  13160. -->
  13161. (I3 ^dir U +)
  13162. Retracting rl*prefer*rvt*predict-no*H0*2
  13163. -->
  13164. (S1 ^operator O1986 = 1.)
  13165. Retracting rl*prefer*rvt*predict-yes*H0*1
  13166. -->
  13167. (S1 ^operator O1985 = 0.)
  13168. =>WM: (14009: S1 ^operator O1988 +)
  13169. =>WM: (14008: S1 ^operator O1987 +)
  13170. =>WM: (14007: I3 ^dir L)
  13171. =>WM: (14006: O1988 ^name predict-no)
  13172. =>WM: (14005: O1987 ^name predict-yes)
  13173. =>WM: (14004: R997 ^value 1)
  13174. =>WM: (14003: R1 ^reward R997)
  13175. =>WM: (14002: I3 ^see 0)
  13176. <=WM: (13993: S1 ^operator O1985 +)
  13177. <=WM: (13994: S1 ^operator O1986 +)
  13178. <=WM: (13995: S1 ^operator O1986)
  13179. <=WM: (13992: I3 ^dir U)
  13180. <=WM: (13988: R1 ^reward R996)
  13181. <=WM: (13987: I3 ^see 1)
  13182. <=WM: (13991: O1986 ^name predict-no)
  13183. <=WM: (13990: O1985 ^name predict-yes)
  13184. <=WM: (13989: R996 ^value 1)
  13185. --- Inner Elaboration Phase, active level 1 (S1) ---
  13186. Firing prefer*rvt*predict-yes*H0
  13187. -->
  13188. Firing rl*prefer*rvt*predict-yes*H0*5*v1*H1*41
  13189. -->
  13190. (S1 ^operator O1987 = 0.7362544663116062)
  13191. Firing rl*prefer*rvt*predict-yes*H0*5
  13192. -->
  13193. (S1 ^operator O1987 = 0.2640492015925779)
  13194. Firing prefer*rvt*predict-yes*H0*5*v1*H1
  13195. -->
  13196. Firing prefer*rvt*predict-no*H0
  13197. -->
  13198. Firing rl*prefer*rvt*predict-no*H0*6
  13199. -->
  13200. (S1 ^operator O1988 = 0.999790145818646)
  13201. inner elaboration loop at bottom goal.
  13202. Retracting rl*prefer*rvt*predict-no*H0*6
  13203. -->
  13204. (S1 ^operator O1986 = 0.999790145818646)
  13205. Retracting rl*prefer*rvt*predict-yes*H0*5
  13206. -->
  13207. (S1 ^operator O1985 = 0.2640492015925779)
  13208. Retracting rl*prefer*rvt*predict-yes*H0*5*v1*H1*41
  13209. -->
  13210. (S1 ^operator O1985 = 0.7362544663116062)
  13211. --- END Proposal Phase ---
  13212. --- Decision Phase ---
  13213. RL update rl*prefer*rvt*predict-no*H0*2 1 0 1 -> 1 0 1(R,m,v=1,1,0)
  13214. =>WM: (14010: S1 ^operator O1987)
  13215. 994: O: O1987 (predict-yes)
  13216. --- END Decision Phase ---
  13217. --- Application Phase ---
  13218. --- Firing Productions (PE) For State At Depth 1 ---
  13219. --- Inner Elaboration Phase, active level 1 (S1) ---
  13220. Firing apply*operator
  13221. -->
  13222. (I3 ^predict-yes N994 + :O )
  13223. Firing apply*operator*complete
  13224. -->
  13225. (I3 ^predict-no N993 - :O )
  13226. inner elaboration loop at bottom goal.
  13227. --- Change Working Memory (PE) ---
  13228. =>WM: (14011: I3 ^predict-yes N994)
  13229. <=WM: (13997: N993 ^status complete)
  13230. <=WM: (13996: I3 ^predict-no N993)
  13231. --- Firing Productions (IE) For State At Depth 1 ---
  13232. --- Inner Elaboration Phase, active level 1 (S1) ---
  13233. Firing monitor*world
  13234. -->
  13235. I see 1 and I'm going to do: predict-yes inner elaboration loop at bottom goal.
  13236. --- Change Working Memory (IE) ---
  13237. --- END Application Phase ---
  13238. --- Output Phase ---
  13239. ENV: Agent did: predict-yes for direction L in state State-B
  13240. In State-B moving L
  13241. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  13242. predict error 0
  13243. dir: dir isL
  13244. --- END Output Phase ---
  13245. |\---- Input Phase ---
  13246. =>WM: (14015: I2 ^dir L)
  13247. =>WM: (14014: I2 ^reward 1)
  13248. =>WM: (14013: I2 ^see 1)
  13249. =>WM: (14012: N994 ^status complete)
  13250. <=WM: (14000: I2 ^dir L)
  13251. <=WM: (13999: I2 ^reward 1)
  13252. <=WM: (13998: I2 ^see 0)
  13253. =>WM: (14016: I2 ^level-1 L1-root)
  13254. <=WM: (14001: I2 ^level-1 R1-root)
  13255. --- END Input Phase ---
  13256. --- Proposal Phase ---
  13257. --- Inner Elaboration Phase, active level 1 (S1) ---
  13258. Firing rl*prefer*rvt*predict-yes*H0*5*v1*H1*31
  13259. -->
  13260. (S1 ^operator O1987 = -0.181727099742844)
  13261. Firing prefer*rvt*predict-yes*H0*5*v1*H1
  13262. -->
  13263. Firing elaborate*copy-see-to-output-link
  13264. -->
  13265. (I3 ^see 1 +)
  13266. Firing elaborate*reward*based*on*reward
  13267. -->
  13268. (R998 ^value 1 +)
  13269. (R1 ^reward R998 +)
  13270. Firing propose*predict-yes
  13271. -->
  13272. (O1989 ^name predict-yes +)
  13273. (S1 ^operator O1989 +)
  13274. Firing propose*predict-no
  13275. -->
  13276. (O1990 ^name predict-no +)
  13277. (S1 ^operator O1990 +)
  13278. Firing rl*prefer*rvt*predict-no*H0*6
  13279. -->
  13280. (S1 ^operator O1988 = 0.999790145818646)
  13281. Firing rl*prefer*rvt*predict-yes*H0*5
  13282. -->
  13283. (S1 ^operator O1987 = 0.2640492015925779)
  13284. Firing prefer*rvt*predict-yes*H0
  13285. -->
  13286. Firing prefer*rvt*predict-no*H0
  13287. -->
  13288. Firing elaborate*copy-dir-to-output-link
  13289. -->
  13290. (I3 ^dir L +)
  13291. inner elaboration loop at bottom goal.
  13292. Retracting elaborate*copy-see-to-output-link
  13293. -->
  13294. (I3 ^see 0 +)
  13295. Retracting propose*predict-no
  13296. -->
  13297. (O1988 ^name predict-no +)
  13298. (S1 ^operator O1988 +)
  13299. Retracting propose*predict-yes
  13300. -->
  13301. (O1987 ^name predict-yes +)
  13302. (S1 ^operator O1987 +)
  13303. Retracting elaborate*reward*based*on*reward
  13304. -->
  13305. (R997 ^value 1 +)
  13306. (R1 ^reward R997 +)
  13307. Retracting elaborate*copy-dir-to-output-link
  13308. -->
  13309. (I3 ^dir L +)
  13310. Retracting rl*prefer*rvt*predict-no*H0*6
  13311. -->
  13312. (S1 ^operator O1988 = 0.999790145818646)
  13313. Retracting rl*prefer*rvt*predict-yes*H0*5
  13314. -->
  13315. (S1 ^operator O1987 = 0.2640492015925779)
  13316. Retracting rl*prefer*rvt*predict-yes*H0*5*v1*H1*41
  13317. -->
  13318. (S1 ^operator O1987 = 0.7362544663116062)
  13319. =>WM: (14023: S1 ^operator O1990 +)
  13320. =>WM: (14022: S1 ^operator O1989 +)
  13321. =>WM: (14021: O1990 ^name predict-no)
  13322. =>WM: (14020: O1989 ^name predict-yes)
  13323. =>WM: (14019: R998 ^value 1)
  13324. =>WM: (14018: R1 ^reward R998)
  13325. =>WM: (14017: I3 ^see 1)
  13326. <=WM: (14008: S1 ^operator O1987 +)
  13327. <=WM: (14010: S1 ^operator O1987)
  13328. <=WM: (14009: S1 ^operator O1988 +)
  13329. <=WM: (14003: R1 ^reward R997)
  13330. <=WM: (14002: I3 ^see 0)
  13331. <=WM: (14006: O1988 ^name predict-no)
  13332. <=WM: (14005: O1987 ^name predict-yes)
  13333. <=WM: (14004: R997 ^value 1)
  13334. --- Inner Elaboration Phase, active level 1 (S1) ---
  13335. Firing prefer*rvt*predict-yes*H0
  13336. -->
  13337. Firing rl*prefer*rvt*predict-yes*H0*5
  13338. -->
  13339. (S1 ^operator O1989 = 0.2640492015925779)
  13340. Firing prefer*rvt*predict-yes*H0*5*v1*H1
  13341. -->
  13342. Firing rl*prefer*rvt*predict-yes*H0*5*v1*H1*31
  13343. -->
  13344. (S1 ^operator O1989 = -0.181727099742844)
  13345. Firing prefer*rvt*predict-no*H0
  13346. -->
  13347. Firing rl*prefer*rvt*predict-no*H0*6
  13348. -->
  13349. (S1 ^operator O1990 = 0.999790145818646)
  13350. inner elaboration loop at bottom goal.
  13351. Retracting rl*prefer*rvt*predict-no*H0*6
  13352. -->
  13353. (S1 ^operator O1988 = 0.999790145818646)
  13354. Retracting rl*prefer*rvt*predict-yes*H0*5
  13355. -->
  13356. (S1 ^operator O1987 = 0.2640492015925779)
  13357. Retracting rl*prefer*rvt*predict-yes*H0*5*v1*H1*31
  13358. -->
  13359. (S1 ^operator O1987 = -0.181727099742844)
  13360. --- END Proposal Phase ---
  13361. --- Decision Phase ---
  13362. RL update rl*prefer*rvt*predict-yes*H0*5 0.554434 -0.290385 0.264049 -> 0.55441 -0.290386 0.264025(R,m,v=1,0.877095,0.108405)
  13363. RL update rl*prefer*rvt*predict-yes*H0*5*v1*H1*41 0.445864 0.29039 0.736254 -> 0.445836 0.29039 0.736226(R,m,v=1,1,0)
  13364. =>WM: (14024: S1 ^operator O1990)
  13365. 995: O: O1990 (predict-no)
  13366. --- END Decision Phase ---
  13367. --- Application Phase ---
  13368. --- Firing Productions (PE) For State At Depth 1 ---
  13369. --- Inner Elaboration Phase, active level 1 (S1) ---
  13370. Firing apply*operator
  13371. -->
  13372. (I3 ^predict-no N995 + :O )
  13373. Firing apply*operator*complete
  13374. -->
  13375. (I3 ^predict-yes N994 - :O )
  13376. inner elaboration loop at bottom goal.
  13377. --- Change Working Memory (PE) ---
  13378. =>WM: (14025: I3 ^predict-no N995)
  13379. <=WM: (14012: N994 ^status complete)
  13380. <=WM: (14011: I3 ^predict-yes N994)
  13381. --- Firing Productions (IE) For State At Depth 1 ---
  13382. --- Inner Elaboration Phase, active level 1 (S1) ---
  13383. Firing monitor*world
  13384. -->
  13385. I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
  13386. --- Change Working Memory (IE) ---
  13387. --- END Application Phase ---
  13388. --- Output Phase ---
  13389. ENV: Agent did: predict-no for direction L in state State-A
  13390. In State-A moving L
  13391. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  13392. predict error 0
  13393. dir: dir isL
  13394. --- END Output Phase ---
  13395. /|\--- Input Phase ---
  13396. =>WM: (14029: I2 ^dir L)
  13397. =>WM: (14028: I2 ^reward 1)
  13398. =>WM: (14027: I2 ^see 0)
  13399. =>WM: (14026: N995 ^status complete)
  13400. <=WM: (14015: I2 ^dir L)
  13401. <=WM: (14014: I2 ^reward 1)
  13402. <=WM: (14013: I2 ^see 1)
  13403. =>WM: (14030: I2 ^level-1 L0-root)
  13404. <=WM: (14016: I2 ^level-1 L1-root)
  13405. --- END Input Phase ---
  13406. --- Proposal Phase ---
  13407. --- Inner Elaboration Phase, active level 1 (S1) ---
  13408. Firing rl*prefer*rvt*predict-yes*H0*5*v1*H1*32
  13409. -->
  13410. (S1 ^operator O1989 = -0.1386470047172653)
  13411. Firing prefer*rvt*predict-yes*H0*5*v1*H1
  13412. -->
  13413. Firing elaborate*copy-see-to-output-link
  13414. -->
  13415. (I3 ^see 0 +)
  13416. Firing elaborate*reward*based*on*reward
  13417. -->
  13418. (R999 ^value 1 +)
  13419. (R1 ^reward R999 +)
  13420. Firing propose*predict-yes
  13421. -->
  13422. (O1991 ^name predict-yes +)
  13423. (S1 ^operator O1991 +)
  13424. Firing propose*predict-no
  13425. -->
  13426. (O1992 ^name predict-no +)
  13427. (S1 ^operator O1992 +)
  13428. Firing rl*prefer*rvt*predict-no*H0*6
  13429. -->
  13430. (S1 ^operator O1990 = 0.999790145818646)
  13431. Firing rl*prefer*rvt*predict-yes*H0*5
  13432. -->
  13433. (S1 ^operator O1989 = 0.2640246623191502)
  13434. Firing prefer*rvt*predict-yes*H0
  13435. -->
  13436. Firing prefer*rvt*predict-no*H0
  13437. -->
  13438. Firing elaborate*copy-dir-to-output-link
  13439. -->
  13440. (I3 ^dir L +)
  13441. inner elaboration loop at bottom goal.
  13442. Retracting elaborate*copy-see-to-output-link
  13443. -->
  13444. (I3 ^see 1 +)
  13445. Retracting propose*predict-no
  13446. -->
  13447. (O1990 ^name predict-no +)
  13448. (S1 ^operator O1990 +)
  13449. Retracting propose*predict-yes
  13450. -->
  13451. (O1989 ^name predict-yes +)
  13452. (S1 ^operator O1989 +)
  13453. Retracting elaborate*reward*based*on*reward
  13454. -->
  13455. (R998 ^value 1 +)
  13456. (R1 ^reward R998 +)
  13457. Retracting elaborate*copy-dir-to-output-link
  13458. -->
  13459. (I3 ^dir L +)
  13460. Retracting rl*prefer*rvt*predict-no*H0*6
  13461. -->
  13462. (S1 ^operator O1990 = 0.999790145818646)
  13463. Retracting rl*prefer*rvt*predict-yes*H0*5*v1*H1*31
  13464. -->
  13465. (S1 ^operator O1989 = -0.181727099742844)
  13466. Retracting rl*prefer*rvt*predict-yes*H0*5
  13467. -->
  13468. (S1 ^operator O1989 = 0.2640246623191502)
  13469. =>WM: (14037: S1 ^operator O1992 +)
  13470. =>WM: (14036: S1 ^operator O1991 +)
  13471. =>WM: (14035: O1992 ^name predict-no)
  13472. =>WM: (14034: O1991 ^name predict-yes)
  13473. =>WM: (14033: R999 ^value 1)
  13474. =>WM: (14032: R1 ^reward R999)
  13475. =>WM: (14031: I3 ^see 0)
  13476. <=WM: (14022: S1 ^operator O1989 +)
  13477. <=WM: (14023: S1 ^operator O1990 +)
  13478. <=WM: (14024: S1 ^operator O1990)
  13479. <=WM: (14018: R1 ^reward R998)
  13480. <=WM: (14017: I3 ^see 1)
  13481. <=WM: (14021: O1990 ^name predict-no)
  13482. <=WM: (14020: O1989 ^name predict-yes)
  13483. <=WM: (14019: R998 ^value 1)
  13484. --- Inner Elaboration Phase, active level 1 (S1) ---
  13485. Firing prefer*rvt*predict-yes*H0
  13486. -->
  13487. Firing rl*prefer*rvt*predict-yes*H0*5
  13488. -->
  13489. (S1 ^operator O1991 = 0.2640246623191502)
  13490. Firing prefer*rvt*predict-yes*H0*5*v1*H1
  13491. -->
  13492. Firing rl*prefer*rvt*predict-yes*H0*5*v1*H1*32
  13493. -->
  13494. (S1 ^operator O1991 = -0.1386470047172653)
  13495. Firing prefer*rvt*predict-no*H0
  13496. -->
  13497. Firing rl*prefer*rvt*predict-no*H0*6
  13498. -->
  13499. (S1 ^operator O1992 = 0.999790145818646)
  13500. inner elaboration loop at bottom goal.
  13501. Retracting rl*prefer*rvt*predict-no*H0*6
  13502. -->
  13503. (S1 ^operator O1990 = 0.999790145818646)
  13504. Retracting rl*prefer*rvt*predict-yes*H0*5
  13505. -->
  13506. (S1 ^operator O1989 = 0.2640246623191502)
  13507. Retracting rl*prefer*rvt*predict-yes*H0*5*v1*H1*32
  13508. -->
  13509. (S1 ^operator O1989 = -0.1386470047172653)
  13510. --- END Proposal Phase ---
  13511. --- Decision Phase ---
  13512. RL update rl*prefer*rvt*predict-no*H0*6 0.99979 0 0.99979 -> 0.999825 0 0.999825(R,m,v=1,0.905405,0.0862291)
  13513. =>WM: (14038: S1 ^operator O1992)
  13514. 996: O: O1992 (predict-no)
  13515. --- END Decision Phase ---
  13516. --- Application Phase ---
  13517. --- Firing Productions (PE) For State At Depth 1 ---
  13518. --- Inner Elaboration Phase, active level 1 (S1) ---
  13519. Firing apply*operator
  13520. -->
  13521. (I3 ^predict-no N996 + :O )
  13522. Firing apply*operator*complete
  13523. -->
  13524. (I3 ^predict-no N995 - :O )
  13525. inner elaboration loop at bottom goal.
  13526. --- Change Working Memory (PE) ---
  13527. =>WM: (14039: I3 ^predict-no N996)
  13528. <=WM: (14026: N995 ^status complete)
  13529. <=WM: (14025: I3 ^predict-no N995)
  13530. --- Firing Productions (IE) For State At Depth 1 ---
  13531. --- Inner Elaboration Phase, active level 1 (S1) ---
  13532. Firing monitor*world
  13533. -->
  13534. I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
  13535. --- Change Working Memory (IE) ---
  13536. --- END Application Phase ---
  13537. --- Output Phase ---
  13538. ENV: Agent did: predict-no for direction L in state State-A
  13539. In State-A moving L
  13540. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  13541. predict error 0
  13542. dir: dir isL
  13543. --- END Output Phase ---
  13544. -/|--- Input Phase ---
  13545. =>WM: (14043: I2 ^dir L)
  13546. =>WM: (14042: I2 ^reward 1)
  13547. =>WM: (14041: I2 ^see 0)
  13548. =>WM: (14040: N996 ^status complete)
  13549. <=WM: (14029: I2 ^dir L)
  13550. <=WM: (14028: I2 ^reward 1)
  13551. <=WM: (14027: I2 ^see 0)
  13552. =>WM: (14044: I2 ^level-1 L0-root)
  13553. <=WM: (14030: I2 ^level-1 L0-root)
  13554. --- END Input Phase ---
  13555. --- Proposal Phase ---
  13556. --- Inner Elaboration Phase, active level 1 (S1) ---
  13557. Firing rl*prefer*rvt*predict-yes*H0*5*v1*H1*32
  13558. -->
  13559. (S1 ^operator O1991 = -0.1386470047172653)
  13560. Firing prefer*rvt*predict-yes*H0*5*v1*H1
  13561. -->
  13562. Firing elaborate*copy-see-to-output-link
  13563. -->
  13564. (I3 ^see 0 +)
  13565. Firing elaborate*reward*based*on*reward
  13566. -->
  13567. (R1000 ^value 1 +)
  13568. (R1 ^reward R1000 +)
  13569. Firing propose*predict-yes
  13570. -->
  13571. (O1993 ^name predict-yes +)
  13572. (S1 ^operator O1993 +)
  13573. Firing propose*predict-no
  13574. -->
  13575. (O1994 ^name predict-no +)
  13576. (S1 ^operator O1994 +)
  13577. Firing rl*prefer*rvt*predict-no*H0*6
  13578. -->
  13579. (S1 ^operator O1992 = 0.9998251377735368)
  13580. Firing rl*prefer*rvt*predict-yes*H0*5
  13581. -->
  13582. (S1 ^operator O1991 = 0.2640246623191502)
  13583. Firing prefer*rvt*predict-yes*H0
  13584. -->
  13585. Firing prefer*rvt*predict-no*H0
  13586. -->
  13587. Firing elaborate*copy-dir-to-output-link
  13588. -->
  13589. (I3 ^dir L +)
  13590. inner elaboration loop at bottom goal.
  13591. Retracting elaborate*copy-see-to-output-link
  13592. -->
  13593. (I3 ^see 0 +)
  13594. Retracting propose*predict-no
  13595. -->
  13596. (O1992 ^name predict-no +)
  13597. (S1 ^operator O1992 +)
  13598. Retracting propose*predict-yes
  13599. -->
  13600. (O1991 ^name predict-yes +)
  13601. (S1 ^operator O1991 +)
  13602. Retracting elaborate*reward*based*on*reward
  13603. -->
  13604. (R999 ^value 1 +)
  13605. (R1 ^reward R999 +)
  13606. Retracting elaborate*copy-dir-to-output-link
  13607. -->
  13608. (I3 ^dir L +)
  13609. Retracting rl*prefer*rvt*predict-no*H0*6
  13610. -->
  13611. (S1 ^operator O1992 = 0.9998251377735368)
  13612. Retracting rl*prefer*rvt*predict-yes*H0*5*v1*H1*32
  13613. -->
  13614. (S1 ^operator O1991 = -0.1386470047172653)
  13615. Retracting rl*prefer*rvt*predict-yes*H0*5
  13616. -->
  13617. (S1 ^operator O1991 = 0.2640246623191502)
  13618. =>WM: (14050: S1 ^operator O1994 +)
  13619. =>WM: (14049: S1 ^operator O1993 +)
  13620. =>WM: (14048: O1994 ^name predict-no)
  13621. =>WM: (14047: O1993 ^name predict-yes)
  13622. =>WM: (14046: R1000 ^value 1)
  13623. =>WM: (14045: R1 ^reward R1000)
  13624. <=WM: (14036: S1 ^operator O1991 +)
  13625. <=WM: (14037: S1 ^operator O1992 +)
  13626. <=WM: (14038: S1 ^operator O1992)
  13627. <=WM: (14032: R1 ^reward R999)
  13628. <=WM: (14035: O1992 ^name predict-no)
  13629. <=WM: (14034: O1991 ^name predict-yes)
  13630. <=WM: (14033: R999 ^value 1)
  13631. --- Inner Elaboration Phase, active level 1 (S1) ---
  13632. Firing prefer*rvt*predict-yes*H0
  13633. -->
  13634. Firing rl*prefer*rvt*predict-yes*H0*5
  13635. -->
  13636. (S1 ^operator O1993 = 0.2640246623191502)
  13637. Firing prefer*rvt*predict-yes*H0*5*v1*H1
  13638. -->
  13639. Firing rl*prefer*rvt*predict-yes*H0*5*v1*H1*32
  13640. -->
  13641. (S1 ^operator O1993 = -0.1386470047172653)
  13642. Firing prefer*rvt*predict-no*H0
  13643. -->
  13644. Firing rl*prefer*rvt*predict-no*H0*6
  13645. -->
  13646. (S1 ^operator O1994 = 0.9998251377735368)
  13647. inner elaboration loop at bottom goal.
  13648. Retracting rl*prefer*rvt*predict-no*H0*6
  13649. -->
  13650. (S1 ^operator O1992 = 0.9998251377735368)
  13651. Retracting rl*prefer*rvt*predict-yes*H0*5
  13652. -->
  13653. (S1 ^operator O1991 = 0.2640246623191502)
  13654. Retracting rl*prefer*rvt*predict-yes*H0*5*v1*H1*32
  13655. -->
  13656. (S1 ^operator O1991 = -0.1386470047172653)
  13657. --- END Proposal Phase ---
  13658. --- Decision Phase ---
  13659. RL update rl*prefer*rvt*predict-no*H0*6 0.999825 0 0.999825 -> 0.999854 0 0.999854(R,m,v=1,0.90604,0.0857065)
  13660. =>WM: (14051: S1 ^operator O1994)
  13661. 997: O: O1994 (predict-no)
  13662. --- END Decision Phase ---
  13663. --- Application Phase ---
  13664. --- Firing Productions (PE) For State At Depth 1 ---
  13665. --- Inner Elaboration Phase, active level 1 (S1) ---
  13666. Firing apply*operator
  13667. -->
  13668. (I3 ^predict-no N997 + :O )
  13669. Firing apply*operator*complete
  13670. -->
  13671. (I3 ^predict-no N996 - :O )
  13672. inner elaboration loop at bottom goal.
  13673. --- Change Working Memory (PE) ---
  13674. =>WM: (14052: I3 ^predict-no N997)
  13675. <=WM: (14040: N996 ^status complete)
  13676. <=WM: (14039: I3 ^predict-no N996)
  13677. --- Firing Productions (IE) For State At Depth 1 ---
  13678. --- Inner Elaboration Phase, active level 1 (S1) ---
  13679. Firing monitor*world
  13680. -->
  13681. I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
  13682. --- Change Working Memory (IE) ---
  13683. --- END Application Phase ---
  13684. --- Output Phase ---
  13685. ENV: Agent did: predict-no for direction L in state State-A
  13686. In State-A moving L
  13687. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  13688. predict error 0
  13689. dir: dir isU
  13690. --- END Output Phase ---
  13691. \-/--- Input Phase ---
  13692. =>WM: (14056: I2 ^dir U)
  13693. =>WM: (14055: I2 ^reward 1)
  13694. =>WM: (14054: I2 ^see 0)
  13695. =>WM: (14053: N997 ^status complete)
  13696. <=WM: (14043: I2 ^dir L)
  13697. <=WM: (14042: I2 ^reward 1)
  13698. <=WM: (14041: I2 ^see 0)
  13699. =>WM: (14057: I2 ^level-1 L0-root)
  13700. <=WM: (14044: I2 ^level-1 L0-root)
  13701. --- END Input Phase ---
  13702. --- Proposal Phase ---
  13703. --- Inner Elaboration Phase, active level 1 (S1) ---
  13704. Firing elaborate*copy-see-to-output-link
  13705. -->
  13706. (I3 ^see 0 +)
  13707. Firing elaborate*reward*based*on*reward
  13708. -->
  13709. (R1001 ^value 1 +)
  13710. (R1 ^reward R1001 +)
  13711. Firing propose*predict-yes
  13712. -->
  13713. (O1995 ^name predict-yes +)
  13714. (S1 ^operator O1995 +)
  13715. Firing propose*predict-no
  13716. -->
  13717. (O1996 ^name predict-no +)
  13718. (S1 ^operator O1996 +)
  13719. Firing rl*prefer*rvt*predict-no*H0*2
  13720. -->
  13721. (S1 ^operator O1994 = 1.)
  13722. Firing rl*prefer*rvt*predict-yes*H0*1
  13723. -->
  13724. (S1 ^operator O1993 = 0.)
  13725. Firing prefer*rvt*predict-yes*H0
  13726. -->
  13727. Firing prefer*rvt*predict-no*H0
  13728. -->
  13729. Firing elaborate*copy-dir-to-output-link
  13730. -->
  13731. (I3 ^dir U +)
  13732. inner elaboration loop at bottom goal.
  13733. Retracting elaborate*copy-see-to-output-link
  13734. -->
  13735. (I3 ^see 0 +)
  13736. Retracting propose*predict-no
  13737. -->
  13738. (O1994 ^name predict-no +)
  13739. (S1 ^operator O1994 +)
  13740. Retracting propose*predict-yes
  13741. -->
  13742. (O1993 ^name predict-yes +)
  13743. (S1 ^operator O1993 +)
  13744. Retracting elaborate*reward*based*on*reward
  13745. -->
  13746. (R1000 ^value 1 +)
  13747. (R1 ^reward R1000 +)
  13748. Retracting elaborate*copy-dir-to-output-link
  13749. -->
  13750. (I3 ^dir L +)
  13751. Retracting rl*prefer*rvt*predict-no*H0*6
  13752. -->
  13753. (S1 ^operator O1994 = 0.9998542623222174)
  13754. Retracting rl*prefer*rvt*predict-yes*H0*5*v1*H1*32
  13755. -->
  13756. (S1 ^operator O1993 = -0.1386470047172653)
  13757. Retracting rl*prefer*rvt*predict-yes*H0*5
  13758. -->
  13759. (S1 ^operator O1993 = 0.2640246623191502)
  13760. =>WM: (14064: S1 ^operator O1996 +)
  13761. =>WM: (14063: S1 ^operator O1995 +)
  13762. =>WM: (14062: I3 ^dir U)
  13763. =>WM: (14061: O1996 ^name predict-no)
  13764. =>WM: (14060: O1995 ^name predict-yes)
  13765. =>WM: (14059: R1001 ^value 1)
  13766. =>WM: (14058: R1 ^reward R1001)
  13767. <=WM: (14049: S1 ^operator O1993 +)
  13768. <=WM: (14050: S1 ^operator O1994 +)
  13769. <=WM: (14051: S1 ^operator O1994)
  13770. <=WM: (14007: I3 ^dir L)
  13771. <=WM: (14045: R1 ^reward R1000)
  13772. <=WM: (14048: O1994 ^name predict-no)
  13773. <=WM: (14047: O1993 ^name predict-yes)
  13774. <=WM: (14046: R1000 ^value 1)
  13775. --- Inner Elaboration Phase, active level 1 (S1) ---
  13776. Firing prefer*rvt*predict-yes*H0
  13777. -->
  13778. Firing rl*prefer*rvt*predict-yes*H0*1
  13779. -->
  13780. (S1 ^operator O1995 = 0.)
  13781. Firing prefer*rvt*predict-no*H0
  13782. -->
  13783. Firing rl*prefer*rvt*predict-no*H0*2
  13784. -->
  13785. (S1 ^operator O1996 = 1.)
  13786. inner elaboration loop at bottom goal.
  13787. Retracting rl*prefer*rvt*predict-no*H0*2
  13788. -->
  13789. (S1 ^operator O1994 = 1.)
  13790. Retracting rl*prefer*rvt*predict-yes*H0*1
  13791. -->
  13792. (S1 ^operator O1993 = 0.)
  13793. --- END Proposal Phase ---
  13794. --- Decision Phase ---
  13795. RL update rl*prefer*rvt*predict-no*H0*6 0.999854 0 0.999854 -> 0.999879 0 0.999879(R,m,v=1,0.906667,0.0851902)
  13796. =>WM: (14065: S1 ^operator O1996)
  13797. 998: O: O1996 (predict-no)
  13798. --- END Decision Phase ---
  13799. --- Application Phase ---
  13800. --- Firing Productions (PE) For State At Depth 1 ---
  13801. --- Inner Elaboration Phase, active level 1 (S1) ---
  13802. Firing apply*operator
  13803. -->
  13804. (I3 ^predict-no N998 + :O )
  13805. Firing apply*operator*complete
  13806. -->
  13807. (I3 ^predict-no N997 - :O )
  13808. inner elaboration loop at bottom goal.
  13809. --- Change Working Memory (PE) ---
  13810. =>WM: (14066: I3 ^predict-no N998)
  13811. <=WM: (14053: N997 ^status complete)
  13812. <=WM: (14052: I3 ^predict-no N997)
  13813. --- Firing Productions (IE) For State At Depth 1 ---
  13814. --- Inner Elaboration Phase, active level 1 (S1) ---
  13815. Firing monitor*world
  13816. -->
  13817. I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
  13818. --- Change Working Memory (IE) ---
  13819. --- END Application Phase ---
  13820. --- Output Phase ---
  13821. ENV: Agent did: predict-no for direction U in state State-A
  13822. In State-A moving U
  13823. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  13824. predict error 0
  13825. dir: dir isU
  13826. --- END Output Phase ---
  13827. |\---- Input Phase ---
  13828. =>WM: (14070: I2 ^dir U)
  13829. =>WM: (14069: I2 ^reward 1)
  13830. =>WM: (14068: I2 ^see 0)
  13831. =>WM: (14067: N998 ^status complete)
  13832. <=WM: (14056: I2 ^dir U)
  13833. <=WM: (14055: I2 ^reward 1)
  13834. <=WM: (14054: I2 ^see 0)
  13835. =>WM: (14071: I2 ^level-1 L0-root)
  13836. <=WM: (14057: I2 ^level-1 L0-root)
  13837. --- END Input Phase ---
  13838. --- Proposal Phase ---
  13839. --- Inner Elaboration Phase, active level 1 (S1) ---
  13840. Firing elaborate*copy-see-to-output-link
  13841. -->
  13842. (I3 ^see 0 +)
  13843. Firing elaborate*reward*based*on*reward
  13844. -->
  13845. (R1002 ^value 1 +)
  13846. (R1 ^reward R1002 +)
  13847. Firing propose*predict-yes
  13848. -->
  13849. (O1997 ^name predict-yes +)
  13850. (S1 ^operator O1997 +)
  13851. Firing propose*predict-no
  13852. -->
  13853. (O1998 ^name predict-no +)
  13854. (S1 ^operator O1998 +)
  13855. Firing rl*prefer*rvt*predict-no*H0*2
  13856. -->
  13857. (S1 ^operator O1996 = 1.)
  13858. Firing rl*prefer*rvt*predict-yes*H0*1
  13859. -->
  13860. (S1 ^operator O1995 = 0.)
  13861. Firing prefer*rvt*predict-yes*H0
  13862. -->
  13863. Firing prefer*rvt*predict-no*H0
  13864. -->
  13865. Firing elaborate*copy-dir-to-output-link
  13866. -->
  13867. (I3 ^dir U +)
  13868. inner elaboration loop at bottom goal.
  13869. Retracting elaborate*copy-see-to-output-link
  13870. -->
  13871. (I3 ^see 0 +)
  13872. Retracting propose*predict-no
  13873. -->
  13874. (O1996 ^name predict-no +)
  13875. (S1 ^operator O1996 +)
  13876. Retracting propose*predict-yes
  13877. -->
  13878. (O1995 ^name predict-yes +)
  13879. (S1 ^operator O1995 +)
  13880. Retracting elaborate*reward*based*on*reward
  13881. -->
  13882. (R1001 ^value 1 +)
  13883. (R1 ^reward R1001 +)
  13884. Retracting elaborate*copy-dir-to-output-link
  13885. -->
  13886. (I3 ^dir U +)
  13887. Retracting rl*prefer*rvt*predict-no*H0*2
  13888. -->
  13889. (S1 ^operator O1996 = 1.)
  13890. Retracting rl*prefer*rvt*predict-yes*H0*1
  13891. -->
  13892. (S1 ^operator O1995 = 0.)
  13893. =>WM: (14077: S1 ^operator O1998 +)
  13894. =>WM: (14076: S1 ^operator O1997 +)
  13895. =>WM: (14075: O1998 ^name predict-no)
  13896. =>WM: (14074: O1997 ^name predict-yes)
  13897. =>WM: (14073: R1002 ^value 1)
  13898. =>WM: (14072: R1 ^reward R1002)
  13899. <=WM: (14063: S1 ^operator O1995 +)
  13900. <=WM: (14064: S1 ^operator O1996 +)
  13901. <=WM: (14065: S1 ^operator O1996)
  13902. <=WM: (14058: R1 ^reward R1001)
  13903. <=WM: (14061: O1996 ^name predict-no)
  13904. <=WM: (14060: O1995 ^name predict-yes)
  13905. <=WM: (14059: R1001 ^value 1)
  13906. --- Inner Elaboration Phase, active level 1 (S1) ---
  13907. Firing prefer*rvt*predict-yes*H0
  13908. -->
  13909. Firing rl*prefer*rvt*predict-yes*H0*1
  13910. -->
  13911. (S1 ^operator O1997 = 0.)
  13912. Firing prefer*rvt*predict-no*H0
  13913. -->
  13914. Firing rl*prefer*rvt*predict-no*H0*2
  13915. -->
  13916. (S1 ^operator O1998 = 1.)
  13917. inner elaboration loop at bottom goal.
  13918. Retracting rl*prefer*rvt*predict-no*H0*2
  13919. -->
  13920. (S1 ^operator O1996 = 1.)
  13921. Retracting rl*prefer*rvt*predict-yes*H0*1
  13922. -->
  13923. (S1 ^operator O1995 = 0.)
  13924. --- END Proposal Phase ---
  13925. --- Decision Phase ---
  13926. RL update rl*prefer*rvt*predict-no*H0*2 1 0 1 -> 1 0 1(R,m,v=1,1,0)
  13927. =>WM: (14078: S1 ^operator O1998)
  13928. 999: O: O1998 (predict-no)
  13929. --- END Decision Phase ---
  13930. --- Application Phase ---
  13931. --- Firing Productions (PE) For State At Depth 1 ---
  13932. --- Inner Elaboration Phase, active level 1 (S1) ---
  13933. Firing apply*operator
  13934. -->
  13935. (I3 ^predict-no N999 + :O )
  13936. Firing apply*operator*complete
  13937. -->
  13938. (I3 ^predict-no N998 - :O )
  13939. inner elaboration loop at bottom goal.
  13940. --- Change Working Memory (PE) ---
  13941. =>WM: (14079: I3 ^predict-no N999)
  13942. <=WM: (14067: N998 ^status complete)
  13943. <=WM: (14066: I3 ^predict-no N998)
  13944. --- Firing Productions (IE) For State At Depth 1 ---
  13945. --- Inner Elaboration Phase, active level 1 (S1) ---
  13946. Firing monitor*world
  13947. -->
  13948. I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
  13949. --- Change Working Memory (IE) ---
  13950. --- END Application Phase ---
  13951. --- Output Phase ---
  13952. ENV: Agent did: predict-no for direction U in state State-A
  13953. In State-A moving U
  13954. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  13955. predict error 0
  13956. dir: dir isR
  13957. --- END Output Phase ---
  13958. /|\--- Input Phase ---
  13959. =>WM: (14083: I2 ^dir R)
  13960. =>WM: (14082: I2 ^reward 1)
  13961. =>WM: (14081: I2 ^see 0)
  13962. =>WM: (14080: N999 ^status complete)
  13963. <=WM: (14070: I2 ^dir U)
  13964. <=WM: (14069: I2 ^reward 1)
  13965. <=WM: (14068: I2 ^see 0)
  13966. =>WM: (14084: I2 ^level-1 L0-root)
  13967. <=WM: (14071: I2 ^level-1 L0-root)
  13968. --- END Input Phase ---
  13969. --- Proposal Phase ---
  13970. --- Inner Elaboration Phase, active level 1 (S1) ---
  13971. Firing rl*prefer*rvt*predict-no*H0*4*v1*H1*33
  13972. -->
  13973. (S1 ^operator O1998 = -0.2817060109291377)
  13974. Firing rl*prefer*rvt*predict-yes*H0*3*v1*H1*34
  13975. -->
  13976. (S1 ^operator O1997 = 0.6623525109664488)
  13977. Firing prefer*rvt*predict-no*H0*4*v1*H1
  13978. -->
  13979. Firing prefer*rvt*predict-yes*H0*3*v1*H1
  13980. -->
  13981. Firing elaborate*copy-see-to-output-link
  13982. -->
  13983. (I3 ^see 0 +)
  13984. Firing elaborate*reward*based*on*reward
  13985. -->
  13986. (R1003 ^value 1 +)
  13987. (R1 ^reward R1003 +)
  13988. Firing propose*predict-yes
  13989. -->
  13990. (O1999 ^name predict-yes +)
  13991. (S1 ^operator O1999 +)
  13992. Firing propose*predict-no
  13993. -->
  13994. (O2000 ^name predict-no +)
  13995. (S1 ^operator O2000 +)
  13996. Firing rl*prefer*rvt*predict-no*H0*4
  13997. -->
  13998. (S1 ^operator O1998 = 0.339773810196969)
  13999. Firing rl*prefer*rvt*predict-yes*H0*3
  14000. -->
  14001. (S1 ^operator O1997 = 0.337717515090074)
  14002. Firing prefer*rvt*predict-yes*H0
  14003. -->
  14004. Firing prefer*rvt*predict-no*H0
  14005. -->
  14006. Firing elaborate*copy-dir-to-output-link
  14007. -->
  14008. (I3 ^dir R +)
  14009. inner elaboration loop at bottom goal.
  14010. Retracting elaborate*copy-see-to-output-link
  14011. -->
  14012. (I3 ^see 0 +)
  14013. Retracting propose*predict-no
  14014. -->
  14015. (O1998 ^name predict-no +)
  14016. (S1 ^operator O1998 +)
  14017. Retracting propose*predict-yes
  14018. -->
  14019. (O1997 ^name predict-yes +)
  14020. (S1 ^operator O1997 +)
  14021. Retracting elaborate*reward*based*on*reward
  14022. -->
  14023. (R1002 ^value 1 +)
  14024. (R1 ^reward R1002 +)
  14025. Retracting elaborate*copy-dir-to-output-link
  14026. -->
  14027. (I3 ^dir U +)
  14028. Retracting rl*prefer*rvt*predict-no*H0*2
  14029. -->
  14030. (S1 ^operator O1998 = 1.)
  14031. Retracting rl*prefer*rvt*predict-yes*H0*1
  14032. -->
  14033. (S1 ^operator O1997 = 0.)
  14034. =>WM: (14091: S1 ^operator O2000 +)
  14035. =>WM: (14090: S1 ^operator O1999 +)
  14036. =>WM: (14089: I3 ^dir R)
  14037. =>WM: (14088: O2000 ^name predict-no)
  14038. =>WM: (14087: O1999 ^name predict-yes)
  14039. =>WM: (14086: R1003 ^value 1)
  14040. =>WM: (14085: R1 ^reward R1003)
  14041. <=WM: (14076: S1 ^operator O1997 +)
  14042. <=WM: (14077: S1 ^operator O1998 +)
  14043. <=WM: (14078: S1 ^operator O1998)
  14044. <=WM: (14062: I3 ^dir U)
  14045. <=WM: (14072: R1 ^reward R1002)
  14046. <=WM: (14075: O1998 ^name predict-no)
  14047. <=WM: (14074: O1997 ^name predict-yes)
  14048. <=WM: (14073: R1002 ^value 1)
  14049. --- Inner Elaboration Phase, active level 1 (S1) ---
  14050. Firing prefer*rvt*predict-yes*H0
  14051. -->
  14052. Firing rl*prefer*rvt*predict-yes*H0*3*v1*H1*34
  14053. -->
  14054. (S1 ^operator O1999 = 0.6623525109664488)
  14055. Firing rl*prefer*rvt*predict-yes*H0*3
  14056. -->
  14057. (S1 ^operator O1999 = 0.337717515090074)
  14058. Firing prefer*rvt*predict-yes*H0*3*v1*H1
  14059. -->
  14060. Firing prefer*rvt*predict-no*H0
  14061. -->
  14062. Firing rl*prefer*rvt*predict-no*H0*4*v1*H1*33
  14063. -->
  14064. (S1 ^operator O2000 = -0.2817060109291377)
  14065. Firing rl*prefer*rvt*predict-no*H0*4
  14066. -->
  14067. (S1 ^operator O2000 = 0.339773810196969)
  14068. Firing prefer*rvt*predict-no*H0*4*v1*H1
  14069. -->
  14070. inner elaboration loop at bottom goal.
  14071. Retracting rl*prefer*rvt*predict-no*H0*4
  14072. -->
  14073. (S1 ^operator O1998 = 0.339773810196969)
  14074. Retracting rl*prefer*rvt*predict-no*H0*4*v1*H1*33
  14075. -->
  14076. (S1 ^operator O1998 = -0.2817060109291377)
  14077. Retracting rl*prefer*rvt*predict-yes*H0*3
  14078. -->
  14079. (S1 ^operator O1997 = 0.337717515090074)
  14080. Retracting rl*prefer*rvt*predict-yes*H0*3*v1*H1*34
  14081. -->
  14082. (S1 ^operator O1997 = 0.6623525109664488)
  14083. --- END Proposal Phase ---
  14084. --- Decision Phase ---
  14085. RL update rl*prefer*rvt*predict-no*H0*2 1 0 1 -> 1 0 1(R,m,v=1,1,0)
  14086. =>WM: (14092: S1 ^operator O1999)
  14087. 1000: O: O1999 (predict-yes)
  14088. --- END Decision Phase ---
  14089. --- Application Phase ---
  14090. --- Firing Productions (PE) For State At Depth 1 ---
  14091. --- Inner Elaboration Phase, active level 1 (S1) ---
  14092. Firing apply*operator
  14093. -->
  14094. (I3 ^predict-yes N1000 + :O )
  14095. Firing apply*operator*complete
  14096. -->
  14097. (I3 ^predict-no N999 - :O )
  14098. inner elaboration loop at bottom goal.
  14099. --- Change Working Memory (PE) ---
  14100. =>WM: (14093: I3 ^predict-yes N1000)
  14101. <=WM: (14080: N999 ^status complete)
  14102. <=WM: (14079: I3 ^predict-no N999)
  14103. --- Firing Productions (IE) For State At Depth 1 ---
  14104. --- Inner Elaboration Phase, active level 1 (S1) ---
  14105. Firing monitor*world
  14106. -->
  14107. I see 1 and I'm going to do: predict-yes inner elaboration loop at bottom goal.
  14108. --- Change Working Memory (IE) ---
  14109. --- END Application Phase ---
  14110. --- Output Phase ---
  14111. ENV: Agent did: predict-yes for direction R in state State-A
  14112. In State-A moving R
  14113. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  14114. predict error 0
  14115. dir: dir isU
  14116. --- END Output Phase ---
  14117. -/|\-/|\-/|--- Input Phase ---
  14118. =>WM: (14097: I2 ^dir U)
  14119. =>WM: (14096: I2 ^reward 1)
  14120. =>WM: (14095: I2 ^see 1)
  14121. =>WM: (14094: N1000 ^status complete)
  14122. <=WM: (14083: I2 ^dir R)
  14123. <=WM: (14082: I2 ^reward 1)
  14124. <=WM: (14081: I2 ^see 0)
  14125. =>WM: (14098: I2 ^level-1 R1-root)
  14126. <=WM: (14084: I2 ^level-1 L0-root)
  14127. --- END Input Phase ---
  14128. --- Proposal Phase ---
  14129. --- Inner Elaboration Phase, active level 1 (S1) ---
  14130. Firing elaborate*copy-see-to-output-link
  14131. -->
  14132. (I3 ^see 1 +)
  14133. Firing elaborate*reward*based*on*reward
  14134. -->
  14135. (R1004 ^value 1 +)
  14136. (R1 ^reward R1004 +)
  14137. Firing propose*predict-yes
  14138. -->
  14139. (O2001 ^name predict-yes +)
  14140. (S1 ^operator O2001 +)
  14141. Firing propose*predict-no
  14142. -->
  14143. (O2002 ^name predict-no +)
  14144. (S1 ^operator O2002 +)
  14145. Firing rl*prefer*rvt*predict-no*H0*2
  14146. -->
  14147. (S1 ^operator O2000 = 1.)
  14148. Firing rl*prefer*rvt*predict-yes*H0*1
  14149. -->
  14150. (S1 ^operator O1999 = 0.)
  14151. Firing prefer*rvt*predict-yes*H0
  14152. -->
  14153. Firing prefer*rvt*predict-no*H0
  14154. -->
  14155. Firing elaborate*copy-dir-to-output-link
  14156. -->
  14157. (I3 ^dir U +)
  14158. inner elaboration loop at bottom goal.
  14159. Retracting elaborate*copy-see-to-output-link
  14160. -->
  14161. (I3 ^see 0 +)
  14162. Retracting propose*predict-no
  14163. -->
  14164. (O2000 ^name predict-no +)
  14165. (S1 ^operator O2000 +)
  14166. Retracting propose*predict-yes
  14167. -->
  14168. (O1999 ^name predict-yes +)
  14169. (S1 ^operator O1999 +)
  14170. Retracting elaborate*reward*based*on*reward
  14171. -->
  14172. (R1003 ^value 1 +)
  14173. (R1 ^reward R1003 +)
  14174. Retracting elaborate*copy-dir-to-output-link
  14175. -->
  14176. (I3 ^dir R +)
  14177. Retracting rl*prefer*rvt*predict-no*H0*4
  14178. -->
  14179. (S1 ^operator O2000 = 0.339773810196969)
  14180. Retracting rl*prefer*rvt*predict-no*H0*4*v1*H1*33
  14181. -->
  14182. (S1 ^operator O2000 = -0.2817060109291377)
  14183. Retracting rl*prefer*rvt*predict-yes*H0*3
  14184. -->
  14185. (S1 ^operator O1999 = 0.337717515090074)
  14186. Retracting rl*prefer*rvt*predict-yes*H0*3*v1*H1*34
  14187. -->
  14188. (S1 ^operator O1999 = 0.6623525109664488)
  14189. =>WM: (14106: S1 ^operator O2002 +)
  14190. =>WM: (14105: S1 ^operator O2001 +)
  14191. =>WM: (14104: I3 ^dir U)
  14192. =>WM: (14103: O2002 ^name predict-no)
  14193. =>WM: (14102: O2001 ^name predict-yes)
  14194. =>WM: (14101: R1004 ^value 1)
  14195. =>WM: (14100: R1 ^reward R1004)
  14196. =>WM: (14099: I3 ^see 1)
  14197. <=WM: (14090: S1 ^operator O1999 +)
  14198. <=WM: (14092: S1 ^operator O1999)
  14199. <=WM: (14091: S1 ^operator O2000 +)
  14200. <=WM: (14089: I3 ^dir R)
  14201. <=WM: (14085: R1 ^reward R1003)
  14202. <=WM: (14031: I3 ^see 0)
  14203. <=WM: (14088: O2000 ^name predict-no)
  14204. <=WM: (14087: O1999 ^name predict-yes)
  14205. <=WM: (14086: R1003 ^value 1)
  14206. --- Inner Elaboration Phase, active level 1 (S1) ---
  14207. Firing prefer*rvt*predict-yes*H0
  14208. -->
  14209. Firing rl*prefer*rvt*predict-yes*H0*1
  14210. -->
  14211. (S1 ^operator O2001 = 0.)
  14212. Firing prefer*rvt*predict-no*H0
  14213. -->
  14214. Firing rl*prefer*rvt*predict-no*H0*2
  14215. -->
  14216. (S1 ^operator O2002 = 1.)
  14217. inner elaboration loop at bottom goal.
  14218. Retracting rl*prefer*rvt*predict-no*H0*2
  14219. -->
  14220. (S1 ^operator O2000 = 1.)
  14221. Retracting rl*prefer*rvt*predict-yes*H0*1
  14222. -->
  14223. (S1 ^operator O1999 = 0.)
  14224. --- END Proposal Phase ---
  14225. --- Decision Phase ---
  14226. RL update rl*prefer*rvt*predict-yes*H0*3 0.590119 -0.252401 0.337718 -> 0.590112 -0.2524 0.337712(R,m,v=1,0.89881,0.0914956)
  14227. RL update rl*prefer*rvt*predict-yes*H0*3*v1*H1*34 0.409962 0.25239 0.662353 -> 0.409954 0.252391 0.662346(R,m,v=1,1,0)
  14228. =>WM: (14107: S1 ^operator O2002)
  14229. 1001: O: O2002 (predict-no)
  14230. --- END Decision Phase ---
  14231. --- Application Phase ---
  14232. --- Firing Productions (PE) For State At Depth 1 ---
  14233. --- Inner Elaboration Phase, active level 1 (S1) ---
  14234. Firing apply*operator
  14235. -->
  14236. (I3 ^predict-no N1001 + :O )
  14237. Firing apply*operator*complete
  14238. -->
  14239. (I3 ^predict-yes N1000 - :O )
  14240. inner elaboration loop at bottom goal.
  14241. --- Change Working Memory (PE) ---
  14242. =>WM: (14108: I3 ^predict-no N1001)
  14243. <=WM: (14094: N1000 ^status complete)
  14244. <=WM: (14093: I3 ^predict-yes N1000)
  14245. --- Firing Productions (IE) For State At Depth 1 ---
  14246. --- Inner Elaboration Phase, active level 1 (S1) ---
  14247. Firing monitor*world
  14248. -->
  14249. I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
  14250. --- Change Working Memory (IE) ---
  14251. --- END Application Phase ---
  14252. --- Output Phase ---
  14253. ENV: Agent did: predict-no for direction U in state State-B
  14254. In State-B moving U
  14255. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  14256. predict error 0
  14257. dir: dir isU
  14258. --- END Output Phase ---
  14259. \--- Input Phase ---
  14260. =>WM: (14112: I2 ^dir U)
  14261. =>WM: (14111: I2 ^reward 1)
  14262. =>WM: (14110: I2 ^see 0)
  14263. =>WM: (14109: N1001 ^status complete)
  14264. <=WM: (14097: I2 ^dir U)
  14265. <=WM: (14096: I2 ^reward 1)
  14266. <=WM: (14095: I2 ^see 1)
  14267. =>WM: (14113: I2 ^level-1 R1-root)
  14268. <=WM: (14098: I2 ^level-1 R1-root)
  14269. --- END Input Phase ---
  14270. --- Proposal Phase ---
  14271. --- Inner Elaboration Phase, active level 1 (S1) ---
  14272. Firing elaborate*copy-see-to-output-link
  14273. -->
  14274. (I3 ^see 0 +)
  14275. Firing elaborate*reward*based*on*reward
  14276. -->
  14277. (R1005 ^value 1 +)
  14278. (R1 ^reward R1005 +)
  14279. Firing propose*predict-yes
  14280. -->
  14281. (O2003 ^name predict-yes +)
  14282. (S1 ^operator O2003 +)
  14283. Firing propose*predict-no
  14284. -->
  14285. (O2004 ^name predict-no +)
  14286. (S1 ^operator O2004 +)
  14287. Firing rl*prefer*rvt*predict-no*H0*2
  14288. -->
  14289. (S1 ^operator O2002 = 1.)
  14290. Firing rl*prefer*rvt*predict-yes*H0*1
  14291. -->
  14292. (S1 ^operator O2001 = 0.)
  14293. Firing prefer*rvt*predict-yes*H0
  14294. -->
  14295. Firing prefer*rvt*predict-no*H0
  14296. -->
  14297. Firing elaborate*copy-dir-to-output-link
  14298. -->
  14299. (I3 ^dir U +)
  14300. inner elaboration loop at bottom goal.
  14301. Retracting elaborate*copy-see-to-output-link
  14302. -->
  14303. (I3 ^see 1 +)
  14304. Retracting propose*predict-no
  14305. -->
  14306. (O2002 ^name predict-no +)
  14307. (S1 ^operator O2002 +)
  14308. Retracting propose*predict-yes
  14309. -->
  14310. (O2001 ^name predict-yes +)
  14311. (S1 ^operator O2001 +)
  14312. Retracting elaborate*reward*based*on*reward
  14313. -->
  14314. (R1004 ^value 1 +)
  14315. (R1 ^reward R1004 +)
  14316. Retracting elaborate*copy-dir-to-output-link
  14317. -->
  14318. (I3 ^dir U +)
  14319. Retracting rl*prefer*rvt*predict-no*H0*2
  14320. -->
  14321. (S1 ^operator O2002 = 1.)
  14322. Retracting rl*prefer*rvt*predict-yes*H0*1
  14323. -->
  14324. (S1 ^operator O2001 = 0.)
  14325. =>WM: (14120: S1 ^operator O2004 +)
  14326. =>WM: (14119: S1 ^operator O2003 +)
  14327. =>WM: (14118: O2004 ^name predict-no)
  14328. =>WM: (14117: O2003 ^name predict-yes)
  14329. =>WM: (14116: R1005 ^value 1)
  14330. =>WM: (14115: R1 ^reward R1005)
  14331. =>WM: (14114: I3 ^see 0)
  14332. <=WM: (14105: S1 ^operator O2001 +)
  14333. <=WM: (14106: S1 ^operator O2002 +)
  14334. <=WM: (14107: S1 ^operator O2002)
  14335. <=WM: (14100: R1 ^reward R1004)
  14336. <=WM: (14099: I3 ^see 1)
  14337. <=WM: (14103: O2002 ^name predict-no)
  14338. <=WM: (14102: O2001 ^name predict-yes)
  14339. <=WM: (14101: R1004 ^value 1)
  14340. --- Inner Elaboration Phase, active level 1 (S1) ---
  14341. Firing prefer*rvt*predict-yes*H0
  14342. -->
  14343. Firing rl*prefer*rvt*predict-yes*H0*1
  14344. -->
  14345. (S1 ^operator O2003 = 0.)
  14346. Firing prefer*rvt*predict-no*H0
  14347. -->
  14348. Firing rl*prefer*rvt*predict-no*H0*2
  14349. -->
  14350. (S1 ^operator O2004 = 1.)
  14351. inner elaboration loop at bottom goal.
  14352. Retracting rl*prefer*rvt*predict-no*H0*2
  14353. -->
  14354. (S1 ^operator O2002 = 1.)
  14355. Retracting rl*prefer*rvt*predict-yes*H0*1
  14356. -->
  14357. (S1 ^operator O2001 = 0.)
  14358. --- END Proposal Phase ---
  14359. --- Decision Phase ---
  14360. RL update rl*prefer*rvt*predict-no*H0*2 1 0 1 -> 1 0 1(R,m,v=1,1,0)
  14361. =>WM: (14121: S1 ^operator O2004)
  14362. 1002: O: O2004 (predict-no)
  14363. --- END Decision Phase ---
  14364. --- Application Phase ---
  14365. --- Firing Productions (PE) For State At Depth 1 ---
  14366. --- Inner Elaboration Phase, active level 1 (S1) ---
  14367. Firing apply*operator
  14368. -->
  14369. (I3 ^predict-no N1002 + :O )
  14370. Firing apply*operator*complete
  14371. -->
  14372. (I3 ^predict-no N1001 - :O )
  14373. inner elaboration loop at bottom goal.
  14374. --- Change Working Memory (PE) ---
  14375. =>WM: (14122: I3 ^predict-no N1002)
  14376. <=WM: (14109: N1001 ^status complete)
  14377. <=WM: (14108: I3 ^predict-no N1001)
  14378. --- Firing Productions (IE) For State At Depth 1 ---
  14379. --- Inner Elaboration Phase, active level 1 (S1) ---
  14380. Firing monitor*world
  14381. -->
  14382. I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
  14383. --- Change Working Memory (IE) ---
  14384. --- END Application Phase ---
  14385. --- Output Phase ---
  14386. ENV: Agent did: predict-no for direction U in state State-B
  14387. In State-B moving U
  14388. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  14389. predict error 0
  14390. dir: dir isU
  14391. --- END Output Phase ---
  14392. ---- Input Phase ---
  14393. =>WM: (14126: I2 ^dir U)
  14394. =>WM: (14125: I2 ^reward 1)
  14395. =>WM: (14124: I2 ^see 0)
  14396. =>WM: (14123: N1002 ^status complete)
  14397. <=WM: (14112: I2 ^dir U)
  14398. <=WM: (14111: I2 ^reward 1)
  14399. <=WM: (14110: I2 ^see 0)
  14400. =>WM: (14127: I2 ^level-1 R1-root)
  14401. <=WM: (14113: I2 ^level-1 R1-root)
  14402. --- END Input Phase ---
  14403. --- Proposal Phase ---
  14404. --- Inner Elaboration Phase, active level 1 (S1) ---
  14405. Firing elaborate*copy-see-to-output-link
  14406. -->
  14407. (I3 ^see 0 +)
  14408. Firing elaborate*reward*based*on*reward
  14409. -->
  14410. (R1006 ^value 1 +)
  14411. (R1 ^reward R1006 +)
  14412. Firing propose*predict-yes
  14413. -->
  14414. (O2005 ^name predict-yes +)
  14415. (S1 ^operator O2005 +)
  14416. Firing propose*predict-no
  14417. -->
  14418. (O2006 ^name predict-no +)
  14419. (S1 ^operator O2006 +)
  14420. Firing rl*prefer*rvt*predict-no*H0*2
  14421. -->
  14422. (S1 ^operator O2004 = 1.)
  14423. Firing rl*prefer*rvt*predict-yes*H0*1
  14424. -->
  14425. (S1 ^operator O2003 = 0.)
  14426. Firing prefer*rvt*predict-yes*H0
  14427. -->
  14428. Firing prefer*rvt*predict-no*H0
  14429. -->
  14430. Firing elaborate*copy-dir-to-output-link
  14431. -->
  14432. (I3 ^dir U +)
  14433. inner elaboration loop at bottom goal.
  14434. Retracting elaborate*copy-see-to-output-link
  14435. -->
  14436. (I3 ^see 0 +)
  14437. Retracting propose*predict-no
  14438. -->
  14439. (O2004 ^name predict-no +)
  14440. (S1 ^operator O2004 +)
  14441. Retracting propose*predict-yes
  14442. -->
  14443. (O2003 ^name predict-yes +)
  14444. (S1 ^operator O2003 +)
  14445. Retracting elaborate*reward*based*on*reward
  14446. -->
  14447. (R1005 ^value 1 +)
  14448. (R1 ^reward R1005 +)
  14449. Retracting elaborate*copy-dir-to-output-link
  14450. -->
  14451. (I3 ^dir U +)
  14452. Retracting rl*prefer*rvt*predict-no*H0*2
  14453. -->
  14454. (S1 ^operator O2004 = 1.)
  14455. Retracting rl*prefer*rvt*predict-yes*H0*1
  14456. -->
  14457. (S1 ^operator O2003 = 0.)
  14458. =>WM: (14133: S1 ^operator O2006 +)
  14459. =>WM: (14132: S1 ^operator O2005 +)
  14460. =>WM: (14131: O2006 ^name predict-no)
  14461. =>WM: (14130: O2005 ^name predict-yes)
  14462. =>WM: (14129: R1006 ^value 1)
  14463. =>WM: (14128: R1 ^reward R1006)
  14464. <=WM: (14119: S1 ^operator O2003 +)
  14465. <=WM: (14120: S1 ^operator O2004 +)
  14466. <=WM: (14121: S1 ^operator O2004)
  14467. <=WM: (14115: R1 ^reward R1005)
  14468. <=WM: (14118: O2004 ^name predict-no)
  14469. <=WM: (14117: O2003 ^name predict-yes)
  14470. <=WM: (14116: R1005 ^value 1)
  14471. --- Inner Elaboration Phase, active level 1 (S1) ---
  14472. Firing prefer*rvt*predict-yes*H0
  14473. -->
  14474. Firing rl*prefer*rvt*predict-yes*H0*1
  14475. -->
  14476. (S1 ^operator O2005 = 0.)
  14477. Firing prefer*rvt*predict-no*H0
  14478. -->
  14479. Firing rl*prefer*rvt*predict-no*H0*2
  14480. -->
  14481. (S1 ^operator O2006 = 1.)
  14482. inner elaboration loop at bottom goal.
  14483. Retracting rl*prefer*rvt*predict-no*H0*2
  14484. -->
  14485. (S1 ^operator O2004 = 1.)
  14486. Retracting rl*prefer*rvt*predict-yes*H0*1
  14487. -->
  14488. (S1 ^operator O2003 = 0.)
  14489. --- END Proposal Phase ---
  14490. --- Decision Phase ---
  14491. RL update rl*prefer*rvt*predict-no*H0*2 1 0 1 -> 1 0 1(R,m,v=1,1,0)
  14492. =>WM: (14134: S1 ^operator O2006)
  14493. 1003: O: O2006 (predict-no)
  14494. --- END Decision Phase ---
  14495. --- Application Phase ---
  14496. --- Firing Productions (PE) For State At Depth 1 ---
  14497. --- Inner Elaboration Phase, active level 1 (S1) ---
  14498. Firing apply*operator
  14499. -->
  14500. (I3 ^predict-no N1003 + :O )
  14501. Firing apply*operator*complete
  14502. -->
  14503. (I3 ^predict-no N1002 - :O )
  14504. inner elaboration loop at bottom goal.
  14505. --- Change Working Memory (PE) ---
  14506. =>WM: (14135: I3 ^predict-no N1003)
  14507. <=WM: (14123: N1002 ^status complete)
  14508. <=WM: (14122: I3 ^predict-no N1002)
  14509. --- Firing Productions (IE) For State At Depth 1 ---
  14510. --- Inner Elaboration Phase, active level 1 (S1) ---
  14511. Firing monitor*world
  14512. -->
  14513. I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
  14514. --- Change Working Memory (IE) ---
  14515. --- END Application Phase ---
  14516. --- Output Phase ---
  14517. ENV: Agent did: predict-no for direction U in state State-B
  14518. In State-B moving U
  14519. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  14520. predict error 0
  14521. dir: dir isU
  14522. --- END Output Phase ---
  14523. /|--- Input Phase ---
  14524. =>WM: (14139: I2 ^dir U)
  14525. =>WM: (14138: I2 ^reward 1)
  14526. =>WM: (14137: I2 ^see 0)
  14527. =>WM: (14136: N1003 ^status complete)
  14528. <=WM: (14126: I2 ^dir U)
  14529. <=WM: (14125: I2 ^reward 1)
  14530. <=WM: (14124: I2 ^see 0)
  14531. =>WM: (14140: I2 ^level-1 R1-root)
  14532. <=WM: (14127: I2 ^level-1 R1-root)
  14533. --- END Input Phase ---
  14534. --- Proposal Phase ---
  14535. --- Inner Elaboration Phase, active level 1 (S1) ---
  14536. Firing elaborate*copy-see-to-output-link
  14537. -->
  14538. (I3 ^see 0 +)
  14539. Firing elaborate*reward*based*on*reward
  14540. -->
  14541. (R1007 ^value 1 +)
  14542. (R1 ^reward R1007 +)
  14543. Firing propose*predict-yes
  14544. -->
  14545. (O2007 ^name predict-yes +)
  14546. (S1 ^operator O2007 +)
  14547. Firing propose*predict-no
  14548. -->
  14549. (O2008 ^name predict-no +)
  14550. (S1 ^operator O2008 +)
  14551. Firing rl*prefer*rvt*predict-no*H0*2
  14552. -->
  14553. (S1 ^operator O2006 = 1.)
  14554. Firing rl*prefer*rvt*predict-yes*H0*1
  14555. -->
  14556. (S1 ^operator O2005 = 0.)
  14557. Firing prefer*rvt*predict-yes*H0
  14558. -->
  14559. Firing prefer*rvt*predict-no*H0
  14560. -->
  14561. Firing elaborate*copy-dir-to-output-link
  14562. -->
  14563. (I3 ^dir U +)
  14564. inner elaboration loop at bottom goal.
  14565. Retracting elaborate*copy-see-to-output-link
  14566. -->
  14567. (I3 ^see 0 +)
  14568. Retracting propose*predict-no
  14569. -->
  14570. (O2006 ^name predict-no +)
  14571. (S1 ^operator O2006 +)
  14572. Retracting propose*predict-yes
  14573. -->
  14574. (O2005 ^name predict-yes +)
  14575. (S1 ^operator O2005 +)
  14576. Retracting elaborate*reward*based*on*reward
  14577. -->
  14578. (R1006 ^value 1 +)
  14579. (R1 ^reward R1006 +)
  14580. Retracting elaborate*copy-dir-to-output-link
  14581. -->
  14582. (I3 ^dir U +)
  14583. Retracting rl*prefer*rvt*predict-no*H0*2
  14584. -->
  14585. (S1 ^operator O2006 = 1.)
  14586. Retracting rl*prefer*rvt*predict-yes*H0*1
  14587. -->
  14588. (S1 ^operator O2005 = 0.)
  14589. =>WM: (14146: S1 ^operator O2008 +)
  14590. =>WM: (14145: S1 ^operator O2007 +)
  14591. =>WM: (14144: O2008 ^name predict-no)
  14592. =>WM: (14143: O2007 ^name predict-yes)
  14593. =>WM: (14142: R1007 ^value 1)
  14594. =>WM: (14141: R1 ^reward R1007)
  14595. <=WM: (14132: S1 ^operator O2005 +)
  14596. <=WM: (14133: S1 ^operator O2006 +)
  14597. <=WM: (14134: S1 ^operator O2006)
  14598. <=WM: (14128: R1 ^reward R1006)
  14599. <=WM: (14131: O2006 ^name predict-no)
  14600. <=WM: (14130: O2005 ^name predict-yes)
  14601. <=WM: (14129: R1006 ^value 1)
  14602. --- Inner Elaboration Phase, active level 1 (S1) ---
  14603. Firing prefer*rvt*predict-yes*H0
  14604. -->
  14605. Firing rl*prefer*rvt*predict-yes*H0*1
  14606. -->
  14607. (S1 ^operator O2007 = 0.)
  14608. Firing prefer*rvt*predict-no*H0
  14609. -->
  14610. Firing rl*prefer*rvt*predict-no*H0*2
  14611. -->
  14612. (S1 ^operator O2008 = 1.)
  14613. inner elaboration loop at bottom goal.
  14614. Retracting rl*prefer*rvt*predict-no*H0*2
  14615. -->
  14616. (S1 ^operator O2006 = 1.)
  14617. Retracting rl*prefer*rvt*predict-yes*H0*1
  14618. -->
  14619. (S1 ^operator O2005 = 0.)
  14620. --- END Proposal Phase ---
  14621. --- Decision Phase ---
  14622. RL update rl*prefer*rvt*predict-no*H0*2 1 0 1 -> 1 0 1(R,m,v=1,1,0)
  14623. =>WM: (14147: S1 ^operator O2008)
  14624. 1004: O: O2008 (predict-no)
  14625. --- END Decision Phase ---
  14626. --- Application Phase ---
  14627. --- Firing Productions (PE) For State At Depth 1 ---
  14628. --- Inner Elaboration Phase, active level 1 (S1) ---
  14629. Firing apply*operator
  14630. -->
  14631. (I3 ^predict-no N1004 + :O )
  14632. Firing apply*operator*complete
  14633. -->
  14634. (I3 ^predict-no N1003 - :O )
  14635. inner elaboration loop at bottom goal.
  14636. --- Change Working Memory (PE) ---
  14637. =>WM: (14148: I3 ^predict-no N1004)
  14638. <=WM: (14136: N1003 ^status complete)
  14639. <=WM: (14135: I3 ^predict-no N1003)
  14640. --- Firing Productions (IE) For State At Depth 1 ---
  14641. --- Inner Elaboration Phase, active level 1 (S1) ---
  14642. Firing monitor*world
  14643. -->
  14644. I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
  14645. --- Change Working Memory (IE) ---
  14646. --- END Application Phase ---
  14647. --- Output Phase ---
  14648. ENV: Agent did: predict-no for direction U in state State-B
  14649. In State-B moving U
  14650. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  14651. predict error 0
  14652. dir: dir isL
  14653. --- END Output Phase ---
  14654. \-/--- Input Phase ---
  14655. =>WM: (14152: I2 ^dir L)
  14656. =>WM: (14151: I2 ^reward 1)
  14657. =>WM: (14150: I2 ^see 0)
  14658. =>WM: (14149: N1004 ^status complete)
  14659. <=WM: (14139: I2 ^dir U)
  14660. <=WM: (14138: I2 ^reward 1)
  14661. <=WM: (14137: I2 ^see 0)
  14662. =>WM: (14153: I2 ^level-1 R1-root)
  14663. <=WM: (14140: I2 ^level-1 R1-root)
  14664. --- END Input Phase ---
  14665. --- Proposal Phase ---
  14666. --- Inner Elaboration Phase, active level 1 (S1) ---
  14667. Firing rl*prefer*rvt*predict-yes*H0*5*v1*H1*41
  14668. -->
  14669. (S1 ^operator O2007 = 0.7362263199804909)
  14670. Firing prefer*rvt*predict-yes*H0*5*v1*H1
  14671. -->
  14672. Firing elaborate*copy-see-to-output-link
  14673. -->
  14674. (I3 ^see 0 +)
  14675. Firing elaborate*reward*based*on*reward
  14676. -->
  14677. (R1008 ^value 1 +)
  14678. (R1 ^reward R1008 +)
  14679. Firing propose*predict-yes
  14680. -->
  14681. (O2009 ^name predict-yes +)
  14682. (S1 ^operator O2009 +)
  14683. Firing propose*predict-no
  14684. -->
  14685. (O2010 ^name predict-no +)
  14686. (S1 ^operator O2010 +)
  14687. Firing rl*prefer*rvt*predict-no*H0*6
  14688. -->
  14689. (S1 ^operator O2008 = 0.9998785089568328)
  14690. Firing rl*prefer*rvt*predict-yes*H0*5
  14691. -->
  14692. (S1 ^operator O2007 = 0.2640246623191502)
  14693. Firing prefer*rvt*predict-yes*H0
  14694. -->
  14695. Firing prefer*rvt*predict-no*H0
  14696. -->
  14697. Firing elaborate*copy-dir-to-output-link
  14698. -->
  14699. (I3 ^dir L +)
  14700. inner elaboration loop at bottom goal.
  14701. Retracting elaborate*copy-see-to-output-link
  14702. -->
  14703. (I3 ^see 0 +)
  14704. Retracting propose*predict-no
  14705. -->
  14706. (O2008 ^name predict-no +)
  14707. (S1 ^operator O2008 +)
  14708. Retracting propose*predict-yes
  14709. -->
  14710. (O2007 ^name predict-yes +)
  14711. (S1 ^operator O2007 +)
  14712. Retracting elaborate*reward*based*on*reward
  14713. -->
  14714. (R1007 ^value 1 +)
  14715. (R1 ^reward R1007 +)
  14716. Retracting elaborate*copy-dir-to-output-link
  14717. -->
  14718. (I3 ^dir U +)
  14719. Retracting rl*prefer*rvt*predict-no*H0*2
  14720. -->
  14721. (S1 ^operator O2008 = 1.)
  14722. Retracting rl*prefer*rvt*predict-yes*H0*1
  14723. -->
  14724. (S1 ^operator O2007 = 0.)
  14725. =>WM: (14160: S1 ^operator O2010 +)
  14726. =>WM: (14159: S1 ^operator O2009 +)
  14727. =>WM: (14158: I3 ^dir L)
  14728. =>WM: (14157: O2010 ^name predict-no)
  14729. =>WM: (14156: O2009 ^name predict-yes)
  14730. =>WM: (14155: R1008 ^value 1)
  14731. =>WM: (14154: R1 ^reward R1008)
  14732. <=WM: (14145: S1 ^operator O2007 +)
  14733. <=WM: (14146: S1 ^operator O2008 +)
  14734. <=WM: (14147: S1 ^operator O2008)
  14735. <=WM: (14104: I3 ^dir U)
  14736. <=WM: (14141: R1 ^reward R1007)
  14737. <=WM: (14144: O2008 ^name predict-no)
  14738. <=WM: (14143: O2007 ^name predict-yes)
  14739. <=WM: (14142: R1007 ^value 1)
  14740. --- Inner Elaboration Phase, active level 1 (S1) ---
  14741. Firing prefer*rvt*predict-yes*H0
  14742. -->
  14743. Firing rl*prefer*rvt*predict-yes*H0*5*v1*H1*41
  14744. -->
  14745. (S1 ^operator O2009 = 0.7362263199804909)
  14746. Firing rl*prefer*rvt*predict-yes*H0*5
  14747. -->
  14748. (S1 ^operator O2009 = 0.2640246623191502)
  14749. Firing prefer*rvt*predict-yes*H0*5*v1*H1
  14750. -->
  14751. Firing prefer*rvt*predict-no*H0
  14752. -->
  14753. Firing rl*prefer*rvt*predict-no*H0*6
  14754. -->
  14755. (S1 ^operator O2010 = 0.9998785089568328)
  14756. inner elaboration loop at bottom goal.
  14757. Retracting rl*prefer*rvt*predict-no*H0*6
  14758. -->
  14759. (S1 ^operator O2008 = 0.9998785089568328)
  14760. Retracting rl*prefer*rvt*predict-yes*H0*5
  14761. -->
  14762. (S1 ^operator O2007 = 0.2640246623191502)
  14763. Retracting rl*prefer*rvt*predict-yes*H0*5*v1*H1*41
  14764. -->
  14765. (S1 ^operator O2007 = 0.7362263199804909)
  14766. --- END Proposal Phase ---
  14767. --- Decision Phase ---
  14768. RL update rl*prefer*rvt*predict-no*H0*2 1 0 1 -> 1 0 1(R,m,v=1,1,0)
  14769. =>WM: (14161: S1 ^operator O2009)
  14770. 1005: O: O2009 (predict-yes)
  14771. --- END Decision Phase ---
  14772. --- Application Phase ---
  14773. --- Firing Productions (PE) For State At Depth 1 ---
  14774. --- Inner Elaboration Phase, active level 1 (S1) ---
  14775. Firing apply*operator
  14776. -->
  14777. (I3 ^predict-yes N1005 + :O )
  14778. Firing apply*operator*complete
  14779. -->
  14780. (I3 ^predict-no N1004 - :O )
  14781. inner elaboration loop at bottom goal.
  14782. --- Change Working Memory (PE) ---
  14783. =>WM: (14162: I3 ^predict-yes N1005)
  14784. <=WM: (14149: N1004 ^status complete)
  14785. <=WM: (14148: I3 ^predict-no N1004)
  14786. --- Firing Productions (IE) For State At Depth 1 ---
  14787. --- Inner Elaboration Phase, active level 1 (S1) ---
  14788. Firing monitor*world
  14789. -->
  14790. I see 1 and I'm going to do: predict-yes inner elaboration loop at bottom goal.
  14791. --- Change Working Memory (IE) ---
  14792. --- END Application Phase ---
  14793. --- Output Phase ---
  14794. ENV: Agent did: predict-yes for direction L in state State-B
  14795. In State-B moving L
  14796. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  14797. predict error 0
  14798. dir: dir isR
  14799. --- END Output Phase ---
  14800. |\---- Input Phase ---
  14801. =>WM: (14166: I2 ^dir R)
  14802. =>WM: (14165: I2 ^reward 1)
  14803. =>WM: (14164: I2 ^see 1)
  14804. =>WM: (14163: N1005 ^status complete)
  14805. <=WM: (14152: I2 ^dir L)
  14806. <=WM: (14151: I2 ^reward 1)
  14807. <=WM: (14150: I2 ^see 0)
  14808. =>WM: (14167: I2 ^level-1 L1-root)
  14809. <=WM: (14153: I2 ^level-1 R1-root)
  14810. --- END Input Phase ---
  14811. --- Proposal Phase ---
  14812. --- Inner Elaboration Phase, active level 1 (S1) ---
  14813. Firing rl*prefer*rvt*predict-no*H0*4*v1*H1*37
  14814. -->
  14815. (S1 ^operator O2010 = -0.2714224023553999)
  14816. Firing rl*prefer*rvt*predict-yes*H0*3*v1*H1*38
  14817. -->
  14818. (S1 ^operator O2009 = 0.6622259046932006)
  14819. Firing prefer*rvt*predict-no*H0*4*v1*H1
  14820. -->
  14821. Firing prefer*rvt*predict-yes*H0*3*v1*H1
  14822. -->
  14823. Firing elaborate*copy-see-to-output-link
  14824. -->
  14825. (I3 ^see 1 +)
  14826. Firing elaborate*reward*based*on*reward
  14827. -->
  14828. (R1009 ^value 1 +)
  14829. (R1 ^reward R1009 +)
  14830. Firing propose*predict-yes
  14831. -->
  14832. (O2011 ^name predict-yes +)
  14833. (S1 ^operator O2011 +)
  14834. Firing propose*predict-no
  14835. -->
  14836. (O2012 ^name predict-no +)
  14837. (S1 ^operator O2012 +)
  14838. Firing rl*prefer*rvt*predict-no*H0*4
  14839. -->
  14840. (S1 ^operator O2010 = 0.339773810196969)
  14841. Firing rl*prefer*rvt*predict-yes*H0*3
  14842. -->
  14843. (S1 ^operator O2009 = 0.3377117977102235)
  14844. Firing prefer*rvt*predict-yes*H0
  14845. -->
  14846. Firing prefer*rvt*predict-no*H0
  14847. -->
  14848. Firing elaborate*copy-dir-to-output-link
  14849. -->
  14850. (I3 ^dir R +)
  14851. inner elaboration loop at bottom goal.
  14852. Retracting elaborate*copy-see-to-output-link
  14853. -->
  14854. (I3 ^see 0 +)
  14855. Retracting propose*predict-no
  14856. -->
  14857. (O2010 ^name predict-no +)
  14858. (S1 ^operator O2010 +)
  14859. Retracting propose*predict-yes
  14860. -->
  14861. (O2009 ^name predict-yes +)
  14862. (S1 ^operator O2009 +)
  14863. Retracting elaborate*reward*based*on*reward
  14864. -->
  14865. (R1008 ^value 1 +)
  14866. (R1 ^reward R1008 +)
  14867. Retracting elaborate*copy-dir-to-output-link
  14868. -->
  14869. (I3 ^dir L +)
  14870. Retracting rl*prefer*rvt*predict-no*H0*6
  14871. -->
  14872. (S1 ^operator O2010 = 0.9998785089568328)
  14873. Retracting rl*prefer*rvt*predict-yes*H0*5
  14874. -->
  14875. (S1 ^operator O2009 = 0.2640246623191502)
  14876. Retracting rl*prefer*rvt*predict-yes*H0*5*v1*H1*41
  14877. -->
  14878. (S1 ^operator O2009 = 0.7362263199804909)
  14879. =>WM: (14175: S1 ^operator O2012 +)
  14880. =>WM: (14174: S1 ^operator O2011 +)
  14881. =>WM: (14173: I3 ^dir R)
  14882. =>WM: (14172: O2012 ^name predict-no)
  14883. =>WM: (14171: O2011 ^name predict-yes)
  14884. =>WM: (14170: R1009 ^value 1)
  14885. =>WM: (14169: R1 ^reward R1009)
  14886. =>WM: (14168: I3 ^see 1)
  14887. <=WM: (14159: S1 ^operator O2009 +)
  14888. <=WM: (14161: S1 ^operator O2009)
  14889. <=WM: (14160: S1 ^operator O2010 +)
  14890. <=WM: (14158: I3 ^dir L)
  14891. <=WM: (14154: R1 ^reward R1008)
  14892. <=WM: (14114: I3 ^see 0)
  14893. <=WM: (14157: O2010 ^name predict-no)
  14894. <=WM: (14156: O2009 ^name predict-yes)
  14895. <=WM: (14155: R1008 ^value 1)
  14896. --- Inner Elaboration Phase, active level 1 (S1) ---
  14897. Firing prefer*rvt*predict-yes*H0
  14898. -->
  14899. Firing rl*prefer*rvt*predict-yes*H0*3
  14900. -->
  14901. (S1 ^operator O2011 = 0.3377117977102235)
  14902. Firing prefer*rvt*predict-yes*H0*3*v1*H1
  14903. -->
  14904. Firing rl*prefer*rvt*predict-yes*H0*3*v1*H1*38
  14905. -->
  14906. (S1 ^operator O2011 = 0.6622259046932006)
  14907. Firing prefer*rvt*predict-no*H0
  14908. -->
  14909. Firing rl*prefer*rvt*predict-no*H0*4
  14910. -->
  14911. (S1 ^operator O2012 = 0.339773810196969)
  14912. Firing prefer*rvt*predict-no*H0*4*v1*H1
  14913. -->
  14914. Firing rl*prefer*rvt*predict-no*H0*4*v1*H1*37
  14915. -->
  14916. (S1 ^operator O2012 = -0.2714224023553999)
  14917. inner elaboration loop at bottom goal.
  14918. Retracting rl*prefer*rvt*predict-no*H0*4
  14919. -->
  14920. (S1 ^operator O2010 = 0.339773810196969)
  14921. Retracting rl*prefer*rvt*predict-no*H0*4*v1*H1*37
  14922. -->
  14923. (S1 ^operator O2010 = -0.2714224023553999)
  14924. Retracting rl*prefer*rvt*predict-yes*H0*3
  14925. -->
  14926. (S1 ^operator O2009 = 0.3377117977102235)
  14927. Retracting rl*prefer*rvt*predict-yes*H0*3*v1*H1*38
  14928. -->
  14929. (S1 ^operator O2009 = 0.6622259046932006)
  14930. --- END Proposal Phase ---
  14931. --- Decision Phase ---
  14932. RL update rl*prefer*rvt*predict-yes*H0*5 0.55441 -0.290386 0.264025 -> 0.55439 -0.290386 0.264004(R,m,v=1,0.877778,0.107883)
  14933. RL update rl*prefer*rvt*predict-yes*H0*5*v1*H1*41 0.445836 0.29039 0.736226 -> 0.445814 0.290389 0.736203(R,m,v=1,1,0)
  14934. =>WM: (14176: S1 ^operator O2011)
  14935. 1006: O: O2011 (predict-yes)
  14936. --- END Decision Phase ---
  14937. --- Application Phase ---
  14938. --- Firing Productions (PE) For State At Depth 1 ---
  14939. --- Inner Elaboration Phase, active level 1 (S1) ---
  14940. Firing apply*operator
  14941. -->
  14942. (I3 ^predict-yes N1006 + :O )
  14943. Firing apply*operator*complete
  14944. -->
  14945. (I3 ^predict-yes N1005 - :O )
  14946. inner elaboration loop at bottom goal.
  14947. --- Change Working Memory (PE) ---
  14948. =>WM: (14177: I3 ^predict-yes N1006)
  14949. <=WM: (14163: N1005 ^status complete)
  14950. <=WM: (14162: I3 ^predict-yes N1005)
  14951. --- Firing Productions (IE) For State At Depth 1 ---
  14952. --- Inner Elaboration Phase, active level 1 (S1) ---
  14953. Firing monitor*world
  14954. -->
  14955. I see 1 and I'm going to do: predict-yes inner elaboration loop at bottom goal.
  14956. --- Change Working Memory (IE) ---
  14957. --- END Application Phase ---
  14958. --- Output Phase ---
  14959. ENV: Agent did: predict-yes for direction R in state State-A
  14960. In State-A moving R
  14961. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  14962. predict error 0
  14963. dir: dir isR
  14964. --- END Output Phase ---
  14965. /|\--- Input Phase ---
  14966. =>WM: (14181: I2 ^dir R)
  14967. =>WM: (14180: I2 ^reward 1)
  14968. =>WM: (14179: I2 ^see 1)
  14969. =>WM: (14178: N1006 ^status complete)
  14970. <=WM: (14166: I2 ^dir R)
  14971. <=WM: (14165: I2 ^reward 1)
  14972. <=WM: (14164: I2 ^see 1)
  14973. =>WM: (14182: I2 ^level-1 R1-root)
  14974. <=WM: (14167: I2 ^level-1 L1-root)
  14975. --- END Input Phase ---
  14976. --- Proposal Phase ---
  14977. --- Inner Elaboration Phase, active level 1 (S1) ---
  14978. Firing rl*prefer*rvt*predict-yes*H0*3*v1*H1*36
  14979. -->
  14980. (S1 ^operator O2011 = -0.1070236389116304)
  14981. Firing rl*prefer*rvt*predict-no*H0*4*v1*H1*35
  14982. -->
  14983. (S1 ^operator O2012 = 0.6602439963649246)
  14984. Firing prefer*rvt*predict-no*H0*4*v1*H1
  14985. -->
  14986. Firing prefer*rvt*predict-yes*H0*3*v1*H1
  14987. -->
  14988. Firing elaborate*copy-see-to-output-link
  14989. -->
  14990. (I3 ^see 1 +)
  14991. Firing elaborate*reward*based*on*reward
  14992. -->
  14993. (R1010 ^value 1 +)
  14994. (R1 ^reward R1010 +)
  14995. Firing propose*predict-yes
  14996. -->
  14997. (O2013 ^name predict-yes +)
  14998. (S1 ^operator O2013 +)
  14999. Firing propose*predict-no
  15000. -->
  15001. (O2014 ^name predict-no +)
  15002. (S1 ^operator O2014 +)
  15003. Firing rl*prefer*rvt*predict-no*H0*4
  15004. -->
  15005. (S1 ^operator O2012 = 0.339773810196969)
  15006. Firing rl*prefer*rvt*predict-yes*H0*3
  15007. -->
  15008. (S1 ^operator O2011 = 0.3377117977102235)
  15009. Firing prefer*rvt*predict-yes*H0
  15010. -->
  15011. Firing prefer*rvt*predict-no*H0
  15012. -->
  15013. Firing elaborate*copy-dir-to-output-link
  15014. -->
  15015. (I3 ^dir R +)
  15016. inner elaboration loop at bottom goal.
  15017. Retracting elaborate*copy-see-to-output-link
  15018. -->
  15019. (I3 ^see 1 +)
  15020. Retracting propose*predict-no
  15021. -->
  15022. (O2012 ^name predict-no +)
  15023. (S1 ^operator O2012 +)
  15024. Retracting propose*predict-yes
  15025. -->
  15026. (O2011 ^name predict-yes +)
  15027. (S1 ^operator O2011 +)
  15028. Retracting elaborate*reward*based*on*reward
  15029. -->
  15030. (R1009 ^value 1 +)
  15031. (R1 ^reward R1009 +)
  15032. Retracting elaborate*copy-dir-to-output-link
  15033. -->
  15034. (I3 ^dir R +)
  15035. Retracting rl*prefer*rvt*predict-no*H0*4*v1*H1*37
  15036. -->
  15037. (S1 ^operator O2012 = -0.2714224023553999)
  15038. Retracting rl*prefer*rvt*predict-no*H0*4
  15039. -->
  15040. (S1 ^operator O2012 = 0.339773810196969)
  15041. Retracting rl*prefer*rvt*predict-yes*H0*3*v1*H1*38
  15042. -->
  15043. (S1 ^operator O2011 = 0.6622259046932006)
  15044. Retracting rl*prefer*rvt*predict-yes*H0*3
  15045. -->
  15046. (S1 ^operator O2011 = 0.3377117977102235)
  15047. =>WM: (14188: S1 ^operator O2014 +)
  15048. =>WM: (14187: S1 ^operator O2013 +)
  15049. =>WM: (14186: O2014 ^name predict-no)
  15050. =>WM: (14185: O2013 ^name predict-yes)
  15051. =>WM: (14184: R1010 ^value 1)
  15052. =>WM: (14183: R1 ^reward R1010)
  15053. <=WM: (14174: S1 ^operator O2011 +)
  15054. <=WM: (14176: S1 ^operator O2011)
  15055. <=WM: (14175: S1 ^operator O2012 +)
  15056. <=WM: (14169: R1 ^reward R1009)
  15057. <=WM: (14172: O2012 ^name predict-no)
  15058. <=WM: (14171: O2011 ^name predict-yes)
  15059. <=WM: (14170: R1009 ^value 1)
  15060. --- Inner Elaboration Phase, active level 1 (S1) ---
  15061. Firing prefer*rvt*predict-yes*H0
  15062. -->
  15063. Firing rl*prefer*rvt*predict-yes*H0*3
  15064. -->
  15065. (S1 ^operator O2013 = 0.3377117977102235)
  15066. Firing prefer*rvt*predict-yes*H0*3*v1*H1
  15067. -->
  15068. Firing rl*prefer*rvt*predict-yes*H0*3*v1*H1*36
  15069. -->
  15070. (S1 ^operator O2013 = -0.1070236389116304)
  15071. Firing prefer*rvt*predict-no*H0
  15072. -->
  15073. Firing rl*prefer*rvt*predict-no*H0*4
  15074. -->
  15075. (S1 ^operator O2014 = 0.339773810196969)
  15076. Firing prefer*rvt*predict-no*H0*4*v1*H1
  15077. -->
  15078. Firing rl*prefer*rvt*predict-no*H0*4*v1*H1*35
  15079. -->
  15080. (S1 ^operator O2014 = 0.6602439963649246)
  15081. inner elaboration loop at bottom goal.
  15082. Retracting rl*prefer*rvt*predict-no*H0*4
  15083. -->
  15084. (S1 ^operator O2012 = 0.339773810196969)
  15085. Retracting rl*prefer*rvt*predict-no*H0*4*v1*H1*35
  15086. -->
  15087. (S1 ^operator O2012 = 0.6602439963649246)
  15088. Retracting rl*prefer*rvt*predict-yes*H0*3
  15089. -->
  15090. (S1 ^operator O2011 = 0.3377117977102235)
  15091. Retracting rl*prefer*rvt*predict-yes*H0*3*v1*H1*36
  15092. -->
  15093. (S1 ^operator O2011 = -0.1070236389116304)
  15094. --- END Proposal Phase ---
  15095. --- Decision Phase ---
  15096. RL update rl*prefer*rvt*predict-yes*H0*3 0.590112 -0.2524 0.337712 -> 0.590118 -0.252401 0.337717(R,m,v=1,0.899408,0.0910116)
  15097. RL update rl*prefer*rvt*predict-yes*H0*3*v1*H1*38 0.409816 0.25241 0.662226 -> 0.409823 0.252409 0.662232(R,m,v=1,1,0)
  15098. =>WM: (14189: S1 ^operator O2014)
  15099. 1007: O: O2014 (predict-no)
  15100. --- END Decision Phase ---
  15101. --- Application Phase ---
  15102. --- Firing Productions (PE) For State At Depth 1 ---
  15103. --- Inner Elaboration Phase, active level 1 (S1) ---
  15104. Firing apply*operator
  15105. -->
  15106. (I3 ^predict-no N1007 + :O )
  15107. Firing apply*operator*complete
  15108. -->
  15109. (I3 ^predict-yes N1006 - :O )
  15110. inner elaboration loop at bottom goal.
  15111. --- Change Working Memory (PE) ---
  15112. =>WM: (14190: I3 ^predict-no N1007)
  15113. <=WM: (14178: N1006 ^status complete)
  15114. <=WM: (14177: I3 ^predict-yes N1006)
  15115. --- Firing Productions (IE) For State At Depth 1 ---
  15116. --- Inner Elaboration Phase, active level 1 (S1) ---
  15117. Firing monitor*world
  15118. -->
  15119. I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
  15120. --- Change Working Memory (IE) ---
  15121. --- END Application Phase ---
  15122. --- Output Phase ---
  15123. ENV: Agent did: predict-no for direction R in state State-B
  15124. In State-B moving R
  15125. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  15126. predict error 0
  15127. dir: dir isU
  15128. --- END Output Phase ---
  15129. -/|--- Input Phase ---
  15130. =>WM: (14194: I2 ^dir U)
  15131. =>WM: (14193: I2 ^reward 1)
  15132. =>WM: (14192: I2 ^see 0)
  15133. =>WM: (14191: N1007 ^status complete)
  15134. <=WM: (14181: I2 ^dir R)
  15135. <=WM: (14180: I2 ^reward 1)
  15136. <=WM: (14179: I2 ^see 1)
  15137. =>WM: (14195: I2 ^level-1 R0-root)
  15138. <=WM: (14182: I2 ^level-1 R1-root)
  15139. --- END Input Phase ---
  15140. --- Proposal Phase ---
  15141. --- Inner Elaboration Phase, active level 1 (S1) ---
  15142. Firing elaborate*copy-see-to-output-link
  15143. -->
  15144. (I3 ^see 0 +)
  15145. Firing elaborate*reward*based*on*reward
  15146. -->
  15147. (R1011 ^value 1 +)
  15148. (R1 ^reward R1011 +)
  15149. Firing propose*predict-yes
  15150. -->
  15151. (O2015 ^name predict-yes +)
  15152. (S1 ^operator O2015 +)
  15153. Firing propose*predict-no
  15154. -->
  15155. (O2016 ^name predict-no +)
  15156. (S1 ^operator O2016 +)
  15157. Firing rl*prefer*rvt*predict-no*H0*2
  15158. -->
  15159. (S1 ^operator O2014 = 1.)
  15160. Firing rl*prefer*rvt*predict-yes*H0*1
  15161. -->
  15162. (S1 ^operator O2013 = 0.)
  15163. Firing prefer*rvt*predict-yes*H0
  15164. -->
  15165. Firing prefer*rvt*predict-no*H0
  15166. -->
  15167. Firing elaborate*copy-dir-to-output-link
  15168. -->
  15169. (I3 ^dir U +)
  15170. inner elaboration loop at bottom goal.
  15171. Retracting elaborate*copy-see-to-output-link
  15172. -->
  15173. (I3 ^see 1 +)
  15174. Retracting propose*predict-no
  15175. -->
  15176. (O2014 ^name predict-no +)
  15177. (S1 ^operator O2014 +)
  15178. Retracting propose*predict-yes
  15179. -->
  15180. (O2013 ^name predict-yes +)
  15181. (S1 ^operator O2013 +)
  15182. Retracting elaborate*reward*based*on*reward
  15183. -->
  15184. (R1010 ^value 1 +)
  15185. (R1 ^reward R1010 +)
  15186. Retracting elaborate*copy-dir-to-output-link
  15187. -->
  15188. (I3 ^dir R +)
  15189. Retracting rl*prefer*rvt*predict-no*H0*4*v1*H1*35
  15190. -->
  15191. (S1 ^operator O2014 = 0.6602439963649246)
  15192. Retracting rl*prefer*rvt*predict-no*H0*4
  15193. -->
  15194. (S1 ^operator O2014 = 0.339773810196969)
  15195. Retracting rl*prefer*rvt*predict-yes*H0*3*v1*H1*36
  15196. -->
  15197. (S1 ^operator O2013 = -0.1070236389116304)
  15198. Retracting rl*prefer*rvt*predict-yes*H0*3
  15199. -->
  15200. (S1 ^operator O2013 = 0.3377168791642142)
  15201. =>WM: (14203: S1 ^operator O2016 +)
  15202. =>WM: (14202: S1 ^operator O2015 +)
  15203. =>WM: (14201: I3 ^dir U)
  15204. =>WM: (14200: O2016 ^name predict-no)
  15205. =>WM: (14199: O2015 ^name predict-yes)
  15206. =>WM: (14198: R1011 ^value 1)
  15207. =>WM: (14197: R1 ^reward R1011)
  15208. =>WM: (14196: I3 ^see 0)
  15209. <=WM: (14187: S1 ^operator O2013 +)
  15210. <=WM: (14188: S1 ^operator O2014 +)
  15211. <=WM: (14189: S1 ^operator O2014)
  15212. <=WM: (14173: I3 ^dir R)
  15213. <=WM: (14183: R1 ^reward R1010)
  15214. <=WM: (14168: I3 ^see 1)
  15215. <=WM: (14186: O2014 ^name predict-no)
  15216. <=WM: (14185: O2013 ^name predict-yes)
  15217. <=WM: (14184: R1010 ^value 1)
  15218. --- Inner Elaboration Phase, active level 1 (S1) ---
  15219. Firing prefer*rvt*predict-yes*H0
  15220. -->
  15221. Firing rl*prefer*rvt*predict-yes*H0*1
  15222. -->
  15223. (S1 ^operator O2015 = 0.)
  15224. Firing prefer*rvt*predict-no*H0
  15225. -->
  15226. Firing rl*prefer*rvt*predict-no*H0*2
  15227. -->
  15228. (S1 ^operator O2016 = 1.)
  15229. inner elaboration loop at bottom goal.
  15230. Retracting rl*prefer*rvt*predict-no*H0*2
  15231. -->
  15232. (S1 ^operator O2014 = 1.)
  15233. Retracting rl*prefer*rvt*predict-yes*H0*1
  15234. -->
  15235. (S1 ^operator O2013 = 0.)
  15236. --- END Proposal Phase ---
  15237. --- Decision Phase ---
  15238. RL update rl*prefer*rvt*predict-no*H0*4 0.570257 -0.230484 0.339774 -> 0.570256 -0.230484 0.339772(R,m,v=1,0.87574,0.109467)
  15239. RL update rl*prefer*rvt*predict-no*H0*4*v1*H1*35 0.429761 0.230483 0.660244 -> 0.429759 0.230483 0.660242(R,m,v=1,1,0)
  15240. =>WM: (14204: S1 ^operator O2016)
  15241. 1008: O: O2016 (predict-no)
  15242. --- END Decision Phase ---
  15243. --- Application Phase ---
  15244. --- Firing Productions (PE) For State At Depth 1 ---
  15245. --- Inner Elaboration Phase, active level 1 (S1) ---
  15246. Firing apply*operator
  15247. -->
  15248. (I3 ^predict-no N1008 + :O )
  15249. Firing apply*operator*complete
  15250. -->
  15251. (I3 ^predict-no N1007 - :O )
  15252. inner elaboration loop at bottom goal.
  15253. --- Change Working Memory (PE) ---
  15254. =>WM: (14205: I3 ^predict-no N1008)
  15255. <=WM: (14191: N1007 ^status complete)
  15256. <=WM: (14190: I3 ^predict-no N1007)
  15257. --- Firing Productions (IE) For State At Depth 1 ---
  15258. --- Inner Elaboration Phase, active level 1 (S1) ---
  15259. Firing monitor*world
  15260. -->
  15261. I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
  15262. --- Change Working Memory (IE) ---
  15263. --- END Application Phase ---
  15264. --- Output Phase ---
  15265. ENV: Agent did: predict-no for direction U in state State-B
  15266. In State-B moving U
  15267. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  15268. predict error 0
  15269. dir: dir isL
  15270. --- END Output Phase ---
  15271. \-/|--- Input Phase ---
  15272. =>WM: (14209: I2 ^dir L)
  15273. =>WM: (14208: I2 ^reward 1)
  15274. =>WM: (14207: I2 ^see 0)
  15275. =>WM: (14206: N1008 ^status complete)
  15276. <=WM: (14194: I2 ^dir U)
  15277. <=WM: (14193: I2 ^reward 1)
  15278. <=WM: (14192: I2 ^see 0)
  15279. =>WM: (14210: I2 ^level-1 R0-root)
  15280. <=WM: (14195: I2 ^level-1 R0-root)
  15281. --- END Input Phase ---
  15282. --- Proposal Phase ---
  15283. --- Inner Elaboration Phase, active level 1 (S1) ---
  15284. Firing rl*prefer*rvt*predict-yes*H0*5*v1*H1*30
  15285. -->
  15286. (S1 ^operator O2015 = 0.7358542477906264)
  15287. Firing prefer*rvt*predict-yes*H0*5*v1*H1
  15288. -->
  15289. Firing elaborate*copy-see-to-output-link
  15290. -->
  15291. (I3 ^see 0 +)
  15292. Firing elaborate*reward*based*on*reward
  15293. -->
  15294. (R1012 ^value 1 +)
  15295. (R1 ^reward R1012 +)
  15296. Firing propose*predict-yes
  15297. -->
  15298. (O2017 ^name predict-yes +)
  15299. (S1 ^operator O2017 +)
  15300. Firing propose*predict-no
  15301. -->
  15302. (O2018 ^name predict-no +)
  15303. (S1 ^operator O2018 +)
  15304. Firing rl*prefer*rvt*predict-no*H0*6
  15305. -->
  15306. (S1 ^operator O2016 = 0.9998785089568328)
  15307. Firing rl*prefer*rvt*predict-yes*H0*5
  15308. -->
  15309. (S1 ^operator O2015 = 0.2640043987919141)
  15310. Firing prefer*rvt*predict-yes*H0
  15311. -->
  15312. Firing prefer*rvt*predict-no*H0
  15313. -->
  15314. Firing elaborate*copy-dir-to-output-link
  15315. -->
  15316. (I3 ^dir L +)
  15317. inner elaboration loop at bottom goal.
  15318. Retracting elaborate*copy-see-to-output-link
  15319. -->
  15320. (I3 ^see 0 +)
  15321. Retracting propose*predict-no
  15322. -->
  15323. (O2016 ^name predict-no +)
  15324. (S1 ^operator O2016 +)
  15325. Retracting propose*predict-yes
  15326. -->
  15327. (O2015 ^name predict-yes +)
  15328. (S1 ^operator O2015 +)
  15329. Retracting elaborate*reward*based*on*reward
  15330. -->
  15331. (R1011 ^value 1 +)
  15332. (R1 ^reward R1011 +)
  15333. Retracting elaborate*copy-dir-to-output-link
  15334. -->
  15335. (I3 ^dir U +)
  15336. Retracting rl*prefer*rvt*predict-no*H0*2
  15337. -->
  15338. (S1 ^operator O2016 = 1.)
  15339. Retracting rl*prefer*rvt*predict-yes*H0*1
  15340. -->
  15341. (S1 ^operator O2015 = 0.)
  15342. =>WM: (14217: S1 ^operator O2018 +)
  15343. =>WM: (14216: S1 ^operator O2017 +)
  15344. =>WM: (14215: I3 ^dir L)
  15345. =>WM: (14214: O2018 ^name predict-no)
  15346. =>WM: (14213: O2017 ^name predict-yes)
  15347. =>WM: (14212: R1012 ^value 1)
  15348. =>WM: (14211: R1 ^reward R1012)
  15349. <=WM: (14202: S1 ^operator O2015 +)
  15350. <=WM: (14203: S1 ^operator O2016 +)
  15351. <=WM: (14204: S1 ^operator O2016)
  15352. <=WM: (14201: I3 ^dir U)
  15353. <=WM: (14197: R1 ^reward R1011)
  15354. <=WM: (14200: O2016 ^name predict-no)
  15355. <=WM: (14199: O2015 ^name predict-yes)
  15356. <=WM: (14198: R1011 ^value 1)
  15357. --- Inner Elaboration Phase, active level 1 (S1) ---
  15358. Firing prefer*rvt*predict-yes*H0
  15359. -->
  15360. Firing rl*prefer*rvt*predict-yes*H0*5*v1*H1*30
  15361. -->
  15362. (S1 ^operator O2017 = 0.7358542477906264)
  15363. Firing rl*prefer*rvt*predict-yes*H0*5
  15364. -->
  15365. (S1 ^operator O2017 = 0.2640043987919141)
  15366. Firing prefer*rvt*predict-yes*H0*5*v1*H1
  15367. -->
  15368. Firing prefer*rvt*predict-no*H0
  15369. -->
  15370. Firing rl*prefer*rvt*predict-no*H0*6
  15371. -->
  15372. (S1 ^operator O2018 = 0.9998785089568328)
  15373. inner elaboration loop at bottom goal.
  15374. Retracting rl*prefer*rvt*predict-no*H0*6
  15375. -->
  15376. (S1 ^operator O2016 = 0.9998785089568328)
  15377. Retracting rl*prefer*rvt*predict-yes*H0*5
  15378. -->
  15379. (S1 ^operator O2015 = 0.2640043987919141)
  15380. Retracting rl*prefer*rvt*predict-yes*H0*5*v1*H1*30
  15381. -->
  15382. (S1 ^operator O2015 = 0.7358542477906264)
  15383. --- END Proposal Phase ---
  15384. --- Decision Phase ---
  15385. RL update rl*prefer*rvt*predict-no*H0*2 1 0 1 -> 1 0 1(R,m,v=1,1,0)
  15386. =>WM: (14218: S1 ^operator O2018)
  15387. 1009: O: O2018 (predict-no)
  15388. --- END Decision Phase ---
  15389. --- Application Phase ---
  15390. --- Firing Productions (PE) For State At Depth 1 ---
  15391. --- Inner Elaboration Phase, active level 1 (S1) ---
  15392. Firing apply*operator
  15393. -->
  15394. (I3 ^predict-no N1009 + :O )
  15395. Firing apply*operator*complete
  15396. -->
  15397. (I3 ^predict-no N1008 - :O )
  15398. inner elaboration loop at bottom goal.
  15399. --- Change Working Memory (PE) ---
  15400. =>WM: (14219: I3 ^predict-no N1009)
  15401. <=WM: (14206: N1008 ^status complete)
  15402. <=WM: (14205: I3 ^predict-no N1008)
  15403. --- Firing Productions (IE) For State At Depth 1 ---
  15404. --- Inner Elaboration Phase, active level 1 (S1) ---
  15405. Firing monitor*world
  15406. -->
  15407. I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
  15408. --- Change Working Memory (IE) ---
  15409. --- END Application Phase ---
  15410. --- Output Phase ---
  15411. ENV: Agent did: predict-no for direction L in state State-B
  15412. In State-B moving L
  15413. ENV: (next state, see, prediction correct?) = (State-A, 1, False)
  15414. predict error 1
  15415. dir: dir isL
  15416. --- END Output Phase ---
  15417. \-/--- Input Phase ---
  15418. =>WM: (14223: I2 ^dir L)
  15419. =>WM: (14222: I2 ^reward 0)
  15420. =>WM: (14221: I2 ^see 1)
  15421. =>WM: (14220: N1009 ^status complete)
  15422. <=WM: (14209: I2 ^dir L)
  15423. <=WM: (14208: I2 ^reward 1)
  15424. <=WM: (14207: I2 ^see 0)
  15425. =>WM: (14224: I2 ^level-1 L1-root)
  15426. <=WM: (14210: I2 ^level-1 R0-root)
  15427. --- END Input Phase ---
  15428. --- Proposal Phase ---
  15429. --- Inner Elaboration Phase, active level 1 (S1) ---
  15430. Firing rl*prefer*rvt*predict-yes*H0*5*v1*H1*31
  15431. -->
  15432. (S1 ^operator O2017 = -0.181727099742844)
  15433. Firing prefer*rvt*predict-yes*H0*5*v1*H1
  15434. -->
  15435. Firing elaborate*copy-see-to-output-link
  15436. -->
  15437. (I3 ^see 1 +)
  15438. Firing elaborate*reward*based*on*reward
  15439. -->
  15440. (R1013 ^value 0 +)
  15441. (R1 ^reward R1013 +)
  15442. Firing propose*predict-yes
  15443. -->
  15444. (O2019 ^name predict-yes +)
  15445. (S1 ^operator O2019 +)
  15446. Firing propose*predict-no
  15447. -->
  15448. (O2020 ^name predict-no +)
  15449. (S1 ^operator O2020 +)
  15450. Firing rl*prefer*rvt*predict-no*H0*6
  15451. -->
  15452. (S1 ^operator O2018 = 0.9998785089568328)
  15453. Firing rl*prefer*rvt*predict-yes*H0*5
  15454. -->
  15455. (S1 ^operator O2017 = 0.2640043987919141)
  15456. Firing prefer*rvt*predict-yes*H0
  15457. -->
  15458. Firing prefer*rvt*predict-no*H0
  15459. -->
  15460. Firing elaborate*copy-dir-to-output-link
  15461. -->
  15462. (I3 ^dir L +)
  15463. inner elaboration loop at bottom goal.
  15464. Retracting elaborate*copy-see-to-output-link
  15465. -->
  15466. (I3 ^see 0 +)
  15467. Retracting propose*predict-no
  15468. -->
  15469. (O2018 ^name predict-no +)
  15470. (S1 ^operator O2018 +)
  15471. Retracting propose*predict-yes
  15472. -->
  15473. (O2017 ^name predict-yes +)
  15474. (S1 ^operator O2017 +)
  15475. Retracting elaborate*reward*based*on*reward
  15476. -->
  15477. (R1012 ^value 1 +)
  15478. (R1 ^reward R1012 +)
  15479. Retracting elaborate*copy-dir-to-output-link
  15480. -->
  15481. (I3 ^dir L +)
  15482. Retracting rl*prefer*rvt*predict-no*H0*6
  15483. -->
  15484. (S1 ^operator O2018 = 0.9998785089568328)
  15485. Retracting rl*prefer*rvt*predict-yes*H0*5
  15486. -->
  15487. (S1 ^operator O2017 = 0.2640043987919141)
  15488. Retracting rl*prefer*rvt*predict-yes*H0*5*v1*H1*30
  15489. -->
  15490. (S1 ^operator O2017 = 0.7358542477906264)
  15491. =>WM: (14231: S1 ^operator O2020 +)
  15492. =>WM: (14230: S1 ^operator O2019 +)
  15493. =>WM: (14229: O2020 ^name predict-no)
  15494. =>WM: (14228: O2019 ^name predict-yes)
  15495. =>WM: (14227: R1013 ^value 0)
  15496. =>WM: (14226: R1 ^reward R1013)
  15497. =>WM: (14225: I3 ^see 1)
  15498. <=WM: (14216: S1 ^operator O2017 +)
  15499. <=WM: (14217: S1 ^operator O2018 +)
  15500. <=WM: (14218: S1 ^operator O2018)
  15501. <=WM: (14211: R1 ^reward R1012)
  15502. <=WM: (14196: I3 ^see 0)
  15503. <=WM: (14214: O2018 ^name predict-no)
  15504. <=WM: (14213: O2017 ^name predict-yes)
  15505. <=WM: (14212: R1012 ^value 1)
  15506. --- Inner Elaboration Phase, active level 1 (S1) ---
  15507. Firing prefer*rvt*predict-yes*H0
  15508. -->
  15509. Firing rl*prefer*rvt*predict-yes*H0*5
  15510. -->
  15511. (S1 ^operator O2019 = 0.2640043987919141)
  15512. Firing prefer*rvt*predict-yes*H0*5*v1*H1
  15513. -->
  15514. Firing rl*prefer*rvt*predict-yes*H0*5*v1*H1*31
  15515. -->
  15516. (S1 ^operator O2019 = -0.181727099742844)
  15517. Firing prefer*rvt*predict-no*H0
  15518. -->
  15519. Firing rl*prefer*rvt*predict-no*H0*6
  15520. -->
  15521. (S1 ^operator O2020 = 0.9998785089568328)
  15522. inner elaboration loop at bottom goal.
  15523. Retracting rl*prefer*rvt*predict-no*H0*6
  15524. -->
  15525. (S1 ^operator O2018 = 0.9998785089568328)
  15526. Retracting rl*prefer*rvt*predict-yes*H0*5
  15527. -->
  15528. (S1 ^operator O2017 = 0.2640043987919141)
  15529. Retracting rl*prefer*rvt*predict-yes*H0*5*v1*H1*31
  15530. -->
  15531. (S1 ^operator O2017 = -0.181727099742844)
  15532. --- END Proposal Phase ---
  15533. --- Decision Phase ---
  15534. RL update rl*prefer*rvt*predict-no*H0*6 0.999879 0 0.999879 -> 0.833711 0 0.833711(R,m,v=0,0.900662,0.0900662)
  15535. =>WM: (14232: S1 ^operator O2020)
  15536. 1010: O: O2020 (predict-no)
  15537. --- END Decision Phase ---
  15538. --- Application Phase ---
  15539. --- Firing Productions (PE) For State At Depth 1 ---
  15540. --- Inner Elaboration Phase, active level 1 (S1) ---
  15541. Firing apply*operator
  15542. -->
  15543. (I3 ^predict-no N1010 + :O )
  15544. Firing apply*operator*complete
  15545. -->
  15546. (I3 ^predict-no N1009 - :O )
  15547. inner elaboration loop at bottom goal.
  15548. --- Change Working Memory (PE) ---
  15549. =>WM: (14233: I3 ^predict-no N1010)
  15550. <=WM: (14220: N1009 ^status complete)
  15551. <=WM: (14219: I3 ^predict-no N1009)
  15552. --- Firing Productions (IE) For State At Depth 1 ---
  15553. --- Inner Elaboration Phase, active level 1 (S1) ---
  15554. Firing monitor*world
  15555. -->
  15556. I see 0 and I'm going to do: predict-no inner elaboration loop at bottom goal.
  15557. --- Change Working Memory (IE) ---
  15558. --- END Application Phase ---
  15559. --- Output Phase ---
  15560. ENV: Agent did: predict-no for direction L in state State-A
  15561. In State-A moving L
  15562. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  15563. predict error 0
  15564. dir: dir isR
  15565. --- END Output Phase ---
  15566. |\---- Input Phase ---
  15567. =>WM: (14237: I2 ^dir R)
  15568. =>WM: (14236: I2 ^reward 1)
  15569. =>WM: (14235: I2 ^see 0)
  15570. =>WM: (14234: N1010 ^status complete)
  15571. <=WM: (14223: I2 ^dir L)
  15572. <=WM: (14222: I2 ^reward 0)
  15573. <=WM: (14221: I2 ^see 1)
  15574. =>WM: (14238: I2 ^level-1 L0-root)
  15575. <=WM: (14224: I2 ^level-1 L1-root)
  15576. --- END Input Phase ---
  15577. --- Proposal Phase ---
  15578. --- Inner Elaboration Phase, active level 1 (S1) ---
  15579. Firing rl*prefer*rvt*predict-no*H0*4*v1*H1*33
  15580. -->
  15581. (S1 ^operator O2020 = -0.2817060109291377)
  15582. Firing rl*prefer*rvt*predict-yes*H0*3*v1*H1*34
  15583. -->
  15584. (S1 ^operator O2019 = 0.6623458215671729)
  15585. Firing prefer*rvt*predict-no*H0*4*v1*H1
  15586. -->
  15587. Firing prefer*rvt*predict-yes*H0*3*v1*H1
  15588. -->
  15589. Firing elaborate*copy-see-to-output-link
  15590. -->
  15591. (I3 ^see 0 +)
  15592. Firing elaborate*reward*based*on*reward
  15593. -->
  15594. (R1014 ^value 1 +)
  15595. (R1 ^reward R1014 +)
  15596. Firing propose*predict-yes
  15597. -->
  15598. (O2021 ^name predict-yes +)
  15599. (S1 ^operator O2021 +)
  15600. Firing propose*predict-no
  15601. -->
  15602. (O2022 ^name predict-no +)
  15603. (S1 ^operator O2022 +)
  15604. Firing rl*prefer*rvt*predict-no*H0*4
  15605. -->
  15606. (S1 ^operator O2020 = 0.3397723577617232)
  15607. Firing rl*prefer*rvt*predict-yes*H0*3
  15608. -->
  15609. (S1 ^operator O2019 = 0.3377168791642142)
  15610. Firing prefer*rvt*predict-yes*H0
  15611. -->
  15612. Firing prefer*rvt*predict-no*H0
  15613. -->
  15614. Firing elaborate*copy-dir-to-output-link
  15615. -->
  15616. (I3 ^dir R +)
  15617. inner elaboration loop at bottom goal.
  15618. Retracting elaborate*copy-see-to-output-link
  15619. -->
  15620. (I3 ^see 1 +)
  15621. Retracting propose*predict-no
  15622. -->
  15623. (O2020 ^name predict-no +)
  15624. (S1 ^operator O2020 +)
  15625. Retracting propose*predict-yes
  15626. -->
  15627. (O2019 ^name predict-yes +)
  15628. (S1 ^operator O2019 +)
  15629. Retracting elaborate*reward*based*on*reward
  15630. -->
  15631. (R1013 ^value 0 +)
  15632. (R1 ^reward R1013 +)
  15633. Retracting elaborate*copy-dir-to-output-link
  15634. -->
  15635. (I3 ^dir L +)
  15636. Retracting rl*prefer*rvt*predict-no*H0*6
  15637. -->
  15638. (S1 ^operator O2020 = 0.8337106497126315)
  15639. Retracting rl*prefer*rvt*predict-yes*H0*5*v1*H1*31
  15640. -->
  15641. (S1 ^operator O2019 = -0.181727099742844)
  15642. Retracting rl*prefer*rvt*predict-yes*H0*5
  15643. -->
  15644. (S1 ^operator O2019 = 0.2640043987919141)
  15645. =>WM: (14246: S1 ^operator O2022 +)
  15646. =>WM: (14245: S1 ^operator O2021 +)
  15647. =>WM: (14244: I3 ^dir R)
  15648. =>WM: (14243: O2022 ^name predict-no)
  15649. =>WM: (14242: O2021 ^name predict-yes)
  15650. =>WM: (14241: R1014 ^value 1)
  15651. =>WM: (14240: R1 ^reward R1014)
  15652. =>WM: (14239: I3 ^see 0)
  15653. <=WM: (14230: S1 ^operator O2019 +)
  15654. <=WM: (14231: S1 ^operator O2020 +)
  15655. <=WM: (14232: S1 ^operator O2020)
  15656. <=WM: (14215: I3 ^dir L)
  15657. <=WM: (14226: R1 ^reward R1013)
  15658. <=WM: (14225: I3 ^see 1)
  15659. <=WM: (14229: O2020 ^name predict-no)
  15660. <=WM: (14228: O2019 ^name predict-yes)
  15661. <=WM: (14227: R1013 ^value 0)
  15662. --- Inner Elaboration Phase, active level 1 (S1) ---
  15663. Firing prefer*rvt*predict-yes*H0
  15664. -->
  15665. Firing rl*prefer*rvt*predict-yes*H0*3
  15666. -->
  15667. (S1 ^operator O2021 = 0.3377168791642142)
  15668. Firing prefer*rvt*predict-yes*H0*3*v1*H1
  15669. -->
  15670. Firing rl*prefer*rvt*predict-yes*H0*3*v1*H1*34
  15671. -->
  15672. (S1 ^operator O2021 = 0.6623458215671729)
  15673. Firing prefer*rvt*predict-no*H0
  15674. -->
  15675. Firing rl*prefer*rvt*predict-no*H0*4
  15676. -->
  15677. (S1 ^operator O2022 = 0.3397723577617232)
  15678. Firing prefer*rvt*predict-no*H0*4*v1*H1
  15679. -->
  15680. Firing rl*prefer*rvt*predict-no*H0*4*v1*H1*33
  15681. -->
  15682. (S1 ^operator O2022 = -0.2817060109291377)
  15683. inner elaboration loop at bottom goal.
  15684. Retracting rl*prefer*rvt*predict-no*H0*4
  15685. -->
  15686. (S1 ^operator O2020 = 0.3397723577617232)
  15687. Retracting rl*prefer*rvt*predict-no*H0*4*v1*H1*33
  15688. -->
  15689. (S1 ^operator O2020 = -0.2817060109291377)
  15690. Retracting rl*prefer*rvt*predict-yes*H0*3
  15691. -->
  15692. (S1 ^operator O2019 = 0.3377168791642142)
  15693. Retracting rl*prefer*rvt*predict-yes*H0*3*v1*H1*34
  15694. -->
  15695. (S1 ^operator O2019 = 0.6623458215671729)
  15696. --- END Proposal Phase ---
  15697. --- Decision Phase ---
  15698. RL update rl*prefer*rvt*predict-no*H0*6 0.833711 0 0.833711 -> 0.861316 0 0.861316(R,m,v=1,0.901316,0.0895347)
  15699. =>WM: (14247: S1 ^operator O2021)
  15700. 1011: O: O2021 (predict-yes)
  15701. --- END Decision Phase ---
  15702. --- Application Phase ---
  15703. --- Firing Productions (PE) For State At Depth 1 ---
  15704. --- Inner Elaboration Phase, active level 1 (S1) ---
  15705. Firing apply*operator
  15706. -->
  15707. (I3 ^predict-yes N1011 + :O )
  15708. Firing apply*operator*complete
  15709. -->
  15710. (I3 ^predict-no N1010 - :O )
  15711. inner elaboration loop at bottom goal.
  15712. --- Change Working Memory (PE) ---
  15713. =>WM: (14248: I3 ^predict-yes N1011)
  15714. <=WM: (14234: N1010 ^status complete)
  15715. <=WM: (14233: I3 ^predict-no N1010)
  15716. --- Firing Productions (IE) For State At Depth 1 ---
  15717. --- Inner Elaboration Phase, active level 1 (S1) ---
  15718. Firing monitor*world
  15719. -->
  15720. I see 1 and I'm going to do: predict-yes inner elaboration loop at bottom goal.
  15721. --- Change Working Memory (IE) ---
  15722. --- END Application Phase ---
  15723. --- Output Phase ---
  15724. ENV: Agent did: predict-yes for direction R in state State-A
  15725. In State-A moving R
  15726. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  15727. predict error 0
  15728. dir: dir isL
  15729. --- END Output Phase ---
  15730. /--- Input Phase ---
  15731. =>WM: (14252: I2 ^dir L)
  15732. =>WM: (14251: I2 ^reward 1)
  15733. =>WM: (14250: I2 ^see 1)
  15734. =>WM: (14249: N1011 ^status complete)
  15735. <=WM: (14237: I2 ^dir R)
  15736. <=WM: (14236: I2 ^reward 1)
  15737. <=WM: (14235: I2 ^see 0)
  15738. =>WM: (14253: I2 ^level-1 R1-root)
  15739. <=WM: (14238: I2 ^level-1 L0-root)
  15740. --- END Input Phase ---
  15741. --- Proposal Phase ---
  15742. --- Inner Elaboration Phase,