PageRenderTime 157ms CodeModel.GetById 36ms RepoModel.GetById 0ms app.codeStats 0ms

/flipv2/20121112-100543-2.5K-ReLST-Wallace/stdout-flip-2.5K_2.txt

https://bitbucket.org/evan13579b/soar-ziggurat
Plain Text | 16457 lines | 15725 code | 732 blank | 0 comment | 0 complexity | 48cf6b25d56458075e17baa5b7c3bbdf MD5 | raw file
Possible License(s): BSD-3-Clause
  1. Seeding... 2
  2. dir: dir isU
  3. Python-Soar Flip environment.
  4. To accept commands from an external sml process, you'll need to
  5. type 'slave <log file> <n decisons>' at the prompt...
  6. sourcing 'flip_predict.soar'
  7. ***********
  8. Total: 11 productions sourced.
  9. seeding Soar with 2 ...
  10. soar> Entering slave mode:
  11. - log file 'rl-slave-2.5K_2.log'....
  12. - will exit slave mode after 2500 decisions
  13. waiting for commands from an externally connected sml process...
  14. -/|sleeping...
  15. \sleeping...
  16. -sleeping...
  17. /sleeping...
  18. |sleeping...
  19. \-/|\-/|\-/sleeping...
  20. |\-/|\-sleeping...
  21. /1: O: O1 (predict-yes)
  22. I see 0 and I'm going to do: predict-yes
  23. ENV: Agent did: predict-yes for direction U in state State-A
  24. In State-A moving U
  25. ENV: (next state, see, prediction correct?) = (State-A, 0, False)
  26. predict error 1
  27. dir: dir isU
  28. rule alias: '*'
  29. rule alias: '*'
  30. |\-/|\-/2: O: O4 (predict-no)
  31. I see 0 and I'm going to do: predict-no
  32. ENV: Agent did: predict-no for direction U in state State-A
  33. In State-A moving U
  34. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  35. predict error 0
  36. dir: dir isL
  37. |\3: O: O5 (predict-yes)
  38. I see 1 and I'm going to do: predict-yes
  39. ENV: Agent did: predict-yes for direction L in state State-A
  40. In State-A moving L
  41. ENV: (next state, see, prediction correct?) = (State-A, 0, False)
  42. predict error 1
  43. dir: dir isL
  44. -/|4: O: O7 (predict-yes)
  45. I see 0 and I'm going to do: predict-yes
  46. ENV: Agent did: predict-yes for direction L in state State-A
  47. In State-A moving L
  48. ENV: (next state, see, prediction correct?) = (State-A, 0, False)
  49. predict error 1
  50. dir: dir isU
  51. \-/5: O: O10 (predict-no)
  52. I see 0 and I'm going to do: predict-no
  53. ENV: Agent did: predict-no for direction U in state State-A
  54. In State-A moving U
  55. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  56. predict error 0
  57. dir: dir isU
  58. |\-6: O: O12 (predict-no)
  59. I see 1 and I'm going to do: predict-no
  60. ENV: Agent did: predict-no for direction U in state State-A
  61. In State-A moving U
  62. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  63. predict error 0
  64. dir: dir isU
  65. /|\7: O: O14 (predict-no)
  66. I see 1 and I'm going to do: predict-no
  67. ENV: Agent did: predict-no for direction U in state State-A
  68. In State-A moving U
  69. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  70. predict error 0
  71. dir: dir isL
  72. -/8: O: O15 (predict-yes)
  73. I see 1 and I'm going to do: predict-yes
  74. ENV: Agent did: predict-yes for direction L in state State-A
  75. In State-A moving L
  76. ENV: (next state, see, prediction correct?) = (State-A, 0, False)
  77. predict error 1
  78. dir: dir isR
  79. |\-9: O: O17 (predict-yes)
  80. I see 0 and I'm going to do: predict-yes
  81. ENV: Agent did: predict-yes for direction R in state State-A
  82. In State-A moving R
  83. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  84. predict error 0
  85. dir: dir isR
  86. /|\10: O: O19 (predict-yes)
  87. I see 1 and I'm going to do: predict-yes
  88. ENV: Agent did: predict-yes for direction R in state State-B
  89. In State-B moving R
  90. ENV: (next state, see, prediction correct?) = (State-B, 0, False)
  91. predict error 1
  92. dir: dir isR
  93. -/|11: O: O21 (predict-yes)
  94. I see 0 and I'm going to do: predict-yes
  95. ENV: Agent did: predict-yes for direction R in state State-B
  96. In State-B moving R
  97. ENV: (next state, see, prediction correct?) = (State-B, 0, False)
  98. predict error 1
  99. dir: dir isL
  100. rule alias: '*'
  101. rule alias: '*'
  102. rule alias: '*'
  103. rule alias: '*'
  104. \12: O: O24 (predict-no)
  105. I see 0 and I'm going to do: predict-no
  106. ENV: Agent did: predict-no for direction L in state State-B
  107. In State-B moving L
  108. ENV: (next state, see, prediction correct?) = (State-A, 1, False)
  109. predict error 1
  110. dir: dir isR
  111. -/13: O: O25 (predict-yes)
  112. I see 0 and I'm going to do: predict-yes
  113. ENV: Agent did: predict-yes for direction R in state State-A
  114. In State-A moving R
  115. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  116. predict error 0
  117. dir: dir isR
  118. |\14: O: O27 (predict-yes)
  119. I see 1 and I'm going to do: predict-yes
  120. ENV: Agent did: predict-yes for direction R in state State-B
  121. In State-B moving R
  122. ENV: (next state, see, prediction correct?) = (State-B, 0, False)
  123. predict error 1
  124. dir: dir isU
  125. -/15: O: O30 (predict-no)
  126. I see 0 and I'm going to do: predict-no
  127. ENV: Agent did: predict-no for direction U in state State-B
  128. In State-B moving U
  129. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  130. predict error 0
  131. dir: dir isU
  132. |\-16: O: O32 (predict-no)
  133. I see 1 and I'm going to do: predict-no
  134. ENV: Agent did: predict-no for direction U in state State-B
  135. In State-B moving U
  136. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  137. predict error 0
  138. dir: dir isU
  139. /|\17: O: O34 (predict-no)
  140. I see 1 and I'm going to do: predict-no
  141. ENV: Agent did: predict-no for direction U in state State-B
  142. In State-B moving U
  143. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  144. predict error 0
  145. dir: dir isR
  146. -/18: O: O35 (predict-yes)
  147. I see 1 and I'm going to do: predict-yes
  148. ENV: Agent did: predict-yes for direction R in state State-B
  149. In State-B moving R
  150. ENV: (next state, see, prediction correct?) = (State-B, 0, False)
  151. predict error 1
  152. dir: dir isR
  153. |\-19: O: O37 (predict-yes)
  154. I see 0 and I'm going to do: predict-yes
  155. ENV: Agent did: predict-yes for direction R in state State-B
  156. In State-B moving R
  157. ENV: (next state, see, prediction correct?) = (State-B, 0, False)
  158. predict error 1
  159. dir: dir isL
  160. /|\20: O: O39 (predict-yes)
  161. I see 0 and I'm going to do: predict-yes
  162. ENV: Agent did: predict-yes for direction L in state State-B
  163. In State-B moving L
  164. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  165. predict error 0
  166. dir: dir isL
  167. -/|21: O: O42 (predict-no)
  168. I see 1 and I'm going to do: predict-no
  169. ENV: Agent did: predict-no for direction L in state State-A
  170. In State-A moving L
  171. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  172. predict error 0
  173. dir: dir isL
  174. \22: O: O43 (predict-yes)
  175. I see 1 and I'm going to do: predict-yes
  176. ENV: Agent did: predict-yes for direction L in state State-A
  177. In State-A moving L
  178. ENV: (next state, see, prediction correct?) = (State-A, 0, False)
  179. predict error 1
  180. dir: dir isR
  181. -/23: O: O45 (predict-yes)
  182. I see 0 and I'm going to do: predict-yes
  183. ENV: Agent did: predict-yes for direction R in state State-A
  184. In State-A moving R
  185. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  186. predict error 0
  187. dir: dir isL
  188. |\24: O: O48 (predict-no)
  189. I see 1 and I'm going to do: predict-no
  190. ENV: Agent did: predict-no for direction L in state State-B
  191. In State-B moving L
  192. ENV: (next state, see, prediction correct?) = (State-A, 1, False)
  193. predict error 1
  194. dir: dir isR
  195. -/25: O: O49 (predict-yes)
  196. I see 0 and I'm going to do: predict-yes
  197. ENV: Agent did: predict-yes for direction R in state State-A
  198. In State-A moving R
  199. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  200. predict error 0
  201. dir: dir isU
  202. |\-26: O: O52 (predict-no)
  203. I see 1 and I'm going to do: predict-no
  204. ENV: Agent did: predict-no for direction U in state State-B
  205. In State-B moving U
  206. ENV: (next state, see, prediction correct?) = (State-B, 0, 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-B
  212. In State-B moving R
  213. ENV: (next state, see, prediction correct?) = (State-B, 0, False)
  214. predict error 1
  215. dir: dir isR
  216. \-/28: O: O55 (predict-yes)
  217. I see 0 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 isL
  223. |\29: O: O58 (predict-no)
  224. I see 0 and I'm going to do: predict-no
  225. ENV: Agent did: predict-no for direction L in state State-B
  226. In State-B moving L
  227. ENV: (next state, see, prediction correct?) = (State-A, 1, False)
  228. predict error 1
  229. dir: dir isL
  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 L in state State-A
  233. In State-A moving L
  234. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  235. predict error 0
  236. dir: dir isL
  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 L in state State-A
  240. In State-A moving L
  241. ENV: (next state, see, prediction correct?) = (State-A, 0, False)
  242. predict error 1
  243. dir: dir isL
  244. |32: O: O64 (predict-no)
  245. I see 0 and I'm going to do: predict-no
  246. ENV: Agent did: predict-no for direction L in state State-A
  247. In State-A moving L
  248. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  249. predict error 0
  250. dir: dir isR
  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 R in state State-A
  254. In State-A moving R
  255. ENV: (next state, see, prediction correct?) = (State-B, 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-B
  261. In State-B moving U
  262. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  263. predict error 0
  264. dir: dir isU
  265. -/|35: O: O70 (predict-no)
  266. I see 1 and I'm going to do: predict-no
  267. ENV: Agent did: predict-no for direction U in state State-B
  268. In State-B moving U
  269. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  270. predict error 0
  271. dir: dir isL
  272. \36: O: O72 (predict-no)
  273. I see 1 and I'm going to do: predict-no
  274. ENV: Agent did: predict-no for direction L in state State-B
  275. In State-B moving L
  276. ENV: (next state, see, prediction correct?) = (State-A, 1, False)
  277. predict error 1
  278. dir: dir isU
  279. -/37: O: O74 (predict-no)
  280. I see 0 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 isU
  286. |\-38: O: O76 (predict-no)
  287. I see 1 and I'm going to do: predict-no
  288. ENV: Agent did: predict-no for direction U in state State-A
  289. In State-A moving U
  290. ENV: (next state, see, prediction correct?) = (State-A, 0, 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-A
  296. In State-A moving U
  297. ENV: (next state, see, prediction correct?) = (State-A, 0, False)
  298. predict error 1
  299. dir: dir isU
  300. -/40: O: O79 (predict-yes)
  301. I see 0 and I'm going to do: predict-yes
  302. ENV: Agent did: predict-yes for direction U in state State-A
  303. In State-A moving U
  304. ENV: (next state, see, prediction correct?) = (State-A, 0, False)
  305. predict error 1
  306. dir: dir isU
  307. |\41: O: O82 (predict-no)
  308. I see 0 and I'm going to do: predict-no
  309. ENV: Agent did: predict-no for direction U in state State-A
  310. In State-A moving U
  311. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  312. predict error 0
  313. dir: dir isU
  314. -42: O: O84 (predict-no)
  315. I see 1 and I'm going to do: predict-no
  316. ENV: Agent did: predict-no for direction U in state State-A
  317. In State-A moving U
  318. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  319. predict error 0
  320. dir: dir isR
  321. /|43: O: O85 (predict-yes)
  322. I see 1 and I'm going to do: predict-yes
  323. ENV: Agent did: predict-yes for direction R in state State-A
  324. In State-A moving R
  325. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  326. predict error 0
  327. dir: dir isU
  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 U in state State-B
  331. In State-B moving U
  332. ENV: (next state, see, prediction correct?) = (State-B, 0, False)
  333. predict error 1
  334. dir: dir isU
  335. /|\45: O: O90 (predict-no)
  336. I see 0 and I'm going to do: predict-no
  337. ENV: Agent did: predict-no for direction U in state State-B
  338. In State-B moving U
  339. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  340. predict error 0
  341. dir: dir isL
  342. -/|46: O: O92 (predict-no)
  343. I see 1 and I'm going to do: predict-no
  344. ENV: Agent did: predict-no for direction L in state State-B
  345. In State-B moving L
  346. ENV: (next state, see, prediction correct?) = (State-A, 1, False)
  347. predict error 1
  348. dir: dir isU
  349. \-/47: O: O94 (predict-no)
  350. I see 0 and I'm going to do: predict-no
  351. ENV: Agent did: predict-no for direction U in state State-A
  352. In State-A moving U
  353. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  354. predict error 0
  355. dir: dir isU
  356. |\-48: O: O96 (predict-no)
  357. I see 1 and I'm going to do: predict-no
  358. ENV: Agent did: predict-no for direction U in state State-A
  359. In State-A moving U
  360. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  361. predict error 0
  362. dir: dir isR
  363. /|\49: O: O97 (predict-yes)
  364. I see 1 and I'm going to do: predict-yes
  365. ENV: Agent did: predict-yes for direction R in state State-A
  366. In State-A moving R
  367. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  368. predict error 0
  369. dir: dir isR
  370. -/|50: O: O99 (predict-yes)
  371. I see 1 and I'm going to do: predict-yes
  372. ENV: Agent did: predict-yes for direction R in state State-B
  373. In State-B moving R
  374. ENV: (next state, see, prediction correct?) = (State-B, 0, False)
  375. predict error 1
  376. dir: dir isR
  377. \-/|\-/sleeping...
  378. |sleeping...
  379. \sleeping...
  380. -sleeping...
  381. /sleeping...
  382. |sleeping...
  383. \sleeping...
  384. -sleeping...
  385. /sleeping...
  386. |sleeping...
  387. \sleeping...
  388. -sleeping...
  389. /sleeping...
  390. |sleeping...
  391. \sleeping...
  392. -sleeping...
  393. /sleeping...
  394. |sleeping...
  395. \51: O: O101 (predict-yes)
  396. I see 0 and I'm going to do: predict-yes
  397. ENV: Agent did: predict-yes for direction R in state State-B
  398. In State-B moving R
  399. ENV: (next state, see, prediction correct?) = (State-B, 0, False)
  400. predict error 1
  401. dir: dir isU
  402. rule alias: '*'
  403. -52: O: O104 (predict-no)
  404. I see 0 and I'm going to do: predict-no
  405. ENV: Agent did: predict-no for direction U in state State-B
  406. In State-B moving U
  407. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  408. predict error 0
  409. dir: dir isR
  410. /|53: O: O105 (predict-yes)
  411. I see 1 and I'm going to do: predict-yes
  412. ENV: Agent did: predict-yes for direction R in state State-B
  413. In State-B moving R
  414. ENV: (next state, see, prediction correct?) = (State-B, 0, False)
  415. predict error 1
  416. dir: dir isU
  417. \-/|54: O: O108 (predict-no)
  418. I see 0 and I'm going to do: predict-no
  419. ENV: Agent did: predict-no for direction U in state State-B
  420. In State-B moving U
  421. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  422. predict error 0
  423. dir: dir isR
  424. \-/55: O: O109 (predict-yes)
  425. I see 1 and I'm going to do: predict-yes
  426. ENV: Agent did: predict-yes for direction R in state State-B
  427. In State-B moving R
  428. ENV: (next state, see, prediction correct?) = (State-B, 0, False)
  429. predict error 1
  430. dir: dir isU
  431. |\56: O: O111 (predict-yes)
  432. I see 0 and I'm going to do: predict-yes
  433. ENV: Agent did: predict-yes for direction U in state State-B
  434. In State-B moving U
  435. ENV: (next state, see, prediction correct?) = (State-B, 0, False)
  436. predict error 1
  437. dir: dir isU
  438. -/57: O: O114 (predict-no)
  439. I see 0 and I'm going to do: predict-no
  440. ENV: Agent did: predict-no for direction U in state State-B
  441. In State-B moving U
  442. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  443. predict error 0
  444. dir: dir isR
  445. |\58: O: O115 (predict-yes)
  446. I see 1 and I'm going to do: predict-yes
  447. ENV: Agent did: predict-yes for direction R in state State-B
  448. In State-B moving R
  449. ENV: (next state, see, prediction correct?) = (State-B, 0, False)
  450. predict error 1
  451. dir: dir isR
  452. -59: O: O117 (predict-yes)
  453. I see 0 and I'm going to do: predict-yes
  454. ENV: Agent did: predict-yes for direction R in state State-B
  455. In State-B moving R
  456. ENV: (next state, see, prediction correct?) = (State-B, 0, False)
  457. predict error 1
  458. dir: dir isU
  459. /|60: O: O120 (predict-no)
  460. I see 0 and I'm going to do: predict-no
  461. ENV: Agent did: predict-no for direction U in state State-B
  462. In State-B moving U
  463. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  464. predict error 0
  465. dir: dir isU
  466. \-/61: O: O122 (predict-no)
  467. I see 1 and I'm going to do: predict-no
  468. ENV: Agent did: predict-no for direction U in state State-B
  469. In State-B moving U
  470. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  471. predict error 0
  472. dir: dir isR
  473. |62: O: O123 (predict-yes)
  474. I see 1 and I'm going to do: predict-yes
  475. ENV: Agent did: predict-yes for direction R in state State-B
  476. In State-B moving R
  477. ENV: (next state, see, prediction correct?) = (State-B, 0, False)
  478. predict error 1
  479. dir: dir isL
  480. \-63: O: O126 (predict-no)
  481. I see 0 and I'm going to do: predict-no
  482. ENV: Agent did: predict-no for direction L in state State-B
  483. In State-B moving L
  484. ENV: (next state, see, prediction correct?) = (State-A, 1, False)
  485. predict error 1
  486. dir: dir isL
  487. /|\-64: O: O128 (predict-no)
  488. I see 0 and I'm going to do: predict-no
  489. ENV: Agent did: predict-no for direction L in state State-A
  490. In State-A moving L
  491. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  492. predict error 0
  493. dir: dir isU
  494. /|65: O: O130 (predict-no)
  495. I see 1 and I'm going to do: predict-no
  496. ENV: Agent did: predict-no for direction U in state State-A
  497. In State-A moving U
  498. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  499. predict error 0
  500. dir: dir isL
  501. \-66: O: O132 (predict-no)
  502. I see 1 and I'm going to do: predict-no
  503. ENV: Agent did: predict-no for direction L in state State-A
  504. In State-A moving L
  505. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  506. predict error 0
  507. dir: dir isU
  508. /67: O: O134 (predict-no)
  509. I see 1 and I'm going to do: predict-no
  510. ENV: Agent did: predict-no for direction U in state State-A
  511. In State-A moving U
  512. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  513. predict error 0
  514. dir: dir isL
  515. |\-68: O: O136 (predict-no)
  516. I see 1 and I'm going to do: predict-no
  517. ENV: Agent did: predict-no for direction L in state State-A
  518. In State-A moving L
  519. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  520. predict error 0
  521. dir: dir isU
  522. /|69: O: O138 (predict-no)
  523. I see 1 and I'm going to do: predict-no
  524. ENV: Agent did: predict-no for direction U in state State-A
  525. In State-A moving U
  526. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  527. predict error 0
  528. dir: dir isL
  529. \-/70: O: O140 (predict-no)
  530. I see 1 and I'm going to do: predict-no
  531. ENV: Agent did: predict-no for direction L in state State-A
  532. In State-A moving L
  533. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  534. predict error 0
  535. dir: dir isU
  536. |\71: O: O142 (predict-no)
  537. I see 1 and I'm going to do: predict-no
  538. ENV: Agent did: predict-no for direction U in state State-A
  539. In State-A moving U
  540. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  541. predict error 0
  542. dir: dir isU
  543. rule alias: '*'
  544. rule alias: '*'
  545. rule alias: '*'
  546. rule alias: '*'
  547. rule alias: '*'
  548. rule alias: '*'
  549. -72: O: O144 (predict-no)
  550. I see 1 and I'm going to do: predict-no
  551. ENV: Agent did: predict-no for direction U in state State-A
  552. In State-A moving U
  553. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  554. predict error 0
  555. dir: dir isR
  556. /|\73: O: O145 (predict-yes)
  557. I see 1 and I'm going to do: predict-yes
  558. ENV: Agent did: predict-yes for direction R in state State-A
  559. In State-A moving R
  560. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  561. predict error 0
  562. dir: dir isR
  563. -/74: O: O147 (predict-yes)
  564. I see 1 and I'm going to do: predict-yes
  565. ENV: Agent did: predict-yes for direction R in state State-B
  566. In State-B moving R
  567. ENV: (next state, see, prediction correct?) = (State-B, 0, False)
  568. predict error 1
  569. dir: dir isR
  570. |\75: O: O149 (predict-yes)
  571. I see 0 and I'm going to do: predict-yes
  572. ENV: Agent did: predict-yes for direction R in state State-B
  573. In State-B moving R
  574. ENV: (next state, see, prediction correct?) = (State-B, 0, False)
  575. predict error 1
  576. dir: dir isR
  577. -/|\76: O: O152 (predict-no)
  578. I see 0 and I'm going to do: predict-no
  579. ENV: Agent did: predict-no for direction R in state State-B
  580. In State-B moving R
  581. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  582. predict error 0
  583. dir: dir isL
  584. -/|77: O: O154 (predict-no)
  585. I see 1 and I'm going to do: predict-no
  586. ENV: Agent did: predict-no for direction L in state State-B
  587. In State-B moving L
  588. ENV: (next state, see, prediction correct?) = (State-A, 1, False)
  589. predict error 1
  590. dir: dir isL
  591. \-/78: O: O156 (predict-no)
  592. I see 0 and I'm going to do: predict-no
  593. ENV: Agent did: predict-no for direction L in state State-A
  594. In State-A moving L
  595. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  596. predict error 0
  597. dir: dir isR
  598. |\79: O: O158 (predict-no)
  599. I see 1 and I'm going to do: predict-no
  600. ENV: Agent did: predict-no for direction R in state State-A
  601. In State-A moving R
  602. ENV: (next state, see, prediction correct?) = (State-B, 1, False)
  603. predict error 1
  604. dir: dir isU
  605. -80: O: O160 (predict-no)
  606. I see 0 and I'm going to do: predict-no
  607. ENV: Agent did: predict-no for direction U in state State-B
  608. In State-B moving U
  609. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  610. predict error 0
  611. dir: dir isR
  612. /|81: O: O162 (predict-no)
  613. I see 1 and I'm going to do: predict-no
  614. ENV: Agent did: predict-no for direction R in state State-B
  615. In State-B moving R
  616. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  617. predict error 0
  618. dir: dir isL
  619. rule alias: '*'
  620. rule alias: '*'
  621. \82: O: O163 (predict-yes)
  622. I see 1 and I'm going to do: predict-yes
  623. ENV: Agent did: predict-yes for direction L in state State-B
  624. In State-B moving L
  625. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  626. predict error 0
  627. dir: dir isU
  628. -/|\83: O: O166 (predict-no)
  629. I see 1 and I'm going to do: predict-no
  630. ENV: Agent did: predict-no for direction U in state State-A
  631. In State-A moving U
  632. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  633. predict error 0
  634. dir: dir isU
  635. -/|84: O: O168 (predict-no)
  636. I see 1 and I'm going to do: predict-no
  637. ENV: Agent did: predict-no for direction U in state State-A
  638. In State-A moving U
  639. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  640. predict error 0
  641. dir: dir isU
  642. \-85: O: O169 (predict-yes)
  643. I see 1 and I'm going to do: predict-yes
  644. ENV: Agent did: predict-yes for direction U in state State-A
  645. In State-A moving U
  646. ENV: (next state, see, prediction correct?) = (State-A, 0, False)
  647. predict error 1
  648. dir: dir isL
  649. /|86: O: O172 (predict-no)
  650. I see 0 and I'm going to do: predict-no
  651. ENV: Agent did: predict-no for direction L in state State-A
  652. In State-A moving L
  653. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  654. predict error 0
  655. dir: dir isU
  656. \-/87: O: O173 (predict-yes)
  657. I see 1 and I'm going to do: predict-yes
  658. ENV: Agent did: predict-yes for direction U in state State-A
  659. In State-A moving U
  660. ENV: (next state, see, prediction correct?) = (State-A, 0, False)
  661. predict error 1
  662. dir: dir isL
  663. |\88: O: O176 (predict-no)
  664. I see 0 and I'm going to do: predict-no
  665. ENV: Agent did: predict-no for direction L in state State-A
  666. In State-A moving L
  667. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  668. predict error 0
  669. dir: dir isR
  670. -/89: O: O177 (predict-yes)
  671. I see 1 and I'm going to do: predict-yes
  672. ENV: Agent did: predict-yes for direction R in state State-A
  673. In State-A moving R
  674. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  675. predict error 0
  676. dir: dir isL
  677. |\90: O: O180 (predict-no)
  678. I see 1 and I'm going to do: predict-no
  679. ENV: Agent did: predict-no for direction L in state State-B
  680. In State-B moving L
  681. ENV: (next state, see, prediction correct?) = (State-A, 1, False)
  682. predict error 1
  683. dir: dir isL
  684. -/|91: O: O182 (predict-no)
  685. I see 0 and I'm going to do: predict-no
  686. ENV: Agent did: predict-no for direction L in state State-A
  687. In State-A moving L
  688. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  689. predict error 0
  690. dir: dir isU
  691. rule alias: '*'
  692. rule alias: '*'
  693. \92: O: O184 (predict-no)
  694. I see 1 and I'm going to do: predict-no
  695. ENV: Agent did: predict-no for direction U in state State-A
  696. In State-A moving U
  697. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  698. predict error 0
  699. dir: dir isL
  700. -/93: O: O186 (predict-no)
  701. I see 1 and I'm going to do: predict-no
  702. ENV: Agent did: predict-no for direction L in state State-A
  703. In State-A moving L
  704. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  705. predict error 0
  706. dir: dir isR
  707. |\94: O: O187 (predict-yes)
  708. I see 1 and I'm going to do: predict-yes
  709. ENV: Agent did: predict-yes for direction R in state State-A
  710. In State-A moving R
  711. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  712. predict error 0
  713. dir: dir isU
  714. -/|95: O: O190 (predict-no)
  715. I see 1 and I'm going to do: predict-no
  716. ENV: Agent did: predict-no for direction U in state State-B
  717. In State-B moving U
  718. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  719. predict error 0
  720. dir: dir isL
  721. \96: O: O191 (predict-yes)
  722. I see 1 and I'm going to do: predict-yes
  723. ENV: Agent did: predict-yes for direction L in state State-B
  724. In State-B moving L
  725. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  726. predict error 0
  727. dir: dir isL
  728. -/97: O: O194 (predict-no)
  729. I see 1 and I'm going to do: predict-no
  730. ENV: Agent did: predict-no for direction L in state State-A
  731. In State-A moving L
  732. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  733. predict error 0
  734. dir: dir isU
  735. |\98: O: O196 (predict-no)
  736. I see 1 and I'm going to do: predict-no
  737. ENV: Agent did: predict-no for direction U in state State-A
  738. In State-A moving U
  739. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  740. predict error 0
  741. dir: dir isR
  742. -/99: O: O198 (predict-no)
  743. I see 1 and I'm going to do: predict-no
  744. ENV: Agent did: predict-no for direction R in state State-A
  745. In State-A moving R
  746. ENV: (next state, see, prediction correct?) = (State-B, 1, False)
  747. predict error 1
  748. dir: dir isU
  749. |\-100: O: O200 (predict-no)
  750. I see 0 and I'm going to do: predict-no
  751. ENV: Agent did: predict-no for direction U in state State-B
  752. In State-B moving U
  753. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  754. predict error 0
  755. dir: dir isL
  756. /|101: O: O201 (predict-yes)
  757. I see 1 and I'm going to do: predict-yes
  758. ENV: Agent did: predict-yes for direction L in state State-B
  759. In State-B moving L
  760. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  761. predict error 0
  762. dir: dir isR
  763. \-102: O: O203 (predict-yes)
  764. I see 1 and I'm going to do: predict-yes
  765. ENV: Agent did: predict-yes for direction R in state State-A
  766. In State-A moving R
  767. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  768. predict error 0
  769. dir: dir isL
  770. /|\103: O: O205 (predict-yes)
  771. I see 1 and I'm going to do: predict-yes
  772. ENV: Agent did: predict-yes for direction L in state State-B
  773. In State-B moving L
  774. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  775. predict error 0
  776. dir: dir isU
  777. -/|\sleeping...
  778. -104: O: O208 (predict-no)
  779. I see 1 and I'm going to do: predict-no
  780. ENV: Agent did: predict-no for direction U in state State-A
  781. In State-A moving U
  782. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  783. predict error 0
  784. dir: dir isL
  785. /|\-105: O: O210 (predict-no)
  786. I see 1 and I'm going to do: predict-no
  787. ENV: Agent did: predict-no for direction L in state State-A
  788. In State-A moving L
  789. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  790. predict error 0
  791. dir: dir isU
  792. /|106: O: O212 (predict-no)
  793. I see 1 and I'm going to do: predict-no
  794. ENV: Agent did: predict-no for direction U in state State-A
  795. In State-A moving U
  796. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  797. predict error 0
  798. dir: dir isL
  799. \-/107: O: O214 (predict-no)
  800. I see 1 and I'm going to do: predict-no
  801. ENV: Agent did: predict-no for direction L in state State-A
  802. In State-A moving L
  803. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  804. predict error 0
  805. dir: dir isU
  806. |\108: O: O216 (predict-no)
  807. I see 1 and I'm going to do: predict-no
  808. ENV: Agent did: predict-no for direction U in state State-A
  809. In State-A moving U
  810. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  811. predict error 0
  812. dir: dir isL
  813. -/|109: O: O218 (predict-no)
  814. I see 1 and I'm going to do: predict-no
  815. ENV: Agent did: predict-no for direction L in state State-A
  816. In State-A moving L
  817. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  818. predict error 0
  819. dir: dir isL
  820. \-110: O: O220 (predict-no)
  821. I see 1 and I'm going to do: predict-no
  822. ENV: Agent did: predict-no for direction L in state State-A
  823. In State-A moving L
  824. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  825. predict error 0
  826. dir: dir isU
  827. /|111: O: O222 (predict-no)
  828. I see 1 and I'm going to do: predict-no
  829. ENV: Agent did: predict-no for direction U in state State-A
  830. In State-A moving U
  831. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  832. predict error 0
  833. dir: dir isL
  834. rule alias: '*'
  835. \112: O: O224 (predict-no)
  836. I see 1 and I'm going to do: predict-no
  837. ENV: Agent did: predict-no for direction L in state State-A
  838. In State-A moving L
  839. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  840. predict error 0
  841. dir: dir isL
  842. -/113: O: O226 (predict-no)
  843. I see 1 and I'm going to do: predict-no
  844. ENV: Agent did: predict-no for direction L in state State-A
  845. In State-A moving L
  846. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  847. predict error 0
  848. dir: dir isU
  849. |\114: O: O228 (predict-no)
  850. I see 1 and I'm going to do: predict-no
  851. ENV: Agent did: predict-no for direction U in state State-A
  852. In State-A moving U
  853. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  854. predict error 0
  855. dir: dir isR
  856. -/|115: O: O229 (predict-yes)
  857. I see 1 and I'm going to do: predict-yes
  858. ENV: Agent did: predict-yes for direction R in state State-A
  859. In State-A moving R
  860. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  861. predict error 0
  862. dir: dir isL
  863. \-116: O: O231 (predict-yes)
  864. I see 1 and I'm going to do: predict-yes
  865. ENV: Agent did: predict-yes for direction L in state State-B
  866. In State-B moving L
  867. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  868. predict error 0
  869. dir: dir isU
  870. /|117: O: O234 (predict-no)
  871. I see 1 and I'm going to do: predict-no
  872. ENV: Agent did: predict-no for direction U in state State-A
  873. In State-A moving U
  874. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  875. predict error 0
  876. dir: dir isL
  877. \-118: O: O236 (predict-no)
  878. I see 1 and I'm going to do: predict-no
  879. ENV: Agent did: predict-no for direction L in state State-A
  880. In State-A moving L
  881. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  882. predict error 0
  883. dir: dir isL
  884. /|\119: O: O238 (predict-no)
  885. I see 1 and I'm going to do: predict-no
  886. ENV: Agent did: predict-no for direction L in state State-A
  887. In State-A moving L
  888. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  889. predict error 0
  890. dir: dir isR
  891. -/|120: O: O239 (predict-yes)
  892. I see 1 and I'm going to do: predict-yes
  893. ENV: Agent did: predict-yes for direction R in state State-A
  894. In State-A moving R
  895. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  896. predict error 0
  897. dir: dir isR
  898. \-/|sleeping...
  899. \121: O: O241 (predict-yes)
  900. I see 1 and I'm going to do: predict-yes
  901. ENV: Agent did: predict-yes for direction R in state State-B
  902. In State-B moving R
  903. ENV: (next state, see, prediction correct?) = (State-B, 0, False)
  904. predict error 1
  905. dir: dir isU
  906. -122: O: O244 (predict-no)
  907. I see 0 and I'm going to do: predict-no
  908. ENV: Agent did: predict-no for direction U in state State-B
  909. In State-B moving U
  910. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  911. predict error 0
  912. dir: dir isL
  913. /|\123: O: O245 (predict-yes)
  914. I see 1 and I'm going to do: predict-yes
  915. ENV: Agent did: predict-yes for direction L in state State-B
  916. In State-B moving L
  917. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  918. predict error 0
  919. dir: dir isR
  920. -/124: O: O248 (predict-no)
  921. I see 1 and I'm going to do: predict-no
  922. ENV: Agent did: predict-no for direction R in state State-A
  923. In State-A moving R
  924. ENV: (next state, see, prediction correct?) = (State-B, 1, False)
  925. predict error 1
  926. dir: dir isL
  927. |\-125: O: O249 (predict-yes)
  928. I see 0 and I'm going to do: predict-yes
  929. ENV: Agent did: predict-yes for direction L in state State-B
  930. In State-B moving L
  931. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  932. predict error 0
  933. dir: dir isR
  934. /|\126: O: O251 (predict-yes)
  935. I see 1 and I'm going to do: predict-yes
  936. ENV: Agent did: predict-yes for direction R in state State-A
  937. In State-A moving R
  938. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  939. predict error 0
  940. dir: dir isU
  941. -/127: O: O254 (predict-no)
  942. I see 1 and I'm going to do: predict-no
  943. ENV: Agent did: predict-no for direction U in state State-B
  944. In State-B moving U
  945. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  946. predict error 0
  947. dir: dir isU
  948. |\-128: O: O256 (predict-no)
  949. I see 1 and I'm going to do: predict-no
  950. ENV: Agent did: predict-no for direction U in state State-B
  951. In State-B moving U
  952. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  953. predict error 0
  954. dir: dir isU
  955. /|129: O: O258 (predict-no)
  956. I see 1 and I'm going to do: predict-no
  957. ENV: Agent did: predict-no for direction U in state State-B
  958. In State-B moving U
  959. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  960. predict error 0
  961. dir: dir isU
  962. \-/130: O: O259 (predict-yes)
  963. I see 1 and I'm going to do: predict-yes
  964. ENV: Agent did: predict-yes for direction U in state State-B
  965. In State-B moving U
  966. ENV: (next state, see, prediction correct?) = (State-B, 0, False)
  967. predict error 1
  968. dir: dir isU
  969. |\131: O: O262 (predict-no)
  970. I see 0 and I'm going to do: predict-no
  971. ENV: Agent did: predict-no for direction U in state State-B
  972. In State-B moving U
  973. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  974. predict error 0
  975. dir: dir isU
  976. -132: O: O264 (predict-no)
  977. I see 1 and I'm going to do: predict-no
  978. ENV: Agent did: predict-no for direction U in state State-B
  979. In State-B moving U
  980. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  981. predict error 0
  982. dir: dir isR
  983. /|\133: O: O265 (predict-yes)
  984. I see 1 and I'm going to do: predict-yes
  985. ENV: Agent did: predict-yes for direction R in state State-B
  986. In State-B moving R
  987. ENV: (next state, see, prediction correct?) = (State-B, 0, False)
  988. predict error 1
  989. dir: dir isL
  990. -/|134: O: O267 (predict-yes)
  991. I see 0 and I'm going to do: predict-yes
  992. ENV: Agent did: predict-yes for direction L in state State-B
  993. In State-B moving L
  994. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  995. predict error 0
  996. dir: dir isR
  997. \-/135: O: O269 (predict-yes)
  998. I see 1 and I'm going to do: predict-yes
  999. ENV: Agent did: predict-yes for direction R in state State-A
  1000. In State-A moving R
  1001. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  1002. predict error 0
  1003. dir: dir isL
  1004. |\136: O: O271 (predict-yes)
  1005. I see 1 and I'm going to do: predict-yes
  1006. ENV: Agent did: predict-yes for direction L in state State-B
  1007. In State-B moving L
  1008. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  1009. predict error 0
  1010. dir: dir isL
  1011. -/|137: O: O274 (predict-no)
  1012. I see 1 and I'm going to do: predict-no
  1013. ENV: Agent did: predict-no for direction L in state State-A
  1014. In State-A moving L
  1015. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  1016. predict error 0
  1017. dir: dir isR
  1018. \-/138: O: O275 (predict-yes)
  1019. I see 1 and I'm going to do: predict-yes
  1020. ENV: Agent did: predict-yes for direction R in state State-A
  1021. In State-A moving R
  1022. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  1023. predict error 0
  1024. dir: dir isU
  1025. |\-139: O: O278 (predict-no)
  1026. I see 1 and I'm going to do: predict-no
  1027. ENV: Agent did: predict-no for direction U in state State-B
  1028. In State-B moving U
  1029. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  1030. predict error 0
  1031. dir: dir isL
  1032. /|\140: O: O279 (predict-yes)
  1033. I see 1 and I'm going to do: predict-yes
  1034. ENV: Agent did: predict-yes for direction L in state State-B
  1035. In State-B moving L
  1036. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  1037. predict error 0
  1038. dir: dir isR
  1039. -/|141: O: O281 (predict-yes)
  1040. I see 1 and I'm going to do: predict-yes
  1041. ENV: Agent did: predict-yes for direction R in state State-A
  1042. In State-A moving R
  1043. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  1044. predict error 0
  1045. dir: dir isR
  1046. \142: O: O284 (predict-no)
  1047. I see 1 and I'm going to do: predict-no
  1048. ENV: Agent did: predict-no for direction R in state State-B
  1049. In State-B moving R
  1050. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  1051. predict error 0
  1052. dir: dir isR
  1053. -/143: O: O286 (predict-no)
  1054. I see 1 and I'm going to do: predict-no
  1055. ENV: Agent did: predict-no for direction R in state State-B
  1056. In State-B moving R
  1057. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  1058. predict error 0
  1059. dir: dir isL
  1060. |\-144: O: O287 (predict-yes)
  1061. I see 1 and I'm going to do: predict-yes
  1062. ENV: Agent did: predict-yes for direction L in state State-B
  1063. In State-B moving L
  1064. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  1065. predict error 0
  1066. dir: dir isU
  1067. /|\145: O: O290 (predict-no)
  1068. I see 1 and I'm going to do: predict-no
  1069. ENV: Agent did: predict-no for direction U in state State-A
  1070. In State-A moving U
  1071. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  1072. predict error 0
  1073. dir: dir isL
  1074. -/|146: O: O292 (predict-no)
  1075. I see 1 and I'm going to do: predict-no
  1076. ENV: Agent did: predict-no for direction L in state State-A
  1077. In State-A moving L
  1078. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  1079. predict error 0
  1080. dir: dir isR
  1081. \-/147: O: O293 (predict-yes)
  1082. I see 1 and I'm going to do: predict-yes
  1083. ENV: Agent did: predict-yes for direction R in state State-A
  1084. In State-A moving R
  1085. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  1086. predict error 0
  1087. dir: dir isR
  1088. |\-148: O: O296 (predict-no)
  1089. I see 1 and I'm going to do: predict-no
  1090. ENV: Agent did: predict-no for direction R in state State-B
  1091. In State-B moving R
  1092. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  1093. predict error 0
  1094. dir: dir isL
  1095. /|\149: O: O297 (predict-yes)
  1096. I see 1 and I'm going to do: predict-yes
  1097. ENV: Agent did: predict-yes for direction L in state State-B
  1098. In State-B moving L
  1099. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  1100. predict error 0
  1101. dir: dir isR
  1102. -/|150: O: O299 (predict-yes)
  1103. I see 1 and I'm going to do: predict-yes
  1104. ENV: Agent did: predict-yes for direction R in state State-A
  1105. In State-A moving R
  1106. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  1107. predict error 0
  1108. dir: dir isL
  1109. \-151: O: O301 (predict-yes)
  1110. I see 1 and I'm going to do: predict-yes
  1111. ENV: Agent did: predict-yes for direction L in state State-B
  1112. In State-B moving L
  1113. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  1114. predict error 0
  1115. dir: dir isL
  1116. /152: O: O304 (predict-no)
  1117. I see 1 and I'm going to do: predict-no
  1118. ENV: Agent did: predict-no for direction L in state State-A
  1119. In State-A moving L
  1120. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  1121. predict error 0
  1122. dir: dir isL
  1123. |\-/153: O: O306 (predict-no)
  1124. I see 1 and I'm going to do: predict-no
  1125. ENV: Agent did: predict-no for direction L in state State-A
  1126. In State-A moving L
  1127. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  1128. predict error 0
  1129. dir: dir isL
  1130. |\154: O: O308 (predict-no)
  1131. I see 1 and I'm going to do: predict-no
  1132. ENV: Agent did: predict-no for direction L in state State-A
  1133. In State-A moving L
  1134. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  1135. predict error 0
  1136. dir: dir isL
  1137. -/|155: O: O310 (predict-no)
  1138. I see 1 and I'm going to do: predict-no
  1139. ENV: Agent did: predict-no for direction L in state State-A
  1140. In State-A moving L
  1141. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  1142. predict error 0
  1143. dir: dir isR
  1144. \-/156: O: O311 (predict-yes)
  1145. I see 1 and I'm going to do: predict-yes
  1146. ENV: Agent did: predict-yes for direction R in state State-A
  1147. In State-A moving R
  1148. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  1149. predict error 0
  1150. dir: dir isR
  1151. |\157: O: O314 (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-B
  1154. In State-B moving R
  1155. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  1156. predict error 0
  1157. dir: dir isU
  1158. -/|158: O: O316 (predict-no)
  1159. I see 1 and I'm going to do: predict-no
  1160. ENV: Agent did: predict-no for direction U in state State-B
  1161. In State-B moving U
  1162. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  1163. predict error 0
  1164. dir: dir isU
  1165. \-/159: O: O318 (predict-no)
  1166. I see 1 and I'm going to do: predict-no
  1167. ENV: Agent did: predict-no for direction U in state State-B
  1168. In State-B moving U
  1169. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  1170. predict error 0
  1171. dir: dir isU
  1172. |\-160: O: O320 (predict-no)
  1173. I see 1 and I'm going to do: predict-no
  1174. ENV: Agent did: predict-no for direction U in state State-B
  1175. In State-B moving U
  1176. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  1177. predict error 0
  1178. dir: dir isL
  1179. /|\161: O: O321 (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. -162: O: O323 (predict-yes)
  1187. I see 1 and I'm going to do: predict-yes
  1188. ENV: Agent did: predict-yes for direction R in state State-A
  1189. In State-A moving R
  1190. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  1191. predict error 0
  1192. dir: dir isL
  1193. /|\-163: O: O325 (predict-yes)
  1194. I see 1 and I'm going to do: predict-yes
  1195. ENV: Agent did: predict-yes for direction L in state State-B
  1196. In State-B moving L
  1197. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  1198. predict error 0
  1199. dir: dir isR
  1200. /|\164: O: O327 (predict-yes)
  1201. I see 1 and I'm going to do: predict-yes
  1202. ENV: Agent did: predict-yes for direction R in state State-A
  1203. In State-A moving R
  1204. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  1205. predict error 0
  1206. dir: dir isR
  1207. -/|165: O: O329 (predict-yes)
  1208. I see 1 and I'm going to do: predict-yes
  1209. ENV: Agent did: predict-yes for direction R in state State-B
  1210. In State-B moving R
  1211. ENV: (next state, see, prediction correct?) = (State-B, 0, False)
  1212. predict error 1
  1213. dir: dir isU
  1214. \-166: O: O332 (predict-no)
  1215. I see 0 and I'm going to do: predict-no
  1216. ENV: Agent did: predict-no for direction U in state State-B
  1217. In State-B moving U
  1218. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  1219. predict error 0
  1220. dir: dir isU
  1221. /|\167: O: O334 (predict-no)
  1222. I see 1 and I'm going to do: predict-no
  1223. ENV: Agent did: predict-no for direction U in state State-B
  1224. In State-B moving U
  1225. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  1226. predict error 0
  1227. dir: dir isL
  1228. -/|168: O: O335 (predict-yes)
  1229. I see 1 and I'm going to do: predict-yes
  1230. ENV: Agent did: predict-yes for direction L in state State-B
  1231. In State-B moving L
  1232. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  1233. predict error 0
  1234. dir: dir isR
  1235. \-/169: O: O337 (predict-yes)
  1236. I see 1 and I'm going to do: predict-yes
  1237. ENV: Agent did: predict-yes for direction R in state State-A
  1238. In State-A moving R
  1239. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  1240. predict error 0
  1241. dir: dir isR
  1242. |\170: O: O340 (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-B
  1245. In State-B moving R
  1246. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  1247. predict error 0
  1248. dir: dir isL
  1249. -/171: O: O342 (predict-no)
  1250. I see 1 and I'm going to do: predict-no
  1251. ENV: Agent did: predict-no for direction L in state State-B
  1252. In State-B moving L
  1253. ENV: (next state, see, prediction correct?) = (State-A, 1, False)
  1254. predict error 1
  1255. dir: dir isL
  1256. |172: O: O344 (predict-no)
  1257. I see 0 and I'm going to do: predict-no
  1258. ENV: Agent did: predict-no for direction L in state State-A
  1259. In State-A moving L
  1260. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  1261. predict error 0
  1262. dir: dir isR
  1263. \-/173: O: O345 (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. |\-174: O: O347 (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 isU
  1277. /|\175: O: O350 (predict-no)
  1278. I see 1 and I'm going to do: predict-no
  1279. ENV: Agent did: predict-no for direction U in state State-A
  1280. In State-A moving U
  1281. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  1282. predict error 0
  1283. dir: dir isL
  1284. -/|176: O: O352 (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 isL
  1291. \-177: O: O354 (predict-no)
  1292. I see 1 and I'm going to do: predict-no
  1293. ENV: Agent did: predict-no for direction L in state State-A
  1294. In State-A moving L
  1295. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  1296. predict error 0
  1297. dir: dir isL
  1298. /|178: O: O356 (predict-no)
  1299. I see 1 and I'm going to do: predict-no
  1300. ENV: Agent did: predict-no for direction L in state State-A
  1301. In State-A moving L
  1302. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  1303. predict error 0
  1304. dir: dir isL
  1305. \-/179: O: O358 (predict-no)
  1306. I see 1 and I'm going to do: predict-no
  1307. ENV: Agent did: predict-no for direction L in state State-A
  1308. In State-A moving L
  1309. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  1310. predict error 0
  1311. dir: dir isL
  1312. |\-180: O: O360 (predict-no)
  1313. I see 1 and I'm going to do: predict-no
  1314. ENV: Agent did: predict-no for direction L in state State-A
  1315. In State-A moving L
  1316. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  1317. predict error 0
  1318. dir: dir isR
  1319. /|181: O: O361 (predict-yes)
  1320. I see 1 and I'm going to do: predict-yes
  1321. ENV: Agent did: predict-yes for direction R in state State-A
  1322. In State-A moving R
  1323. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  1324. predict error 0
  1325. dir: dir isR
  1326. \182: O: O364 (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 isL
  1333. -/|183: O: O365 (predict-yes)
  1334. I see 1 and I'm going to do: predict-yes
  1335. ENV: Agent did: predict-yes for direction L in state State-B
  1336. In State-B moving L
  1337. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  1338. predict error 0
  1339. dir: dir isR
  1340. \-/184: O: O367 (predict-yes)
  1341. I see 1 and I'm going to do: predict-yes
  1342. ENV: Agent did: predict-yes for direction R in state State-A
  1343. In State-A moving R
  1344. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  1345. predict error 0
  1346. dir: dir isL
  1347. |\-185: O: O369 (predict-yes)
  1348. I see 1 and I'm going to do: predict-yes
  1349. ENV: Agent did: predict-yes for direction L in state State-B
  1350. In State-B moving L
  1351. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  1352. predict error 0
  1353. dir: dir isU
  1354. /|186: O: O372 (predict-no)
  1355. I see 1 and I'm going to do: predict-no
  1356. ENV: Agent did: predict-no for direction U in state State-A
  1357. In State-A moving U
  1358. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  1359. predict error 0
  1360. dir: dir isU
  1361. \-/187: O: O374 (predict-no)
  1362. I see 1 and I'm going to do: predict-no
  1363. ENV: Agent did: predict-no for direction U in state State-A
  1364. In State-A moving U
  1365. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  1366. predict error 0
  1367. dir: dir isU
  1368. |\188: O: O376 (predict-no)
  1369. I see 1 and I'm going to do: predict-no
  1370. ENV: Agent did: predict-no for direction U in state State-A
  1371. In State-A moving U
  1372. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  1373. predict error 0
  1374. dir: dir isR
  1375. -/|189: O: O378 (predict-no)
  1376. I see 1 and I'm going to do: predict-no
  1377. ENV: Agent did: predict-no for direction R in state State-A
  1378. In State-A moving R
  1379. ENV: (next state, see, prediction correct?) = (State-B, 1, False)
  1380. predict error 1
  1381. dir: dir isR
  1382. \-190: O: O380 (predict-no)
  1383. I see 0 and I'm going to do: predict-no
  1384. ENV: Agent did: predict-no for direction R in state State-B
  1385. In State-B moving R
  1386. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  1387. predict error 0
  1388. dir: dir isR
  1389. /|\191: O: O382 (predict-no)
  1390. I see 1 and I'm going to do: predict-no
  1391. ENV: Agent did: predict-no for direction R in state State-B
  1392. In State-B moving R
  1393. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  1394. predict error 0
  1395. dir: dir isL
  1396. -192: O: O383 (predict-yes)
  1397. I see 1 and I'm going to do: predict-yes
  1398. ENV: Agent did: predict-yes for direction L in state State-B
  1399. In State-B moving L
  1400. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  1401. predict error 0
  1402. dir: dir isR
  1403. /|193: O: O385 (predict-yes)
  1404. I see 1 and I'm going to do: predict-yes
  1405. ENV: Agent did: predict-yes for direction R in state State-A
  1406. In State-A moving R
  1407. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  1408. predict error 0
  1409. dir: dir isR
  1410. \194: O: O388 (predict-no)
  1411. I see 1 and I'm going to do: predict-no
  1412. ENV: Agent did: predict-no for direction R in state State-B
  1413. In State-B moving R
  1414. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  1415. predict error 0
  1416. dir: dir isL
  1417. -/|195: O: O389 (predict-yes)
  1418. I see 1 and I'm going to do: predict-yes
  1419. ENV: Agent did: predict-yes for direction L in state State-B
  1420. In State-B moving L
  1421. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  1422. predict error 0
  1423. dir: dir isL
  1424. \-/196: O: O392 (predict-no)
  1425. I see 1 and I'm going to do: predict-no
  1426. ENV: Agent did: predict-no for direction L in state State-A
  1427. In State-A moving L
  1428. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  1429. predict error 0
  1430. dir: dir isU
  1431. |\-197: O: O394 (predict-no)
  1432. I see 1 and I'm going to do: predict-no
  1433. ENV: Agent did: predict-no for direction U in state State-A
  1434. In State-A moving U
  1435. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  1436. predict error 0
  1437. dir: dir isR
  1438. /|198: O: O395 (predict-yes)
  1439. I see 1 and I'm going to do: predict-yes
  1440. ENV: Agent did: predict-yes for direction R in state State-A
  1441. In State-A moving R
  1442. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  1443. predict error 0
  1444. dir: dir isR
  1445. \-199: O: O398 (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 isU
  1452. /|\200: O: O400 (predict-no)
  1453. I see 1 and I'm going to do: predict-no
  1454. ENV: Agent did: predict-no for direction U in state State-B
  1455. In State-B moving U
  1456. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  1457. predict error 0
  1458. dir: dir isR
  1459. -/|\-201: O: O402 (predict-no)
  1460. I see 1 and I'm going to do: predict-no
  1461. ENV: Agent did: predict-no for direction R in state State-B
  1462. In State-B moving R
  1463. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  1464. predict error 0
  1465. dir: dir isL
  1466. /202: O: O403 (predict-yes)
  1467. I see 1 and I'm going to do: predict-yes
  1468. ENV: Agent did: predict-yes for direction L in state State-B
  1469. In State-B moving L
  1470. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  1471. predict error 0
  1472. dir: dir isU
  1473. |\-203: O: O406 (predict-no)
  1474. I see 1 and I'm going to do: predict-no
  1475. ENV: Agent did: predict-no for direction U in state State-A
  1476. In State-A moving U
  1477. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  1478. predict error 0
  1479. dir: dir isR
  1480. /|\204: O: O407 (predict-yes)
  1481. I see 1 and I'm going to do: predict-yes
  1482. ENV: Agent did: predict-yes for direction R in state State-A
  1483. In State-A moving R
  1484. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  1485. predict error 0
  1486. dir: dir isL
  1487. -/|205: O: O409 (predict-yes)
  1488. I see 1 and I'm going to do: predict-yes
  1489. ENV: Agent did: predict-yes for direction L in state State-B
  1490. In State-B moving L
  1491. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  1492. predict error 0
  1493. dir: dir isU
  1494. \-206: O: O412 (predict-no)
  1495. I see 1 and I'm going to do: predict-no
  1496. ENV: Agent did: predict-no for direction U in state State-A
  1497. In State-A moving U
  1498. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  1499. predict error 0
  1500. dir: dir isL
  1501. /|207: O: O414 (predict-no)
  1502. I see 1 and I'm going to do: predict-no
  1503. ENV: Agent did: predict-no for direction L in state State-A
  1504. In State-A moving L
  1505. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  1506. predict error 0
  1507. dir: dir isL
  1508. \208: O: O415 (predict-yes)
  1509. I see 1 and I'm going to do: predict-yes
  1510. ENV: Agent did: predict-yes for direction L in state State-A
  1511. In State-A moving L
  1512. ENV: (next state, see, prediction correct?) = (State-A, 0, False)
  1513. predict error 1
  1514. dir: dir isU
  1515. -/209: O: O418 (predict-no)
  1516. I see 0 and I'm going to do: predict-no
  1517. ENV: Agent did: predict-no for direction U in state State-A
  1518. In State-A moving U
  1519. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  1520. predict error 0
  1521. dir: dir isU
  1522. |210: O: O420 (predict-no)
  1523. I see 1 and I'm going to do: predict-no
  1524. ENV: Agent did: predict-no for direction U in state State-A
  1525. In State-A moving U
  1526. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  1527. predict error 0
  1528. dir: dir isL
  1529. \-211: O: O422 (predict-no)
  1530. I see 1 and I'm going to do: predict-no
  1531. ENV: Agent did: predict-no for direction L in state State-A
  1532. In State-A moving L
  1533. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  1534. predict error 0
  1535. dir: dir isR
  1536. /212: O: O423 (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 isR
  1543. |\-213: O: O426 (predict-no)
  1544. I see 1 and I'm going to do: predict-no
  1545. ENV: Agent did: predict-no for direction R in state State-B
  1546. In State-B moving R
  1547. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  1548. predict error 0
  1549. dir: dir isR
  1550. /|\214: O: O428 (predict-no)
  1551. I see 1 and I'm going to do: predict-no
  1552. ENV: Agent did: predict-no for direction R in state State-B
  1553. In State-B moving R
  1554. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  1555. predict error 0
  1556. dir: dir isL
  1557. -/|215: O: O429 (predict-yes)
  1558. I see 1 and I'm going to do: predict-yes
  1559. ENV: Agent did: predict-yes for direction L in state State-B
  1560. In State-B moving L
  1561. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  1562. predict error 0
  1563. dir: dir isR
  1564. \-/216: O: O431 (predict-yes)
  1565. I see 1 and I'm going to do: predict-yes
  1566. ENV: Agent did: predict-yes for direction R in state State-A
  1567. In State-A moving R
  1568. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  1569. predict error 0
  1570. dir: dir isL
  1571. |\-217: O: O433 (predict-yes)
  1572. I see 1 and I'm going to do: predict-yes
  1573. ENV: Agent did: predict-yes for direction L in state State-B
  1574. In State-B moving L
  1575. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  1576. predict error 0
  1577. dir: dir isL
  1578. /|\218: O: O436 (predict-no)
  1579. I see 1 and I'm going to do: predict-no
  1580. ENV: Agent did: predict-no for direction L in state State-A
  1581. In State-A moving L
  1582. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  1583. predict error 0
  1584. dir: dir isR
  1585. -/|\219: O: O437 (predict-yes)
  1586. I see 1 and I'm going to do: predict-yes
  1587. ENV: Agent did: predict-yes for direction R in state State-A
  1588. In State-A moving R
  1589. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  1590. predict error 0
  1591. dir: dir isU
  1592. -/|220: O: O440 (predict-no)
  1593. I see 1 and I'm going to do: predict-no
  1594. ENV: Agent did: predict-no for direction U in state State-B
  1595. In State-B moving U
  1596. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  1597. predict error 0
  1598. dir: dir isL
  1599. \-221: O: O441 (predict-yes)
  1600. I see 1 and I'm going to do: predict-yes
  1601. ENV: Agent did: predict-yes for direction L in state State-B
  1602. In State-B moving L
  1603. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  1604. predict error 0
  1605. dir: dir isU
  1606. /222: O: O444 (predict-no)
  1607. I see 1 and I'm going to do: predict-no
  1608. ENV: Agent did: predict-no for direction U in state State-A
  1609. In State-A moving U
  1610. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  1611. predict error 0
  1612. dir: dir isL
  1613. |\223: O: O446 (predict-no)
  1614. I see 1 and I'm going to do: predict-no
  1615. ENV: Agent did: predict-no for direction L in state State-A
  1616. In State-A moving L
  1617. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  1618. predict error 0
  1619. dir: dir isR
  1620. -/224: O: O447 (predict-yes)
  1621. I see 1 and I'm going to do: predict-yes
  1622. ENV: Agent did: predict-yes for direction R in state State-A
  1623. In State-A moving R
  1624. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  1625. predict error 0
  1626. dir: dir isR
  1627. |\225: O: O449 (predict-yes)
  1628. I see 1 and I'm going to do: predict-yes
  1629. ENV: Agent did: predict-yes for direction R in state State-B
  1630. In State-B moving R
  1631. ENV: (next state, see, prediction correct?) = (State-B, 0, False)
  1632. predict error 1
  1633. dir: dir isR
  1634. -/|226: O: O452 (predict-no)
  1635. I see 0 and I'm going to do: predict-no
  1636. ENV: Agent did: predict-no for direction R in state State-B
  1637. In State-B moving R
  1638. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  1639. predict error 0
  1640. dir: dir isU
  1641. \-/227: O: O454 (predict-no)
  1642. I see 1 and I'm going to do: predict-no
  1643. ENV: Agent did: predict-no for direction U in state State-B
  1644. In State-B moving U
  1645. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  1646. predict error 0
  1647. dir: dir isR
  1648. |\-228: O: O456 (predict-no)
  1649. I see 1 and I'm going to do: predict-no
  1650. ENV: Agent did: predict-no for direction R in state State-B
  1651. In State-B moving R
  1652. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  1653. predict error 0
  1654. dir: dir isL
  1655. /|\229: O: O457 (predict-yes)
  1656. I see 1 and I'm going to do: predict-yes
  1657. ENV: Agent did: predict-yes for direction L in state State-B
  1658. In State-B moving L
  1659. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  1660. predict error 0
  1661. dir: dir isL
  1662. -/|230: O: O460 (predict-no)
  1663. I see 1 and I'm going to do: predict-no
  1664. ENV: Agent did: predict-no for direction L in state State-A
  1665. In State-A moving L
  1666. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  1667. predict error 0
  1668. dir: dir isL
  1669. \-/231: O: O462 (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 isU
  1676. |232: O: O464 (predict-no)
  1677. I see 1 and I'm going to do: predict-no
  1678. ENV: Agent did: predict-no for direction U in state State-A
  1679. In State-A moving U
  1680. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  1681. predict error 0
  1682. dir: dir isR
  1683. \-/233: O: O465 (predict-yes)
  1684. I see 1 and I'm going to do: predict-yes
  1685. ENV: Agent did: predict-yes for direction R in state State-A
  1686. In State-A moving R
  1687. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  1688. predict error 0
  1689. dir: dir isU
  1690. |\-234: O: O468 (predict-no)
  1691. I see 1 and I'm going to do: predict-no
  1692. ENV: Agent did: predict-no for direction U in state State-B
  1693. In State-B moving U
  1694. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  1695. predict error 0
  1696. dir: dir isU
  1697. /|\235: O: O470 (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-B
  1700. In State-B moving U
  1701. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  1702. predict error 0
  1703. dir: dir isL
  1704. -/|236: O: O471 (predict-yes)
  1705. I see 1 and I'm going to do: predict-yes
  1706. ENV: Agent did: predict-yes for direction L in state State-B
  1707. In State-B moving L
  1708. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  1709. predict error 0
  1710. dir: dir isR
  1711. \-/237: O: O474 (predict-no)
  1712. I see 1 and I'm going to do: predict-no
  1713. ENV: Agent did: predict-no for direction R in state State-A
  1714. In State-A moving R
  1715. ENV: (next state, see, prediction correct?) = (State-B, 1, False)
  1716. predict error 1
  1717. dir: dir isU
  1718. |\-238: O: O476 (predict-no)
  1719. I see 0 and I'm going to do: predict-no
  1720. ENV: Agent did: predict-no for direction U in state State-B
  1721. In State-B moving U
  1722. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  1723. predict error 0
  1724. dir: dir isU
  1725. /|239: O: O478 (predict-no)
  1726. I see 1 and I'm going to do: predict-no
  1727. ENV: Agent did: predict-no for direction U in state State-B
  1728. In State-B moving U
  1729. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  1730. predict error 0
  1731. dir: dir isR
  1732. \-/240: O: O480 (predict-no)
  1733. I see 1 and I'm going to do: predict-no
  1734. ENV: Agent did: predict-no for direction R in state State-B
  1735. In State-B moving R
  1736. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  1737. predict error 0
  1738. dir: dir isR
  1739. |\-241: O: O481 (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-B
  1742. In State-B moving R
  1743. ENV: (next state, see, prediction correct?) = (State-B, 0, False)
  1744. predict error 1
  1745. dir: dir isR
  1746. /242: O: O484 (predict-no)
  1747. I see 0 and I'm going to do: predict-no
  1748. ENV: Agent did: predict-no for direction R in state State-B
  1749. In State-B moving R
  1750. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  1751. predict error 0
  1752. dir: dir isU
  1753. |\-243: O: O486 (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. /|244: O: O487 (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. \-245: O: O489 (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. /246: O: O491 (predict-yes)
  1775. I see 1 and I'm going to do: predict-yes
  1776. ENV: Agent did: predict-yes for direction R in state State-B
  1777. In State-B moving R
  1778. ENV: (next state, see, prediction correct?) = (State-B, 0, False)
  1779. predict error 1
  1780. dir: dir isU
  1781. |\-247: O: O494 (predict-no)
  1782. I see 0 and I'm going to do: predict-no
  1783. ENV: Agent did: predict-no for direction U in state State-B
  1784. In State-B moving U
  1785. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  1786. predict error 0
  1787. dir: dir isU
  1788. /|\248: O: O496 (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 isU
  1795. -/|\249: O: O498 (predict-no)
  1796. I see 1 and I'm going to do: predict-no
  1797. ENV: Agent did: predict-no for direction U in state State-B
  1798. In State-B moving U
  1799. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  1800. predict error 0
  1801. dir: dir isU
  1802. -/|250: O: O500 (predict-no)
  1803. I see 1 and I'm going to do: predict-no
  1804. ENV: Agent did: predict-no for direction U in state State-B
  1805. In State-B moving U
  1806. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  1807. predict error 0
  1808. dir: dir isL
  1809. \-/251: O: O501 (predict-yes)
  1810. I see 1 and I'm going to do: predict-yes
  1811. ENV: Agent did: predict-yes for direction L in state State-B
  1812. In State-B moving L
  1813. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  1814. predict error 0
  1815. dir: dir isL
  1816. |252: O: O504 (predict-no)
  1817. I see 1 and I'm going to do: predict-no
  1818. ENV: Agent did: predict-no for direction L in state State-A
  1819. In State-A moving L
  1820. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  1821. predict error 0
  1822. dir: dir isR
  1823. \-/|253: O: O506 (predict-no)
  1824. I see 1 and I'm going to do: predict-no
  1825. ENV: Agent did: predict-no for direction R in state State-A
  1826. In State-A moving R
  1827. ENV: (next state, see, prediction correct?) = (State-B, 1, False)
  1828. predict error 1
  1829. dir: dir isL
  1830. \-254: O: O508 (predict-no)
  1831. I see 0 and I'm going to do: predict-no
  1832. ENV: Agent did: predict-no for direction L in state State-B
  1833. In State-B moving L
  1834. ENV: (next state, see, prediction correct?) = (State-A, 1, False)
  1835. predict error 1
  1836. dir: dir isR
  1837. /|\255: O: O509 (predict-yes)
  1838. I see 0 and I'm going to do: predict-yes
  1839. ENV: Agent did: predict-yes for direction R in state State-A
  1840. In State-A moving R
  1841. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  1842. predict error 0
  1843. dir: dir isU
  1844. -/|\sleeping...
  1845. -256: O: O511 (predict-yes)
  1846. I see 1 and I'm going to do: predict-yes
  1847. ENV: Agent did: predict-yes for direction U in state State-B
  1848. In State-B moving U
  1849. ENV: (next state, see, prediction correct?) = (State-B, 0, False)
  1850. predict error 1
  1851. dir: dir isU
  1852. /|\257: O: O514 (predict-no)
  1853. I see 0 and I'm going to do: predict-no
  1854. ENV: Agent did: predict-no for direction U in state State-B
  1855. In State-B moving U
  1856. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  1857. predict error 0
  1858. dir: dir isR
  1859. -/258: O: O516 (predict-no)
  1860. I see 1 and I'm going to do: predict-no
  1861. ENV: Agent did: predict-no for direction R in state State-B
  1862. In State-B moving R
  1863. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  1864. predict error 0
  1865. dir: dir isU
  1866. |259: O: O517 (predict-yes)
  1867. I see 1 and I'm going to do: predict-yes
  1868. ENV: Agent did: predict-yes for direction U in state State-B
  1869. In State-B moving U
  1870. ENV: (next state, see, prediction correct?) = (State-B, 0, False)
  1871. predict error 1
  1872. dir: dir isL
  1873. \-/260: O: O519 (predict-yes)
  1874. I see 0 and I'm going to do: predict-yes
  1875. ENV: Agent did: predict-yes for direction L in state State-B
  1876. In State-B moving L
  1877. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  1878. predict error 0
  1879. dir: dir isR
  1880. |\261: O: O521 (predict-yes)
  1881. I see 1 and I'm going to do: predict-yes
  1882. ENV: Agent did: predict-yes for direction R in state State-A
  1883. In State-A moving R
  1884. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  1885. predict error 0
  1886. dir: dir isU
  1887. -262: O: O524 (predict-no)
  1888. I see 1 and I'm going to do: predict-no
  1889. ENV: Agent did: predict-no for direction U in state State-B
  1890. In State-B moving U
  1891. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  1892. predict error 0
  1893. dir: dir isL
  1894. /|263: O: O525 (predict-yes)
  1895. I see 1 and I'm going to do: predict-yes
  1896. ENV: Agent did: predict-yes for direction L in state State-B
  1897. In State-B moving L
  1898. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  1899. predict error 0
  1900. dir: dir isR
  1901. \-/264: O: O527 (predict-yes)
  1902. I see 1 and I'm going to do: predict-yes
  1903. ENV: Agent did: predict-yes for direction R in state State-A
  1904. In State-A moving R
  1905. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  1906. predict error 0
  1907. dir: dir isL
  1908. |\-265: O: O529 (predict-yes)
  1909. I see 1 and I'm going to do: predict-yes
  1910. ENV: Agent did: predict-yes for direction L in state State-B
  1911. In State-B moving L
  1912. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  1913. predict error 0
  1914. dir: dir isL
  1915. /|\266: O: O532 (predict-no)
  1916. I see 1 and I'm going to do: predict-no
  1917. ENV: Agent did: predict-no for direction L in state State-A
  1918. In State-A moving L
  1919. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  1920. predict error 0
  1921. dir: dir isU
  1922. -/267: O: O534 (predict-no)
  1923. I see 1 and I'm going to do: predict-no
  1924. ENV: Agent did: predict-no for direction U in state State-A
  1925. In State-A moving U
  1926. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  1927. predict error 0
  1928. dir: dir isU
  1929. |\268: O: O536 (predict-no)
  1930. I see 1 and I'm going to do: predict-no
  1931. ENV: Agent did: predict-no for direction U in state State-A
  1932. In State-A moving U
  1933. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  1934. predict error 0
  1935. dir: dir isR
  1936. -/269: O: O537 (predict-yes)
  1937. I see 1 and I'm going to do: predict-yes
  1938. ENV: Agent did: predict-yes for direction R in state State-A
  1939. In State-A moving R
  1940. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  1941. predict error 0
  1942. dir: dir isL
  1943. |\270: O: O539 (predict-yes)
  1944. I see 1 and I'm going to do: predict-yes
  1945. ENV: Agent did: predict-yes for direction L in state State-B
  1946. In State-B moving L
  1947. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  1948. predict error 0
  1949. dir: dir isL
  1950. -/|271: O: O542 (predict-no)
  1951. I see 1 and I'm going to do: predict-no
  1952. ENV: Agent did: predict-no for direction L in state State-A
  1953. In State-A moving L
  1954. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  1955. predict error 0
  1956. dir: dir isL
  1957. \272: O: O544 (predict-no)
  1958. I see 1 and I'm going to do: predict-no
  1959. ENV: Agent did: predict-no for direction L in state State-A
  1960. In State-A moving L
  1961. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  1962. predict error 0
  1963. dir: dir isU
  1964. -/|273: O: O546 (predict-no)
  1965. I see 1 and I'm going to do: predict-no
  1966. ENV: Agent did: predict-no for direction U in state State-A
  1967. In State-A moving U
  1968. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  1969. predict error 0
  1970. dir: dir isU
  1971. \-/274: O: O548 (predict-no)
  1972. I see 1 and I'm going to do: predict-no
  1973. ENV: Agent did: predict-no for direction U in state State-A
  1974. In State-A moving U
  1975. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  1976. predict error 0
  1977. dir: dir isR
  1978. |\275: O: O549 (predict-yes)
  1979. I see 1 and I'm going to do: predict-yes
  1980. ENV: Agent did: predict-yes for direction R in state State-A
  1981. In State-A moving R
  1982. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  1983. predict error 0
  1984. dir: dir isR
  1985. -/276: O: O552 (predict-no)
  1986. I see 1 and I'm going to do: predict-no
  1987. ENV: Agent did: predict-no for direction R in state State-B
  1988. In State-B moving R
  1989. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  1990. predict error 0
  1991. dir: dir isL
  1992. |\-/277: O: O553 (predict-yes)
  1993. I see 1 and I'm going to do: predict-yes
  1994. ENV: Agent did: predict-yes for direction L in state State-B
  1995. In State-B moving L
  1996. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  1997. predict error 0
  1998. dir: dir isR
  1999. |\-278: O: O555 (predict-yes)
  2000. I see 1 and I'm going to do: predict-yes
  2001. ENV: Agent did: predict-yes for direction R in state State-A
  2002. In State-A moving R
  2003. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  2004. predict error 0
  2005. dir: dir isU
  2006. /|\279: O: O558 (predict-no)
  2007. I see 1 and I'm going to do: predict-no
  2008. ENV: Agent did: predict-no for direction U in state State-B
  2009. In State-B moving U
  2010. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2011. predict error 0
  2012. dir: dir isU
  2013. -/|280: O: O560 (predict-no)
  2014. I see 1 and I'm going to do: predict-no
  2015. ENV: Agent did: predict-no for direction U in state State-B
  2016. In State-B moving U
  2017. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2018. predict error 0
  2019. dir: dir isL
  2020. \-281: O: O561 (predict-yes)
  2021. I see 1 and I'm going to do: predict-yes
  2022. ENV: Agent did: predict-yes for direction L in state State-B
  2023. In State-B moving L
  2024. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  2025. predict error 0
  2026. dir: dir isR
  2027. /282: O: O563 (predict-yes)
  2028. I see 1 and I'm going to do: predict-yes
  2029. ENV: Agent did: predict-yes for direction R in state State-A
  2030. In State-A moving R
  2031. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  2032. predict error 0
  2033. dir: dir isU
  2034. |\-283: O: O565 (predict-yes)
  2035. I see 1 and I'm going to do: predict-yes
  2036. ENV: Agent did: predict-yes for direction U in state State-B
  2037. In State-B moving U
  2038. ENV: (next state, see, prediction correct?) = (State-B, 0, False)
  2039. predict error 1
  2040. dir: dir isL
  2041. /284: O: O567 (predict-yes)
  2042. I see 0 and I'm going to do: predict-yes
  2043. ENV: Agent did: predict-yes for direction L in state State-B
  2044. In State-B moving L
  2045. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  2046. predict error 0
  2047. dir: dir isU
  2048. |\285: O: O569 (predict-yes)
  2049. I see 1 and I'm going to do: predict-yes
  2050. ENV: Agent did: predict-yes for direction U in state State-A
  2051. In State-A moving U
  2052. ENV: (next state, see, prediction correct?) = (State-A, 0, False)
  2053. predict error 1
  2054. dir: dir isR
  2055. -/286: O: O572 (predict-no)
  2056. I see 0 and I'm going to do: predict-no
  2057. ENV: Agent did: predict-no for direction R in state State-A
  2058. In State-A moving R
  2059. ENV: (next state, see, prediction correct?) = (State-B, 1, False)
  2060. predict error 1
  2061. dir: dir isU
  2062. |\287: O: O574 (predict-no)
  2063. I see 0 and I'm going to do: predict-no
  2064. ENV: Agent did: predict-no for direction U in state State-B
  2065. In State-B moving U
  2066. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2067. predict error 0
  2068. dir: dir isR
  2069. -288: O: O576 (predict-no)
  2070. I see 1 and I'm going to do: predict-no
  2071. ENV: Agent did: predict-no for direction R in state State-B
  2072. In State-B moving R
  2073. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2074. predict error 0
  2075. dir: dir isU
  2076. /|\289: O: O578 (predict-no)
  2077. I see 1 and I'm going to do: predict-no
  2078. ENV: Agent did: predict-no for direction U in state State-B
  2079. In State-B moving U
  2080. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2081. predict error 0
  2082. dir: dir isU
  2083. -290: O: O580 (predict-no)
  2084. I see 1 and I'm going to do: predict-no
  2085. ENV: Agent did: predict-no for direction U in state State-B
  2086. In State-B moving U
  2087. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2088. predict error 0
  2089. dir: dir isR
  2090. /|\-291: O: O582 (predict-no)
  2091. I see 1 and I'm going to do: predict-no
  2092. ENV: Agent did: predict-no for direction R in state State-B
  2093. In State-B moving R
  2094. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2095. predict error 0
  2096. dir: dir isL
  2097. /292: O: O583 (predict-yes)
  2098. I see 1 and I'm going to do: predict-yes
  2099. ENV: Agent did: predict-yes for direction L in state State-B
  2100. In State-B moving L
  2101. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  2102. predict error 0
  2103. dir: dir isR
  2104. |\293: O: O585 (predict-yes)
  2105. I see 1 and I'm going to do: predict-yes
  2106. ENV: Agent did: predict-yes for direction R in state State-A
  2107. In State-A moving R
  2108. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  2109. predict error 0
  2110. dir: dir isL
  2111. -294: O: O587 (predict-yes)
  2112. I see 1 and I'm going to do: predict-yes
  2113. ENV: Agent did: predict-yes for direction L in state State-B
  2114. In State-B moving L
  2115. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  2116. predict error 0
  2117. dir: dir isR
  2118. /|\295: O: O589 (predict-yes)
  2119. I see 1 and I'm going to do: predict-yes
  2120. ENV: Agent did: predict-yes for direction R in state State-A
  2121. In State-A moving R
  2122. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  2123. predict error 0
  2124. dir: dir isU
  2125. -/|296: O: O592 (predict-no)
  2126. I see 1 and I'm going to do: predict-no
  2127. ENV: Agent did: predict-no for direction U in state State-B
  2128. In State-B moving U
  2129. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2130. predict error 0
  2131. dir: dir isL
  2132. \-297: O: O593 (predict-yes)
  2133. I see 1 and I'm going to do: predict-yes
  2134. ENV: Agent did: predict-yes for direction L in state State-B
  2135. In State-B moving L
  2136. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  2137. predict error 0
  2138. dir: dir isR
  2139. /|\298: O: O595 (predict-yes)
  2140. I see 1 and I'm going to do: predict-yes
  2141. ENV: Agent did: predict-yes for direction R in state State-A
  2142. In State-A moving R
  2143. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  2144. predict error 0
  2145. dir: dir isR
  2146. -/|299: O: O598 (predict-no)
  2147. I see 1 and I'm going to do: predict-no
  2148. ENV: Agent did: predict-no for direction R in state State-B
  2149. In State-B moving R
  2150. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2151. predict error 0
  2152. dir: dir isR
  2153. \-/300: O: O599 (predict-yes)
  2154. I see 1 and I'm going to do: predict-yes
  2155. ENV: Agent did: predict-yes for direction R in state State-B
  2156. In State-B moving R
  2157. ENV: (next state, see, prediction correct?) = (State-B, 0, False)
  2158. predict error 1
  2159. dir: dir isU
  2160. |\-/|\301: O: O602 (predict-no)
  2161. I see 0 and I'm going to do: predict-no
  2162. ENV: Agent did: predict-no for direction U in state State-B
  2163. In State-B moving U
  2164. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2165. predict error 0
  2166. dir: dir isU
  2167. -302: O: O604 (predict-no)
  2168. I see 1 and I'm going to do: predict-no
  2169. ENV: Agent did: predict-no for direction U in state State-B
  2170. In State-B moving U
  2171. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2172. predict error 0
  2173. dir: dir isU
  2174. /|\303: O: O606 (predict-no)
  2175. I see 1 and I'm going to do: predict-no
  2176. ENV: Agent did: predict-no for direction U in state State-B
  2177. In State-B moving U
  2178. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2179. predict error 0
  2180. dir: dir isR
  2181. -304: O: O608 (predict-no)
  2182. I see 1 and I'm going to do: predict-no
  2183. ENV: Agent did: predict-no for direction R in state State-B
  2184. In State-B moving R
  2185. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2186. predict error 0
  2187. dir: dir isU
  2188. /|305: O: O610 (predict-no)
  2189. I see 1 and I'm going to do: predict-no
  2190. ENV: Agent did: predict-no for direction U in state State-B
  2191. In State-B moving U
  2192. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2193. predict error 0
  2194. dir: dir isL
  2195. \-/306: O: O611 (predict-yes)
  2196. I see 1 and I'm going to do: predict-yes
  2197. ENV: Agent did: predict-yes for direction L in state State-B
  2198. In State-B moving L
  2199. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  2200. predict error 0
  2201. dir: dir isU
  2202. |\-307: O: O614 (predict-no)
  2203. I see 1 and I'm going to do: predict-no
  2204. ENV: Agent did: predict-no for direction U in state State-A
  2205. In State-A moving U
  2206. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  2207. predict error 0
  2208. dir: dir isR
  2209. /308: O: O615 (predict-yes)
  2210. I see 1 and I'm going to do: predict-yes
  2211. ENV: Agent did: predict-yes for direction R in state State-A
  2212. In State-A moving R
  2213. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  2214. predict error 0
  2215. dir: dir isU
  2216. |\-309: O: O617 (predict-yes)
  2217. I see 1 and I'm going to do: predict-yes
  2218. ENV: Agent did: predict-yes for direction U in state State-B
  2219. In State-B moving U
  2220. ENV: (next state, see, prediction correct?) = (State-B, 0, False)
  2221. predict error 1
  2222. dir: dir isU
  2223. /|\310: O: O620 (predict-no)
  2224. I see 0 and I'm going to do: predict-no
  2225. ENV: Agent did: predict-no for direction U in state State-B
  2226. In State-B moving U
  2227. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2228. predict error 0
  2229. dir: dir isL
  2230. -/|311: O: O621 (predict-yes)
  2231. I see 1 and I'm going to do: predict-yes
  2232. ENV: Agent did: predict-yes for direction L in state State-B
  2233. In State-B moving L
  2234. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  2235. predict error 0
  2236. dir: dir isR
  2237. \312: O: O624 (predict-no)
  2238. I see 1 and I'm going to do: predict-no
  2239. ENV: Agent did: predict-no for direction R in state State-A
  2240. In State-A moving R
  2241. ENV: (next state, see, prediction correct?) = (State-B, 1, False)
  2242. predict error 1
  2243. dir: dir isR
  2244. -/313: O: O626 (predict-no)
  2245. I see 0 and I'm going to do: predict-no
  2246. ENV: Agent did: predict-no for direction R in state State-B
  2247. In State-B moving R
  2248. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2249. predict error 0
  2250. dir: dir isU
  2251. |\314: O: O628 (predict-no)
  2252. I see 1 and I'm going to do: predict-no
  2253. ENV: Agent did: predict-no for direction U in state State-B
  2254. In State-B moving U
  2255. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2256. predict error 0
  2257. dir: dir isU
  2258. -/|315: O: O630 (predict-no)
  2259. I see 1 and I'm going to do: predict-no
  2260. ENV: Agent did: predict-no for direction U in state State-B
  2261. In State-B moving U
  2262. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2263. predict error 0
  2264. dir: dir isR
  2265. \-/316: O: O632 (predict-no)
  2266. I see 1 and I'm going to do: predict-no
  2267. ENV: Agent did: predict-no for direction R in state State-B
  2268. In State-B moving R
  2269. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2270. predict error 0
  2271. dir: dir isL
  2272. |\-317: O: O634 (predict-no)
  2273. I see 1 and I'm going to do: predict-no
  2274. ENV: Agent did: predict-no for direction L in state State-B
  2275. In State-B moving L
  2276. ENV: (next state, see, prediction correct?) = (State-A, 1, False)
  2277. predict error 1
  2278. dir: dir isR
  2279. /|\318: O: O635 (predict-yes)
  2280. I see 0 and I'm going to do: predict-yes
  2281. ENV: Agent did: predict-yes for direction R in state State-A
  2282. In State-A moving R
  2283. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  2284. predict error 0
  2285. dir: dir isU
  2286. -/319: O: O638 (predict-no)
  2287. I see 1 and I'm going to do: predict-no
  2288. ENV: Agent did: predict-no for direction U in state State-B
  2289. In State-B moving U
  2290. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2291. predict error 0
  2292. dir: dir isU
  2293. |\-320: O: O640 (predict-no)
  2294. I see 1 and I'm going to do: predict-no
  2295. ENV: Agent did: predict-no for direction U in state State-B
  2296. In State-B moving U
  2297. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2298. predict error 0
  2299. dir: dir isR
  2300. /|\321: O: O642 (predict-no)
  2301. I see 1 and I'm going to do: predict-no
  2302. ENV: Agent did: predict-no for direction R in state State-B
  2303. In State-B moving R
  2304. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2305. predict error 0
  2306. dir: dir isU
  2307. -322: O: O644 (predict-no)
  2308. I see 1 and I'm going to do: predict-no
  2309. ENV: Agent did: predict-no for direction U in state State-B
  2310. In State-B moving U
  2311. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2312. predict error 0
  2313. dir: dir isL
  2314. /|\323: O: O645 (predict-yes)
  2315. I see 1 and I'm going to do: predict-yes
  2316. ENV: Agent did: predict-yes for direction L in state State-B
  2317. In State-B moving L
  2318. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  2319. predict error 0
  2320. dir: dir isU
  2321. -/324: O: O648 (predict-no)
  2322. I see 1 and I'm going to do: predict-no
  2323. ENV: Agent did: predict-no for direction U in state State-A
  2324. In State-A moving U
  2325. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  2326. predict error 0
  2327. dir: dir isU
  2328. |\-325: O: O650 (predict-no)
  2329. I see 1 and I'm going to do: predict-no
  2330. ENV: Agent did: predict-no for direction U in state State-A
  2331. In State-A moving U
  2332. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  2333. predict error 0
  2334. dir: dir isR
  2335. /|\326: O: O651 (predict-yes)
  2336. I see 1 and I'm going to do: predict-yes
  2337. ENV: Agent did: predict-yes for direction R in state State-A
  2338. In State-A moving R
  2339. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  2340. predict error 0
  2341. dir: dir isU
  2342. -/|327: O: O654 (predict-no)
  2343. I see 1 and I'm going to do: predict-no
  2344. ENV: Agent did: predict-no for direction U in state State-B
  2345. In State-B moving U
  2346. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2347. predict error 0
  2348. dir: dir isU
  2349. \-/328: O: O656 (predict-no)
  2350. I see 1 and I'm going to do: predict-no
  2351. ENV: Agent did: predict-no for direction U in state State-B
  2352. In State-B moving U
  2353. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2354. predict error 0
  2355. dir: dir isL
  2356. |\-329: O: O657 (predict-yes)
  2357. I see 1 and I'm going to do: predict-yes
  2358. ENV: Agent did: predict-yes for direction L in state State-B
  2359. In State-B moving L
  2360. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  2361. predict error 0
  2362. dir: dir isU
  2363. /|\330: O: O660 (predict-no)
  2364. I see 1 and I'm going to do: predict-no
  2365. ENV: Agent did: predict-no for direction U in state State-A
  2366. In State-A moving U
  2367. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  2368. predict error 0
  2369. dir: dir isU
  2370. -/|331: O: O662 (predict-no)
  2371. I see 1 and I'm going to do: predict-no
  2372. ENV: Agent did: predict-no for direction U in state State-A
  2373. In State-A moving U
  2374. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  2375. predict error 0
  2376. dir: dir isL
  2377. \332: O: O664 (predict-no)
  2378. I see 1 and I'm going to do: predict-no
  2379. ENV: Agent did: predict-no for direction L in state State-A
  2380. In State-A moving L
  2381. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  2382. predict error 0
  2383. dir: dir isU
  2384. -/|333: O: O665 (predict-yes)
  2385. I see 1 and I'm going to do: predict-yes
  2386. ENV: Agent did: predict-yes for direction U in state State-A
  2387. In State-A moving U
  2388. ENV: (next state, see, prediction correct?) = (State-A, 0, False)
  2389. predict error 1
  2390. dir: dir isR
  2391. \-/334: O: O667 (predict-yes)
  2392. I see 0 and I'm going to do: predict-yes
  2393. ENV: Agent did: predict-yes for direction R in state State-A
  2394. In State-A moving R
  2395. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  2396. predict error 0
  2397. dir: dir isL
  2398. |\335: O: O669 (predict-yes)
  2399. I see 1 and I'm going to do: predict-yes
  2400. ENV: Agent did: predict-yes for direction L in state State-B
  2401. In State-B moving L
  2402. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  2403. predict error 0
  2404. dir: dir isU
  2405. -/336: O: O672 (predict-no)
  2406. I see 1 and I'm going to do: predict-no
  2407. ENV: Agent did: predict-no for direction U in state State-A
  2408. In State-A moving U
  2409. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  2410. predict error 0
  2411. dir: dir isL
  2412. |\-337: O: O674 (predict-no)
  2413. I see 1 and I'm going to do: predict-no
  2414. ENV: Agent did: predict-no for direction L in state State-A
  2415. In State-A moving L
  2416. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  2417. predict error 0
  2418. dir: dir isR
  2419. /|\338: O: O675 (predict-yes)
  2420. I see 1 and I'm going to do: predict-yes
  2421. ENV: Agent did: predict-yes for direction R in state State-A
  2422. In State-A moving R
  2423. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  2424. predict error 0
  2425. dir: dir isR
  2426. -339: O: O678 (predict-no)
  2427. I see 1 and I'm going to do: predict-no
  2428. ENV: Agent did: predict-no for direction R in state State-B
  2429. In State-B moving R
  2430. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2431. predict error 0
  2432. dir: dir isL
  2433. /|\340: O: O679 (predict-yes)
  2434. I see 1 and I'm going to do: predict-yes
  2435. ENV: Agent did: predict-yes for direction L in state State-B
  2436. In State-B moving L
  2437. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  2438. predict error 0
  2439. dir: dir isR
  2440. -341: O: O681 (predict-yes)
  2441. I see 1 and I'm going to do: predict-yes
  2442. ENV: Agent did: predict-yes for direction R in state State-A
  2443. In State-A moving R
  2444. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  2445. predict error 0
  2446. dir: dir isR
  2447. /342: O: O684 (predict-no)
  2448. I see 1 and I'm going to do: predict-no
  2449. ENV: Agent did: predict-no for direction R in state State-B
  2450. In State-B moving R
  2451. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2452. predict error 0
  2453. dir: dir isL
  2454. |\343: O: O685 (predict-yes)
  2455. I see 1 and I'm going to do: predict-yes
  2456. ENV: Agent did: predict-yes for direction L in state State-B
  2457. In State-B moving L
  2458. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  2459. predict error 0
  2460. dir: dir isU
  2461. -/|344: O: O688 (predict-no)
  2462. I see 1 and I'm going to do: predict-no
  2463. ENV: Agent did: predict-no for direction U in state State-A
  2464. In State-A moving U
  2465. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  2466. predict error 0
  2467. dir: dir isL
  2468. \-/345: O: O690 (predict-no)
  2469. I see 1 and I'm going to do: predict-no
  2470. ENV: Agent did: predict-no for direction L in state State-A
  2471. In State-A moving L
  2472. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  2473. predict error 0
  2474. dir: dir isL
  2475. |\-346: O: O692 (predict-no)
  2476. I see 1 and I'm going to do: predict-no
  2477. ENV: Agent did: predict-no for direction L in state State-A
  2478. In State-A moving L
  2479. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  2480. predict error 0
  2481. dir: dir isR
  2482. /|347: O: O693 (predict-yes)
  2483. I see 1 and I'm going to do: predict-yes
  2484. ENV: Agent did: predict-yes for direction R in state State-A
  2485. In State-A moving R
  2486. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  2487. predict error 0
  2488. dir: dir isU
  2489. \-348: O: O696 (predict-no)
  2490. I see 1 and I'm going to do: predict-no
  2491. ENV: Agent did: predict-no for direction U in state State-B
  2492. In State-B moving U
  2493. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2494. predict error 0
  2495. dir: dir isR
  2496. /|\349: O: O698 (predict-no)
  2497. I see 1 and I'm going to do: predict-no
  2498. ENV: Agent did: predict-no for direction R in state State-B
  2499. In State-B moving R
  2500. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2501. predict error 0
  2502. dir: dir isU
  2503. -/|350: O: O700 (predict-no)
  2504. I see 1 and I'm going to do: predict-no
  2505. ENV: Agent did: predict-no for direction U in state State-B
  2506. In State-B moving U
  2507. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2508. predict error 0
  2509. dir: dir isR
  2510. \-351: O: O702 (predict-no)
  2511. I see 1 and I'm going to do: predict-no
  2512. ENV: Agent did: predict-no for direction R in state State-B
  2513. In State-B moving R
  2514. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2515. predict error 0
  2516. dir: dir isU
  2517. /352: O: O703 (predict-yes)
  2518. I see 1 and I'm going to do: predict-yes
  2519. ENV: Agent did: predict-yes for direction U in state State-B
  2520. In State-B moving U
  2521. ENV: (next state, see, prediction correct?) = (State-B, 0, False)
  2522. predict error 1
  2523. dir: dir isR
  2524. |\-353: O: O706 (predict-no)
  2525. I see 0 and I'm going to do: predict-no
  2526. ENV: Agent did: predict-no for direction R in state State-B
  2527. In State-B moving R
  2528. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2529. predict error 0
  2530. dir: dir isL
  2531. /|\354: O: O707 (predict-yes)
  2532. I see 1 and I'm going to do: predict-yes
  2533. ENV: Agent did: predict-yes for direction L in state State-B
  2534. In State-B moving L
  2535. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  2536. predict error 0
  2537. dir: dir isR
  2538. -/|355: O: O709 (predict-yes)
  2539. I see 1 and I'm going to do: predict-yes
  2540. ENV: Agent did: predict-yes for direction R in state State-A
  2541. In State-A moving R
  2542. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  2543. predict error 0
  2544. dir: dir isL
  2545. \-/356: O: O711 (predict-yes)
  2546. I see 1 and I'm going to do: predict-yes
  2547. ENV: Agent did: predict-yes for direction L in state State-B
  2548. In State-B moving L
  2549. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  2550. predict error 0
  2551. dir: dir isL
  2552. |357: O: O714 (predict-no)
  2553. I see 1 and I'm going to do: predict-no
  2554. ENV: Agent did: predict-no for direction L in state State-A
  2555. In State-A moving L
  2556. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  2557. predict error 0
  2558. dir: dir isU
  2559. \-/358: O: O716 (predict-no)
  2560. I see 1 and I'm going to do: predict-no
  2561. ENV: Agent did: predict-no for direction U in state State-A
  2562. In State-A moving U
  2563. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  2564. predict error 0
  2565. dir: dir isL
  2566. |\-359: O: O718 (predict-no)
  2567. I see 1 and I'm going to do: predict-no
  2568. ENV: Agent did: predict-no for direction L in state State-A
  2569. In State-A moving L
  2570. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  2571. predict error 0
  2572. dir: dir isU
  2573. /|360: O: O720 (predict-no)
  2574. I see 1 and I'm going to do: predict-no
  2575. ENV: Agent did: predict-no for direction U in state State-A
  2576. In State-A moving U
  2577. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  2578. predict error 0
  2579. dir: dir isU
  2580. \-/361: O: O721 (predict-yes)
  2581. I see 1 and I'm going to do: predict-yes
  2582. ENV: Agent did: predict-yes for direction U in state State-A
  2583. In State-A moving U
  2584. ENV: (next state, see, prediction correct?) = (State-A, 0, False)
  2585. predict error 1
  2586. dir: dir isR
  2587. |362: O: O723 (predict-yes)
  2588. I see 0 and I'm going to do: predict-yes
  2589. ENV: Agent did: predict-yes for direction R in state State-A
  2590. In State-A moving R
  2591. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  2592. predict error 0
  2593. dir: dir isU
  2594. \-/363: O: O726 (predict-no)
  2595. I see 1 and I'm going to do: predict-no
  2596. ENV: Agent did: predict-no for direction U in state State-B
  2597. In State-B moving U
  2598. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2599. predict error 0
  2600. dir: dir isU
  2601. |\-364: O: O728 (predict-no)
  2602. I see 1 and I'm going to do: predict-no
  2603. ENV: Agent did: predict-no for direction U in state State-B
  2604. In State-B moving U
  2605. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2606. predict error 0
  2607. dir: dir isU
  2608. /|\365: O: O730 (predict-no)
  2609. I see 1 and I'm going to do: predict-no
  2610. ENV: Agent did: predict-no for direction U in state State-B
  2611. In State-B moving U
  2612. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2613. predict error 0
  2614. dir: dir isL
  2615. -/|366: O: O731 (predict-yes)
  2616. I see 1 and I'm going to do: predict-yes
  2617. ENV: Agent did: predict-yes for direction L in state State-B
  2618. In State-B moving L
  2619. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  2620. predict error 0
  2621. dir: dir isL
  2622. \-367: O: O734 (predict-no)
  2623. I see 1 and I'm going to do: predict-no
  2624. ENV: Agent did: predict-no for direction L in state State-A
  2625. In State-A moving L
  2626. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  2627. predict error 0
  2628. dir: dir isR
  2629. /|368: O: O735 (predict-yes)
  2630. I see 1 and I'm going to do: predict-yes
  2631. ENV: Agent did: predict-yes for direction R in state State-A
  2632. In State-A moving R
  2633. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  2634. predict error 0
  2635. dir: dir isR
  2636. \-/369: O: O737 (predict-yes)
  2637. I see 1 and I'm going to do: predict-yes
  2638. ENV: Agent did: predict-yes for direction R in state State-B
  2639. In State-B moving R
  2640. ENV: (next state, see, prediction correct?) = (State-B, 0, False)
  2641. predict error 1
  2642. dir: dir isL
  2643. |370: O: O739 (predict-yes)
  2644. I see 0 and I'm going to do: predict-yes
  2645. ENV: Agent did: predict-yes for direction L in state State-B
  2646. In State-B moving L
  2647. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  2648. predict error 0
  2649. dir: dir isL
  2650. \-/371: O: O742 (predict-no)
  2651. I see 1 and I'm going to do: predict-no
  2652. ENV: Agent did: predict-no for direction L in state State-A
  2653. In State-A moving L
  2654. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  2655. predict error 0
  2656. dir: dir isR
  2657. |372: O: O743 (predict-yes)
  2658. I see 1 and I'm going to do: predict-yes
  2659. ENV: Agent did: predict-yes for direction R in state State-A
  2660. In State-A moving R
  2661. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  2662. predict error 0
  2663. dir: dir isU
  2664. \-/373: O: O746 (predict-no)
  2665. I see 1 and I'm going to do: predict-no
  2666. ENV: Agent did: predict-no for direction U in state State-B
  2667. In State-B moving U
  2668. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2669. predict error 0
  2670. dir: dir isR
  2671. |\374: O: O748 (predict-no)
  2672. I see 1 and I'm going to do: predict-no
  2673. ENV: Agent did: predict-no for direction R in state State-B
  2674. In State-B moving R
  2675. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2676. predict error 0
  2677. dir: dir isR
  2678. -/375: O: O750 (predict-no)
  2679. I see 1 and I'm going to do: predict-no
  2680. ENV: Agent did: predict-no for direction R in state State-B
  2681. In State-B moving R
  2682. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2683. predict error 0
  2684. dir: dir isR
  2685. |376: O: O752 (predict-no)
  2686. I see 1 and I'm going to do: predict-no
  2687. ENV: Agent did: predict-no for direction R in state State-B
  2688. In State-B moving R
  2689. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2690. predict error 0
  2691. dir: dir isR
  2692. \-/377: O: O754 (predict-no)
  2693. I see 1 and I'm going to do: predict-no
  2694. ENV: Agent did: predict-no for direction R in state State-B
  2695. In State-B moving R
  2696. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2697. predict error 0
  2698. dir: dir isU
  2699. |\-378: O: O756 (predict-no)
  2700. I see 1 and I'm going to do: predict-no
  2701. ENV: Agent did: predict-no for direction U in state State-B
  2702. In State-B moving U
  2703. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2704. predict error 0
  2705. dir: dir isL
  2706. /|\379: O: O757 (predict-yes)
  2707. I see 1 and I'm going to do: predict-yes
  2708. ENV: Agent did: predict-yes for direction L in state State-B
  2709. In State-B moving L
  2710. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  2711. predict error 0
  2712. dir: dir isR
  2713. -380: O: O759 (predict-yes)
  2714. I see 1 and I'm going to do: predict-yes
  2715. ENV: Agent did: predict-yes for direction R in state State-A
  2716. In State-A moving R
  2717. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  2718. predict error 0
  2719. dir: dir isR
  2720. /|\381: O: O762 (predict-no)
  2721. I see 1 and I'm going to do: predict-no
  2722. ENV: Agent did: predict-no for direction R in state State-B
  2723. In State-B moving R
  2724. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2725. predict error 0
  2726. dir: dir isR
  2727. -382: O: O764 (predict-no)
  2728. I see 1 and I'm going to do: predict-no
  2729. ENV: Agent did: predict-no for direction R in state State-B
  2730. In State-B moving R
  2731. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2732. predict error 0
  2733. dir: dir isU
  2734. /|\383: O: O766 (predict-no)
  2735. I see 1 and I'm going to do: predict-no
  2736. ENV: Agent did: predict-no for direction U in state State-B
  2737. In State-B moving U
  2738. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2739. predict error 0
  2740. dir: dir isL
  2741. -/|384: O: O767 (predict-yes)
  2742. I see 1 and I'm going to do: predict-yes
  2743. ENV: Agent did: predict-yes for direction L in state State-B
  2744. In State-B moving L
  2745. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  2746. predict error 0
  2747. dir: dir isU
  2748. \-385: O: O770 (predict-no)
  2749. I see 1 and I'm going to do: predict-no
  2750. ENV: Agent did: predict-no for direction U in state State-A
  2751. In State-A moving U
  2752. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  2753. predict error 0
  2754. dir: dir isL
  2755. /|386: O: O772 (predict-no)
  2756. I see 1 and I'm going to do: predict-no
  2757. ENV: Agent did: predict-no for direction L in state State-A
  2758. In State-A moving L
  2759. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  2760. predict error 0
  2761. dir: dir isR
  2762. \-/387: O: O773 (predict-yes)
  2763. I see 1 and I'm going to do: predict-yes
  2764. ENV: Agent did: predict-yes for direction R in state State-A
  2765. In State-A moving R
  2766. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  2767. predict error 0
  2768. dir: dir isU
  2769. |\-388: O: O776 (predict-no)
  2770. I see 1 and I'm going to do: predict-no
  2771. ENV: Agent did: predict-no for direction U in state State-B
  2772. In State-B moving U
  2773. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2774. predict error 0
  2775. dir: dir isR
  2776. /|389: O: O778 (predict-no)
  2777. I see 1 and I'm going to do: predict-no
  2778. ENV: Agent did: predict-no for direction R in state State-B
  2779. In State-B moving R
  2780. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2781. predict error 0
  2782. dir: dir isR
  2783. \390: O: O780 (predict-no)
  2784. I see 1 and I'm going to do: predict-no
  2785. ENV: Agent did: predict-no for direction R in state State-B
  2786. In State-B moving R
  2787. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2788. predict error 0
  2789. dir: dir isU
  2790. -/391: O: O782 (predict-no)
  2791. I see 1 and I'm going to do: predict-no
  2792. ENV: Agent did: predict-no for direction U in state State-B
  2793. In State-B moving U
  2794. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2795. predict error 0
  2796. dir: dir isL
  2797. |392: O: O783 (predict-yes)
  2798. I see 1 and I'm going to do: predict-yes
  2799. ENV: Agent did: predict-yes for direction L in state State-B
  2800. In State-B moving L
  2801. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  2802. predict error 0
  2803. dir: dir isR
  2804. \-/393: O: O785 (predict-yes)
  2805. I see 1 and I'm going to do: predict-yes
  2806. ENV: Agent did: predict-yes for direction R in state State-A
  2807. In State-A moving R
  2808. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  2809. predict error 0
  2810. dir: dir isR
  2811. |\-394: O: O788 (predict-no)
  2812. I see 1 and I'm going to do: predict-no
  2813. ENV: Agent did: predict-no for direction R in state State-B
  2814. In State-B moving R
  2815. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2816. predict error 0
  2817. dir: dir isR
  2818. /|\395: O: O790 (predict-no)
  2819. I see 1 and I'm going to do: predict-no
  2820. ENV: Agent did: predict-no for direction R in state State-B
  2821. In State-B moving R
  2822. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2823. predict error 0
  2824. dir: dir isU
  2825. -/396: O: O792 (predict-no)
  2826. I see 1 and I'm going to do: predict-no
  2827. ENV: Agent did: predict-no for direction U in state State-B
  2828. In State-B moving U
  2829. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2830. predict error 0
  2831. dir: dir isU
  2832. |\-397: O: O794 (predict-no)
  2833. I see 1 and I'm going to do: predict-no
  2834. ENV: Agent did: predict-no for direction U in state State-B
  2835. In State-B moving U
  2836. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2837. predict error 0
  2838. dir: dir isR
  2839. /|398: O: O796 (predict-no)
  2840. I see 1 and I'm going to do: predict-no
  2841. ENV: Agent did: predict-no for direction R in state State-B
  2842. In State-B moving R
  2843. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2844. predict error 0
  2845. dir: dir isL
  2846. \-399: O: O797 (predict-yes)
  2847. I see 1 and I'm going to do: predict-yes
  2848. ENV: Agent did: predict-yes for direction L in state State-B
  2849. In State-B moving L
  2850. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  2851. predict error 0
  2852. dir: dir isL
  2853. /|\400: O: O800 (predict-no)
  2854. I see 1 and I'm going to do: predict-no
  2855. ENV: Agent did: predict-no for direction L in state State-A
  2856. In State-A moving L
  2857. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  2858. predict error 0
  2859. dir: dir isR
  2860. -/401: O: O802 (predict-no)
  2861. I see 1 and I'm going to do: predict-no
  2862. ENV: Agent did: predict-no for direction R in state State-A
  2863. In State-A moving R
  2864. ENV: (next state, see, prediction correct?) = (State-B, 1, False)
  2865. predict error 1
  2866. dir: dir isL
  2867. |402: O: O803 (predict-yes)
  2868. I see 0 and I'm going to do: predict-yes
  2869. ENV: Agent did: predict-yes for direction L in state State-B
  2870. In State-B moving L
  2871. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  2872. predict error 0
  2873. dir: dir isL
  2874. \-403: O: O806 (predict-no)
  2875. I see 1 and I'm going to do: predict-no
  2876. ENV: Agent did: predict-no for direction L in state State-A
  2877. In State-A moving L
  2878. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  2879. predict error 0
  2880. dir: dir isU
  2881. /|404: O: O808 (predict-no)
  2882. I see 1 and I'm going to do: predict-no
  2883. ENV: Agent did: predict-no for direction U in state State-A
  2884. In State-A moving U
  2885. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  2886. predict error 0
  2887. dir: dir isL
  2888. \405: O: O810 (predict-no)
  2889. I see 1 and I'm going to do: predict-no
  2890. ENV: Agent did: predict-no for direction L in state State-A
  2891. In State-A moving L
  2892. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  2893. predict error 0
  2894. dir: dir isU
  2895. -/|406: O: O812 (predict-no)
  2896. I see 1 and I'm going to do: predict-no
  2897. ENV: Agent did: predict-no for direction U in state State-A
  2898. In State-A moving U
  2899. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  2900. predict error 0
  2901. dir: dir isR
  2902. \-407: O: O813 (predict-yes)
  2903. I see 1 and I'm going to do: predict-yes
  2904. ENV: Agent did: predict-yes for direction R in state State-A
  2905. In State-A moving R
  2906. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  2907. predict error 0
  2908. dir: dir isR
  2909. /|\408: O: O816 (predict-no)
  2910. I see 1 and I'm going to do: predict-no
  2911. ENV: Agent did: predict-no for direction R in state State-B
  2912. In State-B moving R
  2913. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2914. predict error 0
  2915. dir: dir isL
  2916. -/|409: O: O817 (predict-yes)
  2917. I see 1 and I'm going to do: predict-yes
  2918. ENV: Agent did: predict-yes for direction L in state State-B
  2919. In State-B moving L
  2920. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  2921. predict error 0
  2922. dir: dir isL
  2923. \-/|410: O: O820 (predict-no)
  2924. I see 1 and I'm going to do: predict-no
  2925. ENV: Agent did: predict-no for direction L in state State-A
  2926. In State-A moving L
  2927. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  2928. predict error 0
  2929. dir: dir isR
  2930. \-/411: O: O821 (predict-yes)
  2931. I see 1 and I'm going to do: predict-yes
  2932. ENV: Agent did: predict-yes for direction R in state State-A
  2933. In State-A moving R
  2934. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  2935. predict error 0
  2936. dir: dir isL
  2937. |412: O: O823 (predict-yes)
  2938. I see 1 and I'm going to do: predict-yes
  2939. ENV: Agent did: predict-yes for direction L in state State-B
  2940. In State-B moving L
  2941. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  2942. predict error 0
  2943. dir: dir isR
  2944. \-/413: O: O825 (predict-yes)
  2945. I see 1 and I'm going to do: predict-yes
  2946. ENV: Agent did: predict-yes for direction R in state State-A
  2947. In State-A moving R
  2948. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  2949. predict error 0
  2950. dir: dir isL
  2951. |414: O: O827 (predict-yes)
  2952. I see 1 and I'm going to do: predict-yes
  2953. ENV: Agent did: predict-yes for direction L in state State-B
  2954. In State-B moving L
  2955. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  2956. predict error 0
  2957. dir: dir isU
  2958. \-415: O: O829 (predict-yes)
  2959. I see 1 and I'm going to do: predict-yes
  2960. ENV: Agent did: predict-yes for direction U in state State-A
  2961. In State-A moving U
  2962. ENV: (next state, see, prediction correct?) = (State-A, 0, False)
  2963. predict error 1
  2964. dir: dir isU
  2965. /|\416: O: O832 (predict-no)
  2966. I see 0 and I'm going to do: predict-no
  2967. ENV: Agent did: predict-no for direction U in state State-A
  2968. In State-A moving U
  2969. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  2970. predict error 0
  2971. dir: dir isR
  2972. -/|417: O: O833 (predict-yes)
  2973. I see 1 and I'm going to do: predict-yes
  2974. ENV: Agent did: predict-yes for direction R in state State-A
  2975. In State-A moving R
  2976. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  2977. predict error 0
  2978. dir: dir isR
  2979. \-/418: O: O836 (predict-no)
  2980. I see 1 and I'm going to do: predict-no
  2981. ENV: Agent did: predict-no for direction R in state State-B
  2982. In State-B moving R
  2983. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2984. predict error 0
  2985. dir: dir isU
  2986. |\-419: O: O838 (predict-no)
  2987. I see 1 and I'm going to do: predict-no
  2988. ENV: Agent did: predict-no for direction U in state State-B
  2989. In State-B moving U
  2990. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  2991. predict error 0
  2992. dir: dir isL
  2993. /|\-420: O: O839 (predict-yes)
  2994. I see 1 and I'm going to do: predict-yes
  2995. ENV: Agent did: predict-yes for direction L in state State-B
  2996. In State-B moving L
  2997. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  2998. predict error 0
  2999. dir: dir isL
  3000. /|\421: O: O842 (predict-no)
  3001. I see 1 and I'm going to do: predict-no
  3002. ENV: Agent did: predict-no for direction L in state State-A
  3003. In State-A moving L
  3004. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3005. predict error 0
  3006. dir: dir isL
  3007. -422: O: O844 (predict-no)
  3008. I see 1 and I'm going to do: predict-no
  3009. ENV: Agent did: predict-no for direction L in state State-A
  3010. In State-A moving L
  3011. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3012. predict error 0
  3013. dir: dir isL
  3014. /|423: O: O846 (predict-no)
  3015. I see 1 and I'm going to do: predict-no
  3016. ENV: Agent did: predict-no for direction L in state State-A
  3017. In State-A moving L
  3018. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3019. predict error 0
  3020. dir: dir isU
  3021. \-/424: O: O848 (predict-no)
  3022. I see 1 and I'm going to do: predict-no
  3023. ENV: Agent did: predict-no for direction U in state State-A
  3024. In State-A moving U
  3025. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3026. predict error 0
  3027. dir: dir isR
  3028. |\425: O: O849 (predict-yes)
  3029. I see 1 and I'm going to do: predict-yes
  3030. ENV: Agent did: predict-yes for direction R in state State-A
  3031. In State-A moving R
  3032. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  3033. predict error 0
  3034. dir: dir isR
  3035. -/|426: O: O852 (predict-no)
  3036. I see 1 and I'm going to do: predict-no
  3037. ENV: Agent did: predict-no for direction R in state State-B
  3038. In State-B moving R
  3039. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3040. predict error 0
  3041. dir: dir isU
  3042. \-427: O: O854 (predict-no)
  3043. I see 1 and I'm going to do: predict-no
  3044. ENV: Agent did: predict-no for direction U in state State-B
  3045. In State-B moving U
  3046. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3047. predict error 0
  3048. dir: dir isL
  3049. /|428: O: O855 (predict-yes)
  3050. I see 1 and I'm going to do: predict-yes
  3051. ENV: Agent did: predict-yes for direction L in state State-B
  3052. In State-B moving L
  3053. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  3054. predict error 0
  3055. dir: dir isU
  3056. \-/429: O: O858 (predict-no)
  3057. I see 1 and I'm going to do: predict-no
  3058. ENV: Agent did: predict-no for direction U in state State-A
  3059. In State-A moving U
  3060. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3061. predict error 0
  3062. dir: dir isR
  3063. |\-430: O: O859 (predict-yes)
  3064. I see 1 and I'm going to do: predict-yes
  3065. ENV: Agent did: predict-yes for direction R in state State-A
  3066. In State-A moving R
  3067. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  3068. predict error 0
  3069. dir: dir isR
  3070. /|\431: O: O862 (predict-no)
  3071. I see 1 and I'm going to do: predict-no
  3072. ENV: Agent did: predict-no for direction R in state State-B
  3073. In State-B moving R
  3074. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3075. predict error 0
  3076. dir: dir isU
  3077. -432: O: O864 (predict-no)
  3078. I see 1 and I'm going to do: predict-no
  3079. ENV: Agent did: predict-no for direction U in state State-B
  3080. In State-B moving U
  3081. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3082. predict error 0
  3083. dir: dir isR
  3084. /|433: O: O866 (predict-no)
  3085. I see 1 and I'm going to do: predict-no
  3086. ENV: Agent did: predict-no for direction R in state State-B
  3087. In State-B moving R
  3088. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3089. predict error 0
  3090. dir: dir isU
  3091. \-434: O: O867 (predict-yes)
  3092. I see 1 and I'm going to do: predict-yes
  3093. ENV: Agent did: predict-yes for direction U in state State-B
  3094. In State-B moving U
  3095. ENV: (next state, see, prediction correct?) = (State-B, 0, False)
  3096. predict error 1
  3097. dir: dir isU
  3098. /|\435: O: O870 (predict-no)
  3099. I see 0 and I'm going to do: predict-no
  3100. ENV: Agent did: predict-no for direction U in state State-B
  3101. In State-B moving U
  3102. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3103. predict error 0
  3104. dir: dir isR
  3105. -/|436: O: O872 (predict-no)
  3106. I see 1 and I'm going to do: predict-no
  3107. ENV: Agent did: predict-no for direction R in state State-B
  3108. In State-B moving R
  3109. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3110. predict error 0
  3111. dir: dir isU
  3112. \-/437: O: O873 (predict-yes)
  3113. I see 1 and I'm going to do: predict-yes
  3114. ENV: Agent did: predict-yes for direction U in state State-B
  3115. In State-B moving U
  3116. ENV: (next state, see, prediction correct?) = (State-B, 0, False)
  3117. predict error 1
  3118. dir: dir isU
  3119. |\-438: O: O876 (predict-no)
  3120. I see 0 and I'm going to do: predict-no
  3121. ENV: Agent did: predict-no for direction U in state State-B
  3122. In State-B moving U
  3123. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3124. predict error 0
  3125. dir: dir isU
  3126. /|\439: O: O878 (predict-no)
  3127. I see 1 and I'm going to do: predict-no
  3128. ENV: Agent did: predict-no for direction U in state State-B
  3129. In State-B moving U
  3130. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3131. predict error 0
  3132. dir: dir isU
  3133. -/|440: O: O880 (predict-no)
  3134. I see 1 and I'm going to do: predict-no
  3135. ENV: Agent did: predict-no for direction U in state State-B
  3136. In State-B moving U
  3137. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3138. predict error 0
  3139. dir: dir isU
  3140. \-441: O: O882 (predict-no)
  3141. I see 1 and I'm going to do: predict-no
  3142. ENV: Agent did: predict-no for direction U in state State-B
  3143. In State-B moving U
  3144. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3145. predict error 0
  3146. dir: dir isU
  3147. /442: O: O884 (predict-no)
  3148. I see 1 and I'm going to do: predict-no
  3149. ENV: Agent did: predict-no for direction U in state State-B
  3150. In State-B moving U
  3151. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3152. predict error 0
  3153. dir: dir isU
  3154. |\443: O: O886 (predict-no)
  3155. I see 1 and I'm going to do: predict-no
  3156. ENV: Agent did: predict-no for direction U in state State-B
  3157. In State-B moving U
  3158. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3159. predict error 0
  3160. dir: dir isU
  3161. -/444: O: O888 (predict-no)
  3162. I see 1 and I'm going to do: predict-no
  3163. ENV: Agent did: predict-no for direction U in state State-B
  3164. In State-B moving U
  3165. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3166. predict error 0
  3167. dir: dir isL
  3168. |\445: O: O889 (predict-yes)
  3169. I see 1 and I'm going to do: predict-yes
  3170. ENV: Agent did: predict-yes for direction L in state State-B
  3171. In State-B moving L
  3172. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  3173. predict error 0
  3174. dir: dir isR
  3175. -/|446: O: O891 (predict-yes)
  3176. I see 1 and I'm going to do: predict-yes
  3177. ENV: Agent did: predict-yes for direction R in state State-A
  3178. In State-A moving R
  3179. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  3180. predict error 0
  3181. dir: dir isU
  3182. \-/447: O: O894 (predict-no)
  3183. I see 1 and I'm going to do: predict-no
  3184. ENV: Agent did: predict-no for direction U in state State-B
  3185. In State-B moving U
  3186. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3187. predict error 0
  3188. dir: dir isR
  3189. |\-448: O: O896 (predict-no)
  3190. I see 1 and I'm going to do: predict-no
  3191. ENV: Agent did: predict-no for direction R in state State-B
  3192. In State-B moving R
  3193. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3194. predict error 0
  3195. dir: dir isR
  3196. /|\449: O: O898 (predict-no)
  3197. I see 1 and I'm going to do: predict-no
  3198. ENV: Agent did: predict-no for direction R in state State-B
  3199. In State-B moving R
  3200. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3201. predict error 0
  3202. dir: dir isL
  3203. -/|450: O: O899 (predict-yes)
  3204. I see 1 and I'm going to do: predict-yes
  3205. ENV: Agent did: predict-yes for direction L in state State-B
  3206. In State-B moving L
  3207. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  3208. predict error 0
  3209. dir: dir isU
  3210. \-/451: O: O902 (predict-no)
  3211. I see 1 and I'm going to do: predict-no
  3212. ENV: Agent did: predict-no for direction U in state State-A
  3213. In State-A moving U
  3214. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3215. predict error 0
  3216. dir: dir isR
  3217. |452: O: O903 (predict-yes)
  3218. I see 1 and I'm going to do: predict-yes
  3219. ENV: Agent did: predict-yes for direction R in state State-A
  3220. In State-A moving R
  3221. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  3222. predict error 0
  3223. dir: dir isR
  3224. \-/453: O: O906 (predict-no)
  3225. I see 1 and I'm going to do: predict-no
  3226. ENV: Agent did: predict-no for direction R in state State-B
  3227. In State-B moving R
  3228. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3229. predict error 0
  3230. dir: dir isU
  3231. |\454: O: O908 (predict-no)
  3232. I see 1 and I'm going to do: predict-no
  3233. ENV: Agent did: predict-no for direction U in state State-B
  3234. In State-B moving U
  3235. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3236. predict error 0
  3237. dir: dir isL
  3238. -/455: O: O909 (predict-yes)
  3239. I see 1 and I'm going to do: predict-yes
  3240. ENV: Agent did: predict-yes for direction L in state State-B
  3241. In State-B moving L
  3242. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  3243. predict error 0
  3244. dir: dir isU
  3245. |\456: O: O912 (predict-no)
  3246. I see 1 and I'm going to do: predict-no
  3247. ENV: Agent did: predict-no for direction U in state State-A
  3248. In State-A moving U
  3249. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3250. predict error 0
  3251. dir: dir isL
  3252. -/|457: O: O913 (predict-yes)
  3253. I see 1 and I'm going to do: predict-yes
  3254. ENV: Agent did: predict-yes for direction L in state State-A
  3255. In State-A moving L
  3256. ENV: (next state, see, prediction correct?) = (State-A, 0, False)
  3257. predict error 1
  3258. dir: dir isL
  3259. \-/458: O: O916 (predict-no)
  3260. I see 0 and I'm going to do: predict-no
  3261. ENV: Agent did: predict-no for direction L in state State-A
  3262. In State-A moving L
  3263. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3264. predict error 0
  3265. dir: dir isR
  3266. |\-459: O: O917 (predict-yes)
  3267. I see 1 and I'm going to do: predict-yes
  3268. ENV: Agent did: predict-yes for direction R in state State-A
  3269. In State-A moving R
  3270. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  3271. predict error 0
  3272. dir: dir isR
  3273. /|\460: O: O920 (predict-no)
  3274. I see 1 and I'm going to do: predict-no
  3275. ENV: Agent did: predict-no for direction R in state State-B
  3276. In State-B moving R
  3277. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3278. predict error 0
  3279. dir: dir isU
  3280. -/|461: O: O922 (predict-no)
  3281. I see 1 and I'm going to do: predict-no
  3282. ENV: Agent did: predict-no for direction U in state State-B
  3283. In State-B moving U
  3284. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3285. predict error 0
  3286. dir: dir isU
  3287. \462: O: O924 (predict-no)
  3288. I see 1 and I'm going to do: predict-no
  3289. ENV: Agent did: predict-no for direction U in state State-B
  3290. In State-B moving U
  3291. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3292. predict error 0
  3293. dir: dir isU
  3294. -/|463: O: O926 (predict-no)
  3295. I see 1 and I'm going to do: predict-no
  3296. ENV: Agent did: predict-no for direction U in state State-B
  3297. In State-B moving U
  3298. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3299. predict error 0
  3300. dir: dir isR
  3301. \-464: O: O928 (predict-no)
  3302. I see 1 and I'm going to do: predict-no
  3303. ENV: Agent did: predict-no for direction R in state State-B
  3304. In State-B moving R
  3305. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3306. predict error 0
  3307. dir: dir isR
  3308. /|\465: O: O930 (predict-no)
  3309. I see 1 and I'm going to do: predict-no
  3310. ENV: Agent did: predict-no for direction R in state State-B
  3311. In State-B moving R
  3312. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3313. predict error 0
  3314. dir: dir isL
  3315. -/|466: O: O931 (predict-yes)
  3316. I see 1 and I'm going to do: predict-yes
  3317. ENV: Agent did: predict-yes for direction L in state State-B
  3318. In State-B moving L
  3319. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  3320. predict error 0
  3321. dir: dir isU
  3322. \-/467: O: O934 (predict-no)
  3323. I see 1 and I'm going to do: predict-no
  3324. ENV: Agent did: predict-no for direction U in state State-A
  3325. In State-A moving U
  3326. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3327. predict error 0
  3328. dir: dir isR
  3329. |\-468: O: O935 (predict-yes)
  3330. I see 1 and I'm going to do: predict-yes
  3331. ENV: Agent did: predict-yes for direction R in state State-A
  3332. In State-A moving R
  3333. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  3334. predict error 0
  3335. dir: dir isL
  3336. /|469: O: O937 (predict-yes)
  3337. I see 1 and I'm going to do: predict-yes
  3338. ENV: Agent did: predict-yes for direction L in state State-B
  3339. In State-B moving L
  3340. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  3341. predict error 0
  3342. dir: dir isR
  3343. \-/470: O: O939 (predict-yes)
  3344. I see 1 and I'm going to do: predict-yes
  3345. ENV: Agent did: predict-yes for direction R in state State-A
  3346. In State-A moving R
  3347. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  3348. predict error 0
  3349. dir: dir isL
  3350. |\-471: O: O941 (predict-yes)
  3351. I see 1 and I'm going to do: predict-yes
  3352. ENV: Agent did: predict-yes for direction L in state State-B
  3353. In State-B moving L
  3354. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  3355. predict error 0
  3356. dir: dir isL
  3357. /472: O: O943 (predict-yes)
  3358. I see 1 and I'm going to do: predict-yes
  3359. ENV: Agent did: predict-yes for direction L in state State-A
  3360. In State-A moving L
  3361. ENV: (next state, see, prediction correct?) = (State-A, 0, False)
  3362. predict error 1
  3363. dir: dir isU
  3364. |\-473: O: O946 (predict-no)
  3365. I see 0 and I'm going to do: predict-no
  3366. ENV: Agent did: predict-no for direction U in state State-A
  3367. In State-A moving U
  3368. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3369. predict error 0
  3370. dir: dir isL
  3371. /|\474: O: O948 (predict-no)
  3372. I see 1 and I'm going to do: predict-no
  3373. ENV: Agent did: predict-no for direction L in state State-A
  3374. In State-A moving L
  3375. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3376. predict error 0
  3377. dir: dir isL
  3378. -/|475: O: O950 (predict-no)
  3379. I see 1 and I'm going to do: predict-no
  3380. ENV: Agent did: predict-no for direction L in state State-A
  3381. In State-A moving L
  3382. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3383. predict error 0
  3384. dir: dir isL
  3385. \-476: O: O952 (predict-no)
  3386. I see 1 and I'm going to do: predict-no
  3387. ENV: Agent did: predict-no for direction L in state State-A
  3388. In State-A moving L
  3389. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3390. predict error 0
  3391. dir: dir isL
  3392. /|\477: O: O953 (predict-yes)
  3393. I see 1 and I'm going to do: predict-yes
  3394. ENV: Agent did: predict-yes for direction L in state State-A
  3395. In State-A moving L
  3396. ENV: (next state, see, prediction correct?) = (State-A, 0, False)
  3397. predict error 1
  3398. dir: dir isR
  3399. -/|478: O: O955 (predict-yes)
  3400. I see 0 and I'm going to do: predict-yes
  3401. ENV: Agent did: predict-yes for direction R in state State-A
  3402. In State-A moving R
  3403. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  3404. predict error 0
  3405. dir: dir isL
  3406. \-479: O: O957 (predict-yes)
  3407. I see 1 and I'm going to do: predict-yes
  3408. ENV: Agent did: predict-yes for direction L in state State-B
  3409. In State-B moving L
  3410. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  3411. predict error 0
  3412. dir: dir isR
  3413. /|\480: O: O959 (predict-yes)
  3414. I see 1 and I'm going to do: predict-yes
  3415. ENV: Agent did: predict-yes for direction R in state State-A
  3416. In State-A moving R
  3417. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  3418. predict error 0
  3419. dir: dir isL
  3420. -/|481: O: O962 (predict-no)
  3421. I see 1 and I'm going to do: predict-no
  3422. ENV: Agent did: predict-no for direction L in state State-B
  3423. In State-B moving L
  3424. ENV: (next state, see, prediction correct?) = (State-A, 1, False)
  3425. predict error 1
  3426. dir: dir isL
  3427. \482: O: O964 (predict-no)
  3428. I see 0 and I'm going to do: predict-no
  3429. ENV: Agent did: predict-no for direction L in state State-A
  3430. In State-A moving L
  3431. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3432. predict error 0
  3433. dir: dir isR
  3434. -/|483: O: O965 (predict-yes)
  3435. I see 1 and I'm going to do: predict-yes
  3436. ENV: Agent did: predict-yes for direction R in state State-A
  3437. In State-A moving R
  3438. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  3439. predict error 0
  3440. dir: dir isR
  3441. \-484: O: O968 (predict-no)
  3442. I see 1 and I'm going to do: predict-no
  3443. ENV: Agent did: predict-no for direction R in state State-B
  3444. In State-B moving R
  3445. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3446. predict error 0
  3447. dir: dir isR
  3448. /|\485: O: O970 (predict-no)
  3449. I see 1 and I'm going to do: predict-no
  3450. ENV: Agent did: predict-no for direction R in state State-B
  3451. In State-B moving R
  3452. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3453. predict error 0
  3454. dir: dir isU
  3455. -/|\486: O: O972 (predict-no)
  3456. I see 1 and I'm going to do: predict-no
  3457. ENV: Agent did: predict-no for direction U in state State-B
  3458. In State-B moving U
  3459. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3460. predict error 0
  3461. dir: dir isL
  3462. -487: O: O973 (predict-yes)
  3463. I see 1 and I'm going to do: predict-yes
  3464. ENV: Agent did: predict-yes for direction L in state State-B
  3465. In State-B moving L
  3466. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  3467. predict error 0
  3468. dir: dir isL
  3469. /|\488: O: O976 (predict-no)
  3470. I see 1 and I'm going to do: predict-no
  3471. ENV: Agent did: predict-no for direction L in state State-A
  3472. In State-A moving L
  3473. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3474. predict error 0
  3475. dir: dir isU
  3476. -/|489: O: O978 (predict-no)
  3477. I see 1 and I'm going to do: predict-no
  3478. ENV: Agent did: predict-no for direction U in state State-A
  3479. In State-A moving U
  3480. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3481. predict error 0
  3482. dir: dir isR
  3483. \-490: O: O979 (predict-yes)
  3484. I see 1 and I'm going to do: predict-yes
  3485. ENV: Agent did: predict-yes for direction R in state State-A
  3486. In State-A moving R
  3487. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  3488. predict error 0
  3489. dir: dir isU
  3490. /|\491: O: O982 (predict-no)
  3491. I see 1 and I'm going to do: predict-no
  3492. ENV: Agent did: predict-no for direction U in state State-B
  3493. In State-B moving U
  3494. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3495. predict error 0
  3496. dir: dir isL
  3497. -492: O: O983 (predict-yes)
  3498. I see 1 and I'm going to do: predict-yes
  3499. ENV: Agent did: predict-yes for direction L in state State-B
  3500. In State-B moving L
  3501. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  3502. predict error 0
  3503. dir: dir isR
  3504. /|493: O: O985 (predict-yes)
  3505. I see 1 and I'm going to do: predict-yes
  3506. ENV: Agent did: predict-yes for direction R in state State-A
  3507. In State-A moving R
  3508. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  3509. predict error 0
  3510. dir: dir isU
  3511. \-/494: O: O988 (predict-no)
  3512. I see 1 and I'm going to do: predict-no
  3513. ENV: Agent did: predict-no for direction U in state State-B
  3514. In State-B moving U
  3515. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3516. predict error 0
  3517. dir: dir isR
  3518. |\-495: O: O990 (predict-no)
  3519. I see 1 and I'm going to do: predict-no
  3520. ENV: Agent did: predict-no for direction R in state State-B
  3521. In State-B moving R
  3522. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3523. predict error 0
  3524. dir: dir isU
  3525. /|496: O: O992 (predict-no)
  3526. I see 1 and I'm going to do: predict-no
  3527. ENV: Agent did: predict-no for direction U in state State-B
  3528. In State-B moving U
  3529. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3530. predict error 0
  3531. dir: dir isR
  3532. \-/497: O: O994 (predict-no)
  3533. I see 1 and I'm going to do: predict-no
  3534. ENV: Agent did: predict-no for direction R in state State-B
  3535. In State-B moving R
  3536. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3537. predict error 0
  3538. dir: dir isR
  3539. |\-498: O: O996 (predict-no)
  3540. I see 1 and I'm going to do: predict-no
  3541. ENV: Agent did: predict-no for direction R in state State-B
  3542. In State-B moving R
  3543. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3544. predict error 0
  3545. dir: dir isU
  3546. /|\499: O: O998 (predict-no)
  3547. I see 1 and I'm going to do: predict-no
  3548. ENV: Agent did: predict-no for direction U in state State-B
  3549. In State-B moving U
  3550. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3551. predict error 0
  3552. dir: dir isR
  3553. -500: O: O1000 (predict-no)
  3554. I see 1 and I'm going to do: predict-no
  3555. ENV: Agent did: predict-no for direction R in state State-B
  3556. In State-B moving R
  3557. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3558. predict error 0
  3559. dir: dir isR
  3560. /|\-501: O: O1002 (predict-no)
  3561. I see 1 and I'm going to do: predict-no
  3562. ENV: Agent did: predict-no for direction R in state State-B
  3563. In State-B moving R
  3564. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3565. predict error 0
  3566. dir: dir isR
  3567. /502: O: O1004 (predict-no)
  3568. I see 1 and I'm going to do: predict-no
  3569. ENV: Agent did: predict-no for direction R in state State-B
  3570. In State-B moving R
  3571. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3572. predict error 0
  3573. dir: dir isL
  3574. |\-503: O: O1005 (predict-yes)
  3575. I see 1 and I'm going to do: predict-yes
  3576. ENV: Agent did: predict-yes for direction L in state State-B
  3577. In State-B moving L
  3578. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  3579. predict error 0
  3580. dir: dir isU
  3581. /|504: O: O1008 (predict-no)
  3582. I see 1 and I'm going to do: predict-no
  3583. ENV: Agent did: predict-no for direction U in state State-A
  3584. In State-A moving U
  3585. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3586. predict error 0
  3587. dir: dir isR
  3588. \-/505: O: O1009 (predict-yes)
  3589. I see 1 and I'm going to do: predict-yes
  3590. ENV: Agent did: predict-yes for direction R in state State-A
  3591. In State-A moving R
  3592. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  3593. predict error 0
  3594. dir: dir isR
  3595. |\-506: O: O1012 (predict-no)
  3596. I see 1 and I'm going to do: predict-no
  3597. ENV: Agent did: predict-no for direction R in state State-B
  3598. In State-B moving R
  3599. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3600. predict error 0
  3601. dir: dir isR
  3602. /|\507: O: O1014 (predict-no)
  3603. I see 1 and I'm going to do: predict-no
  3604. ENV: Agent did: predict-no for direction R in state State-B
  3605. In State-B moving R
  3606. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3607. predict error 0
  3608. dir: dir isU
  3609. -/508: O: O1016 (predict-no)
  3610. I see 1 and I'm going to do: predict-no
  3611. ENV: Agent did: predict-no for direction U in state State-B
  3612. In State-B moving U
  3613. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3614. predict error 0
  3615. dir: dir isU
  3616. |\509: O: O1018 (predict-no)
  3617. I see 1 and I'm going to do: predict-no
  3618. ENV: Agent did: predict-no for direction U in state State-B
  3619. In State-B moving U
  3620. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3621. predict error 0
  3622. dir: dir isU
  3623. -/510: O: O1020 (predict-no)
  3624. I see 1 and I'm going to do: predict-no
  3625. ENV: Agent did: predict-no for direction U in state State-B
  3626. In State-B moving U
  3627. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3628. predict error 0
  3629. dir: dir isR
  3630. |\511: O: O1022 (predict-no)
  3631. I see 1 and I'm going to do: predict-no
  3632. ENV: Agent did: predict-no for direction R in state State-B
  3633. In State-B moving R
  3634. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3635. predict error 0
  3636. dir: dir isR
  3637. -512: O: O1024 (predict-no)
  3638. I see 1 and I'm going to do: predict-no
  3639. ENV: Agent did: predict-no for direction R in state State-B
  3640. In State-B moving R
  3641. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3642. predict error 0
  3643. dir: dir isR
  3644. /|\513: O: O1026 (predict-no)
  3645. I see 1 and I'm going to do: predict-no
  3646. ENV: Agent did: predict-no for direction R in state State-B
  3647. In State-B moving R
  3648. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3649. predict error 0
  3650. dir: dir isL
  3651. -/|514: O: O1027 (predict-yes)
  3652. I see 1 and I'm going to do: predict-yes
  3653. ENV: Agent did: predict-yes for direction L in state State-B
  3654. In State-B moving L
  3655. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  3656. predict error 0
  3657. dir: dir isL
  3658. \-/515: O: O1030 (predict-no)
  3659. I see 1 and I'm going to do: predict-no
  3660. ENV: Agent did: predict-no for direction L in state State-A
  3661. In State-A moving L
  3662. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3663. predict error 0
  3664. dir: dir isU
  3665. |\-516: O: O1032 (predict-no)
  3666. I see 1 and I'm going to do: predict-no
  3667. ENV: Agent did: predict-no for direction U in state State-A
  3668. In State-A moving U
  3669. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3670. predict error 0
  3671. dir: dir isL
  3672. /|\-517: O: O1034 (predict-no)
  3673. I see 1 and I'm going to do: predict-no
  3674. ENV: Agent did: predict-no for direction L in state State-A
  3675. In State-A moving L
  3676. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3677. predict error 0
  3678. dir: dir isU
  3679. /|518: O: O1036 (predict-no)
  3680. I see 1 and I'm going to do: predict-no
  3681. ENV: Agent did: predict-no for direction U in state State-A
  3682. In State-A moving U
  3683. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3684. predict error 0
  3685. dir: dir isU
  3686. \-/|519: O: O1038 (predict-no)
  3687. I see 1 and I'm going to do: predict-no
  3688. ENV: Agent did: predict-no for direction U in state State-A
  3689. In State-A moving U
  3690. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3691. predict error 0
  3692. dir: dir isU
  3693. \-/520: O: O1040 (predict-no)
  3694. I see 1 and I'm going to do: predict-no
  3695. ENV: Agent did: predict-no for direction U in state State-A
  3696. In State-A moving U
  3697. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3698. predict error 0
  3699. dir: dir isL
  3700. |\521: O: O1042 (predict-no)
  3701. I see 1 and I'm going to do: predict-no
  3702. ENV: Agent did: predict-no for direction L in state State-A
  3703. In State-A moving L
  3704. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3705. predict error 0
  3706. dir: dir isL
  3707. -522: O: O1044 (predict-no)
  3708. I see 1 and I'm going to do: predict-no
  3709. ENV: Agent did: predict-no for direction L in state State-A
  3710. In State-A moving L
  3711. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3712. predict error 0
  3713. dir: dir isU
  3714. /|\523: O: O1046 (predict-no)
  3715. I see 1 and I'm going to do: predict-no
  3716. ENV: Agent did: predict-no for direction U in state State-A
  3717. In State-A moving U
  3718. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3719. predict error 0
  3720. dir: dir isL
  3721. -/524: O: O1048 (predict-no)
  3722. I see 1 and I'm going to do: predict-no
  3723. ENV: Agent did: predict-no for direction L in state State-A
  3724. In State-A moving L
  3725. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3726. predict error 0
  3727. dir: dir isL
  3728. |\525: O: O1050 (predict-no)
  3729. I see 1 and I'm going to do: predict-no
  3730. ENV: Agent did: predict-no for direction L in state State-A
  3731. In State-A moving L
  3732. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3733. predict error 0
  3734. dir: dir isR
  3735. -/526: O: O1052 (predict-no)
  3736. I see 1 and I'm going to do: predict-no
  3737. ENV: Agent did: predict-no for direction R in state State-A
  3738. In State-A moving R
  3739. ENV: (next state, see, prediction correct?) = (State-B, 1, False)
  3740. predict error 1
  3741. dir: dir isL
  3742. |\527: O: O1053 (predict-yes)
  3743. I see 0 and I'm going to do: predict-yes
  3744. ENV: Agent did: predict-yes for direction L in state State-B
  3745. In State-B moving L
  3746. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  3747. predict error 0
  3748. dir: dir isL
  3749. -/|528: O: O1056 (predict-no)
  3750. I see 1 and I'm going to do: predict-no
  3751. ENV: Agent did: predict-no for direction L in state State-A
  3752. In State-A moving L
  3753. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3754. predict error 0
  3755. dir: dir isU
  3756. \-/529: O: O1058 (predict-no)
  3757. I see 1 and I'm going to do: predict-no
  3758. ENV: Agent did: predict-no for direction U in state State-A
  3759. In State-A moving U
  3760. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3761. predict error 0
  3762. dir: dir isL
  3763. |\-530: O: O1060 (predict-no)
  3764. I see 1 and I'm going to do: predict-no
  3765. ENV: Agent did: predict-no for direction L in state State-A
  3766. In State-A moving L
  3767. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3768. predict error 0
  3769. dir: dir isU
  3770. /|\531: O: O1062 (predict-no)
  3771. I see 1 and I'm going to do: predict-no
  3772. ENV: Agent did: predict-no for direction U in state State-A
  3773. In State-A moving U
  3774. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3775. predict error 0
  3776. dir: dir isR
  3777. -532: O: O1063 (predict-yes)
  3778. I see 1 and I'm going to do: predict-yes
  3779. ENV: Agent did: predict-yes for direction R in state State-A
  3780. In State-A moving R
  3781. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  3782. predict error 0
  3783. dir: dir isL
  3784. /|\533: O: O1065 (predict-yes)
  3785. I see 1 and I'm going to do: predict-yes
  3786. ENV: Agent did: predict-yes for direction L in state State-B
  3787. In State-B moving L
  3788. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  3789. predict error 0
  3790. dir: dir isU
  3791. -/534: O: O1068 (predict-no)
  3792. I see 1 and I'm going to do: predict-no
  3793. ENV: Agent did: predict-no for direction U in state State-A
  3794. In State-A moving U
  3795. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3796. predict error 0
  3797. dir: dir isL
  3798. |\-535: O: O1070 (predict-no)
  3799. I see 1 and I'm going to do: predict-no
  3800. ENV: Agent did: predict-no for direction L in state State-A
  3801. In State-A moving L
  3802. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3803. predict error 0
  3804. dir: dir isR
  3805. /|\536: O: O1071 (predict-yes)
  3806. I see 1 and I'm going to do: predict-yes
  3807. ENV: Agent did: predict-yes for direction R in state State-A
  3808. In State-A moving R
  3809. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  3810. predict error 0
  3811. dir: dir isR
  3812. -/|537: O: O1074 (predict-no)
  3813. I see 1 and I'm going to do: predict-no
  3814. ENV: Agent did: predict-no for direction R in state State-B
  3815. In State-B moving R
  3816. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3817. predict error 0
  3818. dir: dir isL
  3819. \-/538: O: O1075 (predict-yes)
  3820. I see 1 and I'm going to do: predict-yes
  3821. ENV: Agent did: predict-yes for direction L in state State-B
  3822. In State-B moving L
  3823. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  3824. predict error 0
  3825. dir: dir isR
  3826. |\-539: O: O1077 (predict-yes)
  3827. I see 1 and I'm going to do: predict-yes
  3828. ENV: Agent did: predict-yes for direction R in state State-A
  3829. In State-A moving R
  3830. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  3831. predict error 0
  3832. dir: dir isL
  3833. /|\540: O: O1079 (predict-yes)
  3834. I see 1 and I'm going to do: predict-yes
  3835. ENV: Agent did: predict-yes for direction L in state State-B
  3836. In State-B moving L
  3837. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  3838. predict error 0
  3839. dir: dir isL
  3840. -/|541: O: O1082 (predict-no)
  3841. I see 1 and I'm going to do: predict-no
  3842. ENV: Agent did: predict-no for direction L in state State-A
  3843. In State-A moving L
  3844. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3845. predict error 0
  3846. dir: dir isU
  3847. \542: O: O1084 (predict-no)
  3848. I see 1 and I'm going to do: predict-no
  3849. ENV: Agent did: predict-no for direction U in state State-A
  3850. In State-A moving U
  3851. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3852. predict error 0
  3853. dir: dir isU
  3854. -/|543: O: O1086 (predict-no)
  3855. I see 1 and I'm going to do: predict-no
  3856. ENV: Agent did: predict-no for direction U in state State-A
  3857. In State-A moving U
  3858. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3859. predict error 0
  3860. dir: dir isR
  3861. \-/|544: O: O1087 (predict-yes)
  3862. I see 1 and I'm going to do: predict-yes
  3863. ENV: Agent did: predict-yes for direction R in state State-A
  3864. In State-A moving R
  3865. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  3866. predict error 0
  3867. dir: dir isU
  3868. \-/545: O: O1090 (predict-no)
  3869. I see 1 and I'm going to do: predict-no
  3870. ENV: Agent did: predict-no for direction U in state State-B
  3871. In State-B moving U
  3872. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3873. predict error 0
  3874. dir: dir isU
  3875. |\-546: O: O1092 (predict-no)
  3876. I see 1 and I'm going to do: predict-no
  3877. ENV: Agent did: predict-no for direction U in state State-B
  3878. In State-B moving U
  3879. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3880. predict error 0
  3881. dir: dir isL
  3882. /|\547: O: O1093 (predict-yes)
  3883. I see 1 and I'm going to do: predict-yes
  3884. ENV: Agent did: predict-yes for direction L in state State-B
  3885. In State-B moving L
  3886. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  3887. predict error 0
  3888. dir: dir isR
  3889. -/|548: O: O1095 (predict-yes)
  3890. I see 1 and I'm going to do: predict-yes
  3891. ENV: Agent did: predict-yes for direction R in state State-A
  3892. In State-A moving R
  3893. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  3894. predict error 0
  3895. dir: dir isL
  3896. \549: O: O1097 (predict-yes)
  3897. I see 1 and I'm going to do: predict-yes
  3898. ENV: Agent did: predict-yes for direction L in state State-B
  3899. In State-B moving L
  3900. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  3901. predict error 0
  3902. dir: dir isL
  3903. -/|550: O: O1100 (predict-no)
  3904. I see 1 and I'm going to do: predict-no
  3905. ENV: Agent did: predict-no for direction L in state State-A
  3906. In State-A moving L
  3907. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3908. predict error 0
  3909. dir: dir isL
  3910. \-/551: O: O1102 (predict-no)
  3911. I see 1 and I'm going to do: predict-no
  3912. ENV: Agent did: predict-no for direction L in state State-A
  3913. In State-A moving L
  3914. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3915. predict error 0
  3916. dir: dir isL
  3917. |552: O: O1104 (predict-no)
  3918. I see 1 and I'm going to do: predict-no
  3919. ENV: Agent did: predict-no for direction L in state State-A
  3920. In State-A moving L
  3921. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3922. predict error 0
  3923. dir: dir isL
  3924. \-/553: O: O1106 (predict-no)
  3925. I see 1 and I'm going to do: predict-no
  3926. ENV: Agent did: predict-no for direction L in state State-A
  3927. In State-A moving L
  3928. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3929. predict error 0
  3930. dir: dir isL
  3931. |\-554: O: O1108 (predict-no)
  3932. I see 1 and I'm going to do: predict-no
  3933. ENV: Agent did: predict-no for direction L in state State-A
  3934. In State-A moving L
  3935. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3936. predict error 0
  3937. dir: dir isR
  3938. /|555: O: O1109 (predict-yes)
  3939. I see 1 and I'm going to do: predict-yes
  3940. ENV: Agent did: predict-yes for direction R in state State-A
  3941. In State-A moving R
  3942. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  3943. predict error 0
  3944. dir: dir isR
  3945. \-/556: O: O1112 (predict-no)
  3946. I see 1 and I'm going to do: predict-no
  3947. ENV: Agent did: predict-no for direction R in state State-B
  3948. In State-B moving R
  3949. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3950. predict error 0
  3951. dir: dir isU
  3952. |\-557: O: O1114 (predict-no)
  3953. I see 1 and I'm going to do: predict-no
  3954. ENV: Agent did: predict-no for direction U in state State-B
  3955. In State-B moving U
  3956. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3957. predict error 0
  3958. dir: dir isU
  3959. /|558: O: O1116 (predict-no)
  3960. I see 1 and I'm going to do: predict-no
  3961. ENV: Agent did: predict-no for direction U in state State-B
  3962. In State-B moving U
  3963. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3964. predict error 0
  3965. dir: dir isU
  3966. \-/559: O: O1117 (predict-yes)
  3967. I see 1 and I'm going to do: predict-yes
  3968. ENV: Agent did: predict-yes for direction U in state State-B
  3969. In State-B moving U
  3970. ENV: (next state, see, prediction correct?) = (State-B, 0, False)
  3971. predict error 1
  3972. dir: dir isR
  3973. |\-560: O: O1120 (predict-no)
  3974. I see 0 and I'm going to do: predict-no
  3975. ENV: Agent did: predict-no for direction R in state State-B
  3976. In State-B moving R
  3977. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3978. predict error 0
  3979. dir: dir isU
  3980. /|561: O: O1122 (predict-no)
  3981. I see 1 and I'm going to do: predict-no
  3982. ENV: Agent did: predict-no for direction U in state State-B
  3983. In State-B moving U
  3984. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  3985. predict error 0
  3986. dir: dir isL
  3987. \562: O: O1123 (predict-yes)
  3988. I see 1 and I'm going to do: predict-yes
  3989. ENV: Agent did: predict-yes for direction L in state State-B
  3990. In State-B moving L
  3991. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  3992. predict error 0
  3993. dir: dir isL
  3994. -/|563: O: O1126 (predict-no)
  3995. I see 1 and I'm going to do: predict-no
  3996. ENV: Agent did: predict-no for direction L in state State-A
  3997. In State-A moving L
  3998. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  3999. predict error 0
  4000. dir: dir isU
  4001. \-/564: O: O1128 (predict-no)
  4002. I see 1 and I'm going to do: predict-no
  4003. ENV: Agent did: predict-no for direction U in state State-A
  4004. In State-A moving U
  4005. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4006. predict error 0
  4007. dir: dir isR
  4008. |\-565: O: O1129 (predict-yes)
  4009. I see 1 and I'm going to do: predict-yes
  4010. ENV: Agent did: predict-yes for direction R in state State-A
  4011. In State-A moving R
  4012. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  4013. predict error 0
  4014. dir: dir isL
  4015. /|\566: O: O1131 (predict-yes)
  4016. I see 1 and I'm going to do: predict-yes
  4017. ENV: Agent did: predict-yes for direction L in state State-B
  4018. In State-B moving L
  4019. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  4020. predict error 0
  4021. dir: dir isR
  4022. -/|567: O: O1133 (predict-yes)
  4023. I see 1 and I'm going to do: predict-yes
  4024. ENV: Agent did: predict-yes for direction R in state State-A
  4025. In State-A moving R
  4026. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  4027. predict error 0
  4028. dir: dir isL
  4029. \-/568: O: O1135 (predict-yes)
  4030. I see 1 and I'm going to do: predict-yes
  4031. ENV: Agent did: predict-yes for direction L in state State-B
  4032. In State-B moving L
  4033. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  4034. predict error 0
  4035. dir: dir isR
  4036. |\-569: O: O1137 (predict-yes)
  4037. I see 1 and I'm going to do: predict-yes
  4038. ENV: Agent did: predict-yes for direction R in state State-A
  4039. In State-A moving R
  4040. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  4041. predict error 0
  4042. dir: dir isR
  4043. /570: O: O1140 (predict-no)
  4044. I see 1 and I'm going to do: predict-no
  4045. ENV: Agent did: predict-no for direction R in state State-B
  4046. In State-B moving R
  4047. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4048. predict error 0
  4049. dir: dir isR
  4050. |\-571: O: O1142 (predict-no)
  4051. I see 1 and I'm going to do: predict-no
  4052. ENV: Agent did: predict-no for direction R in state State-B
  4053. In State-B moving R
  4054. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4055. predict error 0
  4056. dir: dir isU
  4057. /572: O: O1144 (predict-no)
  4058. I see 1 and I'm going to do: predict-no
  4059. ENV: Agent did: predict-no for direction U in state State-B
  4060. In State-B moving U
  4061. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4062. predict error 0
  4063. dir: dir isU
  4064. |\-573: O: O1146 (predict-no)
  4065. I see 1 and I'm going to do: predict-no
  4066. ENV: Agent did: predict-no for direction U in state State-B
  4067. In State-B moving U
  4068. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4069. predict error 0
  4070. dir: dir isR
  4071. /|\574: O: O1148 (predict-no)
  4072. I see 1 and I'm going to do: predict-no
  4073. ENV: Agent did: predict-no for direction R in state State-B
  4074. In State-B moving R
  4075. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4076. predict error 0
  4077. dir: dir isR
  4078. -/|575: O: O1150 (predict-no)
  4079. I see 1 and I'm going to do: predict-no
  4080. ENV: Agent did: predict-no for direction R in state State-B
  4081. In State-B moving R
  4082. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4083. predict error 0
  4084. dir: dir isL
  4085. \-/576: O: O1151 (predict-yes)
  4086. I see 1 and I'm going to do: predict-yes
  4087. ENV: Agent did: predict-yes for direction L in state State-B
  4088. In State-B moving L
  4089. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  4090. predict error 0
  4091. dir: dir isU
  4092. |\577: O: O1154 (predict-no)
  4093. I see 1 and I'm going to do: predict-no
  4094. ENV: Agent did: predict-no for direction U in state State-A
  4095. In State-A moving U
  4096. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4097. predict error 0
  4098. dir: dir isU
  4099. -/|578: O: O1156 (predict-no)
  4100. I see 1 and I'm going to do: predict-no
  4101. ENV: Agent did: predict-no for direction U in state State-A
  4102. In State-A moving U
  4103. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4104. predict error 0
  4105. dir: dir isL
  4106. \-/|579: O: O1158 (predict-no)
  4107. I see 1 and I'm going to do: predict-no
  4108. ENV: Agent did: predict-no for direction L in state State-A
  4109. In State-A moving L
  4110. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4111. predict error 0
  4112. dir: dir isU
  4113. \-/|580: O: O1160 (predict-no)
  4114. I see 1 and I'm going to do: predict-no
  4115. ENV: Agent did: predict-no for direction U in state State-A
  4116. In State-A moving U
  4117. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4118. predict error 0
  4119. dir: dir isU
  4120. \-/581: O: O1162 (predict-no)
  4121. I see 1 and I'm going to do: predict-no
  4122. ENV: Agent did: predict-no for direction U in state State-A
  4123. In State-A moving U
  4124. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4125. predict error 0
  4126. dir: dir isR
  4127. |582: O: O1163 (predict-yes)
  4128. I see 1 and I'm going to do: predict-yes
  4129. ENV: Agent did: predict-yes for direction R in state State-A
  4130. In State-A moving R
  4131. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  4132. predict error 0
  4133. dir: dir isL
  4134. \-/583: O: O1165 (predict-yes)
  4135. I see 1 and I'm going to do: predict-yes
  4136. ENV: Agent did: predict-yes for direction L in state State-B
  4137. In State-B moving L
  4138. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  4139. predict error 0
  4140. dir: dir isR
  4141. |\-584: O: O1167 (predict-yes)
  4142. I see 1 and I'm going to do: predict-yes
  4143. ENV: Agent did: predict-yes for direction R in state State-A
  4144. In State-A moving R
  4145. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  4146. predict error 0
  4147. dir: dir isL
  4148. /|585: O: O1169 (predict-yes)
  4149. I see 1 and I'm going to do: predict-yes
  4150. ENV: Agent did: predict-yes for direction L in state State-B
  4151. In State-B moving L
  4152. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  4153. predict error 0
  4154. dir: dir isL
  4155. \-/586: O: O1172 (predict-no)
  4156. I see 1 and I'm going to do: predict-no
  4157. ENV: Agent did: predict-no for direction L in state State-A
  4158. In State-A moving L
  4159. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4160. predict error 0
  4161. dir: dir isR
  4162. |\587: O: O1173 (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 isR
  4169. -/|588: O: O1176 (predict-no)
  4170. I see 1 and I'm going to do: predict-no
  4171. ENV: Agent did: predict-no for direction R in state State-B
  4172. In State-B moving R
  4173. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4174. predict error 0
  4175. dir: dir isR
  4176. \-/589: O: O1178 (predict-no)
  4177. I see 1 and I'm going to do: predict-no
  4178. ENV: Agent did: predict-no for direction R in state State-B
  4179. In State-B moving R
  4180. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4181. predict error 0
  4182. dir: dir isU
  4183. |590: O: O1180 (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-B
  4186. In State-B moving U
  4187. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4188. predict error 0
  4189. dir: dir isU
  4190. \-/591: O: O1182 (predict-no)
  4191. I see 1 and I'm going to do: predict-no
  4192. ENV: Agent did: predict-no for direction U in state State-B
  4193. In State-B moving U
  4194. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4195. predict error 0
  4196. dir: dir isR
  4197. |592: O: O1184 (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. \-593: O: O1185 (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. /|\594: O: O1188 (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 isU
  4218. -/|595: O: O1190 (predict-no)
  4219. I see 1 and I'm going to do: predict-no
  4220. ENV: Agent did: predict-no for direction U in state State-A
  4221. In State-A moving U
  4222. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4223. predict error 0
  4224. dir: dir isU
  4225. \-/596: O: O1192 (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-A
  4228. In State-A moving U
  4229. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4230. predict error 0
  4231. dir: dir isR
  4232. |\597: O: O1193 (predict-yes)
  4233. I see 1 and I'm going to do: predict-yes
  4234. ENV: Agent did: predict-yes for direction R in state State-A
  4235. In State-A moving R
  4236. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  4237. predict error 0
  4238. dir: dir isL
  4239. -/|598: O: O1195 (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 isL
  4246. \-/599: O: O1198 (predict-no)
  4247. I see 1 and I'm going to do: predict-no
  4248. ENV: Agent did: predict-no for direction L in state State-A
  4249. In State-A moving L
  4250. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4251. predict error 0
  4252. dir: dir isL
  4253. |\600: O: O1200 (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 isR
  4260. -/|\601: O: O1201 (predict-yes)
  4261. I see 1 and I'm going to do: predict-yes
  4262. ENV: Agent did: predict-yes for direction R in state State-A
  4263. In State-A moving R
  4264. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  4265. predict error 0
  4266. dir: dir isR
  4267. -602: O: O1204 (predict-no)
  4268. I see 1 and I'm going to do: predict-no
  4269. ENV: Agent did: predict-no for direction R in state State-B
  4270. In State-B moving R
  4271. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4272. predict error 0
  4273. dir: dir isL
  4274. /|\603: O: O1205 (predict-yes)
  4275. I see 1 and I'm going to do: predict-yes
  4276. ENV: Agent did: predict-yes for direction L in state State-B
  4277. In State-B moving L
  4278. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  4279. predict error 0
  4280. dir: dir isU
  4281. -/|604: O: O1208 (predict-no)
  4282. I see 1 and I'm going to do: predict-no
  4283. ENV: Agent did: predict-no for direction U in state State-A
  4284. In State-A moving U
  4285. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4286. predict error 0
  4287. dir: dir isU
  4288. \-/605: O: O1209 (predict-yes)
  4289. I see 1 and I'm going to do: predict-yes
  4290. ENV: Agent did: predict-yes for direction U in state State-A
  4291. In State-A moving U
  4292. ENV: (next state, see, prediction correct?) = (State-A, 0, False)
  4293. predict error 1
  4294. dir: dir isU
  4295. |\-606: O: O1212 (predict-no)
  4296. I see 0 and I'm going to do: predict-no
  4297. ENV: Agent did: predict-no for direction U in state State-A
  4298. In State-A moving U
  4299. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4300. predict error 0
  4301. dir: dir isR
  4302. /|\607: O: O1213 (predict-yes)
  4303. I see 1 and I'm going to do: predict-yes
  4304. ENV: Agent did: predict-yes for direction R in state State-A
  4305. In State-A moving R
  4306. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  4307. predict error 0
  4308. dir: dir isL
  4309. -/608: O: O1215 (predict-yes)
  4310. I see 1 and I'm going to do: predict-yes
  4311. ENV: Agent did: predict-yes for direction L in state State-B
  4312. In State-B moving L
  4313. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  4314. predict error 0
  4315. dir: dir isL
  4316. |\609: O: O1218 (predict-no)
  4317. I see 1 and I'm going to do: predict-no
  4318. ENV: Agent did: predict-no for direction L in state State-A
  4319. In State-A moving L
  4320. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4321. predict error 0
  4322. dir: dir isU
  4323. -/610: O: O1220 (predict-no)
  4324. I see 1 and I'm going to do: predict-no
  4325. ENV: Agent did: predict-no for direction U in state State-A
  4326. In State-A moving U
  4327. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4328. predict error 0
  4329. dir: dir isU
  4330. |\-611: O: O1222 (predict-no)
  4331. I see 1 and I'm going to do: predict-no
  4332. ENV: Agent did: predict-no for direction U in state State-A
  4333. In State-A moving U
  4334. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4335. predict error 0
  4336. dir: dir isL
  4337. /612: O: O1224 (predict-no)
  4338. I see 1 and I'm going to do: predict-no
  4339. ENV: Agent did: predict-no for direction L in state State-A
  4340. In State-A moving L
  4341. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4342. predict error 0
  4343. dir: dir isU
  4344. |\-613: O: O1226 (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. /614: O: O1227 (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 isR
  4358. |615: O: O1230 (predict-no)
  4359. I see 1 and I'm going to do: predict-no
  4360. ENV: Agent did: predict-no for direction R in state State-B
  4361. In State-B moving R
  4362. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4363. predict error 0
  4364. dir: dir isR
  4365. \-/616: O: O1232 (predict-no)
  4366. I see 1 and I'm going to do: predict-no
  4367. ENV: Agent did: predict-no for direction R in state State-B
  4368. In State-B moving R
  4369. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4370. predict error 0
  4371. dir: dir isU
  4372. |\-617: O: O1234 (predict-no)
  4373. I see 1 and I'm going to do: predict-no
  4374. ENV: Agent did: predict-no for direction U in state State-B
  4375. In State-B moving U
  4376. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4377. predict error 0
  4378. dir: dir isR
  4379. /618: O: O1236 (predict-no)
  4380. I see 1 and I'm going to do: predict-no
  4381. ENV: Agent did: predict-no for direction R in state State-B
  4382. In State-B moving R
  4383. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4384. predict error 0
  4385. dir: dir isR
  4386. |\-619: O: O1238 (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. /|\620: O: O1239 (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. -/|621: O: O1242 (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. \622: O: O1244 (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 isU
  4414. -/|623: O: O1246 (predict-no)
  4415. I see 1 and I'm going to do: predict-no
  4416. ENV: Agent did: predict-no for direction U in state State-A
  4417. In State-A moving U
  4418. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4419. predict error 0
  4420. dir: dir isL
  4421. \-/624: O: O1248 (predict-no)
  4422. I see 1 and I'm going to do: predict-no
  4423. ENV: Agent did: predict-no for direction L in state State-A
  4424. In State-A moving L
  4425. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4426. predict error 0
  4427. dir: dir isL
  4428. |\-625: O: O1250 (predict-no)
  4429. I see 1 and I'm going to do: predict-no
  4430. ENV: Agent did: predict-no for direction L in state State-A
  4431. In State-A moving L
  4432. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4433. predict error 0
  4434. dir: dir isR
  4435. /|\626: O: O1251 (predict-yes)
  4436. I see 1 and I'm going to do: predict-yes
  4437. ENV: Agent did: predict-yes for direction R in state State-A
  4438. In State-A moving R
  4439. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  4440. predict error 0
  4441. dir: dir isR
  4442. -/627: O: O1254 (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. |\-628: O: O1256 (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 isU
  4456. /|\629: O: O1258 (predict-no)
  4457. I see 1 and I'm going to do: predict-no
  4458. ENV: Agent did: predict-no for direction U in state State-B
  4459. In State-B moving U
  4460. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4461. predict error 0
  4462. dir: dir isL
  4463. -/630: O: O1259 (predict-yes)
  4464. I see 1 and I'm going to do: predict-yes
  4465. ENV: Agent did: predict-yes for direction L in state State-B
  4466. In State-B moving L
  4467. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  4468. predict error 0
  4469. dir: dir isU
  4470. |\-/631: O: O1262 (predict-no)
  4471. I see 1 and I'm going to do: predict-no
  4472. ENV: Agent did: predict-no for direction U in state State-A
  4473. In State-A moving U
  4474. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4475. predict error 0
  4476. dir: dir isU
  4477. |632: O: O1264 (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-A
  4480. In State-A moving U
  4481. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4482. predict error 0
  4483. dir: dir isU
  4484. \-/633: O: O1266 (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-A
  4487. In State-A moving U
  4488. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4489. predict error 0
  4490. dir: dir isR
  4491. |\634: O: O1267 (predict-yes)
  4492. I see 1 and I'm going to do: predict-yes
  4493. ENV: Agent did: predict-yes for direction R in state State-A
  4494. In State-A moving R
  4495. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  4496. predict error 0
  4497. dir: dir isR
  4498. -/|635: O: O1270 (predict-no)
  4499. I see 1 and I'm going to do: predict-no
  4500. ENV: Agent did: predict-no for direction R in state State-B
  4501. In State-B moving R
  4502. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4503. predict error 0
  4504. dir: dir isR
  4505. \636: O: O1272 (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 isR
  4512. -/637: O: O1274 (predict-no)
  4513. I see 1 and I'm going to do: predict-no
  4514. ENV: Agent did: predict-no for direction R in state State-B
  4515. In State-B moving R
  4516. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4517. predict error 0
  4518. dir: dir isL
  4519. |\-638: O: O1275 (predict-yes)
  4520. I see 1 and I'm going to do: predict-yes
  4521. ENV: Agent did: predict-yes for direction L in state State-B
  4522. In State-B moving L
  4523. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  4524. predict error 0
  4525. dir: dir isL
  4526. /|\639: O: O1278 (predict-no)
  4527. I see 1 and I'm going to do: predict-no
  4528. ENV: Agent did: predict-no for direction L in state State-A
  4529. In State-A moving L
  4530. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4531. predict error 0
  4532. dir: dir isR
  4533. -/640: O: O1279 (predict-yes)
  4534. I see 1 and I'm going to do: predict-yes
  4535. ENV: Agent did: predict-yes for direction R in state State-A
  4536. In State-A moving R
  4537. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  4538. predict error 0
  4539. dir: dir isL
  4540. |\641: O: O1281 (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 isR
  4547. -642: O: O1283 (predict-yes)
  4548. I see 1 and I'm going to do: predict-yes
  4549. ENV: Agent did: predict-yes for direction R in state State-A
  4550. In State-A moving R
  4551. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  4552. predict error 0
  4553. dir: dir isR
  4554. /|\643: O: O1286 (predict-no)
  4555. I see 1 and I'm going to do: predict-no
  4556. ENV: Agent did: predict-no for direction R in state State-B
  4557. In State-B moving R
  4558. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4559. predict error 0
  4560. dir: dir isL
  4561. -/|644: O: O1287 (predict-yes)
  4562. I see 1 and I'm going to do: predict-yes
  4563. ENV: Agent did: predict-yes for direction L in state State-B
  4564. In State-B moving L
  4565. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  4566. predict error 0
  4567. dir: dir isL
  4568. \-/645: O: O1290 (predict-no)
  4569. I see 1 and I'm going to do: predict-no
  4570. ENV: Agent did: predict-no for direction L in state State-A
  4571. In State-A moving L
  4572. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4573. predict error 0
  4574. dir: dir isR
  4575. |\-646: O: O1291 (predict-yes)
  4576. I see 1 and I'm going to do: predict-yes
  4577. ENV: Agent did: predict-yes for direction R in state State-A
  4578. In State-A moving R
  4579. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  4580. predict error 0
  4581. dir: dir isU
  4582. /|\647: O: O1294 (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. -/|648: O: O1295 (predict-yes)
  4590. I see 1 and I'm going to do: predict-yes
  4591. ENV: Agent did: predict-yes for direction L in state State-B
  4592. In State-B moving L
  4593. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  4594. predict error 0
  4595. dir: dir isR
  4596. \-649: O: O1297 (predict-yes)
  4597. I see 1 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 isR
  4603. /|\650: O: O1300 (predict-no)
  4604. I see 1 and I'm going to do: predict-no
  4605. ENV: Agent did: predict-no for direction R in state State-B
  4606. In State-B moving R
  4607. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4608. predict error 0
  4609. dir: dir isU
  4610. -/|651: O: O1302 (predict-no)
  4611. I see 1 and I'm going to do: predict-no
  4612. ENV: Agent did: predict-no for direction U in state State-B
  4613. In State-B moving U
  4614. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4615. predict error 0
  4616. dir: dir isU
  4617. \652: O: O1304 (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-B
  4620. In State-B moving U
  4621. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4622. predict error 0
  4623. dir: dir isL
  4624. -/|653: O: O1305 (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-B
  4627. In State-B moving L
  4628. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  4629. predict error 0
  4630. dir: dir isL
  4631. \-/654: O: O1308 (predict-no)
  4632. I see 1 and I'm going to do: predict-no
  4633. ENV: Agent did: predict-no for direction L in state State-A
  4634. In State-A moving L
  4635. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4636. predict error 0
  4637. dir: dir isU
  4638. |\-655: O: O1310 (predict-no)
  4639. I see 1 and I'm going to do: predict-no
  4640. ENV: Agent did: predict-no for direction U in state State-A
  4641. In State-A moving U
  4642. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4643. predict error 0
  4644. dir: dir isL
  4645. /|656: O: O1312 (predict-no)
  4646. I see 1 and I'm going to do: predict-no
  4647. ENV: Agent did: predict-no for direction L in state State-A
  4648. In State-A moving L
  4649. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4650. predict error 0
  4651. dir: dir isL
  4652. \-/657: O: O1314 (predict-no)
  4653. I see 1 and I'm going to do: predict-no
  4654. ENV: Agent did: predict-no for direction L in state State-A
  4655. In State-A moving L
  4656. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4657. predict error 0
  4658. dir: dir isU
  4659. |\-658: O: O1316 (predict-no)
  4660. I see 1 and I'm going to do: predict-no
  4661. ENV: Agent did: predict-no for direction U in state State-A
  4662. In State-A moving U
  4663. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4664. predict error 0
  4665. dir: dir isL
  4666. /|\659: O: O1318 (predict-no)
  4667. I see 1 and I'm going to do: predict-no
  4668. ENV: Agent did: predict-no for direction L in state State-A
  4669. In State-A moving L
  4670. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4671. predict error 0
  4672. dir: dir isL
  4673. -/|660: O: O1320 (predict-no)
  4674. I see 1 and I'm going to do: predict-no
  4675. ENV: Agent did: predict-no for direction L in state State-A
  4676. In State-A moving L
  4677. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4678. predict error 0
  4679. dir: dir isL
  4680. \-661: O: O1322 (predict-no)
  4681. I see 1 and I'm going to do: predict-no
  4682. ENV: Agent did: predict-no for direction L in state State-A
  4683. In State-A moving L
  4684. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4685. predict error 0
  4686. dir: dir isL
  4687. /662: O: O1324 (predict-no)
  4688. I see 1 and I'm going to do: predict-no
  4689. ENV: Agent did: predict-no for direction L in state State-A
  4690. In State-A moving L
  4691. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4692. predict error 0
  4693. dir: dir isU
  4694. |\663: O: O1326 (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 isR
  4701. -/|664: O: O1327 (predict-yes)
  4702. I see 1 and I'm going to do: predict-yes
  4703. ENV: Agent did: predict-yes for direction R in state State-A
  4704. In State-A moving R
  4705. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  4706. predict error 0
  4707. dir: dir isR
  4708. \-/665: O: O1330 (predict-no)
  4709. I see 1 and I'm going to do: predict-no
  4710. ENV: Agent did: predict-no for direction R in state State-B
  4711. In State-B moving R
  4712. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4713. predict error 0
  4714. dir: dir isR
  4715. |\666: O: O1332 (predict-no)
  4716. I see 1 and I'm going to do: predict-no
  4717. ENV: Agent did: predict-no for direction R in state State-B
  4718. In State-B moving R
  4719. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4720. predict error 0
  4721. dir: dir isU
  4722. -/|667: O: O1334 (predict-no)
  4723. I see 1 and I'm going to do: predict-no
  4724. ENV: Agent did: predict-no for direction U in state State-B
  4725. In State-B moving U
  4726. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4727. predict error 0
  4728. dir: dir isL
  4729. \-/668: O: O1335 (predict-yes)
  4730. I see 1 and I'm going to do: predict-yes
  4731. ENV: Agent did: predict-yes for direction L in state State-B
  4732. In State-B moving L
  4733. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  4734. predict error 0
  4735. dir: dir isR
  4736. |\-669: O: O1337 (predict-yes)
  4737. I see 1 and I'm going to do: predict-yes
  4738. ENV: Agent did: predict-yes for direction R in state State-A
  4739. In State-A moving R
  4740. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  4741. predict error 0
  4742. dir: dir isL
  4743. /670: O: O1339 (predict-yes)
  4744. I see 1 and I'm going to do: predict-yes
  4745. ENV: Agent did: predict-yes for direction L in state State-B
  4746. In State-B moving L
  4747. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  4748. predict error 0
  4749. dir: dir isL
  4750. |\-671: O: O1342 (predict-no)
  4751. I see 1 and I'm going to do: predict-no
  4752. ENV: Agent did: predict-no for direction L in state State-A
  4753. In State-A moving L
  4754. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4755. predict error 0
  4756. dir: dir isR
  4757. /672: O: O1343 (predict-yes)
  4758. I see 1 and I'm going to do: predict-yes
  4759. ENV: Agent did: predict-yes for direction R in state State-A
  4760. In State-A moving R
  4761. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  4762. predict error 0
  4763. dir: dir isR
  4764. |\-673: O: O1346 (predict-no)
  4765. I see 1 and I'm going to do: predict-no
  4766. ENV: Agent did: predict-no for direction R in state State-B
  4767. In State-B moving R
  4768. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4769. predict error 0
  4770. dir: dir isL
  4771. /|\674: O: O1347 (predict-yes)
  4772. I see 1 and I'm going to do: predict-yes
  4773. ENV: Agent did: predict-yes for direction L in state State-B
  4774. In State-B moving L
  4775. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  4776. predict error 0
  4777. dir: dir isR
  4778. -/|675: O: O1349 (predict-yes)
  4779. I see 1 and I'm going to do: predict-yes
  4780. ENV: Agent did: predict-yes for direction R in state State-A
  4781. In State-A moving R
  4782. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  4783. predict error 0
  4784. dir: dir isU
  4785. \-/676: O: O1352 (predict-no)
  4786. I see 1 and I'm going to do: predict-no
  4787. ENV: Agent did: predict-no for direction U in state State-B
  4788. In State-B moving U
  4789. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4790. predict error 0
  4791. dir: dir isR
  4792. |\-677: O: O1354 (predict-no)
  4793. I see 1 and I'm going to do: predict-no
  4794. ENV: Agent did: predict-no for direction R in state State-B
  4795. In State-B moving R
  4796. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4797. predict error 0
  4798. dir: dir isR
  4799. /|\678: O: O1356 (predict-no)
  4800. I see 1 and I'm going to do: predict-no
  4801. ENV: Agent did: predict-no for direction R in state State-B
  4802. In State-B moving R
  4803. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4804. predict error 0
  4805. dir: dir isU
  4806. -/|679: O: O1358 (predict-no)
  4807. I see 1 and I'm going to do: predict-no
  4808. ENV: Agent did: predict-no for direction U in state State-B
  4809. In State-B moving U
  4810. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4811. predict error 0
  4812. dir: dir isU
  4813. \-/680: O: O1360 (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 isL
  4820. |\-/681: O: O1361 (predict-yes)
  4821. I see 1 and I'm going to do: predict-yes
  4822. ENV: Agent did: predict-yes for direction L in state State-B
  4823. In State-B moving L
  4824. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  4825. predict error 0
  4826. dir: dir isL
  4827. |682: O: O1364 (predict-no)
  4828. I see 1 and I'm going to do: predict-no
  4829. ENV: Agent did: predict-no for direction L in state State-A
  4830. In State-A moving L
  4831. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4832. predict error 0
  4833. dir: dir isU
  4834. \-/683: O: O1366 (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-A
  4837. In State-A moving U
  4838. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4839. predict error 0
  4840. dir: dir isU
  4841. |\684: O: O1368 (predict-no)
  4842. I see 1 and I'm going to do: predict-no
  4843. ENV: Agent did: predict-no for direction U in state State-A
  4844. In State-A moving U
  4845. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4846. predict error 0
  4847. dir: dir isL
  4848. -/|685: O: O1370 (predict-no)
  4849. I see 1 and I'm going to do: predict-no
  4850. ENV: Agent did: predict-no for direction L in state State-A
  4851. In State-A moving L
  4852. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4853. predict error 0
  4854. dir: dir isU
  4855. \-/686: O: O1372 (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 isU
  4862. |\-687: O: O1374 (predict-no)
  4863. I see 1 and I'm going to do: predict-no
  4864. ENV: Agent did: predict-no for direction U in state State-A
  4865. In State-A moving U
  4866. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4867. predict error 0
  4868. dir: dir isR
  4869. /|\688: O: O1375 (predict-yes)
  4870. I see 1 and I'm going to do: predict-yes
  4871. ENV: Agent did: predict-yes for direction R in state State-A
  4872. In State-A moving R
  4873. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  4874. predict error 0
  4875. dir: dir isU
  4876. -/689: O: O1378 (predict-no)
  4877. I see 1 and I'm going to do: predict-no
  4878. ENV: Agent did: predict-no for direction U in state State-B
  4879. In State-B moving U
  4880. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4881. predict error 0
  4882. dir: dir isR
  4883. |\690: O: O1380 (predict-no)
  4884. I see 1 and I'm going to do: predict-no
  4885. ENV: Agent did: predict-no for direction R in state State-B
  4886. In State-B moving R
  4887. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4888. predict error 0
  4889. dir: dir isL
  4890. -/|691: O: O1381 (predict-yes)
  4891. I see 1 and I'm going to do: predict-yes
  4892. ENV: Agent did: predict-yes for direction L in state State-B
  4893. In State-B moving L
  4894. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  4895. predict error 0
  4896. dir: dir isL
  4897. \692: O: O1384 (predict-no)
  4898. I see 1 and I'm going to do: predict-no
  4899. ENV: Agent did: predict-no for direction L in state State-A
  4900. In State-A moving L
  4901. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4902. predict error 0
  4903. dir: dir isL
  4904. -/|693: O: O1386 (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 isR
  4911. \-/694: O: O1387 (predict-yes)
  4912. I see 1 and I'm going to do: predict-yes
  4913. ENV: Agent did: predict-yes for direction R in state State-A
  4914. In State-A moving R
  4915. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  4916. predict error 0
  4917. dir: dir isL
  4918. |\-695: O: O1389 (predict-yes)
  4919. I see 1 and I'm going to do: predict-yes
  4920. ENV: Agent did: predict-yes for direction L in state State-B
  4921. In State-B moving L
  4922. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  4923. predict error 0
  4924. dir: dir isR
  4925. /|696: O: O1391 (predict-yes)
  4926. I see 1 and I'm going to do: predict-yes
  4927. ENV: Agent did: predict-yes for direction R in state State-A
  4928. In State-A moving R
  4929. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  4930. predict error 0
  4931. dir: dir isR
  4932. \-/697: O: O1394 (predict-no)
  4933. I see 1 and I'm going to do: predict-no
  4934. ENV: Agent did: predict-no for direction R in state State-B
  4935. In State-B moving R
  4936. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4937. predict error 0
  4938. dir: dir isR
  4939. |\-698: O: O1396 (predict-no)
  4940. I see 1 and I'm going to do: predict-no
  4941. ENV: Agent did: predict-no for direction R in state State-B
  4942. In State-B moving R
  4943. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4944. predict error 0
  4945. dir: dir isU
  4946. /|\699: O: O1398 (predict-no)
  4947. I see 1 and I'm going to do: predict-no
  4948. ENV: Agent did: predict-no for direction U in state State-B
  4949. In State-B moving U
  4950. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4951. predict error 0
  4952. dir: dir isR
  4953. -/|700: O: O1400 (predict-no)
  4954. I see 1 and I'm going to do: predict-no
  4955. ENV: Agent did: predict-no for direction R in state State-B
  4956. In State-B moving R
  4957. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4958. predict error 0
  4959. dir: dir isR
  4960. \-701: O: O1402 (predict-no)
  4961. I see 1 and I'm going to do: predict-no
  4962. ENV: Agent did: predict-no for direction R in state State-B
  4963. In State-B moving R
  4964. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4965. predict error 0
  4966. dir: dir isR
  4967. /702: O: O1404 (predict-no)
  4968. I see 1 and I'm going to do: predict-no
  4969. ENV: Agent did: predict-no for direction R in state State-B
  4970. In State-B moving R
  4971. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  4972. predict error 0
  4973. dir: dir isL
  4974. |\-703: O: O1405 (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 isL
  4981. /|\704: O: O1408 (predict-no)
  4982. I see 1 and I'm going to do: predict-no
  4983. ENV: Agent did: predict-no for direction L in state State-A
  4984. In State-A moving L
  4985. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  4986. predict error 0
  4987. dir: dir isR
  4988. -/|705: O: O1409 (predict-yes)
  4989. I see 1 and I'm going to do: predict-yes
  4990. ENV: Agent did: predict-yes for direction R in state State-A
  4991. In State-A moving R
  4992. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  4993. predict error 0
  4994. dir: dir isU
  4995. \-/706: O: O1412 (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 isL
  5002. |\-707: O: O1413 (predict-yes)
  5003. I see 1 and I'm going to do: predict-yes
  5004. ENV: Agent did: predict-yes for direction L in state State-B
  5005. In State-B moving L
  5006. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  5007. predict error 0
  5008. dir: dir isU
  5009. /|\708: O: O1416 (predict-no)
  5010. I see 1 and I'm going to do: predict-no
  5011. ENV: Agent did: predict-no for direction U in state State-A
  5012. In State-A moving U
  5013. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  5014. predict error 0
  5015. dir: dir isU
  5016. -/709: O: O1418 (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 isL
  5023. |\710: O: O1420 (predict-no)
  5024. I see 1 and I'm going to do: predict-no
  5025. ENV: Agent did: predict-no for direction L in state State-A
  5026. In State-A moving L
  5027. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  5028. predict error 0
  5029. dir: dir isU
  5030. -/|711: O: O1422 (predict-no)
  5031. I see 1 and I'm going to do: predict-no
  5032. ENV: Agent did: predict-no for direction U in state State-A
  5033. In State-A moving U
  5034. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  5035. predict error 0
  5036. dir: dir isR
  5037. \712: O: O1423 (predict-yes)
  5038. I see 1 and I'm going to do: predict-yes
  5039. ENV: Agent did: predict-yes for direction R in state State-A
  5040. In State-A moving R
  5041. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  5042. predict error 0
  5043. dir: dir isR
  5044. -/|713: O: O1426 (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 isL
  5051. \-/714: O: O1427 (predict-yes)
  5052. I see 1 and I'm going to do: predict-yes
  5053. ENV: Agent did: predict-yes for direction L in state State-B
  5054. In State-B moving L
  5055. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  5056. predict error 0
  5057. dir: dir isR
  5058. |\715: O: O1429 (predict-yes)
  5059. I see 1 and I'm going to do: predict-yes
  5060. ENV: Agent did: predict-yes for direction R in state State-A
  5061. In State-A moving R
  5062. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  5063. predict error 0
  5064. dir: dir isR
  5065. -/|716: O: O1432 (predict-no)
  5066. I see 1 and I'm going to do: predict-no
  5067. ENV: Agent did: predict-no for direction R in state State-B
  5068. In State-B moving R
  5069. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5070. predict error 0
  5071. dir: dir isU
  5072. \-/717: O: O1434 (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. |\-718: O: O1436 (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 isU
  5086. /|\719: O: O1438 (predict-no)
  5087. I see 1 and I'm going to do: predict-no
  5088. ENV: Agent did: predict-no for direction U in state State-B
  5089. In State-B moving U
  5090. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5091. predict error 0
  5092. dir: dir isU
  5093. -/|720: O: O1440 (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. \-/721: O: O1441 (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. |722: O: O1444 (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 isR
  5114. \-/723: O: O1445 (predict-yes)
  5115. I see 1 and I'm going to do: predict-yes
  5116. ENV: Agent did: predict-yes for direction R in state State-A
  5117. In State-A moving R
  5118. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  5119. predict error 0
  5120. dir: dir isL
  5121. |\-724: O: O1447 (predict-yes)
  5122. I see 1 and I'm going to do: predict-yes
  5123. ENV: Agent did: predict-yes for direction L in state State-B
  5124. In State-B moving L
  5125. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  5126. predict error 0
  5127. dir: dir isL
  5128. /|\725: O: O1450 (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 isL
  5135. -/|726: O: O1452 (predict-no)
  5136. I see 1 and I'm going to do: predict-no
  5137. ENV: Agent did: predict-no for direction L in state State-A
  5138. In State-A moving L
  5139. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  5140. predict error 0
  5141. dir: dir isR
  5142. \-727: O: O1453 (predict-yes)
  5143. I see 1 and I'm going to do: predict-yes
  5144. ENV: Agent did: predict-yes for direction R in state State-A
  5145. In State-A moving R
  5146. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  5147. predict error 0
  5148. dir: dir isR
  5149. /|728: O: O1456 (predict-no)
  5150. I see 1 and I'm going to do: predict-no
  5151. ENV: Agent did: predict-no for direction R in state State-B
  5152. In State-B moving R
  5153. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5154. predict error 0
  5155. dir: dir isR
  5156. \-/729: O: O1458 (predict-no)
  5157. I see 1 and I'm going to do: predict-no
  5158. ENV: Agent did: predict-no for direction R in state State-B
  5159. In State-B moving R
  5160. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5161. predict error 0
  5162. dir: dir isU
  5163. |\730: O: O1460 (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-B
  5166. In State-B moving U
  5167. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5168. predict error 0
  5169. dir: dir isL
  5170. -/|731: O: O1461 (predict-yes)
  5171. I see 1 and I'm going to do: predict-yes
  5172. ENV: Agent did: predict-yes for direction L in state State-B
  5173. In State-B moving L
  5174. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  5175. predict error 0
  5176. dir: dir isR
  5177. \732: O: O1463 (predict-yes)
  5178. I see 1 and I'm going to do: predict-yes
  5179. ENV: Agent did: predict-yes for direction R in state State-A
  5180. In State-A moving R
  5181. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  5182. predict error 0
  5183. dir: dir isL
  5184. -/|733: O: O1465 (predict-yes)
  5185. I see 1 and I'm going to do: predict-yes
  5186. ENV: Agent did: predict-yes for direction L in state State-B
  5187. In State-B moving L
  5188. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  5189. predict error 0
  5190. dir: dir isU
  5191. \-734: O: O1468 (predict-no)
  5192. I see 1 and I'm going to do: predict-no
  5193. ENV: Agent did: predict-no for direction U in state State-A
  5194. In State-A moving U
  5195. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  5196. predict error 0
  5197. dir: dir isR
  5198. /|\-735: O: O1469 (predict-yes)
  5199. I see 1 and I'm going to do: predict-yes
  5200. ENV: Agent did: predict-yes for direction R in state State-A
  5201. In State-A moving R
  5202. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  5203. predict error 0
  5204. dir: dir isL
  5205. /|\736: O: O1471 (predict-yes)
  5206. I see 1 and I'm going to do: predict-yes
  5207. ENV: Agent did: predict-yes for direction L in state State-B
  5208. In State-B moving L
  5209. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  5210. predict error 0
  5211. dir: dir isL
  5212. -/|737: O: O1474 (predict-no)
  5213. I see 1 and I'm going to do: predict-no
  5214. ENV: Agent did: predict-no for direction L in state State-A
  5215. In State-A moving L
  5216. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  5217. predict error 0
  5218. dir: dir isR
  5219. \-738: O: O1475 (predict-yes)
  5220. I see 1 and I'm going to do: predict-yes
  5221. ENV: Agent did: predict-yes for direction R in state State-A
  5222. In State-A moving R
  5223. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  5224. predict error 0
  5225. dir: dir isR
  5226. /|\739: O: O1478 (predict-no)
  5227. I see 1 and I'm going to do: predict-no
  5228. ENV: Agent did: predict-no for direction R in state State-B
  5229. In State-B moving R
  5230. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5231. predict error 0
  5232. dir: dir isU
  5233. -/|740: O: O1480 (predict-no)
  5234. I see 1 and I'm going to do: predict-no
  5235. ENV: Agent did: predict-no for direction U in state State-B
  5236. In State-B moving U
  5237. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5238. predict error 0
  5239. dir: dir isR
  5240. \-741: O: O1482 (predict-no)
  5241. I see 1 and I'm going to do: predict-no
  5242. ENV: Agent did: predict-no for direction R in state State-B
  5243. In State-B moving R
  5244. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5245. predict error 0
  5246. dir: dir isR
  5247. /742: O: O1484 (predict-no)
  5248. I see 1 and I'm going to do: predict-no
  5249. ENV: Agent did: predict-no for direction R in state State-B
  5250. In State-B moving R
  5251. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5252. predict error 0
  5253. dir: dir isU
  5254. |\-743: O: O1486 (predict-no)
  5255. I see 1 and I'm going to do: predict-no
  5256. ENV: Agent did: predict-no for direction U in state State-B
  5257. In State-B moving U
  5258. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5259. predict error 0
  5260. dir: dir isR
  5261. /|\744: O: O1488 (predict-no)
  5262. I see 1 and I'm going to do: predict-no
  5263. ENV: Agent did: predict-no for direction R in state State-B
  5264. In State-B moving R
  5265. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5266. predict error 0
  5267. dir: dir isL
  5268. -/|745: O: O1489 (predict-yes)
  5269. I see 1 and I'm going to do: predict-yes
  5270. ENV: Agent did: predict-yes for direction L in state State-B
  5271. In State-B moving L
  5272. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  5273. predict error 0
  5274. dir: dir isU
  5275. \-746: O: O1492 (predict-no)
  5276. I see 1 and I'm going to do: predict-no
  5277. ENV: Agent did: predict-no for direction U in state State-A
  5278. In State-A moving U
  5279. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  5280. predict error 0
  5281. dir: dir isR
  5282. /|747: O: O1493 (predict-yes)
  5283. I see 1 and I'm going to do: predict-yes
  5284. ENV: Agent did: predict-yes for direction R in state State-A
  5285. In State-A moving R
  5286. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  5287. predict error 0
  5288. dir: dir isU
  5289. \-/748: O: O1496 (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-B
  5292. In State-B moving U
  5293. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5294. predict error 0
  5295. dir: dir isR
  5296. |\749: O: O1498 (predict-no)
  5297. I see 1 and I'm going to do: predict-no
  5298. ENV: Agent did: predict-no for direction R in state State-B
  5299. In State-B moving R
  5300. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5301. predict error 0
  5302. dir: dir isU
  5303. -/|750: O: O1500 (predict-no)
  5304. I see 1 and I'm going to do: predict-no
  5305. ENV: Agent did: predict-no for direction U in state State-B
  5306. In State-B moving U
  5307. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5308. predict error 0
  5309. dir: dir isU
  5310. \-/751: O: O1502 (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-B
  5313. In State-B moving U
  5314. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5315. predict error 0
  5316. dir: dir isR
  5317. |752: O: O1504 (predict-no)
  5318. I see 1 and I'm going to do: predict-no
  5319. ENV: Agent did: predict-no for direction R in state State-B
  5320. In State-B moving R
  5321. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5322. predict error 0
  5323. dir: dir isU
  5324. \-/753: O: O1506 (predict-no)
  5325. I see 1 and I'm going to do: predict-no
  5326. ENV: Agent did: predict-no for direction U in state State-B
  5327. In State-B moving U
  5328. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5329. predict error 0
  5330. dir: dir isL
  5331. |\-754: O: O1507 (predict-yes)
  5332. I see 1 and I'm going to do: predict-yes
  5333. ENV: Agent did: predict-yes for direction L in state State-B
  5334. In State-B moving L
  5335. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  5336. predict error 0
  5337. dir: dir isR
  5338. /|755: O: O1509 (predict-yes)
  5339. I see 1 and I'm going to do: predict-yes
  5340. ENV: Agent did: predict-yes for direction R in state State-A
  5341. In State-A moving R
  5342. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  5343. predict error 0
  5344. dir: dir isU
  5345. \-/|756: O: O1512 (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-B
  5348. In State-B moving U
  5349. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5350. predict error 0
  5351. dir: dir isL
  5352. \-/757: O: O1513 (predict-yes)
  5353. I see 1 and I'm going to do: predict-yes
  5354. ENV: Agent did: predict-yes for direction L in state State-B
  5355. In State-B moving L
  5356. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  5357. predict error 0
  5358. dir: dir isU
  5359. |\758: O: O1516 (predict-no)
  5360. I see 1 and I'm going to do: predict-no
  5361. ENV: Agent did: predict-no for direction U in state State-A
  5362. In State-A moving U
  5363. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  5364. predict error 0
  5365. dir: dir isU
  5366. -/|759: O: O1518 (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-A
  5369. In State-A moving U
  5370. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  5371. predict error 0
  5372. dir: dir isU
  5373. \-/760: O: O1520 (predict-no)
  5374. I see 1 and I'm going to do: predict-no
  5375. ENV: Agent did: predict-no for direction U in state State-A
  5376. In State-A moving U
  5377. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  5378. predict error 0
  5379. dir: dir isU
  5380. |\-761: O: O1522 (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 isL
  5387. /762: O: O1524 (predict-no)
  5388. I see 1 and I'm going to do: predict-no
  5389. ENV: Agent did: predict-no for direction L in state State-A
  5390. In State-A moving L
  5391. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  5392. predict error 0
  5393. dir: dir isR
  5394. |\-763: O: O1526 (predict-no)
  5395. I see 1 and I'm going to do: predict-no
  5396. ENV: Agent did: predict-no for direction R in state State-A
  5397. In State-A moving R
  5398. ENV: (next state, see, prediction correct?) = (State-B, 1, False)
  5399. predict error 1
  5400. dir: dir isR
  5401. /|\764: O: O1528 (predict-no)
  5402. I see 0 and I'm going to do: predict-no
  5403. ENV: Agent did: predict-no for direction R in state State-B
  5404. In State-B moving R
  5405. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5406. predict error 0
  5407. dir: dir isR
  5408. -/765: O: O1530 (predict-no)
  5409. I see 1 and I'm going to do: predict-no
  5410. ENV: Agent did: predict-no for direction R in state State-B
  5411. In State-B moving R
  5412. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5413. predict error 0
  5414. dir: dir isR
  5415. |\-766: O: O1532 (predict-no)
  5416. I see 1 and I'm going to do: predict-no
  5417. ENV: Agent did: predict-no for direction R in state State-B
  5418. In State-B moving R
  5419. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5420. predict error 0
  5421. dir: dir isU
  5422. /|\767: O: O1534 (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-B
  5425. In State-B moving U
  5426. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5427. predict error 0
  5428. dir: dir isL
  5429. -/|768: O: O1535 (predict-yes)
  5430. I see 1 and I'm going to do: predict-yes
  5431. ENV: Agent did: predict-yes for direction L in state State-B
  5432. In State-B moving L
  5433. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  5434. predict error 0
  5435. dir: dir isL
  5436. \-769: O: O1538 (predict-no)
  5437. I see 1 and I'm going to do: predict-no
  5438. ENV: Agent did: predict-no for direction L in state State-A
  5439. In State-A moving L
  5440. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  5441. predict error 0
  5442. dir: dir isR
  5443. /|\770: O: O1539 (predict-yes)
  5444. I see 1 and I'm going to do: predict-yes
  5445. ENV: Agent did: predict-yes for direction R in state State-A
  5446. In State-A moving R
  5447. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  5448. predict error 0
  5449. dir: dir isU
  5450. -/|771: O: O1542 (predict-no)
  5451. I see 1 and I'm going to do: predict-no
  5452. ENV: Agent did: predict-no for direction U in state State-B
  5453. In State-B moving U
  5454. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5455. predict error 0
  5456. dir: dir isU
  5457. \772: O: O1544 (predict-no)
  5458. I see 1 and I'm going to do: predict-no
  5459. ENV: Agent did: predict-no for direction U in state State-B
  5460. In State-B moving U
  5461. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5462. predict error 0
  5463. dir: dir isU
  5464. -/773: O: O1546 (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 isL
  5471. |\-774: O: O1547 (predict-yes)
  5472. I see 1 and I'm going to do: predict-yes
  5473. ENV: Agent did: predict-yes for direction L in state State-B
  5474. In State-B moving L
  5475. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  5476. predict error 0
  5477. dir: dir isU
  5478. /|\775: O: O1550 (predict-no)
  5479. I see 1 and I'm going to do: predict-no
  5480. ENV: Agent did: predict-no for direction U in state State-A
  5481. In State-A moving U
  5482. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  5483. predict error 0
  5484. dir: dir isL
  5485. -/776: O: O1552 (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 isL
  5492. |777: O: O1554 (predict-no)
  5493. I see 1 and I'm going to do: predict-no
  5494. ENV: Agent did: predict-no for direction L in state State-A
  5495. In State-A moving L
  5496. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  5497. predict error 0
  5498. dir: dir isU
  5499. \-/778: O: O1556 (predict-no)
  5500. I see 1 and I'm going to do: predict-no
  5501. ENV: Agent did: predict-no for direction U in state State-A
  5502. In State-A moving U
  5503. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  5504. predict error 0
  5505. dir: dir isU
  5506. |\-779: O: O1558 (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 isR
  5513. /|\780: O: O1559 (predict-yes)
  5514. I see 1 and I'm going to do: predict-yes
  5515. ENV: Agent did: predict-yes for direction R in state State-A
  5516. In State-A moving R
  5517. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  5518. predict error 0
  5519. dir: dir isU
  5520. -/|781: O: O1562 (predict-no)
  5521. I see 1 and I'm going to do: predict-no
  5522. ENV: Agent did: predict-no for direction U in state State-B
  5523. In State-B moving U
  5524. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5525. predict error 0
  5526. dir: dir isL
  5527. \782: O: O1563 (predict-yes)
  5528. I see 1 and I'm going to do: predict-yes
  5529. ENV: Agent did: predict-yes for direction L in state State-B
  5530. In State-B moving L
  5531. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  5532. predict error 0
  5533. dir: dir isR
  5534. -/783: O: O1565 (predict-yes)
  5535. I see 1 and I'm going to do: predict-yes
  5536. ENV: Agent did: predict-yes for direction R in state State-A
  5537. In State-A moving R
  5538. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  5539. predict error 0
  5540. dir: dir isL
  5541. |\-784: O: O1567 (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 isL
  5548. /|785: O: O1570 (predict-no)
  5549. I see 1 and I'm going to do: predict-no
  5550. ENV: Agent did: predict-no for direction L in state State-A
  5551. In State-A moving L
  5552. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  5553. predict error 0
  5554. dir: dir isL
  5555. \-786: O: O1572 (predict-no)
  5556. I see 1 and I'm going to do: predict-no
  5557. ENV: Agent did: predict-no for direction L in state State-A
  5558. In State-A moving L
  5559. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  5560. predict error 0
  5561. dir: dir isL
  5562. /787: O: O1574 (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. |\-788: O: O1575 (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. /|\789: O: O1578 (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 isL
  5583. -/|\790: O: O1579 (predict-yes)
  5584. I see 1 and I'm going to do: predict-yes
  5585. ENV: Agent did: predict-yes for direction L in state State-B
  5586. In State-B moving L
  5587. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  5588. predict error 0
  5589. dir: dir isR
  5590. -/|\791: O: O1581 (predict-yes)
  5591. I see 1 and I'm going to do: predict-yes
  5592. ENV: Agent did: predict-yes for direction R in state State-A
  5593. In State-A moving R
  5594. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  5595. predict error 0
  5596. dir: dir isL
  5597. -792: O: O1583 (predict-yes)
  5598. I see 1 and I'm going to do: predict-yes
  5599. ENV: Agent did: predict-yes for direction L in state State-B
  5600. In State-B moving L
  5601. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  5602. predict error 0
  5603. dir: dir isR
  5604. /|793: O: O1585 (predict-yes)
  5605. I see 1 and I'm going to do: predict-yes
  5606. ENV: Agent did: predict-yes for direction R in state State-A
  5607. In State-A moving R
  5608. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  5609. predict error 0
  5610. dir: dir isR
  5611. \-794: O: O1588 (predict-no)
  5612. I see 1 and I'm going to do: predict-no
  5613. ENV: Agent did: predict-no for direction R in state State-B
  5614. In State-B moving R
  5615. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5616. predict error 0
  5617. dir: dir isR
  5618. /|\795: O: O1590 (predict-no)
  5619. I see 1 and I'm going to do: predict-no
  5620. ENV: Agent did: predict-no for direction R in state State-B
  5621. In State-B moving R
  5622. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5623. predict error 0
  5624. dir: dir isU
  5625. -/|796: O: O1592 (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-B
  5628. In State-B moving U
  5629. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5630. predict error 0
  5631. dir: dir isL
  5632. \-/|797: O: O1593 (predict-yes)
  5633. I see 1 and I'm going to do: predict-yes
  5634. ENV: Agent did: predict-yes for direction L in state State-B
  5635. In State-B moving L
  5636. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  5637. predict error 0
  5638. dir: dir isR
  5639. \-/798: O: O1595 (predict-yes)
  5640. I see 1 and I'm going to do: predict-yes
  5641. ENV: Agent did: predict-yes for direction R in state State-A
  5642. In State-A moving R
  5643. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  5644. predict error 0
  5645. dir: dir isR
  5646. |\799: O: O1598 (predict-no)
  5647. I see 1 and I'm going to do: predict-no
  5648. ENV: Agent did: predict-no for direction R in state State-B
  5649. In State-B moving R
  5650. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5651. predict error 0
  5652. dir: dir isR
  5653. -/800: O: O1600 (predict-no)
  5654. I see 1 and I'm going to do: predict-no
  5655. ENV: Agent did: predict-no for direction R in state State-B
  5656. In State-B moving R
  5657. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5658. predict error 0
  5659. dir: dir isU
  5660. |\-801: O: O1602 (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. /802: O: O1604 (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 isR
  5674. |\-803: O: O1606 (predict-no)
  5675. I see 1 and I'm going to do: predict-no
  5676. ENV: Agent did: predict-no for direction R in state State-B
  5677. In State-B moving R
  5678. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5679. predict error 0
  5680. dir: dir isR
  5681. /|\804: O: O1608 (predict-no)
  5682. I see 1 and I'm going to do: predict-no
  5683. ENV: Agent did: predict-no for direction R in state State-B
  5684. In State-B moving R
  5685. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5686. predict error 0
  5687. dir: dir isR
  5688. -/|805: O: O1610 (predict-no)
  5689. I see 1 and I'm going to do: predict-no
  5690. ENV: Agent did: predict-no for direction R in state State-B
  5691. In State-B moving R
  5692. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5693. predict error 0
  5694. dir: dir isU
  5695. \-/806: O: O1612 (predict-no)
  5696. I see 1 and I'm going to do: predict-no
  5697. ENV: Agent did: predict-no for direction U in state State-B
  5698. In State-B moving U
  5699. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5700. predict error 0
  5701. dir: dir isU
  5702. |\-807: O: O1614 (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-B
  5705. In State-B moving U
  5706. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5707. predict error 0
  5708. dir: dir isR
  5709. /|\808: O: O1616 (predict-no)
  5710. I see 1 and I'm going to do: predict-no
  5711. ENV: Agent did: predict-no for direction R in state State-B
  5712. In State-B moving R
  5713. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5714. predict error 0
  5715. dir: dir isL
  5716. -/|809: O: O1617 (predict-yes)
  5717. I see 1 and I'm going to do: predict-yes
  5718. ENV: Agent did: predict-yes for direction L in state State-B
  5719. In State-B moving L
  5720. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  5721. predict error 0
  5722. dir: dir isR
  5723. \-/810: O: O1619 (predict-yes)
  5724. I see 1 and I'm going to do: predict-yes
  5725. ENV: Agent did: predict-yes for direction R in state State-A
  5726. In State-A moving R
  5727. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  5728. predict error 0
  5729. dir: dir isL
  5730. |\811: O: O1621 (predict-yes)
  5731. I see 1 and I'm going to do: predict-yes
  5732. ENV: Agent did: predict-yes for direction L in state State-B
  5733. In State-B moving L
  5734. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  5735. predict error 0
  5736. dir: dir isR
  5737. -812: O: O1623 (predict-yes)
  5738. I see 1 and I'm going to do: predict-yes
  5739. ENV: Agent did: predict-yes for direction R in state State-A
  5740. In State-A moving R
  5741. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  5742. predict error 0
  5743. dir: dir isL
  5744. /|\813: O: O1625 (predict-yes)
  5745. I see 1 and I'm going to do: predict-yes
  5746. ENV: Agent did: predict-yes for direction L in state State-B
  5747. In State-B moving L
  5748. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  5749. predict error 0
  5750. dir: dir isU
  5751. -/|814: O: O1628 (predict-no)
  5752. I see 1 and I'm going to do: predict-no
  5753. ENV: Agent did: predict-no for direction U in state State-A
  5754. In State-A moving U
  5755. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  5756. predict error 0
  5757. dir: dir isU
  5758. \-815: O: O1630 (predict-no)
  5759. I see 1 and I'm going to do: predict-no
  5760. ENV: Agent did: predict-no for direction U in state State-A
  5761. In State-A moving U
  5762. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  5763. predict error 0
  5764. dir: dir isR
  5765. /|\816: O: O1631 (predict-yes)
  5766. I see 1 and I'm going to do: predict-yes
  5767. ENV: Agent did: predict-yes for direction R in state State-A
  5768. In State-A moving R
  5769. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  5770. predict error 0
  5771. dir: dir isR
  5772. -/|817: O: O1634 (predict-no)
  5773. I see 1 and I'm going to do: predict-no
  5774. ENV: Agent did: predict-no for direction R in state State-B
  5775. In State-B moving R
  5776. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5777. predict error 0
  5778. dir: dir isL
  5779. \-/818: O: O1635 (predict-yes)
  5780. I see 1 and I'm going to do: predict-yes
  5781. ENV: Agent did: predict-yes for direction L in state State-B
  5782. In State-B moving L
  5783. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  5784. predict error 0
  5785. dir: dir isR
  5786. |\819: O: O1637 (predict-yes)
  5787. I see 1 and I'm going to do: predict-yes
  5788. ENV: Agent did: predict-yes for direction R in state State-A
  5789. In State-A moving R
  5790. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  5791. predict error 0
  5792. dir: dir isR
  5793. -/|820: O: O1640 (predict-no)
  5794. I see 1 and I'm going to do: predict-no
  5795. ENV: Agent did: predict-no for direction R in state State-B
  5796. In State-B moving R
  5797. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5798. predict error 0
  5799. dir: dir isR
  5800. \-/821: O: O1642 (predict-no)
  5801. I see 1 and I'm going to do: predict-no
  5802. ENV: Agent did: predict-no for direction R in state State-B
  5803. In State-B moving R
  5804. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5805. predict error 0
  5806. dir: dir isL
  5807. |822: O: O1643 (predict-yes)
  5808. I see 1 and I'm going to do: predict-yes
  5809. ENV: Agent did: predict-yes for direction L in state State-B
  5810. In State-B moving L
  5811. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  5812. predict error 0
  5813. dir: dir isL
  5814. \-/823: O: O1646 (predict-no)
  5815. I see 1 and I'm going to do: predict-no
  5816. ENV: Agent did: predict-no for direction L in state State-A
  5817. In State-A moving L
  5818. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  5819. predict error 0
  5820. dir: dir isU
  5821. |\-824: O: O1648 (predict-no)
  5822. I see 1 and I'm going to do: predict-no
  5823. ENV: Agent did: predict-no for direction U in state State-A
  5824. In State-A moving U
  5825. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  5826. predict error 0
  5827. dir: dir isU
  5828. /|\825: O: O1650 (predict-no)
  5829. I see 1 and I'm going to do: predict-no
  5830. ENV: Agent did: predict-no for direction U in state State-A
  5831. In State-A moving U
  5832. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  5833. predict error 0
  5834. dir: dir isU
  5835. -/|826: O: O1652 (predict-no)
  5836. I see 1 and I'm going to do: predict-no
  5837. ENV: Agent did: predict-no for direction U in state State-A
  5838. In State-A moving U
  5839. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  5840. predict error 0
  5841. dir: dir isR
  5842. \-/827: O: O1653 (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 isL
  5849. |\-/828: O: O1655 (predict-yes)
  5850. I see 1 and I'm going to do: predict-yes
  5851. ENV: Agent did: predict-yes for direction L in state State-B
  5852. In State-B moving L
  5853. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  5854. predict error 0
  5855. dir: dir isL
  5856. |\-829: O: O1658 (predict-no)
  5857. I see 1 and I'm going to do: predict-no
  5858. ENV: Agent did: predict-no for direction L in state State-A
  5859. In State-A moving L
  5860. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  5861. predict error 0
  5862. dir: dir isU
  5863. /|\830: O: O1660 (predict-no)
  5864. I see 1 and I'm going to do: predict-no
  5865. ENV: Agent did: predict-no for direction U in state State-A
  5866. In State-A moving U
  5867. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  5868. predict error 0
  5869. dir: dir isU
  5870. -/831: O: O1662 (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 isR
  5877. |832: O: O1663 (predict-yes)
  5878. I see 1 and I'm going to do: predict-yes
  5879. ENV: Agent did: predict-yes for direction R in state State-A
  5880. In State-A moving R
  5881. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  5882. predict error 0
  5883. dir: dir isR
  5884. \-/833: O: O1666 (predict-no)
  5885. I see 1 and I'm going to do: predict-no
  5886. ENV: Agent did: predict-no for direction R in state State-B
  5887. In State-B moving R
  5888. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5889. predict error 0
  5890. dir: dir isU
  5891. |\-834: O: O1668 (predict-no)
  5892. I see 1 and I'm going to do: predict-no
  5893. ENV: Agent did: predict-no for direction U in state State-B
  5894. In State-B moving U
  5895. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5896. predict error 0
  5897. dir: dir isL
  5898. /|\835: O: O1669 (predict-yes)
  5899. I see 1 and I'm going to do: predict-yes
  5900. ENV: Agent did: predict-yes for direction L in state State-B
  5901. In State-B moving L
  5902. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  5903. predict error 0
  5904. dir: dir isU
  5905. -/|836: O: O1672 (predict-no)
  5906. I see 1 and I'm going to do: predict-no
  5907. ENV: Agent did: predict-no for direction U in state State-A
  5908. In State-A moving U
  5909. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  5910. predict error 0
  5911. dir: dir isR
  5912. \-/837: O: O1673 (predict-yes)
  5913. I see 1 and I'm going to do: predict-yes
  5914. ENV: Agent did: predict-yes for direction R in state State-A
  5915. In State-A moving R
  5916. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  5917. predict error 0
  5918. dir: dir isU
  5919. |\-838: O: O1676 (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-B
  5922. In State-B moving U
  5923. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5924. predict error 0
  5925. dir: dir isR
  5926. /|\-839: O: O1678 (predict-no)
  5927. I see 1 and I'm going to do: predict-no
  5928. ENV: Agent did: predict-no for direction R in state State-B
  5929. In State-B moving R
  5930. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5931. predict error 0
  5932. dir: dir isR
  5933. /|\840: O: O1680 (predict-no)
  5934. I see 1 and I'm going to do: predict-no
  5935. ENV: Agent did: predict-no for direction R in state State-B
  5936. In State-B moving R
  5937. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5938. predict error 0
  5939. dir: dir isR
  5940. -/|841: O: O1682 (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. \842: O: O1684 (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 isR
  5954. -/|843: O: O1686 (predict-no)
  5955. I see 1 and I'm going to do: predict-no
  5956. ENV: Agent did: predict-no for direction R in state State-B
  5957. In State-B moving R
  5958. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5959. predict error 0
  5960. dir: dir isU
  5961. \-/844: O: O1688 (predict-no)
  5962. I see 1 and I'm going to do: predict-no
  5963. ENV: Agent did: predict-no for direction U in state State-B
  5964. In State-B moving U
  5965. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5966. predict error 0
  5967. dir: dir isU
  5968. |\-845: O: O1690 (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-B
  5971. In State-B moving U
  5972. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5973. predict error 0
  5974. dir: dir isR
  5975. /|\846: O: O1692 (predict-no)
  5976. I see 1 and I'm going to do: predict-no
  5977. ENV: Agent did: predict-no for direction R in state State-B
  5978. In State-B moving R
  5979. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5980. predict error 0
  5981. dir: dir isR
  5982. -/|847: O: O1694 (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 isU
  5989. \-/848: O: O1696 (predict-no)
  5990. I see 1 and I'm going to do: predict-no
  5991. ENV: Agent did: predict-no for direction U in state State-B
  5992. In State-B moving U
  5993. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  5994. predict error 0
  5995. dir: dir isU
  5996. |\-849: O: O1698 (predict-no)
  5997. I see 1 and I'm going to do: predict-no
  5998. ENV: Agent did: predict-no for direction U in state State-B
  5999. In State-B moving U
  6000. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  6001. predict error 0
  6002. dir: dir isR
  6003. /|\850: O: O1700 (predict-no)
  6004. I see 1 and I'm going to do: predict-no
  6005. ENV: Agent did: predict-no for direction R in state State-B
  6006. In State-B moving R
  6007. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  6008. predict error 0
  6009. dir: dir isU
  6010. -/|851: O: O1702 (predict-no)
  6011. I see 1 and I'm going to do: predict-no
  6012. ENV: Agent did: predict-no for direction U in state State-B
  6013. In State-B moving U
  6014. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  6015. predict error 0
  6016. dir: dir isL
  6017. \852: O: O1703 (predict-yes)
  6018. I see 1 and I'm going to do: predict-yes
  6019. ENV: Agent did: predict-yes for direction L in state State-B
  6020. In State-B moving L
  6021. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  6022. predict error 0
  6023. dir: dir isR
  6024. -/|853: O: O1705 (predict-yes)
  6025. I see 1 and I'm going to do: predict-yes
  6026. ENV: Agent did: predict-yes for direction R in state State-A
  6027. In State-A moving R
  6028. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  6029. predict error 0
  6030. dir: dir isR
  6031. \-/854: O: O1708 (predict-no)
  6032. I see 1 and I'm going to do: predict-no
  6033. ENV: Agent did: predict-no for direction R in state State-B
  6034. In State-B moving R
  6035. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  6036. predict error 0
  6037. dir: dir isR
  6038. |\-855: O: O1710 (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 isU
  6045. /|\856: O: O1712 (predict-no)
  6046. I see 1 and I'm going to do: predict-no
  6047. ENV: Agent did: predict-no for direction U in state State-B
  6048. In State-B moving U
  6049. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  6050. predict error 0
  6051. dir: dir isU
  6052. -/|857: O: O1714 (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-B
  6055. In State-B moving U
  6056. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  6057. predict error 0
  6058. dir: dir isR
  6059. \-/858: O: O1716 (predict-no)
  6060. I see 1 and I'm going to do: predict-no
  6061. ENV: Agent did: predict-no for direction R in state State-B
  6062. In State-B moving R
  6063. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  6064. predict error 0
  6065. dir: dir isR
  6066. |\859: O: O1718 (predict-no)
  6067. I see 1 and I'm going to do: predict-no
  6068. ENV: Agent did: predict-no for direction R in state State-B
  6069. In State-B moving R
  6070. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  6071. predict error 0
  6072. dir: dir isU
  6073. -860: O: O1720 (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. /|861: O: O1722 (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 isR
  6087. \862: O: O1724 (predict-no)
  6088. I see 1 and I'm going to do: predict-no
  6089. ENV: Agent did: predict-no for direction R in state State-B
  6090. In State-B moving R
  6091. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  6092. predict error 0
  6093. dir: dir isU
  6094. -/|863: O: O1726 (predict-no)
  6095. I see 1 and I'm going to do: predict-no
  6096. ENV: Agent did: predict-no for direction U in state State-B
  6097. In State-B moving U
  6098. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  6099. predict error 0
  6100. dir: dir isR
  6101. \-864: O: O1728 (predict-no)
  6102. I see 1 and I'm going to do: predict-no
  6103. ENV: Agent did: predict-no for direction R in state State-B
  6104. In State-B moving R
  6105. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  6106. predict error 0
  6107. dir: dir isL
  6108. /|865: O: O1729 (predict-yes)
  6109. I see 1 and I'm going to do: predict-yes
  6110. ENV: Agent did: predict-yes for direction L in state State-B
  6111. In State-B moving L
  6112. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  6113. predict error 0
  6114. dir: dir isR
  6115. \-866: O: O1731 (predict-yes)
  6116. I see 1 and I'm going to do: predict-yes
  6117. ENV: Agent did: predict-yes for direction R in state State-A
  6118. In State-A moving R
  6119. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  6120. predict error 0
  6121. dir: dir isR
  6122. /|\867: O: O1734 (predict-no)
  6123. I see 1 and I'm going to do: predict-no
  6124. ENV: Agent did: predict-no for direction R in state State-B
  6125. In State-B moving R
  6126. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  6127. predict error 0
  6128. dir: dir isR
  6129. -/|\868: O: O1736 (predict-no)
  6130. I see 1 and I'm going to do: predict-no
  6131. ENV: Agent did: predict-no for direction R in state State-B
  6132. In State-B moving R
  6133. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  6134. predict error 0
  6135. dir: dir isR
  6136. -/|869: O: O1738 (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. \-/870: O: O1740 (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 isU
  6150. |\-871: O: O1742 (predict-no)
  6151. I see 1 and I'm going to do: predict-no
  6152. ENV: Agent did: predict-no for direction U in state State-B
  6153. In State-B moving U
  6154. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  6155. predict error 0
  6156. dir: dir isR
  6157. /872: O: O1744 (predict-no)
  6158. I see 1 and I'm going to do: predict-no
  6159. ENV: Agent did: predict-no for direction R in state State-B
  6160. In State-B moving R
  6161. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  6162. predict error 0
  6163. dir: dir isU
  6164. |\873: O: O1746 (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-B
  6167. In State-B moving U
  6168. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  6169. predict error 0
  6170. dir: dir isR
  6171. -/|\874: O: O1748 (predict-no)
  6172. I see 1 and I'm going to do: predict-no
  6173. ENV: Agent did: predict-no for direction R in state State-B
  6174. In State-B moving R
  6175. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  6176. predict error 0
  6177. dir: dir isR
  6178. -/|875: O: O1750 (predict-no)
  6179. I see 1 and I'm going to do: predict-no
  6180. ENV: Agent did: predict-no for direction R in state State-B
  6181. In State-B moving R
  6182. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  6183. predict error 0
  6184. dir: dir isR
  6185. \-876: O: O1752 (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. /|\877: O: O1754 (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 isU
  6199. -/878: O: O1756 (predict-no)
  6200. I see 1 and I'm going to do: predict-no
  6201. ENV: Agent did: predict-no for direction U in state State-B
  6202. In State-B moving U
  6203. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  6204. predict error 0
  6205. dir: dir isU
  6206. |\-879: O: O1758 (predict-no)
  6207. I see 1 and I'm going to do: predict-no
  6208. ENV: Agent did: predict-no for direction U in state State-B
  6209. In State-B moving U
  6210. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  6211. predict error 0
  6212. dir: dir isU
  6213. /|\880: O: O1760 (predict-no)
  6214. I see 1 and I'm going to do: predict-no
  6215. ENV: Agent did: predict-no for direction U in state State-B
  6216. In State-B moving U
  6217. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  6218. predict error 0
  6219. dir: dir isR
  6220. -/881: O: O1762 (predict-no)
  6221. I see 1 and I'm going to do: predict-no
  6222. ENV: Agent did: predict-no for direction R in state State-B
  6223. In State-B moving R
  6224. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  6225. predict error 0
  6226. dir: dir isL
  6227. |882: O: O1763 (predict-yes)
  6228. I see 1 and I'm going to do: predict-yes
  6229. ENV: Agent did: predict-yes for direction L in state State-B
  6230. In State-B moving L
  6231. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  6232. predict error 0
  6233. dir: dir isR
  6234. \-/883: O: O1765 (predict-yes)
  6235. I see 1 and I'm going to do: predict-yes
  6236. ENV: Agent did: predict-yes for direction R in state State-A
  6237. In State-A moving R
  6238. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  6239. predict error 0
  6240. dir: dir isL
  6241. |\884: O: O1767 (predict-yes)
  6242. I see 1 and I'm going to do: predict-yes
  6243. ENV: Agent did: predict-yes for direction L in state State-B
  6244. In State-B moving L
  6245. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  6246. predict error 0
  6247. dir: dir isU
  6248. -/|885: O: O1770 (predict-no)
  6249. I see 1 and I'm going to do: predict-no
  6250. ENV: Agent did: predict-no for direction U in state State-A
  6251. In State-A moving U
  6252. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  6253. predict error 0
  6254. dir: dir isR
  6255. \-/886: O: O1771 (predict-yes)
  6256. I see 1 and I'm going to do: predict-yes
  6257. ENV: Agent did: predict-yes for direction R in state State-A
  6258. In State-A moving R
  6259. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  6260. predict error 0
  6261. dir: dir isR
  6262. |\-887: O: O1774 (predict-no)
  6263. I see 1 and I'm going to do: predict-no
  6264. ENV: Agent did: predict-no for direction R in state State-B
  6265. In State-B moving R
  6266. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  6267. predict error 0
  6268. dir: dir isU
  6269. /|\888: O: O1776 (predict-no)
  6270. I see 1 and I'm going to do: predict-no
  6271. ENV: Agent did: predict-no for direction U in state State-B
  6272. In State-B moving U
  6273. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  6274. predict error 0
  6275. dir: dir isL
  6276. -/|889: O: O1777 (predict-yes)
  6277. I see 1 and I'm going to do: predict-yes
  6278. ENV: Agent did: predict-yes for direction L in state State-B
  6279. In State-B moving L
  6280. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  6281. predict error 0
  6282. dir: dir isU
  6283. \-/890: O: O1780 (predict-no)
  6284. I see 1 and I'm going to do: predict-no
  6285. ENV: Agent did: predict-no for direction U in state State-A
  6286. In State-A moving U
  6287. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  6288. predict error 0
  6289. dir: dir isL
  6290. |\891: O: O1782 (predict-no)
  6291. I see 1 and I'm going to do: predict-no
  6292. ENV: Agent did: predict-no for direction L in state State-A
  6293. In State-A moving L
  6294. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  6295. predict error 0
  6296. dir: dir isL
  6297. -892: O: O1784 (predict-no)
  6298. I see 1 and I'm going to do: predict-no
  6299. ENV: Agent did: predict-no for direction L in state State-A
  6300. In State-A moving L
  6301. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  6302. predict error 0
  6303. dir: dir isR
  6304. /|\893: O: O1785 (predict-yes)
  6305. I see 1 and I'm going to do: predict-yes
  6306. ENV: Agent did: predict-yes for direction R in state State-A
  6307. In State-A moving R
  6308. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  6309. predict error 0
  6310. dir: dir isR
  6311. -/|894: O: O1788 (predict-no)
  6312. I see 1 and I'm going to do: predict-no
  6313. ENV: Agent did: predict-no for direction R in state State-B
  6314. In State-B moving R
  6315. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  6316. predict error 0
  6317. dir: dir isU
  6318. \-/895: O: O1790 (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-B
  6321. In State-B moving U
  6322. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  6323. predict error 0
  6324. dir: dir isR
  6325. |\-896: O: O1792 (predict-no)
  6326. I see 1 and I'm going to do: predict-no
  6327. ENV: Agent did: predict-no for direction R in state State-B
  6328. In State-B moving R
  6329. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  6330. predict error 0
  6331. dir: dir isL
  6332. /|\-897: O: O1793 (predict-yes)
  6333. I see 1 and I'm going to do: predict-yes
  6334. ENV: Agent did: predict-yes for direction L in state State-B
  6335. In State-B moving L
  6336. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  6337. predict error 0
  6338. dir: dir isL
  6339. /|\898: O: O1796 (predict-no)
  6340. I see 1 and I'm going to do: predict-no
  6341. ENV: Agent did: predict-no for direction L in state State-A
  6342. In State-A moving L
  6343. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  6344. predict error 0
  6345. dir: dir isL
  6346. -/|899: O: O1798 (predict-no)
  6347. I see 1 and I'm going to do: predict-no
  6348. ENV: Agent did: predict-no for direction L in state State-A
  6349. In State-A moving L
  6350. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  6351. predict error 0
  6352. dir: dir isR
  6353. \-900: O: O1799 (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. /|\901: O: O1802 (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 isL
  6367. -902: O: O1803 (predict-yes)
  6368. I see 1 and I'm going to do: predict-yes
  6369. ENV: Agent did: predict-yes for direction L in state State-B
  6370. In State-B moving L
  6371. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  6372. predict error 0
  6373. dir: dir isL
  6374. /|\903: O: O1806 (predict-no)
  6375. I see 1 and I'm going to do: predict-no
  6376. ENV: Agent did: predict-no for direction L in state State-A
  6377. In State-A moving L
  6378. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  6379. predict error 0
  6380. dir: dir isR
  6381. -/|904: O: O1807 (predict-yes)
  6382. I see 1 and I'm going to do: predict-yes
  6383. ENV: Agent did: predict-yes for direction R in state State-A
  6384. In State-A moving R
  6385. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  6386. predict error 0
  6387. dir: dir isU
  6388. \-/|905: O: O1810 (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-B
  6391. In State-B moving U
  6392. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  6393. predict error 0
  6394. dir: dir isU
  6395. \-/906: O: O1812 (predict-no)
  6396. I see 1 and I'm going to do: predict-no
  6397. ENV: Agent did: predict-no for direction U in state State-B
  6398. In State-B moving U
  6399. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  6400. predict error 0
  6401. dir: dir isU
  6402. |\-907: O: O1814 (predict-no)
  6403. I see 1 and I'm going to do: predict-no
  6404. ENV: Agent did: predict-no for direction U in state State-B
  6405. In State-B moving U
  6406. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  6407. predict error 0
  6408. dir: dir isR
  6409. /|\908: O: O1816 (predict-no)
  6410. I see 1 and I'm going to do: predict-no
  6411. ENV: Agent did: predict-no for direction R in state State-B
  6412. In State-B moving R
  6413. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  6414. predict error 0
  6415. dir: dir isR
  6416. -/909: O: O1818 (predict-no)
  6417. I see 1 and I'm going to do: predict-no
  6418. ENV: Agent did: predict-no for direction R in state State-B
  6419. In State-B moving R
  6420. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  6421. predict error 0
  6422. dir: dir isL
  6423. |\910: O: O1819 (predict-yes)
  6424. I see 1 and I'm going to do: predict-yes
  6425. ENV: Agent did: predict-yes for direction L in state State-B
  6426. In State-B moving L
  6427. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  6428. predict error 0
  6429. dir: dir isR
  6430. -/|911: O: O1821 (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 isL
  6437. \912: O: O1823 (predict-yes)
  6438. I see 1 and I'm going to do: predict-yes
  6439. ENV: Agent did: predict-yes for direction L in state State-B
  6440. In State-B moving L
  6441. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  6442. predict error 0
  6443. dir: dir isL
  6444. -/|913: O: O1826 (predict-no)
  6445. I see 1 and I'm going to do: predict-no
  6446. ENV: Agent did: predict-no for direction L in state State-A
  6447. In State-A moving L
  6448. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  6449. predict error 0
  6450. dir: dir isU
  6451. \-/914: O: O1828 (predict-no)
  6452. I see 1 and I'm going to do: predict-no
  6453. ENV: Agent did: predict-no for direction U in state State-A
  6454. In State-A moving U
  6455. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  6456. predict error 0
  6457. dir: dir isR
  6458. |\-915: O: O1829 (predict-yes)
  6459. I see 1 and I'm going to do: predict-yes
  6460. ENV: Agent did: predict-yes for direction R in state State-A
  6461. In State-A moving R
  6462. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  6463. predict error 0
  6464. dir: dir isU
  6465. /|\916: O: O1832 (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-B
  6468. In State-B moving U
  6469. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  6470. predict error 0
  6471. dir: dir isR
  6472. -/|917: O: O1834 (predict-no)
  6473. I see 1 and I'm going to do: predict-no
  6474. ENV: Agent did: predict-no for direction R in state State-B
  6475. In State-B moving R
  6476. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  6477. predict error 0
  6478. dir: dir isL
  6479. \-/918: O: O1835 (predict-yes)
  6480. I see 1 and I'm going to do: predict-yes
  6481. ENV: Agent did: predict-yes for direction L in state State-B
  6482. In State-B moving L
  6483. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  6484. predict error 0
  6485. dir: dir isR
  6486. |\-919: O: O1837 (predict-yes)
  6487. I see 1 and I'm going to do: predict-yes
  6488. ENV: Agent did: predict-yes for direction R in state State-A
  6489. In State-A moving R
  6490. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  6491. predict error 0
  6492. dir: dir isR
  6493. /|\920: O: O1840 (predict-no)
  6494. I see 1 and I'm going to do: predict-no
  6495. ENV: Agent did: predict-no for direction R in state State-B
  6496. In State-B moving R
  6497. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  6498. predict error 0
  6499. dir: dir isL
  6500. -/|921: O: O1841 (predict-yes)
  6501. I see 1 and I'm going to do: predict-yes
  6502. ENV: Agent did: predict-yes for direction L in state State-B
  6503. In State-B moving L
  6504. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  6505. predict error 0
  6506. dir: dir isU
  6507. \922: O: O1844 (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 isU
  6514. -/923: O: O1846 (predict-no)
  6515. I see 1 and I'm going to do: predict-no
  6516. ENV: Agent did: predict-no for direction U in state State-A
  6517. In State-A moving U
  6518. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  6519. predict error 0
  6520. dir: dir isL
  6521. |\-924: O: O1848 (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 isL
  6528. /|\925: O: O1850 (predict-no)
  6529. I see 1 and I'm going to do: predict-no
  6530. ENV: Agent did: predict-no for direction L in state State-A
  6531. In State-A moving L
  6532. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  6533. predict error 0
  6534. dir: dir isU
  6535. -/|926: O: O1852 (predict-no)
  6536. I see 1 and I'm going to do: predict-no
  6537. ENV: Agent did: predict-no for direction U in state State-A
  6538. In State-A moving U
  6539. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  6540. predict error 0
  6541. dir: dir isU
  6542. \-927: O: O1854 (predict-no)
  6543. I see 1 and I'm going to do: predict-no
  6544. ENV: Agent did: predict-no for direction U in state State-A
  6545. In State-A moving U
  6546. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  6547. predict error 0
  6548. dir: dir isL
  6549. /|\928: O: O1856 (predict-no)
  6550. I see 1 and I'm going to do: predict-no
  6551. ENV: Agent did: predict-no for direction L in state State-A
  6552. In State-A moving L
  6553. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  6554. predict error 0
  6555. dir: dir isR
  6556. -/929: O: O1857 (predict-yes)
  6557. I see 1 and I'm going to do: predict-yes
  6558. ENV: Agent did: predict-yes for direction R in state State-A
  6559. In State-A moving R
  6560. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  6561. predict error 0
  6562. dir: dir isL
  6563. |\-930: O: O1859 (predict-yes)
  6564. I see 1 and I'm going to do: predict-yes
  6565. ENV: Agent did: predict-yes for direction L in state State-B
  6566. In State-B moving L
  6567. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  6568. predict error 0
  6569. dir: dir isU
  6570. /|\931: O: O1862 (predict-no)
  6571. I see 1 and I'm going to do: predict-no
  6572. ENV: Agent did: predict-no for direction U in state State-A
  6573. In State-A moving U
  6574. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  6575. predict error 0
  6576. dir: dir isR
  6577. -932: O: O1863 (predict-yes)
  6578. I see 1 and I'm going to do: predict-yes
  6579. ENV: Agent did: predict-yes for direction R in state State-A
  6580. In State-A moving R
  6581. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  6582. predict error 0
  6583. dir: dir isR
  6584. /|\933: O: O1866 (predict-no)
  6585. I see 1 and I'm going to do: predict-no
  6586. ENV: Agent did: predict-no for direction R in state State-B
  6587. In State-B moving R
  6588. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  6589. predict error 0
  6590. dir: dir isL
  6591. -/|934: O: O1867 (predict-yes)
  6592. I see 1 and I'm going to do: predict-yes
  6593. ENV: Agent did: predict-yes for direction L in state State-B
  6594. In State-B moving L
  6595. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  6596. predict error 0
  6597. dir: dir isR
  6598. \-935: O: O1869 (predict-yes)
  6599. I see 1 and I'm going to do: predict-yes
  6600. ENV: Agent did: predict-yes for direction R in state State-A
  6601. In State-A moving R
  6602. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  6603. predict error 0
  6604. dir: dir isR
  6605. /|\936: O: O1872 (predict-no)
  6606. I see 1 and I'm going to do: predict-no
  6607. ENV: Agent did: predict-no for direction R in state State-B
  6608. In State-B moving R
  6609. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  6610. predict error 0
  6611. dir: dir isR
  6612. -/|\937: O: O1874 (predict-no)
  6613. I see 1 and I'm going to do: predict-no
  6614. ENV: Agent did: predict-no for direction R in state State-B
  6615. In State-B moving R
  6616. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  6617. predict error 0
  6618. dir: dir isL
  6619. -/|938: O: O1875 (predict-yes)
  6620. I see 1 and I'm going to do: predict-yes
  6621. ENV: Agent did: predict-yes for direction L in state State-B
  6622. In State-B moving L
  6623. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  6624. predict error 0
  6625. dir: dir isL
  6626. \-/939: O: O1878 (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 isU
  6633. |\-940: O: O1880 (predict-no)
  6634. I see 1 and I'm going to do: predict-no
  6635. ENV: Agent did: predict-no for direction U in state State-A
  6636. In State-A moving U
  6637. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  6638. predict error 0
  6639. dir: dir isU
  6640. /|\941: O: O1882 (predict-no)
  6641. I see 1 and I'm going to do: predict-no
  6642. ENV: Agent did: predict-no for direction U in state State-A
  6643. In State-A moving U
  6644. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  6645. predict error 0
  6646. dir: dir isU
  6647. -942: O: O1884 (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-A
  6650. In State-A moving U
  6651. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  6652. predict error 0
  6653. dir: dir isR
  6654. /|943: O: O1885 (predict-yes)
  6655. I see 1 and I'm going to do: predict-yes
  6656. ENV: Agent did: predict-yes for direction R in state State-A
  6657. In State-A moving R
  6658. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  6659. predict error 0
  6660. dir: dir isU
  6661. \-944: O: O1888 (predict-no)
  6662. I see 1 and I'm going to do: predict-no
  6663. ENV: Agent did: predict-no for direction U in state State-B
  6664. In State-B moving U
  6665. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  6666. predict error 0
  6667. dir: dir isL
  6668. /|945: O: O1889 (predict-yes)
  6669. I see 1 and I'm going to do: predict-yes
  6670. ENV: Agent did: predict-yes for direction L in state State-B
  6671. In State-B moving L
  6672. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  6673. predict error 0
  6674. dir: dir isL
  6675. \-/946: O: O1892 (predict-no)
  6676. I see 1 and I'm going to do: predict-no
  6677. ENV: Agent did: predict-no for direction L in state State-A
  6678. In State-A moving L
  6679. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  6680. predict error 0
  6681. dir: dir isU
  6682. |\-947: O: O1894 (predict-no)
  6683. I see 1 and I'm going to do: predict-no
  6684. ENV: Agent did: predict-no for direction U in state State-A
  6685. In State-A moving U
  6686. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  6687. predict error 0
  6688. dir: dir isL
  6689. /|\948: O: O1896 (predict-no)
  6690. I see 1 and I'm going to do: predict-no
  6691. ENV: Agent did: predict-no for direction L in state State-A
  6692. In State-A moving L
  6693. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  6694. predict error 0
  6695. dir: dir isL
  6696. -/|949: O: O1898 (predict-no)
  6697. I see 1 and I'm going to do: predict-no
  6698. ENV: Agent did: predict-no for direction L in state State-A
  6699. In State-A moving L
  6700. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  6701. predict error 0
  6702. dir: dir isU
  6703. \-/950: O: O1900 (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-A
  6706. In State-A moving U
  6707. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  6708. predict error 0
  6709. dir: dir isL
  6710. |\-/|\-/--- Input Phase ---
  6711. =>WM: (13326: I2 ^dir L)
  6712. =>WM: (13325: I2 ^reward 1)
  6713. =>WM: (13324: I2 ^see 0)
  6714. =>WM: (13323: N950 ^status complete)
  6715. <=WM: (13312: I2 ^dir U)
  6716. <=WM: (13311: I2 ^reward 1)
  6717. <=WM: (13310: I2 ^see 0)
  6718. =>WM: (13327: I2 ^level-1 L0-root)
  6719. <=WM: (13313: I2 ^level-1 L0-root)
  6720. --- END Input Phase ---
  6721. --- Proposal Phase ---
  6722. --- Inner Elaboration Phase, active level 1 (S1) ---
  6723. Firing rl*prefer*rvt*predict-yes*H0*3*H1*13
  6724. -->
  6725. (S1 ^operator O1899 = -0.208713043145708)
  6726. Firing rl*prefer*rvt*predict-no*H0*4*H1*12
  6727. -->
  6728. (S1 ^operator O1900 = 0.6854017956462798)
  6729. Firing prefer*rvt*predict-no*H0*4*H1
  6730. -->
  6731. Firing prefer*rvt*predict-yes*H0*3*H1
  6732. -->
  6733. Firing elaborate*copy-see-to-output-link
  6734. -->
  6735. (I3 ^see 0 +)
  6736. Firing elaborate*reward*based*on*reward
  6737. -->
  6738. (R954 ^value 1 +)
  6739. (R1 ^reward R954 +)
  6740. Firing propose*predict-yes
  6741. -->
  6742. (O1901 ^name predict-yes +)
  6743. (S1 ^operator O1901 +)
  6744. Firing propose*predict-no
  6745. -->
  6746. (O1902 ^name predict-no +)
  6747. (S1 ^operator O1902 +)
  6748. Firing rl*prefer*rvt*predict-no*H0*4
  6749. -->
  6750. (S1 ^operator O1900 = 0.3145080651024651)
  6751. Firing rl*prefer*rvt*predict-yes*H0*3
  6752. -->
  6753. (S1 ^operator O1899 = 0.3908143935841644)
  6754. Firing prefer*rvt*predict-yes*H0
  6755. -->
  6756. Firing prefer*rvt*predict-no*H0
  6757. -->
  6758. Firing elaborate*copy-dir-to-output-link
  6759. -->
  6760. (I3 ^dir L +)
  6761. inner elaboration loop at bottom goal.
  6762. Retracting elaborate*copy-see-to-output-link
  6763. -->
  6764. (I3 ^see 0 +)
  6765. Retracting propose*predict-no
  6766. -->
  6767. (O1900 ^name predict-no +)
  6768. (S1 ^operator O1900 +)
  6769. Retracting propose*predict-yes
  6770. -->
  6771. (O1899 ^name predict-yes +)
  6772. (S1 ^operator O1899 +)
  6773. Retracting elaborate*reward*based*on*reward
  6774. -->
  6775. (R953 ^value 1 +)
  6776. (R1 ^reward R953 +)
  6777. Retracting elaborate*copy-dir-to-output-link
  6778. -->
  6779. (I3 ^dir U +)
  6780. Retracting rl*prefer*rvt*predict-no*H0*2
  6781. -->
  6782. (S1 ^operator O1900 = 1.)
  6783. Retracting rl*prefer*rvt*predict-yes*H0*1
  6784. -->
  6785. (S1 ^operator O1899 = 0.)
  6786. =>WM: (13334: S1 ^operator O1902 +)
  6787. =>WM: (13333: S1 ^operator O1901 +)
  6788. =>WM: (13332: I3 ^dir L)
  6789. =>WM: (13331: O1902 ^name predict-no)
  6790. =>WM: (13330: O1901 ^name predict-yes)
  6791. =>WM: (13329: R954 ^value 1)
  6792. =>WM: (13328: R1 ^reward R954)
  6793. <=WM: (13319: S1 ^operator O1899 +)
  6794. <=WM: (13320: S1 ^operator O1900 +)
  6795. <=WM: (13321: S1 ^operator O1900)
  6796. <=WM: (13318: I3 ^dir U)
  6797. <=WM: (13314: R1 ^reward R953)
  6798. <=WM: (13317: O1900 ^name predict-no)
  6799. <=WM: (13316: O1899 ^name predict-yes)
  6800. <=WM: (13315: R953 ^value 1)
  6801. --- Inner Elaboration Phase, active level 1 (S1) ---
  6802. Firing prefer*rvt*predict-yes*H0
  6803. -->
  6804. Firing rl*prefer*rvt*predict-yes*H0*3*H1*13
  6805. -->
  6806. (S1 ^operator O1901 = -0.208713043145708)
  6807. Firing rl*prefer*rvt*predict-yes*H0*3
  6808. -->
  6809. (S1 ^operator O1901 = 0.3908143935841644)
  6810. Firing prefer*rvt*predict-yes*H0*3*H1
  6811. -->
  6812. Firing prefer*rvt*predict-no*H0
  6813. -->
  6814. Firing rl*prefer*rvt*predict-no*H0*4*H1*12
  6815. -->
  6816. (S1 ^operator O1902 = 0.6854017956462798)
  6817. Firing rl*prefer*rvt*predict-no*H0*4
  6818. -->
  6819. (S1 ^operator O1902 = 0.3145080651024651)
  6820. Firing prefer*rvt*predict-no*H0*4*H1
  6821. -->
  6822. inner elaboration loop at bottom goal.
  6823. Retracting rl*prefer*rvt*predict-no*H0*4
  6824. -->
  6825. (S1 ^operator O1900 = 0.3145080651024651)
  6826. Retracting rl*prefer*rvt*predict-no*H0*4*H1*12
  6827. -->
  6828. (S1 ^operator O1900 = 0.6854017956462798)
  6829. Retracting rl*prefer*rvt*predict-yes*H0*3
  6830. -->
  6831. (S1 ^operator O1899 = 0.3908143935841644)
  6832. Retracting rl*prefer*rvt*predict-yes*H0*3*H1*13
  6833. -->
  6834. (S1 ^operator O1899 = -0.208713043145708)
  6835. --- END Proposal Phase ---
  6836. --- Decision Phase ---
  6837. RL update rl*prefer*rvt*predict-no*H0*2 1 0 1 -> 1 0 1(R,m,v=1,1,0)
  6838. =>WM: (13335: S1 ^operator O1902)
  6839. 951: O: O1902 (predict-no)
  6840. --- END Decision Phase ---
  6841. --- Application Phase ---
  6842. --- Firing Productions (PE) For State At Depth 1 ---
  6843. --- Inner Elaboration Phase, active level 1 (S1) ---
  6844. Firing apply*operator
  6845. -->
  6846. (I3 ^predict-no N951 + :O )
  6847. Firing apply*operator*complete
  6848. -->
  6849. (I3 ^predict-no N950 - :O )
  6850. inner elaboration loop at bottom goal.
  6851. --- Change Working Memory (PE) ---
  6852. =>WM: (13336: I3 ^predict-no N951)
  6853. <=WM: (13323: N950 ^status complete)
  6854. <=WM: (13322: I3 ^predict-no N950)
  6855. --- Firing Productions (IE) For State At Depth 1 ---
  6856. --- Inner Elaboration Phase, active level 1 (S1) ---
  6857. Firing monitor*world
  6858. -->
  6859. I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
  6860. --- Change Working Memory (IE) ---
  6861. --- END Application Phase ---
  6862. --- Output Phase ---
  6863. ENV: Agent did: predict-no for direction L in state State-A
  6864. In State-A moving L
  6865. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  6866. predict error 0
  6867. dir: dir isL
  6868. --- END Output Phase ---
  6869. |--- Input Phase ---
  6870. =>WM: (13340: I2 ^dir L)
  6871. =>WM: (13339: I2 ^reward 1)
  6872. =>WM: (13338: I2 ^see 0)
  6873. =>WM: (13337: N951 ^status complete)
  6874. <=WM: (13326: I2 ^dir L)
  6875. <=WM: (13325: I2 ^reward 1)
  6876. <=WM: (13324: I2 ^see 0)
  6877. =>WM: (13341: I2 ^level-1 L0-root)
  6878. <=WM: (13327: I2 ^level-1 L0-root)
  6879. --- END Input Phase ---
  6880. --- Proposal Phase ---
  6881. --- Inner Elaboration Phase, active level 1 (S1) ---
  6882. Firing rl*prefer*rvt*predict-yes*H0*3*H1*13
  6883. -->
  6884. (S1 ^operator O1901 = -0.208713043145708)
  6885. Firing rl*prefer*rvt*predict-no*H0*4*H1*12
  6886. -->
  6887. (S1 ^operator O1902 = 0.6854017956462798)
  6888. Firing prefer*rvt*predict-no*H0*4*H1
  6889. -->
  6890. Firing prefer*rvt*predict-yes*H0*3*H1
  6891. -->
  6892. Firing elaborate*copy-see-to-output-link
  6893. -->
  6894. (I3 ^see 0 +)
  6895. Firing elaborate*reward*based*on*reward
  6896. -->
  6897. (R955 ^value 1 +)
  6898. (R1 ^reward R955 +)
  6899. Firing propose*predict-yes
  6900. -->
  6901. (O1903 ^name predict-yes +)
  6902. (S1 ^operator O1903 +)
  6903. Firing propose*predict-no
  6904. -->
  6905. (O1904 ^name predict-no +)
  6906. (S1 ^operator O1904 +)
  6907. Firing rl*prefer*rvt*predict-no*H0*4
  6908. -->
  6909. (S1 ^operator O1902 = 0.3145080651024651)
  6910. Firing rl*prefer*rvt*predict-yes*H0*3
  6911. -->
  6912. (S1 ^operator O1901 = 0.3908143935841644)
  6913. Firing prefer*rvt*predict-yes*H0
  6914. -->
  6915. Firing prefer*rvt*predict-no*H0
  6916. -->
  6917. Firing elaborate*copy-dir-to-output-link
  6918. -->
  6919. (I3 ^dir L +)
  6920. inner elaboration loop at bottom goal.
  6921. Retracting elaborate*copy-see-to-output-link
  6922. -->
  6923. (I3 ^see 0 +)
  6924. Retracting propose*predict-no
  6925. -->
  6926. (O1902 ^name predict-no +)
  6927. (S1 ^operator O1902 +)
  6928. Retracting propose*predict-yes
  6929. -->
  6930. (O1901 ^name predict-yes +)
  6931. (S1 ^operator O1901 +)
  6932. Retracting elaborate*reward*based*on*reward
  6933. -->
  6934. (R954 ^value 1 +)
  6935. (R1 ^reward R954 +)
  6936. Retracting elaborate*copy-dir-to-output-link
  6937. -->
  6938. (I3 ^dir L +)
  6939. Retracting rl*prefer*rvt*predict-no*H0*4
  6940. -->
  6941. (S1 ^operator O1902 = 0.3145080651024651)
  6942. Retracting rl*prefer*rvt*predict-no*H0*4*H1*12
  6943. -->
  6944. (S1 ^operator O1902 = 0.6854017956462798)
  6945. Retracting rl*prefer*rvt*predict-yes*H0*3
  6946. -->
  6947. (S1 ^operator O1901 = 0.3908143935841644)
  6948. Retracting rl*prefer*rvt*predict-yes*H0*3*H1*13
  6949. -->
  6950. (S1 ^operator O1901 = -0.208713043145708)
  6951. =>WM: (13347: S1 ^operator O1904 +)
  6952. =>WM: (13346: S1 ^operator O1903 +)
  6953. =>WM: (13345: O1904 ^name predict-no)
  6954. =>WM: (13344: O1903 ^name predict-yes)
  6955. =>WM: (13343: R955 ^value 1)
  6956. =>WM: (13342: R1 ^reward R955)
  6957. <=WM: (13333: S1 ^operator O1901 +)
  6958. <=WM: (13334: S1 ^operator O1902 +)
  6959. <=WM: (13335: S1 ^operator O1902)
  6960. <=WM: (13328: R1 ^reward R954)
  6961. <=WM: (13331: O1902 ^name predict-no)
  6962. <=WM: (13330: O1901 ^name predict-yes)
  6963. <=WM: (13329: R954 ^value 1)
  6964. --- Inner Elaboration Phase, active level 1 (S1) ---
  6965. Firing prefer*rvt*predict-yes*H0
  6966. -->
  6967. Firing rl*prefer*rvt*predict-yes*H0*3*H1*13
  6968. -->
  6969. (S1 ^operator O1903 = -0.208713043145708)
  6970. Firing rl*prefer*rvt*predict-yes*H0*3
  6971. -->
  6972. (S1 ^operator O1903 = 0.3908143935841644)
  6973. Firing prefer*rvt*predict-yes*H0*3*H1
  6974. -->
  6975. Firing prefer*rvt*predict-no*H0
  6976. -->
  6977. Firing rl*prefer*rvt*predict-no*H0*4*H1*12
  6978. -->
  6979. (S1 ^operator O1904 = 0.6854017956462798)
  6980. Firing rl*prefer*rvt*predict-no*H0*4
  6981. -->
  6982. (S1 ^operator O1904 = 0.3145080651024651)
  6983. Firing prefer*rvt*predict-no*H0*4*H1
  6984. -->
  6985. inner elaboration loop at bottom goal.
  6986. Retracting rl*prefer*rvt*predict-no*H0*4
  6987. -->
  6988. (S1 ^operator O1902 = 0.3145080651024651)
  6989. Retracting rl*prefer*rvt*predict-no*H0*4*H1*12
  6990. -->
  6991. (S1 ^operator O1902 = 0.6854017956462798)
  6992. Retracting rl*prefer*rvt*predict-yes*H0*3
  6993. -->
  6994. (S1 ^operator O1901 = 0.3908143935841644)
  6995. Retracting rl*prefer*rvt*predict-yes*H0*3*H1*13
  6996. -->
  6997. (S1 ^operator O1901 = -0.208713043145708)
  6998. --- END Proposal Phase ---
  6999. --- Decision Phase ---
  7000. RL update rl*prefer*rvt*predict-no*H0*4 0.478556 -0.164048 0.314508 -> 0.478563 -0.164047 0.314516(R,m,v=1,0.917808,0.0759565)
  7001. RL update rl*prefer*rvt*predict-no*H0*4*H1*12 0.521362 0.16404 0.685402 -> 0.52137 0.16404 0.685411(R,m,v=1,1,0)
  7002. =>WM: (13348: S1 ^operator O1904)
  7003. 952: O: O1904 (predict-no)
  7004. --- END Decision Phase ---
  7005. --- Application Phase ---
  7006. --- Firing Productions (PE) For State At Depth 1 ---
  7007. --- Inner Elaboration Phase, active level 1 (S1) ---
  7008. Firing apply*operator
  7009. -->
  7010. (I3 ^predict-no N952 + :O )
  7011. Firing apply*operator*complete
  7012. -->
  7013. (I3 ^predict-no N951 - :O )
  7014. inner elaboration loop at bottom goal.
  7015. --- Change Working Memory (PE) ---
  7016. =>WM: (13349: I3 ^predict-no N952)
  7017. <=WM: (13337: N951 ^status complete)
  7018. <=WM: (13336: I3 ^predict-no N951)
  7019. --- Firing Productions (IE) For State At Depth 1 ---
  7020. --- Inner Elaboration Phase, active level 1 (S1) ---
  7021. Firing monitor*world
  7022. -->
  7023. I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
  7024. --- Change Working Memory (IE) ---
  7025. --- END Application Phase ---
  7026. --- Output Phase ---
  7027. ENV: Agent did: predict-no for direction L in state State-A
  7028. In State-A moving L
  7029. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  7030. predict error 0
  7031. dir: dir isR
  7032. --- END Output Phase ---
  7033. \-/--- Input Phase ---
  7034. =>WM: (13353: I2 ^dir R)
  7035. =>WM: (13352: I2 ^reward 1)
  7036. =>WM: (13351: I2 ^see 0)
  7037. =>WM: (13350: N952 ^status complete)
  7038. <=WM: (13340: I2 ^dir L)
  7039. <=WM: (13339: I2 ^reward 1)
  7040. <=WM: (13338: I2 ^see 0)
  7041. =>WM: (13354: I2 ^level-1 L0-root)
  7042. <=WM: (13341: I2 ^level-1 L0-root)
  7043. --- END Input Phase ---
  7044. --- Proposal Phase ---
  7045. --- Inner Elaboration Phase, active level 1 (S1) ---
  7046. Firing rl*prefer*rvt*predict-yes*H0*5*H1*14
  7047. -->
  7048. (S1 ^operator O1903 = 0.8783877442642956)
  7049. Firing prefer*rvt*predict-yes*H0*5*H1
  7050. -->
  7051. Firing elaborate*copy-see-to-output-link
  7052. -->
  7053. (I3 ^see 0 +)
  7054. Firing elaborate*reward*based*on*reward
  7055. -->
  7056. (R956 ^value 1 +)
  7057. (R1 ^reward R956 +)
  7058. Firing propose*predict-yes
  7059. -->
  7060. (O1905 ^name predict-yes +)
  7061. (S1 ^operator O1905 +)
  7062. Firing propose*predict-no
  7063. -->
  7064. (O1906 ^name predict-no +)
  7065. (S1 ^operator O1906 +)
  7066. Firing rl*prefer*rvt*predict-no*H0*6
  7067. -->
  7068. (S1 ^operator O1904 = 0.999977424773942)
  7069. Firing rl*prefer*rvt*predict-yes*H0*5
  7070. -->
  7071. (S1 ^operator O1903 = 0.1215951465100475)
  7072. Firing prefer*rvt*predict-yes*H0
  7073. -->
  7074. Firing prefer*rvt*predict-no*H0
  7075. -->
  7076. Firing elaborate*copy-dir-to-output-link
  7077. -->
  7078. (I3 ^dir R +)
  7079. inner elaboration loop at bottom goal.
  7080. Retracting elaborate*copy-see-to-output-link
  7081. -->
  7082. (I3 ^see 0 +)
  7083. Retracting propose*predict-no
  7084. -->
  7085. (O1904 ^name predict-no +)
  7086. (S1 ^operator O1904 +)
  7087. Retracting propose*predict-yes
  7088. -->
  7089. (O1903 ^name predict-yes +)
  7090. (S1 ^operator O1903 +)
  7091. Retracting elaborate*reward*based*on*reward
  7092. -->
  7093. (R955 ^value 1 +)
  7094. (R1 ^reward R955 +)
  7095. Retracting elaborate*copy-dir-to-output-link
  7096. -->
  7097. (I3 ^dir L +)
  7098. Retracting rl*prefer*rvt*predict-no*H0*4
  7099. -->
  7100. (S1 ^operator O1904 = 0.3145155972863931)
  7101. Retracting rl*prefer*rvt*predict-no*H0*4*H1*12
  7102. -->
  7103. (S1 ^operator O1904 = 0.6854105587116136)
  7104. Retracting rl*prefer*rvt*predict-yes*H0*3
  7105. -->
  7106. (S1 ^operator O1903 = 0.3908143935841644)
  7107. Retracting rl*prefer*rvt*predict-yes*H0*3*H1*13
  7108. -->
  7109. (S1 ^operator O1903 = -0.208713043145708)
  7110. =>WM: (13361: S1 ^operator O1906 +)
  7111. =>WM: (13360: S1 ^operator O1905 +)
  7112. =>WM: (13359: I3 ^dir R)
  7113. =>WM: (13358: O1906 ^name predict-no)
  7114. =>WM: (13357: O1905 ^name predict-yes)
  7115. =>WM: (13356: R956 ^value 1)
  7116. =>WM: (13355: R1 ^reward R956)
  7117. <=WM: (13346: S1 ^operator O1903 +)
  7118. <=WM: (13347: S1 ^operator O1904 +)
  7119. <=WM: (13348: S1 ^operator O1904)
  7120. <=WM: (13332: I3 ^dir L)
  7121. <=WM: (13342: R1 ^reward R955)
  7122. <=WM: (13345: O1904 ^name predict-no)
  7123. <=WM: (13344: O1903 ^name predict-yes)
  7124. <=WM: (13343: R955 ^value 1)
  7125. --- Inner Elaboration Phase, active level 1 (S1) ---
  7126. Firing prefer*rvt*predict-yes*H0
  7127. -->
  7128. Firing rl*prefer*rvt*predict-yes*H0*5*H1*14
  7129. -->
  7130. (S1 ^operator O1905 = 0.8783877442642956)
  7131. Firing rl*prefer*rvt*predict-yes*H0*5
  7132. -->
  7133. (S1 ^operator O1905 = 0.1215951465100475)
  7134. Firing prefer*rvt*predict-yes*H0*5*H1
  7135. -->
  7136. Firing prefer*rvt*predict-no*H0
  7137. -->
  7138. Firing rl*prefer*rvt*predict-no*H0*6
  7139. -->
  7140. (S1 ^operator O1906 = 0.999977424773942)
  7141. inner elaboration loop at bottom goal.
  7142. Retracting rl*prefer*rvt*predict-no*H0*6
  7143. -->
  7144. (S1 ^operator O1904 = 0.999977424773942)
  7145. Retracting rl*prefer*rvt*predict-yes*H0*5
  7146. -->
  7147. (S1 ^operator O1903 = 0.1215951465100475)
  7148. Retracting rl*prefer*rvt*predict-yes*H0*5*H1*14
  7149. -->
  7150. (S1 ^operator O1903 = 0.8783877442642956)
  7151. --- END Proposal Phase ---
  7152. --- Decision Phase ---
  7153. RL update rl*prefer*rvt*predict-no*H0*4 0.478563 -0.164047 0.314516 -> 0.478568 -0.164047 0.314522(R,m,v=1,0.918367,0.0754822)
  7154. RL update rl*prefer*rvt*predict-no*H0*4*H1*12 0.52137 0.16404 0.685411 -> 0.521377 0.164041 0.685418(R,m,v=1,1,0)
  7155. =>WM: (13362: S1 ^operator O1905)
  7156. 953: O: O1905 (predict-yes)
  7157. --- END Decision Phase ---
  7158. --- Application Phase ---
  7159. --- Firing Productions (PE) For State At Depth 1 ---
  7160. --- Inner Elaboration Phase, active level 1 (S1) ---
  7161. Firing apply*operator
  7162. -->
  7163. (I3 ^predict-yes N953 + :O )
  7164. Firing apply*operator*complete
  7165. -->
  7166. (I3 ^predict-no N952 - :O )
  7167. inner elaboration loop at bottom goal.
  7168. --- Change Working Memory (PE) ---
  7169. =>WM: (13363: I3 ^predict-yes N953)
  7170. <=WM: (13350: N952 ^status complete)
  7171. <=WM: (13349: I3 ^predict-no N952)
  7172. --- Firing Productions (IE) For State At Depth 1 ---
  7173. --- Inner Elaboration Phase, active level 1 (S1) ---
  7174. Firing monitor*world
  7175. -->
  7176. I see 1 and I'm going to do: predict-yes inner elaboration loop at bottom goal.
  7177. --- Change Working Memory (IE) ---
  7178. --- END Application Phase ---
  7179. --- Output Phase ---
  7180. ENV: Agent did: predict-yes for direction R in state State-A
  7181. In State-A moving R
  7182. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  7183. predict error 0
  7184. dir: dir isU
  7185. --- END Output Phase ---
  7186. |\---- Input Phase ---
  7187. =>WM: (13367: I2 ^dir U)
  7188. =>WM: (13366: I2 ^reward 1)
  7189. =>WM: (13365: I2 ^see 1)
  7190. =>WM: (13364: N953 ^status complete)
  7191. <=WM: (13353: I2 ^dir R)
  7192. <=WM: (13352: I2 ^reward 1)
  7193. <=WM: (13351: I2 ^see 0)
  7194. =>WM: (13368: I2 ^level-1 R1-root)
  7195. <=WM: (13354: I2 ^level-1 L0-root)
  7196. --- END Input Phase ---
  7197. --- Proposal Phase ---
  7198. --- Inner Elaboration Phase, active level 1 (S1) ---
  7199. Firing elaborate*copy-see-to-output-link
  7200. -->
  7201. (I3 ^see 1 +)
  7202. Firing elaborate*reward*based*on*reward
  7203. -->
  7204. (R957 ^value 1 +)
  7205. (R1 ^reward R957 +)
  7206. Firing propose*predict-yes
  7207. -->
  7208. (O1907 ^name predict-yes +)
  7209. (S1 ^operator O1907 +)
  7210. Firing propose*predict-no
  7211. -->
  7212. (O1908 ^name predict-no +)
  7213. (S1 ^operator O1908 +)
  7214. Firing rl*prefer*rvt*predict-no*H0*2
  7215. -->
  7216. (S1 ^operator O1906 = 1.)
  7217. Firing rl*prefer*rvt*predict-yes*H0*1
  7218. -->
  7219. (S1 ^operator O1905 = 0.)
  7220. Firing prefer*rvt*predict-yes*H0
  7221. -->
  7222. Firing prefer*rvt*predict-no*H0
  7223. -->
  7224. Firing elaborate*copy-dir-to-output-link
  7225. -->
  7226. (I3 ^dir U +)
  7227. inner elaboration loop at bottom goal.
  7228. Retracting elaborate*copy-see-to-output-link
  7229. -->
  7230. (I3 ^see 0 +)
  7231. Retracting propose*predict-no
  7232. -->
  7233. (O1906 ^name predict-no +)
  7234. (S1 ^operator O1906 +)
  7235. Retracting propose*predict-yes
  7236. -->
  7237. (O1905 ^name predict-yes +)
  7238. (S1 ^operator O1905 +)
  7239. Retracting elaborate*reward*based*on*reward
  7240. -->
  7241. (R956 ^value 1 +)
  7242. (R1 ^reward R956 +)
  7243. Retracting elaborate*copy-dir-to-output-link
  7244. -->
  7245. (I3 ^dir R +)
  7246. Retracting rl*prefer*rvt*predict-no*H0*6
  7247. -->
  7248. (S1 ^operator O1906 = 0.999977424773942)
  7249. Retracting rl*prefer*rvt*predict-yes*H0*5
  7250. -->
  7251. (S1 ^operator O1905 = 0.1215951465100475)
  7252. Retracting rl*prefer*rvt*predict-yes*H0*5*H1*14
  7253. -->
  7254. (S1 ^operator O1905 = 0.8783877442642956)
  7255. =>WM: (13376: S1 ^operator O1908 +)
  7256. =>WM: (13375: S1 ^operator O1907 +)
  7257. =>WM: (13374: I3 ^dir U)
  7258. =>WM: (13373: O1908 ^name predict-no)
  7259. =>WM: (13372: O1907 ^name predict-yes)
  7260. =>WM: (13371: R957 ^value 1)
  7261. =>WM: (13370: R1 ^reward R957)
  7262. =>WM: (13369: I3 ^see 1)
  7263. <=WM: (13360: S1 ^operator O1905 +)
  7264. <=WM: (13362: S1 ^operator O1905)
  7265. <=WM: (13361: S1 ^operator O1906 +)
  7266. <=WM: (13359: I3 ^dir R)
  7267. <=WM: (13355: R1 ^reward R956)
  7268. <=WM: (13272: I3 ^see 0)
  7269. <=WM: (13358: O1906 ^name predict-no)
  7270. <=WM: (13357: O1905 ^name predict-yes)
  7271. <=WM: (13356: R956 ^value 1)
  7272. --- Inner Elaboration Phase, active level 1 (S1) ---
  7273. Firing prefer*rvt*predict-yes*H0
  7274. -->
  7275. Firing rl*prefer*rvt*predict-yes*H0*1
  7276. -->
  7277. (S1 ^operator O1907 = 0.)
  7278. Firing prefer*rvt*predict-no*H0
  7279. -->
  7280. Firing rl*prefer*rvt*predict-no*H0*2
  7281. -->
  7282. (S1 ^operator O1908 = 1.)
  7283. inner elaboration loop at bottom goal.
  7284. Retracting rl*prefer*rvt*predict-no*H0*2
  7285. -->
  7286. (S1 ^operator O1906 = 1.)
  7287. Retracting rl*prefer*rvt*predict-yes*H0*1
  7288. -->
  7289. (S1 ^operator O1905 = 0.)
  7290. --- END Proposal Phase ---
  7291. --- Decision Phase ---
  7292. RL update rl*prefer*rvt*predict-yes*H0*5 0.534522 -0.412927 0.121595 -> 0.534523 -0.412926 0.121597(R,m,v=1,0.857143,0.123182)
  7293. RL update rl*prefer*rvt*predict-yes*H0*5*H1*14 0.465464 0.412924 0.878388 -> 0.465465 0.412924 0.878389(R,m,v=1,1,0)
  7294. =>WM: (13377: S1 ^operator O1908)
  7295. 954: O: O1908 (predict-no)
  7296. --- END Decision Phase ---
  7297. --- Application Phase ---
  7298. --- Firing Productions (PE) For State At Depth 1 ---
  7299. --- Inner Elaboration Phase, active level 1 (S1) ---
  7300. Firing apply*operator
  7301. -->
  7302. (I3 ^predict-no N954 + :O )
  7303. Firing apply*operator*complete
  7304. -->
  7305. (I3 ^predict-yes N953 - :O )
  7306. inner elaboration loop at bottom goal.
  7307. --- Change Working Memory (PE) ---
  7308. =>WM: (13378: I3 ^predict-no N954)
  7309. <=WM: (13364: N953 ^status complete)
  7310. <=WM: (13363: I3 ^predict-yes N953)
  7311. --- Firing Productions (IE) For State At Depth 1 ---
  7312. --- Inner Elaboration Phase, active level 1 (S1) ---
  7313. Firing monitor*world
  7314. -->
  7315. I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
  7316. --- Change Working Memory (IE) ---
  7317. --- END Application Phase ---
  7318. --- Output Phase ---
  7319. ENV: Agent did: predict-no for direction U in state State-B
  7320. In State-B moving U
  7321. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  7322. predict error 0
  7323. dir: dir isL
  7324. --- END Output Phase ---
  7325. /|\--- Input Phase ---
  7326. =>WM: (13382: I2 ^dir L)
  7327. =>WM: (13381: I2 ^reward 1)
  7328. =>WM: (13380: I2 ^see 0)
  7329. =>WM: (13379: N954 ^status complete)
  7330. <=WM: (13367: I2 ^dir U)
  7331. <=WM: (13366: I2 ^reward 1)
  7332. <=WM: (13365: I2 ^see 1)
  7333. =>WM: (13383: I2 ^level-1 R1-root)
  7334. <=WM: (13368: I2 ^level-1 R1-root)
  7335. --- END Input Phase ---
  7336. --- Proposal Phase ---
  7337. --- Inner Elaboration Phase, active level 1 (S1) ---
  7338. Firing rl*prefer*rvt*predict-no*H0*4*H1*16
  7339. -->
  7340. (S1 ^operator O1908 = -0.168718511744511)
  7341. Firing rl*prefer*rvt*predict-yes*H0*3*H1*17
  7342. -->
  7343. (S1 ^operator O1907 = 0.6093893278107597)
  7344. Firing prefer*rvt*predict-no*H0*4*H1
  7345. -->
  7346. Firing prefer*rvt*predict-yes*H0*3*H1
  7347. -->
  7348. Firing elaborate*copy-see-to-output-link
  7349. -->
  7350. (I3 ^see 0 +)
  7351. Firing elaborate*reward*based*on*reward
  7352. -->
  7353. (R958 ^value 1 +)
  7354. (R1 ^reward R958 +)
  7355. Firing propose*predict-yes
  7356. -->
  7357. (O1909 ^name predict-yes +)
  7358. (S1 ^operator O1909 +)
  7359. Firing propose*predict-no
  7360. -->
  7361. (O1910 ^name predict-no +)
  7362. (S1 ^operator O1910 +)
  7363. Firing rl*prefer*rvt*predict-no*H0*4
  7364. -->
  7365. (S1 ^operator O1908 = 0.3145217607813431)
  7366. Firing rl*prefer*rvt*predict-yes*H0*3
  7367. -->
  7368. (S1 ^operator O1907 = 0.3908143935841644)
  7369. Firing prefer*rvt*predict-yes*H0
  7370. -->
  7371. Firing prefer*rvt*predict-no*H0
  7372. -->
  7373. Firing elaborate*copy-dir-to-output-link
  7374. -->
  7375. (I3 ^dir L +)
  7376. inner elaboration loop at bottom goal.
  7377. Retracting elaborate*copy-see-to-output-link
  7378. -->
  7379. (I3 ^see 1 +)
  7380. Retracting propose*predict-no
  7381. -->
  7382. (O1908 ^name predict-no +)
  7383. (S1 ^operator O1908 +)
  7384. Retracting propose*predict-yes
  7385. -->
  7386. (O1907 ^name predict-yes +)
  7387. (S1 ^operator O1907 +)
  7388. Retracting elaborate*reward*based*on*reward
  7389. -->
  7390. (R957 ^value 1 +)
  7391. (R1 ^reward R957 +)
  7392. Retracting elaborate*copy-dir-to-output-link
  7393. -->
  7394. (I3 ^dir U +)
  7395. Retracting rl*prefer*rvt*predict-no*H0*2
  7396. -->
  7397. (S1 ^operator O1908 = 1.)
  7398. Retracting rl*prefer*rvt*predict-yes*H0*1
  7399. -->
  7400. (S1 ^operator O1907 = 0.)
  7401. =>WM: (13391: S1 ^operator O1910 +)
  7402. =>WM: (13390: S1 ^operator O1909 +)
  7403. =>WM: (13389: I3 ^dir L)
  7404. =>WM: (13388: O1910 ^name predict-no)
  7405. =>WM: (13387: O1909 ^name predict-yes)
  7406. =>WM: (13386: R958 ^value 1)
  7407. =>WM: (13385: R1 ^reward R958)
  7408. =>WM: (13384: I3 ^see 0)
  7409. <=WM: (13375: S1 ^operator O1907 +)
  7410. <=WM: (13376: S1 ^operator O1908 +)
  7411. <=WM: (13377: S1 ^operator O1908)
  7412. <=WM: (13374: I3 ^dir U)
  7413. <=WM: (13370: R1 ^reward R957)
  7414. <=WM: (13369: I3 ^see 1)
  7415. <=WM: (13373: O1908 ^name predict-no)
  7416. <=WM: (13372: O1907 ^name predict-yes)
  7417. <=WM: (13371: 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*3*H1*17
  7422. -->
  7423. (S1 ^operator O1909 = 0.6093893278107597)
  7424. Firing rl*prefer*rvt*predict-yes*H0*3
  7425. -->
  7426. (S1 ^operator O1909 = 0.3908143935841644)
  7427. Firing prefer*rvt*predict-yes*H0*3*H1
  7428. -->
  7429. Firing prefer*rvt*predict-no*H0
  7430. -->
  7431. Firing rl*prefer*rvt*predict-no*H0*4*H1*16
  7432. -->
  7433. (S1 ^operator O1910 = -0.168718511744511)
  7434. Firing rl*prefer*rvt*predict-no*H0*4
  7435. -->
  7436. (S1 ^operator O1910 = 0.3145217607813431)
  7437. Firing prefer*rvt*predict-no*H0*4*H1
  7438. -->
  7439. inner elaboration loop at bottom goal.
  7440. Retracting rl*prefer*rvt*predict-no*H0*4
  7441. -->
  7442. (S1 ^operator O1908 = 0.3145217607813431)
  7443. Retracting rl*prefer*rvt*predict-no*H0*4*H1*16
  7444. -->
  7445. (S1 ^operator O1908 = -0.168718511744511)
  7446. Retracting rl*prefer*rvt*predict-yes*H0*3
  7447. -->
  7448. (S1 ^operator O1907 = 0.3908143935841644)
  7449. Retracting rl*prefer*rvt*predict-yes*H0*3*H1*17
  7450. -->
  7451. (S1 ^operator O1907 = 0.6093893278107597)
  7452. --- END Proposal Phase ---
  7453. --- Decision Phase ---
  7454. RL update rl*prefer*rvt*predict-no*H0*2 1 0 1 -> 1 0 1(R,m,v=1,1,0)
  7455. =>WM: (13392: S1 ^operator O1909)
  7456. 955: O: O1909 (predict-yes)
  7457. --- END Decision Phase ---
  7458. --- Application Phase ---
  7459. --- Firing Productions (PE) For State At Depth 1 ---
  7460. --- Inner Elaboration Phase, active level 1 (S1) ---
  7461. Firing apply*operator
  7462. -->
  7463. (I3 ^predict-yes N955 + :O )
  7464. Firing apply*operator*complete
  7465. -->
  7466. (I3 ^predict-no N954 - :O )
  7467. inner elaboration loop at bottom goal.
  7468. --- Change Working Memory (PE) ---
  7469. =>WM: (13393: I3 ^predict-yes N955)
  7470. <=WM: (13379: N954 ^status complete)
  7471. <=WM: (13378: I3 ^predict-no N954)
  7472. --- Firing Productions (IE) For State At Depth 1 ---
  7473. --- Inner Elaboration Phase, active level 1 (S1) ---
  7474. Firing monitor*world
  7475. -->
  7476. I see 1 and I'm going to do: predict-yes inner elaboration loop at bottom goal.
  7477. --- Change Working Memory (IE) ---
  7478. --- END Application Phase ---
  7479. --- Output Phase ---
  7480. ENV: Agent did: predict-yes for direction L in state State-B
  7481. In State-B moving L
  7482. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  7483. predict error 0
  7484. dir: dir isU
  7485. --- END Output Phase ---
  7486. -/--- Input Phase ---
  7487. =>WM: (13397: I2 ^dir U)
  7488. =>WM: (13396: I2 ^reward 1)
  7489. =>WM: (13395: I2 ^see 1)
  7490. =>WM: (13394: N955 ^status complete)
  7491. <=WM: (13382: I2 ^dir L)
  7492. <=WM: (13381: I2 ^reward 1)
  7493. <=WM: (13380: I2 ^see 0)
  7494. =>WM: (13398: I2 ^level-1 L1-root)
  7495. <=WM: (13383: I2 ^level-1 R1-root)
  7496. --- END Input Phase ---
  7497. --- Proposal Phase ---
  7498. --- Inner Elaboration Phase, active level 1 (S1) ---
  7499. Firing elaborate*copy-see-to-output-link
  7500. -->
  7501. (I3 ^see 1 +)
  7502. Firing elaborate*reward*based*on*reward
  7503. -->
  7504. (R959 ^value 1 +)
  7505. (R1 ^reward R959 +)
  7506. Firing propose*predict-yes
  7507. -->
  7508. (O1911 ^name predict-yes +)
  7509. (S1 ^operator O1911 +)
  7510. Firing propose*predict-no
  7511. -->
  7512. (O1912 ^name predict-no +)
  7513. (S1 ^operator O1912 +)
  7514. Firing rl*prefer*rvt*predict-no*H0*2
  7515. -->
  7516. (S1 ^operator O1910 = 1.)
  7517. Firing rl*prefer*rvt*predict-yes*H0*1
  7518. -->
  7519. (S1 ^operator O1909 = 0.)
  7520. Firing prefer*rvt*predict-yes*H0
  7521. -->
  7522. Firing prefer*rvt*predict-no*H0
  7523. -->
  7524. Firing elaborate*copy-dir-to-output-link
  7525. -->
  7526. (I3 ^dir U +)
  7527. inner elaboration loop at bottom goal.
  7528. Retracting elaborate*copy-see-to-output-link
  7529. -->
  7530. (I3 ^see 0 +)
  7531. Retracting propose*predict-no
  7532. -->
  7533. (O1910 ^name predict-no +)
  7534. (S1 ^operator O1910 +)
  7535. Retracting propose*predict-yes
  7536. -->
  7537. (O1909 ^name predict-yes +)
  7538. (S1 ^operator O1909 +)
  7539. Retracting elaborate*reward*based*on*reward
  7540. -->
  7541. (R958 ^value 1 +)
  7542. (R1 ^reward R958 +)
  7543. Retracting elaborate*copy-dir-to-output-link
  7544. -->
  7545. (I3 ^dir L +)
  7546. Retracting rl*prefer*rvt*predict-no*H0*4
  7547. -->
  7548. (S1 ^operator O1910 = 0.3145217607813431)
  7549. Retracting rl*prefer*rvt*predict-no*H0*4*H1*16
  7550. -->
  7551. (S1 ^operator O1910 = -0.168718511744511)
  7552. Retracting rl*prefer*rvt*predict-yes*H0*3
  7553. -->
  7554. (S1 ^operator O1909 = 0.3908143935841644)
  7555. Retracting rl*prefer*rvt*predict-yes*H0*3*H1*17
  7556. -->
  7557. (S1 ^operator O1909 = 0.6093893278107597)
  7558. =>WM: (13406: S1 ^operator O1912 +)
  7559. =>WM: (13405: S1 ^operator O1911 +)
  7560. =>WM: (13404: I3 ^dir U)
  7561. =>WM: (13403: O1912 ^name predict-no)
  7562. =>WM: (13402: O1911 ^name predict-yes)
  7563. =>WM: (13401: R959 ^value 1)
  7564. =>WM: (13400: R1 ^reward R959)
  7565. =>WM: (13399: I3 ^see 1)
  7566. <=WM: (13390: S1 ^operator O1909 +)
  7567. <=WM: (13392: S1 ^operator O1909)
  7568. <=WM: (13391: S1 ^operator O1910 +)
  7569. <=WM: (13389: I3 ^dir L)
  7570. <=WM: (13385: R1 ^reward R958)
  7571. <=WM: (13384: I3 ^see 0)
  7572. <=WM: (13388: O1910 ^name predict-no)
  7573. <=WM: (13387: O1909 ^name predict-yes)
  7574. <=WM: (13386: R958 ^value 1)
  7575. --- Inner Elaboration Phase, active level 1 (S1) ---
  7576. Firing prefer*rvt*predict-yes*H0
  7577. -->
  7578. Firing rl*prefer*rvt*predict-yes*H0*1
  7579. -->
  7580. (S1 ^operator O1911 = 0.)
  7581. Firing prefer*rvt*predict-no*H0
  7582. -->
  7583. Firing rl*prefer*rvt*predict-no*H0*2
  7584. -->
  7585. (S1 ^operator O1912 = 1.)
  7586. inner elaboration loop at bottom goal.
  7587. Retracting rl*prefer*rvt*predict-no*H0*2
  7588. -->
  7589. (S1 ^operator O1910 = 1.)
  7590. Retracting rl*prefer*rvt*predict-yes*H0*1
  7591. -->
  7592. (S1 ^operator O1909 = 0.)
  7593. --- END Proposal Phase ---
  7594. --- Decision Phase ---
  7595. RL update rl*prefer*rvt*predict-yes*H0*3 0.472355 -0.0815405 0.390814 -> 0.47234 -0.081543 0.390797(R,m,v=1,0.940789,0.0560735)
  7596. RL update rl*prefer*rvt*predict-yes*H0*3*H1*17 0.527819 0.0815706 0.609389 -> 0.527802 0.0815677 0.60937(R,m,v=1,1,0)
  7597. =>WM: (13407: S1 ^operator O1912)
  7598. 956: O: O1912 (predict-no)
  7599. --- END Decision Phase ---
  7600. --- Application Phase ---
  7601. --- Firing Productions (PE) For State At Depth 1 ---
  7602. --- Inner Elaboration Phase, active level 1 (S1) ---
  7603. Firing apply*operator
  7604. -->
  7605. (I3 ^predict-no N956 + :O )
  7606. Firing apply*operator*complete
  7607. -->
  7608. (I3 ^predict-yes N955 - :O )
  7609. inner elaboration loop at bottom goal.
  7610. --- Change Working Memory (PE) ---
  7611. =>WM: (13408: I3 ^predict-no N956)
  7612. <=WM: (13394: N955 ^status complete)
  7613. <=WM: (13393: I3 ^predict-yes N955)
  7614. --- Firing Productions (IE) For State At Depth 1 ---
  7615. --- Inner Elaboration Phase, active level 1 (S1) ---
  7616. Firing monitor*world
  7617. -->
  7618. I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
  7619. --- Change Working Memory (IE) ---
  7620. --- END Application Phase ---
  7621. --- Output Phase ---
  7622. ENV: Agent did: predict-no for direction U in state State-A
  7623. In State-A moving U
  7624. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  7625. predict error 0
  7626. dir: dir isL
  7627. --- END Output Phase ---
  7628. |\---- Input Phase ---
  7629. =>WM: (13412: I2 ^dir L)
  7630. =>WM: (13411: I2 ^reward 1)
  7631. =>WM: (13410: I2 ^see 0)
  7632. =>WM: (13409: N956 ^status complete)
  7633. <=WM: (13397: I2 ^dir U)
  7634. <=WM: (13396: I2 ^reward 1)
  7635. <=WM: (13395: I2 ^see 1)
  7636. =>WM: (13413: I2 ^level-1 L1-root)
  7637. <=WM: (13398: I2 ^level-1 L1-root)
  7638. --- END Input Phase ---
  7639. --- Proposal Phase ---
  7640. --- Inner Elaboration Phase, active level 1 (S1) ---
  7641. Firing rl*prefer*rvt*predict-yes*H0*3*H1*11
  7642. -->
  7643. (S1 ^operator O1911 = -0.2062723012911647)
  7644. Firing rl*prefer*rvt*predict-no*H0*4*H1*10
  7645. -->
  7646. (S1 ^operator O1912 = 0.6855673437364445)
  7647. Firing prefer*rvt*predict-no*H0*4*H1
  7648. -->
  7649. Firing prefer*rvt*predict-yes*H0*3*H1
  7650. -->
  7651. Firing elaborate*copy-see-to-output-link
  7652. -->
  7653. (I3 ^see 0 +)
  7654. Firing elaborate*reward*based*on*reward
  7655. -->
  7656. (R960 ^value 1 +)
  7657. (R1 ^reward R960 +)
  7658. Firing propose*predict-yes
  7659. -->
  7660. (O1913 ^name predict-yes +)
  7661. (S1 ^operator O1913 +)
  7662. Firing propose*predict-no
  7663. -->
  7664. (O1914 ^name predict-no +)
  7665. (S1 ^operator O1914 +)
  7666. Firing rl*prefer*rvt*predict-no*H0*4
  7667. -->
  7668. (S1 ^operator O1912 = 0.3145217607813431)
  7669. Firing rl*prefer*rvt*predict-yes*H0*3
  7670. -->
  7671. (S1 ^operator O1911 = 0.3907974841024591)
  7672. Firing prefer*rvt*predict-yes*H0
  7673. -->
  7674. Firing prefer*rvt*predict-no*H0
  7675. -->
  7676. Firing elaborate*copy-dir-to-output-link
  7677. -->
  7678. (I3 ^dir L +)
  7679. inner elaboration loop at bottom goal.
  7680. Retracting elaborate*copy-see-to-output-link
  7681. -->
  7682. (I3 ^see 1 +)
  7683. Retracting propose*predict-no
  7684. -->
  7685. (O1912 ^name predict-no +)
  7686. (S1 ^operator O1912 +)
  7687. Retracting propose*predict-yes
  7688. -->
  7689. (O1911 ^name predict-yes +)
  7690. (S1 ^operator O1911 +)
  7691. Retracting elaborate*reward*based*on*reward
  7692. -->
  7693. (R959 ^value 1 +)
  7694. (R1 ^reward R959 +)
  7695. Retracting elaborate*copy-dir-to-output-link
  7696. -->
  7697. (I3 ^dir U +)
  7698. Retracting rl*prefer*rvt*predict-no*H0*2
  7699. -->
  7700. (S1 ^operator O1912 = 1.)
  7701. Retracting rl*prefer*rvt*predict-yes*H0*1
  7702. -->
  7703. (S1 ^operator O1911 = 0.)
  7704. =>WM: (13421: S1 ^operator O1914 +)
  7705. =>WM: (13420: S1 ^operator O1913 +)
  7706. =>WM: (13419: I3 ^dir L)
  7707. =>WM: (13418: O1914 ^name predict-no)
  7708. =>WM: (13417: O1913 ^name predict-yes)
  7709. =>WM: (13416: R960 ^value 1)
  7710. =>WM: (13415: R1 ^reward R960)
  7711. =>WM: (13414: I3 ^see 0)
  7712. <=WM: (13405: S1 ^operator O1911 +)
  7713. <=WM: (13406: S1 ^operator O1912 +)
  7714. <=WM: (13407: S1 ^operator O1912)
  7715. <=WM: (13404: I3 ^dir U)
  7716. <=WM: (13400: R1 ^reward R959)
  7717. <=WM: (13399: I3 ^see 1)
  7718. <=WM: (13403: O1912 ^name predict-no)
  7719. <=WM: (13402: O1911 ^name predict-yes)
  7720. <=WM: (13401: R959 ^value 1)
  7721. --- Inner Elaboration Phase, active level 1 (S1) ---
  7722. Firing prefer*rvt*predict-yes*H0
  7723. -->
  7724. Firing rl*prefer*rvt*predict-yes*H0*3*H1*11
  7725. -->
  7726. (S1 ^operator O1913 = -0.2062723012911647)
  7727. Firing rl*prefer*rvt*predict-yes*H0*3
  7728. -->
  7729. (S1 ^operator O1913 = 0.3907974841024591)
  7730. Firing prefer*rvt*predict-yes*H0*3*H1
  7731. -->
  7732. Firing prefer*rvt*predict-no*H0
  7733. -->
  7734. Firing rl*prefer*rvt*predict-no*H0*4*H1*10
  7735. -->
  7736. (S1 ^operator O1914 = 0.6855673437364445)
  7737. Firing rl*prefer*rvt*predict-no*H0*4
  7738. -->
  7739. (S1 ^operator O1914 = 0.3145217607813431)
  7740. Firing prefer*rvt*predict-no*H0*4*H1
  7741. -->
  7742. inner elaboration loop at bottom goal.
  7743. Retracting rl*prefer*rvt*predict-no*H0*4
  7744. -->
  7745. (S1 ^operator O1912 = 0.3145217607813431)
  7746. Retracting rl*prefer*rvt*predict-no*H0*4*H1*10
  7747. -->
  7748. (S1 ^operator O1912 = 0.6855673437364445)
  7749. Retracting rl*prefer*rvt*predict-yes*H0*3
  7750. -->
  7751. (S1 ^operator O1911 = 0.3907974841024591)
  7752. Retracting rl*prefer*rvt*predict-yes*H0*3*H1*11
  7753. -->
  7754. (S1 ^operator O1911 = -0.2062723012911647)
  7755. --- END Proposal Phase ---
  7756. --- Decision Phase ---
  7757. RL update rl*prefer*rvt*predict-no*H0*2 1 0 1 -> 1 0 1(R,m,v=1,1,0)
  7758. =>WM: (13422: S1 ^operator O1914)
  7759. 957: O: O1914 (predict-no)
  7760. --- END Decision Phase ---
  7761. --- Application Phase ---
  7762. --- Firing Productions (PE) For State At Depth 1 ---
  7763. --- Inner Elaboration Phase, active level 1 (S1) ---
  7764. Firing apply*operator
  7765. -->
  7766. (I3 ^predict-no N957 + :O )
  7767. Firing apply*operator*complete
  7768. -->
  7769. (I3 ^predict-no N956 - :O )
  7770. inner elaboration loop at bottom goal.
  7771. --- Change Working Memory (PE) ---
  7772. =>WM: (13423: I3 ^predict-no N957)
  7773. <=WM: (13409: N956 ^status complete)
  7774. <=WM: (13408: I3 ^predict-no N956)
  7775. --- Firing Productions (IE) For State At Depth 1 ---
  7776. --- Inner Elaboration Phase, active level 1 (S1) ---
  7777. Firing monitor*world
  7778. -->
  7779. I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
  7780. --- Change Working Memory (IE) ---
  7781. --- END Application Phase ---
  7782. --- Output Phase ---
  7783. ENV: Agent did: predict-no for direction L in state State-A
  7784. In State-A moving L
  7785. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  7786. predict error 0
  7787. dir: dir isR
  7788. --- END Output Phase ---
  7789. /|\--- Input Phase ---
  7790. =>WM: (13427: I2 ^dir R)
  7791. =>WM: (13426: I2 ^reward 1)
  7792. =>WM: (13425: I2 ^see 0)
  7793. =>WM: (13424: N957 ^status complete)
  7794. <=WM: (13412: I2 ^dir L)
  7795. <=WM: (13411: I2 ^reward 1)
  7796. <=WM: (13410: I2 ^see 0)
  7797. =>WM: (13428: I2 ^level-1 L0-root)
  7798. <=WM: (13413: I2 ^level-1 L1-root)
  7799. --- END Input Phase ---
  7800. --- Proposal Phase ---
  7801. --- Inner Elaboration Phase, active level 1 (S1) ---
  7802. Firing rl*prefer*rvt*predict-yes*H0*5*H1*14
  7803. -->
  7804. (S1 ^operator O1913 = 0.8783894024939338)
  7805. Firing prefer*rvt*predict-yes*H0*5*H1
  7806. -->
  7807. Firing elaborate*copy-see-to-output-link
  7808. -->
  7809. (I3 ^see 0 +)
  7810. Firing elaborate*reward*based*on*reward
  7811. -->
  7812. (R961 ^value 1 +)
  7813. (R1 ^reward R961 +)
  7814. Firing propose*predict-yes
  7815. -->
  7816. (O1915 ^name predict-yes +)
  7817. (S1 ^operator O1915 +)
  7818. Firing propose*predict-no
  7819. -->
  7820. (O1916 ^name predict-no +)
  7821. (S1 ^operator O1916 +)
  7822. Firing rl*prefer*rvt*predict-no*H0*6
  7823. -->
  7824. (S1 ^operator O1914 = 0.999977424773942)
  7825. Firing rl*prefer*rvt*predict-yes*H0*5
  7826. -->
  7827. (S1 ^operator O1913 = 0.1215965434178113)
  7828. Firing prefer*rvt*predict-yes*H0
  7829. -->
  7830. Firing prefer*rvt*predict-no*H0
  7831. -->
  7832. Firing elaborate*copy-dir-to-output-link
  7833. -->
  7834. (I3 ^dir R +)
  7835. inner elaboration loop at bottom goal.
  7836. Retracting elaborate*copy-see-to-output-link
  7837. -->
  7838. (I3 ^see 0 +)
  7839. Retracting propose*predict-no
  7840. -->
  7841. (O1914 ^name predict-no +)
  7842. (S1 ^operator O1914 +)
  7843. Retracting propose*predict-yes
  7844. -->
  7845. (O1913 ^name predict-yes +)
  7846. (S1 ^operator O1913 +)
  7847. Retracting elaborate*reward*based*on*reward
  7848. -->
  7849. (R960 ^value 1 +)
  7850. (R1 ^reward R960 +)
  7851. Retracting elaborate*copy-dir-to-output-link
  7852. -->
  7853. (I3 ^dir L +)
  7854. Retracting rl*prefer*rvt*predict-no*H0*4
  7855. -->
  7856. (S1 ^operator O1914 = 0.3145217607813431)
  7857. Retracting rl*prefer*rvt*predict-no*H0*4*H1*10
  7858. -->
  7859. (S1 ^operator O1914 = 0.6855673437364445)
  7860. Retracting rl*prefer*rvt*predict-yes*H0*3
  7861. -->
  7862. (S1 ^operator O1913 = 0.3907974841024591)
  7863. Retracting rl*prefer*rvt*predict-yes*H0*3*H1*11
  7864. -->
  7865. (S1 ^operator O1913 = -0.2062723012911647)
  7866. =>WM: (13435: S1 ^operator O1916 +)
  7867. =>WM: (13434: S1 ^operator O1915 +)
  7868. =>WM: (13433: I3 ^dir R)
  7869. =>WM: (13432: O1916 ^name predict-no)
  7870. =>WM: (13431: O1915 ^name predict-yes)
  7871. =>WM: (13430: R961 ^value 1)
  7872. =>WM: (13429: R1 ^reward R961)
  7873. <=WM: (13420: S1 ^operator O1913 +)
  7874. <=WM: (13421: S1 ^operator O1914 +)
  7875. <=WM: (13422: S1 ^operator O1914)
  7876. <=WM: (13419: I3 ^dir L)
  7877. <=WM: (13415: R1 ^reward R960)
  7878. <=WM: (13418: O1914 ^name predict-no)
  7879. <=WM: (13417: O1913 ^name predict-yes)
  7880. <=WM: (13416: R960 ^value 1)
  7881. --- Inner Elaboration Phase, active level 1 (S1) ---
  7882. Firing prefer*rvt*predict-yes*H0
  7883. -->
  7884. Firing rl*prefer*rvt*predict-yes*H0*5
  7885. -->
  7886. (S1 ^operator O1915 = 0.1215965434178113)
  7887. Firing prefer*rvt*predict-yes*H0*5*H1
  7888. -->
  7889. Firing rl*prefer*rvt*predict-yes*H0*5*H1*14
  7890. -->
  7891. (S1 ^operator O1915 = 0.8783894024939338)
  7892. Firing prefer*rvt*predict-no*H0
  7893. -->
  7894. Firing rl*prefer*rvt*predict-no*H0*6
  7895. -->
  7896. (S1 ^operator O1916 = 0.999977424773942)
  7897. inner elaboration loop at bottom goal.
  7898. Retracting rl*prefer*rvt*predict-no*H0*6
  7899. -->
  7900. (S1 ^operator O1914 = 0.999977424773942)
  7901. Retracting rl*prefer*rvt*predict-yes*H0*5
  7902. -->
  7903. (S1 ^operator O1913 = 0.1215965434178113)
  7904. Retracting rl*prefer*rvt*predict-yes*H0*5*H1*14
  7905. -->
  7906. (S1 ^operator O1913 = 0.8783894024939338)
  7907. --- END Proposal Phase ---
  7908. --- Decision Phase ---
  7909. RL update rl*prefer*rvt*predict-no*H0*4 0.478568 -0.164047 0.314522 -> 0.478562 -0.164047 0.314514(R,m,v=1,0.918919,0.0750138)
  7910. RL update rl*prefer*rvt*predict-no*H0*4*H1*10 0.521513 0.164055 0.685567 -> 0.521505 0.164054 0.685559(R,m,v=1,1,0)
  7911. =>WM: (13436: S1 ^operator O1915)
  7912. 958: O: O1915 (predict-yes)
  7913. --- END Decision Phase ---
  7914. --- Application Phase ---
  7915. --- Firing Productions (PE) For State At Depth 1 ---
  7916. --- Inner Elaboration Phase, active level 1 (S1) ---
  7917. Firing apply*operator
  7918. -->
  7919. (I3 ^predict-yes N958 + :O )
  7920. Firing apply*operator*complete
  7921. -->
  7922. (I3 ^predict-no N957 - :O )
  7923. inner elaboration loop at bottom goal.
  7924. --- Change Working Memory (PE) ---
  7925. =>WM: (13437: I3 ^predict-yes N958)
  7926. <=WM: (13424: N957 ^status complete)
  7927. <=WM: (13423: I3 ^predict-no N957)
  7928. --- Firing Productions (IE) For State At Depth 1 ---
  7929. --- Inner Elaboration Phase, active level 1 (S1) ---
  7930. Firing monitor*world
  7931. -->
  7932. I see 1 and I'm going to do: predict-yes inner elaboration loop at bottom goal.
  7933. --- Change Working Memory (IE) ---
  7934. --- END Application Phase ---
  7935. --- Output Phase ---
  7936. ENV: Agent did: predict-yes for direction R in state State-A
  7937. In State-A moving R
  7938. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  7939. predict error 0
  7940. dir: dir isR
  7941. --- END Output Phase ---
  7942. -/|--- Input Phase ---
  7943. =>WM: (13441: I2 ^dir R)
  7944. =>WM: (13440: I2 ^reward 1)
  7945. =>WM: (13439: I2 ^see 1)
  7946. =>WM: (13438: N958 ^status complete)
  7947. <=WM: (13427: I2 ^dir R)
  7948. <=WM: (13426: I2 ^reward 1)
  7949. <=WM: (13425: I2 ^see 0)
  7950. =>WM: (13442: I2 ^level-1 R1-root)
  7951. <=WM: (13428: I2 ^level-1 L0-root)
  7952. --- END Input Phase ---
  7953. --- Proposal Phase ---
  7954. --- Inner Elaboration Phase, active level 1 (S1) ---
  7955. Firing rl*prefer*rvt*predict-yes*H0*5*H1*15
  7956. -->
  7957. (S1 ^operator O1915 = -0.04253361215288998)
  7958. Firing prefer*rvt*predict-yes*H0*5*H1
  7959. -->
  7960. Firing elaborate*copy-see-to-output-link
  7961. -->
  7962. (I3 ^see 1 +)
  7963. Firing elaborate*reward*based*on*reward
  7964. -->
  7965. (R962 ^value 1 +)
  7966. (R1 ^reward R962 +)
  7967. Firing propose*predict-yes
  7968. -->
  7969. (O1917 ^name predict-yes +)
  7970. (S1 ^operator O1917 +)
  7971. Firing propose*predict-no
  7972. -->
  7973. (O1918 ^name predict-no +)
  7974. (S1 ^operator O1918 +)
  7975. Firing rl*prefer*rvt*predict-no*H0*6
  7976. -->
  7977. (S1 ^operator O1916 = 0.999977424773942)
  7978. Firing rl*prefer*rvt*predict-yes*H0*5
  7979. -->
  7980. (S1 ^operator O1915 = 0.1215965434178113)
  7981. Firing prefer*rvt*predict-yes*H0
  7982. -->
  7983. Firing prefer*rvt*predict-no*H0
  7984. -->
  7985. Firing elaborate*copy-dir-to-output-link
  7986. -->
  7987. (I3 ^dir R +)
  7988. inner elaboration loop at bottom goal.
  7989. Retracting elaborate*copy-see-to-output-link
  7990. -->
  7991. (I3 ^see 0 +)
  7992. Retracting propose*predict-no
  7993. -->
  7994. (O1916 ^name predict-no +)
  7995. (S1 ^operator O1916 +)
  7996. Retracting propose*predict-yes
  7997. -->
  7998. (O1915 ^name predict-yes +)
  7999. (S1 ^operator O1915 +)
  8000. Retracting elaborate*reward*based*on*reward
  8001. -->
  8002. (R961 ^value 1 +)
  8003. (R1 ^reward R961 +)
  8004. Retracting elaborate*copy-dir-to-output-link
  8005. -->
  8006. (I3 ^dir R +)
  8007. Retracting rl*prefer*rvt*predict-no*H0*6
  8008. -->
  8009. (S1 ^operator O1916 = 0.999977424773942)
  8010. Retracting rl*prefer*rvt*predict-yes*H0*5*H1*14
  8011. -->
  8012. (S1 ^operator O1915 = 0.8783894024939338)
  8013. Retracting rl*prefer*rvt*predict-yes*H0*5
  8014. -->
  8015. (S1 ^operator O1915 = 0.1215965434178113)
  8016. =>WM: (13449: S1 ^operator O1918 +)
  8017. =>WM: (13448: S1 ^operator O1917 +)
  8018. =>WM: (13447: O1918 ^name predict-no)
  8019. =>WM: (13446: O1917 ^name predict-yes)
  8020. =>WM: (13445: R962 ^value 1)
  8021. =>WM: (13444: R1 ^reward R962)
  8022. =>WM: (13443: I3 ^see 1)
  8023. <=WM: (13434: S1 ^operator O1915 +)
  8024. <=WM: (13436: S1 ^operator O1915)
  8025. <=WM: (13435: S1 ^operator O1916 +)
  8026. <=WM: (13429: R1 ^reward R961)
  8027. <=WM: (13414: I3 ^see 0)
  8028. <=WM: (13432: O1916 ^name predict-no)
  8029. <=WM: (13431: O1915 ^name predict-yes)
  8030. <=WM: (13430: R961 ^value 1)
  8031. --- Inner Elaboration Phase, active level 1 (S1) ---
  8032. Firing prefer*rvt*predict-yes*H0
  8033. -->
  8034. Firing rl*prefer*rvt*predict-yes*H0*5
  8035. -->
  8036. (S1 ^operator O1917 = 0.1215965434178113)
  8037. Firing prefer*rvt*predict-yes*H0*5*H1
  8038. -->
  8039. Firing rl*prefer*rvt*predict-yes*H0*5*H1*15
  8040. -->
  8041. (S1 ^operator O1917 = -0.04253361215288998)
  8042. Firing prefer*rvt*predict-no*H0
  8043. -->
  8044. Firing rl*prefer*rvt*predict-no*H0*6
  8045. -->
  8046. (S1 ^operator O1918 = 0.999977424773942)
  8047. inner elaboration loop at bottom goal.
  8048. Retracting rl*prefer*rvt*predict-no*H0*6
  8049. -->
  8050. (S1 ^operator O1916 = 0.999977424773942)
  8051. Retracting rl*prefer*rvt*predict-yes*H0*5
  8052. -->
  8053. (S1 ^operator O1915 = 0.1215965434178113)
  8054. Retracting rl*prefer*rvt*predict-yes*H0*5*H1*15
  8055. -->
  8056. (S1 ^operator O1915 = -0.04253361215288998)
  8057. --- END Proposal Phase ---
  8058. --- Decision Phase ---
  8059. RL update rl*prefer*rvt*predict-yes*H0*5 0.534523 -0.412926 0.121597 -> 0.534524 -0.412926 0.121598(R,m,v=1,0.857988,0.12257)
  8060. RL update rl*prefer*rvt*predict-yes*H0*5*H1*14 0.465465 0.412924 0.878389 -> 0.465467 0.412924 0.878391(R,m,v=1,1,0)
  8061. =>WM: (13450: S1 ^operator O1918)
  8062. 959: O: O1918 (predict-no)
  8063. --- END Decision Phase ---
  8064. --- Application Phase ---
  8065. --- Firing Productions (PE) For State At Depth 1 ---
  8066. --- Inner Elaboration Phase, active level 1 (S1) ---
  8067. Firing apply*operator
  8068. -->
  8069. (I3 ^predict-no N959 + :O )
  8070. Firing apply*operator*complete
  8071. -->
  8072. (I3 ^predict-yes N958 - :O )
  8073. inner elaboration loop at bottom goal.
  8074. --- Change Working Memory (PE) ---
  8075. =>WM: (13451: I3 ^predict-no N959)
  8076. <=WM: (13438: N958 ^status complete)
  8077. <=WM: (13437: I3 ^predict-yes N958)
  8078. --- Firing Productions (IE) For State At Depth 1 ---
  8079. --- Inner Elaboration Phase, active level 1 (S1) ---
  8080. Firing monitor*world
  8081. -->
  8082. I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
  8083. --- Change Working Memory (IE) ---
  8084. --- END Application Phase ---
  8085. --- Output Phase ---
  8086. ENV: Agent did: predict-no for direction R in state State-B
  8087. In State-B moving R
  8088. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  8089. predict error 0
  8090. dir: dir isL
  8091. --- END Output Phase ---
  8092. \---- Input Phase ---
  8093. =>WM: (13455: I2 ^dir L)
  8094. =>WM: (13454: I2 ^reward 1)
  8095. =>WM: (13453: I2 ^see 0)
  8096. =>WM: (13452: N959 ^status complete)
  8097. <=WM: (13441: I2 ^dir R)
  8098. <=WM: (13440: I2 ^reward 1)
  8099. <=WM: (13439: I2 ^see 1)
  8100. =>WM: (13456: I2 ^level-1 R0-root)
  8101. <=WM: (13442: I2 ^level-1 R1-root)
  8102. --- END Input Phase ---
  8103. --- Proposal Phase ---
  8104. --- Inner Elaboration Phase, active level 1 (S1) ---
  8105. Firing rl*prefer*rvt*predict-no*H0*4*H1*8
  8106. -->
  8107. (S1 ^operator O1918 = -0.1984300550322165)
  8108. Firing rl*prefer*rvt*predict-yes*H0*3*H1*9
  8109. -->
  8110. (S1 ^operator O1917 = 0.6090773459257411)
  8111. Firing prefer*rvt*predict-no*H0*4*H1
  8112. -->
  8113. Firing prefer*rvt*predict-yes*H0*3*H1
  8114. -->
  8115. Firing elaborate*copy-see-to-output-link
  8116. -->
  8117. (I3 ^see 0 +)
  8118. Firing elaborate*reward*based*on*reward
  8119. -->
  8120. (R963 ^value 1 +)
  8121. (R1 ^reward R963 +)
  8122. Firing propose*predict-yes
  8123. -->
  8124. (O1919 ^name predict-yes +)
  8125. (S1 ^operator O1919 +)
  8126. Firing propose*predict-no
  8127. -->
  8128. (O1920 ^name predict-no +)
  8129. (S1 ^operator O1920 +)
  8130. Firing rl*prefer*rvt*predict-no*H0*4
  8131. -->
  8132. (S1 ^operator O1918 = 0.3145143319532709)
  8133. Firing rl*prefer*rvt*predict-yes*H0*3
  8134. -->
  8135. (S1 ^operator O1917 = 0.3907974841024591)
  8136. Firing prefer*rvt*predict-yes*H0
  8137. -->
  8138. Firing prefer*rvt*predict-no*H0
  8139. -->
  8140. Firing elaborate*copy-dir-to-output-link
  8141. -->
  8142. (I3 ^dir L +)
  8143. inner elaboration loop at bottom goal.
  8144. Retracting elaborate*copy-see-to-output-link
  8145. -->
  8146. (I3 ^see 1 +)
  8147. Retracting propose*predict-no
  8148. -->
  8149. (O1918 ^name predict-no +)
  8150. (S1 ^operator O1918 +)
  8151. Retracting propose*predict-yes
  8152. -->
  8153. (O1917 ^name predict-yes +)
  8154. (S1 ^operator O1917 +)
  8155. Retracting elaborate*reward*based*on*reward
  8156. -->
  8157. (R962 ^value 1 +)
  8158. (R1 ^reward R962 +)
  8159. Retracting elaborate*copy-dir-to-output-link
  8160. -->
  8161. (I3 ^dir R +)
  8162. Retracting rl*prefer*rvt*predict-no*H0*6
  8163. -->
  8164. (S1 ^operator O1918 = 0.999977424773942)
  8165. Retracting rl*prefer*rvt*predict-yes*H0*5*H1*15
  8166. -->
  8167. (S1 ^operator O1917 = -0.04253361215288998)
  8168. Retracting rl*prefer*rvt*predict-yes*H0*5
  8169. -->
  8170. (S1 ^operator O1917 = 0.121597689773478)
  8171. =>WM: (13464: S1 ^operator O1920 +)
  8172. =>WM: (13463: S1 ^operator O1919 +)
  8173. =>WM: (13462: I3 ^dir L)
  8174. =>WM: (13461: O1920 ^name predict-no)
  8175. =>WM: (13460: O1919 ^name predict-yes)
  8176. =>WM: (13459: R963 ^value 1)
  8177. =>WM: (13458: R1 ^reward R963)
  8178. =>WM: (13457: I3 ^see 0)
  8179. <=WM: (13448: S1 ^operator O1917 +)
  8180. <=WM: (13449: S1 ^operator O1918 +)
  8181. <=WM: (13450: S1 ^operator O1918)
  8182. <=WM: (13433: I3 ^dir R)
  8183. <=WM: (13444: R1 ^reward R962)
  8184. <=WM: (13443: I3 ^see 1)
  8185. <=WM: (13447: O1918 ^name predict-no)
  8186. <=WM: (13446: O1917 ^name predict-yes)
  8187. <=WM: (13445: R962 ^value 1)
  8188. --- Inner Elaboration Phase, active level 1 (S1) ---
  8189. Firing prefer*rvt*predict-yes*H0
  8190. -->
  8191. Firing rl*prefer*rvt*predict-yes*H0*3
  8192. -->
  8193. (S1 ^operator O1919 = 0.3907974841024591)
  8194. Firing prefer*rvt*predict-yes*H0*3*H1
  8195. -->
  8196. Firing rl*prefer*rvt*predict-yes*H0*3*H1*9
  8197. -->
  8198. (S1 ^operator O1919 = 0.6090773459257411)
  8199. Firing prefer*rvt*predict-no*H0
  8200. -->
  8201. Firing rl*prefer*rvt*predict-no*H0*4
  8202. -->
  8203. (S1 ^operator O1920 = 0.3145143319532709)
  8204. Firing prefer*rvt*predict-no*H0*4*H1
  8205. -->
  8206. Firing rl*prefer*rvt*predict-no*H0*4*H1*8
  8207. -->
  8208. (S1 ^operator O1920 = -0.1984300550322165)
  8209. inner elaboration loop at bottom goal.
  8210. Retracting rl*prefer*rvt*predict-no*H0*4
  8211. -->
  8212. (S1 ^operator O1918 = 0.3145143319532709)
  8213. Retracting rl*prefer*rvt*predict-no*H0*4*H1*8
  8214. -->
  8215. (S1 ^operator O1918 = -0.1984300550322165)
  8216. Retracting rl*prefer*rvt*predict-yes*H0*3
  8217. -->
  8218. (S1 ^operator O1917 = 0.3907974841024591)
  8219. Retracting rl*prefer*rvt*predict-yes*H0*3*H1*9
  8220. -->
  8221. (S1 ^operator O1917 = 0.6090773459257411)
  8222. --- END Proposal Phase ---
  8223. --- Decision Phase ---
  8224. RL update rl*prefer*rvt*predict-no*H0*6 0.999977 0 0.999977 -> 0.999981 0 0.999981(R,m,v=1,0.936782,0.0595641)
  8225. =>WM: (13465: S1 ^operator O1919)
  8226. 960: O: O1919 (predict-yes)
  8227. --- END Decision Phase ---
  8228. --- Application Phase ---
  8229. --- Firing Productions (PE) For State At Depth 1 ---
  8230. --- Inner Elaboration Phase, active level 1 (S1) ---
  8231. Firing apply*operator
  8232. -->
  8233. (I3 ^predict-yes N960 + :O )
  8234. Firing apply*operator*complete
  8235. -->
  8236. (I3 ^predict-no N959 - :O )
  8237. inner elaboration loop at bottom goal.
  8238. --- Change Working Memory (PE) ---
  8239. =>WM: (13466: I3 ^predict-yes N960)
  8240. <=WM: (13452: N959 ^status complete)
  8241. <=WM: (13451: I3 ^predict-no N959)
  8242. --- Firing Productions (IE) For State At Depth 1 ---
  8243. --- Inner Elaboration Phase, active level 1 (S1) ---
  8244. Firing monitor*world
  8245. -->
  8246. I see 1 and I'm going to do: predict-yes inner elaboration loop at bottom goal.
  8247. --- Change Working Memory (IE) ---
  8248. --- END Application Phase ---
  8249. --- Output Phase ---
  8250. ENV: Agent did: predict-yes for direction L in state State-B
  8251. In State-B moving L
  8252. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  8253. predict error 0
  8254. dir: dir isU
  8255. --- END Output Phase ---
  8256. /|\---- Input Phase ---
  8257. =>WM: (13470: I2 ^dir U)
  8258. =>WM: (13469: I2 ^reward 1)
  8259. =>WM: (13468: I2 ^see 1)
  8260. =>WM: (13467: N960 ^status complete)
  8261. <=WM: (13455: I2 ^dir L)
  8262. <=WM: (13454: I2 ^reward 1)
  8263. <=WM: (13453: I2 ^see 0)
  8264. =>WM: (13471: I2 ^level-1 L1-root)
  8265. <=WM: (13456: I2 ^level-1 R0-root)
  8266. --- END Input Phase ---
  8267. --- Proposal Phase ---
  8268. --- Inner Elaboration Phase, active level 1 (S1) ---
  8269. Firing elaborate*copy-see-to-output-link
  8270. -->
  8271. (I3 ^see 1 +)
  8272. Firing elaborate*reward*based*on*reward
  8273. -->
  8274. (R964 ^value 1 +)
  8275. (R1 ^reward R964 +)
  8276. Firing propose*predict-yes
  8277. -->
  8278. (O1921 ^name predict-yes +)
  8279. (S1 ^operator O1921 +)
  8280. Firing propose*predict-no
  8281. -->
  8282. (O1922 ^name predict-no +)
  8283. (S1 ^operator O1922 +)
  8284. Firing rl*prefer*rvt*predict-no*H0*2
  8285. -->
  8286. (S1 ^operator O1920 = 1.)
  8287. Firing rl*prefer*rvt*predict-yes*H0*1
  8288. -->
  8289. (S1 ^operator O1919 = 0.)
  8290. Firing prefer*rvt*predict-yes*H0
  8291. -->
  8292. Firing prefer*rvt*predict-no*H0
  8293. -->
  8294. Firing elaborate*copy-dir-to-output-link
  8295. -->
  8296. (I3 ^dir U +)
  8297. inner elaboration loop at bottom goal.
  8298. Retracting elaborate*copy-see-to-output-link
  8299. -->
  8300. (I3 ^see 0 +)
  8301. Retracting propose*predict-no
  8302. -->
  8303. (O1920 ^name predict-no +)
  8304. (S1 ^operator O1920 +)
  8305. Retracting propose*predict-yes
  8306. -->
  8307. (O1919 ^name predict-yes +)
  8308. (S1 ^operator O1919 +)
  8309. Retracting elaborate*reward*based*on*reward
  8310. -->
  8311. (R963 ^value 1 +)
  8312. (R1 ^reward R963 +)
  8313. Retracting elaborate*copy-dir-to-output-link
  8314. -->
  8315. (I3 ^dir L +)
  8316. Retracting rl*prefer*rvt*predict-no*H0*4*H1*8
  8317. -->
  8318. (S1 ^operator O1920 = -0.1984300550322165)
  8319. Retracting rl*prefer*rvt*predict-no*H0*4
  8320. -->
  8321. (S1 ^operator O1920 = 0.3145143319532709)
  8322. Retracting rl*prefer*rvt*predict-yes*H0*3*H1*9
  8323. -->
  8324. (S1 ^operator O1919 = 0.6090773459257411)
  8325. Retracting rl*prefer*rvt*predict-yes*H0*3
  8326. -->
  8327. (S1 ^operator O1919 = 0.3907974841024591)
  8328. =>WM: (13479: S1 ^operator O1922 +)
  8329. =>WM: (13478: S1 ^operator O1921 +)
  8330. =>WM: (13477: I3 ^dir U)
  8331. =>WM: (13476: O1922 ^name predict-no)
  8332. =>WM: (13475: O1921 ^name predict-yes)
  8333. =>WM: (13474: R964 ^value 1)
  8334. =>WM: (13473: R1 ^reward R964)
  8335. =>WM: (13472: I3 ^see 1)
  8336. <=WM: (13463: S1 ^operator O1919 +)
  8337. <=WM: (13465: S1 ^operator O1919)
  8338. <=WM: (13464: S1 ^operator O1920 +)
  8339. <=WM: (13462: I3 ^dir L)
  8340. <=WM: (13458: R1 ^reward R963)
  8341. <=WM: (13457: I3 ^see 0)
  8342. <=WM: (13461: O1920 ^name predict-no)
  8343. <=WM: (13460: O1919 ^name predict-yes)
  8344. <=WM: (13459: R963 ^value 1)
  8345. --- Inner Elaboration Phase, active level 1 (S1) ---
  8346. Firing prefer*rvt*predict-yes*H0
  8347. -->
  8348. Firing rl*prefer*rvt*predict-yes*H0*1
  8349. -->
  8350. (S1 ^operator O1921 = 0.)
  8351. Firing prefer*rvt*predict-no*H0
  8352. -->
  8353. Firing rl*prefer*rvt*predict-no*H0*2
  8354. -->
  8355. (S1 ^operator O1922 = 1.)
  8356. inner elaboration loop at bottom goal.
  8357. Retracting rl*prefer*rvt*predict-no*H0*2
  8358. -->
  8359. (S1 ^operator O1920 = 1.)
  8360. Retracting rl*prefer*rvt*predict-yes*H0*1
  8361. -->
  8362. (S1 ^operator O1919 = 0.)
  8363. --- END Proposal Phase ---
  8364. --- Decision Phase ---
  8365. RL update rl*prefer*rvt*predict-yes*H0*3 0.47234 -0.081543 0.390797 -> 0.472349 -0.0815415 0.390808(R,m,v=1,0.941176,0.0557276)
  8366. RL update rl*prefer*rvt*predict-yes*H0*3*H1*9 0.527553 0.0815245 0.609077 -> 0.527563 0.0815262 0.609089(R,m,v=1,1,0)
  8367. =>WM: (13480: S1 ^operator O1922)
  8368. 961: O: O1922 (predict-no)
  8369. --- END Decision Phase ---
  8370. --- Application Phase ---
  8371. --- Firing Productions (PE) For State At Depth 1 ---
  8372. --- Inner Elaboration Phase, active level 1 (S1) ---
  8373. Firing apply*operator
  8374. -->
  8375. (I3 ^predict-no N961 + :O )
  8376. Firing apply*operator*complete
  8377. -->
  8378. (I3 ^predict-yes N960 - :O )
  8379. inner elaboration loop at bottom goal.
  8380. --- Change Working Memory (PE) ---
  8381. =>WM: (13481: I3 ^predict-no N961)
  8382. <=WM: (13467: N960 ^status complete)
  8383. <=WM: (13466: I3 ^predict-yes N960)
  8384. --- Firing Productions (IE) For State At Depth 1 ---
  8385. --- Inner Elaboration Phase, active level 1 (S1) ---
  8386. Firing monitor*world
  8387. -->
  8388. I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
  8389. --- Change Working Memory (IE) ---
  8390. --- END Application Phase ---
  8391. --- Output Phase ---
  8392. ENV: Agent did: predict-no for direction U in state State-A
  8393. In State-A moving U
  8394. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  8395. predict error 0
  8396. dir: dir isL
  8397. --- END Output Phase ---
  8398. /--- Input Phase ---
  8399. =>WM: (13485: I2 ^dir L)
  8400. =>WM: (13484: I2 ^reward 1)
  8401. =>WM: (13483: I2 ^see 0)
  8402. =>WM: (13482: N961 ^status complete)
  8403. <=WM: (13470: I2 ^dir U)
  8404. <=WM: (13469: I2 ^reward 1)
  8405. <=WM: (13468: I2 ^see 1)
  8406. =>WM: (13486: I2 ^level-1 L1-root)
  8407. <=WM: (13471: I2 ^level-1 L1-root)
  8408. --- END Input Phase ---
  8409. --- Proposal Phase ---
  8410. --- Inner Elaboration Phase, active level 1 (S1) ---
  8411. Firing rl*prefer*rvt*predict-yes*H0*3*H1*11
  8412. -->
  8413. (S1 ^operator O1921 = -0.2062723012911647)
  8414. Firing rl*prefer*rvt*predict-no*H0*4*H1*10
  8415. -->
  8416. (S1 ^operator O1922 = 0.685558831823503)
  8417. Firing prefer*rvt*predict-no*H0*4*H1
  8418. -->
  8419. Firing prefer*rvt*predict-yes*H0*3*H1
  8420. -->
  8421. Firing elaborate*copy-see-to-output-link
  8422. -->
  8423. (I3 ^see 0 +)
  8424. Firing elaborate*reward*based*on*reward
  8425. -->
  8426. (R965 ^value 1 +)
  8427. (R1 ^reward R965 +)
  8428. Firing propose*predict-yes
  8429. -->
  8430. (O1923 ^name predict-yes +)
  8431. (S1 ^operator O1923 +)
  8432. Firing propose*predict-no
  8433. -->
  8434. (O1924 ^name predict-no +)
  8435. (S1 ^operator O1924 +)
  8436. Firing rl*prefer*rvt*predict-no*H0*4
  8437. -->
  8438. (S1 ^operator O1922 = 0.3145143319532709)
  8439. Firing rl*prefer*rvt*predict-yes*H0*3
  8440. -->
  8441. (S1 ^operator O1921 = 0.390807862285058)
  8442. Firing prefer*rvt*predict-yes*H0
  8443. -->
  8444. Firing prefer*rvt*predict-no*H0
  8445. -->
  8446. Firing elaborate*copy-dir-to-output-link
  8447. -->
  8448. (I3 ^dir L +)
  8449. inner elaboration loop at bottom goal.
  8450. Retracting elaborate*copy-see-to-output-link
  8451. -->
  8452. (I3 ^see 1 +)
  8453. Retracting propose*predict-no
  8454. -->
  8455. (O1922 ^name predict-no +)
  8456. (S1 ^operator O1922 +)
  8457. Retracting propose*predict-yes
  8458. -->
  8459. (O1921 ^name predict-yes +)
  8460. (S1 ^operator O1921 +)
  8461. Retracting elaborate*reward*based*on*reward
  8462. -->
  8463. (R964 ^value 1 +)
  8464. (R1 ^reward R964 +)
  8465. Retracting elaborate*copy-dir-to-output-link
  8466. -->
  8467. (I3 ^dir U +)
  8468. Retracting rl*prefer*rvt*predict-no*H0*2
  8469. -->
  8470. (S1 ^operator O1922 = 1.)
  8471. Retracting rl*prefer*rvt*predict-yes*H0*1
  8472. -->
  8473. (S1 ^operator O1921 = 0.)
  8474. =>WM: (13494: S1 ^operator O1924 +)
  8475. =>WM: (13493: S1 ^operator O1923 +)
  8476. =>WM: (13492: I3 ^dir L)
  8477. =>WM: (13491: O1924 ^name predict-no)
  8478. =>WM: (13490: O1923 ^name predict-yes)
  8479. =>WM: (13489: R965 ^value 1)
  8480. =>WM: (13488: R1 ^reward R965)
  8481. =>WM: (13487: I3 ^see 0)
  8482. <=WM: (13478: S1 ^operator O1921 +)
  8483. <=WM: (13479: S1 ^operator O1922 +)
  8484. <=WM: (13480: S1 ^operator O1922)
  8485. <=WM: (13477: I3 ^dir U)
  8486. <=WM: (13473: R1 ^reward R964)
  8487. <=WM: (13472: I3 ^see 1)
  8488. <=WM: (13476: O1922 ^name predict-no)
  8489. <=WM: (13475: O1921 ^name predict-yes)
  8490. <=WM: (13474: R964 ^value 1)
  8491. --- Inner Elaboration Phase, active level 1 (S1) ---
  8492. Firing prefer*rvt*predict-yes*H0
  8493. -->
  8494. Firing rl*prefer*rvt*predict-yes*H0*3*H1*11
  8495. -->
  8496. (S1 ^operator O1923 = -0.2062723012911647)
  8497. Firing rl*prefer*rvt*predict-yes*H0*3
  8498. -->
  8499. (S1 ^operator O1923 = 0.390807862285058)
  8500. Firing prefer*rvt*predict-yes*H0*3*H1
  8501. -->
  8502. Firing prefer*rvt*predict-no*H0
  8503. -->
  8504. Firing rl*prefer*rvt*predict-no*H0*4*H1*10
  8505. -->
  8506. (S1 ^operator O1924 = 0.685558831823503)
  8507. Firing rl*prefer*rvt*predict-no*H0*4
  8508. -->
  8509. (S1 ^operator O1924 = 0.3145143319532709)
  8510. Firing prefer*rvt*predict-no*H0*4*H1
  8511. -->
  8512. inner elaboration loop at bottom goal.
  8513. Retracting rl*prefer*rvt*predict-no*H0*4
  8514. -->
  8515. (S1 ^operator O1922 = 0.3145143319532709)
  8516. Retracting rl*prefer*rvt*predict-no*H0*4*H1*10
  8517. -->
  8518. (S1 ^operator O1922 = 0.685558831823503)
  8519. Retracting rl*prefer*rvt*predict-yes*H0*3
  8520. -->
  8521. (S1 ^operator O1921 = 0.390807862285058)
  8522. Retracting rl*prefer*rvt*predict-yes*H0*3*H1*11
  8523. -->
  8524. (S1 ^operator O1921 = -0.2062723012911647)
  8525. --- END Proposal Phase ---
  8526. --- Decision Phase ---
  8527. RL update rl*prefer*rvt*predict-no*H0*2 1 0 1 -> 1 0 1(R,m,v=1,1,0)
  8528. =>WM: (13495: S1 ^operator O1924)
  8529. 962: O: O1924 (predict-no)
  8530. --- END Decision Phase ---
  8531. --- Application Phase ---
  8532. --- Firing Productions (PE) For State At Depth 1 ---
  8533. --- Inner Elaboration Phase, active level 1 (S1) ---
  8534. Firing apply*operator
  8535. -->
  8536. (I3 ^predict-no N962 + :O )
  8537. Firing apply*operator*complete
  8538. -->
  8539. (I3 ^predict-no N961 - :O )
  8540. inner elaboration loop at bottom goal.
  8541. --- Change Working Memory (PE) ---
  8542. =>WM: (13496: I3 ^predict-no N962)
  8543. <=WM: (13482: N961 ^status complete)
  8544. <=WM: (13481: I3 ^predict-no N961)
  8545. --- Firing Productions (IE) For State At Depth 1 ---
  8546. --- Inner Elaboration Phase, active level 1 (S1) ---
  8547. Firing monitor*world
  8548. -->
  8549. I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
  8550. --- Change Working Memory (IE) ---
  8551. --- END Application Phase ---
  8552. --- Output Phase ---
  8553. ENV: Agent did: predict-no for direction L in state State-A
  8554. In State-A moving L
  8555. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  8556. predict error 0
  8557. dir: dir isU
  8558. --- END Output Phase ---
  8559. |\--- Input Phase ---
  8560. =>WM: (13500: I2 ^dir U)
  8561. =>WM: (13499: I2 ^reward 1)
  8562. =>WM: (13498: I2 ^see 0)
  8563. =>WM: (13497: N962 ^status complete)
  8564. <=WM: (13485: I2 ^dir L)
  8565. <=WM: (13484: I2 ^reward 1)
  8566. <=WM: (13483: I2 ^see 0)
  8567. =>WM: (13501: I2 ^level-1 L0-root)
  8568. <=WM: (13486: I2 ^level-1 L1-root)
  8569. --- END Input Phase ---
  8570. --- Proposal Phase ---
  8571. --- Inner Elaboration Phase, active level 1 (S1) ---
  8572. Firing elaborate*copy-see-to-output-link
  8573. -->
  8574. (I3 ^see 0 +)
  8575. Firing elaborate*reward*based*on*reward
  8576. -->
  8577. (R966 ^value 1 +)
  8578. (R1 ^reward R966 +)
  8579. Firing propose*predict-yes
  8580. -->
  8581. (O1925 ^name predict-yes +)
  8582. (S1 ^operator O1925 +)
  8583. Firing propose*predict-no
  8584. -->
  8585. (O1926 ^name predict-no +)
  8586. (S1 ^operator O1926 +)
  8587. Firing rl*prefer*rvt*predict-no*H0*2
  8588. -->
  8589. (S1 ^operator O1924 = 1.)
  8590. Firing rl*prefer*rvt*predict-yes*H0*1
  8591. -->
  8592. (S1 ^operator O1923 = 0.)
  8593. Firing prefer*rvt*predict-yes*H0
  8594. -->
  8595. Firing prefer*rvt*predict-no*H0
  8596. -->
  8597. Firing elaborate*copy-dir-to-output-link
  8598. -->
  8599. (I3 ^dir U +)
  8600. inner elaboration loop at bottom goal.
  8601. Retracting elaborate*copy-see-to-output-link
  8602. -->
  8603. (I3 ^see 0 +)
  8604. Retracting propose*predict-no
  8605. -->
  8606. (O1924 ^name predict-no +)
  8607. (S1 ^operator O1924 +)
  8608. Retracting propose*predict-yes
  8609. -->
  8610. (O1923 ^name predict-yes +)
  8611. (S1 ^operator O1923 +)
  8612. Retracting elaborate*reward*based*on*reward
  8613. -->
  8614. (R965 ^value 1 +)
  8615. (R1 ^reward R965 +)
  8616. Retracting elaborate*copy-dir-to-output-link
  8617. -->
  8618. (I3 ^dir L +)
  8619. Retracting rl*prefer*rvt*predict-no*H0*4
  8620. -->
  8621. (S1 ^operator O1924 = 0.3145143319532709)
  8622. Retracting rl*prefer*rvt*predict-no*H0*4*H1*10
  8623. -->
  8624. (S1 ^operator O1924 = 0.685558831823503)
  8625. Retracting rl*prefer*rvt*predict-yes*H0*3
  8626. -->
  8627. (S1 ^operator O1923 = 0.390807862285058)
  8628. Retracting rl*prefer*rvt*predict-yes*H0*3*H1*11
  8629. -->
  8630. (S1 ^operator O1923 = -0.2062723012911647)
  8631. =>WM: (13508: S1 ^operator O1926 +)
  8632. =>WM: (13507: S1 ^operator O1925 +)
  8633. =>WM: (13506: I3 ^dir U)
  8634. =>WM: (13505: O1926 ^name predict-no)
  8635. =>WM: (13504: O1925 ^name predict-yes)
  8636. =>WM: (13503: R966 ^value 1)
  8637. =>WM: (13502: R1 ^reward R966)
  8638. <=WM: (13493: S1 ^operator O1923 +)
  8639. <=WM: (13494: S1 ^operator O1924 +)
  8640. <=WM: (13495: S1 ^operator O1924)
  8641. <=WM: (13492: I3 ^dir L)
  8642. <=WM: (13488: R1 ^reward R965)
  8643. <=WM: (13491: O1924 ^name predict-no)
  8644. <=WM: (13490: O1923 ^name predict-yes)
  8645. <=WM: (13489: R965 ^value 1)
  8646. --- Inner Elaboration Phase, active level 1 (S1) ---
  8647. Firing prefer*rvt*predict-yes*H0
  8648. -->
  8649. Firing rl*prefer*rvt*predict-yes*H0*1
  8650. -->
  8651. (S1 ^operator O1925 = 0.)
  8652. Firing prefer*rvt*predict-no*H0
  8653. -->
  8654. Firing rl*prefer*rvt*predict-no*H0*2
  8655. -->
  8656. (S1 ^operator O1926 = 1.)
  8657. inner elaboration loop at bottom goal.
  8658. Retracting rl*prefer*rvt*predict-no*H0*2
  8659. -->
  8660. (S1 ^operator O1924 = 1.)
  8661. Retracting rl*prefer*rvt*predict-yes*H0*1
  8662. -->
  8663. (S1 ^operator O1923 = 0.)
  8664. --- END Proposal Phase ---
  8665. --- Decision Phase ---
  8666. RL update rl*prefer*rvt*predict-no*H0*4 0.478562 -0.164047 0.314514 -> 0.478556 -0.164048 0.314508(R,m,v=1,0.919463,0.0745511)
  8667. RL update rl*prefer*rvt*predict-no*H0*4*H1*10 0.521505 0.164054 0.685559 -> 0.521498 0.164053 0.685552(R,m,v=1,1,0)
  8668. =>WM: (13509: S1 ^operator O1926)
  8669. 963: O: O1926 (predict-no)
  8670. --- END Decision Phase ---
  8671. --- Application Phase ---
  8672. --- Firing Productions (PE) For State At Depth 1 ---
  8673. --- Inner Elaboration Phase, active level 1 (S1) ---
  8674. Firing apply*operator
  8675. -->
  8676. (I3 ^predict-no N963 + :O )
  8677. Firing apply*operator*complete
  8678. -->
  8679. (I3 ^predict-no N962 - :O )
  8680. inner elaboration loop at bottom goal.
  8681. --- Change Working Memory (PE) ---
  8682. =>WM: (13510: I3 ^predict-no N963)
  8683. <=WM: (13497: N962 ^status complete)
  8684. <=WM: (13496: I3 ^predict-no N962)
  8685. --- Firing Productions (IE) For State At Depth 1 ---
  8686. --- Inner Elaboration Phase, active level 1 (S1) ---
  8687. Firing monitor*world
  8688. -->
  8689. I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
  8690. --- Change Working Memory (IE) ---
  8691. --- END Application Phase ---
  8692. --- Output Phase ---
  8693. ENV: Agent did: predict-no for direction U in state State-A
  8694. In State-A moving U
  8695. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  8696. predict error 0
  8697. dir: dir isU
  8698. --- END Output Phase ---
  8699. -/|--- Input Phase ---
  8700. =>WM: (13514: I2 ^dir U)
  8701. =>WM: (13513: I2 ^reward 1)
  8702. =>WM: (13512: I2 ^see 0)
  8703. =>WM: (13511: N963 ^status complete)
  8704. <=WM: (13500: I2 ^dir U)
  8705. <=WM: (13499: I2 ^reward 1)
  8706. <=WM: (13498: I2 ^see 0)
  8707. =>WM: (13515: I2 ^level-1 L0-root)
  8708. <=WM: (13501: I2 ^level-1 L0-root)
  8709. --- END Input Phase ---
  8710. --- Proposal Phase ---
  8711. --- Inner Elaboration Phase, active level 1 (S1) ---
  8712. Firing elaborate*copy-see-to-output-link
  8713. -->
  8714. (I3 ^see 0 +)
  8715. Firing elaborate*reward*based*on*reward
  8716. -->
  8717. (R967 ^value 1 +)
  8718. (R1 ^reward R967 +)
  8719. Firing propose*predict-yes
  8720. -->
  8721. (O1927 ^name predict-yes +)
  8722. (S1 ^operator O1927 +)
  8723. Firing propose*predict-no
  8724. -->
  8725. (O1928 ^name predict-no +)
  8726. (S1 ^operator O1928 +)
  8727. Firing rl*prefer*rvt*predict-no*H0*2
  8728. -->
  8729. (S1 ^operator O1926 = 1.)
  8730. Firing rl*prefer*rvt*predict-yes*H0*1
  8731. -->
  8732. (S1 ^operator O1925 = 0.)
  8733. Firing prefer*rvt*predict-yes*H0
  8734. -->
  8735. Firing prefer*rvt*predict-no*H0
  8736. -->
  8737. Firing elaborate*copy-dir-to-output-link
  8738. -->
  8739. (I3 ^dir U +)
  8740. inner elaboration loop at bottom goal.
  8741. Retracting elaborate*copy-see-to-output-link
  8742. -->
  8743. (I3 ^see 0 +)
  8744. Retracting propose*predict-no
  8745. -->
  8746. (O1926 ^name predict-no +)
  8747. (S1 ^operator O1926 +)
  8748. Retracting propose*predict-yes
  8749. -->
  8750. (O1925 ^name predict-yes +)
  8751. (S1 ^operator O1925 +)
  8752. Retracting elaborate*reward*based*on*reward
  8753. -->
  8754. (R966 ^value 1 +)
  8755. (R1 ^reward R966 +)
  8756. Retracting elaborate*copy-dir-to-output-link
  8757. -->
  8758. (I3 ^dir U +)
  8759. Retracting rl*prefer*rvt*predict-no*H0*2
  8760. -->
  8761. (S1 ^operator O1926 = 1.)
  8762. Retracting rl*prefer*rvt*predict-yes*H0*1
  8763. -->
  8764. (S1 ^operator O1925 = 0.)
  8765. =>WM: (13521: S1 ^operator O1928 +)
  8766. =>WM: (13520: S1 ^operator O1927 +)
  8767. =>WM: (13519: O1928 ^name predict-no)
  8768. =>WM: (13518: O1927 ^name predict-yes)
  8769. =>WM: (13517: R967 ^value 1)
  8770. =>WM: (13516: R1 ^reward R967)
  8771. <=WM: (13507: S1 ^operator O1925 +)
  8772. <=WM: (13508: S1 ^operator O1926 +)
  8773. <=WM: (13509: S1 ^operator O1926)
  8774. <=WM: (13502: R1 ^reward R966)
  8775. <=WM: (13505: O1926 ^name predict-no)
  8776. <=WM: (13504: O1925 ^name predict-yes)
  8777. <=WM: (13503: R966 ^value 1)
  8778. --- Inner Elaboration Phase, active level 1 (S1) ---
  8779. Firing prefer*rvt*predict-yes*H0
  8780. -->
  8781. Firing rl*prefer*rvt*predict-yes*H0*1
  8782. -->
  8783. (S1 ^operator O1927 = 0.)
  8784. Firing prefer*rvt*predict-no*H0
  8785. -->
  8786. Firing rl*prefer*rvt*predict-no*H0*2
  8787. -->
  8788. (S1 ^operator O1928 = 1.)
  8789. inner elaboration loop at bottom goal.
  8790. Retracting rl*prefer*rvt*predict-no*H0*2
  8791. -->
  8792. (S1 ^operator O1926 = 1.)
  8793. Retracting rl*prefer*rvt*predict-yes*H0*1
  8794. -->
  8795. (S1 ^operator O1925 = 0.)
  8796. --- END Proposal Phase ---
  8797. --- Decision Phase ---
  8798. RL update rl*prefer*rvt*predict-no*H0*2 1 0 1 -> 1 0 1(R,m,v=1,1,0)
  8799. =>WM: (13522: S1 ^operator O1928)
  8800. 964: O: O1928 (predict-no)
  8801. --- END Decision Phase ---
  8802. --- Application Phase ---
  8803. --- Firing Productions (PE) For State At Depth 1 ---
  8804. --- Inner Elaboration Phase, active level 1 (S1) ---
  8805. Firing apply*operator
  8806. -->
  8807. (I3 ^predict-no N964 + :O )
  8808. Firing apply*operator*complete
  8809. -->
  8810. (I3 ^predict-no N963 - :O )
  8811. inner elaboration loop at bottom goal.
  8812. --- Change Working Memory (PE) ---
  8813. =>WM: (13523: I3 ^predict-no N964)
  8814. <=WM: (13511: N963 ^status complete)
  8815. <=WM: (13510: I3 ^predict-no N963)
  8816. --- Firing Productions (IE) For State At Depth 1 ---
  8817. --- Inner Elaboration Phase, active level 1 (S1) ---
  8818. Firing monitor*world
  8819. -->
  8820. I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
  8821. --- Change Working Memory (IE) ---
  8822. --- END Application Phase ---
  8823. --- Output Phase ---
  8824. ENV: Agent did: predict-no for direction U in state State-A
  8825. In State-A moving U
  8826. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  8827. predict error 0
  8828. dir: dir isR
  8829. --- END Output Phase ---
  8830. \-/--- Input Phase ---
  8831. =>WM: (13527: I2 ^dir R)
  8832. =>WM: (13526: I2 ^reward 1)
  8833. =>WM: (13525: I2 ^see 0)
  8834. =>WM: (13524: N964 ^status complete)
  8835. <=WM: (13514: I2 ^dir U)
  8836. <=WM: (13513: I2 ^reward 1)
  8837. <=WM: (13512: I2 ^see 0)
  8838. =>WM: (13528: I2 ^level-1 L0-root)
  8839. <=WM: (13515: I2 ^level-1 L0-root)
  8840. --- END Input Phase ---
  8841. --- Proposal Phase ---
  8842. --- Inner Elaboration Phase, active level 1 (S1) ---
  8843. Firing rl*prefer*rvt*predict-yes*H0*5*H1*14
  8844. -->
  8845. (S1 ^operator O1927 = 0.878390760537652)
  8846. Firing prefer*rvt*predict-yes*H0*5*H1
  8847. -->
  8848. Firing elaborate*copy-see-to-output-link
  8849. -->
  8850. (I3 ^see 0 +)
  8851. Firing elaborate*reward*based*on*reward
  8852. -->
  8853. (R968 ^value 1 +)
  8854. (R1 ^reward R968 +)
  8855. Firing propose*predict-yes
  8856. -->
  8857. (O1929 ^name predict-yes +)
  8858. (S1 ^operator O1929 +)
  8859. Firing propose*predict-no
  8860. -->
  8861. (O1930 ^name predict-no +)
  8862. (S1 ^operator O1930 +)
  8863. Firing rl*prefer*rvt*predict-no*H0*6
  8864. -->
  8865. (S1 ^operator O1928 = 0.9999810901454903)
  8866. Firing rl*prefer*rvt*predict-yes*H0*5
  8867. -->
  8868. (S1 ^operator O1927 = 0.121597689773478)
  8869. Firing prefer*rvt*predict-yes*H0
  8870. -->
  8871. Firing prefer*rvt*predict-no*H0
  8872. -->
  8873. Firing elaborate*copy-dir-to-output-link
  8874. -->
  8875. (I3 ^dir R +)
  8876. inner elaboration loop at bottom goal.
  8877. Retracting elaborate*copy-see-to-output-link
  8878. -->
  8879. (I3 ^see 0 +)
  8880. Retracting propose*predict-no
  8881. -->
  8882. (O1928 ^name predict-no +)
  8883. (S1 ^operator O1928 +)
  8884. Retracting propose*predict-yes
  8885. -->
  8886. (O1927 ^name predict-yes +)
  8887. (S1 ^operator O1927 +)
  8888. Retracting elaborate*reward*based*on*reward
  8889. -->
  8890. (R967 ^value 1 +)
  8891. (R1 ^reward R967 +)
  8892. Retracting elaborate*copy-dir-to-output-link
  8893. -->
  8894. (I3 ^dir U +)
  8895. Retracting rl*prefer*rvt*predict-no*H0*2
  8896. -->
  8897. (S1 ^operator O1928 = 1.)
  8898. Retracting rl*prefer*rvt*predict-yes*H0*1
  8899. -->
  8900. (S1 ^operator O1927 = 0.)
  8901. =>WM: (13535: S1 ^operator O1930 +)
  8902. =>WM: (13534: S1 ^operator O1929 +)
  8903. =>WM: (13533: I3 ^dir R)
  8904. =>WM: (13532: O1930 ^name predict-no)
  8905. =>WM: (13531: O1929 ^name predict-yes)
  8906. =>WM: (13530: R968 ^value 1)
  8907. =>WM: (13529: R1 ^reward R968)
  8908. <=WM: (13520: S1 ^operator O1927 +)
  8909. <=WM: (13521: S1 ^operator O1928 +)
  8910. <=WM: (13522: S1 ^operator O1928)
  8911. <=WM: (13506: I3 ^dir U)
  8912. <=WM: (13516: R1 ^reward R967)
  8913. <=WM: (13519: O1928 ^name predict-no)
  8914. <=WM: (13518: O1927 ^name predict-yes)
  8915. <=WM: (13517: R967 ^value 1)
  8916. --- Inner Elaboration Phase, active level 1 (S1) ---
  8917. Firing prefer*rvt*predict-yes*H0
  8918. -->
  8919. Firing rl*prefer*rvt*predict-yes*H0*5*H1*14
  8920. -->
  8921. (S1 ^operator O1929 = 0.878390760537652)
  8922. Firing rl*prefer*rvt*predict-yes*H0*5
  8923. -->
  8924. (S1 ^operator O1929 = 0.121597689773478)
  8925. Firing prefer*rvt*predict-yes*H0*5*H1
  8926. -->
  8927. Firing prefer*rvt*predict-no*H0
  8928. -->
  8929. Firing rl*prefer*rvt*predict-no*H0*6
  8930. -->
  8931. (S1 ^operator O1930 = 0.9999810901454903)
  8932. inner elaboration loop at bottom goal.
  8933. Retracting rl*prefer*rvt*predict-no*H0*6
  8934. -->
  8935. (S1 ^operator O1928 = 0.9999810901454903)
  8936. Retracting rl*prefer*rvt*predict-yes*H0*5
  8937. -->
  8938. (S1 ^operator O1927 = 0.121597689773478)
  8939. Retracting rl*prefer*rvt*predict-yes*H0*5*H1*14
  8940. -->
  8941. (S1 ^operator O1927 = 0.878390760537652)
  8942. --- END Proposal Phase ---
  8943. --- Decision Phase ---
  8944. RL update rl*prefer*rvt*predict-no*H0*2 1 0 1 -> 1 0 1(R,m,v=1,1,0)
  8945. =>WM: (13536: S1 ^operator O1929)
  8946. 965: O: O1929 (predict-yes)
  8947. --- END Decision Phase ---
  8948. --- Application Phase ---
  8949. --- Firing Productions (PE) For State At Depth 1 ---
  8950. --- Inner Elaboration Phase, active level 1 (S1) ---
  8951. Firing apply*operator
  8952. -->
  8953. (I3 ^predict-yes N965 + :O )
  8954. Firing apply*operator*complete
  8955. -->
  8956. (I3 ^predict-no N964 - :O )
  8957. inner elaboration loop at bottom goal.
  8958. --- Change Working Memory (PE) ---
  8959. =>WM: (13537: I3 ^predict-yes N965)
  8960. <=WM: (13524: N964 ^status complete)
  8961. <=WM: (13523: I3 ^predict-no N964)
  8962. --- Firing Productions (IE) For State At Depth 1 ---
  8963. --- Inner Elaboration Phase, active level 1 (S1) ---
  8964. Firing monitor*world
  8965. -->
  8966. I see 1 and I'm going to do: predict-yes inner elaboration loop at bottom goal.
  8967. --- Change Working Memory (IE) ---
  8968. --- END Application Phase ---
  8969. --- Output Phase ---
  8970. ENV: Agent did: predict-yes for direction R in state State-A
  8971. In State-A moving R
  8972. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  8973. predict error 0
  8974. dir: dir isU
  8975. --- END Output Phase ---
  8976. |\---- Input Phase ---
  8977. =>WM: (13541: I2 ^dir U)
  8978. =>WM: (13540: I2 ^reward 1)
  8979. =>WM: (13539: I2 ^see 1)
  8980. =>WM: (13538: N965 ^status complete)
  8981. <=WM: (13527: I2 ^dir R)
  8982. <=WM: (13526: I2 ^reward 1)
  8983. <=WM: (13525: I2 ^see 0)
  8984. =>WM: (13542: I2 ^level-1 R1-root)
  8985. <=WM: (13528: I2 ^level-1 L0-root)
  8986. --- END Input Phase ---
  8987. --- Proposal Phase ---
  8988. --- Inner Elaboration Phase, active level 1 (S1) ---
  8989. Firing elaborate*copy-see-to-output-link
  8990. -->
  8991. (I3 ^see 1 +)
  8992. Firing elaborate*reward*based*on*reward
  8993. -->
  8994. (R969 ^value 1 +)
  8995. (R1 ^reward R969 +)
  8996. Firing propose*predict-yes
  8997. -->
  8998. (O1931 ^name predict-yes +)
  8999. (S1 ^operator O1931 +)
  9000. Firing propose*predict-no
  9001. -->
  9002. (O1932 ^name predict-no +)
  9003. (S1 ^operator O1932 +)
  9004. Firing rl*prefer*rvt*predict-no*H0*2
  9005. -->
  9006. (S1 ^operator O1930 = 1.)
  9007. Firing rl*prefer*rvt*predict-yes*H0*1
  9008. -->
  9009. (S1 ^operator O1929 = 0.)
  9010. Firing prefer*rvt*predict-yes*H0
  9011. -->
  9012. Firing prefer*rvt*predict-no*H0
  9013. -->
  9014. Firing elaborate*copy-dir-to-output-link
  9015. -->
  9016. (I3 ^dir U +)
  9017. inner elaboration loop at bottom goal.
  9018. Retracting elaborate*copy-see-to-output-link
  9019. -->
  9020. (I3 ^see 0 +)
  9021. Retracting propose*predict-no
  9022. -->
  9023. (O1930 ^name predict-no +)
  9024. (S1 ^operator O1930 +)
  9025. Retracting propose*predict-yes
  9026. -->
  9027. (O1929 ^name predict-yes +)
  9028. (S1 ^operator O1929 +)
  9029. Retracting elaborate*reward*based*on*reward
  9030. -->
  9031. (R968 ^value 1 +)
  9032. (R1 ^reward R968 +)
  9033. Retracting elaborate*copy-dir-to-output-link
  9034. -->
  9035. (I3 ^dir R +)
  9036. Retracting rl*prefer*rvt*predict-no*H0*6
  9037. -->
  9038. (S1 ^operator O1930 = 0.9999810901454903)
  9039. Retracting rl*prefer*rvt*predict-yes*H0*5
  9040. -->
  9041. (S1 ^operator O1929 = 0.121597689773478)
  9042. Retracting rl*prefer*rvt*predict-yes*H0*5*H1*14
  9043. -->
  9044. (S1 ^operator O1929 = 0.878390760537652)
  9045. =>WM: (13550: S1 ^operator O1932 +)
  9046. =>WM: (13549: S1 ^operator O1931 +)
  9047. =>WM: (13548: I3 ^dir U)
  9048. =>WM: (13547: O1932 ^name predict-no)
  9049. =>WM: (13546: O1931 ^name predict-yes)
  9050. =>WM: (13545: R969 ^value 1)
  9051. =>WM: (13544: R1 ^reward R969)
  9052. =>WM: (13543: I3 ^see 1)
  9053. <=WM: (13534: S1 ^operator O1929 +)
  9054. <=WM: (13536: S1 ^operator O1929)
  9055. <=WM: (13535: S1 ^operator O1930 +)
  9056. <=WM: (13533: I3 ^dir R)
  9057. <=WM: (13529: R1 ^reward R968)
  9058. <=WM: (13487: I3 ^see 0)
  9059. <=WM: (13532: O1930 ^name predict-no)
  9060. <=WM: (13531: O1929 ^name predict-yes)
  9061. <=WM: (13530: R968 ^value 1)
  9062. --- Inner Elaboration Phase, active level 1 (S1) ---
  9063. Firing prefer*rvt*predict-yes*H0
  9064. -->
  9065. Firing rl*prefer*rvt*predict-yes*H0*1
  9066. -->
  9067. (S1 ^operator O1931 = 0.)
  9068. Firing prefer*rvt*predict-no*H0
  9069. -->
  9070. Firing rl*prefer*rvt*predict-no*H0*2
  9071. -->
  9072. (S1 ^operator O1932 = 1.)
  9073. inner elaboration loop at bottom goal.
  9074. Retracting rl*prefer*rvt*predict-no*H0*2
  9075. -->
  9076. (S1 ^operator O1930 = 1.)
  9077. Retracting rl*prefer*rvt*predict-yes*H0*1
  9078. -->
  9079. (S1 ^operator O1929 = 0.)
  9080. --- END Proposal Phase ---
  9081. --- Decision Phase ---
  9082. RL update rl*prefer*rvt*predict-yes*H0*5 0.534524 -0.412926 0.121598 -> 0.534525 -0.412926 0.121599(R,m,v=1,0.858824,0.121963)
  9083. RL update rl*prefer*rvt*predict-yes*H0*5*H1*14 0.465467 0.412924 0.878391 -> 0.465467 0.412924 0.878392(R,m,v=1,1,0)
  9084. =>WM: (13551: S1 ^operator O1932)
  9085. 966: O: O1932 (predict-no)
  9086. --- END Decision Phase ---
  9087. --- Application Phase ---
  9088. --- Firing Productions (PE) For State At Depth 1 ---
  9089. --- Inner Elaboration Phase, active level 1 (S1) ---
  9090. Firing apply*operator
  9091. -->
  9092. (I3 ^predict-no N966 + :O )
  9093. Firing apply*operator*complete
  9094. -->
  9095. (I3 ^predict-yes N965 - :O )
  9096. inner elaboration loop at bottom goal.
  9097. --- Change Working Memory (PE) ---
  9098. =>WM: (13552: I3 ^predict-no N966)
  9099. <=WM: (13538: N965 ^status complete)
  9100. <=WM: (13537: I3 ^predict-yes N965)
  9101. --- Firing Productions (IE) For State At Depth 1 ---
  9102. --- Inner Elaboration Phase, active level 1 (S1) ---
  9103. Firing monitor*world
  9104. -->
  9105. I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
  9106. --- Change Working Memory (IE) ---
  9107. --- END Application Phase ---
  9108. --- Output Phase ---
  9109. ENV: Agent did: predict-no for direction U in state State-B
  9110. In State-B moving U
  9111. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  9112. predict error 0
  9113. dir: dir isL
  9114. --- END Output Phase ---
  9115. /|--- Input Phase ---
  9116. =>WM: (13556: I2 ^dir L)
  9117. =>WM: (13555: I2 ^reward 1)
  9118. =>WM: (13554: I2 ^see 0)
  9119. =>WM: (13553: N966 ^status complete)
  9120. <=WM: (13541: I2 ^dir U)
  9121. <=WM: (13540: I2 ^reward 1)
  9122. <=WM: (13539: I2 ^see 1)
  9123. =>WM: (13557: I2 ^level-1 R1-root)
  9124. <=WM: (13542: I2 ^level-1 R1-root)
  9125. --- END Input Phase ---
  9126. --- Proposal Phase ---
  9127. --- Inner Elaboration Phase, active level 1 (S1) ---
  9128. Firing rl*prefer*rvt*predict-no*H0*4*H1*16
  9129. -->
  9130. (S1 ^operator O1932 = -0.168718511744511)
  9131. Firing rl*prefer*rvt*predict-yes*H0*3*H1*17
  9132. -->
  9133. (S1 ^operator O1931 = 0.6093697568764296)
  9134. Firing prefer*rvt*predict-no*H0*4*H1
  9135. -->
  9136. Firing prefer*rvt*predict-yes*H0*3*H1
  9137. -->
  9138. Firing elaborate*copy-see-to-output-link
  9139. -->
  9140. (I3 ^see 0 +)
  9141. Firing elaborate*reward*based*on*reward
  9142. -->
  9143. (R970 ^value 1 +)
  9144. (R1 ^reward R970 +)
  9145. Firing propose*predict-yes
  9146. -->
  9147. (O1933 ^name predict-yes +)
  9148. (S1 ^operator O1933 +)
  9149. Firing propose*predict-no
  9150. -->
  9151. (O1934 ^name predict-no +)
  9152. (S1 ^operator O1934 +)
  9153. Firing rl*prefer*rvt*predict-no*H0*4
  9154. -->
  9155. (S1 ^operator O1932 = 0.3145082389793297)
  9156. Firing rl*prefer*rvt*predict-yes*H0*3
  9157. -->
  9158. (S1 ^operator O1931 = 0.390807862285058)
  9159. Firing prefer*rvt*predict-yes*H0
  9160. -->
  9161. Firing prefer*rvt*predict-no*H0
  9162. -->
  9163. Firing elaborate*copy-dir-to-output-link
  9164. -->
  9165. (I3 ^dir L +)
  9166. inner elaboration loop at bottom goal.
  9167. Retracting elaborate*copy-see-to-output-link
  9168. -->
  9169. (I3 ^see 1 +)
  9170. Retracting propose*predict-no
  9171. -->
  9172. (O1932 ^name predict-no +)
  9173. (S1 ^operator O1932 +)
  9174. Retracting propose*predict-yes
  9175. -->
  9176. (O1931 ^name predict-yes +)
  9177. (S1 ^operator O1931 +)
  9178. Retracting elaborate*reward*based*on*reward
  9179. -->
  9180. (R969 ^value 1 +)
  9181. (R1 ^reward R969 +)
  9182. Retracting elaborate*copy-dir-to-output-link
  9183. -->
  9184. (I3 ^dir U +)
  9185. Retracting rl*prefer*rvt*predict-no*H0*2
  9186. -->
  9187. (S1 ^operator O1932 = 1.)
  9188. Retracting rl*prefer*rvt*predict-yes*H0*1
  9189. -->
  9190. (S1 ^operator O1931 = 0.)
  9191. =>WM: (13565: S1 ^operator O1934 +)
  9192. =>WM: (13564: S1 ^operator O1933 +)
  9193. =>WM: (13563: I3 ^dir L)
  9194. =>WM: (13562: O1934 ^name predict-no)
  9195. =>WM: (13561: O1933 ^name predict-yes)
  9196. =>WM: (13560: R970 ^value 1)
  9197. =>WM: (13559: R1 ^reward R970)
  9198. =>WM: (13558: I3 ^see 0)
  9199. <=WM: (13549: S1 ^operator O1931 +)
  9200. <=WM: (13550: S1 ^operator O1932 +)
  9201. <=WM: (13551: S1 ^operator O1932)
  9202. <=WM: (13548: I3 ^dir U)
  9203. <=WM: (13544: R1 ^reward R969)
  9204. <=WM: (13543: I3 ^see 1)
  9205. <=WM: (13547: O1932 ^name predict-no)
  9206. <=WM: (13546: O1931 ^name predict-yes)
  9207. <=WM: (13545: R969 ^value 1)
  9208. --- Inner Elaboration Phase, active level 1 (S1) ---
  9209. Firing prefer*rvt*predict-yes*H0
  9210. -->
  9211. Firing rl*prefer*rvt*predict-yes*H0*3*H1*17
  9212. -->
  9213. (S1 ^operator O1933 = 0.6093697568764296)
  9214. Firing rl*prefer*rvt*predict-yes*H0*3
  9215. -->
  9216. (S1 ^operator O1933 = 0.390807862285058)
  9217. Firing prefer*rvt*predict-yes*H0*3*H1
  9218. -->
  9219. Firing prefer*rvt*predict-no*H0
  9220. -->
  9221. Firing rl*prefer*rvt*predict-no*H0*4*H1*16
  9222. -->
  9223. (S1 ^operator O1934 = -0.168718511744511)
  9224. Firing rl*prefer*rvt*predict-no*H0*4
  9225. -->
  9226. (S1 ^operator O1934 = 0.3145082389793297)
  9227. Firing prefer*rvt*predict-no*H0*4*H1
  9228. -->
  9229. inner elaboration loop at bottom goal.
  9230. Retracting rl*prefer*rvt*predict-no*H0*4
  9231. -->
  9232. (S1 ^operator O1932 = 0.3145082389793297)
  9233. Retracting rl*prefer*rvt*predict-no*H0*4*H1*16
  9234. -->
  9235. (S1 ^operator O1932 = -0.168718511744511)
  9236. Retracting rl*prefer*rvt*predict-yes*H0*3
  9237. -->
  9238. (S1 ^operator O1931 = 0.390807862285058)
  9239. Retracting rl*prefer*rvt*predict-yes*H0*3*H1*17
  9240. -->
  9241. (S1 ^operator O1931 = 0.6093697568764296)
  9242. --- END Proposal Phase ---
  9243. --- Decision Phase ---
  9244. RL update rl*prefer*rvt*predict-no*H0*2 1 0 1 -> 1 0 1(R,m,v=1,1,0)
  9245. =>WM: (13566: S1 ^operator O1933)
  9246. 967: O: O1933 (predict-yes)
  9247. --- END Decision Phase ---
  9248. --- Application Phase ---
  9249. --- Firing Productions (PE) For State At Depth 1 ---
  9250. --- Inner Elaboration Phase, active level 1 (S1) ---
  9251. Firing apply*operator
  9252. -->
  9253. (I3 ^predict-yes N967 + :O )
  9254. Firing apply*operator*complete
  9255. -->
  9256. (I3 ^predict-no N966 - :O )
  9257. inner elaboration loop at bottom goal.
  9258. --- Change Working Memory (PE) ---
  9259. =>WM: (13567: I3 ^predict-yes N967)
  9260. <=WM: (13553: N966 ^status complete)
  9261. <=WM: (13552: I3 ^predict-no N966)
  9262. --- Firing Productions (IE) For State At Depth 1 ---
  9263. --- Inner Elaboration Phase, active level 1 (S1) ---
  9264. Firing monitor*world
  9265. -->
  9266. I see 1 and I'm going to do: predict-yes inner elaboration loop at bottom goal.
  9267. --- Change Working Memory (IE) ---
  9268. --- END Application Phase ---
  9269. --- Output Phase ---
  9270. ENV: Agent did: predict-yes for direction L in state State-B
  9271. In State-B moving L
  9272. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  9273. predict error 0
  9274. dir: dir isL
  9275. --- END Output Phase ---
  9276. \-/--- Input Phase ---
  9277. =>WM: (13571: I2 ^dir L)
  9278. =>WM: (13570: I2 ^reward 1)
  9279. =>WM: (13569: I2 ^see 1)
  9280. =>WM: (13568: N967 ^status complete)
  9281. <=WM: (13556: I2 ^dir L)
  9282. <=WM: (13555: I2 ^reward 1)
  9283. <=WM: (13554: I2 ^see 0)
  9284. =>WM: (13572: I2 ^level-1 L1-root)
  9285. <=WM: (13557: I2 ^level-1 R1-root)
  9286. --- END Input Phase ---
  9287. --- Proposal Phase ---
  9288. --- Inner Elaboration Phase, active level 1 (S1) ---
  9289. Firing rl*prefer*rvt*predict-yes*H0*3*H1*11
  9290. -->
  9291. (S1 ^operator O1933 = -0.2062723012911647)
  9292. Firing rl*prefer*rvt*predict-no*H0*4*H1*10
  9293. -->
  9294. (S1 ^operator O1934 = 0.685551861847024)
  9295. Firing prefer*rvt*predict-no*H0*4*H1
  9296. -->
  9297. Firing prefer*rvt*predict-yes*H0*3*H1
  9298. -->
  9299. Firing elaborate*copy-see-to-output-link
  9300. -->
  9301. (I3 ^see 1 +)
  9302. Firing elaborate*reward*based*on*reward
  9303. -->
  9304. (R971 ^value 1 +)
  9305. (R1 ^reward R971 +)
  9306. Firing propose*predict-yes
  9307. -->
  9308. (O1935 ^name predict-yes +)
  9309. (S1 ^operator O1935 +)
  9310. Firing propose*predict-no
  9311. -->
  9312. (O1936 ^name predict-no +)
  9313. (S1 ^operator O1936 +)
  9314. Firing rl*prefer*rvt*predict-no*H0*4
  9315. -->
  9316. (S1 ^operator O1934 = 0.3145082389793297)
  9317. Firing rl*prefer*rvt*predict-yes*H0*3
  9318. -->
  9319. (S1 ^operator O1933 = 0.390807862285058)
  9320. Firing prefer*rvt*predict-yes*H0
  9321. -->
  9322. Firing prefer*rvt*predict-no*H0
  9323. -->
  9324. Firing elaborate*copy-dir-to-output-link
  9325. -->
  9326. (I3 ^dir L +)
  9327. inner elaboration loop at bottom goal.
  9328. Retracting elaborate*copy-see-to-output-link
  9329. -->
  9330. (I3 ^see 0 +)
  9331. Retracting propose*predict-no
  9332. -->
  9333. (O1934 ^name predict-no +)
  9334. (S1 ^operator O1934 +)
  9335. Retracting propose*predict-yes
  9336. -->
  9337. (O1933 ^name predict-yes +)
  9338. (S1 ^operator O1933 +)
  9339. Retracting elaborate*reward*based*on*reward
  9340. -->
  9341. (R970 ^value 1 +)
  9342. (R1 ^reward R970 +)
  9343. Retracting elaborate*copy-dir-to-output-link
  9344. -->
  9345. (I3 ^dir L +)
  9346. Retracting rl*prefer*rvt*predict-no*H0*4
  9347. -->
  9348. (S1 ^operator O1934 = 0.3145082389793297)
  9349. Retracting rl*prefer*rvt*predict-no*H0*4*H1*16
  9350. -->
  9351. (S1 ^operator O1934 = -0.168718511744511)
  9352. Retracting rl*prefer*rvt*predict-yes*H0*3
  9353. -->
  9354. (S1 ^operator O1933 = 0.390807862285058)
  9355. Retracting rl*prefer*rvt*predict-yes*H0*3*H1*17
  9356. -->
  9357. (S1 ^operator O1933 = 0.6093697568764296)
  9358. =>WM: (13579: S1 ^operator O1936 +)
  9359. =>WM: (13578: S1 ^operator O1935 +)
  9360. =>WM: (13577: O1936 ^name predict-no)
  9361. =>WM: (13576: O1935 ^name predict-yes)
  9362. =>WM: (13575: R971 ^value 1)
  9363. =>WM: (13574: R1 ^reward R971)
  9364. =>WM: (13573: I3 ^see 1)
  9365. <=WM: (13564: S1 ^operator O1933 +)
  9366. <=WM: (13566: S1 ^operator O1933)
  9367. <=WM: (13565: S1 ^operator O1934 +)
  9368. <=WM: (13559: R1 ^reward R970)
  9369. <=WM: (13558: I3 ^see 0)
  9370. <=WM: (13562: O1934 ^name predict-no)
  9371. <=WM: (13561: O1933 ^name predict-yes)
  9372. <=WM: (13560: R970 ^value 1)
  9373. --- Inner Elaboration Phase, active level 1 (S1) ---
  9374. Firing prefer*rvt*predict-yes*H0
  9375. -->
  9376. Firing rl*prefer*rvt*predict-yes*H0*3
  9377. -->
  9378. (S1 ^operator O1935 = 0.390807862285058)
  9379. Firing prefer*rvt*predict-yes*H0*3*H1
  9380. -->
  9381. Firing rl*prefer*rvt*predict-yes*H0*3*H1*11
  9382. -->
  9383. (S1 ^operator O1935 = -0.2062723012911647)
  9384. Firing prefer*rvt*predict-no*H0
  9385. -->
  9386. Firing rl*prefer*rvt*predict-no*H0*4
  9387. -->
  9388. (S1 ^operator O1936 = 0.3145082389793297)
  9389. Firing prefer*rvt*predict-no*H0*4*H1
  9390. -->
  9391. Firing rl*prefer*rvt*predict-no*H0*4*H1*10
  9392. -->
  9393. (S1 ^operator O1936 = 0.685551861847024)
  9394. inner elaboration loop at bottom goal.
  9395. Retracting rl*prefer*rvt*predict-no*H0*4
  9396. -->
  9397. (S1 ^operator O1934 = 0.3145082389793297)
  9398. Retracting rl*prefer*rvt*predict-no*H0*4*H1*10
  9399. -->
  9400. (S1 ^operator O1934 = 0.685551861847024)
  9401. Retracting rl*prefer*rvt*predict-yes*H0*3
  9402. -->
  9403. (S1 ^operator O1933 = 0.390807862285058)
  9404. Retracting rl*prefer*rvt*predict-yes*H0*3*H1*11
  9405. -->
  9406. (S1 ^operator O1933 = -0.2062723012911647)
  9407. --- END Proposal Phase ---
  9408. --- Decision Phase ---
  9409. RL update rl*prefer*rvt*predict-yes*H0*3 0.472349 -0.0815415 0.390808 -> 0.472337 -0.0815436 0.390793(R,m,v=1,0.941558,0.0553858)
  9410. RL update rl*prefer*rvt*predict-yes*H0*3*H1*17 0.527802 0.0815677 0.60937 -> 0.527788 0.0815652 0.609353(R,m,v=1,1,0)
  9411. =>WM: (13580: S1 ^operator O1936)
  9412. 968: O: O1936 (predict-no)
  9413. --- END Decision Phase ---
  9414. --- Application Phase ---
  9415. --- Firing Productions (PE) For State At Depth 1 ---
  9416. --- Inner Elaboration Phase, active level 1 (S1) ---
  9417. Firing apply*operator
  9418. -->
  9419. (I3 ^predict-no N968 + :O )
  9420. Firing apply*operator*complete
  9421. -->
  9422. (I3 ^predict-yes N967 - :O )
  9423. inner elaboration loop at bottom goal.
  9424. --- Change Working Memory (PE) ---
  9425. =>WM: (13581: I3 ^predict-no N968)
  9426. <=WM: (13568: N967 ^status complete)
  9427. <=WM: (13567: I3 ^predict-yes N967)
  9428. --- Firing Productions (IE) For State At Depth 1 ---
  9429. --- Inner Elaboration Phase, active level 1 (S1) ---
  9430. Firing monitor*world
  9431. -->
  9432. I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
  9433. --- Change Working Memory (IE) ---
  9434. --- END Application Phase ---
  9435. --- Output Phase ---
  9436. ENV: Agent did: predict-no for direction L in state State-A
  9437. In State-A moving L
  9438. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  9439. predict error 0
  9440. dir: dir isR
  9441. --- END Output Phase ---
  9442. |\-/sleeping...
  9443. |--- Input Phase ---
  9444. =>WM: (13585: I2 ^dir R)
  9445. =>WM: (13584: I2 ^reward 1)
  9446. =>WM: (13583: I2 ^see 0)
  9447. =>WM: (13582: N968 ^status complete)
  9448. <=WM: (13571: I2 ^dir L)
  9449. <=WM: (13570: I2 ^reward 1)
  9450. <=WM: (13569: I2 ^see 1)
  9451. =>WM: (13586: I2 ^level-1 L0-root)
  9452. <=WM: (13572: I2 ^level-1 L1-root)
  9453. --- END Input Phase ---
  9454. --- Proposal Phase ---
  9455. --- Inner Elaboration Phase, active level 1 (S1) ---
  9456. Firing rl*prefer*rvt*predict-yes*H0*5*H1*14
  9457. -->
  9458. (S1 ^operator O1935 = 0.8783918732984659)
  9459. Firing prefer*rvt*predict-yes*H0*5*H1
  9460. -->
  9461. Firing elaborate*copy-see-to-output-link
  9462. -->
  9463. (I3 ^see 0 +)
  9464. Firing elaborate*reward*based*on*reward
  9465. -->
  9466. (R972 ^value 1 +)
  9467. (R1 ^reward R972 +)
  9468. Firing propose*predict-yes
  9469. -->
  9470. (O1937 ^name predict-yes +)
  9471. (S1 ^operator O1937 +)
  9472. Firing propose*predict-no
  9473. -->
  9474. (O1938 ^name predict-no +)
  9475. (S1 ^operator O1938 +)
  9476. Firing rl*prefer*rvt*predict-no*H0*6
  9477. -->
  9478. (S1 ^operator O1936 = 0.9999810901454903)
  9479. Firing rl*prefer*rvt*predict-yes*H0*5
  9480. -->
  9481. (S1 ^operator O1935 = 0.1215986309459259)
  9482. Firing prefer*rvt*predict-yes*H0
  9483. -->
  9484. Firing prefer*rvt*predict-no*H0
  9485. -->
  9486. Firing elaborate*copy-dir-to-output-link
  9487. -->
  9488. (I3 ^dir R +)
  9489. inner elaboration loop at bottom goal.
  9490. Retracting elaborate*copy-see-to-output-link
  9491. -->
  9492. (I3 ^see 1 +)
  9493. Retracting propose*predict-no
  9494. -->
  9495. (O1936 ^name predict-no +)
  9496. (S1 ^operator O1936 +)
  9497. Retracting propose*predict-yes
  9498. -->
  9499. (O1935 ^name predict-yes +)
  9500. (S1 ^operator O1935 +)
  9501. Retracting elaborate*reward*based*on*reward
  9502. -->
  9503. (R971 ^value 1 +)
  9504. (R1 ^reward R971 +)
  9505. Retracting elaborate*copy-dir-to-output-link
  9506. -->
  9507. (I3 ^dir L +)
  9508. Retracting rl*prefer*rvt*predict-no*H0*4*H1*10
  9509. -->
  9510. (S1 ^operator O1936 = 0.685551861847024)
  9511. Retracting rl*prefer*rvt*predict-no*H0*4
  9512. -->
  9513. (S1 ^operator O1936 = 0.3145082389793297)
  9514. Retracting rl*prefer*rvt*predict-yes*H0*3*H1*11
  9515. -->
  9516. (S1 ^operator O1935 = -0.2062723012911647)
  9517. Retracting rl*prefer*rvt*predict-yes*H0*3
  9518. -->
  9519. (S1 ^operator O1935 = 0.3907931512898603)
  9520. =>WM: (13594: S1 ^operator O1938 +)
  9521. =>WM: (13593: S1 ^operator O1937 +)
  9522. =>WM: (13592: I3 ^dir R)
  9523. =>WM: (13591: O1938 ^name predict-no)
  9524. =>WM: (13590: O1937 ^name predict-yes)
  9525. =>WM: (13589: R972 ^value 1)
  9526. =>WM: (13588: R1 ^reward R972)
  9527. =>WM: (13587: I3 ^see 0)
  9528. <=WM: (13578: S1 ^operator O1935 +)
  9529. <=WM: (13579: S1 ^operator O1936 +)
  9530. <=WM: (13580: S1 ^operator O1936)
  9531. <=WM: (13563: I3 ^dir L)
  9532. <=WM: (13574: R1 ^reward R971)
  9533. <=WM: (13573: I3 ^see 1)
  9534. <=WM: (13577: O1936 ^name predict-no)
  9535. <=WM: (13576: O1935 ^name predict-yes)
  9536. <=WM: (13575: R971 ^value 1)
  9537. --- Inner Elaboration Phase, active level 1 (S1) ---
  9538. Firing prefer*rvt*predict-yes*H0
  9539. -->
  9540. Firing rl*prefer*rvt*predict-yes*H0*5
  9541. -->
  9542. (S1 ^operator O1937 = 0.1215986309459259)
  9543. Firing prefer*rvt*predict-yes*H0*5*H1
  9544. -->
  9545. Firing rl*prefer*rvt*predict-yes*H0*5*H1*14
  9546. -->
  9547. (S1 ^operator O1937 = 0.8783918732984659)
  9548. Firing prefer*rvt*predict-no*H0
  9549. -->
  9550. Firing rl*prefer*rvt*predict-no*H0*6
  9551. -->
  9552. (S1 ^operator O1938 = 0.9999810901454903)
  9553. inner elaboration loop at bottom goal.
  9554. Retracting rl*prefer*rvt*predict-no*H0*6
  9555. -->
  9556. (S1 ^operator O1936 = 0.9999810901454903)
  9557. Retracting rl*prefer*rvt*predict-yes*H0*5
  9558. -->
  9559. (S1 ^operator O1935 = 0.1215986309459259)
  9560. Retracting rl*prefer*rvt*predict-yes*H0*5*H1*14
  9561. -->
  9562. (S1 ^operator O1935 = 0.8783918732984659)
  9563. --- END Proposal Phase ---
  9564. --- Decision Phase ---
  9565. RL update rl*prefer*rvt*predict-no*H0*4 0.478556 -0.164048 0.314508 -> 0.478552 -0.164048 0.314503(R,m,v=1,0.92,0.074094)
  9566. RL update rl*prefer*rvt*predict-no*H0*4*H1*10 0.521498 0.164053 0.685552 -> 0.521493 0.164053 0.685546(R,m,v=1,1,0)
  9567. =>WM: (13595: S1 ^operator O1937)
  9568. 969: O: O1937 (predict-yes)
  9569. --- END Decision Phase ---
  9570. --- Application Phase ---
  9571. --- Firing Productions (PE) For State At Depth 1 ---
  9572. --- Inner Elaboration Phase, active level 1 (S1) ---
  9573. Firing apply*operator
  9574. -->
  9575. (I3 ^predict-yes N969 + :O )
  9576. Firing apply*operator*complete
  9577. -->
  9578. (I3 ^predict-no N968 - :O )
  9579. inner elaboration loop at bottom goal.
  9580. --- Change Working Memory (PE) ---
  9581. =>WM: (13596: I3 ^predict-yes N969)
  9582. <=WM: (13582: N968 ^status complete)
  9583. <=WM: (13581: I3 ^predict-no N968)
  9584. --- Firing Productions (IE) For State At Depth 1 ---
  9585. --- Inner Elaboration Phase, active level 1 (S1) ---
  9586. Firing monitor*world
  9587. -->
  9588. I see 1 and I'm going to do: predict-yes inner elaboration loop at bottom goal.
  9589. --- Change Working Memory (IE) ---
  9590. --- END Application Phase ---
  9591. --- Output Phase ---
  9592. ENV: Agent did: predict-yes for direction R in state State-A
  9593. In State-A moving R
  9594. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  9595. predict error 0
  9596. dir: dir isL
  9597. --- END Output Phase ---
  9598. \-/--- Input Phase ---
  9599. =>WM: (13600: I2 ^dir L)
  9600. =>WM: (13599: I2 ^reward 1)
  9601. =>WM: (13598: I2 ^see 1)
  9602. =>WM: (13597: N969 ^status complete)
  9603. <=WM: (13585: I2 ^dir R)
  9604. <=WM: (13584: I2 ^reward 1)
  9605. <=WM: (13583: I2 ^see 0)
  9606. =>WM: (13601: I2 ^level-1 R1-root)
  9607. <=WM: (13586: I2 ^level-1 L0-root)
  9608. --- END Input Phase ---
  9609. --- Proposal Phase ---
  9610. --- Inner Elaboration Phase, active level 1 (S1) ---
  9611. Firing rl*prefer*rvt*predict-no*H0*4*H1*16
  9612. -->
  9613. (S1 ^operator O1938 = -0.168718511744511)
  9614. Firing rl*prefer*rvt*predict-yes*H0*3*H1*17
  9615. -->
  9616. (S1 ^operator O1937 = 0.6093527419421177)
  9617. Firing prefer*rvt*predict-no*H0*4*H1
  9618. -->
  9619. Firing prefer*rvt*predict-yes*H0*3*H1
  9620. -->
  9621. Firing elaborate*copy-see-to-output-link
  9622. -->
  9623. (I3 ^see 1 +)
  9624. Firing elaborate*reward*based*on*reward
  9625. -->
  9626. (R973 ^value 1 +)
  9627. (R1 ^reward R973 +)
  9628. Firing propose*predict-yes
  9629. -->
  9630. (O1939 ^name predict-yes +)
  9631. (S1 ^operator O1939 +)
  9632. Firing propose*predict-no
  9633. -->
  9634. (O1940 ^name predict-no +)
  9635. (S1 ^operator O1940 +)
  9636. Firing rl*prefer*rvt*predict-no*H0*4
  9637. -->
  9638. (S1 ^operator O1938 = 0.3145032394390637)
  9639. Firing rl*prefer*rvt*predict-yes*H0*3
  9640. -->
  9641. (S1 ^operator O1937 = 0.3907931512898603)
  9642. Firing prefer*rvt*predict-yes*H0
  9643. -->
  9644. Firing prefer*rvt*predict-no*H0
  9645. -->
  9646. Firing elaborate*copy-dir-to-output-link
  9647. -->
  9648. (I3 ^dir L +)
  9649. inner elaboration loop at bottom goal.
  9650. Retracting elaborate*copy-see-to-output-link
  9651. -->
  9652. (I3 ^see 0 +)
  9653. Retracting propose*predict-no
  9654. -->
  9655. (O1938 ^name predict-no +)
  9656. (S1 ^operator O1938 +)
  9657. Retracting propose*predict-yes
  9658. -->
  9659. (O1937 ^name predict-yes +)
  9660. (S1 ^operator O1937 +)
  9661. Retracting elaborate*reward*based*on*reward
  9662. -->
  9663. (R972 ^value 1 +)
  9664. (R1 ^reward R972 +)
  9665. Retracting elaborate*copy-dir-to-output-link
  9666. -->
  9667. (I3 ^dir R +)
  9668. Retracting rl*prefer*rvt*predict-no*H0*6
  9669. -->
  9670. (S1 ^operator O1938 = 0.9999810901454903)
  9671. Retracting rl*prefer*rvt*predict-yes*H0*5*H1*14
  9672. -->
  9673. (S1 ^operator O1937 = 0.8783918732984659)
  9674. Retracting rl*prefer*rvt*predict-yes*H0*5
  9675. -->
  9676. (S1 ^operator O1937 = 0.1215986309459259)
  9677. =>WM: (13609: S1 ^operator O1940 +)
  9678. =>WM: (13608: S1 ^operator O1939 +)
  9679. =>WM: (13607: I3 ^dir L)
  9680. =>WM: (13606: O1940 ^name predict-no)
  9681. =>WM: (13605: O1939 ^name predict-yes)
  9682. =>WM: (13604: R973 ^value 1)
  9683. =>WM: (13603: R1 ^reward R973)
  9684. =>WM: (13602: I3 ^see 1)
  9685. <=WM: (13593: S1 ^operator O1937 +)
  9686. <=WM: (13595: S1 ^operator O1937)
  9687. <=WM: (13594: S1 ^operator O1938 +)
  9688. <=WM: (13592: I3 ^dir R)
  9689. <=WM: (13588: R1 ^reward R972)
  9690. <=WM: (13587: I3 ^see 0)
  9691. <=WM: (13591: O1938 ^name predict-no)
  9692. <=WM: (13590: O1937 ^name predict-yes)
  9693. <=WM: (13589: R972 ^value 1)
  9694. --- Inner Elaboration Phase, active level 1 (S1) ---
  9695. Firing prefer*rvt*predict-yes*H0
  9696. -->
  9697. Firing rl*prefer*rvt*predict-yes*H0*3
  9698. -->
  9699. (S1 ^operator O1939 = 0.3907931512898603)
  9700. Firing prefer*rvt*predict-yes*H0*3*H1
  9701. -->
  9702. Firing rl*prefer*rvt*predict-yes*H0*3*H1*17
  9703. -->
  9704. (S1 ^operator O1939 = 0.6093527419421177)
  9705. Firing prefer*rvt*predict-no*H0
  9706. -->
  9707. Firing rl*prefer*rvt*predict-no*H0*4
  9708. -->
  9709. (S1 ^operator O1940 = 0.3145032394390637)
  9710. Firing prefer*rvt*predict-no*H0*4*H1
  9711. -->
  9712. Firing rl*prefer*rvt*predict-no*H0*4*H1*16
  9713. -->
  9714. (S1 ^operator O1940 = -0.168718511744511)
  9715. inner elaboration loop at bottom goal.
  9716. Retracting rl*prefer*rvt*predict-no*H0*4
  9717. -->
  9718. (S1 ^operator O1938 = 0.3145032394390637)
  9719. Retracting rl*prefer*rvt*predict-no*H0*4*H1*16
  9720. -->
  9721. (S1 ^operator O1938 = -0.168718511744511)
  9722. Retracting rl*prefer*rvt*predict-yes*H0*3
  9723. -->
  9724. (S1 ^operator O1937 = 0.3907931512898603)
  9725. Retracting rl*prefer*rvt*predict-yes*H0*3*H1*17
  9726. -->
  9727. (S1 ^operator O1937 = 0.6093527419421177)
  9728. --- END Proposal Phase ---
  9729. --- Decision Phase ---
  9730. RL update rl*prefer*rvt*predict-yes*H0*5 0.534525 -0.412926 0.121599 -> 0.534525 -0.412926 0.121599(R,m,v=1,0.859649,0.121362)
  9731. RL update rl*prefer*rvt*predict-yes*H0*5*H1*14 0.465467 0.412924 0.878392 -> 0.465468 0.412925 0.878393(R,m,v=1,1,0)
  9732. =>WM: (13610: S1 ^operator O1939)
  9733. 970: O: O1939 (predict-yes)
  9734. --- END Decision Phase ---
  9735. --- Application Phase ---
  9736. --- Firing Productions (PE) For State At Depth 1 ---
  9737. --- Inner Elaboration Phase, active level 1 (S1) ---
  9738. Firing apply*operator
  9739. -->
  9740. (I3 ^predict-yes N970 + :O )
  9741. Firing apply*operator*complete
  9742. -->
  9743. (I3 ^predict-yes N969 - :O )
  9744. inner elaboration loop at bottom goal.
  9745. --- Change Working Memory (PE) ---
  9746. =>WM: (13611: I3 ^predict-yes N970)
  9747. <=WM: (13597: N969 ^status complete)
  9748. <=WM: (13596: I3 ^predict-yes N969)
  9749. --- Firing Productions (IE) For State At Depth 1 ---
  9750. --- Inner Elaboration Phase, active level 1 (S1) ---
  9751. Firing monitor*world
  9752. -->
  9753. I see 1 and I'm going to do: predict-yes inner elaboration loop at bottom goal.
  9754. --- Change Working Memory (IE) ---
  9755. --- END Application Phase ---
  9756. --- Output Phase ---
  9757. ENV: Agent did: predict-yes for direction L in state State-B
  9758. In State-B moving L
  9759. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  9760. predict error 0
  9761. dir: dir isU
  9762. --- END Output Phase ---
  9763. |\--- Input Phase ---
  9764. =>WM: (13615: I2 ^dir U)
  9765. =>WM: (13614: I2 ^reward 1)
  9766. =>WM: (13613: I2 ^see 1)
  9767. =>WM: (13612: N970 ^status complete)
  9768. <=WM: (13600: I2 ^dir L)
  9769. <=WM: (13599: I2 ^reward 1)
  9770. <=WM: (13598: I2 ^see 1)
  9771. =>WM: (13616: I2 ^level-1 L1-root)
  9772. <=WM: (13601: I2 ^level-1 R1-root)
  9773. --- END Input Phase ---
  9774. --- Proposal Phase ---
  9775. --- Inner Elaboration Phase, active level 1 (S1) ---
  9776. Firing elaborate*copy-see-to-output-link
  9777. -->
  9778. (I3 ^see 1 +)
  9779. Firing elaborate*reward*based*on*reward
  9780. -->
  9781. (R974 ^value 1 +)
  9782. (R1 ^reward R974 +)
  9783. Firing propose*predict-yes
  9784. -->
  9785. (O1941 ^name predict-yes +)
  9786. (S1 ^operator O1941 +)
  9787. Firing propose*predict-no
  9788. -->
  9789. (O1942 ^name predict-no +)
  9790. (S1 ^operator O1942 +)
  9791. Firing rl*prefer*rvt*predict-no*H0*2
  9792. -->
  9793. (S1 ^operator O1940 = 1.)
  9794. Firing rl*prefer*rvt*predict-yes*H0*1
  9795. -->
  9796. (S1 ^operator O1939 = 0.)
  9797. Firing prefer*rvt*predict-yes*H0
  9798. -->
  9799. Firing prefer*rvt*predict-no*H0
  9800. -->
  9801. Firing elaborate*copy-dir-to-output-link
  9802. -->
  9803. (I3 ^dir U +)
  9804. inner elaboration loop at bottom goal.
  9805. Retracting elaborate*copy-see-to-output-link
  9806. -->
  9807. (I3 ^see 1 +)
  9808. Retracting propose*predict-no
  9809. -->
  9810. (O1940 ^name predict-no +)
  9811. (S1 ^operator O1940 +)
  9812. Retracting propose*predict-yes
  9813. -->
  9814. (O1939 ^name predict-yes +)
  9815. (S1 ^operator O1939 +)
  9816. Retracting elaborate*reward*based*on*reward
  9817. -->
  9818. (R973 ^value 1 +)
  9819. (R1 ^reward R973 +)
  9820. Retracting elaborate*copy-dir-to-output-link
  9821. -->
  9822. (I3 ^dir L +)
  9823. Retracting rl*prefer*rvt*predict-no*H0*4*H1*16
  9824. -->
  9825. (S1 ^operator O1940 = -0.168718511744511)
  9826. Retracting rl*prefer*rvt*predict-no*H0*4
  9827. -->
  9828. (S1 ^operator O1940 = 0.3145032394390637)
  9829. Retracting rl*prefer*rvt*predict-yes*H0*3*H1*17
  9830. -->
  9831. (S1 ^operator O1939 = 0.6093527419421177)
  9832. Retracting rl*prefer*rvt*predict-yes*H0*3
  9833. -->
  9834. (S1 ^operator O1939 = 0.3907931512898603)
  9835. =>WM: (13623: S1 ^operator O1942 +)
  9836. =>WM: (13622: S1 ^operator O1941 +)
  9837. =>WM: (13621: I3 ^dir U)
  9838. =>WM: (13620: O1942 ^name predict-no)
  9839. =>WM: (13619: O1941 ^name predict-yes)
  9840. =>WM: (13618: R974 ^value 1)
  9841. =>WM: (13617: R1 ^reward R974)
  9842. <=WM: (13608: S1 ^operator O1939 +)
  9843. <=WM: (13610: S1 ^operator O1939)
  9844. <=WM: (13609: S1 ^operator O1940 +)
  9845. <=WM: (13607: I3 ^dir L)
  9846. <=WM: (13603: R1 ^reward R973)
  9847. <=WM: (13606: O1940 ^name predict-no)
  9848. <=WM: (13605: O1939 ^name predict-yes)
  9849. <=WM: (13604: R973 ^value 1)
  9850. --- Inner Elaboration Phase, active level 1 (S1) ---
  9851. Firing prefer*rvt*predict-yes*H0
  9852. -->
  9853. Firing rl*prefer*rvt*predict-yes*H0*1
  9854. -->
  9855. (S1 ^operator O1941 = 0.)
  9856. Firing prefer*rvt*predict-no*H0
  9857. -->
  9858. Firing rl*prefer*rvt*predict-no*H0*2
  9859. -->
  9860. (S1 ^operator O1942 = 1.)
  9861. inner elaboration loop at bottom goal.
  9862. Retracting rl*prefer*rvt*predict-no*H0*2
  9863. -->
  9864. (S1 ^operator O1940 = 1.)
  9865. Retracting rl*prefer*rvt*predict-yes*H0*1
  9866. -->
  9867. (S1 ^operator O1939 = 0.)
  9868. --- END Proposal Phase ---
  9869. --- Decision Phase ---
  9870. RL update rl*prefer*rvt*predict-yes*H0*3 0.472337 -0.0815436 0.390793 -> 0.472327 -0.0815454 0.390781(R,m,v=1,0.941935,0.0550482)
  9871. RL update rl*prefer*rvt*predict-yes*H0*3*H1*17 0.527788 0.0815652 0.609353 -> 0.527776 0.0815632 0.609339(R,m,v=1,1,0)
  9872. =>WM: (13624: S1 ^operator O1942)
  9873. 971: O: O1942 (predict-no)
  9874. --- END Decision Phase ---
  9875. --- Application Phase ---
  9876. --- Firing Productions (PE) For State At Depth 1 ---
  9877. --- Inner Elaboration Phase, active level 1 (S1) ---
  9878. Firing apply*operator
  9879. -->
  9880. (I3 ^predict-no N971 + :O )
  9881. Firing apply*operator*complete
  9882. -->
  9883. (I3 ^predict-yes N970 - :O )
  9884. inner elaboration loop at bottom goal.
  9885. --- Change Working Memory (PE) ---
  9886. =>WM: (13625: I3 ^predict-no N971)
  9887. <=WM: (13612: N970 ^status complete)
  9888. <=WM: (13611: I3 ^predict-yes N970)
  9889. --- Firing Productions (IE) For State At Depth 1 ---
  9890. --- Inner Elaboration Phase, active level 1 (S1) ---
  9891. Firing monitor*world
  9892. -->
  9893. I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
  9894. --- Change Working Memory (IE) ---
  9895. --- END Application Phase ---
  9896. --- Output Phase ---
  9897. ENV: Agent did: predict-no for direction U in state State-A
  9898. In State-A moving U
  9899. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  9900. predict error 0
  9901. dir: dir isR
  9902. --- END Output Phase ---
  9903. ---- Input Phase ---
  9904. =>WM: (13629: I2 ^dir R)
  9905. =>WM: (13628: I2 ^reward 1)
  9906. =>WM: (13627: I2 ^see 0)
  9907. =>WM: (13626: N971 ^status complete)
  9908. <=WM: (13615: I2 ^dir U)
  9909. <=WM: (13614: I2 ^reward 1)
  9910. <=WM: (13613: I2 ^see 1)
  9911. =>WM: (13630: I2 ^level-1 L1-root)
  9912. <=WM: (13616: I2 ^level-1 L1-root)
  9913. --- END Input Phase ---
  9914. --- Proposal Phase ---
  9915. --- Inner Elaboration Phase, active level 1 (S1) ---
  9916. Firing rl*prefer*rvt*predict-yes*H0*5*H1*18
  9917. -->
  9918. (S1 ^operator O1941 = 0.8784169509457307)
  9919. Firing prefer*rvt*predict-yes*H0*5*H1
  9920. -->
  9921. Firing elaborate*copy-see-to-output-link
  9922. -->
  9923. (I3 ^see 0 +)
  9924. Firing elaborate*reward*based*on*reward
  9925. -->
  9926. (R975 ^value 1 +)
  9927. (R1 ^reward R975 +)
  9928. Firing propose*predict-yes
  9929. -->
  9930. (O1943 ^name predict-yes +)
  9931. (S1 ^operator O1943 +)
  9932. Firing propose*predict-no
  9933. -->
  9934. (O1944 ^name predict-no +)
  9935. (S1 ^operator O1944 +)
  9936. Firing rl*prefer*rvt*predict-no*H0*6
  9937. -->
  9938. (S1 ^operator O1942 = 0.9999810901454903)
  9939. Firing rl*prefer*rvt*predict-yes*H0*5
  9940. -->
  9941. (S1 ^operator O1941 = 0.1215994040064755)
  9942. Firing prefer*rvt*predict-yes*H0
  9943. -->
  9944. Firing prefer*rvt*predict-no*H0
  9945. -->
  9946. Firing elaborate*copy-dir-to-output-link
  9947. -->
  9948. (I3 ^dir R +)
  9949. inner elaboration loop at bottom goal.
  9950. Retracting elaborate*copy-see-to-output-link
  9951. -->
  9952. (I3 ^see 1 +)
  9953. Retracting propose*predict-no
  9954. -->
  9955. (O1942 ^name predict-no +)
  9956. (S1 ^operator O1942 +)
  9957. Retracting propose*predict-yes
  9958. -->
  9959. (O1941 ^name predict-yes +)
  9960. (S1 ^operator O1941 +)
  9961. Retracting elaborate*reward*based*on*reward
  9962. -->
  9963. (R974 ^value 1 +)
  9964. (R1 ^reward R974 +)
  9965. Retracting elaborate*copy-dir-to-output-link
  9966. -->
  9967. (I3 ^dir U +)
  9968. Retracting rl*prefer*rvt*predict-no*H0*2
  9969. -->
  9970. (S1 ^operator O1942 = 1.)
  9971. Retracting rl*prefer*rvt*predict-yes*H0*1
  9972. -->
  9973. (S1 ^operator O1941 = 0.)
  9974. =>WM: (13638: S1 ^operator O1944 +)
  9975. =>WM: (13637: S1 ^operator O1943 +)
  9976. =>WM: (13636: I3 ^dir R)
  9977. =>WM: (13635: O1944 ^name predict-no)
  9978. =>WM: (13634: O1943 ^name predict-yes)
  9979. =>WM: (13633: R975 ^value 1)
  9980. =>WM: (13632: R1 ^reward R975)
  9981. =>WM: (13631: I3 ^see 0)
  9982. <=WM: (13622: S1 ^operator O1941 +)
  9983. <=WM: (13623: S1 ^operator O1942 +)
  9984. <=WM: (13624: S1 ^operator O1942)
  9985. <=WM: (13621: I3 ^dir U)
  9986. <=WM: (13617: R1 ^reward R974)
  9987. <=WM: (13602: I3 ^see 1)
  9988. <=WM: (13620: O1942 ^name predict-no)
  9989. <=WM: (13619: O1941 ^name predict-yes)
  9990. <=WM: (13618: R974 ^value 1)
  9991. --- Inner Elaboration Phase, active level 1 (S1) ---
  9992. Firing prefer*rvt*predict-yes*H0
  9993. -->
  9994. Firing rl*prefer*rvt*predict-yes*H0*5*H1*18
  9995. -->
  9996. (S1 ^operator O1943 = 0.8784169509457307)
  9997. Firing rl*prefer*rvt*predict-yes*H0*5
  9998. -->
  9999. (S1 ^operator O1943 = 0.1215994040064755)
  10000. Firing prefer*rvt*predict-yes*H0*5*H1
  10001. -->
  10002. Firing prefer*rvt*predict-no*H0
  10003. -->
  10004. Firing rl*prefer*rvt*predict-no*H0*6
  10005. -->
  10006. (S1 ^operator O1944 = 0.9999810901454903)
  10007. inner elaboration loop at bottom goal.
  10008. Retracting rl*prefer*rvt*predict-no*H0*6
  10009. -->
  10010. (S1 ^operator O1942 = 0.9999810901454903)
  10011. Retracting rl*prefer*rvt*predict-yes*H0*5
  10012. -->
  10013. (S1 ^operator O1941 = 0.1215994040064755)
  10014. Retracting rl*prefer*rvt*predict-yes*H0*5*H1*18
  10015. -->
  10016. (S1 ^operator O1941 = 0.8784169509457307)
  10017. --- END Proposal Phase ---
  10018. --- Decision Phase ---
  10019. RL update rl*prefer*rvt*predict-no*H0*2 1 0 1 -> 1 0 1(R,m,v=1,1,0)
  10020. =>WM: (13639: S1 ^operator O1943)
  10021. 972: O: O1943 (predict-yes)
  10022. --- END Decision Phase ---
  10023. --- Application Phase ---
  10024. --- Firing Productions (PE) For State At Depth 1 ---
  10025. --- Inner Elaboration Phase, active level 1 (S1) ---
  10026. Firing apply*operator
  10027. -->
  10028. (I3 ^predict-yes N972 + :O )
  10029. Firing apply*operator*complete
  10030. -->
  10031. (I3 ^predict-no N971 - :O )
  10032. inner elaboration loop at bottom goal.
  10033. --- Change Working Memory (PE) ---
  10034. =>WM: (13640: I3 ^predict-yes N972)
  10035. <=WM: (13626: N971 ^status complete)
  10036. <=WM: (13625: I3 ^predict-no N971)
  10037. --- Firing Productions (IE) For State At Depth 1 ---
  10038. --- Inner Elaboration Phase, active level 1 (S1) ---
  10039. Firing monitor*world
  10040. -->
  10041. I see 1 and I'm going to do: predict-yes inner elaboration loop at bottom goal.
  10042. --- Change Working Memory (IE) ---
  10043. --- END Application Phase ---
  10044. --- Output Phase ---
  10045. ENV: Agent did: predict-yes for direction R in state State-A
  10046. In State-A moving R
  10047. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  10048. predict error 0
  10049. dir: dir isU
  10050. --- END Output Phase ---
  10051. /|\--- Input Phase ---
  10052. =>WM: (13644: I2 ^dir U)
  10053. =>WM: (13643: I2 ^reward 1)
  10054. =>WM: (13642: I2 ^see 1)
  10055. =>WM: (13641: N972 ^status complete)
  10056. <=WM: (13629: I2 ^dir R)
  10057. <=WM: (13628: I2 ^reward 1)
  10058. <=WM: (13627: I2 ^see 0)
  10059. =>WM: (13645: I2 ^level-1 R1-root)
  10060. <=WM: (13630: I2 ^level-1 L1-root)
  10061. --- END Input Phase ---
  10062. --- Proposal Phase ---
  10063. --- Inner Elaboration Phase, active level 1 (S1) ---
  10064. Firing elaborate*copy-see-to-output-link
  10065. -->
  10066. (I3 ^see 1 +)
  10067. Firing elaborate*reward*based*on*reward
  10068. -->
  10069. (R976 ^value 1 +)
  10070. (R1 ^reward R976 +)
  10071. Firing propose*predict-yes
  10072. -->
  10073. (O1945 ^name predict-yes +)
  10074. (S1 ^operator O1945 +)
  10075. Firing propose*predict-no
  10076. -->
  10077. (O1946 ^name predict-no +)
  10078. (S1 ^operator O1946 +)
  10079. Firing rl*prefer*rvt*predict-no*H0*2
  10080. -->
  10081. (S1 ^operator O1944 = 1.)
  10082. Firing rl*prefer*rvt*predict-yes*H0*1
  10083. -->
  10084. (S1 ^operator O1943 = 0.)
  10085. Firing prefer*rvt*predict-yes*H0
  10086. -->
  10087. Firing prefer*rvt*predict-no*H0
  10088. -->
  10089. Firing elaborate*copy-dir-to-output-link
  10090. -->
  10091. (I3 ^dir U +)
  10092. inner elaboration loop at bottom goal.
  10093. Retracting elaborate*copy-see-to-output-link
  10094. -->
  10095. (I3 ^see 0 +)
  10096. Retracting propose*predict-no
  10097. -->
  10098. (O1944 ^name predict-no +)
  10099. (S1 ^operator O1944 +)
  10100. Retracting propose*predict-yes
  10101. -->
  10102. (O1943 ^name predict-yes +)
  10103. (S1 ^operator O1943 +)
  10104. Retracting elaborate*reward*based*on*reward
  10105. -->
  10106. (R975 ^value 1 +)
  10107. (R1 ^reward R975 +)
  10108. Retracting elaborate*copy-dir-to-output-link
  10109. -->
  10110. (I3 ^dir R +)
  10111. Retracting rl*prefer*rvt*predict-no*H0*6
  10112. -->
  10113. (S1 ^operator O1944 = 0.9999810901454903)
  10114. Retracting rl*prefer*rvt*predict-yes*H0*5
  10115. -->
  10116. (S1 ^operator O1943 = 0.1215994040064755)
  10117. Retracting rl*prefer*rvt*predict-yes*H0*5*H1*18
  10118. -->
  10119. (S1 ^operator O1943 = 0.8784169509457307)
  10120. =>WM: (13653: S1 ^operator O1946 +)
  10121. =>WM: (13652: S1 ^operator O1945 +)
  10122. =>WM: (13651: I3 ^dir U)
  10123. =>WM: (13650: O1946 ^name predict-no)
  10124. =>WM: (13649: O1945 ^name predict-yes)
  10125. =>WM: (13648: R976 ^value 1)
  10126. =>WM: (13647: R1 ^reward R976)
  10127. =>WM: (13646: I3 ^see 1)
  10128. <=WM: (13637: S1 ^operator O1943 +)
  10129. <=WM: (13639: S1 ^operator O1943)
  10130. <=WM: (13638: S1 ^operator O1944 +)
  10131. <=WM: (13636: I3 ^dir R)
  10132. <=WM: (13632: R1 ^reward R975)
  10133. <=WM: (13631: I3 ^see 0)
  10134. <=WM: (13635: O1944 ^name predict-no)
  10135. <=WM: (13634: O1943 ^name predict-yes)
  10136. <=WM: (13633: R975 ^value 1)
  10137. --- Inner Elaboration Phase, active level 1 (S1) ---
  10138. Firing prefer*rvt*predict-yes*H0
  10139. -->
  10140. Firing rl*prefer*rvt*predict-yes*H0*1
  10141. -->
  10142. (S1 ^operator O1945 = 0.)
  10143. Firing prefer*rvt*predict-no*H0
  10144. -->
  10145. Firing rl*prefer*rvt*predict-no*H0*2
  10146. -->
  10147. (S1 ^operator O1946 = 1.)
  10148. inner elaboration loop at bottom goal.
  10149. Retracting rl*prefer*rvt*predict-no*H0*2
  10150. -->
  10151. (S1 ^operator O1944 = 1.)
  10152. Retracting rl*prefer*rvt*predict-yes*H0*1
  10153. -->
  10154. (S1 ^operator O1943 = 0.)
  10155. --- END Proposal Phase ---
  10156. --- Decision Phase ---
  10157. RL update rl*prefer*rvt*predict-yes*H0*5 0.534525 -0.412926 0.121599 -> 0.534524 -0.412926 0.121598(R,m,v=1,0.860465,0.120767)
  10158. RL update rl*prefer*rvt*predict-yes*H0*5*H1*18 0.465488 0.412929 0.878417 -> 0.465487 0.412928 0.878415(R,m,v=1,1,0)
  10159. =>WM: (13654: S1 ^operator O1946)
  10160. 973: O: O1946 (predict-no)
  10161. --- END Decision Phase ---
  10162. --- Application Phase ---
  10163. --- Firing Productions (PE) For State At Depth 1 ---
  10164. --- Inner Elaboration Phase, active level 1 (S1) ---
  10165. Firing apply*operator
  10166. -->
  10167. (I3 ^predict-no N973 + :O )
  10168. Firing apply*operator*complete
  10169. -->
  10170. (I3 ^predict-yes N972 - :O )
  10171. inner elaboration loop at bottom goal.
  10172. --- Change Working Memory (PE) ---
  10173. =>WM: (13655: I3 ^predict-no N973)
  10174. <=WM: (13641: N972 ^status complete)
  10175. <=WM: (13640: I3 ^predict-yes N972)
  10176. --- Firing Productions (IE) For State At Depth 1 ---
  10177. --- Inner Elaboration Phase, active level 1 (S1) ---
  10178. Firing monitor*world
  10179. -->
  10180. I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
  10181. --- Change Working Memory (IE) ---
  10182. --- END Application Phase ---
  10183. --- Output Phase ---
  10184. ENV: Agent did: predict-no for direction U in state State-B
  10185. In State-B moving U
  10186. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  10187. predict error 0
  10188. dir: dir isL
  10189. --- END Output Phase ---
  10190. -/--- Input Phase ---
  10191. =>WM: (13659: I2 ^dir L)
  10192. =>WM: (13658: I2 ^reward 1)
  10193. =>WM: (13657: I2 ^see 0)
  10194. =>WM: (13656: N973 ^status complete)
  10195. <=WM: (13644: I2 ^dir U)
  10196. <=WM: (13643: I2 ^reward 1)
  10197. <=WM: (13642: I2 ^see 1)
  10198. =>WM: (13660: I2 ^level-1 R1-root)
  10199. <=WM: (13645: I2 ^level-1 R1-root)
  10200. --- END Input Phase ---
  10201. --- Proposal Phase ---
  10202. --- Inner Elaboration Phase, active level 1 (S1) ---
  10203. Firing rl*prefer*rvt*predict-no*H0*4*H1*16
  10204. -->
  10205. (S1 ^operator O1946 = -0.168718511744511)
  10206. Firing rl*prefer*rvt*predict-yes*H0*3*H1*17
  10207. -->
  10208. (S1 ^operator O1945 = 0.609338805157315)
  10209. Firing prefer*rvt*predict-no*H0*4*H1
  10210. -->
  10211. Firing prefer*rvt*predict-yes*H0*3*H1
  10212. -->
  10213. Firing elaborate*copy-see-to-output-link
  10214. -->
  10215. (I3 ^see 0 +)
  10216. Firing elaborate*reward*based*on*reward
  10217. -->
  10218. (R977 ^value 1 +)
  10219. (R1 ^reward R977 +)
  10220. Firing propose*predict-yes
  10221. -->
  10222. (O1947 ^name predict-yes +)
  10223. (S1 ^operator O1947 +)
  10224. Firing propose*predict-no
  10225. -->
  10226. (O1948 ^name predict-no +)
  10227. (S1 ^operator O1948 +)
  10228. Firing rl*prefer*rvt*predict-no*H0*4
  10229. -->
  10230. (S1 ^operator O1946 = 0.3145032394390637)
  10231. Firing rl*prefer*rvt*predict-yes*H0*3
  10232. -->
  10233. (S1 ^operator O1945 = 0.3907810808803528)
  10234. Firing prefer*rvt*predict-yes*H0
  10235. -->
  10236. Firing prefer*rvt*predict-no*H0
  10237. -->
  10238. Firing elaborate*copy-dir-to-output-link
  10239. -->
  10240. (I3 ^dir L +)
  10241. inner elaboration loop at bottom goal.
  10242. Retracting elaborate*copy-see-to-output-link
  10243. -->
  10244. (I3 ^see 1 +)
  10245. Retracting propose*predict-no
  10246. -->
  10247. (O1946 ^name predict-no +)
  10248. (S1 ^operator O1946 +)
  10249. Retracting propose*predict-yes
  10250. -->
  10251. (O1945 ^name predict-yes +)
  10252. (S1 ^operator O1945 +)
  10253. Retracting elaborate*reward*based*on*reward
  10254. -->
  10255. (R976 ^value 1 +)
  10256. (R1 ^reward R976 +)
  10257. Retracting elaborate*copy-dir-to-output-link
  10258. -->
  10259. (I3 ^dir U +)
  10260. Retracting rl*prefer*rvt*predict-no*H0*2
  10261. -->
  10262. (S1 ^operator O1946 = 1.)
  10263. Retracting rl*prefer*rvt*predict-yes*H0*1
  10264. -->
  10265. (S1 ^operator O1945 = 0.)
  10266. =>WM: (13668: S1 ^operator O1948 +)
  10267. =>WM: (13667: S1 ^operator O1947 +)
  10268. =>WM: (13666: I3 ^dir L)
  10269. =>WM: (13665: O1948 ^name predict-no)
  10270. =>WM: (13664: O1947 ^name predict-yes)
  10271. =>WM: (13663: R977 ^value 1)
  10272. =>WM: (13662: R1 ^reward R977)
  10273. =>WM: (13661: I3 ^see 0)
  10274. <=WM: (13652: S1 ^operator O1945 +)
  10275. <=WM: (13653: S1 ^operator O1946 +)
  10276. <=WM: (13654: S1 ^operator O1946)
  10277. <=WM: (13651: I3 ^dir U)
  10278. <=WM: (13647: R1 ^reward R976)
  10279. <=WM: (13646: I3 ^see 1)
  10280. <=WM: (13650: O1946 ^name predict-no)
  10281. <=WM: (13649: O1945 ^name predict-yes)
  10282. <=WM: (13648: R976 ^value 1)
  10283. --- Inner Elaboration Phase, active level 1 (S1) ---
  10284. Firing prefer*rvt*predict-yes*H0
  10285. -->
  10286. Firing rl*prefer*rvt*predict-yes*H0*3*H1*17
  10287. -->
  10288. (S1 ^operator O1947 = 0.609338805157315)
  10289. Firing rl*prefer*rvt*predict-yes*H0*3
  10290. -->
  10291. (S1 ^operator O1947 = 0.3907810808803528)
  10292. Firing prefer*rvt*predict-yes*H0*3*H1
  10293. -->
  10294. Firing prefer*rvt*predict-no*H0
  10295. -->
  10296. Firing rl*prefer*rvt*predict-no*H0*4*H1*16
  10297. -->
  10298. (S1 ^operator O1948 = -0.168718511744511)
  10299. Firing rl*prefer*rvt*predict-no*H0*4
  10300. -->
  10301. (S1 ^operator O1948 = 0.3145032394390637)
  10302. Firing prefer*rvt*predict-no*H0*4*H1
  10303. -->
  10304. inner elaboration loop at bottom goal.
  10305. Retracting rl*prefer*rvt*predict-no*H0*4
  10306. -->
  10307. (S1 ^operator O1946 = 0.3145032394390637)
  10308. Retracting rl*prefer*rvt*predict-no*H0*4*H1*16
  10309. -->
  10310. (S1 ^operator O1946 = -0.168718511744511)
  10311. Retracting rl*prefer*rvt*predict-yes*H0*3
  10312. -->
  10313. (S1 ^operator O1945 = 0.3907810808803528)
  10314. Retracting rl*prefer*rvt*predict-yes*H0*3*H1*17
  10315. -->
  10316. (S1 ^operator O1945 = 0.609338805157315)
  10317. --- END Proposal Phase ---
  10318. --- Decision Phase ---
  10319. RL update rl*prefer*rvt*predict-no*H0*2 1 0 1 -> 1 0 1(R,m,v=1,1,0)
  10320. =>WM: (13669: S1 ^operator O1947)
  10321. 974: O: O1947 (predict-yes)
  10322. --- END Decision Phase ---
  10323. --- Application Phase ---
  10324. --- Firing Productions (PE) For State At Depth 1 ---
  10325. --- Inner Elaboration Phase, active level 1 (S1) ---
  10326. Firing apply*operator
  10327. -->
  10328. (I3 ^predict-yes N974 + :O )
  10329. Firing apply*operator*complete
  10330. -->
  10331. (I3 ^predict-no N973 - :O )
  10332. inner elaboration loop at bottom goal.
  10333. --- Change Working Memory (PE) ---
  10334. =>WM: (13670: I3 ^predict-yes N974)
  10335. <=WM: (13656: N973 ^status complete)
  10336. <=WM: (13655: I3 ^predict-no N973)
  10337. --- Firing Productions (IE) For State At Depth 1 ---
  10338. --- Inner Elaboration Phase, active level 1 (S1) ---
  10339. Firing monitor*world
  10340. -->
  10341. I see 1 and I'm going to do: predict-yes inner elaboration loop at bottom goal.
  10342. --- Change Working Memory (IE) ---
  10343. --- END Application Phase ---
  10344. --- Output Phase ---
  10345. ENV: Agent did: predict-yes for direction L in state State-B
  10346. In State-B moving L
  10347. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  10348. predict error 0
  10349. dir: dir isL
  10350. --- END Output Phase ---
  10351. |\---- Input Phase ---
  10352. =>WM: (13674: I2 ^dir L)
  10353. =>WM: (13673: I2 ^reward 1)
  10354. =>WM: (13672: I2 ^see 1)
  10355. =>WM: (13671: N974 ^status complete)
  10356. <=WM: (13659: I2 ^dir L)
  10357. <=WM: (13658: I2 ^reward 1)
  10358. <=WM: (13657: I2 ^see 0)
  10359. =>WM: (13675: I2 ^level-1 L1-root)
  10360. <=WM: (13660: I2 ^level-1 R1-root)
  10361. --- END Input Phase ---
  10362. --- Proposal Phase ---
  10363. --- Inner Elaboration Phase, active level 1 (S1) ---
  10364. Firing rl*prefer*rvt*predict-yes*H0*3*H1*11
  10365. -->
  10366. (S1 ^operator O1947 = -0.2062723012911647)
  10367. Firing rl*prefer*rvt*predict-no*H0*4*H1*10
  10368. -->
  10369. (S1 ^operator O1948 = 0.6855461517499103)
  10370. Firing prefer*rvt*predict-no*H0*4*H1
  10371. -->
  10372. Firing prefer*rvt*predict-yes*H0*3*H1
  10373. -->
  10374. Firing elaborate*copy-see-to-output-link
  10375. -->
  10376. (I3 ^see 1 +)
  10377. Firing elaborate*reward*based*on*reward
  10378. -->
  10379. (R978 ^value 1 +)
  10380. (R1 ^reward R978 +)
  10381. Firing propose*predict-yes
  10382. -->
  10383. (O1949 ^name predict-yes +)
  10384. (S1 ^operator O1949 +)
  10385. Firing propose*predict-no
  10386. -->
  10387. (O1950 ^name predict-no +)
  10388. (S1 ^operator O1950 +)
  10389. Firing rl*prefer*rvt*predict-no*H0*4
  10390. -->
  10391. (S1 ^operator O1948 = 0.3145032394390637)
  10392. Firing rl*prefer*rvt*predict-yes*H0*3
  10393. -->
  10394. (S1 ^operator O1947 = 0.3907810808803528)
  10395. Firing prefer*rvt*predict-yes*H0
  10396. -->
  10397. Firing prefer*rvt*predict-no*H0
  10398. -->
  10399. Firing elaborate*copy-dir-to-output-link
  10400. -->
  10401. (I3 ^dir L +)
  10402. inner elaboration loop at bottom goal.
  10403. Retracting elaborate*copy-see-to-output-link
  10404. -->
  10405. (I3 ^see 0 +)
  10406. Retracting propose*predict-no
  10407. -->
  10408. (O1948 ^name predict-no +)
  10409. (S1 ^operator O1948 +)
  10410. Retracting propose*predict-yes
  10411. -->
  10412. (O1947 ^name predict-yes +)
  10413. (S1 ^operator O1947 +)
  10414. Retracting elaborate*reward*based*on*reward
  10415. -->
  10416. (R977 ^value 1 +)
  10417. (R1 ^reward R977 +)
  10418. Retracting elaborate*copy-dir-to-output-link
  10419. -->
  10420. (I3 ^dir L +)
  10421. Retracting rl*prefer*rvt*predict-no*H0*4
  10422. -->
  10423. (S1 ^operator O1948 = 0.3145032394390637)
  10424. Retracting rl*prefer*rvt*predict-no*H0*4*H1*16
  10425. -->
  10426. (S1 ^operator O1948 = -0.168718511744511)
  10427. Retracting rl*prefer*rvt*predict-yes*H0*3
  10428. -->
  10429. (S1 ^operator O1947 = 0.3907810808803528)
  10430. Retracting rl*prefer*rvt*predict-yes*H0*3*H1*17
  10431. -->
  10432. (S1 ^operator O1947 = 0.609338805157315)
  10433. =>WM: (13682: S1 ^operator O1950 +)
  10434. =>WM: (13681: S1 ^operator O1949 +)
  10435. =>WM: (13680: O1950 ^name predict-no)
  10436. =>WM: (13679: O1949 ^name predict-yes)
  10437. =>WM: (13678: R978 ^value 1)
  10438. =>WM: (13677: R1 ^reward R978)
  10439. =>WM: (13676: I3 ^see 1)
  10440. <=WM: (13667: S1 ^operator O1947 +)
  10441. <=WM: (13669: S1 ^operator O1947)
  10442. <=WM: (13668: S1 ^operator O1948 +)
  10443. <=WM: (13662: R1 ^reward R977)
  10444. <=WM: (13661: I3 ^see 0)
  10445. <=WM: (13665: O1948 ^name predict-no)
  10446. <=WM: (13664: O1947 ^name predict-yes)
  10447. <=WM: (13663: R977 ^value 1)
  10448. --- Inner Elaboration Phase, active level 1 (S1) ---
  10449. Firing prefer*rvt*predict-yes*H0
  10450. -->
  10451. Firing rl*prefer*rvt*predict-yes*H0*3
  10452. -->
  10453. (S1 ^operator O1949 = 0.3907810808803528)
  10454. Firing prefer*rvt*predict-yes*H0*3*H1
  10455. -->
  10456. Firing rl*prefer*rvt*predict-yes*H0*3*H1*11
  10457. -->
  10458. (S1 ^operator O1949 = -0.2062723012911647)
  10459. Firing prefer*rvt*predict-no*H0
  10460. -->
  10461. Firing rl*prefer*rvt*predict-no*H0*4
  10462. -->
  10463. (S1 ^operator O1950 = 0.3145032394390637)
  10464. Firing prefer*rvt*predict-no*H0*4*H1
  10465. -->
  10466. Firing rl*prefer*rvt*predict-no*H0*4*H1*10
  10467. -->
  10468. (S1 ^operator O1950 = 0.6855461517499103)
  10469. inner elaboration loop at bottom goal.
  10470. Retracting rl*prefer*rvt*predict-no*H0*4
  10471. -->
  10472. (S1 ^operator O1948 = 0.3145032394390637)
  10473. Retracting rl*prefer*rvt*predict-no*H0*4*H1*10
  10474. -->
  10475. (S1 ^operator O1948 = 0.6855461517499103)
  10476. Retracting rl*prefer*rvt*predict-yes*H0*3
  10477. -->
  10478. (S1 ^operator O1947 = 0.3907810808803528)
  10479. Retracting rl*prefer*rvt*predict-yes*H0*3*H1*11
  10480. -->
  10481. (S1 ^operator O1947 = -0.2062723012911647)
  10482. --- END Proposal Phase ---
  10483. --- Decision Phase ---
  10484. RL update rl*prefer*rvt*predict-yes*H0*3 0.472327 -0.0815454 0.390781 -> 0.472318 -0.0815469 0.390771(R,m,v=1,0.942308,0.0547146)
  10485. RL update rl*prefer*rvt*predict-yes*H0*3*H1*17 0.527776 0.0815632 0.609339 -> 0.527766 0.0815615 0.609327(R,m,v=1,1,0)
  10486. =>WM: (13683: S1 ^operator O1950)
  10487. 975: O: O1950 (predict-no)
  10488. --- END Decision Phase ---
  10489. --- Application Phase ---
  10490. --- Firing Productions (PE) For State At Depth 1 ---
  10491. --- Inner Elaboration Phase, active level 1 (S1) ---
  10492. Firing apply*operator
  10493. -->
  10494. (I3 ^predict-no N975 + :O )
  10495. Firing apply*operator*complete
  10496. -->
  10497. (I3 ^predict-yes N974 - :O )
  10498. inner elaboration loop at bottom goal.
  10499. --- Change Working Memory (PE) ---
  10500. =>WM: (13684: I3 ^predict-no N975)
  10501. <=WM: (13671: N974 ^status complete)
  10502. <=WM: (13670: I3 ^predict-yes N974)
  10503. --- Firing Productions (IE) For State At Depth 1 ---
  10504. --- Inner Elaboration Phase, active level 1 (S1) ---
  10505. Firing monitor*world
  10506. -->
  10507. I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
  10508. --- Change Working Memory (IE) ---
  10509. --- END Application Phase ---
  10510. --- Output Phase ---
  10511. ENV: Agent did: predict-no for direction L in state State-A
  10512. In State-A moving L
  10513. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  10514. predict error 0
  10515. dir: dir isU
  10516. --- END Output Phase ---
  10517. /|\--- Input Phase ---
  10518. =>WM: (13688: I2 ^dir U)
  10519. =>WM: (13687: I2 ^reward 1)
  10520. =>WM: (13686: I2 ^see 0)
  10521. =>WM: (13685: N975 ^status complete)
  10522. <=WM: (13674: I2 ^dir L)
  10523. <=WM: (13673: I2 ^reward 1)
  10524. <=WM: (13672: I2 ^see 1)
  10525. =>WM: (13689: I2 ^level-1 L0-root)
  10526. <=WM: (13675: I2 ^level-1 L1-root)
  10527. --- END Input Phase ---
  10528. --- Proposal Phase ---
  10529. --- Inner Elaboration Phase, active level 1 (S1) ---
  10530. Firing elaborate*copy-see-to-output-link
  10531. -->
  10532. (I3 ^see 0 +)
  10533. Firing elaborate*reward*based*on*reward
  10534. -->
  10535. (R979 ^value 1 +)
  10536. (R1 ^reward R979 +)
  10537. Firing propose*predict-yes
  10538. -->
  10539. (O1951 ^name predict-yes +)
  10540. (S1 ^operator O1951 +)
  10541. Firing propose*predict-no
  10542. -->
  10543. (O1952 ^name predict-no +)
  10544. (S1 ^operator O1952 +)
  10545. Firing rl*prefer*rvt*predict-no*H0*2
  10546. -->
  10547. (S1 ^operator O1950 = 1.)
  10548. Firing rl*prefer*rvt*predict-yes*H0*1
  10549. -->
  10550. (S1 ^operator O1949 = 0.)
  10551. Firing prefer*rvt*predict-yes*H0
  10552. -->
  10553. Firing prefer*rvt*predict-no*H0
  10554. -->
  10555. Firing elaborate*copy-dir-to-output-link
  10556. -->
  10557. (I3 ^dir U +)
  10558. inner elaboration loop at bottom goal.
  10559. Retracting elaborate*copy-see-to-output-link
  10560. -->
  10561. (I3 ^see 1 +)
  10562. Retracting propose*predict-no
  10563. -->
  10564. (O1950 ^name predict-no +)
  10565. (S1 ^operator O1950 +)
  10566. Retracting propose*predict-yes
  10567. -->
  10568. (O1949 ^name predict-yes +)
  10569. (S1 ^operator O1949 +)
  10570. Retracting elaborate*reward*based*on*reward
  10571. -->
  10572. (R978 ^value 1 +)
  10573. (R1 ^reward R978 +)
  10574. Retracting elaborate*copy-dir-to-output-link
  10575. -->
  10576. (I3 ^dir L +)
  10577. Retracting rl*prefer*rvt*predict-no*H0*4*H1*10
  10578. -->
  10579. (S1 ^operator O1950 = 0.6855461517499103)
  10580. Retracting rl*prefer*rvt*predict-no*H0*4
  10581. -->
  10582. (S1 ^operator O1950 = 0.3145032394390637)
  10583. Retracting rl*prefer*rvt*predict-yes*H0*3*H1*11
  10584. -->
  10585. (S1 ^operator O1949 = -0.2062723012911647)
  10586. Retracting rl*prefer*rvt*predict-yes*H0*3
  10587. -->
  10588. (S1 ^operator O1949 = 0.3907711727075364)
  10589. =>WM: (13697: S1 ^operator O1952 +)
  10590. =>WM: (13696: S1 ^operator O1951 +)
  10591. =>WM: (13695: I3 ^dir U)
  10592. =>WM: (13694: O1952 ^name predict-no)
  10593. =>WM: (13693: O1951 ^name predict-yes)
  10594. =>WM: (13692: R979 ^value 1)
  10595. =>WM: (13691: R1 ^reward R979)
  10596. =>WM: (13690: I3 ^see 0)
  10597. <=WM: (13681: S1 ^operator O1949 +)
  10598. <=WM: (13682: S1 ^operator O1950 +)
  10599. <=WM: (13683: S1 ^operator O1950)
  10600. <=WM: (13666: I3 ^dir L)
  10601. <=WM: (13677: R1 ^reward R978)
  10602. <=WM: (13676: I3 ^see 1)
  10603. <=WM: (13680: O1950 ^name predict-no)
  10604. <=WM: (13679: O1949 ^name predict-yes)
  10605. <=WM: (13678: R978 ^value 1)
  10606. --- Inner Elaboration Phase, active level 1 (S1) ---
  10607. Firing prefer*rvt*predict-yes*H0
  10608. -->
  10609. Firing rl*prefer*rvt*predict-yes*H0*1
  10610. -->
  10611. (S1 ^operator O1951 = 0.)
  10612. Firing prefer*rvt*predict-no*H0
  10613. -->
  10614. Firing rl*prefer*rvt*predict-no*H0*2
  10615. -->
  10616. (S1 ^operator O1952 = 1.)
  10617. inner elaboration loop at bottom goal.
  10618. Retracting rl*prefer*rvt*predict-no*H0*2
  10619. -->
  10620. (S1 ^operator O1950 = 1.)
  10621. Retracting rl*prefer*rvt*predict-yes*H0*1
  10622. -->
  10623. (S1 ^operator O1949 = 0.)
  10624. --- END Proposal Phase ---
  10625. --- Decision Phase ---
  10626. RL update rl*prefer*rvt*predict-no*H0*4 0.478552 -0.164048 0.314503 -> 0.478548 -0.164049 0.314499(R,m,v=1,0.92053,0.0736424)
  10627. RL update rl*prefer*rvt*predict-no*H0*4*H1*10 0.521493 0.164053 0.685546 -> 0.521489 0.164052 0.685541(R,m,v=1,1,0)
  10628. =>WM: (13698: S1 ^operator O1952)
  10629. 976: O: O1952 (predict-no)
  10630. --- END Decision Phase ---
  10631. --- Application Phase ---
  10632. --- Firing Productions (PE) For State At Depth 1 ---
  10633. --- Inner Elaboration Phase, active level 1 (S1) ---
  10634. Firing apply*operator
  10635. -->
  10636. (I3 ^predict-no N976 + :O )
  10637. Firing apply*operator*complete
  10638. -->
  10639. (I3 ^predict-no N975 - :O )
  10640. inner elaboration loop at bottom goal.
  10641. --- Change Working Memory (PE) ---
  10642. =>WM: (13699: I3 ^predict-no N976)
  10643. <=WM: (13685: N975 ^status complete)
  10644. <=WM: (13684: I3 ^predict-no N975)
  10645. --- Firing Productions (IE) For State At Depth 1 ---
  10646. --- Inner Elaboration Phase, active level 1 (S1) ---
  10647. Firing monitor*world
  10648. -->
  10649. I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
  10650. --- Change Working Memory (IE) ---
  10651. --- END Application Phase ---
  10652. --- Output Phase ---
  10653. ENV: Agent did: predict-no for direction U in state State-A
  10654. In State-A moving U
  10655. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  10656. predict error 0
  10657. dir: dir isL
  10658. --- END Output Phase ---
  10659. -/|--- Input Phase ---
  10660. =>WM: (13703: I2 ^dir L)
  10661. =>WM: (13702: I2 ^reward 1)
  10662. =>WM: (13701: I2 ^see 0)
  10663. =>WM: (13700: N976 ^status complete)
  10664. <=WM: (13688: I2 ^dir U)
  10665. <=WM: (13687: I2 ^reward 1)
  10666. <=WM: (13686: I2 ^see 0)
  10667. =>WM: (13704: I2 ^level-1 L0-root)
  10668. <=WM: (13689: I2 ^level-1 L0-root)
  10669. --- END Input Phase ---
  10670. --- Proposal Phase ---
  10671. --- Inner Elaboration Phase, active level 1 (S1) ---
  10672. Firing rl*prefer*rvt*predict-yes*H0*3*H1*13
  10673. -->
  10674. (S1 ^operator O1951 = -0.208713043145708)
  10675. Firing rl*prefer*rvt*predict-no*H0*4*H1*12
  10676. -->
  10677. (S1 ^operator O1952 = 0.6854177156873388)
  10678. Firing prefer*rvt*predict-no*H0*4*H1
  10679. -->
  10680. Firing prefer*rvt*predict-yes*H0*3*H1
  10681. -->
  10682. Firing elaborate*copy-see-to-output-link
  10683. -->
  10684. (I3 ^see 0 +)
  10685. Firing elaborate*reward*based*on*reward
  10686. -->
  10687. (R980 ^value 1 +)
  10688. (R1 ^reward R980 +)
  10689. Firing propose*predict-yes
  10690. -->
  10691. (O1953 ^name predict-yes +)
  10692. (S1 ^operator O1953 +)
  10693. Firing propose*predict-no
  10694. -->
  10695. (O1954 ^name predict-no +)
  10696. (S1 ^operator O1954 +)
  10697. Firing rl*prefer*rvt*predict-no*H0*4
  10698. -->
  10699. (S1 ^operator O1952 = 0.3144991353263821)
  10700. Firing rl*prefer*rvt*predict-yes*H0*3
  10701. -->
  10702. (S1 ^operator O1951 = 0.3907711727075364)
  10703. Firing prefer*rvt*predict-yes*H0
  10704. -->
  10705. Firing prefer*rvt*predict-no*H0
  10706. -->
  10707. Firing elaborate*copy-dir-to-output-link
  10708. -->
  10709. (I3 ^dir L +)
  10710. inner elaboration loop at bottom goal.
  10711. Retracting elaborate*copy-see-to-output-link
  10712. -->
  10713. (I3 ^see 0 +)
  10714. Retracting propose*predict-no
  10715. -->
  10716. (O1952 ^name predict-no +)
  10717. (S1 ^operator O1952 +)
  10718. Retracting propose*predict-yes
  10719. -->
  10720. (O1951 ^name predict-yes +)
  10721. (S1 ^operator O1951 +)
  10722. Retracting elaborate*reward*based*on*reward
  10723. -->
  10724. (R979 ^value 1 +)
  10725. (R1 ^reward R979 +)
  10726. Retracting elaborate*copy-dir-to-output-link
  10727. -->
  10728. (I3 ^dir U +)
  10729. Retracting rl*prefer*rvt*predict-no*H0*2
  10730. -->
  10731. (S1 ^operator O1952 = 1.)
  10732. Retracting rl*prefer*rvt*predict-yes*H0*1
  10733. -->
  10734. (S1 ^operator O1951 = 0.)
  10735. =>WM: (13711: S1 ^operator O1954 +)
  10736. =>WM: (13710: S1 ^operator O1953 +)
  10737. =>WM: (13709: I3 ^dir L)
  10738. =>WM: (13708: O1954 ^name predict-no)
  10739. =>WM: (13707: O1953 ^name predict-yes)
  10740. =>WM: (13706: R980 ^value 1)
  10741. =>WM: (13705: R1 ^reward R980)
  10742. <=WM: (13696: S1 ^operator O1951 +)
  10743. <=WM: (13697: S1 ^operator O1952 +)
  10744. <=WM: (13698: S1 ^operator O1952)
  10745. <=WM: (13695: I3 ^dir U)
  10746. <=WM: (13691: R1 ^reward R979)
  10747. <=WM: (13694: O1952 ^name predict-no)
  10748. <=WM: (13693: O1951 ^name predict-yes)
  10749. <=WM: (13692: R979 ^value 1)
  10750. --- Inner Elaboration Phase, active level 1 (S1) ---
  10751. Firing prefer*rvt*predict-yes*H0
  10752. -->
  10753. Firing rl*prefer*rvt*predict-yes*H0*3*H1*13
  10754. -->
  10755. (S1 ^operator O1953 = -0.208713043145708)
  10756. Firing rl*prefer*rvt*predict-yes*H0*3
  10757. -->
  10758. (S1 ^operator O1953 = 0.3907711727075364)
  10759. Firing prefer*rvt*predict-yes*H0*3*H1
  10760. -->
  10761. Firing prefer*rvt*predict-no*H0
  10762. -->
  10763. Firing rl*prefer*rvt*predict-no*H0*4*H1*12
  10764. -->
  10765. (S1 ^operator O1954 = 0.6854177156873388)
  10766. Firing rl*prefer*rvt*predict-no*H0*4
  10767. -->
  10768. (S1 ^operator O1954 = 0.3144991353263821)
  10769. Firing prefer*rvt*predict-no*H0*4*H1
  10770. -->
  10771. inner elaboration loop at bottom goal.
  10772. Retracting rl*prefer*rvt*predict-no*H0*4
  10773. -->
  10774. (S1 ^operator O1952 = 0.3144991353263821)
  10775. Retracting rl*prefer*rvt*predict-no*H0*4*H1*12
  10776. -->
  10777. (S1 ^operator O1952 = 0.6854177156873388)
  10778. Retracting rl*prefer*rvt*predict-yes*H0*3
  10779. -->
  10780. (S1 ^operator O1951 = 0.3907711727075364)
  10781. Retracting rl*prefer*rvt*predict-yes*H0*3*H1*13
  10782. -->
  10783. (S1 ^operator O1951 = -0.208713043145708)
  10784. --- END Proposal Phase ---
  10785. --- Decision Phase ---
  10786. RL update rl*prefer*rvt*predict-no*H0*2 1 0 1 -> 1 0 1(R,m,v=1,1,0)
  10787. =>WM: (13712: S1 ^operator O1954)
  10788. 977: O: O1954 (predict-no)
  10789. --- END Decision Phase ---
  10790. --- Application Phase ---
  10791. --- Firing Productions (PE) For State At Depth 1 ---
  10792. --- Inner Elaboration Phase, active level 1 (S1) ---
  10793. Firing apply*operator
  10794. -->
  10795. (I3 ^predict-no N977 + :O )
  10796. Firing apply*operator*complete
  10797. -->
  10798. (I3 ^predict-no N976 - :O )
  10799. inner elaboration loop at bottom goal.
  10800. --- Change Working Memory (PE) ---
  10801. =>WM: (13713: I3 ^predict-no N977)
  10802. <=WM: (13700: N976 ^status complete)
  10803. <=WM: (13699: I3 ^predict-no N976)
  10804. --- Firing Productions (IE) For State At Depth 1 ---
  10805. --- Inner Elaboration Phase, active level 1 (S1) ---
  10806. Firing monitor*world
  10807. -->
  10808. I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
  10809. --- Change Working Memory (IE) ---
  10810. --- END Application Phase ---
  10811. --- Output Phase ---
  10812. ENV: Agent did: predict-no for direction L in state State-A
  10813. In State-A moving L
  10814. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  10815. predict error 0
  10816. dir: dir isR
  10817. --- END Output Phase ---
  10818. \-/--- Input Phase ---
  10819. =>WM: (13717: I2 ^dir R)
  10820. =>WM: (13716: I2 ^reward 1)
  10821. =>WM: (13715: I2 ^see 0)
  10822. =>WM: (13714: N977 ^status complete)
  10823. <=WM: (13703: I2 ^dir L)
  10824. <=WM: (13702: I2 ^reward 1)
  10825. <=WM: (13701: I2 ^see 0)
  10826. =>WM: (13718: I2 ^level-1 L0-root)
  10827. <=WM: (13704: I2 ^level-1 L0-root)
  10828. --- END Input Phase ---
  10829. --- Proposal Phase ---
  10830. --- Inner Elaboration Phase, active level 1 (S1) ---
  10831. Firing rl*prefer*rvt*predict-yes*H0*5*H1*14
  10832. -->
  10833. (S1 ^operator O1953 = 0.8783927855286688)
  10834. Firing prefer*rvt*predict-yes*H0*5*H1
  10835. -->
  10836. Firing elaborate*copy-see-to-output-link
  10837. -->
  10838. (I3 ^see 0 +)
  10839. Firing elaborate*reward*based*on*reward
  10840. -->
  10841. (R981 ^value 1 +)
  10842. (R1 ^reward R981 +)
  10843. Firing propose*predict-yes
  10844. -->
  10845. (O1955 ^name predict-yes +)
  10846. (S1 ^operator O1955 +)
  10847. Firing propose*predict-no
  10848. -->
  10849. (O1956 ^name predict-no +)
  10850. (S1 ^operator O1956 +)
  10851. Firing rl*prefer*rvt*predict-no*H0*6
  10852. -->
  10853. (S1 ^operator O1954 = 0.9999810901454903)
  10854. Firing rl*prefer*rvt*predict-yes*H0*5
  10855. -->
  10856. (S1 ^operator O1953 = 0.1215980737936329)
  10857. Firing prefer*rvt*predict-yes*H0
  10858. -->
  10859. Firing prefer*rvt*predict-no*H0
  10860. -->
  10861. Firing elaborate*copy-dir-to-output-link
  10862. -->
  10863. (I3 ^dir R +)
  10864. inner elaboration loop at bottom goal.
  10865. Retracting elaborate*copy-see-to-output-link
  10866. -->
  10867. (I3 ^see 0 +)
  10868. Retracting propose*predict-no
  10869. -->
  10870. (O1954 ^name predict-no +)
  10871. (S1 ^operator O1954 +)
  10872. Retracting propose*predict-yes
  10873. -->
  10874. (O1953 ^name predict-yes +)
  10875. (S1 ^operator O1953 +)
  10876. Retracting elaborate*reward*based*on*reward
  10877. -->
  10878. (R980 ^value 1 +)
  10879. (R1 ^reward R980 +)
  10880. Retracting elaborate*copy-dir-to-output-link
  10881. -->
  10882. (I3 ^dir L +)
  10883. Retracting rl*prefer*rvt*predict-no*H0*4
  10884. -->
  10885. (S1 ^operator O1954 = 0.3144991353263821)
  10886. Retracting rl*prefer*rvt*predict-no*H0*4*H1*12
  10887. -->
  10888. (S1 ^operator O1954 = 0.6854177156873388)
  10889. Retracting rl*prefer*rvt*predict-yes*H0*3
  10890. -->
  10891. (S1 ^operator O1953 = 0.3907711727075364)
  10892. Retracting rl*prefer*rvt*predict-yes*H0*3*H1*13
  10893. -->
  10894. (S1 ^operator O1953 = -0.208713043145708)
  10895. =>WM: (13725: S1 ^operator O1956 +)
  10896. =>WM: (13724: S1 ^operator O1955 +)
  10897. =>WM: (13723: I3 ^dir R)
  10898. =>WM: (13722: O1956 ^name predict-no)
  10899. =>WM: (13721: O1955 ^name predict-yes)
  10900. =>WM: (13720: R981 ^value 1)
  10901. =>WM: (13719: R1 ^reward R981)
  10902. <=WM: (13710: S1 ^operator O1953 +)
  10903. <=WM: (13711: S1 ^operator O1954 +)
  10904. <=WM: (13712: S1 ^operator O1954)
  10905. <=WM: (13709: I3 ^dir L)
  10906. <=WM: (13705: R1 ^reward R980)
  10907. <=WM: (13708: O1954 ^name predict-no)
  10908. <=WM: (13707: O1953 ^name predict-yes)
  10909. <=WM: (13706: R980 ^value 1)
  10910. --- Inner Elaboration Phase, active level 1 (S1) ---
  10911. Firing prefer*rvt*predict-yes*H0
  10912. -->
  10913. Firing rl*prefer*rvt*predict-yes*H0*5*H1*14
  10914. -->
  10915. (S1 ^operator O1955 = 0.8783927855286688)
  10916. Firing rl*prefer*rvt*predict-yes*H0*5
  10917. -->
  10918. (S1 ^operator O1955 = 0.1215980737936329)
  10919. Firing prefer*rvt*predict-yes*H0*5*H1
  10920. -->
  10921. Firing prefer*rvt*predict-no*H0
  10922. -->
  10923. Firing rl*prefer*rvt*predict-no*H0*6
  10924. -->
  10925. (S1 ^operator O1956 = 0.9999810901454903)
  10926. inner elaboration loop at bottom goal.
  10927. Retracting rl*prefer*rvt*predict-no*H0*6
  10928. -->
  10929. (S1 ^operator O1954 = 0.9999810901454903)
  10930. Retracting rl*prefer*rvt*predict-yes*H0*5
  10931. -->
  10932. (S1 ^operator O1953 = 0.1215980737936329)
  10933. Retracting rl*prefer*rvt*predict-yes*H0*5*H1*14
  10934. -->
  10935. (S1 ^operator O1953 = 0.8783927855286688)
  10936. --- END Proposal Phase ---
  10937. --- Decision Phase ---
  10938. RL update rl*prefer*rvt*predict-no*H0*4 0.478548 -0.164049 0.314499 -> 0.478554 -0.164048 0.314506(R,m,v=1,0.921053,0.0731962)
  10939. RL update rl*prefer*rvt*predict-no*H0*4*H1*12 0.521377 0.164041 0.685418 -> 0.521384 0.164042 0.685426(R,m,v=1,1,0)
  10940. =>WM: (13726: S1 ^operator O1955)
  10941. 978: O: O1955 (predict-yes)
  10942. --- END Decision Phase ---
  10943. --- Application Phase ---
  10944. --- Firing Productions (PE) For State At Depth 1 ---
  10945. --- Inner Elaboration Phase, active level 1 (S1) ---
  10946. Firing apply*operator
  10947. -->
  10948. (I3 ^predict-yes N978 + :O )
  10949. Firing apply*operator*complete
  10950. -->
  10951. (I3 ^predict-no N977 - :O )
  10952. inner elaboration loop at bottom goal.
  10953. --- Change Working Memory (PE) ---
  10954. =>WM: (13727: I3 ^predict-yes N978)
  10955. <=WM: (13714: N977 ^status complete)
  10956. <=WM: (13713: I3 ^predict-no N977)
  10957. --- Firing Productions (IE) For State At Depth 1 ---
  10958. --- Inner Elaboration Phase, active level 1 (S1) ---
  10959. Firing monitor*world
  10960. -->
  10961. I see 1 and I'm going to do: predict-yes inner elaboration loop at bottom goal.
  10962. --- Change Working Memory (IE) ---
  10963. --- END Application Phase ---
  10964. --- Output Phase ---
  10965. ENV: Agent did: predict-yes for direction R in state State-A
  10966. In State-A moving R
  10967. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  10968. predict error 0
  10969. dir: dir isL
  10970. --- END Output Phase ---
  10971. |\---- Input Phase ---
  10972. =>WM: (13731: I2 ^dir L)
  10973. =>WM: (13730: I2 ^reward 1)
  10974. =>WM: (13729: I2 ^see 1)
  10975. =>WM: (13728: N978 ^status complete)
  10976. <=WM: (13717: I2 ^dir R)
  10977. <=WM: (13716: I2 ^reward 1)
  10978. <=WM: (13715: I2 ^see 0)
  10979. =>WM: (13732: I2 ^level-1 R1-root)
  10980. <=WM: (13718: I2 ^level-1 L0-root)
  10981. --- END Input Phase ---
  10982. --- Proposal Phase ---
  10983. --- Inner Elaboration Phase, active level 1 (S1) ---
  10984. Firing rl*prefer*rvt*predict-no*H0*4*H1*16
  10985. -->
  10986. (S1 ^operator O1956 = -0.168718511744511)
  10987. Firing rl*prefer*rvt*predict-yes*H0*3*H1*17
  10988. -->
  10989. (S1 ^operator O1955 = 0.6093273841659509)
  10990. Firing prefer*rvt*predict-no*H0*4*H1
  10991. -->
  10992. Firing prefer*rvt*predict-yes*H0*3*H1
  10993. -->
  10994. Firing elaborate*copy-see-to-output-link
  10995. -->
  10996. (I3 ^see 1 +)
  10997. Firing elaborate*reward*based*on*reward
  10998. -->
  10999. (R982 ^value 1 +)
  11000. (R1 ^reward R982 +)
  11001. Firing propose*predict-yes
  11002. -->
  11003. (O1957 ^name predict-yes +)
  11004. (S1 ^operator O1957 +)
  11005. Firing propose*predict-no
  11006. -->
  11007. (O1958 ^name predict-no +)
  11008. (S1 ^operator O1958 +)
  11009. Firing rl*prefer*rvt*predict-no*H0*4
  11010. -->
  11011. (S1 ^operator O1956 = 0.3145060369395525)
  11012. Firing rl*prefer*rvt*predict-yes*H0*3
  11013. -->
  11014. (S1 ^operator O1955 = 0.3907711727075364)
  11015. Firing prefer*rvt*predict-yes*H0
  11016. -->
  11017. Firing prefer*rvt*predict-no*H0
  11018. -->
  11019. Firing elaborate*copy-dir-to-output-link
  11020. -->
  11021. (I3 ^dir L +)
  11022. inner elaboration loop at bottom goal.
  11023. Retracting elaborate*copy-see-to-output-link
  11024. -->
  11025. (I3 ^see 0 +)
  11026. Retracting propose*predict-no
  11027. -->
  11028. (O1956 ^name predict-no +)
  11029. (S1 ^operator O1956 +)
  11030. Retracting propose*predict-yes
  11031. -->
  11032. (O1955 ^name predict-yes +)
  11033. (S1 ^operator O1955 +)
  11034. Retracting elaborate*reward*based*on*reward
  11035. -->
  11036. (R981 ^value 1 +)
  11037. (R1 ^reward R981 +)
  11038. Retracting elaborate*copy-dir-to-output-link
  11039. -->
  11040. (I3 ^dir R +)
  11041. Retracting rl*prefer*rvt*predict-no*H0*6
  11042. -->
  11043. (S1 ^operator O1956 = 0.9999810901454903)
  11044. Retracting rl*prefer*rvt*predict-yes*H0*5
  11045. -->
  11046. (S1 ^operator O1955 = 0.1215980737936329)
  11047. Retracting rl*prefer*rvt*predict-yes*H0*5*H1*14
  11048. -->
  11049. (S1 ^operator O1955 = 0.8783927855286688)
  11050. =>WM: (13740: S1 ^operator O1958 +)
  11051. =>WM: (13739: S1 ^operator O1957 +)
  11052. =>WM: (13738: I3 ^dir L)
  11053. =>WM: (13737: O1958 ^name predict-no)
  11054. =>WM: (13736: O1957 ^name predict-yes)
  11055. =>WM: (13735: R982 ^value 1)
  11056. =>WM: (13734: R1 ^reward R982)
  11057. =>WM: (13733: I3 ^see 1)
  11058. <=WM: (13724: S1 ^operator O1955 +)
  11059. <=WM: (13726: S1 ^operator O1955)
  11060. <=WM: (13725: S1 ^operator O1956 +)
  11061. <=WM: (13723: I3 ^dir R)
  11062. <=WM: (13719: R1 ^reward R981)
  11063. <=WM: (13690: I3 ^see 0)
  11064. <=WM: (13722: O1956 ^name predict-no)
  11065. <=WM: (13721: O1955 ^name predict-yes)
  11066. <=WM: (13720: R981 ^value 1)
  11067. --- Inner Elaboration Phase, active level 1 (S1) ---
  11068. Firing prefer*rvt*predict-yes*H0
  11069. -->
  11070. Firing rl*prefer*rvt*predict-yes*H0*3
  11071. -->
  11072. (S1 ^operator O1957 = 0.3907711727075364)
  11073. Firing prefer*rvt*predict-yes*H0*3*H1
  11074. -->
  11075. Firing rl*prefer*rvt*predict-yes*H0*3*H1*17
  11076. -->
  11077. (S1 ^operator O1957 = 0.6093273841659509)
  11078. Firing prefer*rvt*predict-no*H0
  11079. -->
  11080. Firing rl*prefer*rvt*predict-no*H0*4
  11081. -->
  11082. (S1 ^operator O1958 = 0.3145060369395525)
  11083. Firing prefer*rvt*predict-no*H0*4*H1
  11084. -->
  11085. Firing rl*prefer*rvt*predict-no*H0*4*H1*16
  11086. -->
  11087. (S1 ^operator O1958 = -0.168718511744511)
  11088. inner elaboration loop at bottom goal.
  11089. Retracting rl*prefer*rvt*predict-no*H0*4
  11090. -->
  11091. (S1 ^operator O1956 = 0.3145060369395525)
  11092. Retracting rl*prefer*rvt*predict-no*H0*4*H1*16
  11093. -->
  11094. (S1 ^operator O1956 = -0.168718511744511)
  11095. Retracting rl*prefer*rvt*predict-yes*H0*3
  11096. -->
  11097. (S1 ^operator O1955 = 0.3907711727075364)
  11098. Retracting rl*prefer*rvt*predict-yes*H0*3*H1*17
  11099. -->
  11100. (S1 ^operator O1955 = 0.6093273841659509)
  11101. --- END Proposal Phase ---
  11102. --- Decision Phase ---
  11103. RL update rl*prefer*rvt*predict-yes*H0*5 0.534524 -0.412926 0.121598 -> 0.534525 -0.412926 0.121599(R,m,v=1,0.861272,0.120177)
  11104. RL update rl*prefer*rvt*predict-yes*H0*5*H1*14 0.465468 0.412925 0.878393 -> 0.465469 0.412925 0.878394(R,m,v=1,1,0)
  11105. =>WM: (13741: S1 ^operator O1957)
  11106. 979: O: O1957 (predict-yes)
  11107. --- END Decision Phase ---
  11108. --- Application Phase ---
  11109. --- Firing Productions (PE) For State At Depth 1 ---
  11110. --- Inner Elaboration Phase, active level 1 (S1) ---
  11111. Firing apply*operator
  11112. -->
  11113. (I3 ^predict-yes N979 + :O )
  11114. Firing apply*operator*complete
  11115. -->
  11116. (I3 ^predict-yes N978 - :O )
  11117. inner elaboration loop at bottom goal.
  11118. --- Change Working Memory (PE) ---
  11119. =>WM: (13742: I3 ^predict-yes N979)
  11120. <=WM: (13728: N978 ^status complete)
  11121. <=WM: (13727: I3 ^predict-yes N978)
  11122. --- Firing Productions (IE) For State At Depth 1 ---
  11123. --- Inner Elaboration Phase, active level 1 (S1) ---
  11124. Firing monitor*world
  11125. -->
  11126. I see 1 and I'm going to do: predict-yes inner elaboration loop at bottom goal.
  11127. --- Change Working Memory (IE) ---
  11128. --- END Application Phase ---
  11129. --- Output Phase ---
  11130. ENV: Agent did: predict-yes for direction L in state State-B
  11131. In State-B moving L
  11132. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  11133. predict error 0
  11134. dir: dir isR
  11135. --- END Output Phase ---
  11136. /|--- Input Phase ---
  11137. =>WM: (13746: I2 ^dir R)
  11138. =>WM: (13745: I2 ^reward 1)
  11139. =>WM: (13744: I2 ^see 1)
  11140. =>WM: (13743: N979 ^status complete)
  11141. <=WM: (13731: I2 ^dir L)
  11142. <=WM: (13730: I2 ^reward 1)
  11143. <=WM: (13729: I2 ^see 1)
  11144. =>WM: (13747: I2 ^level-1 L1-root)
  11145. <=WM: (13732: I2 ^level-1 R1-root)
  11146. --- END Input Phase ---
  11147. --- Proposal Phase ---
  11148. --- Inner Elaboration Phase, active level 1 (S1) ---
  11149. Firing rl*prefer*rvt*predict-yes*H0*5*H1*18
  11150. -->
  11151. (S1 ^operator O1957 = 0.8784154092082219)
  11152. Firing prefer*rvt*predict-yes*H0*5*H1
  11153. -->
  11154. Firing elaborate*copy-see-to-output-link
  11155. -->
  11156. (I3 ^see 1 +)
  11157. Firing elaborate*reward*based*on*reward
  11158. -->
  11159. (R983 ^value 1 +)
  11160. (R1 ^reward R983 +)
  11161. Firing propose*predict-yes
  11162. -->
  11163. (O1959 ^name predict-yes +)
  11164. (S1 ^operator O1959 +)
  11165. Firing propose*predict-no
  11166. -->
  11167. (O1960 ^name predict-no +)
  11168. (S1 ^operator O1960 +)
  11169. Firing rl*prefer*rvt*predict-no*H0*6
  11170. -->
  11171. (S1 ^operator O1958 = 0.9999810901454903)
  11172. Firing rl*prefer*rvt*predict-yes*H0*5
  11173. -->
  11174. (S1 ^operator O1957 = 0.1215988165406292)
  11175. Firing prefer*rvt*predict-yes*H0
  11176. -->
  11177. Firing prefer*rvt*predict-no*H0
  11178. -->
  11179. Firing elaborate*copy-dir-to-output-link
  11180. -->
  11181. (I3 ^dir R +)
  11182. inner elaboration loop at bottom goal.
  11183. Retracting elaborate*copy-see-to-output-link
  11184. -->
  11185. (I3 ^see 1 +)
  11186. Retracting propose*predict-no
  11187. -->
  11188. (O1958 ^name predict-no +)
  11189. (S1 ^operator O1958 +)
  11190. Retracting propose*predict-yes
  11191. -->
  11192. (O1957 ^name predict-yes +)
  11193. (S1 ^operator O1957 +)
  11194. Retracting elaborate*reward*based*on*reward
  11195. -->
  11196. (R982 ^value 1 +)
  11197. (R1 ^reward R982 +)
  11198. Retracting elaborate*copy-dir-to-output-link
  11199. -->
  11200. (I3 ^dir L +)
  11201. Retracting rl*prefer*rvt*predict-no*H0*4*H1*16
  11202. -->
  11203. (S1 ^operator O1958 = -0.168718511744511)
  11204. Retracting rl*prefer*rvt*predict-no*H0*4
  11205. -->
  11206. (S1 ^operator O1958 = 0.3145060369395525)
  11207. Retracting rl*prefer*rvt*predict-yes*H0*3*H1*17
  11208. -->
  11209. (S1 ^operator O1957 = 0.6093273841659509)
  11210. Retracting rl*prefer*rvt*predict-yes*H0*3
  11211. -->
  11212. (S1 ^operator O1957 = 0.3907711727075364)
  11213. =>WM: (13754: S1 ^operator O1960 +)
  11214. =>WM: (13753: S1 ^operator O1959 +)
  11215. =>WM: (13752: I3 ^dir R)
  11216. =>WM: (13751: O1960 ^name predict-no)
  11217. =>WM: (13750: O1959 ^name predict-yes)
  11218. =>WM: (13749: R983 ^value 1)
  11219. =>WM: (13748: R1 ^reward R983)
  11220. <=WM: (13739: S1 ^operator O1957 +)
  11221. <=WM: (13741: S1 ^operator O1957)
  11222. <=WM: (13740: S1 ^operator O1958 +)
  11223. <=WM: (13738: I3 ^dir L)
  11224. <=WM: (13734: R1 ^reward R982)
  11225. <=WM: (13737: O1958 ^name predict-no)
  11226. <=WM: (13736: O1957 ^name predict-yes)
  11227. <=WM: (13735: R982 ^value 1)
  11228. --- Inner Elaboration Phase, active level 1 (S1) ---
  11229. Firing prefer*rvt*predict-yes*H0
  11230. -->
  11231. Firing rl*prefer*rvt*predict-yes*H0*5
  11232. -->
  11233. (S1 ^operator O1959 = 0.1215988165406292)
  11234. Firing prefer*rvt*predict-yes*H0*5*H1
  11235. -->
  11236. Firing rl*prefer*rvt*predict-yes*H0*5*H1*18
  11237. -->
  11238. (S1 ^operator O1959 = 0.8784154092082219)
  11239. Firing prefer*rvt*predict-no*H0
  11240. -->
  11241. Firing rl*prefer*rvt*predict-no*H0*6
  11242. -->
  11243. (S1 ^operator O1960 = 0.9999810901454903)
  11244. inner elaboration loop at bottom goal.
  11245. Retracting rl*prefer*rvt*predict-no*H0*6
  11246. -->
  11247. (S1 ^operator O1958 = 0.9999810901454903)
  11248. Retracting rl*prefer*rvt*predict-yes*H0*5
  11249. -->
  11250. (S1 ^operator O1957 = 0.1215988165406292)
  11251. Retracting rl*prefer*rvt*predict-yes*H0*5*H1*18
  11252. -->
  11253. (S1 ^operator O1957 = 0.8784154092082219)
  11254. --- END Proposal Phase ---
  11255. --- Decision Phase ---
  11256. RL update rl*prefer*rvt*predict-yes*H0*3 0.472318 -0.0815469 0.390771 -> 0.472311 -0.0815481 0.390763(R,m,v=1,0.942675,0.0543851)
  11257. RL update rl*prefer*rvt*predict-yes*H0*3*H1*17 0.527766 0.0815615 0.609327 -> 0.527758 0.0815601 0.609318(R,m,v=1,1,0)
  11258. =>WM: (13755: S1 ^operator O1959)
  11259. 980: O: O1959 (predict-yes)
  11260. --- END Decision Phase ---
  11261. --- Application Phase ---
  11262. --- Firing Productions (PE) For State At Depth 1 ---
  11263. --- Inner Elaboration Phase, active level 1 (S1) ---
  11264. Firing apply*operator
  11265. -->
  11266. (I3 ^predict-yes N980 + :O )
  11267. Firing apply*operator*complete
  11268. -->
  11269. (I3 ^predict-yes N979 - :O )
  11270. inner elaboration loop at bottom goal.
  11271. --- Change Working Memory (PE) ---
  11272. =>WM: (13756: I3 ^predict-yes N980)
  11273. <=WM: (13743: N979 ^status complete)
  11274. <=WM: (13742: I3 ^predict-yes N979)
  11275. --- Firing Productions (IE) For State At Depth 1 ---
  11276. --- Inner Elaboration Phase, active level 1 (S1) ---
  11277. Firing monitor*world
  11278. -->
  11279. I see 1 and I'm going to do: predict-yes inner elaboration loop at bottom goal.
  11280. --- Change Working Memory (IE) ---
  11281. --- END Application Phase ---
  11282. --- Output Phase ---
  11283. ENV: Agent did: predict-yes for direction R in state State-A
  11284. In State-A moving R
  11285. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  11286. predict error 0
  11287. dir: dir isR
  11288. --- END Output Phase ---
  11289. \-/--- Input Phase ---
  11290. =>WM: (13760: I2 ^dir R)
  11291. =>WM: (13759: I2 ^reward 1)
  11292. =>WM: (13758: I2 ^see 1)
  11293. =>WM: (13757: N980 ^status complete)
  11294. <=WM: (13746: I2 ^dir R)
  11295. <=WM: (13745: I2 ^reward 1)
  11296. <=WM: (13744: I2 ^see 1)
  11297. =>WM: (13761: I2 ^level-1 R1-root)
  11298. <=WM: (13747: I2 ^level-1 L1-root)
  11299. --- END Input Phase ---
  11300. --- Proposal Phase ---
  11301. --- Inner Elaboration Phase, active level 1 (S1) ---
  11302. Firing rl*prefer*rvt*predict-yes*H0*5*H1*15
  11303. -->
  11304. (S1 ^operator O1959 = -0.04253361215288998)
  11305. Firing prefer*rvt*predict-yes*H0*5*H1
  11306. -->
  11307. Firing elaborate*copy-see-to-output-link
  11308. -->
  11309. (I3 ^see 1 +)
  11310. Firing elaborate*reward*based*on*reward
  11311. -->
  11312. (R984 ^value 1 +)
  11313. (R1 ^reward R984 +)
  11314. Firing propose*predict-yes
  11315. -->
  11316. (O1961 ^name predict-yes +)
  11317. (S1 ^operator O1961 +)
  11318. Firing propose*predict-no
  11319. -->
  11320. (O1962 ^name predict-no +)
  11321. (S1 ^operator O1962 +)
  11322. Firing rl*prefer*rvt*predict-no*H0*6
  11323. -->
  11324. (S1 ^operator O1960 = 0.9999810901454903)
  11325. Firing rl*prefer*rvt*predict-yes*H0*5
  11326. -->
  11327. (S1 ^operator O1959 = 0.1215988165406292)
  11328. Firing prefer*rvt*predict-yes*H0
  11329. -->
  11330. Firing prefer*rvt*predict-no*H0
  11331. -->
  11332. Firing elaborate*copy-dir-to-output-link
  11333. -->
  11334. (I3 ^dir R +)
  11335. inner elaboration loop at bottom goal.
  11336. Retracting elaborate*copy-see-to-output-link
  11337. -->
  11338. (I3 ^see 1 +)
  11339. Retracting propose*predict-no
  11340. -->
  11341. (O1960 ^name predict-no +)
  11342. (S1 ^operator O1960 +)
  11343. Retracting propose*predict-yes
  11344. -->
  11345. (O1959 ^name predict-yes +)
  11346. (S1 ^operator O1959 +)
  11347. Retracting elaborate*reward*based*on*reward
  11348. -->
  11349. (R983 ^value 1 +)
  11350. (R1 ^reward R983 +)
  11351. Retracting elaborate*copy-dir-to-output-link
  11352. -->
  11353. (I3 ^dir R +)
  11354. Retracting rl*prefer*rvt*predict-no*H0*6
  11355. -->
  11356. (S1 ^operator O1960 = 0.9999810901454903)
  11357. Retracting rl*prefer*rvt*predict-yes*H0*5*H1*18
  11358. -->
  11359. (S1 ^operator O1959 = 0.8784154092082219)
  11360. Retracting rl*prefer*rvt*predict-yes*H0*5
  11361. -->
  11362. (S1 ^operator O1959 = 0.1215988165406292)
  11363. =>WM: (13767: S1 ^operator O1962 +)
  11364. =>WM: (13766: S1 ^operator O1961 +)
  11365. =>WM: (13765: O1962 ^name predict-no)
  11366. =>WM: (13764: O1961 ^name predict-yes)
  11367. =>WM: (13763: R984 ^value 1)
  11368. =>WM: (13762: R1 ^reward R984)
  11369. <=WM: (13753: S1 ^operator O1959 +)
  11370. <=WM: (13755: S1 ^operator O1959)
  11371. <=WM: (13754: S1 ^operator O1960 +)
  11372. <=WM: (13748: R1 ^reward R983)
  11373. <=WM: (13751: O1960 ^name predict-no)
  11374. <=WM: (13750: O1959 ^name predict-yes)
  11375. <=WM: (13749: R983 ^value 1)
  11376. --- Inner Elaboration Phase, active level 1 (S1) ---
  11377. Firing prefer*rvt*predict-yes*H0
  11378. -->
  11379. Firing rl*prefer*rvt*predict-yes*H0*5
  11380. -->
  11381. (S1 ^operator O1961 = 0.1215988165406292)
  11382. Firing prefer*rvt*predict-yes*H0*5*H1
  11383. -->
  11384. Firing rl*prefer*rvt*predict-yes*H0*5*H1*15
  11385. -->
  11386. (S1 ^operator O1961 = -0.04253361215288998)
  11387. Firing prefer*rvt*predict-no*H0
  11388. -->
  11389. Firing rl*prefer*rvt*predict-no*H0*6
  11390. -->
  11391. (S1 ^operator O1962 = 0.9999810901454903)
  11392. inner elaboration loop at bottom goal.
  11393. Retracting rl*prefer*rvt*predict-no*H0*6
  11394. -->
  11395. (S1 ^operator O1960 = 0.9999810901454903)
  11396. Retracting rl*prefer*rvt*predict-yes*H0*5
  11397. -->
  11398. (S1 ^operator O1959 = 0.1215988165406292)
  11399. Retracting rl*prefer*rvt*predict-yes*H0*5*H1*15
  11400. -->
  11401. (S1 ^operator O1959 = -0.04253361215288998)
  11402. --- END Proposal Phase ---
  11403. --- Decision Phase ---
  11404. RL update rl*prefer*rvt*predict-yes*H0*5 0.534525 -0.412926 0.121599 -> 0.534524 -0.412926 0.121598(R,m,v=1,0.862069,0.119593)
  11405. RL update rl*prefer*rvt*predict-yes*H0*5*H1*18 0.465487 0.412928 0.878415 -> 0.465486 0.412928 0.878414(R,m,v=1,1,0)
  11406. =>WM: (13768: S1 ^operator O1962)
  11407. 981: O: O1962 (predict-no)
  11408. --- END Decision Phase ---
  11409. --- Application Phase ---
  11410. --- Firing Productions (PE) For State At Depth 1 ---
  11411. --- Inner Elaboration Phase, active level 1 (S1) ---
  11412. Firing apply*operator
  11413. -->
  11414. (I3 ^predict-no N981 + :O )
  11415. Firing apply*operator*complete
  11416. -->
  11417. (I3 ^predict-yes N980 - :O )
  11418. inner elaboration loop at bottom goal.
  11419. --- Change Working Memory (PE) ---
  11420. =>WM: (13769: I3 ^predict-no N981)
  11421. <=WM: (13757: N980 ^status complete)
  11422. <=WM: (13756: I3 ^predict-yes N980)
  11423. --- Firing Productions (IE) For State At Depth 1 ---
  11424. --- Inner Elaboration Phase, active level 1 (S1) ---
  11425. Firing monitor*world
  11426. -->
  11427. I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
  11428. --- Change Working Memory (IE) ---
  11429. --- END Application Phase ---
  11430. --- Output Phase ---
  11431. ENV: Agent did: predict-no for direction R in state State-B
  11432. In State-B moving R
  11433. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  11434. predict error 0
  11435. dir: dir isL
  11436. --- END Output Phase ---
  11437. |--- Input Phase ---
  11438. =>WM: (13773: I2 ^dir L)
  11439. =>WM: (13772: I2 ^reward 1)
  11440. =>WM: (13771: I2 ^see 0)
  11441. =>WM: (13770: N981 ^status complete)
  11442. <=WM: (13760: I2 ^dir R)
  11443. <=WM: (13759: I2 ^reward 1)
  11444. <=WM: (13758: I2 ^see 1)
  11445. =>WM: (13774: I2 ^level-1 R0-root)
  11446. <=WM: (13761: I2 ^level-1 R1-root)
  11447. --- END Input Phase ---
  11448. --- Proposal Phase ---
  11449. --- Inner Elaboration Phase, active level 1 (S1) ---
  11450. Firing rl*prefer*rvt*predict-no*H0*4*H1*8
  11451. -->
  11452. (S1 ^operator O1962 = -0.1984300550322165)
  11453. Firing rl*prefer*rvt*predict-yes*H0*3*H1*9
  11454. -->
  11455. (S1 ^operator O1961 = 0.609089086334031)
  11456. Firing prefer*rvt*predict-no*H0*4*H1
  11457. -->
  11458. Firing prefer*rvt*predict-yes*H0*3*H1
  11459. -->
  11460. Firing elaborate*copy-see-to-output-link
  11461. -->
  11462. (I3 ^see 0 +)
  11463. Firing elaborate*reward*based*on*reward
  11464. -->
  11465. (R985 ^value 1 +)
  11466. (R1 ^reward R985 +)
  11467. Firing propose*predict-yes
  11468. -->
  11469. (O1963 ^name predict-yes +)
  11470. (S1 ^operator O1963 +)
  11471. Firing propose*predict-no
  11472. -->
  11473. (O1964 ^name predict-no +)
  11474. (S1 ^operator O1964 +)
  11475. Firing rl*prefer*rvt*predict-no*H0*4
  11476. -->
  11477. (S1 ^operator O1962 = 0.3145060369395525)
  11478. Firing rl*prefer*rvt*predict-yes*H0*3
  11479. -->
  11480. (S1 ^operator O1961 = 0.39076303591152)
  11481. Firing prefer*rvt*predict-yes*H0
  11482. -->
  11483. Firing prefer*rvt*predict-no*H0
  11484. -->
  11485. Firing elaborate*copy-dir-to-output-link
  11486. -->
  11487. (I3 ^dir L +)
  11488. inner elaboration loop at bottom goal.
  11489. Retracting elaborate*copy-see-to-output-link
  11490. -->
  11491. (I3 ^see 1 +)
  11492. Retracting propose*predict-no
  11493. -->
  11494. (O1962 ^name predict-no +)
  11495. (S1 ^operator O1962 +)
  11496. Retracting propose*predict-yes
  11497. -->
  11498. (O1961 ^name predict-yes +)
  11499. (S1 ^operator O1961 +)
  11500. Retracting elaborate*reward*based*on*reward
  11501. -->
  11502. (R984 ^value 1 +)
  11503. (R1 ^reward R984 +)
  11504. Retracting elaborate*copy-dir-to-output-link
  11505. -->
  11506. (I3 ^dir R +)
  11507. Retracting rl*prefer*rvt*predict-no*H0*6
  11508. -->
  11509. (S1 ^operator O1962 = 0.9999810901454903)
  11510. Retracting rl*prefer*rvt*predict-yes*H0*5*H1*15
  11511. -->
  11512. (S1 ^operator O1961 = -0.04253361215288998)
  11513. Retracting rl*prefer*rvt*predict-yes*H0*5
  11514. -->
  11515. (S1 ^operator O1961 = 0.1215976616761118)
  11516. =>WM: (13782: S1 ^operator O1964 +)
  11517. =>WM: (13781: S1 ^operator O1963 +)
  11518. =>WM: (13780: I3 ^dir L)
  11519. =>WM: (13779: O1964 ^name predict-no)
  11520. =>WM: (13778: O1963 ^name predict-yes)
  11521. =>WM: (13777: R985 ^value 1)
  11522. =>WM: (13776: R1 ^reward R985)
  11523. =>WM: (13775: I3 ^see 0)
  11524. <=WM: (13766: S1 ^operator O1961 +)
  11525. <=WM: (13767: S1 ^operator O1962 +)
  11526. <=WM: (13768: S1 ^operator O1962)
  11527. <=WM: (13752: I3 ^dir R)
  11528. <=WM: (13762: R1 ^reward R984)
  11529. <=WM: (13733: I3 ^see 1)
  11530. <=WM: (13765: O1962 ^name predict-no)
  11531. <=WM: (13764: O1961 ^name predict-yes)
  11532. <=WM: (13763: R984 ^value 1)
  11533. --- Inner Elaboration Phase, active level 1 (S1) ---
  11534. Firing prefer*rvt*predict-yes*H0
  11535. -->
  11536. Firing rl*prefer*rvt*predict-yes*H0*3
  11537. -->
  11538. (S1 ^operator O1963 = 0.39076303591152)
  11539. Firing prefer*rvt*predict-yes*H0*3*H1
  11540. -->
  11541. Firing rl*prefer*rvt*predict-yes*H0*3*H1*9
  11542. -->
  11543. (S1 ^operator O1963 = 0.609089086334031)
  11544. Firing prefer*rvt*predict-no*H0
  11545. -->
  11546. Firing rl*prefer*rvt*predict-no*H0*4
  11547. -->
  11548. (S1 ^operator O1964 = 0.3145060369395525)
  11549. Firing prefer*rvt*predict-no*H0*4*H1
  11550. -->
  11551. Firing rl*prefer*rvt*predict-no*H0*4*H1*8
  11552. -->
  11553. (S1 ^operator O1964 = -0.1984300550322165)
  11554. inner elaboration loop at bottom goal.
  11555. Retracting rl*prefer*rvt*predict-no*H0*4
  11556. -->
  11557. (S1 ^operator O1962 = 0.3145060369395525)
  11558. Retracting rl*prefer*rvt*predict-no*H0*4*H1*8
  11559. -->
  11560. (S1 ^operator O1962 = -0.1984300550322165)
  11561. Retracting rl*prefer*rvt*predict-yes*H0*3
  11562. -->
  11563. (S1 ^operator O1961 = 0.39076303591152)
  11564. Retracting rl*prefer*rvt*predict-yes*H0*3*H1*9
  11565. -->
  11566. (S1 ^operator O1961 = 0.609089086334031)
  11567. --- END Proposal Phase ---
  11568. --- Decision Phase ---
  11569. RL update rl*prefer*rvt*predict-no*H0*6 0.999981 0 0.999981 -> 0.999984 0 0.999984(R,m,v=1,0.937143,0.0592447)
  11570. =>WM: (13783: S1 ^operator O1963)
  11571. 982: O: O1963 (predict-yes)
  11572. --- END Decision Phase ---
  11573. --- Application Phase ---
  11574. --- Firing Productions (PE) For State At Depth 1 ---
  11575. --- Inner Elaboration Phase, active level 1 (S1) ---
  11576. Firing apply*operator
  11577. -->
  11578. (I3 ^predict-yes N982 + :O )
  11579. Firing apply*operator*complete
  11580. -->
  11581. (I3 ^predict-no N981 - :O )
  11582. inner elaboration loop at bottom goal.
  11583. --- Change Working Memory (PE) ---
  11584. =>WM: (13784: I3 ^predict-yes N982)
  11585. <=WM: (13770: N981 ^status complete)
  11586. <=WM: (13769: I3 ^predict-no N981)
  11587. --- Firing Productions (IE) For State At Depth 1 ---
  11588. --- Inner Elaboration Phase, active level 1 (S1) ---
  11589. Firing monitor*world
  11590. -->
  11591. I see 1 and I'm going to do: predict-yes inner elaboration loop at bottom goal.
  11592. --- Change Working Memory (IE) ---
  11593. --- END Application Phase ---
  11594. --- Output Phase ---
  11595. ENV: Agent did: predict-yes for direction L in state State-B
  11596. In State-B moving L
  11597. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  11598. predict error 0
  11599. dir: dir isL
  11600. --- END Output Phase ---
  11601. \-/--- Input Phase ---
  11602. =>WM: (13788: I2 ^dir L)
  11603. =>WM: (13787: I2 ^reward 1)
  11604. =>WM: (13786: I2 ^see 1)
  11605. =>WM: (13785: N982 ^status complete)
  11606. <=WM: (13773: I2 ^dir L)
  11607. <=WM: (13772: I2 ^reward 1)
  11608. <=WM: (13771: I2 ^see 0)
  11609. =>WM: (13789: I2 ^level-1 L1-root)
  11610. <=WM: (13774: I2 ^level-1 R0-root)
  11611. --- END Input Phase ---
  11612. --- Proposal Phase ---
  11613. --- Inner Elaboration Phase, active level 1 (S1) ---
  11614. Firing rl*prefer*rvt*predict-yes*H0*3*H1*11
  11615. -->
  11616. (S1 ^operator O1963 = -0.2062723012911647)
  11617. Firing rl*prefer*rvt*predict-no*H0*4*H1*10
  11618. -->
  11619. (S1 ^operator O1964 = 0.6855414715988584)
  11620. Firing prefer*rvt*predict-no*H0*4*H1
  11621. -->
  11622. Firing prefer*rvt*predict-yes*H0*3*H1
  11623. -->
  11624. Firing elaborate*copy-see-to-output-link
  11625. -->
  11626. (I3 ^see 1 +)
  11627. Firing elaborate*reward*based*on*reward
  11628. -->
  11629. (R986 ^value 1 +)
  11630. (R1 ^reward R986 +)
  11631. Firing propose*predict-yes
  11632. -->
  11633. (O1965 ^name predict-yes +)
  11634. (S1 ^operator O1965 +)
  11635. Firing propose*predict-no
  11636. -->
  11637. (O1966 ^name predict-no +)
  11638. (S1 ^operator O1966 +)
  11639. Firing rl*prefer*rvt*predict-no*H0*4
  11640. -->
  11641. (S1 ^operator O1964 = 0.3145060369395525)
  11642. Firing rl*prefer*rvt*predict-yes*H0*3
  11643. -->
  11644. (S1 ^operator O1963 = 0.39076303591152)
  11645. Firing prefer*rvt*predict-yes*H0
  11646. -->
  11647. Firing prefer*rvt*predict-no*H0
  11648. -->
  11649. Firing elaborate*copy-dir-to-output-link
  11650. -->
  11651. (I3 ^dir L +)
  11652. inner elaboration loop at bottom goal.
  11653. Retracting elaborate*copy-see-to-output-link
  11654. -->
  11655. (I3 ^see 0 +)
  11656. Retracting propose*predict-no
  11657. -->
  11658. (O1964 ^name predict-no +)
  11659. (S1 ^operator O1964 +)
  11660. Retracting propose*predict-yes
  11661. -->
  11662. (O1963 ^name predict-yes +)
  11663. (S1 ^operator O1963 +)
  11664. Retracting elaborate*reward*based*on*reward
  11665. -->
  11666. (R985 ^value 1 +)
  11667. (R1 ^reward R985 +)
  11668. Retracting elaborate*copy-dir-to-output-link
  11669. -->
  11670. (I3 ^dir L +)
  11671. Retracting rl*prefer*rvt*predict-no*H0*4*H1*8
  11672. -->
  11673. (S1 ^operator O1964 = -0.1984300550322165)
  11674. Retracting rl*prefer*rvt*predict-no*H0*4
  11675. -->
  11676. (S1 ^operator O1964 = 0.3145060369395525)
  11677. Retracting rl*prefer*rvt*predict-yes*H0*3*H1*9
  11678. -->
  11679. (S1 ^operator O1963 = 0.609089086334031)
  11680. Retracting rl*prefer*rvt*predict-yes*H0*3
  11681. -->
  11682. (S1 ^operator O1963 = 0.39076303591152)
  11683. =>WM: (13796: S1 ^operator O1966 +)
  11684. =>WM: (13795: S1 ^operator O1965 +)
  11685. =>WM: (13794: O1966 ^name predict-no)
  11686. =>WM: (13793: O1965 ^name predict-yes)
  11687. =>WM: (13792: R986 ^value 1)
  11688. =>WM: (13791: R1 ^reward R986)
  11689. =>WM: (13790: I3 ^see 1)
  11690. <=WM: (13781: S1 ^operator O1963 +)
  11691. <=WM: (13783: S1 ^operator O1963)
  11692. <=WM: (13782: S1 ^operator O1964 +)
  11693. <=WM: (13776: R1 ^reward R985)
  11694. <=WM: (13775: I3 ^see 0)
  11695. <=WM: (13779: O1964 ^name predict-no)
  11696. <=WM: (13778: O1963 ^name predict-yes)
  11697. <=WM: (13777: R985 ^value 1)
  11698. --- Inner Elaboration Phase, active level 1 (S1) ---
  11699. Firing prefer*rvt*predict-yes*H0
  11700. -->
  11701. Firing rl*prefer*rvt*predict-yes*H0*3
  11702. -->
  11703. (S1 ^operator O1965 = 0.39076303591152)
  11704. Firing prefer*rvt*predict-yes*H0*3*H1
  11705. -->
  11706. Firing rl*prefer*rvt*predict-yes*H0*3*H1*11
  11707. -->
  11708. (S1 ^operator O1965 = -0.2062723012911647)
  11709. Firing prefer*rvt*predict-no*H0
  11710. -->
  11711. Firing rl*prefer*rvt*predict-no*H0*4
  11712. -->
  11713. (S1 ^operator O1966 = 0.3145060369395525)
  11714. Firing prefer*rvt*predict-no*H0*4*H1
  11715. -->
  11716. Firing rl*prefer*rvt*predict-no*H0*4*H1*10
  11717. -->
  11718. (S1 ^operator O1966 = 0.6855414715988584)
  11719. inner elaboration loop at bottom goal.
  11720. Retracting rl*prefer*rvt*predict-no*H0*4
  11721. -->
  11722. (S1 ^operator O1964 = 0.3145060369395525)
  11723. Retracting rl*prefer*rvt*predict-no*H0*4*H1*10
  11724. -->
  11725. (S1 ^operator O1964 = 0.6855414715988584)
  11726. Retracting rl*prefer*rvt*predict-yes*H0*3
  11727. -->
  11728. (S1 ^operator O1963 = 0.39076303591152)
  11729. Retracting rl*prefer*rvt*predict-yes*H0*3*H1*11
  11730. -->
  11731. (S1 ^operator O1963 = -0.2062723012911647)
  11732. --- END Proposal Phase ---
  11733. --- Decision Phase ---
  11734. RL update rl*prefer*rvt*predict-yes*H0*3 0.472311 -0.0815481 0.390763 -> 0.472322 -0.0815463 0.390775(R,m,v=1,0.943038,0.0540595)
  11735. RL update rl*prefer*rvt*predict-yes*H0*3*H1*9 0.527563 0.0815262 0.609089 -> 0.527575 0.0815283 0.609103(R,m,v=1,1,0)
  11736. =>WM: (13797: S1 ^operator O1966)
  11737. 983: O: O1966 (predict-no)
  11738. --- END Decision Phase ---
  11739. --- Application Phase ---
  11740. --- Firing Productions (PE) For State At Depth 1 ---
  11741. --- Inner Elaboration Phase, active level 1 (S1) ---
  11742. Firing apply*operator
  11743. -->
  11744. (I3 ^predict-no N983 + :O )
  11745. Firing apply*operator*complete
  11746. -->
  11747. (I3 ^predict-yes N982 - :O )
  11748. inner elaboration loop at bottom goal.
  11749. --- Change Working Memory (PE) ---
  11750. =>WM: (13798: I3 ^predict-no N983)
  11751. <=WM: (13785: N982 ^status complete)
  11752. <=WM: (13784: I3 ^predict-yes N982)
  11753. --- Firing Productions (IE) For State At Depth 1 ---
  11754. --- Inner Elaboration Phase, active level 1 (S1) ---
  11755. Firing monitor*world
  11756. -->
  11757. I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
  11758. --- Change Working Memory (IE) ---
  11759. --- END Application Phase ---
  11760. --- Output Phase ---
  11761. ENV: Agent did: predict-no for direction L in state State-A
  11762. In State-A moving L
  11763. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  11764. predict error 0
  11765. dir: dir isR
  11766. --- END Output Phase ---
  11767. |\---- Input Phase ---
  11768. =>WM: (13802: I2 ^dir R)
  11769. =>WM: (13801: I2 ^reward 1)
  11770. =>WM: (13800: I2 ^see 0)
  11771. =>WM: (13799: N983 ^status complete)
  11772. <=WM: (13788: I2 ^dir L)
  11773. <=WM: (13787: I2 ^reward 1)
  11774. <=WM: (13786: I2 ^see 1)
  11775. =>WM: (13803: I2 ^level-1 L0-root)
  11776. <=WM: (13789: I2 ^level-1 L1-root)
  11777. --- END Input Phase ---
  11778. --- Proposal Phase ---
  11779. --- Inner Elaboration Phase, active level 1 (S1) ---
  11780. Firing rl*prefer*rvt*predict-yes*H0*5*H1*14
  11781. -->
  11782. (S1 ^operator O1965 = 0.8783936611550894)
  11783. Firing prefer*rvt*predict-yes*H0*5*H1
  11784. -->
  11785. Firing elaborate*copy-see-to-output-link
  11786. -->
  11787. (I3 ^see 0 +)
  11788. Firing elaborate*reward*based*on*reward
  11789. -->
  11790. (R987 ^value 1 +)
  11791. (R1 ^reward R987 +)
  11792. Firing propose*predict-yes
  11793. -->
  11794. (O1967 ^name predict-yes +)
  11795. (S1 ^operator O1967 +)
  11796. Firing propose*predict-no
  11797. -->
  11798. (O1968 ^name predict-no +)
  11799. (S1 ^operator O1968 +)
  11800. Firing rl*prefer*rvt*predict-no*H0*6
  11801. -->
  11802. (S1 ^operator O1966 = 0.9999841575438704)
  11803. Firing rl*prefer*rvt*predict-yes*H0*5
  11804. -->
  11805. (S1 ^operator O1965 = 0.1215976616761118)
  11806. Firing prefer*rvt*predict-yes*H0
  11807. -->
  11808. Firing prefer*rvt*predict-no*H0
  11809. -->
  11810. Firing elaborate*copy-dir-to-output-link
  11811. -->
  11812. (I3 ^dir R +)
  11813. inner elaboration loop at bottom goal.
  11814. Retracting elaborate*copy-see-to-output-link
  11815. -->
  11816. (I3 ^see 1 +)
  11817. Retracting propose*predict-no
  11818. -->
  11819. (O1966 ^name predict-no +)
  11820. (S1 ^operator O1966 +)
  11821. Retracting propose*predict-yes
  11822. -->
  11823. (O1965 ^name predict-yes +)
  11824. (S1 ^operator O1965 +)
  11825. Retracting elaborate*reward*based*on*reward
  11826. -->
  11827. (R986 ^value 1 +)
  11828. (R1 ^reward R986 +)
  11829. Retracting elaborate*copy-dir-to-output-link
  11830. -->
  11831. (I3 ^dir L +)
  11832. Retracting rl*prefer*rvt*predict-no*H0*4*H1*10
  11833. -->
  11834. (S1 ^operator O1966 = 0.6855414715988584)
  11835. Retracting rl*prefer*rvt*predict-no*H0*4
  11836. -->
  11837. (S1 ^operator O1966 = 0.3145060369395525)
  11838. Retracting rl*prefer*rvt*predict-yes*H0*3*H1*11
  11839. -->
  11840. (S1 ^operator O1965 = -0.2062723012911647)
  11841. Retracting rl*prefer*rvt*predict-yes*H0*3
  11842. -->
  11843. (S1 ^operator O1965 = 0.390775231823802)
  11844. =>WM: (13811: S1 ^operator O1968 +)
  11845. =>WM: (13810: S1 ^operator O1967 +)
  11846. =>WM: (13809: I3 ^dir R)
  11847. =>WM: (13808: O1968 ^name predict-no)
  11848. =>WM: (13807: O1967 ^name predict-yes)
  11849. =>WM: (13806: R987 ^value 1)
  11850. =>WM: (13805: R1 ^reward R987)
  11851. =>WM: (13804: I3 ^see 0)
  11852. <=WM: (13795: S1 ^operator O1965 +)
  11853. <=WM: (13796: S1 ^operator O1966 +)
  11854. <=WM: (13797: S1 ^operator O1966)
  11855. <=WM: (13780: I3 ^dir L)
  11856. <=WM: (13791: R1 ^reward R986)
  11857. <=WM: (13790: I3 ^see 1)
  11858. <=WM: (13794: O1966 ^name predict-no)
  11859. <=WM: (13793: O1965 ^name predict-yes)
  11860. <=WM: (13792: R986 ^value 1)
  11861. --- Inner Elaboration Phase, active level 1 (S1) ---
  11862. Firing prefer*rvt*predict-yes*H0
  11863. -->
  11864. Firing rl*prefer*rvt*predict-yes*H0*5
  11865. -->
  11866. (S1 ^operator O1967 = 0.1215976616761118)
  11867. Firing prefer*rvt*predict-yes*H0*5*H1
  11868. -->
  11869. Firing rl*prefer*rvt*predict-yes*H0*5*H1*14
  11870. -->
  11871. (S1 ^operator O1967 = 0.8783936611550894)
  11872. Firing prefer*rvt*predict-no*H0
  11873. -->
  11874. Firing rl*prefer*rvt*predict-no*H0*6
  11875. -->
  11876. (S1 ^operator O1968 = 0.9999841575438704)
  11877. inner elaboration loop at bottom goal.
  11878. Retracting rl*prefer*rvt*predict-no*H0*6
  11879. -->
  11880. (S1 ^operator O1966 = 0.9999841575438704)
  11881. Retracting rl*prefer*rvt*predict-yes*H0*5
  11882. -->
  11883. (S1 ^operator O1965 = 0.1215976616761118)
  11884. Retracting rl*prefer*rvt*predict-yes*H0*5*H1*14
  11885. -->
  11886. (S1 ^operator O1965 = 0.8783936611550894)
  11887. --- END Proposal Phase ---
  11888. --- Decision Phase ---
  11889. RL update rl*prefer*rvt*predict-no*H0*4 0.478554 -0.164048 0.314506 -> 0.478551 -0.164048 0.314502(R,m,v=1,0.921569,0.0727554)
  11890. RL update rl*prefer*rvt*predict-no*H0*4*H1*10 0.521489 0.164052 0.685541 -> 0.521485 0.164052 0.685537(R,m,v=1,1,0)
  11891. =>WM: (13812: S1 ^operator O1967)
  11892. 984: O: O1967 (predict-yes)
  11893. --- END Decision Phase ---
  11894. --- Application Phase ---
  11895. --- Firing Productions (PE) For State At Depth 1 ---
  11896. --- Inner Elaboration Phase, active level 1 (S1) ---
  11897. Firing apply*operator
  11898. -->
  11899. (I3 ^predict-yes N984 + :O )
  11900. Firing apply*operator*complete
  11901. -->
  11902. (I3 ^predict-no N983 - :O )
  11903. inner elaboration loop at bottom goal.
  11904. --- Change Working Memory (PE) ---
  11905. =>WM: (13813: I3 ^predict-yes N984)
  11906. <=WM: (13799: N983 ^status complete)
  11907. <=WM: (13798: I3 ^predict-no N983)
  11908. --- Firing Productions (IE) For State At Depth 1 ---
  11909. --- Inner Elaboration Phase, active level 1 (S1) ---
  11910. Firing monitor*world
  11911. -->
  11912. I see 1 and I'm going to do: predict-yes inner elaboration loop at bottom goal.
  11913. --- Change Working Memory (IE) ---
  11914. --- END Application Phase ---
  11915. --- Output Phase ---
  11916. ENV: Agent did: predict-yes for direction R in state State-A
  11917. In State-A moving R
  11918. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  11919. predict error 0
  11920. dir: dir isU
  11921. --- END Output Phase ---
  11922. /|\---- Input Phase ---
  11923. =>WM: (13817: I2 ^dir U)
  11924. =>WM: (13816: I2 ^reward 1)
  11925. =>WM: (13815: I2 ^see 1)
  11926. =>WM: (13814: N984 ^status complete)
  11927. <=WM: (13802: I2 ^dir R)
  11928. <=WM: (13801: I2 ^reward 1)
  11929. <=WM: (13800: I2 ^see 0)
  11930. =>WM: (13818: I2 ^level-1 R1-root)
  11931. <=WM: (13803: I2 ^level-1 L0-root)
  11932. --- END Input Phase ---
  11933. --- Proposal Phase ---
  11934. --- Inner Elaboration Phase, active level 1 (S1) ---
  11935. Firing elaborate*copy-see-to-output-link
  11936. -->
  11937. (I3 ^see 1 +)
  11938. Firing elaborate*reward*based*on*reward
  11939. -->
  11940. (R988 ^value 1 +)
  11941. (R1 ^reward R988 +)
  11942. Firing propose*predict-yes
  11943. -->
  11944. (O1969 ^name predict-yes +)
  11945. (S1 ^operator O1969 +)
  11946. Firing propose*predict-no
  11947. -->
  11948. (O1970 ^name predict-no +)
  11949. (S1 ^operator O1970 +)
  11950. Firing rl*prefer*rvt*predict-no*H0*2
  11951. -->
  11952. (S1 ^operator O1968 = 1.)
  11953. Firing rl*prefer*rvt*predict-yes*H0*1
  11954. -->
  11955. (S1 ^operator O1967 = 0.)
  11956. Firing prefer*rvt*predict-yes*H0
  11957. -->
  11958. Firing prefer*rvt*predict-no*H0
  11959. -->
  11960. Firing elaborate*copy-dir-to-output-link
  11961. -->
  11962. (I3 ^dir U +)
  11963. inner elaboration loop at bottom goal.
  11964. Retracting elaborate*copy-see-to-output-link
  11965. -->
  11966. (I3 ^see 0 +)
  11967. Retracting propose*predict-no
  11968. -->
  11969. (O1968 ^name predict-no +)
  11970. (S1 ^operator O1968 +)
  11971. Retracting propose*predict-yes
  11972. -->
  11973. (O1967 ^name predict-yes +)
  11974. (S1 ^operator O1967 +)
  11975. Retracting elaborate*reward*based*on*reward
  11976. -->
  11977. (R987 ^value 1 +)
  11978. (R1 ^reward R987 +)
  11979. Retracting elaborate*copy-dir-to-output-link
  11980. -->
  11981. (I3 ^dir R +)
  11982. Retracting rl*prefer*rvt*predict-no*H0*6
  11983. -->
  11984. (S1 ^operator O1968 = 0.9999841575438704)
  11985. Retracting rl*prefer*rvt*predict-yes*H0*5*H1*14
  11986. -->
  11987. (S1 ^operator O1967 = 0.8783936611550894)
  11988. Retracting rl*prefer*rvt*predict-yes*H0*5
  11989. -->
  11990. (S1 ^operator O1967 = 0.1215976616761118)
  11991. =>WM: (13826: S1 ^operator O1970 +)
  11992. =>WM: (13825: S1 ^operator O1969 +)
  11993. =>WM: (13824: I3 ^dir U)
  11994. =>WM: (13823: O1970 ^name predict-no)
  11995. =>WM: (13822: O1969 ^name predict-yes)
  11996. =>WM: (13821: R988 ^value 1)
  11997. =>WM: (13820: R1 ^reward R988)
  11998. =>WM: (13819: I3 ^see 1)
  11999. <=WM: (13810: S1 ^operator O1967 +)
  12000. <=WM: (13812: S1 ^operator O1967)
  12001. <=WM: (13811: S1 ^operator O1968 +)
  12002. <=WM: (13809: I3 ^dir R)
  12003. <=WM: (13805: R1 ^reward R987)
  12004. <=WM: (13804: I3 ^see 0)
  12005. <=WM: (13808: O1968 ^name predict-no)
  12006. <=WM: (13807: O1967 ^name predict-yes)
  12007. <=WM: (13806: R987 ^value 1)
  12008. --- Inner Elaboration Phase, active level 1 (S1) ---
  12009. Firing prefer*rvt*predict-yes*H0
  12010. -->
  12011. Firing rl*prefer*rvt*predict-yes*H0*1
  12012. -->
  12013. (S1 ^operator O1969 = 0.)
  12014. Firing prefer*rvt*predict-no*H0
  12015. -->
  12016. Firing rl*prefer*rvt*predict-no*H0*2
  12017. -->
  12018. (S1 ^operator O1970 = 1.)
  12019. inner elaboration loop at bottom goal.
  12020. Retracting rl*prefer*rvt*predict-no*H0*2
  12021. -->
  12022. (S1 ^operator O1968 = 1.)
  12023. Retracting rl*prefer*rvt*predict-yes*H0*1
  12024. -->
  12025. (S1 ^operator O1967 = 0.)
  12026. --- END Proposal Phase ---
  12027. --- Decision Phase ---
  12028. RL update rl*prefer*rvt*predict-yes*H0*5 0.534524 -0.412926 0.121598 -> 0.534524 -0.412926 0.121598(R,m,v=1,0.862857,0.119015)
  12029. RL update rl*prefer*rvt*predict-yes*H0*5*H1*14 0.465469 0.412925 0.878394 -> 0.46547 0.412925 0.878394(R,m,v=1,1,0)
  12030. =>WM: (13827: S1 ^operator O1970)
  12031. 985: O: O1970 (predict-no)
  12032. --- END Decision Phase ---
  12033. --- Application Phase ---
  12034. --- Firing Productions (PE) For State At Depth 1 ---
  12035. --- Inner Elaboration Phase, active level 1 (S1) ---
  12036. Firing apply*operator
  12037. -->
  12038. (I3 ^predict-no N985 + :O )
  12039. Firing apply*operator*complete
  12040. -->
  12041. (I3 ^predict-yes N984 - :O )
  12042. inner elaboration loop at bottom goal.
  12043. --- Change Working Memory (PE) ---
  12044. =>WM: (13828: I3 ^predict-no N985)
  12045. <=WM: (13814: N984 ^status complete)
  12046. <=WM: (13813: I3 ^predict-yes N984)
  12047. --- Firing Productions (IE) For State At Depth 1 ---
  12048. --- Inner Elaboration Phase, active level 1 (S1) ---
  12049. Firing monitor*world
  12050. -->
  12051. I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
  12052. --- Change Working Memory (IE) ---
  12053. --- END Application Phase ---
  12054. --- Output Phase ---
  12055. ENV: Agent did: predict-no for direction U in state State-B
  12056. In State-B moving U
  12057. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  12058. predict error 0
  12059. dir: dir isL
  12060. --- END Output Phase ---
  12061. /|\--- Input Phase ---
  12062. =>WM: (13832: I2 ^dir L)
  12063. =>WM: (13831: I2 ^reward 1)
  12064. =>WM: (13830: I2 ^see 0)
  12065. =>WM: (13829: N985 ^status complete)
  12066. <=WM: (13817: I2 ^dir U)
  12067. <=WM: (13816: I2 ^reward 1)
  12068. <=WM: (13815: I2 ^see 1)
  12069. =>WM: (13833: I2 ^level-1 R1-root)
  12070. <=WM: (13818: I2 ^level-1 R1-root)
  12071. --- END Input Phase ---
  12072. --- Proposal Phase ---
  12073. --- Inner Elaboration Phase, active level 1 (S1) ---
  12074. Firing rl*prefer*rvt*predict-no*H0*4*H1*16
  12075. -->
  12076. (S1 ^operator O1970 = -0.168718511744511)
  12077. Firing rl*prefer*rvt*predict-yes*H0*3*H1*17
  12078. -->
  12079. (S1 ^operator O1969 = 0.6093180204125221)
  12080. Firing prefer*rvt*predict-no*H0*4*H1
  12081. -->
  12082. Firing prefer*rvt*predict-yes*H0*3*H1
  12083. -->
  12084. Firing elaborate*copy-see-to-output-link
  12085. -->
  12086. (I3 ^see 0 +)
  12087. Firing elaborate*reward*based*on*reward
  12088. -->
  12089. (R989 ^value 1 +)
  12090. (R1 ^reward R989 +)
  12091. Firing propose*predict-yes
  12092. -->
  12093. (O1971 ^name predict-yes +)
  12094. (S1 ^operator O1971 +)
  12095. Firing propose*predict-no
  12096. -->
  12097. (O1972 ^name predict-no +)
  12098. (S1 ^operator O1972 +)
  12099. Firing rl*prefer*rvt*predict-no*H0*4
  12100. -->
  12101. (S1 ^operator O1970 = 0.3145020978774952)
  12102. Firing rl*prefer*rvt*predict-yes*H0*3
  12103. -->
  12104. (S1 ^operator O1969 = 0.390775231823802)
  12105. Firing prefer*rvt*predict-yes*H0
  12106. -->
  12107. Firing prefer*rvt*predict-no*H0
  12108. -->
  12109. Firing elaborate*copy-dir-to-output-link
  12110. -->
  12111. (I3 ^dir L +)
  12112. inner elaboration loop at bottom goal.
  12113. Retracting elaborate*copy-see-to-output-link
  12114. -->
  12115. (I3 ^see 1 +)
  12116. Retracting propose*predict-no
  12117. -->
  12118. (O1970 ^name predict-no +)
  12119. (S1 ^operator O1970 +)
  12120. Retracting propose*predict-yes
  12121. -->
  12122. (O1969 ^name predict-yes +)
  12123. (S1 ^operator O1969 +)
  12124. Retracting elaborate*reward*based*on*reward
  12125. -->
  12126. (R988 ^value 1 +)
  12127. (R1 ^reward R988 +)
  12128. Retracting elaborate*copy-dir-to-output-link
  12129. -->
  12130. (I3 ^dir U +)
  12131. Retracting rl*prefer*rvt*predict-no*H0*2
  12132. -->
  12133. (S1 ^operator O1970 = 1.)
  12134. Retracting rl*prefer*rvt*predict-yes*H0*1
  12135. -->
  12136. (S1 ^operator O1969 = 0.)
  12137. =>WM: (13841: S1 ^operator O1972 +)
  12138. =>WM: (13840: S1 ^operator O1971 +)
  12139. =>WM: (13839: I3 ^dir L)
  12140. =>WM: (13838: O1972 ^name predict-no)
  12141. =>WM: (13837: O1971 ^name predict-yes)
  12142. =>WM: (13836: R989 ^value 1)
  12143. =>WM: (13835: R1 ^reward R989)
  12144. =>WM: (13834: I3 ^see 0)
  12145. <=WM: (13825: S1 ^operator O1969 +)
  12146. <=WM: (13826: S1 ^operator O1970 +)
  12147. <=WM: (13827: S1 ^operator O1970)
  12148. <=WM: (13824: I3 ^dir U)
  12149. <=WM: (13820: R1 ^reward R988)
  12150. <=WM: (13819: I3 ^see 1)
  12151. <=WM: (13823: O1970 ^name predict-no)
  12152. <=WM: (13822: O1969 ^name predict-yes)
  12153. <=WM: (13821: R988 ^value 1)
  12154. --- Inner Elaboration Phase, active level 1 (S1) ---
  12155. Firing prefer*rvt*predict-yes*H0
  12156. -->
  12157. Firing rl*prefer*rvt*predict-yes*H0*3*H1*17
  12158. -->
  12159. (S1 ^operator O1971 = 0.6093180204125221)
  12160. Firing rl*prefer*rvt*predict-yes*H0*3
  12161. -->
  12162. (S1 ^operator O1971 = 0.390775231823802)
  12163. Firing prefer*rvt*predict-yes*H0*3*H1
  12164. -->
  12165. Firing prefer*rvt*predict-no*H0
  12166. -->
  12167. Firing rl*prefer*rvt*predict-no*H0*4*H1*16
  12168. -->
  12169. (S1 ^operator O1972 = -0.168718511744511)
  12170. Firing rl*prefer*rvt*predict-no*H0*4
  12171. -->
  12172. (S1 ^operator O1972 = 0.3145020978774952)
  12173. Firing prefer*rvt*predict-no*H0*4*H1
  12174. -->
  12175. inner elaboration loop at bottom goal.
  12176. Retracting rl*prefer*rvt*predict-no*H0*4
  12177. -->
  12178. (S1 ^operator O1970 = 0.3145020978774952)
  12179. Retracting rl*prefer*rvt*predict-no*H0*4*H1*16
  12180. -->
  12181. (S1 ^operator O1970 = -0.168718511744511)
  12182. Retracting rl*prefer*rvt*predict-yes*H0*3
  12183. -->
  12184. (S1 ^operator O1969 = 0.390775231823802)
  12185. Retracting rl*prefer*rvt*predict-yes*H0*3*H1*17
  12186. -->
  12187. (S1 ^operator O1969 = 0.6093180204125221)
  12188. --- END Proposal Phase ---
  12189. --- Decision Phase ---
  12190. RL update rl*prefer*rvt*predict-no*H0*2 1 0 1 -> 1 0 1(R,m,v=1,1,0)
  12191. =>WM: (13842: S1 ^operator O1971)
  12192. 986: O: O1971 (predict-yes)
  12193. --- END Decision Phase ---
  12194. --- Application Phase ---
  12195. --- Firing Productions (PE) For State At Depth 1 ---
  12196. --- Inner Elaboration Phase, active level 1 (S1) ---
  12197. Firing apply*operator
  12198. -->
  12199. (I3 ^predict-yes N986 + :O )
  12200. Firing apply*operator*complete
  12201. -->
  12202. (I3 ^predict-no N985 - :O )
  12203. inner elaboration loop at bottom goal.
  12204. --- Change Working Memory (PE) ---
  12205. =>WM: (13843: I3 ^predict-yes N986)
  12206. <=WM: (13829: N985 ^status complete)
  12207. <=WM: (13828: I3 ^predict-no N985)
  12208. --- Firing Productions (IE) For State At Depth 1 ---
  12209. --- Inner Elaboration Phase, active level 1 (S1) ---
  12210. Firing monitor*world
  12211. -->
  12212. I see 1 and I'm going to do: predict-yes inner elaboration loop at bottom goal.
  12213. --- Change Working Memory (IE) ---
  12214. --- END Application Phase ---
  12215. --- Output Phase ---
  12216. ENV: Agent did: predict-yes for direction L in state State-B
  12217. In State-B moving L
  12218. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  12219. predict error 0
  12220. dir: dir isL
  12221. --- END Output Phase ---
  12222. -/|--- Input Phase ---
  12223. =>WM: (13847: I2 ^dir L)
  12224. =>WM: (13846: I2 ^reward 1)
  12225. =>WM: (13845: I2 ^see 1)
  12226. =>WM: (13844: N986 ^status complete)
  12227. <=WM: (13832: I2 ^dir L)
  12228. <=WM: (13831: I2 ^reward 1)
  12229. <=WM: (13830: I2 ^see 0)
  12230. =>WM: (13848: I2 ^level-1 L1-root)
  12231. <=WM: (13833: I2 ^level-1 R1-root)
  12232. --- END Input Phase ---
  12233. --- Proposal Phase ---
  12234. --- Inner Elaboration Phase, active level 1 (S1) ---
  12235. Firing rl*prefer*rvt*predict-yes*H0*3*H1*11
  12236. -->
  12237. (S1 ^operator O1971 = -0.2062723012911647)
  12238. Firing rl*prefer*rvt*predict-no*H0*4*H1*10
  12239. -->
  12240. (S1 ^operator O1972 = 0.6855369815787629)
  12241. Firing prefer*rvt*predict-no*H0*4*H1
  12242. -->
  12243. Firing prefer*rvt*predict-yes*H0*3*H1
  12244. -->
  12245. Firing elaborate*copy-see-to-output-link
  12246. -->
  12247. (I3 ^see 1 +)
  12248. Firing elaborate*reward*based*on*reward
  12249. -->
  12250. (R990 ^value 1 +)
  12251. (R1 ^reward R990 +)
  12252. Firing propose*predict-yes
  12253. -->
  12254. (O1973 ^name predict-yes +)
  12255. (S1 ^operator O1973 +)
  12256. Firing propose*predict-no
  12257. -->
  12258. (O1974 ^name predict-no +)
  12259. (S1 ^operator O1974 +)
  12260. Firing rl*prefer*rvt*predict-no*H0*4
  12261. -->
  12262. (S1 ^operator O1972 = 0.3145020978774952)
  12263. Firing rl*prefer*rvt*predict-yes*H0*3
  12264. -->
  12265. (S1 ^operator O1971 = 0.390775231823802)
  12266. Firing prefer*rvt*predict-yes*H0
  12267. -->
  12268. Firing prefer*rvt*predict-no*H0
  12269. -->
  12270. Firing elaborate*copy-dir-to-output-link
  12271. -->
  12272. (I3 ^dir L +)
  12273. inner elaboration loop at bottom goal.
  12274. Retracting elaborate*copy-see-to-output-link
  12275. -->
  12276. (I3 ^see 0 +)
  12277. Retracting propose*predict-no
  12278. -->
  12279. (O1972 ^name predict-no +)
  12280. (S1 ^operator O1972 +)
  12281. Retracting propose*predict-yes
  12282. -->
  12283. (O1971 ^name predict-yes +)
  12284. (S1 ^operator O1971 +)
  12285. Retracting elaborate*reward*based*on*reward
  12286. -->
  12287. (R989 ^value 1 +)
  12288. (R1 ^reward R989 +)
  12289. Retracting elaborate*copy-dir-to-output-link
  12290. -->
  12291. (I3 ^dir L +)
  12292. Retracting rl*prefer*rvt*predict-no*H0*4
  12293. -->
  12294. (S1 ^operator O1972 = 0.3145020978774952)
  12295. Retracting rl*prefer*rvt*predict-no*H0*4*H1*16
  12296. -->
  12297. (S1 ^operator O1972 = -0.168718511744511)
  12298. Retracting rl*prefer*rvt*predict-yes*H0*3
  12299. -->
  12300. (S1 ^operator O1971 = 0.390775231823802)
  12301. Retracting rl*prefer*rvt*predict-yes*H0*3*H1*17
  12302. -->
  12303. (S1 ^operator O1971 = 0.6093180204125221)
  12304. =>WM: (13855: S1 ^operator O1974 +)
  12305. =>WM: (13854: S1 ^operator O1973 +)
  12306. =>WM: (13853: O1974 ^name predict-no)
  12307. =>WM: (13852: O1973 ^name predict-yes)
  12308. =>WM: (13851: R990 ^value 1)
  12309. =>WM: (13850: R1 ^reward R990)
  12310. =>WM: (13849: I3 ^see 1)
  12311. <=WM: (13840: S1 ^operator O1971 +)
  12312. <=WM: (13842: S1 ^operator O1971)
  12313. <=WM: (13841: S1 ^operator O1972 +)
  12314. <=WM: (13835: R1 ^reward R989)
  12315. <=WM: (13834: I3 ^see 0)
  12316. <=WM: (13838: O1972 ^name predict-no)
  12317. <=WM: (13837: O1971 ^name predict-yes)
  12318. <=WM: (13836: R989 ^value 1)
  12319. --- Inner Elaboration Phase, active level 1 (S1) ---
  12320. Firing prefer*rvt*predict-yes*H0
  12321. -->
  12322. Firing rl*prefer*rvt*predict-yes*H0*3
  12323. -->
  12324. (S1 ^operator O1973 = 0.390775231823802)
  12325. Firing prefer*rvt*predict-yes*H0*3*H1
  12326. -->
  12327. Firing rl*prefer*rvt*predict-yes*H0*3*H1*11
  12328. -->
  12329. (S1 ^operator O1973 = -0.2062723012911647)
  12330. Firing prefer*rvt*predict-no*H0
  12331. -->
  12332. Firing rl*prefer*rvt*predict-no*H0*4
  12333. -->
  12334. (S1 ^operator O1974 = 0.3145020978774952)
  12335. Firing prefer*rvt*predict-no*H0*4*H1
  12336. -->
  12337. Firing rl*prefer*rvt*predict-no*H0*4*H1*10
  12338. -->
  12339. (S1 ^operator O1974 = 0.6855369815787629)
  12340. inner elaboration loop at bottom goal.
  12341. Retracting rl*prefer*rvt*predict-no*H0*4
  12342. -->
  12343. (S1 ^operator O1972 = 0.3145020978774952)
  12344. Retracting rl*prefer*rvt*predict-no*H0*4*H1*10
  12345. -->
  12346. (S1 ^operator O1972 = 0.6855369815787629)
  12347. Retracting rl*prefer*rvt*predict-yes*H0*3
  12348. -->
  12349. (S1 ^operator O1971 = 0.390775231823802)
  12350. Retracting rl*prefer*rvt*predict-yes*H0*3*H1*11
  12351. -->
  12352. (S1 ^operator O1971 = -0.2062723012911647)
  12353. --- END Proposal Phase ---
  12354. --- Decision Phase ---
  12355. RL update rl*prefer*rvt*predict-yes*H0*3 0.472322 -0.0815463 0.390775 -> 0.472315 -0.0815474 0.390768(R,m,v=1,0.943396,0.0537378)
  12356. RL update rl*prefer*rvt*predict-yes*H0*3*H1*17 0.527758 0.0815601 0.609318 -> 0.52775 0.0815588 0.609309(R,m,v=1,1,0)
  12357. =>WM: (13856: S1 ^operator O1974)
  12358. 987: O: O1974 (predict-no)
  12359. --- END Decision Phase ---
  12360. --- Application Phase ---
  12361. --- Firing Productions (PE) For State At Depth 1 ---
  12362. --- Inner Elaboration Phase, active level 1 (S1) ---
  12363. Firing apply*operator
  12364. -->
  12365. (I3 ^predict-no N987 + :O )
  12366. Firing apply*operator*complete
  12367. -->
  12368. (I3 ^predict-yes N986 - :O )
  12369. inner elaboration loop at bottom goal.
  12370. --- Change Working Memory (PE) ---
  12371. =>WM: (13857: I3 ^predict-no N987)
  12372. <=WM: (13844: N986 ^status complete)
  12373. <=WM: (13843: I3 ^predict-yes N986)
  12374. --- Firing Productions (IE) For State At Depth 1 ---
  12375. --- Inner Elaboration Phase, active level 1 (S1) ---
  12376. Firing monitor*world
  12377. -->
  12378. I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
  12379. --- Change Working Memory (IE) ---
  12380. --- END Application Phase ---
  12381. --- Output Phase ---
  12382. ENV: Agent did: predict-no for direction L in state State-A
  12383. In State-A moving L
  12384. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  12385. predict error 0
  12386. dir: dir isR
  12387. --- END Output Phase ---
  12388. \---- Input Phase ---
  12389. =>WM: (13861: I2 ^dir R)
  12390. =>WM: (13860: I2 ^reward 1)
  12391. =>WM: (13859: I2 ^see 0)
  12392. =>WM: (13858: N987 ^status complete)
  12393. <=WM: (13847: I2 ^dir L)
  12394. <=WM: (13846: I2 ^reward 1)
  12395. <=WM: (13845: I2 ^see 1)
  12396. =>WM: (13862: I2 ^level-1 L0-root)
  12397. <=WM: (13848: I2 ^level-1 L1-root)
  12398. --- END Input Phase ---
  12399. --- Proposal Phase ---
  12400. --- Inner Elaboration Phase, active level 1 (S1) ---
  12401. Firing rl*prefer*rvt*predict-yes*H0*5*H1*14
  12402. -->
  12403. (S1 ^operator O1973 = 0.8783944900614931)
  12404. Firing prefer*rvt*predict-yes*H0*5*H1
  12405. -->
  12406. Firing elaborate*copy-see-to-output-link
  12407. -->
  12408. (I3 ^see 0 +)
  12409. Firing elaborate*reward*based*on*reward
  12410. -->
  12411. (R991 ^value 1 +)
  12412. (R1 ^reward R991 +)
  12413. Firing propose*predict-yes
  12414. -->
  12415. (O1975 ^name predict-yes +)
  12416. (S1 ^operator O1975 +)
  12417. Firing propose*predict-no
  12418. -->
  12419. (O1976 ^name predict-no +)
  12420. (S1 ^operator O1976 +)
  12421. Firing rl*prefer*rvt*predict-no*H0*6
  12422. -->
  12423. (S1 ^operator O1974 = 0.9999841575438704)
  12424. Firing rl*prefer*rvt*predict-yes*H0*5
  12425. -->
  12426. (S1 ^operator O1973 = 0.1215983654449722)
  12427. Firing prefer*rvt*predict-yes*H0
  12428. -->
  12429. Firing prefer*rvt*predict-no*H0
  12430. -->
  12431. Firing elaborate*copy-dir-to-output-link
  12432. -->
  12433. (I3 ^dir R +)
  12434. inner elaboration loop at bottom goal.
  12435. Retracting elaborate*copy-see-to-output-link
  12436. -->
  12437. (I3 ^see 1 +)
  12438. Retracting propose*predict-no
  12439. -->
  12440. (O1974 ^name predict-no +)
  12441. (S1 ^operator O1974 +)
  12442. Retracting propose*predict-yes
  12443. -->
  12444. (O1973 ^name predict-yes +)
  12445. (S1 ^operator O1973 +)
  12446. Retracting elaborate*reward*based*on*reward
  12447. -->
  12448. (R990 ^value 1 +)
  12449. (R1 ^reward R990 +)
  12450. Retracting elaborate*copy-dir-to-output-link
  12451. -->
  12452. (I3 ^dir L +)
  12453. Retracting rl*prefer*rvt*predict-no*H0*4*H1*10
  12454. -->
  12455. (S1 ^operator O1974 = 0.6855369815787629)
  12456. Retracting rl*prefer*rvt*predict-no*H0*4
  12457. -->
  12458. (S1 ^operator O1974 = 0.3145020978774952)
  12459. Retracting rl*prefer*rvt*predict-yes*H0*3*H1*11
  12460. -->
  12461. (S1 ^operator O1973 = -0.2062723012911647)
  12462. Retracting rl*prefer*rvt*predict-yes*H0*3
  12463. -->
  12464. (S1 ^operator O1973 = 0.3907675490335307)
  12465. =>WM: (13870: S1 ^operator O1976 +)
  12466. =>WM: (13869: S1 ^operator O1975 +)
  12467. =>WM: (13868: I3 ^dir R)
  12468. =>WM: (13867: O1976 ^name predict-no)
  12469. =>WM: (13866: O1975 ^name predict-yes)
  12470. =>WM: (13865: R991 ^value 1)
  12471. =>WM: (13864: R1 ^reward R991)
  12472. =>WM: (13863: I3 ^see 0)
  12473. <=WM: (13854: S1 ^operator O1973 +)
  12474. <=WM: (13855: S1 ^operator O1974 +)
  12475. <=WM: (13856: S1 ^operator O1974)
  12476. <=WM: (13839: I3 ^dir L)
  12477. <=WM: (13850: R1 ^reward R990)
  12478. <=WM: (13849: I3 ^see 1)
  12479. <=WM: (13853: O1974 ^name predict-no)
  12480. <=WM: (13852: O1973 ^name predict-yes)
  12481. <=WM: (13851: R990 ^value 1)
  12482. --- Inner Elaboration Phase, active level 1 (S1) ---
  12483. Firing prefer*rvt*predict-yes*H0
  12484. -->
  12485. Firing rl*prefer*rvt*predict-yes*H0*5
  12486. -->
  12487. (S1 ^operator O1975 = 0.1215983654449722)
  12488. Firing prefer*rvt*predict-yes*H0*5*H1
  12489. -->
  12490. Firing rl*prefer*rvt*predict-yes*H0*5*H1*14
  12491. -->
  12492. (S1 ^operator O1975 = 0.8783944900614931)
  12493. Firing prefer*rvt*predict-no*H0
  12494. -->
  12495. Firing rl*prefer*rvt*predict-no*H0*6
  12496. -->
  12497. (S1 ^operator O1976 = 0.9999841575438704)
  12498. inner elaboration loop at bottom goal.
  12499. Retracting rl*prefer*rvt*predict-no*H0*6
  12500. -->
  12501. (S1 ^operator O1974 = 0.9999841575438704)
  12502. Retracting rl*prefer*rvt*predict-yes*H0*5
  12503. -->
  12504. (S1 ^operator O1973 = 0.1215983654449722)
  12505. Retracting rl*prefer*rvt*predict-yes*H0*5*H1*14
  12506. -->
  12507. (S1 ^operator O1973 = 0.8783944900614931)
  12508. --- END Proposal Phase ---
  12509. --- Decision Phase ---
  12510. RL update rl*prefer*rvt*predict-no*H0*4 0.478551 -0.164048 0.314502 -> 0.478548 -0.164049 0.314499(R,m,v=1,0.922078,0.0723198)
  12511. RL update rl*prefer*rvt*predict-no*H0*4*H1*10 0.521485 0.164052 0.685537 -> 0.521482 0.164052 0.685533(R,m,v=1,1,0)
  12512. =>WM: (13871: S1 ^operator O1975)
  12513. 988: O: O1975 (predict-yes)
  12514. --- END Decision Phase ---
  12515. --- Application Phase ---
  12516. --- Firing Productions (PE) For State At Depth 1 ---
  12517. --- Inner Elaboration Phase, active level 1 (S1) ---
  12518. Firing apply*operator
  12519. -->
  12520. (I3 ^predict-yes N988 + :O )
  12521. Firing apply*operator*complete
  12522. -->
  12523. (I3 ^predict-no N987 - :O )
  12524. inner elaboration loop at bottom goal.
  12525. --- Change Working Memory (PE) ---
  12526. =>WM: (13872: I3 ^predict-yes N988)
  12527. <=WM: (13858: N987 ^status complete)
  12528. <=WM: (13857: I3 ^predict-no N987)
  12529. --- Firing Productions (IE) For State At Depth 1 ---
  12530. --- Inner Elaboration Phase, active level 1 (S1) ---
  12531. Firing monitor*world
  12532. -->
  12533. I see 1 and I'm going to do: predict-yes inner elaboration loop at bottom goal.
  12534. --- Change Working Memory (IE) ---
  12535. --- END Application Phase ---
  12536. --- Output Phase ---
  12537. ENV: Agent did: predict-yes for direction R in state State-A
  12538. In State-A moving R
  12539. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  12540. predict error 0
  12541. dir: dir isR
  12542. --- END Output Phase ---
  12543. /|\--- Input Phase ---
  12544. =>WM: (13876: I2 ^dir R)
  12545. =>WM: (13875: I2 ^reward 1)
  12546. =>WM: (13874: I2 ^see 1)
  12547. =>WM: (13873: N988 ^status complete)
  12548. <=WM: (13861: I2 ^dir R)
  12549. <=WM: (13860: I2 ^reward 1)
  12550. <=WM: (13859: I2 ^see 0)
  12551. =>WM: (13877: I2 ^level-1 R1-root)
  12552. <=WM: (13862: I2 ^level-1 L0-root)
  12553. --- END Input Phase ---
  12554. --- Proposal Phase ---
  12555. --- Inner Elaboration Phase, active level 1 (S1) ---
  12556. Firing rl*prefer*rvt*predict-yes*H0*5*H1*15
  12557. -->
  12558. (S1 ^operator O1975 = -0.04253361215288998)
  12559. Firing prefer*rvt*predict-yes*H0*5*H1
  12560. -->
  12561. Firing elaborate*copy-see-to-output-link
  12562. -->
  12563. (I3 ^see 1 +)
  12564. Firing elaborate*reward*based*on*reward
  12565. -->
  12566. (R992 ^value 1 +)
  12567. (R1 ^reward R992 +)
  12568. Firing propose*predict-yes
  12569. -->
  12570. (O1977 ^name predict-yes +)
  12571. (S1 ^operator O1977 +)
  12572. Firing propose*predict-no
  12573. -->
  12574. (O1978 ^name predict-no +)
  12575. (S1 ^operator O1978 +)
  12576. Firing rl*prefer*rvt*predict-no*H0*6
  12577. -->
  12578. (S1 ^operator O1976 = 0.9999841575438704)
  12579. Firing rl*prefer*rvt*predict-yes*H0*5
  12580. -->
  12581. (S1 ^operator O1975 = 0.1215983654449722)
  12582. Firing prefer*rvt*predict-yes*H0
  12583. -->
  12584. Firing prefer*rvt*predict-no*H0
  12585. -->
  12586. Firing elaborate*copy-dir-to-output-link
  12587. -->
  12588. (I3 ^dir R +)
  12589. inner elaboration loop at bottom goal.
  12590. Retracting elaborate*copy-see-to-output-link
  12591. -->
  12592. (I3 ^see 0 +)
  12593. Retracting propose*predict-no
  12594. -->
  12595. (O1976 ^name predict-no +)
  12596. (S1 ^operator O1976 +)
  12597. Retracting propose*predict-yes
  12598. -->
  12599. (O1975 ^name predict-yes +)
  12600. (S1 ^operator O1975 +)
  12601. Retracting elaborate*reward*based*on*reward
  12602. -->
  12603. (R991 ^value 1 +)
  12604. (R1 ^reward R991 +)
  12605. Retracting elaborate*copy-dir-to-output-link
  12606. -->
  12607. (I3 ^dir R +)
  12608. Retracting rl*prefer*rvt*predict-no*H0*6
  12609. -->
  12610. (S1 ^operator O1976 = 0.9999841575438704)
  12611. Retracting rl*prefer*rvt*predict-yes*H0*5*H1*14
  12612. -->
  12613. (S1 ^operator O1975 = 0.8783944900614931)
  12614. Retracting rl*prefer*rvt*predict-yes*H0*5
  12615. -->
  12616. (S1 ^operator O1975 = 0.1215983654449722)
  12617. =>WM: (13884: S1 ^operator O1978 +)
  12618. =>WM: (13883: S1 ^operator O1977 +)
  12619. =>WM: (13882: O1978 ^name predict-no)
  12620. =>WM: (13881: O1977 ^name predict-yes)
  12621. =>WM: (13880: R992 ^value 1)
  12622. =>WM: (13879: R1 ^reward R992)
  12623. =>WM: (13878: I3 ^see 1)
  12624. <=WM: (13869: S1 ^operator O1975 +)
  12625. <=WM: (13871: S1 ^operator O1975)
  12626. <=WM: (13870: S1 ^operator O1976 +)
  12627. <=WM: (13864: R1 ^reward R991)
  12628. <=WM: (13863: I3 ^see 0)
  12629. <=WM: (13867: O1976 ^name predict-no)
  12630. <=WM: (13866: O1975 ^name predict-yes)
  12631. <=WM: (13865: R991 ^value 1)
  12632. --- Inner Elaboration Phase, active level 1 (S1) ---
  12633. Firing prefer*rvt*predict-yes*H0
  12634. -->
  12635. Firing rl*prefer*rvt*predict-yes*H0*5
  12636. -->
  12637. (S1 ^operator O1977 = 0.1215983654449722)
  12638. Firing prefer*rvt*predict-yes*H0*5*H1
  12639. -->
  12640. Firing rl*prefer*rvt*predict-yes*H0*5*H1*15
  12641. -->
  12642. (S1 ^operator O1977 = -0.04253361215288998)
  12643. Firing prefer*rvt*predict-no*H0
  12644. -->
  12645. Firing rl*prefer*rvt*predict-no*H0*6
  12646. -->
  12647. (S1 ^operator O1978 = 0.9999841575438704)
  12648. inner elaboration loop at bottom goal.
  12649. Retracting rl*prefer*rvt*predict-no*H0*6
  12650. -->
  12651. (S1 ^operator O1976 = 0.9999841575438704)
  12652. Retracting rl*prefer*rvt*predict-yes*H0*5
  12653. -->
  12654. (S1 ^operator O1975 = 0.1215983654449722)
  12655. Retracting rl*prefer*rvt*predict-yes*H0*5*H1*15
  12656. -->
  12657. (S1 ^operator O1975 = -0.04253361215288998)
  12658. --- END Proposal Phase ---
  12659. --- Decision Phase ---
  12660. RL update rl*prefer*rvt*predict-yes*H0*5 0.534524 -0.412926 0.121598 -> 0.534525 -0.412926 0.121599(R,m,v=1,0.863636,0.118442)
  12661. RL update rl*prefer*rvt*predict-yes*H0*5*H1*14 0.46547 0.412925 0.878394 -> 0.46547 0.412925 0.878395(R,m,v=1,1,0)
  12662. =>WM: (13885: S1 ^operator O1978)
  12663. 989: O: O1978 (predict-no)
  12664. --- END Decision Phase ---
  12665. --- Application Phase ---
  12666. --- Firing Productions (PE) For State At Depth 1 ---
  12667. --- Inner Elaboration Phase, active level 1 (S1) ---
  12668. Firing apply*operator
  12669. -->
  12670. (I3 ^predict-no N989 + :O )
  12671. Firing apply*operator*complete
  12672. -->
  12673. (I3 ^predict-yes N988 - :O )
  12674. inner elaboration loop at bottom goal.
  12675. --- Change Working Memory (PE) ---
  12676. =>WM: (13886: I3 ^predict-no N989)
  12677. <=WM: (13873: N988 ^status complete)
  12678. <=WM: (13872: I3 ^predict-yes N988)
  12679. --- Firing Productions (IE) For State At Depth 1 ---
  12680. --- Inner Elaboration Phase, active level 1 (S1) ---
  12681. Firing monitor*world
  12682. -->
  12683. I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
  12684. --- Change Working Memory (IE) ---
  12685. --- END Application Phase ---
  12686. --- Output Phase ---
  12687. ENV: Agent did: predict-no for direction R in state State-B
  12688. In State-B moving R
  12689. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  12690. predict error 0
  12691. dir: dir isU
  12692. --- END Output Phase ---
  12693. -/|--- Input Phase ---
  12694. =>WM: (13890: I2 ^dir U)
  12695. =>WM: (13889: I2 ^reward 1)
  12696. =>WM: (13888: I2 ^see 0)
  12697. =>WM: (13887: N989 ^status complete)
  12698. <=WM: (13876: I2 ^dir R)
  12699. <=WM: (13875: I2 ^reward 1)
  12700. <=WM: (13874: I2 ^see 1)
  12701. =>WM: (13891: I2 ^level-1 R0-root)
  12702. <=WM: (13877: I2 ^level-1 R1-root)
  12703. --- END Input Phase ---
  12704. --- Proposal Phase ---
  12705. --- Inner Elaboration Phase, active level 1 (S1) ---
  12706. Firing elaborate*copy-see-to-output-link
  12707. -->
  12708. (I3 ^see 0 +)
  12709. Firing elaborate*reward*based*on*reward
  12710. -->
  12711. (R993 ^value 1 +)
  12712. (R1 ^reward R993 +)
  12713. Firing propose*predict-yes
  12714. -->
  12715. (O1979 ^name predict-yes +)
  12716. (S1 ^operator O1979 +)
  12717. Firing propose*predict-no
  12718. -->
  12719. (O1980 ^name predict-no +)
  12720. (S1 ^operator O1980 +)
  12721. Firing rl*prefer*rvt*predict-no*H0*2
  12722. -->
  12723. (S1 ^operator O1978 = 1.)
  12724. Firing rl*prefer*rvt*predict-yes*H0*1
  12725. -->
  12726. (S1 ^operator O1977 = 0.)
  12727. Firing prefer*rvt*predict-yes*H0
  12728. -->
  12729. Firing prefer*rvt*predict-no*H0
  12730. -->
  12731. Firing elaborate*copy-dir-to-output-link
  12732. -->
  12733. (I3 ^dir U +)
  12734. inner elaboration loop at bottom goal.
  12735. Retracting elaborate*copy-see-to-output-link
  12736. -->
  12737. (I3 ^see 1 +)
  12738. Retracting propose*predict-no
  12739. -->
  12740. (O1978 ^name predict-no +)
  12741. (S1 ^operator O1978 +)
  12742. Retracting propose*predict-yes
  12743. -->
  12744. (O1977 ^name predict-yes +)
  12745. (S1 ^operator O1977 +)
  12746. Retracting elaborate*reward*based*on*reward
  12747. -->
  12748. (R992 ^value 1 +)
  12749. (R1 ^reward R992 +)
  12750. Retracting elaborate*copy-dir-to-output-link
  12751. -->
  12752. (I3 ^dir R +)
  12753. Retracting rl*prefer*rvt*predict-no*H0*6
  12754. -->
  12755. (S1 ^operator O1978 = 0.9999841575438704)
  12756. Retracting rl*prefer*rvt*predict-yes*H0*5*H1*15
  12757. -->
  12758. (S1 ^operator O1977 = -0.04253361215288998)
  12759. Retracting rl*prefer*rvt*predict-yes*H0*5
  12760. -->
  12761. (S1 ^operator O1977 = 0.1215989443698621)
  12762. =>WM: (13899: S1 ^operator O1980 +)
  12763. =>WM: (13898: S1 ^operator O1979 +)
  12764. =>WM: (13897: I3 ^dir U)
  12765. =>WM: (13896: O1980 ^name predict-no)
  12766. =>WM: (13895: O1979 ^name predict-yes)
  12767. =>WM: (13894: R993 ^value 1)
  12768. =>WM: (13893: R1 ^reward R993)
  12769. =>WM: (13892: I3 ^see 0)
  12770. <=WM: (13883: S1 ^operator O1977 +)
  12771. <=WM: (13884: S1 ^operator O1978 +)
  12772. <=WM: (13885: S1 ^operator O1978)
  12773. <=WM: (13868: I3 ^dir R)
  12774. <=WM: (13879: R1 ^reward R992)
  12775. <=WM: (13878: I3 ^see 1)
  12776. <=WM: (13882: O1978 ^name predict-no)
  12777. <=WM: (13881: O1977 ^name predict-yes)
  12778. <=WM: (13880: R992 ^value 1)
  12779. --- Inner Elaboration Phase, active level 1 (S1) ---
  12780. Firing prefer*rvt*predict-yes*H0
  12781. -->
  12782. Firing rl*prefer*rvt*predict-yes*H0*1
  12783. -->
  12784. (S1 ^operator O1979 = 0.)
  12785. Firing prefer*rvt*predict-no*H0
  12786. -->
  12787. Firing rl*prefer*rvt*predict-no*H0*2
  12788. -->
  12789. (S1 ^operator O1980 = 1.)
  12790. inner elaboration loop at bottom goal.
  12791. Retracting rl*prefer*rvt*predict-no*H0*2
  12792. -->
  12793. (S1 ^operator O1978 = 1.)
  12794. Retracting rl*prefer*rvt*predict-yes*H0*1
  12795. -->
  12796. (S1 ^operator O1977 = 0.)
  12797. --- END Proposal Phase ---
  12798. --- Decision Phase ---
  12799. RL update rl*prefer*rvt*predict-no*H0*6 0.999984 0 0.999984 -> 0.999987 0 0.999987(R,m,v=1,0.9375,0.0589286)
  12800. =>WM: (13900: S1 ^operator O1980)
  12801. 990: O: O1980 (predict-no)
  12802. --- END Decision Phase ---
  12803. --- Application Phase ---
  12804. --- Firing Productions (PE) For State At Depth 1 ---
  12805. --- Inner Elaboration Phase, active level 1 (S1) ---
  12806. Firing apply*operator
  12807. -->
  12808. (I3 ^predict-no N990 + :O )
  12809. Firing apply*operator*complete
  12810. -->
  12811. (I3 ^predict-no N989 - :O )
  12812. inner elaboration loop at bottom goal.
  12813. --- Change Working Memory (PE) ---
  12814. =>WM: (13901: I3 ^predict-no N990)
  12815. <=WM: (13887: N989 ^status complete)
  12816. <=WM: (13886: I3 ^predict-no N989)
  12817. --- Firing Productions (IE) For State At Depth 1 ---
  12818. --- Inner Elaboration Phase, active level 1 (S1) ---
  12819. Firing monitor*world
  12820. -->
  12821. I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
  12822. --- Change Working Memory (IE) ---
  12823. --- END Application Phase ---
  12824. --- Output Phase ---
  12825. ENV: Agent did: predict-no for direction U in state State-B
  12826. In State-B moving U
  12827. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  12828. predict error 0
  12829. dir: dir isR
  12830. --- END Output Phase ---
  12831. \-/--- Input Phase ---
  12832. =>WM: (13905: I2 ^dir R)
  12833. =>WM: (13904: I2 ^reward 1)
  12834. =>WM: (13903: I2 ^see 0)
  12835. =>WM: (13902: N990 ^status complete)
  12836. <=WM: (13890: I2 ^dir U)
  12837. <=WM: (13889: I2 ^reward 1)
  12838. <=WM: (13888: I2 ^see 0)
  12839. =>WM: (13906: I2 ^level-1 R0-root)
  12840. <=WM: (13891: I2 ^level-1 R0-root)
  12841. --- END Input Phase ---
  12842. --- Proposal Phase ---
  12843. --- Inner Elaboration Phase, active level 1 (S1) ---
  12844. Firing rl*prefer*rvt*predict-yes*H0*5*H1*7
  12845. -->
  12846. (S1 ^operator O1979 = -0.1512366769350551)
  12847. Firing prefer*rvt*predict-yes*H0*5*H1
  12848. -->
  12849. Firing elaborate*copy-see-to-output-link
  12850. -->
  12851. (I3 ^see 0 +)
  12852. Firing elaborate*reward*based*on*reward
  12853. -->
  12854. (R994 ^value 1 +)
  12855. (R1 ^reward R994 +)
  12856. Firing propose*predict-yes
  12857. -->
  12858. (O1981 ^name predict-yes +)
  12859. (S1 ^operator O1981 +)
  12860. Firing propose*predict-no
  12861. -->
  12862. (O1982 ^name predict-no +)
  12863. (S1 ^operator O1982 +)
  12864. Firing rl*prefer*rvt*predict-no*H0*6
  12865. -->
  12866. (S1 ^operator O1980 = 0.9999867250014868)
  12867. Firing rl*prefer*rvt*predict-yes*H0*5
  12868. -->
  12869. (S1 ^operator O1979 = 0.1215989443698621)
  12870. Firing prefer*rvt*predict-yes*H0
  12871. -->
  12872. Firing prefer*rvt*predict-no*H0
  12873. -->
  12874. Firing elaborate*copy-dir-to-output-link
  12875. -->
  12876. (I3 ^dir R +)
  12877. inner elaboration loop at bottom goal.
  12878. Retracting elaborate*copy-see-to-output-link
  12879. -->
  12880. (I3 ^see 0 +)
  12881. Retracting propose*predict-no
  12882. -->
  12883. (O1980 ^name predict-no +)
  12884. (S1 ^operator O1980 +)
  12885. Retracting propose*predict-yes
  12886. -->
  12887. (O1979 ^name predict-yes +)
  12888. (S1 ^operator O1979 +)
  12889. Retracting elaborate*reward*based*on*reward
  12890. -->
  12891. (R993 ^value 1 +)
  12892. (R1 ^reward R993 +)
  12893. Retracting elaborate*copy-dir-to-output-link
  12894. -->
  12895. (I3 ^dir U +)
  12896. Retracting rl*prefer*rvt*predict-no*H0*2
  12897. -->
  12898. (S1 ^operator O1980 = 1.)
  12899. Retracting rl*prefer*rvt*predict-yes*H0*1
  12900. -->
  12901. (S1 ^operator O1979 = 0.)
  12902. =>WM: (13913: S1 ^operator O1982 +)
  12903. =>WM: (13912: S1 ^operator O1981 +)
  12904. =>WM: (13911: I3 ^dir R)
  12905. =>WM: (13910: O1982 ^name predict-no)
  12906. =>WM: (13909: O1981 ^name predict-yes)
  12907. =>WM: (13908: R994 ^value 1)
  12908. =>WM: (13907: R1 ^reward R994)
  12909. <=WM: (13898: S1 ^operator O1979 +)
  12910. <=WM: (13899: S1 ^operator O1980 +)
  12911. <=WM: (13900: S1 ^operator O1980)
  12912. <=WM: (13897: I3 ^dir U)
  12913. <=WM: (13893: R1 ^reward R993)
  12914. <=WM: (13896: O1980 ^name predict-no)
  12915. <=WM: (13895: O1979 ^name predict-yes)
  12916. <=WM: (13894: R993 ^value 1)
  12917. --- Inner Elaboration Phase, active level 1 (S1) ---
  12918. Firing prefer*rvt*predict-yes*H0
  12919. -->
  12920. Firing rl*prefer*rvt*predict-yes*H0*5*H1*7
  12921. -->
  12922. (S1 ^operator O1981 = -0.1512366769350551)
  12923. Firing rl*prefer*rvt*predict-yes*H0*5
  12924. -->
  12925. (S1 ^operator O1981 = 0.1215989443698621)
  12926. Firing prefer*rvt*predict-yes*H0*5*H1
  12927. -->
  12928. Firing prefer*rvt*predict-no*H0
  12929. -->
  12930. Firing rl*prefer*rvt*predict-no*H0*6
  12931. -->
  12932. (S1 ^operator O1982 = 0.9999867250014868)
  12933. inner elaboration loop at bottom goal.
  12934. Retracting rl*prefer*rvt*predict-no*H0*6
  12935. -->
  12936. (S1 ^operator O1980 = 0.9999867250014868)
  12937. Retracting rl*prefer*rvt*predict-yes*H0*5
  12938. -->
  12939. (S1 ^operator O1979 = 0.1215989443698621)
  12940. Retracting rl*prefer*rvt*predict-yes*H0*5*H1*7
  12941. -->
  12942. (S1 ^operator O1979 = -0.1512366769350551)
  12943. --- END Proposal Phase ---
  12944. --- Decision Phase ---
  12945. RL update rl*prefer*rvt*predict-no*H0*2 1 0 1 -> 1 0 1(R,m,v=1,1,0)
  12946. =>WM: (13914: S1 ^operator O1982)
  12947. 991: O: O1982 (predict-no)
  12948. --- END Decision Phase ---
  12949. --- Application Phase ---
  12950. --- Firing Productions (PE) For State At Depth 1 ---
  12951. --- Inner Elaboration Phase, active level 1 (S1) ---
  12952. Firing apply*operator
  12953. -->
  12954. (I3 ^predict-no N991 + :O )
  12955. Firing apply*operator*complete
  12956. -->
  12957. (I3 ^predict-no N990 - :O )
  12958. inner elaboration loop at bottom goal.
  12959. --- Change Working Memory (PE) ---
  12960. =>WM: (13915: I3 ^predict-no N991)
  12961. <=WM: (13902: N990 ^status complete)
  12962. <=WM: (13901: I3 ^predict-no N990)
  12963. --- Firing Productions (IE) For State At Depth 1 ---
  12964. --- Inner Elaboration Phase, active level 1 (S1) ---
  12965. Firing monitor*world
  12966. -->
  12967. I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
  12968. --- Change Working Memory (IE) ---
  12969. --- END Application Phase ---
  12970. --- Output Phase ---
  12971. ENV: Agent did: predict-no for direction R in state State-B
  12972. In State-B moving R
  12973. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  12974. predict error 0
  12975. dir: dir isU
  12976. --- END Output Phase ---
  12977. |--- Input Phase ---
  12978. =>WM: (13919: I2 ^dir U)
  12979. =>WM: (13918: I2 ^reward 1)
  12980. =>WM: (13917: I2 ^see 0)
  12981. =>WM: (13916: N991 ^status complete)
  12982. <=WM: (13905: I2 ^dir R)
  12983. <=WM: (13904: I2 ^reward 1)
  12984. <=WM: (13903: I2 ^see 0)
  12985. =>WM: (13920: I2 ^level-1 R0-root)
  12986. <=WM: (13906: I2 ^level-1 R0-root)
  12987. --- END Input Phase ---
  12988. --- Proposal Phase ---
  12989. --- Inner Elaboration Phase, active level 1 (S1) ---
  12990. Firing elaborate*copy-see-to-output-link
  12991. -->
  12992. (I3 ^see 0 +)
  12993. Firing elaborate*reward*based*on*reward
  12994. -->
  12995. (R995 ^value 1 +)
  12996. (R1 ^reward R995 +)
  12997. Firing propose*predict-yes
  12998. -->
  12999. (O1983 ^name predict-yes +)
  13000. (S1 ^operator O1983 +)
  13001. Firing propose*predict-no
  13002. -->
  13003. (O1984 ^name predict-no +)
  13004. (S1 ^operator O1984 +)
  13005. Firing rl*prefer*rvt*predict-no*H0*2
  13006. -->
  13007. (S1 ^operator O1982 = 1.)
  13008. Firing rl*prefer*rvt*predict-yes*H0*1
  13009. -->
  13010. (S1 ^operator O1981 = 0.)
  13011. Firing prefer*rvt*predict-yes*H0
  13012. -->
  13013. Firing prefer*rvt*predict-no*H0
  13014. -->
  13015. Firing elaborate*copy-dir-to-output-link
  13016. -->
  13017. (I3 ^dir U +)
  13018. inner elaboration loop at bottom goal.
  13019. Retracting elaborate*copy-see-to-output-link
  13020. -->
  13021. (I3 ^see 0 +)
  13022. Retracting propose*predict-no
  13023. -->
  13024. (O1982 ^name predict-no +)
  13025. (S1 ^operator O1982 +)
  13026. Retracting propose*predict-yes
  13027. -->
  13028. (O1981 ^name predict-yes +)
  13029. (S1 ^operator O1981 +)
  13030. Retracting elaborate*reward*based*on*reward
  13031. -->
  13032. (R994 ^value 1 +)
  13033. (R1 ^reward R994 +)
  13034. Retracting elaborate*copy-dir-to-output-link
  13035. -->
  13036. (I3 ^dir R +)
  13037. Retracting rl*prefer*rvt*predict-no*H0*6
  13038. -->
  13039. (S1 ^operator O1982 = 0.9999867250014868)
  13040. Retracting rl*prefer*rvt*predict-yes*H0*5
  13041. -->
  13042. (S1 ^operator O1981 = 0.1215989443698621)
  13043. Retracting rl*prefer*rvt*predict-yes*H0*5*H1*7
  13044. -->
  13045. (S1 ^operator O1981 = -0.1512366769350551)
  13046. =>WM: (13927: S1 ^operator O1984 +)
  13047. =>WM: (13926: S1 ^operator O1983 +)
  13048. =>WM: (13925: I3 ^dir U)
  13049. =>WM: (13924: O1984 ^name predict-no)
  13050. =>WM: (13923: O1983 ^name predict-yes)
  13051. =>WM: (13922: R995 ^value 1)
  13052. =>WM: (13921: R1 ^reward R995)
  13053. <=WM: (13912: S1 ^operator O1981 +)
  13054. <=WM: (13913: S1 ^operator O1982 +)
  13055. <=WM: (13914: S1 ^operator O1982)
  13056. <=WM: (13911: I3 ^dir R)
  13057. <=WM: (13907: R1 ^reward R994)
  13058. <=WM: (13910: O1982 ^name predict-no)
  13059. <=WM: (13909: O1981 ^name predict-yes)
  13060. <=WM: (13908: R994 ^value 1)
  13061. --- Inner Elaboration Phase, active level 1 (S1) ---
  13062. Firing prefer*rvt*predict-yes*H0
  13063. -->
  13064. Firing rl*prefer*rvt*predict-yes*H0*1
  13065. -->
  13066. (S1 ^operator O1983 = 0.)
  13067. Firing prefer*rvt*predict-no*H0
  13068. -->
  13069. Firing rl*prefer*rvt*predict-no*H0*2
  13070. -->
  13071. (S1 ^operator O1984 = 1.)
  13072. inner elaboration loop at bottom goal.
  13073. Retracting rl*prefer*rvt*predict-no*H0*2
  13074. -->
  13075. (S1 ^operator O1982 = 1.)
  13076. Retracting rl*prefer*rvt*predict-yes*H0*1
  13077. -->
  13078. (S1 ^operator O1981 = 0.)
  13079. --- END Proposal Phase ---
  13080. --- Decision Phase ---
  13081. RL update rl*prefer*rvt*predict-no*H0*6 0.999987 0 0.999987 -> 0.999989 0 0.999989(R,m,v=1,0.937853,0.0586158)
  13082. =>WM: (13928: S1 ^operator O1984)
  13083. 992: O: O1984 (predict-no)
  13084. --- END Decision Phase ---
  13085. --- Application Phase ---
  13086. --- Firing Productions (PE) For State At Depth 1 ---
  13087. --- Inner Elaboration Phase, active level 1 (S1) ---
  13088. Firing apply*operator
  13089. -->
  13090. (I3 ^predict-no N992 + :O )
  13091. Firing apply*operator*complete
  13092. -->
  13093. (I3 ^predict-no N991 - :O )
  13094. inner elaboration loop at bottom goal.
  13095. --- Change Working Memory (PE) ---
  13096. =>WM: (13929: I3 ^predict-no N992)
  13097. <=WM: (13916: N991 ^status complete)
  13098. <=WM: (13915: I3 ^predict-no N991)
  13099. --- Firing Productions (IE) For State At Depth 1 ---
  13100. --- Inner Elaboration Phase, active level 1 (S1) ---
  13101. Firing monitor*world
  13102. -->
  13103. I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
  13104. --- Change Working Memory (IE) ---
  13105. --- END Application Phase ---
  13106. --- Output Phase ---
  13107. ENV: Agent did: predict-no for direction U in state State-B
  13108. In State-B moving U
  13109. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  13110. predict error 0
  13111. dir: dir isL
  13112. --- END Output Phase ---
  13113. \---- Input Phase ---
  13114. =>WM: (13933: I2 ^dir L)
  13115. =>WM: (13932: I2 ^reward 1)
  13116. =>WM: (13931: I2 ^see 0)
  13117. =>WM: (13930: N992 ^status complete)
  13118. <=WM: (13919: I2 ^dir U)
  13119. <=WM: (13918: I2 ^reward 1)
  13120. <=WM: (13917: I2 ^see 0)
  13121. =>WM: (13934: I2 ^level-1 R0-root)
  13122. <=WM: (13920: I2 ^level-1 R0-root)
  13123. --- END Input Phase ---
  13124. --- Proposal Phase ---
  13125. --- Inner Elaboration Phase, active level 1 (S1) ---
  13126. Firing rl*prefer*rvt*predict-no*H0*4*H1*8
  13127. -->
  13128. (S1 ^operator O1984 = -0.1984300550322165)
  13129. Firing rl*prefer*rvt*predict-yes*H0*3*H1*9
  13130. -->
  13131. (S1 ^operator O1983 = 0.6091029227055655)
  13132. Firing prefer*rvt*predict-no*H0*4*H1
  13133. -->
  13134. Firing prefer*rvt*predict-yes*H0*3*H1
  13135. -->
  13136. Firing elaborate*copy-see-to-output-link
  13137. -->
  13138. (I3 ^see 0 +)
  13139. Firing elaborate*reward*based*on*reward
  13140. -->
  13141. (R996 ^value 1 +)
  13142. (R1 ^reward R996 +)
  13143. Firing propose*predict-yes
  13144. -->
  13145. (O1985 ^name predict-yes +)
  13146. (S1 ^operator O1985 +)
  13147. Firing propose*predict-no
  13148. -->
  13149. (O1986 ^name predict-no +)
  13150. (S1 ^operator O1986 +)
  13151. Firing rl*prefer*rvt*predict-no*H0*4
  13152. -->
  13153. (S1 ^operator O1984 = 0.3144988611901438)
  13154. Firing rl*prefer*rvt*predict-yes*H0*3
  13155. -->
  13156. (S1 ^operator O1983 = 0.3907675490335307)
  13157. Firing prefer*rvt*predict-yes*H0
  13158. -->
  13159. Firing prefer*rvt*predict-no*H0
  13160. -->
  13161. Firing elaborate*copy-dir-to-output-link
  13162. -->
  13163. (I3 ^dir L +)
  13164. inner elaboration loop at bottom goal.
  13165. Retracting elaborate*copy-see-to-output-link
  13166. -->
  13167. (I3 ^see 0 +)
  13168. Retracting propose*predict-no
  13169. -->
  13170. (O1984 ^name predict-no +)
  13171. (S1 ^operator O1984 +)
  13172. Retracting propose*predict-yes
  13173. -->
  13174. (O1983 ^name predict-yes +)
  13175. (S1 ^operator O1983 +)
  13176. Retracting elaborate*reward*based*on*reward
  13177. -->
  13178. (R995 ^value 1 +)
  13179. (R1 ^reward R995 +)
  13180. Retracting elaborate*copy-dir-to-output-link
  13181. -->
  13182. (I3 ^dir U +)
  13183. Retracting rl*prefer*rvt*predict-no*H0*2
  13184. -->
  13185. (S1 ^operator O1984 = 1.)
  13186. Retracting rl*prefer*rvt*predict-yes*H0*1
  13187. -->
  13188. (S1 ^operator O1983 = 0.)
  13189. =>WM: (13941: S1 ^operator O1986 +)
  13190. =>WM: (13940: S1 ^operator O1985 +)
  13191. =>WM: (13939: I3 ^dir L)
  13192. =>WM: (13938: O1986 ^name predict-no)
  13193. =>WM: (13937: O1985 ^name predict-yes)
  13194. =>WM: (13936: R996 ^value 1)
  13195. =>WM: (13935: R1 ^reward R996)
  13196. <=WM: (13926: S1 ^operator O1983 +)
  13197. <=WM: (13927: S1 ^operator O1984 +)
  13198. <=WM: (13928: S1 ^operator O1984)
  13199. <=WM: (13925: I3 ^dir U)
  13200. <=WM: (13921: R1 ^reward R995)
  13201. <=WM: (13924: O1984 ^name predict-no)
  13202. <=WM: (13923: O1983 ^name predict-yes)
  13203. <=WM: (13922: R995 ^value 1)
  13204. --- Inner Elaboration Phase, active level 1 (S1) ---
  13205. Firing prefer*rvt*predict-yes*H0
  13206. -->
  13207. Firing rl*prefer*rvt*predict-yes*H0*3*H1*9
  13208. -->
  13209. (S1 ^operator O1985 = 0.6091029227055655)
  13210. Firing rl*prefer*rvt*predict-yes*H0*3
  13211. -->
  13212. (S1 ^operator O1985 = 0.3907675490335307)
  13213. Firing prefer*rvt*predict-yes*H0*3*H1
  13214. -->
  13215. Firing prefer*rvt*predict-no*H0
  13216. -->
  13217. Firing rl*prefer*rvt*predict-no*H0*4*H1*8
  13218. -->
  13219. (S1 ^operator O1986 = -0.1984300550322165)
  13220. Firing rl*prefer*rvt*predict-no*H0*4
  13221. -->
  13222. (S1 ^operator O1986 = 0.3144988611901438)
  13223. Firing prefer*rvt*predict-no*H0*4*H1
  13224. -->
  13225. inner elaboration loop at bottom goal.
  13226. Retracting rl*prefer*rvt*predict-no*H0*4
  13227. -->
  13228. (S1 ^operator O1984 = 0.3144988611901438)
  13229. Retracting rl*prefer*rvt*predict-no*H0*4*H1*8
  13230. -->
  13231. (S1 ^operator O1984 = -0.1984300550322165)
  13232. Retracting rl*prefer*rvt*predict-yes*H0*3
  13233. -->
  13234. (S1 ^operator O1983 = 0.3907675490335307)
  13235. Retracting rl*prefer*rvt*predict-yes*H0*3*H1*9
  13236. -->
  13237. (S1 ^operator O1983 = 0.6091029227055655)
  13238. --- END Proposal Phase ---
  13239. --- Decision Phase ---
  13240. RL update rl*prefer*rvt*predict-no*H0*2 1 0 1 -> 1 0 1(R,m,v=1,1,0)
  13241. =>WM: (13942: S1 ^operator O1985)
  13242. 993: O: O1985 (predict-yes)
  13243. --- END Decision Phase ---
  13244. --- Application Phase ---
  13245. --- Firing Productions (PE) For State At Depth 1 ---
  13246. --- Inner Elaboration Phase, active level 1 (S1) ---
  13247. Firing apply*operator
  13248. -->
  13249. (I3 ^predict-yes N993 + :O )
  13250. Firing apply*operator*complete
  13251. -->
  13252. (I3 ^predict-no N992 - :O )
  13253. inner elaboration loop at bottom goal.
  13254. --- Change Working Memory (PE) ---
  13255. =>WM: (13943: I3 ^predict-yes N993)
  13256. <=WM: (13930: N992 ^status complete)
  13257. <=WM: (13929: I3 ^predict-no N992)
  13258. --- Firing Productions (IE) For State At Depth 1 ---
  13259. --- Inner Elaboration Phase, active level 1 (S1) ---
  13260. Firing monitor*world
  13261. -->
  13262. I see 1 and I'm going to do: predict-yes inner elaboration loop at bottom goal.
  13263. --- Change Working Memory (IE) ---
  13264. --- END Application Phase ---
  13265. --- Output Phase ---
  13266. ENV: Agent did: predict-yes for direction L in state State-B
  13267. In State-B moving L
  13268. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  13269. predict error 0
  13270. dir: dir isU
  13271. --- END Output Phase ---
  13272. /|--- Input Phase ---
  13273. =>WM: (13947: I2 ^dir U)
  13274. =>WM: (13946: I2 ^reward 1)
  13275. =>WM: (13945: I2 ^see 1)
  13276. =>WM: (13944: N993 ^status complete)
  13277. <=WM: (13933: I2 ^dir L)
  13278. <=WM: (13932: I2 ^reward 1)
  13279. <=WM: (13931: I2 ^see 0)
  13280. =>WM: (13948: I2 ^level-1 L1-root)
  13281. <=WM: (13934: I2 ^level-1 R0-root)
  13282. --- END Input Phase ---
  13283. --- Proposal Phase ---
  13284. --- Inner Elaboration Phase, active level 1 (S1) ---
  13285. Firing elaborate*copy-see-to-output-link
  13286. -->
  13287. (I3 ^see 1 +)
  13288. Firing elaborate*reward*based*on*reward
  13289. -->
  13290. (R997 ^value 1 +)
  13291. (R1 ^reward R997 +)
  13292. Firing propose*predict-yes
  13293. -->
  13294. (O1987 ^name predict-yes +)
  13295. (S1 ^operator O1987 +)
  13296. Firing propose*predict-no
  13297. -->
  13298. (O1988 ^name predict-no +)
  13299. (S1 ^operator O1988 +)
  13300. Firing rl*prefer*rvt*predict-no*H0*2
  13301. -->
  13302. (S1 ^operator O1986 = 1.)
  13303. Firing rl*prefer*rvt*predict-yes*H0*1
  13304. -->
  13305. (S1 ^operator O1985 = 0.)
  13306. Firing prefer*rvt*predict-yes*H0
  13307. -->
  13308. Firing prefer*rvt*predict-no*H0
  13309. -->
  13310. Firing elaborate*copy-dir-to-output-link
  13311. -->
  13312. (I3 ^dir U +)
  13313. inner elaboration loop at bottom goal.
  13314. Retracting elaborate*copy-see-to-output-link
  13315. -->
  13316. (I3 ^see 0 +)
  13317. Retracting propose*predict-no
  13318. -->
  13319. (O1986 ^name predict-no +)
  13320. (S1 ^operator O1986 +)
  13321. Retracting propose*predict-yes
  13322. -->
  13323. (O1985 ^name predict-yes +)
  13324. (S1 ^operator O1985 +)
  13325. Retracting elaborate*reward*based*on*reward
  13326. -->
  13327. (R996 ^value 1 +)
  13328. (R1 ^reward R996 +)
  13329. Retracting elaborate*copy-dir-to-output-link
  13330. -->
  13331. (I3 ^dir L +)
  13332. Retracting rl*prefer*rvt*predict-no*H0*4
  13333. -->
  13334. (S1 ^operator O1986 = 0.3144988611901438)
  13335. Retracting rl*prefer*rvt*predict-no*H0*4*H1*8
  13336. -->
  13337. (S1 ^operator O1986 = -0.1984300550322165)
  13338. Retracting rl*prefer*rvt*predict-yes*H0*3
  13339. -->
  13340. (S1 ^operator O1985 = 0.3907675490335307)
  13341. Retracting rl*prefer*rvt*predict-yes*H0*3*H1*9
  13342. -->
  13343. (S1 ^operator O1985 = 0.6091029227055655)
  13344. =>WM: (13956: S1 ^operator O1988 +)
  13345. =>WM: (13955: S1 ^operator O1987 +)
  13346. =>WM: (13954: I3 ^dir U)
  13347. =>WM: (13953: O1988 ^name predict-no)
  13348. =>WM: (13952: O1987 ^name predict-yes)
  13349. =>WM: (13951: R997 ^value 1)
  13350. =>WM: (13950: R1 ^reward R997)
  13351. =>WM: (13949: I3 ^see 1)
  13352. <=WM: (13940: S1 ^operator O1985 +)
  13353. <=WM: (13942: S1 ^operator O1985)
  13354. <=WM: (13941: S1 ^operator O1986 +)
  13355. <=WM: (13939: I3 ^dir L)
  13356. <=WM: (13935: R1 ^reward R996)
  13357. <=WM: (13892: I3 ^see 0)
  13358. <=WM: (13938: O1986 ^name predict-no)
  13359. <=WM: (13937: O1985 ^name predict-yes)
  13360. <=WM: (13936: R996 ^value 1)
  13361. --- Inner Elaboration Phase, active level 1 (S1) ---
  13362. Firing prefer*rvt*predict-yes*H0
  13363. -->
  13364. Firing rl*prefer*rvt*predict-yes*H0*1
  13365. -->
  13366. (S1 ^operator O1987 = 0.)
  13367. Firing prefer*rvt*predict-no*H0
  13368. -->
  13369. Firing rl*prefer*rvt*predict-no*H0*2
  13370. -->
  13371. (S1 ^operator O1988 = 1.)
  13372. inner elaboration loop at bottom goal.
  13373. Retracting rl*prefer*rvt*predict-no*H0*2
  13374. -->
  13375. (S1 ^operator O1986 = 1.)
  13376. Retracting rl*prefer*rvt*predict-yes*H0*1
  13377. -->
  13378. (S1 ^operator O1985 = 0.)
  13379. --- END Proposal Phase ---
  13380. --- Decision Phase ---
  13381. RL update rl*prefer*rvt*predict-yes*H0*3 0.472315 -0.0815474 0.390768 -> 0.472324 -0.0815458 0.390778(R,m,v=1,0.94375,0.0534198)
  13382. RL update rl*prefer*rvt*predict-yes*H0*3*H1*9 0.527575 0.0815283 0.609103 -> 0.527585 0.0815301 0.609115(R,m,v=1,1,0)
  13383. =>WM: (13957: S1 ^operator O1988)
  13384. 994: O: O1988 (predict-no)
  13385. --- END Decision Phase ---
  13386. --- Application Phase ---
  13387. --- Firing Productions (PE) For State At Depth 1 ---
  13388. --- Inner Elaboration Phase, active level 1 (S1) ---
  13389. Firing apply*operator
  13390. -->
  13391. (I3 ^predict-no N994 + :O )
  13392. Firing apply*operator*complete
  13393. -->
  13394. (I3 ^predict-yes N993 - :O )
  13395. inner elaboration loop at bottom goal.
  13396. --- Change Working Memory (PE) ---
  13397. =>WM: (13958: I3 ^predict-no N994)
  13398. <=WM: (13944: N993 ^status complete)
  13399. <=WM: (13943: I3 ^predict-yes N993)
  13400. --- Firing Productions (IE) For State At Depth 1 ---
  13401. --- Inner Elaboration Phase, active level 1 (S1) ---
  13402. Firing monitor*world
  13403. -->
  13404. I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
  13405. --- Change Working Memory (IE) ---
  13406. --- END Application Phase ---
  13407. --- Output Phase ---
  13408. ENV: Agent did: predict-no for direction U in state State-A
  13409. In State-A moving U
  13410. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  13411. predict error 0
  13412. dir: dir isL
  13413. --- END Output Phase ---
  13414. \-/--- Input Phase ---
  13415. =>WM: (13962: I2 ^dir L)
  13416. =>WM: (13961: I2 ^reward 1)
  13417. =>WM: (13960: I2 ^see 0)
  13418. =>WM: (13959: N994 ^status complete)
  13419. <=WM: (13947: I2 ^dir U)
  13420. <=WM: (13946: I2 ^reward 1)
  13421. <=WM: (13945: I2 ^see 1)
  13422. =>WM: (13963: I2 ^level-1 L1-root)
  13423. <=WM: (13948: I2 ^level-1 L1-root)
  13424. --- END Input Phase ---
  13425. --- Proposal Phase ---
  13426. --- Inner Elaboration Phase, active level 1 (S1) ---
  13427. Firing rl*prefer*rvt*predict-yes*H0*3*H1*11
  13428. -->
  13429. (S1 ^operator O1987 = -0.2062723012911647)
  13430. Firing rl*prefer*rvt*predict-no*H0*4*H1*10
  13431. -->
  13432. (S1 ^operator O1988 = 0.685533297663165)
  13433. Firing prefer*rvt*predict-no*H0*4*H1
  13434. -->
  13435. Firing prefer*rvt*predict-yes*H0*3*H1
  13436. -->
  13437. Firing elaborate*copy-see-to-output-link
  13438. -->
  13439. (I3 ^see 0 +)
  13440. Firing elaborate*reward*based*on*reward
  13441. -->
  13442. (R998 ^value 1 +)
  13443. (R1 ^reward R998 +)
  13444. Firing propose*predict-yes
  13445. -->
  13446. (O1989 ^name predict-yes +)
  13447. (S1 ^operator O1989 +)
  13448. Firing propose*predict-no
  13449. -->
  13450. (O1990 ^name predict-no +)
  13451. (S1 ^operator O1990 +)
  13452. Firing rl*prefer*rvt*predict-no*H0*4
  13453. -->
  13454. (S1 ^operator O1988 = 0.3144988611901438)
  13455. Firing rl*prefer*rvt*predict-yes*H0*3
  13456. -->
  13457. (S1 ^operator O1987 = 0.3907782094907327)
  13458. Firing prefer*rvt*predict-yes*H0
  13459. -->
  13460. Firing prefer*rvt*predict-no*H0
  13461. -->
  13462. Firing elaborate*copy-dir-to-output-link
  13463. -->
  13464. (I3 ^dir L +)
  13465. inner elaboration loop at bottom goal.
  13466. Retracting elaborate*copy-see-to-output-link
  13467. -->
  13468. (I3 ^see 1 +)
  13469. Retracting propose*predict-no
  13470. -->
  13471. (O1988 ^name predict-no +)
  13472. (S1 ^operator O1988 +)
  13473. Retracting propose*predict-yes
  13474. -->
  13475. (O1987 ^name predict-yes +)
  13476. (S1 ^operator O1987 +)
  13477. Retracting elaborate*reward*based*on*reward
  13478. -->
  13479. (R997 ^value 1 +)
  13480. (R1 ^reward R997 +)
  13481. Retracting elaborate*copy-dir-to-output-link
  13482. -->
  13483. (I3 ^dir U +)
  13484. Retracting rl*prefer*rvt*predict-no*H0*2
  13485. -->
  13486. (S1 ^operator O1988 = 1.)
  13487. Retracting rl*prefer*rvt*predict-yes*H0*1
  13488. -->
  13489. (S1 ^operator O1987 = 0.)
  13490. =>WM: (13971: S1 ^operator O1990 +)
  13491. =>WM: (13970: S1 ^operator O1989 +)
  13492. =>WM: (13969: I3 ^dir L)
  13493. =>WM: (13968: O1990 ^name predict-no)
  13494. =>WM: (13967: O1989 ^name predict-yes)
  13495. =>WM: (13966: R998 ^value 1)
  13496. =>WM: (13965: R1 ^reward R998)
  13497. =>WM: (13964: I3 ^see 0)
  13498. <=WM: (13955: S1 ^operator O1987 +)
  13499. <=WM: (13956: S1 ^operator O1988 +)
  13500. <=WM: (13957: S1 ^operator O1988)
  13501. <=WM: (13954: I3 ^dir U)
  13502. <=WM: (13950: R1 ^reward R997)
  13503. <=WM: (13949: I3 ^see 1)
  13504. <=WM: (13953: O1988 ^name predict-no)
  13505. <=WM: (13952: O1987 ^name predict-yes)
  13506. <=WM: (13951: R997 ^value 1)
  13507. --- Inner Elaboration Phase, active level 1 (S1) ---
  13508. Firing prefer*rvt*predict-yes*H0
  13509. -->
  13510. Firing rl*prefer*rvt*predict-yes*H0*3*H1*11
  13511. -->
  13512. (S1 ^operator O1989 = -0.2062723012911647)
  13513. Firing rl*prefer*rvt*predict-yes*H0*3
  13514. -->
  13515. (S1 ^operator O1989 = 0.3907782094907327)
  13516. Firing prefer*rvt*predict-yes*H0*3*H1
  13517. -->
  13518. Firing prefer*rvt*predict-no*H0
  13519. -->
  13520. Firing rl*prefer*rvt*predict-no*H0*4*H1*10
  13521. -->
  13522. (S1 ^operator O1990 = 0.685533297663165)
  13523. Firing rl*prefer*rvt*predict-no*H0*4
  13524. -->
  13525. (S1 ^operator O1990 = 0.3144988611901438)
  13526. Firing prefer*rvt*predict-no*H0*4*H1
  13527. -->
  13528. inner elaboration loop at bottom goal.
  13529. Retracting rl*prefer*rvt*predict-no*H0*4
  13530. -->
  13531. (S1 ^operator O1988 = 0.3144988611901438)
  13532. Retracting rl*prefer*rvt*predict-no*H0*4*H1*10
  13533. -->
  13534. (S1 ^operator O1988 = 0.685533297663165)
  13535. Retracting rl*prefer*rvt*predict-yes*H0*3
  13536. -->
  13537. (S1 ^operator O1987 = 0.3907782094907327)
  13538. Retracting rl*prefer*rvt*predict-yes*H0*3*H1*11
  13539. -->
  13540. (S1 ^operator O1987 = -0.2062723012911647)
  13541. --- END Proposal Phase ---
  13542. --- Decision Phase ---
  13543. RL update rl*prefer*rvt*predict-no*H0*2 1 0 1 -> 1 0 1(R,m,v=1,1,0)
  13544. =>WM: (13972: S1 ^operator O1990)
  13545. 995: O: O1990 (predict-no)
  13546. --- END Decision Phase ---
  13547. --- Application Phase ---
  13548. --- Firing Productions (PE) For State At Depth 1 ---
  13549. --- Inner Elaboration Phase, active level 1 (S1) ---
  13550. Firing apply*operator
  13551. -->
  13552. (I3 ^predict-no N995 + :O )
  13553. Firing apply*operator*complete
  13554. -->
  13555. (I3 ^predict-no N994 - :O )
  13556. inner elaboration loop at bottom goal.
  13557. --- Change Working Memory (PE) ---
  13558. =>WM: (13973: I3 ^predict-no N995)
  13559. <=WM: (13959: N994 ^status complete)
  13560. <=WM: (13958: I3 ^predict-no N994)
  13561. --- Firing Productions (IE) For State At Depth 1 ---
  13562. --- Inner Elaboration Phase, active level 1 (S1) ---
  13563. Firing monitor*world
  13564. -->
  13565. I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
  13566. --- Change Working Memory (IE) ---
  13567. --- END Application Phase ---
  13568. --- Output Phase ---
  13569. ENV: Agent did: predict-no for direction L in state State-A
  13570. In State-A moving L
  13571. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  13572. predict error 0
  13573. dir: dir isL
  13574. --- END Output Phase ---
  13575. |\---- Input Phase ---
  13576. =>WM: (13977: I2 ^dir L)
  13577. =>WM: (13976: I2 ^reward 1)
  13578. =>WM: (13975: I2 ^see 0)
  13579. =>WM: (13974: N995 ^status complete)
  13580. <=WM: (13962: I2 ^dir L)
  13581. <=WM: (13961: I2 ^reward 1)
  13582. <=WM: (13960: I2 ^see 0)
  13583. =>WM: (13978: I2 ^level-1 L0-root)
  13584. <=WM: (13963: I2 ^level-1 L1-root)
  13585. --- END Input Phase ---
  13586. --- Proposal Phase ---
  13587. --- Inner Elaboration Phase, active level 1 (S1) ---
  13588. Firing rl*prefer*rvt*predict-yes*H0*3*H1*13
  13589. -->
  13590. (S1 ^operator O1989 = -0.208713043145708)
  13591. Firing rl*prefer*rvt*predict-no*H0*4*H1*12
  13592. -->
  13593. (S1 ^operator O1990 = 0.6854257503571404)
  13594. Firing prefer*rvt*predict-no*H0*4*H1
  13595. -->
  13596. Firing prefer*rvt*predict-yes*H0*3*H1
  13597. -->
  13598. Firing elaborate*copy-see-to-output-link
  13599. -->
  13600. (I3 ^see 0 +)
  13601. Firing elaborate*reward*based*on*reward
  13602. -->
  13603. (R999 ^value 1 +)
  13604. (R1 ^reward R999 +)
  13605. Firing propose*predict-yes
  13606. -->
  13607. (O1991 ^name predict-yes +)
  13608. (S1 ^operator O1991 +)
  13609. Firing propose*predict-no
  13610. -->
  13611. (O1992 ^name predict-no +)
  13612. (S1 ^operator O1992 +)
  13613. Firing rl*prefer*rvt*predict-no*H0*4
  13614. -->
  13615. (S1 ^operator O1990 = 0.3144988611901438)
  13616. Firing rl*prefer*rvt*predict-yes*H0*3
  13617. -->
  13618. (S1 ^operator O1989 = 0.3907782094907327)
  13619. Firing prefer*rvt*predict-yes*H0
  13620. -->
  13621. Firing prefer*rvt*predict-no*H0
  13622. -->
  13623. Firing elaborate*copy-dir-to-output-link
  13624. -->
  13625. (I3 ^dir L +)
  13626. inner elaboration loop at bottom goal.
  13627. Retracting elaborate*copy-see-to-output-link
  13628. -->
  13629. (I3 ^see 0 +)
  13630. Retracting propose*predict-no
  13631. -->
  13632. (O1990 ^name predict-no +)
  13633. (S1 ^operator O1990 +)
  13634. Retracting propose*predict-yes
  13635. -->
  13636. (O1989 ^name predict-yes +)
  13637. (S1 ^operator O1989 +)
  13638. Retracting elaborate*reward*based*on*reward
  13639. -->
  13640. (R998 ^value 1 +)
  13641. (R1 ^reward R998 +)
  13642. Retracting elaborate*copy-dir-to-output-link
  13643. -->
  13644. (I3 ^dir L +)
  13645. Retracting rl*prefer*rvt*predict-no*H0*4
  13646. -->
  13647. (S1 ^operator O1990 = 0.3144988611901438)
  13648. Retracting rl*prefer*rvt*predict-no*H0*4*H1*10
  13649. -->
  13650. (S1 ^operator O1990 = 0.685533297663165)
  13651. Retracting rl*prefer*rvt*predict-yes*H0*3
  13652. -->
  13653. (S1 ^operator O1989 = 0.3907782094907327)
  13654. Retracting rl*prefer*rvt*predict-yes*H0*3*H1*11
  13655. -->
  13656. (S1 ^operator O1989 = -0.2062723012911647)
  13657. =>WM: (13984: S1 ^operator O1992 +)
  13658. =>WM: (13983: S1 ^operator O1991 +)
  13659. =>WM: (13982: O1992 ^name predict-no)
  13660. =>WM: (13981: O1991 ^name predict-yes)
  13661. =>WM: (13980: R999 ^value 1)
  13662. =>WM: (13979: R1 ^reward R999)
  13663. <=WM: (13970: S1 ^operator O1989 +)
  13664. <=WM: (13971: S1 ^operator O1990 +)
  13665. <=WM: (13972: S1 ^operator O1990)
  13666. <=WM: (13965: R1 ^reward R998)
  13667. <=WM: (13968: O1990 ^name predict-no)
  13668. <=WM: (13967: O1989 ^name predict-yes)
  13669. <=WM: (13966: R998 ^value 1)
  13670. --- Inner Elaboration Phase, active level 1 (S1) ---
  13671. Firing prefer*rvt*predict-yes*H0
  13672. -->
  13673. Firing rl*prefer*rvt*predict-yes*H0*3
  13674. -->
  13675. (S1 ^operator O1991 = 0.3907782094907327)
  13676. Firing prefer*rvt*predict-yes*H0*3*H1
  13677. -->
  13678. Firing rl*prefer*rvt*predict-yes*H0*3*H1*13
  13679. -->
  13680. (S1 ^operator O1991 = -0.208713043145708)
  13681. Firing prefer*rvt*predict-no*H0
  13682. -->
  13683. Firing rl*prefer*rvt*predict-no*H0*4
  13684. -->
  13685. (S1 ^operator O1992 = 0.3144988611901438)
  13686. Firing prefer*rvt*predict-no*H0*4*H1
  13687. -->
  13688. Firing rl*prefer*rvt*predict-no*H0*4*H1*12
  13689. -->
  13690. (S1 ^operator O1992 = 0.6854257503571404)
  13691. inner elaboration loop at bottom goal.
  13692. Retracting rl*prefer*rvt*predict-no*H0*4
  13693. -->
  13694. (S1 ^operator O1990 = 0.3144988611901438)
  13695. Retracting rl*prefer*rvt*predict-no*H0*4*H1*12
  13696. -->
  13697. (S1 ^operator O1990 = 0.6854257503571404)
  13698. Retracting rl*prefer*rvt*predict-yes*H0*3
  13699. -->
  13700. (S1 ^operator O1989 = 0.3907782094907327)
  13701. Retracting rl*prefer*rvt*predict-yes*H0*3*H1*13
  13702. -->
  13703. (S1 ^operator O1989 = -0.208713043145708)
  13704. --- END Proposal Phase ---
  13705. --- Decision Phase ---
  13706. RL update rl*prefer*rvt*predict-no*H0*4 0.478548 -0.164049 0.314499 -> 0.478545 -0.164049 0.314496(R,m,v=1,0.922581,0.0718894)
  13707. RL update rl*prefer*rvt*predict-no*H0*4*H1*10 0.521482 0.164052 0.685533 -> 0.521479 0.164051 0.68553(R,m,v=1,1,0)
  13708. =>WM: (13985: S1 ^operator O1992)
  13709. 996: O: O1992 (predict-no)
  13710. --- END Decision Phase ---
  13711. --- Application Phase ---
  13712. --- Firing Productions (PE) For State At Depth 1 ---
  13713. --- Inner Elaboration Phase, active level 1 (S1) ---
  13714. Firing apply*operator
  13715. -->
  13716. (I3 ^predict-no N996 + :O )
  13717. Firing apply*operator*complete
  13718. -->
  13719. (I3 ^predict-no N995 - :O )
  13720. inner elaboration loop at bottom goal.
  13721. --- Change Working Memory (PE) ---
  13722. =>WM: (13986: I3 ^predict-no N996)
  13723. <=WM: (13974: N995 ^status complete)
  13724. <=WM: (13973: I3 ^predict-no N995)
  13725. --- Firing Productions (IE) For State At Depth 1 ---
  13726. --- Inner Elaboration Phase, active level 1 (S1) ---
  13727. Firing monitor*world
  13728. -->
  13729. I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
  13730. --- Change Working Memory (IE) ---
  13731. --- END Application Phase ---
  13732. --- Output Phase ---
  13733. ENV: Agent did: predict-no for direction L in state State-A
  13734. In State-A moving L
  13735. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  13736. predict error 0
  13737. dir: dir isL
  13738. --- END Output Phase ---
  13739. /|\--- Input Phase ---
  13740. =>WM: (13990: I2 ^dir L)
  13741. =>WM: (13989: I2 ^reward 1)
  13742. =>WM: (13988: I2 ^see 0)
  13743. =>WM: (13987: N996 ^status complete)
  13744. <=WM: (13977: I2 ^dir L)
  13745. <=WM: (13976: I2 ^reward 1)
  13746. <=WM: (13975: I2 ^see 0)
  13747. =>WM: (13991: I2 ^level-1 L0-root)
  13748. <=WM: (13978: I2 ^level-1 L0-root)
  13749. --- END Input Phase ---
  13750. --- Proposal Phase ---
  13751. --- Inner Elaboration Phase, active level 1 (S1) ---
  13752. Firing rl*prefer*rvt*predict-yes*H0*3*H1*13
  13753. -->
  13754. (S1 ^operator O1991 = -0.208713043145708)
  13755. Firing rl*prefer*rvt*predict-no*H0*4*H1*12
  13756. -->
  13757. (S1 ^operator O1992 = 0.6854257503571404)
  13758. Firing prefer*rvt*predict-no*H0*4*H1
  13759. -->
  13760. Firing prefer*rvt*predict-yes*H0*3*H1
  13761. -->
  13762. Firing elaborate*copy-see-to-output-link
  13763. -->
  13764. (I3 ^see 0 +)
  13765. Firing elaborate*reward*based*on*reward
  13766. -->
  13767. (R1000 ^value 1 +)
  13768. (R1 ^reward R1000 +)
  13769. Firing propose*predict-yes
  13770. -->
  13771. (O1993 ^name predict-yes +)
  13772. (S1 ^operator O1993 +)
  13773. Firing propose*predict-no
  13774. -->
  13775. (O1994 ^name predict-no +)
  13776. (S1 ^operator O1994 +)
  13777. Firing rl*prefer*rvt*predict-no*H0*4
  13778. -->
  13779. (S1 ^operator O1992 = 0.3144962005421928)
  13780. Firing rl*prefer*rvt*predict-yes*H0*3
  13781. -->
  13782. (S1 ^operator O1991 = 0.3907782094907327)
  13783. Firing prefer*rvt*predict-yes*H0
  13784. -->
  13785. Firing prefer*rvt*predict-no*H0
  13786. -->
  13787. Firing elaborate*copy-dir-to-output-link
  13788. -->
  13789. (I3 ^dir L +)
  13790. inner elaboration loop at bottom goal.
  13791. Retracting elaborate*copy-see-to-output-link
  13792. -->
  13793. (I3 ^see 0 +)
  13794. Retracting propose*predict-no
  13795. -->
  13796. (O1992 ^name predict-no +)
  13797. (S1 ^operator O1992 +)
  13798. Retracting propose*predict-yes
  13799. -->
  13800. (O1991 ^name predict-yes +)
  13801. (S1 ^operator O1991 +)
  13802. Retracting elaborate*reward*based*on*reward
  13803. -->
  13804. (R999 ^value 1 +)
  13805. (R1 ^reward R999 +)
  13806. Retracting elaborate*copy-dir-to-output-link
  13807. -->
  13808. (I3 ^dir L +)
  13809. Retracting rl*prefer*rvt*predict-no*H0*4*H1*12
  13810. -->
  13811. (S1 ^operator O1992 = 0.6854257503571404)
  13812. Retracting rl*prefer*rvt*predict-no*H0*4
  13813. -->
  13814. (S1 ^operator O1992 = 0.3144962005421928)
  13815. Retracting rl*prefer*rvt*predict-yes*H0*3*H1*13
  13816. -->
  13817. (S1 ^operator O1991 = -0.208713043145708)
  13818. Retracting rl*prefer*rvt*predict-yes*H0*3
  13819. -->
  13820. (S1 ^operator O1991 = 0.3907782094907327)
  13821. =>WM: (13997: S1 ^operator O1994 +)
  13822. =>WM: (13996: S1 ^operator O1993 +)
  13823. =>WM: (13995: O1994 ^name predict-no)
  13824. =>WM: (13994: O1993 ^name predict-yes)
  13825. =>WM: (13993: R1000 ^value 1)
  13826. =>WM: (13992: R1 ^reward R1000)
  13827. <=WM: (13983: S1 ^operator O1991 +)
  13828. <=WM: (13984: S1 ^operator O1992 +)
  13829. <=WM: (13985: S1 ^operator O1992)
  13830. <=WM: (13979: R1 ^reward R999)
  13831. <=WM: (13982: O1992 ^name predict-no)
  13832. <=WM: (13981: O1991 ^name predict-yes)
  13833. <=WM: (13980: R999 ^value 1)
  13834. --- Inner Elaboration Phase, active level 1 (S1) ---
  13835. Firing prefer*rvt*predict-yes*H0
  13836. -->
  13837. Firing rl*prefer*rvt*predict-yes*H0*3
  13838. -->
  13839. (S1 ^operator O1993 = 0.3907782094907327)
  13840. Firing prefer*rvt*predict-yes*H0*3*H1
  13841. -->
  13842. Firing rl*prefer*rvt*predict-yes*H0*3*H1*13
  13843. -->
  13844. (S1 ^operator O1993 = -0.208713043145708)
  13845. Firing prefer*rvt*predict-no*H0
  13846. -->
  13847. Firing rl*prefer*rvt*predict-no*H0*4
  13848. -->
  13849. (S1 ^operator O1994 = 0.3144962005421928)
  13850. Firing prefer*rvt*predict-no*H0*4*H1
  13851. -->
  13852. Firing rl*prefer*rvt*predict-no*H0*4*H1*12
  13853. -->
  13854. (S1 ^operator O1994 = 0.6854257503571404)
  13855. inner elaboration loop at bottom goal.
  13856. Retracting rl*prefer*rvt*predict-no*H0*4
  13857. -->
  13858. (S1 ^operator O1992 = 0.3144962005421928)
  13859. Retracting rl*prefer*rvt*predict-no*H0*4*H1*12
  13860. -->
  13861. (S1 ^operator O1992 = 0.6854257503571404)
  13862. Retracting rl*prefer*rvt*predict-yes*H0*3
  13863. -->
  13864. (S1 ^operator O1991 = 0.3907782094907327)
  13865. Retracting rl*prefer*rvt*predict-yes*H0*3*H1*13
  13866. -->
  13867. (S1 ^operator O1991 = -0.208713043145708)
  13868. --- END Proposal Phase ---
  13869. --- Decision Phase ---
  13870. RL update rl*prefer*rvt*predict-no*H0*4 0.478545 -0.164049 0.314496 -> 0.478551 -0.164048 0.314503(R,m,v=1,0.923077,0.071464)
  13871. RL update rl*prefer*rvt*predict-no*H0*4*H1*12 0.521384 0.164042 0.685426 -> 0.521391 0.164042 0.685433(R,m,v=1,1,0)
  13872. =>WM: (13998: S1 ^operator O1994)
  13873. 997: O: O1994 (predict-no)
  13874. --- END Decision Phase ---
  13875. --- Application Phase ---
  13876. --- Firing Productions (PE) For State At Depth 1 ---
  13877. --- Inner Elaboration Phase, active level 1 (S1) ---
  13878. Firing apply*operator
  13879. -->
  13880. (I3 ^predict-no N997 + :O )
  13881. Firing apply*operator*complete
  13882. -->
  13883. (I3 ^predict-no N996 - :O )
  13884. inner elaboration loop at bottom goal.
  13885. --- Change Working Memory (PE) ---
  13886. =>WM: (13999: I3 ^predict-no N997)
  13887. <=WM: (13987: N996 ^status complete)
  13888. <=WM: (13986: I3 ^predict-no N996)
  13889. --- Firing Productions (IE) For State At Depth 1 ---
  13890. --- Inner Elaboration Phase, active level 1 (S1) ---
  13891. Firing monitor*world
  13892. -->
  13893. I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
  13894. --- Change Working Memory (IE) ---
  13895. --- END Application Phase ---
  13896. --- Output Phase ---
  13897. ENV: Agent did: predict-no for direction L in state State-A
  13898. In State-A moving L
  13899. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  13900. predict error 0
  13901. dir: dir isU
  13902. --- END Output Phase ---
  13903. -/|--- Input Phase ---
  13904. =>WM: (14003: I2 ^dir U)
  13905. =>WM: (14002: I2 ^reward 1)
  13906. =>WM: (14001: I2 ^see 0)
  13907. =>WM: (14000: N997 ^status complete)
  13908. <=WM: (13990: I2 ^dir L)
  13909. <=WM: (13989: I2 ^reward 1)
  13910. <=WM: (13988: I2 ^see 0)
  13911. =>WM: (14004: I2 ^level-1 L0-root)
  13912. <=WM: (13991: I2 ^level-1 L0-root)
  13913. --- END Input Phase ---
  13914. --- Proposal Phase ---
  13915. --- Inner Elaboration Phase, active level 1 (S1) ---
  13916. Firing elaborate*copy-see-to-output-link
  13917. -->
  13918. (I3 ^see 0 +)
  13919. Firing elaborate*reward*based*on*reward
  13920. -->
  13921. (R1001 ^value 1 +)
  13922. (R1 ^reward R1001 +)
  13923. Firing propose*predict-yes
  13924. -->
  13925. (O1995 ^name predict-yes +)
  13926. (S1 ^operator O1995 +)
  13927. Firing propose*predict-no
  13928. -->
  13929. (O1996 ^name predict-no +)
  13930. (S1 ^operator O1996 +)
  13931. Firing rl*prefer*rvt*predict-no*H0*2
  13932. -->
  13933. (S1 ^operator O1994 = 1.)
  13934. Firing rl*prefer*rvt*predict-yes*H0*1
  13935. -->
  13936. (S1 ^operator O1993 = 0.)
  13937. Firing prefer*rvt*predict-yes*H0
  13938. -->
  13939. Firing prefer*rvt*predict-no*H0
  13940. -->
  13941. Firing elaborate*copy-dir-to-output-link
  13942. -->
  13943. (I3 ^dir U +)
  13944. inner elaboration loop at bottom goal.
  13945. Retracting elaborate*copy-see-to-output-link
  13946. -->
  13947. (I3 ^see 0 +)
  13948. Retracting propose*predict-no
  13949. -->
  13950. (O1994 ^name predict-no +)
  13951. (S1 ^operator O1994 +)
  13952. Retracting propose*predict-yes
  13953. -->
  13954. (O1993 ^name predict-yes +)
  13955. (S1 ^operator O1993 +)
  13956. Retracting elaborate*reward*based*on*reward
  13957. -->
  13958. (R1000 ^value 1 +)
  13959. (R1 ^reward R1000 +)
  13960. Retracting elaborate*copy-dir-to-output-link
  13961. -->
  13962. (I3 ^dir L +)
  13963. Retracting rl*prefer*rvt*predict-no*H0*4*H1*12
  13964. -->
  13965. (S1 ^operator O1994 = 0.6854332700385593)
  13966. Retracting rl*prefer*rvt*predict-no*H0*4
  13967. -->
  13968. (S1 ^operator O1994 = 0.3145026510346156)
  13969. Retracting rl*prefer*rvt*predict-yes*H0*3*H1*13
  13970. -->
  13971. (S1 ^operator O1993 = -0.208713043145708)
  13972. Retracting rl*prefer*rvt*predict-yes*H0*3
  13973. -->
  13974. (S1 ^operator O1993 = 0.3907782094907327)
  13975. =>WM: (14011: S1 ^operator O1996 +)
  13976. =>WM: (14010: S1 ^operator O1995 +)
  13977. =>WM: (14009: I3 ^dir U)
  13978. =>WM: (14008: O1996 ^name predict-no)
  13979. =>WM: (14007: O1995 ^name predict-yes)
  13980. =>WM: (14006: R1001 ^value 1)
  13981. =>WM: (14005: R1 ^reward R1001)
  13982. <=WM: (13996: S1 ^operator O1993 +)
  13983. <=WM: (13997: S1 ^operator O1994 +)
  13984. <=WM: (13998: S1 ^operator O1994)
  13985. <=WM: (13969: I3 ^dir L)
  13986. <=WM: (13992: R1 ^reward R1000)
  13987. <=WM: (13995: O1994 ^name predict-no)
  13988. <=WM: (13994: O1993 ^name predict-yes)
  13989. <=WM: (13993: R1000 ^value 1)
  13990. --- Inner Elaboration Phase, active level 1 (S1) ---
  13991. Firing prefer*rvt*predict-yes*H0
  13992. -->
  13993. Firing rl*prefer*rvt*predict-yes*H0*1
  13994. -->
  13995. (S1 ^operator O1995 = 0.)
  13996. Firing prefer*rvt*predict-no*H0
  13997. -->
  13998. Firing rl*prefer*rvt*predict-no*H0*2
  13999. -->
  14000. (S1 ^operator O1996 = 1.)
  14001. inner elaboration loop at bottom goal.
  14002. Retracting rl*prefer*rvt*predict-no*H0*2
  14003. -->
  14004. (S1 ^operator O1994 = 1.)
  14005. Retracting rl*prefer*rvt*predict-yes*H0*1
  14006. -->
  14007. (S1 ^operator O1993 = 0.)
  14008. --- END Proposal Phase ---
  14009. --- Decision Phase ---
  14010. RL update rl*prefer*rvt*predict-no*H0*4 0.478551 -0.164048 0.314503 -> 0.478556 -0.164048 0.314508(R,m,v=1,0.923567,0.0710436)
  14011. RL update rl*prefer*rvt*predict-no*H0*4*H1*12 0.521391 0.164042 0.685433 -> 0.521396 0.164043 0.685439(R,m,v=1,1,0)
  14012. =>WM: (14012: S1 ^operator O1996)
  14013. 998: O: O1996 (predict-no)
  14014. --- END Decision Phase ---
  14015. --- Application Phase ---
  14016. --- Firing Productions (PE) For State At Depth 1 ---
  14017. --- Inner Elaboration Phase, active level 1 (S1) ---
  14018. Firing apply*operator
  14019. -->
  14020. (I3 ^predict-no N998 + :O )
  14021. Firing apply*operator*complete
  14022. -->
  14023. (I3 ^predict-no N997 - :O )
  14024. inner elaboration loop at bottom goal.
  14025. --- Change Working Memory (PE) ---
  14026. =>WM: (14013: I3 ^predict-no N998)
  14027. <=WM: (14000: N997 ^status complete)
  14028. <=WM: (13999: I3 ^predict-no N997)
  14029. --- Firing Productions (IE) For State At Depth 1 ---
  14030. --- Inner Elaboration Phase, active level 1 (S1) ---
  14031. Firing monitor*world
  14032. -->
  14033. I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
  14034. --- Change Working Memory (IE) ---
  14035. --- END Application Phase ---
  14036. --- Output Phase ---
  14037. ENV: Agent did: predict-no for direction U in state State-A
  14038. In State-A moving U
  14039. ENV: (next state, see, prediction correct?) = (State-A, 0, True)
  14040. predict error 0
  14041. dir: dir isR
  14042. --- END Output Phase ---
  14043. \-/--- Input Phase ---
  14044. =>WM: (14017: I2 ^dir R)
  14045. =>WM: (14016: I2 ^reward 1)
  14046. =>WM: (14015: I2 ^see 0)
  14047. =>WM: (14014: N998 ^status complete)
  14048. <=WM: (14003: I2 ^dir U)
  14049. <=WM: (14002: I2 ^reward 1)
  14050. <=WM: (14001: I2 ^see 0)
  14051. =>WM: (14018: I2 ^level-1 L0-root)
  14052. <=WM: (14004: I2 ^level-1 L0-root)
  14053. --- END Input Phase ---
  14054. --- Proposal Phase ---
  14055. --- Inner Elaboration Phase, active level 1 (S1) ---
  14056. Firing rl*prefer*rvt*predict-yes*H0*5*H1*14
  14057. -->
  14058. (S1 ^operator O1995 = 0.8783951706845293)
  14059. Firing prefer*rvt*predict-yes*H0*5*H1
  14060. -->
  14061. Firing elaborate*copy-see-to-output-link
  14062. -->
  14063. (I3 ^see 0 +)
  14064. Firing elaborate*reward*based*on*reward
  14065. -->
  14066. (R1002 ^value 1 +)
  14067. (R1 ^reward R1002 +)
  14068. Firing propose*predict-yes
  14069. -->
  14070. (O1997 ^name predict-yes +)
  14071. (S1 ^operator O1997 +)
  14072. Firing propose*predict-no
  14073. -->
  14074. (O1998 ^name predict-no +)
  14075. (S1 ^operator O1998 +)
  14076. Firing rl*prefer*rvt*predict-no*H0*6
  14077. -->
  14078. (S1 ^operator O1996 = 0.9999888743986174)
  14079. Firing rl*prefer*rvt*predict-yes*H0*5
  14080. -->
  14081. (S1 ^operator O1995 = 0.1215989443698621)
  14082. Firing prefer*rvt*predict-yes*H0
  14083. -->
  14084. Firing prefer*rvt*predict-no*H0
  14085. -->
  14086. Firing elaborate*copy-dir-to-output-link
  14087. -->
  14088. (I3 ^dir R +)
  14089. inner elaboration loop at bottom goal.
  14090. Retracting elaborate*copy-see-to-output-link
  14091. -->
  14092. (I3 ^see 0 +)
  14093. Retracting propose*predict-no
  14094. -->
  14095. (O1996 ^name predict-no +)
  14096. (S1 ^operator O1996 +)
  14097. Retracting propose*predict-yes
  14098. -->
  14099. (O1995 ^name predict-yes +)
  14100. (S1 ^operator O1995 +)
  14101. Retracting elaborate*reward*based*on*reward
  14102. -->
  14103. (R1001 ^value 1 +)
  14104. (R1 ^reward R1001 +)
  14105. Retracting elaborate*copy-dir-to-output-link
  14106. -->
  14107. (I3 ^dir U +)
  14108. Retracting rl*prefer*rvt*predict-no*H0*2
  14109. -->
  14110. (S1 ^operator O1996 = 1.)
  14111. Retracting rl*prefer*rvt*predict-yes*H0*1
  14112. -->
  14113. (S1 ^operator O1995 = 0.)
  14114. =>WM: (14025: S1 ^operator O1998 +)
  14115. =>WM: (14024: S1 ^operator O1997 +)
  14116. =>WM: (14023: I3 ^dir R)
  14117. =>WM: (14022: O1998 ^name predict-no)
  14118. =>WM: (14021: O1997 ^name predict-yes)
  14119. =>WM: (14020: R1002 ^value 1)
  14120. =>WM: (14019: R1 ^reward R1002)
  14121. <=WM: (14010: S1 ^operator O1995 +)
  14122. <=WM: (14011: S1 ^operator O1996 +)
  14123. <=WM: (14012: S1 ^operator O1996)
  14124. <=WM: (14009: I3 ^dir U)
  14125. <=WM: (14005: R1 ^reward R1001)
  14126. <=WM: (14008: O1996 ^name predict-no)
  14127. <=WM: (14007: O1995 ^name predict-yes)
  14128. <=WM: (14006: R1001 ^value 1)
  14129. --- Inner Elaboration Phase, active level 1 (S1) ---
  14130. Firing prefer*rvt*predict-yes*H0
  14131. -->
  14132. Firing rl*prefer*rvt*predict-yes*H0*5*H1*14
  14133. -->
  14134. (S1 ^operator O1997 = 0.8783951706845293)
  14135. Firing rl*prefer*rvt*predict-yes*H0*5
  14136. -->
  14137. (S1 ^operator O1997 = 0.1215989443698621)
  14138. Firing prefer*rvt*predict-yes*H0*5*H1
  14139. -->
  14140. Firing prefer*rvt*predict-no*H0
  14141. -->
  14142. Firing rl*prefer*rvt*predict-no*H0*6
  14143. -->
  14144. (S1 ^operator O1998 = 0.9999888743986174)
  14145. inner elaboration loop at bottom goal.
  14146. Retracting rl*prefer*rvt*predict-no*H0*6
  14147. -->
  14148. (S1 ^operator O1996 = 0.9999888743986174)
  14149. Retracting rl*prefer*rvt*predict-yes*H0*5
  14150. -->
  14151. (S1 ^operator O1995 = 0.1215989443698621)
  14152. Retracting rl*prefer*rvt*predict-yes*H0*5*H1*14
  14153. -->
  14154. (S1 ^operator O1995 = 0.8783951706845293)
  14155. --- END Proposal Phase ---
  14156. --- Decision Phase ---
  14157. RL update rl*prefer*rvt*predict-no*H0*2 1 0 1 -> 1 0 1(R,m,v=1,1,0)
  14158. =>WM: (14026: S1 ^operator O1997)
  14159. 999: O: O1997 (predict-yes)
  14160. --- END Decision Phase ---
  14161. --- Application Phase ---
  14162. --- Firing Productions (PE) For State At Depth 1 ---
  14163. --- Inner Elaboration Phase, active level 1 (S1) ---
  14164. Firing apply*operator
  14165. -->
  14166. (I3 ^predict-yes N999 + :O )
  14167. Firing apply*operator*complete
  14168. -->
  14169. (I3 ^predict-no N998 - :O )
  14170. inner elaboration loop at bottom goal.
  14171. --- Change Working Memory (PE) ---
  14172. =>WM: (14027: I3 ^predict-yes N999)
  14173. <=WM: (14014: N998 ^status complete)
  14174. <=WM: (14013: I3 ^predict-no N998)
  14175. --- Firing Productions (IE) For State At Depth 1 ---
  14176. --- Inner Elaboration Phase, active level 1 (S1) ---
  14177. Firing monitor*world
  14178. -->
  14179. I see 1 and I'm going to do: predict-yes inner elaboration loop at bottom goal.
  14180. --- Change Working Memory (IE) ---
  14181. --- END Application Phase ---
  14182. --- Output Phase ---
  14183. ENV: Agent did: predict-yes for direction R in state State-A
  14184. In State-A moving R
  14185. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  14186. predict error 0
  14187. dir: dir isU
  14188. --- END Output Phase ---
  14189. |\---- Input Phase ---
  14190. =>WM: (14031: I2 ^dir U)
  14191. =>WM: (14030: I2 ^reward 1)
  14192. =>WM: (14029: I2 ^see 1)
  14193. =>WM: (14028: N999 ^status complete)
  14194. <=WM: (14017: I2 ^dir R)
  14195. <=WM: (14016: I2 ^reward 1)
  14196. <=WM: (14015: I2 ^see 0)
  14197. =>WM: (14032: I2 ^level-1 R1-root)
  14198. <=WM: (14018: I2 ^level-1 L0-root)
  14199. --- END Input Phase ---
  14200. --- Proposal Phase ---
  14201. --- Inner Elaboration Phase, active level 1 (S1) ---
  14202. Firing elaborate*copy-see-to-output-link
  14203. -->
  14204. (I3 ^see 1 +)
  14205. Firing elaborate*reward*based*on*reward
  14206. -->
  14207. (R1003 ^value 1 +)
  14208. (R1 ^reward R1003 +)
  14209. Firing propose*predict-yes
  14210. -->
  14211. (O1999 ^name predict-yes +)
  14212. (S1 ^operator O1999 +)
  14213. Firing propose*predict-no
  14214. -->
  14215. (O2000 ^name predict-no +)
  14216. (S1 ^operator O2000 +)
  14217. Firing rl*prefer*rvt*predict-no*H0*2
  14218. -->
  14219. (S1 ^operator O1998 = 1.)
  14220. Firing rl*prefer*rvt*predict-yes*H0*1
  14221. -->
  14222. (S1 ^operator O1997 = 0.)
  14223. Firing prefer*rvt*predict-yes*H0
  14224. -->
  14225. Firing prefer*rvt*predict-no*H0
  14226. -->
  14227. Firing elaborate*copy-dir-to-output-link
  14228. -->
  14229. (I3 ^dir U +)
  14230. inner elaboration loop at bottom goal.
  14231. Retracting elaborate*copy-see-to-output-link
  14232. -->
  14233. (I3 ^see 0 +)
  14234. Retracting propose*predict-no
  14235. -->
  14236. (O1998 ^name predict-no +)
  14237. (S1 ^operator O1998 +)
  14238. Retracting propose*predict-yes
  14239. -->
  14240. (O1997 ^name predict-yes +)
  14241. (S1 ^operator O1997 +)
  14242. Retracting elaborate*reward*based*on*reward
  14243. -->
  14244. (R1002 ^value 1 +)
  14245. (R1 ^reward R1002 +)
  14246. Retracting elaborate*copy-dir-to-output-link
  14247. -->
  14248. (I3 ^dir R +)
  14249. Retracting rl*prefer*rvt*predict-no*H0*6
  14250. -->
  14251. (S1 ^operator O1998 = 0.9999888743986174)
  14252. Retracting rl*prefer*rvt*predict-yes*H0*5
  14253. -->
  14254. (S1 ^operator O1997 = 0.1215989443698621)
  14255. Retracting rl*prefer*rvt*predict-yes*H0*5*H1*14
  14256. -->
  14257. (S1 ^operator O1997 = 0.8783951706845293)
  14258. =>WM: (14040: S1 ^operator O2000 +)
  14259. =>WM: (14039: S1 ^operator O1999 +)
  14260. =>WM: (14038: I3 ^dir U)
  14261. =>WM: (14037: O2000 ^name predict-no)
  14262. =>WM: (14036: O1999 ^name predict-yes)
  14263. =>WM: (14035: R1003 ^value 1)
  14264. =>WM: (14034: R1 ^reward R1003)
  14265. =>WM: (14033: I3 ^see 1)
  14266. <=WM: (14024: S1 ^operator O1997 +)
  14267. <=WM: (14026: S1 ^operator O1997)
  14268. <=WM: (14025: S1 ^operator O1998 +)
  14269. <=WM: (14023: I3 ^dir R)
  14270. <=WM: (14019: R1 ^reward R1002)
  14271. <=WM: (13964: I3 ^see 0)
  14272. <=WM: (14022: O1998 ^name predict-no)
  14273. <=WM: (14021: O1997 ^name predict-yes)
  14274. <=WM: (14020: R1002 ^value 1)
  14275. --- Inner Elaboration Phase, active level 1 (S1) ---
  14276. Firing prefer*rvt*predict-yes*H0
  14277. -->
  14278. Firing rl*prefer*rvt*predict-yes*H0*1
  14279. -->
  14280. (S1 ^operator O1999 = 0.)
  14281. Firing prefer*rvt*predict-no*H0
  14282. -->
  14283. Firing rl*prefer*rvt*predict-no*H0*2
  14284. -->
  14285. (S1 ^operator O2000 = 1.)
  14286. inner elaboration loop at bottom goal.
  14287. Retracting rl*prefer*rvt*predict-no*H0*2
  14288. -->
  14289. (S1 ^operator O1998 = 1.)
  14290. Retracting rl*prefer*rvt*predict-yes*H0*1
  14291. -->
  14292. (S1 ^operator O1997 = 0.)
  14293. --- END Proposal Phase ---
  14294. --- Decision Phase ---
  14295. RL update rl*prefer*rvt*predict-yes*H0*5 0.534525 -0.412926 0.121599 -> 0.534525 -0.412926 0.121599(R,m,v=1,0.864407,0.117874)
  14296. RL update rl*prefer*rvt*predict-yes*H0*5*H1*14 0.46547 0.412925 0.878395 -> 0.465471 0.412925 0.878396(R,m,v=1,1,0)
  14297. =>WM: (14041: S1 ^operator O2000)
  14298. 1000: O: O2000 (predict-no)
  14299. --- END Decision Phase ---
  14300. --- Application Phase ---
  14301. --- Firing Productions (PE) For State At Depth 1 ---
  14302. --- Inner Elaboration Phase, active level 1 (S1) ---
  14303. Firing apply*operator
  14304. -->
  14305. (I3 ^predict-no N1000 + :O )
  14306. Firing apply*operator*complete
  14307. -->
  14308. (I3 ^predict-yes N999 - :O )
  14309. inner elaboration loop at bottom goal.
  14310. --- Change Working Memory (PE) ---
  14311. =>WM: (14042: I3 ^predict-no N1000)
  14312. <=WM: (14028: N999 ^status complete)
  14313. <=WM: (14027: I3 ^predict-yes N999)
  14314. --- Firing Productions (IE) For State At Depth 1 ---
  14315. --- Inner Elaboration Phase, active level 1 (S1) ---
  14316. Firing monitor*world
  14317. -->
  14318. I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
  14319. --- Change Working Memory (IE) ---
  14320. --- END Application Phase ---
  14321. --- Output Phase ---
  14322. ENV: Agent did: predict-no for direction U in state State-B
  14323. In State-B moving U
  14324. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  14325. predict error 0
  14326. dir: dir isU
  14327. --- END Output Phase ---
  14328. /|\-/|\-/|--- Input Phase ---
  14329. =>WM: (14046: I2 ^dir U)
  14330. =>WM: (14045: I2 ^reward 1)
  14331. =>WM: (14044: I2 ^see 0)
  14332. =>WM: (14043: N1000 ^status complete)
  14333. <=WM: (14031: I2 ^dir U)
  14334. <=WM: (14030: I2 ^reward 1)
  14335. <=WM: (14029: I2 ^see 1)
  14336. =>WM: (14047: I2 ^level-1 R1-root)
  14337. <=WM: (14032: I2 ^level-1 R1-root)
  14338. --- END Input Phase ---
  14339. --- Proposal Phase ---
  14340. --- Inner Elaboration Phase, active level 1 (S1) ---
  14341. Firing elaborate*copy-see-to-output-link
  14342. -->
  14343. (I3 ^see 0 +)
  14344. Firing elaborate*reward*based*on*reward
  14345. -->
  14346. (R1004 ^value 1 +)
  14347. (R1 ^reward R1004 +)
  14348. Firing propose*predict-yes
  14349. -->
  14350. (O2001 ^name predict-yes +)
  14351. (S1 ^operator O2001 +)
  14352. Firing propose*predict-no
  14353. -->
  14354. (O2002 ^name predict-no +)
  14355. (S1 ^operator O2002 +)
  14356. Firing rl*prefer*rvt*predict-no*H0*2
  14357. -->
  14358. (S1 ^operator O2000 = 1.)
  14359. Firing rl*prefer*rvt*predict-yes*H0*1
  14360. -->
  14361. (S1 ^operator O1999 = 0.)
  14362. Firing prefer*rvt*predict-yes*H0
  14363. -->
  14364. Firing prefer*rvt*predict-no*H0
  14365. -->
  14366. Firing elaborate*copy-dir-to-output-link
  14367. -->
  14368. (I3 ^dir U +)
  14369. inner elaboration loop at bottom goal.
  14370. Retracting elaborate*copy-see-to-output-link
  14371. -->
  14372. (I3 ^see 1 +)
  14373. Retracting propose*predict-no
  14374. -->
  14375. (O2000 ^name predict-no +)
  14376. (S1 ^operator O2000 +)
  14377. Retracting propose*predict-yes
  14378. -->
  14379. (O1999 ^name predict-yes +)
  14380. (S1 ^operator O1999 +)
  14381. Retracting elaborate*reward*based*on*reward
  14382. -->
  14383. (R1003 ^value 1 +)
  14384. (R1 ^reward R1003 +)
  14385. Retracting elaborate*copy-dir-to-output-link
  14386. -->
  14387. (I3 ^dir U +)
  14388. Retracting rl*prefer*rvt*predict-no*H0*2
  14389. -->
  14390. (S1 ^operator O2000 = 1.)
  14391. Retracting rl*prefer*rvt*predict-yes*H0*1
  14392. -->
  14393. (S1 ^operator O1999 = 0.)
  14394. =>WM: (14054: S1 ^operator O2002 +)
  14395. =>WM: (14053: S1 ^operator O2001 +)
  14396. =>WM: (14052: O2002 ^name predict-no)
  14397. =>WM: (14051: O2001 ^name predict-yes)
  14398. =>WM: (14050: R1004 ^value 1)
  14399. =>WM: (14049: R1 ^reward R1004)
  14400. =>WM: (14048: I3 ^see 0)
  14401. <=WM: (14039: S1 ^operator O1999 +)
  14402. <=WM: (14040: S1 ^operator O2000 +)
  14403. <=WM: (14041: S1 ^operator O2000)
  14404. <=WM: (14034: R1 ^reward R1003)
  14405. <=WM: (14033: I3 ^see 1)
  14406. <=WM: (14037: O2000 ^name predict-no)
  14407. <=WM: (14036: O1999 ^name predict-yes)
  14408. <=WM: (14035: R1003 ^value 1)
  14409. --- Inner Elaboration Phase, active level 1 (S1) ---
  14410. Firing prefer*rvt*predict-yes*H0
  14411. -->
  14412. Firing rl*prefer*rvt*predict-yes*H0*1
  14413. -->
  14414. (S1 ^operator O2001 = 0.)
  14415. Firing prefer*rvt*predict-no*H0
  14416. -->
  14417. Firing rl*prefer*rvt*predict-no*H0*2
  14418. -->
  14419. (S1 ^operator O2002 = 1.)
  14420. inner elaboration loop at bottom goal.
  14421. Retracting rl*prefer*rvt*predict-no*H0*2
  14422. -->
  14423. (S1 ^operator O2000 = 1.)
  14424. Retracting rl*prefer*rvt*predict-yes*H0*1
  14425. -->
  14426. (S1 ^operator O1999 = 0.)
  14427. --- END Proposal Phase ---
  14428. --- Decision Phase ---
  14429. RL update rl*prefer*rvt*predict-no*H0*2 1 0 1 -> 1 0 1(R,m,v=1,1,0)
  14430. =>WM: (14055: S1 ^operator O2002)
  14431. 1001: O: O2002 (predict-no)
  14432. --- END Decision Phase ---
  14433. --- Application Phase ---
  14434. --- Firing Productions (PE) For State At Depth 1 ---
  14435. --- Inner Elaboration Phase, active level 1 (S1) ---
  14436. Firing apply*operator
  14437. -->
  14438. (I3 ^predict-no N1001 + :O )
  14439. Firing apply*operator*complete
  14440. -->
  14441. (I3 ^predict-no N1000 - :O )
  14442. inner elaboration loop at bottom goal.
  14443. --- Change Working Memory (PE) ---
  14444. =>WM: (14056: I3 ^predict-no N1001)
  14445. <=WM: (14043: N1000 ^status complete)
  14446. <=WM: (14042: I3 ^predict-no N1000)
  14447. --- Firing Productions (IE) For State At Depth 1 ---
  14448. --- Inner Elaboration Phase, active level 1 (S1) ---
  14449. Firing monitor*world
  14450. -->
  14451. I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
  14452. --- Change Working Memory (IE) ---
  14453. --- END Application Phase ---
  14454. --- Output Phase ---
  14455. ENV: Agent did: predict-no for direction U in state State-B
  14456. In State-B moving U
  14457. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  14458. predict error 0
  14459. dir: dir isU
  14460. --- END Output Phase ---
  14461. \--- Input Phase ---
  14462. =>WM: (14060: I2 ^dir U)
  14463. =>WM: (14059: I2 ^reward 1)
  14464. =>WM: (14058: I2 ^see 0)
  14465. =>WM: (14057: N1001 ^status complete)
  14466. <=WM: (14046: I2 ^dir U)
  14467. <=WM: (14045: I2 ^reward 1)
  14468. <=WM: (14044: I2 ^see 0)
  14469. =>WM: (14061: I2 ^level-1 R1-root)
  14470. <=WM: (14047: I2 ^level-1 R1-root)
  14471. --- END Input Phase ---
  14472. --- Proposal Phase ---
  14473. --- Inner Elaboration Phase, active level 1 (S1) ---
  14474. Firing elaborate*copy-see-to-output-link
  14475. -->
  14476. (I3 ^see 0 +)
  14477. Firing elaborate*reward*based*on*reward
  14478. -->
  14479. (R1005 ^value 1 +)
  14480. (R1 ^reward R1005 +)
  14481. Firing propose*predict-yes
  14482. -->
  14483. (O2003 ^name predict-yes +)
  14484. (S1 ^operator O2003 +)
  14485. Firing propose*predict-no
  14486. -->
  14487. (O2004 ^name predict-no +)
  14488. (S1 ^operator O2004 +)
  14489. Firing rl*prefer*rvt*predict-no*H0*2
  14490. -->
  14491. (S1 ^operator O2002 = 1.)
  14492. Firing rl*prefer*rvt*predict-yes*H0*1
  14493. -->
  14494. (S1 ^operator O2001 = 0.)
  14495. Firing prefer*rvt*predict-yes*H0
  14496. -->
  14497. Firing prefer*rvt*predict-no*H0
  14498. -->
  14499. Firing elaborate*copy-dir-to-output-link
  14500. -->
  14501. (I3 ^dir U +)
  14502. inner elaboration loop at bottom goal.
  14503. Retracting elaborate*copy-see-to-output-link
  14504. -->
  14505. (I3 ^see 0 +)
  14506. Retracting propose*predict-no
  14507. -->
  14508. (O2002 ^name predict-no +)
  14509. (S1 ^operator O2002 +)
  14510. Retracting propose*predict-yes
  14511. -->
  14512. (O2001 ^name predict-yes +)
  14513. (S1 ^operator O2001 +)
  14514. Retracting elaborate*reward*based*on*reward
  14515. -->
  14516. (R1004 ^value 1 +)
  14517. (R1 ^reward R1004 +)
  14518. Retracting elaborate*copy-dir-to-output-link
  14519. -->
  14520. (I3 ^dir U +)
  14521. Retracting rl*prefer*rvt*predict-no*H0*2
  14522. -->
  14523. (S1 ^operator O2002 = 1.)
  14524. Retracting rl*prefer*rvt*predict-yes*H0*1
  14525. -->
  14526. (S1 ^operator O2001 = 0.)
  14527. =>WM: (14067: S1 ^operator O2004 +)
  14528. =>WM: (14066: S1 ^operator O2003 +)
  14529. =>WM: (14065: O2004 ^name predict-no)
  14530. =>WM: (14064: O2003 ^name predict-yes)
  14531. =>WM: (14063: R1005 ^value 1)
  14532. =>WM: (14062: R1 ^reward R1005)
  14533. <=WM: (14053: S1 ^operator O2001 +)
  14534. <=WM: (14054: S1 ^operator O2002 +)
  14535. <=WM: (14055: S1 ^operator O2002)
  14536. <=WM: (14049: R1 ^reward R1004)
  14537. <=WM: (14052: O2002 ^name predict-no)
  14538. <=WM: (14051: O2001 ^name predict-yes)
  14539. <=WM: (14050: R1004 ^value 1)
  14540. --- Inner Elaboration Phase, active level 1 (S1) ---
  14541. Firing prefer*rvt*predict-yes*H0
  14542. -->
  14543. Firing rl*prefer*rvt*predict-yes*H0*1
  14544. -->
  14545. (S1 ^operator O2003 = 0.)
  14546. Firing prefer*rvt*predict-no*H0
  14547. -->
  14548. Firing rl*prefer*rvt*predict-no*H0*2
  14549. -->
  14550. (S1 ^operator O2004 = 1.)
  14551. inner elaboration loop at bottom goal.
  14552. Retracting rl*prefer*rvt*predict-no*H0*2
  14553. -->
  14554. (S1 ^operator O2002 = 1.)
  14555. Retracting rl*prefer*rvt*predict-yes*H0*1
  14556. -->
  14557. (S1 ^operator O2001 = 0.)
  14558. --- END Proposal Phase ---
  14559. --- Decision Phase ---
  14560. RL update rl*prefer*rvt*predict-no*H0*2 1 0 1 -> 1 0 1(R,m,v=1,1,0)
  14561. =>WM: (14068: S1 ^operator O2004)
  14562. 1002: O: O2004 (predict-no)
  14563. --- END Decision Phase ---
  14564. --- Application Phase ---
  14565. --- Firing Productions (PE) For State At Depth 1 ---
  14566. --- Inner Elaboration Phase, active level 1 (S1) ---
  14567. Firing apply*operator
  14568. -->
  14569. (I3 ^predict-no N1002 + :O )
  14570. Firing apply*operator*complete
  14571. -->
  14572. (I3 ^predict-no N1001 - :O )
  14573. inner elaboration loop at bottom goal.
  14574. --- Change Working Memory (PE) ---
  14575. =>WM: (14069: I3 ^predict-no N1002)
  14576. <=WM: (14057: N1001 ^status complete)
  14577. <=WM: (14056: I3 ^predict-no N1001)
  14578. --- Firing Productions (IE) For State At Depth 1 ---
  14579. --- Inner Elaboration Phase, active level 1 (S1) ---
  14580. Firing monitor*world
  14581. -->
  14582. I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
  14583. --- Change Working Memory (IE) ---
  14584. --- END Application Phase ---
  14585. --- Output Phase ---
  14586. ENV: Agent did: predict-no for direction U in state State-B
  14587. In State-B moving U
  14588. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  14589. predict error 0
  14590. dir: dir isR
  14591. --- END Output Phase ---
  14592. -/--- Input Phase ---
  14593. =>WM: (14073: I2 ^dir R)
  14594. =>WM: (14072: I2 ^reward 1)
  14595. =>WM: (14071: I2 ^see 0)
  14596. =>WM: (14070: N1002 ^status complete)
  14597. <=WM: (14060: I2 ^dir U)
  14598. <=WM: (14059: I2 ^reward 1)
  14599. <=WM: (14058: I2 ^see 0)
  14600. =>WM: (14074: I2 ^level-1 R1-root)
  14601. <=WM: (14061: I2 ^level-1 R1-root)
  14602. --- END Input Phase ---
  14603. --- Proposal Phase ---
  14604. --- Inner Elaboration Phase, active level 1 (S1) ---
  14605. Firing rl*prefer*rvt*predict-yes*H0*5*H1*15
  14606. -->
  14607. (S1 ^operator O2003 = -0.04253361215288998)
  14608. Firing prefer*rvt*predict-yes*H0*5*H1
  14609. -->
  14610. Firing elaborate*copy-see-to-output-link
  14611. -->
  14612. (I3 ^see 0 +)
  14613. Firing elaborate*reward*based*on*reward
  14614. -->
  14615. (R1006 ^value 1 +)
  14616. (R1 ^reward R1006 +)
  14617. Firing propose*predict-yes
  14618. -->
  14619. (O2005 ^name predict-yes +)
  14620. (S1 ^operator O2005 +)
  14621. Firing propose*predict-no
  14622. -->
  14623. (O2006 ^name predict-no +)
  14624. (S1 ^operator O2006 +)
  14625. Firing rl*prefer*rvt*predict-no*H0*6
  14626. -->
  14627. (S1 ^operator O2004 = 0.9999888743986174)
  14628. Firing rl*prefer*rvt*predict-yes*H0*5
  14629. -->
  14630. (S1 ^operator O2003 = 0.1215994207949702)
  14631. Firing prefer*rvt*predict-yes*H0
  14632. -->
  14633. Firing prefer*rvt*predict-no*H0
  14634. -->
  14635. Firing elaborate*copy-dir-to-output-link
  14636. -->
  14637. (I3 ^dir R +)
  14638. inner elaboration loop at bottom goal.
  14639. Retracting elaborate*copy-see-to-output-link
  14640. -->
  14641. (I3 ^see 0 +)
  14642. Retracting propose*predict-no
  14643. -->
  14644. (O2004 ^name predict-no +)
  14645. (S1 ^operator O2004 +)
  14646. Retracting propose*predict-yes
  14647. -->
  14648. (O2003 ^name predict-yes +)
  14649. (S1 ^operator O2003 +)
  14650. Retracting elaborate*reward*based*on*reward
  14651. -->
  14652. (R1005 ^value 1 +)
  14653. (R1 ^reward R1005 +)
  14654. Retracting elaborate*copy-dir-to-output-link
  14655. -->
  14656. (I3 ^dir U +)
  14657. Retracting rl*prefer*rvt*predict-no*H0*2
  14658. -->
  14659. (S1 ^operator O2004 = 1.)
  14660. Retracting rl*prefer*rvt*predict-yes*H0*1
  14661. -->
  14662. (S1 ^operator O2003 = 0.)
  14663. =>WM: (14081: S1 ^operator O2006 +)
  14664. =>WM: (14080: S1 ^operator O2005 +)
  14665. =>WM: (14079: I3 ^dir R)
  14666. =>WM: (14078: O2006 ^name predict-no)
  14667. =>WM: (14077: O2005 ^name predict-yes)
  14668. =>WM: (14076: R1006 ^value 1)
  14669. =>WM: (14075: R1 ^reward R1006)
  14670. <=WM: (14066: S1 ^operator O2003 +)
  14671. <=WM: (14067: S1 ^operator O2004 +)
  14672. <=WM: (14068: S1 ^operator O2004)
  14673. <=WM: (14038: I3 ^dir U)
  14674. <=WM: (14062: R1 ^reward R1005)
  14675. <=WM: (14065: O2004 ^name predict-no)
  14676. <=WM: (14064: O2003 ^name predict-yes)
  14677. <=WM: (14063: R1005 ^value 1)
  14678. --- Inner Elaboration Phase, active level 1 (S1) ---
  14679. Firing prefer*rvt*predict-yes*H0
  14680. -->
  14681. Firing rl*prefer*rvt*predict-yes*H0*5*H1*15
  14682. -->
  14683. (S1 ^operator O2005 = -0.04253361215288998)
  14684. Firing rl*prefer*rvt*predict-yes*H0*5
  14685. -->
  14686. (S1 ^operator O2005 = 0.1215994207949702)
  14687. Firing prefer*rvt*predict-yes*H0*5*H1
  14688. -->
  14689. Firing prefer*rvt*predict-no*H0
  14690. -->
  14691. Firing rl*prefer*rvt*predict-no*H0*6
  14692. -->
  14693. (S1 ^operator O2006 = 0.9999888743986174)
  14694. inner elaboration loop at bottom goal.
  14695. Retracting rl*prefer*rvt*predict-no*H0*6
  14696. -->
  14697. (S1 ^operator O2004 = 0.9999888743986174)
  14698. Retracting rl*prefer*rvt*predict-yes*H0*5
  14699. -->
  14700. (S1 ^operator O2003 = 0.1215994207949702)
  14701. Retracting rl*prefer*rvt*predict-yes*H0*5*H1*15
  14702. -->
  14703. (S1 ^operator O2003 = -0.04253361215288998)
  14704. --- END Proposal Phase ---
  14705. --- Decision Phase ---
  14706. RL update rl*prefer*rvt*predict-no*H0*2 1 0 1 -> 1 0 1(R,m,v=1,1,0)
  14707. =>WM: (14082: S1 ^operator O2006)
  14708. 1003: O: O2006 (predict-no)
  14709. --- END Decision Phase ---
  14710. --- Application Phase ---
  14711. --- Firing Productions (PE) For State At Depth 1 ---
  14712. --- Inner Elaboration Phase, active level 1 (S1) ---
  14713. Firing apply*operator
  14714. -->
  14715. (I3 ^predict-no N1003 + :O )
  14716. Firing apply*operator*complete
  14717. -->
  14718. (I3 ^predict-no N1002 - :O )
  14719. inner elaboration loop at bottom goal.
  14720. --- Change Working Memory (PE) ---
  14721. =>WM: (14083: I3 ^predict-no N1003)
  14722. <=WM: (14070: N1002 ^status complete)
  14723. <=WM: (14069: I3 ^predict-no N1002)
  14724. --- Firing Productions (IE) For State At Depth 1 ---
  14725. --- Inner Elaboration Phase, active level 1 (S1) ---
  14726. Firing monitor*world
  14727. -->
  14728. I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
  14729. --- Change Working Memory (IE) ---
  14730. --- END Application Phase ---
  14731. --- Output Phase ---
  14732. ENV: Agent did: predict-no for direction R in state State-B
  14733. In State-B moving R
  14734. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  14735. predict error 0
  14736. dir: dir isR
  14737. --- END Output Phase ---
  14738. |\---- Input Phase ---
  14739. =>WM: (14087: I2 ^dir R)
  14740. =>WM: (14086: I2 ^reward 1)
  14741. =>WM: (14085: I2 ^see 0)
  14742. =>WM: (14084: N1003 ^status complete)
  14743. <=WM: (14073: I2 ^dir R)
  14744. <=WM: (14072: I2 ^reward 1)
  14745. <=WM: (14071: I2 ^see 0)
  14746. =>WM: (14088: I2 ^level-1 R0-root)
  14747. <=WM: (14074: I2 ^level-1 R1-root)
  14748. --- END Input Phase ---
  14749. --- Proposal Phase ---
  14750. --- Inner Elaboration Phase, active level 1 (S1) ---
  14751. Firing rl*prefer*rvt*predict-yes*H0*5*H1*7
  14752. -->
  14753. (S1 ^operator O2005 = -0.1512366769350551)
  14754. Firing prefer*rvt*predict-yes*H0*5*H1
  14755. -->
  14756. Firing elaborate*copy-see-to-output-link
  14757. -->
  14758. (I3 ^see 0 +)
  14759. Firing elaborate*reward*based*on*reward
  14760. -->
  14761. (R1007 ^value 1 +)
  14762. (R1 ^reward R1007 +)
  14763. Firing propose*predict-yes
  14764. -->
  14765. (O2007 ^name predict-yes +)
  14766. (S1 ^operator O2007 +)
  14767. Firing propose*predict-no
  14768. -->
  14769. (O2008 ^name predict-no +)
  14770. (S1 ^operator O2008 +)
  14771. Firing rl*prefer*rvt*predict-no*H0*6
  14772. -->
  14773. (S1 ^operator O2006 = 0.9999888743986174)
  14774. Firing rl*prefer*rvt*predict-yes*H0*5
  14775. -->
  14776. (S1 ^operator O2005 = 0.1215994207949702)
  14777. Firing prefer*rvt*predict-yes*H0
  14778. -->
  14779. Firing prefer*rvt*predict-no*H0
  14780. -->
  14781. Firing elaborate*copy-dir-to-output-link
  14782. -->
  14783. (I3 ^dir R +)
  14784. inner elaboration loop at bottom goal.
  14785. Retracting elaborate*copy-see-to-output-link
  14786. -->
  14787. (I3 ^see 0 +)
  14788. Retracting propose*predict-no
  14789. -->
  14790. (O2006 ^name predict-no +)
  14791. (S1 ^operator O2006 +)
  14792. Retracting propose*predict-yes
  14793. -->
  14794. (O2005 ^name predict-yes +)
  14795. (S1 ^operator O2005 +)
  14796. Retracting elaborate*reward*based*on*reward
  14797. -->
  14798. (R1006 ^value 1 +)
  14799. (R1 ^reward R1006 +)
  14800. Retracting elaborate*copy-dir-to-output-link
  14801. -->
  14802. (I3 ^dir R +)
  14803. Retracting rl*prefer*rvt*predict-no*H0*6
  14804. -->
  14805. (S1 ^operator O2006 = 0.9999888743986174)
  14806. Retracting rl*prefer*rvt*predict-yes*H0*5
  14807. -->
  14808. (S1 ^operator O2005 = 0.1215994207949702)
  14809. Retracting rl*prefer*rvt*predict-yes*H0*5*H1*15
  14810. -->
  14811. (S1 ^operator O2005 = -0.04253361215288998)
  14812. =>WM: (14094: S1 ^operator O2008 +)
  14813. =>WM: (14093: S1 ^operator O2007 +)
  14814. =>WM: (14092: O2008 ^name predict-no)
  14815. =>WM: (14091: O2007 ^name predict-yes)
  14816. =>WM: (14090: R1007 ^value 1)
  14817. =>WM: (14089: R1 ^reward R1007)
  14818. <=WM: (14080: S1 ^operator O2005 +)
  14819. <=WM: (14081: S1 ^operator O2006 +)
  14820. <=WM: (14082: S1 ^operator O2006)
  14821. <=WM: (14075: R1 ^reward R1006)
  14822. <=WM: (14078: O2006 ^name predict-no)
  14823. <=WM: (14077: O2005 ^name predict-yes)
  14824. <=WM: (14076: R1006 ^value 1)
  14825. --- Inner Elaboration Phase, active level 1 (S1) ---
  14826. Firing prefer*rvt*predict-yes*H0
  14827. -->
  14828. Firing rl*prefer*rvt*predict-yes*H0*5
  14829. -->
  14830. (S1 ^operator O2007 = 0.1215994207949702)
  14831. Firing prefer*rvt*predict-yes*H0*5*H1
  14832. -->
  14833. Firing rl*prefer*rvt*predict-yes*H0*5*H1*7
  14834. -->
  14835. (S1 ^operator O2007 = -0.1512366769350551)
  14836. Firing prefer*rvt*predict-no*H0
  14837. -->
  14838. Firing rl*prefer*rvt*predict-no*H0*6
  14839. -->
  14840. (S1 ^operator O2008 = 0.9999888743986174)
  14841. inner elaboration loop at bottom goal.
  14842. Retracting rl*prefer*rvt*predict-no*H0*6
  14843. -->
  14844. (S1 ^operator O2006 = 0.9999888743986174)
  14845. Retracting rl*prefer*rvt*predict-yes*H0*5
  14846. -->
  14847. (S1 ^operator O2005 = 0.1215994207949702)
  14848. Retracting rl*prefer*rvt*predict-yes*H0*5*H1*7
  14849. -->
  14850. (S1 ^operator O2005 = -0.1512366769350551)
  14851. --- END Proposal Phase ---
  14852. --- Decision Phase ---
  14853. RL update rl*prefer*rvt*predict-no*H0*6 0.999989 0 0.999989 -> 0.999991 0 0.999991(R,m,v=1,0.938202,0.0583064)
  14854. =>WM: (14095: S1 ^operator O2008)
  14855. 1004: O: O2008 (predict-no)
  14856. --- END Decision Phase ---
  14857. --- Application Phase ---
  14858. --- Firing Productions (PE) For State At Depth 1 ---
  14859. --- Inner Elaboration Phase, active level 1 (S1) ---
  14860. Firing apply*operator
  14861. -->
  14862. (I3 ^predict-no N1004 + :O )
  14863. Firing apply*operator*complete
  14864. -->
  14865. (I3 ^predict-no N1003 - :O )
  14866. inner elaboration loop at bottom goal.
  14867. --- Change Working Memory (PE) ---
  14868. =>WM: (14096: I3 ^predict-no N1004)
  14869. <=WM: (14084: N1003 ^status complete)
  14870. <=WM: (14083: I3 ^predict-no N1003)
  14871. --- Firing Productions (IE) For State At Depth 1 ---
  14872. --- Inner Elaboration Phase, active level 1 (S1) ---
  14873. Firing monitor*world
  14874. -->
  14875. I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
  14876. --- Change Working Memory (IE) ---
  14877. --- END Application Phase ---
  14878. --- Output Phase ---
  14879. ENV: Agent did: predict-no for direction R in state State-B
  14880. In State-B moving R
  14881. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  14882. predict error 0
  14883. dir: dir isU
  14884. --- END Output Phase ---
  14885. /|\--- Input Phase ---
  14886. =>WM: (14100: I2 ^dir U)
  14887. =>WM: (14099: I2 ^reward 1)
  14888. =>WM: (14098: I2 ^see 0)
  14889. =>WM: (14097: N1004 ^status complete)
  14890. <=WM: (14087: I2 ^dir R)
  14891. <=WM: (14086: I2 ^reward 1)
  14892. <=WM: (14085: I2 ^see 0)
  14893. =>WM: (14101: I2 ^level-1 R0-root)
  14894. <=WM: (14088: I2 ^level-1 R0-root)
  14895. --- END Input Phase ---
  14896. --- Proposal Phase ---
  14897. --- Inner Elaboration Phase, active level 1 (S1) ---
  14898. Firing elaborate*copy-see-to-output-link
  14899. -->
  14900. (I3 ^see 0 +)
  14901. Firing elaborate*reward*based*on*reward
  14902. -->
  14903. (R1008 ^value 1 +)
  14904. (R1 ^reward R1008 +)
  14905. Firing propose*predict-yes
  14906. -->
  14907. (O2009 ^name predict-yes +)
  14908. (S1 ^operator O2009 +)
  14909. Firing propose*predict-no
  14910. -->
  14911. (O2010 ^name predict-no +)
  14912. (S1 ^operator O2010 +)
  14913. Firing rl*prefer*rvt*predict-no*H0*2
  14914. -->
  14915. (S1 ^operator O2008 = 1.)
  14916. Firing rl*prefer*rvt*predict-yes*H0*1
  14917. -->
  14918. (S1 ^operator O2007 = 0.)
  14919. Firing prefer*rvt*predict-yes*H0
  14920. -->
  14921. Firing prefer*rvt*predict-no*H0
  14922. -->
  14923. Firing elaborate*copy-dir-to-output-link
  14924. -->
  14925. (I3 ^dir U +)
  14926. inner elaboration loop at bottom goal.
  14927. Retracting elaborate*copy-see-to-output-link
  14928. -->
  14929. (I3 ^see 0 +)
  14930. Retracting propose*predict-no
  14931. -->
  14932. (O2008 ^name predict-no +)
  14933. (S1 ^operator O2008 +)
  14934. Retracting propose*predict-yes
  14935. -->
  14936. (O2007 ^name predict-yes +)
  14937. (S1 ^operator O2007 +)
  14938. Retracting elaborate*reward*based*on*reward
  14939. -->
  14940. (R1007 ^value 1 +)
  14941. (R1 ^reward R1007 +)
  14942. Retracting elaborate*copy-dir-to-output-link
  14943. -->
  14944. (I3 ^dir R +)
  14945. Retracting rl*prefer*rvt*predict-no*H0*6
  14946. -->
  14947. (S1 ^operator O2008 = 0.9999906741383352)
  14948. Retracting rl*prefer*rvt*predict-yes*H0*5*H1*7
  14949. -->
  14950. (S1 ^operator O2007 = -0.1512366769350551)
  14951. Retracting rl*prefer*rvt*predict-yes*H0*5
  14952. -->
  14953. (S1 ^operator O2007 = 0.1215994207949702)
  14954. =>WM: (14108: S1 ^operator O2010 +)
  14955. =>WM: (14107: S1 ^operator O2009 +)
  14956. =>WM: (14106: I3 ^dir U)
  14957. =>WM: (14105: O2010 ^name predict-no)
  14958. =>WM: (14104: O2009 ^name predict-yes)
  14959. =>WM: (14103: R1008 ^value 1)
  14960. =>WM: (14102: R1 ^reward R1008)
  14961. <=WM: (14093: S1 ^operator O2007 +)
  14962. <=WM: (14094: S1 ^operator O2008 +)
  14963. <=WM: (14095: S1 ^operator O2008)
  14964. <=WM: (14079: I3 ^dir R)
  14965. <=WM: (14089: R1 ^reward R1007)
  14966. <=WM: (14092: O2008 ^name predict-no)
  14967. <=WM: (14091: O2007 ^name predict-yes)
  14968. <=WM: (14090: R1007 ^value 1)
  14969. --- Inner Elaboration Phase, active level 1 (S1) ---
  14970. Firing prefer*rvt*predict-yes*H0
  14971. -->
  14972. Firing rl*prefer*rvt*predict-yes*H0*1
  14973. -->
  14974. (S1 ^operator O2009 = 0.)
  14975. Firing prefer*rvt*predict-no*H0
  14976. -->
  14977. Firing rl*prefer*rvt*predict-no*H0*2
  14978. -->
  14979. (S1 ^operator O2010 = 1.)
  14980. inner elaboration loop at bottom goal.
  14981. Retracting rl*prefer*rvt*predict-no*H0*2
  14982. -->
  14983. (S1 ^operator O2008 = 1.)
  14984. Retracting rl*prefer*rvt*predict-yes*H0*1
  14985. -->
  14986. (S1 ^operator O2007 = 0.)
  14987. --- END Proposal Phase ---
  14988. --- Decision Phase ---
  14989. RL update rl*prefer*rvt*predict-no*H0*6 0.999991 0 0.999991 -> 0.999992 0 0.999992(R,m,v=1,0.938547,0.0580001)
  14990. =>WM: (14109: S1 ^operator O2010)
  14991. 1005: O: O2010 (predict-no)
  14992. --- END Decision Phase ---
  14993. --- Application Phase ---
  14994. --- Firing Productions (PE) For State At Depth 1 ---
  14995. --- Inner Elaboration Phase, active level 1 (S1) ---
  14996. Firing apply*operator
  14997. -->
  14998. (I3 ^predict-no N1005 + :O )
  14999. Firing apply*operator*complete
  15000. -->
  15001. (I3 ^predict-no N1004 - :O )
  15002. inner elaboration loop at bottom goal.
  15003. --- Change Working Memory (PE) ---
  15004. =>WM: (14110: I3 ^predict-no N1005)
  15005. <=WM: (14097: N1004 ^status complete)
  15006. <=WM: (14096: I3 ^predict-no N1004)
  15007. --- Firing Productions (IE) For State At Depth 1 ---
  15008. --- Inner Elaboration Phase, active level 1 (S1) ---
  15009. Firing monitor*world
  15010. -->
  15011. I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
  15012. --- Change Working Memory (IE) ---
  15013. --- END Application Phase ---
  15014. --- Output Phase ---
  15015. ENV: Agent did: predict-no for direction U in state State-B
  15016. In State-B moving U
  15017. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  15018. predict error 0
  15019. dir: dir isU
  15020. --- END Output Phase ---
  15021. -/--- Input Phase ---
  15022. =>WM: (14114: I2 ^dir U)
  15023. =>WM: (14113: I2 ^reward 1)
  15024. =>WM: (14112: I2 ^see 0)
  15025. =>WM: (14111: N1005 ^status complete)
  15026. <=WM: (14100: I2 ^dir U)
  15027. <=WM: (14099: I2 ^reward 1)
  15028. <=WM: (14098: I2 ^see 0)
  15029. =>WM: (14115: I2 ^level-1 R0-root)
  15030. <=WM: (14101: I2 ^level-1 R0-root)
  15031. --- END Input Phase ---
  15032. --- Proposal Phase ---
  15033. --- Inner Elaboration Phase, active level 1 (S1) ---
  15034. Firing elaborate*copy-see-to-output-link
  15035. -->
  15036. (I3 ^see 0 +)
  15037. Firing elaborate*reward*based*on*reward
  15038. -->
  15039. (R1009 ^value 1 +)
  15040. (R1 ^reward R1009 +)
  15041. Firing propose*predict-yes
  15042. -->
  15043. (O2011 ^name predict-yes +)
  15044. (S1 ^operator O2011 +)
  15045. Firing propose*predict-no
  15046. -->
  15047. (O2012 ^name predict-no +)
  15048. (S1 ^operator O2012 +)
  15049. Firing rl*prefer*rvt*predict-no*H0*2
  15050. -->
  15051. (S1 ^operator O2010 = 1.)
  15052. Firing rl*prefer*rvt*predict-yes*H0*1
  15053. -->
  15054. (S1 ^operator O2009 = 0.)
  15055. Firing prefer*rvt*predict-yes*H0
  15056. -->
  15057. Firing prefer*rvt*predict-no*H0
  15058. -->
  15059. Firing elaborate*copy-dir-to-output-link
  15060. -->
  15061. (I3 ^dir U +)
  15062. inner elaboration loop at bottom goal.
  15063. Retracting elaborate*copy-see-to-output-link
  15064. -->
  15065. (I3 ^see 0 +)
  15066. Retracting propose*predict-no
  15067. -->
  15068. (O2010 ^name predict-no +)
  15069. (S1 ^operator O2010 +)
  15070. Retracting propose*predict-yes
  15071. -->
  15072. (O2009 ^name predict-yes +)
  15073. (S1 ^operator O2009 +)
  15074. Retracting elaborate*reward*based*on*reward
  15075. -->
  15076. (R1008 ^value 1 +)
  15077. (R1 ^reward R1008 +)
  15078. Retracting elaborate*copy-dir-to-output-link
  15079. -->
  15080. (I3 ^dir U +)
  15081. Retracting rl*prefer*rvt*predict-no*H0*2
  15082. -->
  15083. (S1 ^operator O2010 = 1.)
  15084. Retracting rl*prefer*rvt*predict-yes*H0*1
  15085. -->
  15086. (S1 ^operator O2009 = 0.)
  15087. =>WM: (14121: S1 ^operator O2012 +)
  15088. =>WM: (14120: S1 ^operator O2011 +)
  15089. =>WM: (14119: O2012 ^name predict-no)
  15090. =>WM: (14118: O2011 ^name predict-yes)
  15091. =>WM: (14117: R1009 ^value 1)
  15092. =>WM: (14116: R1 ^reward R1009)
  15093. <=WM: (14107: S1 ^operator O2009 +)
  15094. <=WM: (14108: S1 ^operator O2010 +)
  15095. <=WM: (14109: S1 ^operator O2010)
  15096. <=WM: (14102: R1 ^reward R1008)
  15097. <=WM: (14105: O2010 ^name predict-no)
  15098. <=WM: (14104: O2009 ^name predict-yes)
  15099. <=WM: (14103: R1008 ^value 1)
  15100. --- Inner Elaboration Phase, active level 1 (S1) ---
  15101. Firing prefer*rvt*predict-yes*H0
  15102. -->
  15103. Firing rl*prefer*rvt*predict-yes*H0*1
  15104. -->
  15105. (S1 ^operator O2011 = 0.)
  15106. Firing prefer*rvt*predict-no*H0
  15107. -->
  15108. Firing rl*prefer*rvt*predict-no*H0*2
  15109. -->
  15110. (S1 ^operator O2012 = 1.)
  15111. inner elaboration loop at bottom goal.
  15112. Retracting rl*prefer*rvt*predict-no*H0*2
  15113. -->
  15114. (S1 ^operator O2010 = 1.)
  15115. Retracting rl*prefer*rvt*predict-yes*H0*1
  15116. -->
  15117. (S1 ^operator O2009 = 0.)
  15118. --- END Proposal Phase ---
  15119. --- Decision Phase ---
  15120. RL update rl*prefer*rvt*predict-no*H0*2 1 0 1 -> 1 0 1(R,m,v=1,1,0)
  15121. =>WM: (14122: S1 ^operator O2012)
  15122. 1006: O: O2012 (predict-no)
  15123. --- END Decision Phase ---
  15124. --- Application Phase ---
  15125. --- Firing Productions (PE) For State At Depth 1 ---
  15126. --- Inner Elaboration Phase, active level 1 (S1) ---
  15127. Firing apply*operator
  15128. -->
  15129. (I3 ^predict-no N1006 + :O )
  15130. Firing apply*operator*complete
  15131. -->
  15132. (I3 ^predict-no N1005 - :O )
  15133. inner elaboration loop at bottom goal.
  15134. --- Change Working Memory (PE) ---
  15135. =>WM: (14123: I3 ^predict-no N1006)
  15136. <=WM: (14111: N1005 ^status complete)
  15137. <=WM: (14110: I3 ^predict-no N1005)
  15138. --- Firing Productions (IE) For State At Depth 1 ---
  15139. --- Inner Elaboration Phase, active level 1 (S1) ---
  15140. Firing monitor*world
  15141. -->
  15142. I see 1 and I'm going to do: predict-no inner elaboration loop at bottom goal.
  15143. --- Change Working Memory (IE) ---
  15144. --- END Application Phase ---
  15145. --- Output Phase ---
  15146. ENV: Agent did: predict-no for direction U in state State-B
  15147. In State-B moving U
  15148. ENV: (next state, see, prediction correct?) = (State-B, 0, True)
  15149. predict error 0
  15150. dir: dir isL
  15151. --- END Output Phase ---
  15152. |\--- Input Phase ---
  15153. =>WM: (14127: I2 ^dir L)
  15154. =>WM: (14126: I2 ^reward 1)
  15155. =>WM: (14125: I2 ^see 0)
  15156. =>WM: (14124: N1006 ^status complete)
  15157. <=WM: (14114: I2 ^dir U)
  15158. <=WM: (14113: I2 ^reward 1)
  15159. <=WM: (14112: I2 ^see 0)
  15160. =>WM: (14128: I2 ^level-1 R0-root)
  15161. <=WM: (14115: I2 ^level-1 R0-root)
  15162. --- END Input Phase ---
  15163. --- Proposal Phase ---
  15164. --- Inner Elaboration Phase, active level 1 (S1) ---
  15165. Firing rl*prefer*rvt*predict-no*H0*4*H1*8
  15166. -->
  15167. (S1 ^operator O2012 = -0.1984300550322165)
  15168. Firing rl*prefer*rvt*predict-yes*H0*3*H1*9
  15169. -->
  15170. (S1 ^operator O2011 = 0.6091150129894595)
  15171. Firing prefer*rvt*predict-no*H0*4*H1
  15172. -->
  15173. Firing prefer*rvt*predict-yes*H0*3*H1
  15174. -->
  15175. Firing elaborate*copy-see-to-output-link
  15176. -->
  15177. (I3 ^see 0 +)
  15178. Firing elaborate*reward*based*on*reward
  15179. -->
  15180. (R1010 ^value 1 +)
  15181. (R1 ^reward R1010 +)
  15182. Firing propose*predict-yes
  15183. -->
  15184. (O2013 ^name predict-yes +)
  15185. (S1 ^operator O2013 +)
  15186. Firing propose*predict-no
  15187. -->
  15188. (O2014 ^name predict-no +)
  15189. (S1 ^operator O2014 +)
  15190. Firing rl*prefer*rvt*predict-no*H0*4
  15191. -->
  15192. (S1 ^operator O2012 = 0.3145079413521559)
  15193. Firing rl*prefer*rvt*predict-yes*H0*3
  15194. -->
  15195. (S1 ^operator O2011 = 0.3907782094907327)
  15196. Firing prefer*rvt*predict-yes*H0
  15197. -->
  15198. Firing prefer*rvt*predict-no*H0
  15199. -->
  15200. Firing elaborate*copy-dir-to-output-link
  15201. -->
  15202. (I3 ^dir L +)
  15203. inner elaboration loop at bottom goal.
  15204. Retracting elaborate*copy-see-to-output-link
  15205. -->
  15206. (I3 ^see 0 +)
  15207. Retracting propose*predict-no
  15208. -->
  15209. (O2012 ^name predict-no +)
  15210. (S1 ^operator O2012 +)
  15211. Retracting propose*predict-yes
  15212. -->
  15213. (O2011 ^name predict-yes +)
  15214. (S1 ^operator O2011 +)
  15215. Retracting elaborate*reward*based*on*reward
  15216. -->
  15217. (R1009 ^value 1 +)
  15218. (R1 ^reward R1009 +)
  15219. Retracting elaborate*copy-dir-to-output-link
  15220. -->
  15221. (I3 ^dir U +)
  15222. Retracting rl*prefer*rvt*predict-no*H0*2
  15223. -->
  15224. (S1 ^operator O2012 = 1.)
  15225. Retracting rl*prefer*rvt*predict-yes*H0*1
  15226. -->
  15227. (S1 ^operator O2011 = 0.)
  15228. =>WM: (14135: S1 ^operator O2014 +)
  15229. =>WM: (14134: S1 ^operator O2013 +)
  15230. =>WM: (14133: I3 ^dir L)
  15231. =>WM: (14132: O2014 ^name predict-no)
  15232. =>WM: (14131: O2013 ^name predict-yes)
  15233. =>WM: (14130: R1010 ^value 1)
  15234. =>WM: (14129: R1 ^reward R1010)
  15235. <=WM: (14120: S1 ^operator O2011 +)
  15236. <=WM: (14121: S1 ^operator O2012 +)
  15237. <=WM: (14122: S1 ^operator O2012)
  15238. <=WM: (14106: I3 ^dir U)
  15239. <=WM: (14116: R1 ^reward R1009)
  15240. <=WM: (14119: O2012 ^name predict-no)
  15241. <=WM: (14118: O2011 ^name predict-yes)
  15242. <=WM: (14117: R1009 ^value 1)
  15243. --- Inner Elaboration Phase, active level 1 (S1) ---
  15244. Firing prefer*rvt*predict-yes*H0
  15245. -->
  15246. Firing rl*prefer*rvt*predict-yes*H0*3*H1*9
  15247. -->
  15248. (S1 ^operator O2013 = 0.6091150129894595)
  15249. Firing rl*prefer*rvt*predict-yes*H0*3
  15250. -->
  15251. (S1 ^operator O2013 = 0.3907782094907327)
  15252. Firing prefer*rvt*predict-yes*H0*3*H1
  15253. -->
  15254. Firing prefer*rvt*predict-no*H0
  15255. -->
  15256. Firing rl*prefer*rvt*predict-no*H0*4*H1*8
  15257. -->
  15258. (S1 ^operator O2014 = -0.1984300550322165)
  15259. Firing rl*prefer*rvt*predict-no*H0*4
  15260. -->
  15261. (S1 ^operator O2014 = 0.3145079413521559)
  15262. Firing prefer*rvt*predict-no*H0*4*H1
  15263. -->
  15264. inner elaboration loop at bottom goal.
  15265. Retracting rl*prefer*rvt*predict-no*H0*4
  15266. -->
  15267. (S1 ^operator O2012 = 0.3145079413521559)
  15268. Retracting rl*prefer*rvt*predict-no*H0*4*H1*8
  15269. -->
  15270. (S1 ^operator O2012 = -0.1984300550322165)
  15271. Retracting rl*prefer*rvt*predict-yes*H0*3
  15272. -->
  15273. (S1 ^operator O2011 = 0.3907782094907327)
  15274. Retracting rl*prefer*rvt*predict-yes*H0*3*H1*9
  15275. -->
  15276. (S1 ^operator O2011 = 0.6091150129894595)
  15277. --- END Proposal Phase ---
  15278. --- Decision Phase ---
  15279. RL update rl*prefer*rvt*predict-no*H0*2 1 0 1 -> 1 0 1(R,m,v=1,1,0)
  15280. =>WM: (14136: S1 ^operator O2013)
  15281. 1007: O: O2013 (predict-yes)
  15282. --- END Decision Phase ---
  15283. --- Application Phase ---
  15284. --- Firing Productions (PE) For State At Depth 1 ---
  15285. --- Inner Elaboration Phase, active level 1 (S1) ---
  15286. Firing apply*operator
  15287. -->
  15288. (I3 ^predict-yes N1007 + :O )
  15289. Firing apply*operator*complete
  15290. -->
  15291. (I3 ^predict-no N1006 - :O )
  15292. inner elaboration loop at bottom goal.
  15293. --- Change Working Memory (PE) ---
  15294. =>WM: (14137: I3 ^predict-yes N1007)
  15295. <=WM: (14124: N1006 ^status complete)
  15296. <=WM: (14123: I3 ^predict-no N1006)
  15297. --- Firing Productions (IE) For State At Depth 1 ---
  15298. --- Inner Elaboration Phase, active level 1 (S1) ---
  15299. Firing monitor*world
  15300. -->
  15301. I see 1 and I'm going to do: predict-yes inner elaboration loop at bottom goal.
  15302. --- Change Working Memory (IE) ---
  15303. --- END Application Phase ---
  15304. --- Output Phase ---
  15305. ENV: Agent did: predict-yes for direction L in state State-B
  15306. In State-B moving L
  15307. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  15308. predict error 0
  15309. dir: dir isR
  15310. --- END Output Phase ---
  15311. -/|--- Input Phase ---
  15312. =>WM: (14141: I2 ^dir R)
  15313. =>WM: (14140: I2 ^reward 1)
  15314. =>WM: (14139: I2 ^see 1)
  15315. =>WM: (14138: N1007 ^status complete)
  15316. <=WM: (14127: I2 ^dir L)
  15317. <=WM: (14126: I2 ^reward 1)
  15318. <=WM: (14125: I2 ^see 0)
  15319. =>WM: (14142: I2 ^level-1 L1-root)
  15320. <=WM: (14128: I2 ^level-1 R0-root)
  15321. --- END Input Phase ---
  15322. --- Proposal Phase ---
  15323. --- Inner Elaboration Phase, active level 1 (S1) ---
  15324. Firing rl*prefer*rvt*predict-yes*H0*5*H1*18
  15325. -->
  15326. (S1 ^operator O2013 = 0.8784140715701729)
  15327. Firing prefer*rvt*predict-yes*H0*5*H1
  15328. -->
  15329. Firing elaborate*copy-see-to-output-link
  15330. -->
  15331. (I3 ^see 1 +)
  15332. Firing elaborate*reward*based*on*reward
  15333. -->
  15334. (R1011 ^value 1 +)
  15335. (R1 ^reward R1011 +)
  15336. Firing propose*predict-yes
  15337. -->
  15338. (O2015 ^name predict-yes +)
  15339. (S1 ^operator O2015 +)
  15340. Firing propose*predict-no
  15341. -->
  15342. (O2016 ^name predict-no +)
  15343. (S1 ^operator O2016 +)
  15344. Firing rl*prefer*rvt*predict-no*H0*6
  15345. -->
  15346. (S1 ^operator O2014 = 0.9999921813761182)
  15347. Firing rl*prefer*rvt*predict-yes*H0*5
  15348. -->
  15349. (S1 ^operator O2013 = 0.1215994207949702)
  15350. Firing prefer*rvt*predict-yes*H0
  15351. -->
  15352. Firing prefer*rvt*predict-no*H0
  15353. -->
  15354. Firing elaborate*copy-dir-to-output-link
  15355. -->
  15356. (I3 ^dir R +)
  15357. inner elaboration loop at bottom goal.
  15358. Retracting elaborate*copy-see-to-output-link
  15359. -->
  15360. (I3 ^see 0 +)
  15361. Retracting propose*predict-no
  15362. -->
  15363. (O2014 ^name predict-no +)
  15364. (S1 ^operator O2014 +)
  15365. Retracting propose*predict-yes
  15366. -->
  15367. (O2013 ^name predict-yes +)
  15368. (S1 ^operator O2013 +)
  15369. Retracting elaborate*reward*based*on*reward
  15370. -->
  15371. (R1010 ^value 1 +)
  15372. (R1 ^reward R1010 +)
  15373. Retracting elaborate*copy-dir-to-output-link
  15374. -->
  15375. (I3 ^dir L +)
  15376. Retracting rl*prefer*rvt*predict-no*H0*4
  15377. -->
  15378. (S1 ^operator O2014 = 0.3145079413521559)
  15379. Retracting rl*prefer*rvt*predict-no*H0*4*H1*8
  15380. -->
  15381. (S1 ^operator O2014 = -0.1984300550322165)
  15382. Retracting rl*prefer*rvt*predict-yes*H0*3
  15383. -->
  15384. (S1 ^operator O2013 = 0.3907782094907327)
  15385. Retracting rl*prefer*rvt*predict-yes*H0*3*H1*9
  15386. -->
  15387. (S1 ^operator O2013 = 0.6091150129894595)
  15388. =>WM: (14150: S1 ^operator O2016 +)
  15389. =>WM: (14149: S1 ^operator O2015 +)
  15390. =>WM: (14148: I3 ^dir R)
  15391. =>WM: (14147: O2016 ^name predict-no)
  15392. =>WM: (14146: O2015 ^name predict-yes)
  15393. =>WM: (14145: R1011 ^value 1)
  15394. =>WM: (14144: R1 ^reward R1011)
  15395. =>WM: (14143: I3 ^see 1)
  15396. <=WM: (14134: S1 ^operator O2013 +)
  15397. <=WM: (14136: S1 ^operator O2013)
  15398. <=WM: (14135: S1 ^operator O2014 +)
  15399. <=WM: (14133: I3 ^dir L)
  15400. <=WM: (14129: R1 ^reward R1010)
  15401. <=WM: (14048: I3 ^see 0)
  15402. <=WM: (14132: O2014 ^name predict-no)
  15403. <=WM: (14131: O2013 ^name predict-yes)
  15404. <=WM: (14130: R1010 ^value 1)
  15405. --- Inner Elaboration Phase, active level 1 (S1) ---
  15406. Firing prefer*rvt*predict-yes*H0
  15407. -->
  15408. Firing rl*prefer*rvt*predict-yes*H0*5
  15409. -->
  15410. (S1 ^operator O2015 = 0.1215994207949702)
  15411. Firing prefer*rvt*predict-yes*H0*5*H1
  15412. -->
  15413. Firing rl*prefer*rvt*predict-yes*H0*5*H1*18
  15414. -->
  15415. (S1 ^operator O2015 = 0.8784140715701729)
  15416. Firing prefer*rvt*predict-no*H0
  15417. -->
  15418. Firing rl*prefer*rvt*predict-no*H0*6
  15419. -->
  15420. (S1 ^operator O2016 = 0.9999921813761182)
  15421. inner elaboration loop at bottom goal.
  15422. Retracting rl*prefer*rvt*predict-no*H0*6
  15423. -->
  15424. (S1 ^operator O2014 = 0.9999921813761182)
  15425. Retracting rl*prefer*rvt*predict-yes*H0*5
  15426. -->
  15427. (S1 ^operator O2013 = 0.1215994207949702)
  15428. Retracting rl*prefer*rvt*predict-yes*H0*5*H1*18
  15429. -->
  15430. (S1 ^operator O2013 = 0.8784140715701729)
  15431. --- END Proposal Phase ---
  15432. --- Decision Phase ---
  15433. RL update rl*prefer*rvt*predict-yes*H0*3 0.472324 -0.0815458 0.390778 -> 0.472332 -0.0815445 0.390787(R,m,v=1,0.944099,0.0531056)
  15434. RL update rl*prefer*rvt*predict-yes*H0*3*H1*9 0.527585 0.0815301 0.609115 -> 0.527593 0.0815315 0.609125(R,m,v=1,1,0)
  15435. =>WM: (14151: S1 ^operator O2015)
  15436. 1008: O: O2015 (predict-yes)
  15437. --- END Decision Phase ---
  15438. --- Application Phase ---
  15439. --- Firing Productions (PE) For State At Depth 1 ---
  15440. --- Inner Elaboration Phase, active level 1 (S1) ---
  15441. Firing apply*operator
  15442. -->
  15443. (I3 ^predict-yes N1008 + :O )
  15444. Firing apply*operator*complete
  15445. -->
  15446. (I3 ^predict-yes N1007 - :O )
  15447. inner elaboration loop at bottom goal.
  15448. --- Change Working Memory (PE) ---
  15449. =>WM: (14152: I3 ^predict-yes N1008)
  15450. <=WM: (14138: N1007 ^status complete)
  15451. <=WM: (14137: I3 ^predict-yes N1007)
  15452. --- Firing Productions (IE) For State At Depth 1 ---
  15453. --- Inner Elaboration Phase, active level 1 (S1) ---
  15454. Firing monitor*world
  15455. -->
  15456. I see 1 and I'm going to do: predict-yes inner elaboration loop at bottom goal.
  15457. --- Change Working Memory (IE) ---
  15458. --- END Application Phase ---
  15459. --- Output Phase ---
  15460. ENV: Agent did: predict-yes for direction R in state State-A
  15461. In State-A moving R
  15462. ENV: (next state, see, prediction correct?) = (State-B, 1, True)
  15463. predict error 0
  15464. dir: dir isL
  15465. --- END Output Phase ---
  15466. \---- Input Phase ---
  15467. =>WM: (14156: I2 ^dir L)
  15468. =>WM: (14155: I2 ^reward 1)
  15469. =>WM: (14154: I2 ^see 1)
  15470. =>WM: (14153: N1008 ^status complete)
  15471. <=WM: (14141: I2 ^dir R)
  15472. <=WM: (14140: I2 ^reward 1)
  15473. <=WM: (14139: I2 ^see 1)
  15474. =>WM: (14157: I2 ^level-1 R1-root)
  15475. <=WM: (14142: I2 ^level-1 L1-root)
  15476. --- END Input Phase ---
  15477. --- Proposal Phase ---
  15478. --- Inner Elaboration Phase, active level 1 (S1) ---
  15479. Firing rl*prefer*rvt*predict-no*H0*4*H1*16
  15480. -->
  15481. (S1 ^operator O2016 = -0.168718511744511)
  15482. Firing rl*prefer*rvt*predict-yes*H0*3*H1*17
  15483. -->
  15484. (S1 ^operator O2015 = 0.6093091841289463)
  15485. Firing prefer*rvt*predict-no*H0*4*H1
  15486. -->
  15487. Firing prefer*rvt*predict-yes*H0*3*H1
  15488. -->
  15489. Firing elaborate*copy-see-to-output-link
  15490. -->
  15491. (I3 ^see 1 +)
  15492. Firing elaborate*reward*based*on*reward
  15493. -->
  15494. (R1012 ^value 1 +)
  15495. (R1 ^reward R1012 +)
  15496. Firing propose*predict-yes
  15497. -->
  15498. (O2017 ^name predict-yes +)
  15499. (S1 ^operator O2017 +)
  15500. Firing propose*predict-no
  15501. -->
  15502. (O2018 ^name predict-no +)
  15503. (S1 ^operator O2018 +)
  15504. Firing rl*prefer*rvt*predict-no*H0*4
  15505. -->
  15506. (S1 ^operator O2016 = 0.3145079413521559)
  15507. Firing rl*prefer*rvt*predict-yes*H0*3
  15508. -->
  15509. (S1 ^operator O2015 = 0.3907869885089824)
  15510. Firing prefer*rvt*predict-yes*H0
  15511. -->
  15512. Firing prefer*rvt*predict-no*H0
  15513. -->
  15514. Firing elaborate*copy-dir-to-output-link
  15515. -->
  15516. (I3 ^dir L +)
  15517. inner elaboration loop at bottom goal.
  15518. Retracting elaborate*copy-see-to-output-link
  15519. -->
  15520. (I3 ^see 1 +)
  15521. Retracting propose*predict-no
  15522. -->
  15523. (O2016 ^name predict-no +)
  15524. (S1 ^operator O2016 +)
  15525. Retracting propose*predict-yes
  15526. -->
  15527. (O2015 ^name predict-yes +)
  15528. (S1 ^operator O2015 +)
  15529. Retracting elaborate*reward*based*on*reward
  15530. -->
  15531. (R1011 ^value 1 +)
  15532. (R1 ^reward R1011 +)
  15533. Retracting elaborate*copy-dir-to-output-link
  15534. -->
  15535. (I3 ^dir R +)
  15536. Retracting rl*prefer*rvt*predict-no*H0*6
  15537. -->
  15538. (S1 ^operator O2016 = 0.9999921813761182)
  15539. Retracting rl*prefer*rvt*predict-yes*H0*5*H1*18
  15540. -->
  15541. (S1 ^operator O2015 = 0.8784140715701729)
  15542. Retracting rl*prefer*rvt*predict-yes*H0*5
  15543. -->
  15544. (S1 ^operator O2015 = 0.1215994207949702)
  15545. =>WM: (14164: S1 ^operator O2018 +)
  15546. =>WM: (14163: S1 ^operator O2017 +)
  15547. =>WM: (14162: I3 ^dir L)
  15548. =>WM: (14161: O2018 ^name predict-no)
  15549. =>WM: (14160: O2017 ^name predict-yes)
  15550. =>WM: (14159: R1012 ^value 1)
  15551. =>WM: (14158: R1 ^reward R1012)
  15552. <=WM: (14149: S1 ^operator O2015 +)
  15553. <=WM: (14151: S1 ^operator O2015)
  15554. <=WM: (14150: S1 ^operator O2016 +)
  15555. <=WM: (14148: I3 ^dir R)
  15556. <=WM: (14144: R1 ^reward R1011)
  15557. <=WM: (14147: O2016 ^name predict-no)
  15558. <=WM: (14146: O2015 ^name predict-yes)
  15559. <=WM: (14145: R1011 ^value 1)
  15560. --- Inner Elaboration Phase, active level 1 (S1) ---
  15561. Firing prefer*rvt*predict-yes*H0
  15562. -->
  15563. Firing rl*prefer*rvt*predict-yes*H0*3
  15564. -->
  15565. (S1 ^operator O2017 = 0.3907869885089824)
  15566. Firing prefer*rvt*predict-yes*H0*3*H1
  15567. -->
  15568. Firing rl*prefer*rvt*predict-yes*H0*3*H1*17
  15569. -->
  15570. (S1 ^operator O2017 = 0.6093091841289463)
  15571. Firing prefer*rvt*predict-no*H0
  15572. -->
  15573. Firing rl*prefer*rvt*predict-no*H0*4
  15574. -->
  15575. (S1 ^operator O2018 = 0.3145079413521559)
  15576. Firing prefer*rvt*predict-no*H0*4*H1
  15577. -->
  15578. Firing rl*prefer*rvt*predict-no*H0*4*H1*16
  15579. -->
  15580. (S1 ^operator O2018 = -0.168718511744511)
  15581. inner elaboration loop at bottom goal.
  15582. Retracting rl*prefer*rvt*predict-no*H0*4
  15583. -->
  15584. (S1 ^operator O2016 = 0.3145079413521559)
  15585. Retracting rl*prefer*rvt*predict-no*H0*4*H1*16
  15586. -->
  15587. (S1 ^operator O2016 = -0.168718511744511)
  15588. Retracting rl*prefer*rvt*predict-yes*H0*3
  15589. -->
  15590. (S1 ^operator O2015 = 0.3907869885089824)
  15591. Retracting rl*prefer*rvt*predict-yes*H0*3*H1*17
  15592. -->
  15593. (S1 ^operator O2015 = 0.6093091841289463)
  15594. --- END Proposal Phase ---
  15595. --- Decision Phase ---
  15596. RL update rl*prefer*rvt*predict-yes*H0*5 0.534525 -0.412926 0.121599 -> 0.534524 -0.412926 0.121598(R,m,v=1,0.865169,0.117311)
  15597. RL update rl*prefer*rvt*predict-yes*H0*5*H1*18 0.465486 0.412928 0.878414 -> 0.465485 0.412928 0.878413(R,m,v=1,1,0)
  15598. =>WM: (14165: S1 ^operator O2017)
  15599. 1009: O: O2017 (predict-yes)
  15600. --- END Decision Phase ---
  15601. --- Application Phase ---
  15602. --- Firing Productions (PE) For State At Depth 1 ---
  15603. --- Inner Elaboration Phase, active level 1 (S1) ---
  15604. Firing apply*operator
  15605. -->
  15606. (I3 ^predict-yes N1009 + :O )
  15607. Firing apply*operator*complete
  15608. -->
  15609. (I3 ^predict-yes N1008 - :O )
  15610. inner elaboration loop at bottom goal.
  15611. --- Change Working Memory (PE) ---
  15612. =>WM: (14166: I3 ^predict-yes N1009)
  15613. <=WM: (14153: N1008 ^status complete)
  15614. <=WM: (14152: I3 ^predict-yes N1008)
  15615. --- Firing Productions (IE) For State At Depth 1 ---
  15616. --- Inner Elaboration Phase, active level 1 (S1) ---
  15617. Firing monitor*world
  15618. -->
  15619. I see 1 and I'm going to do: predict-yes inner elaboration loop at bottom goal.
  15620. --- Change Working Memory (IE) ---
  15621. --- END Application Phase ---
  15622. --- Output Phase ---
  15623. ENV: Agent did: predict-yes for direction L in state State-B
  15624. In State-B moving L
  15625. ENV: (next state, see, prediction correct?) = (State-A, 1, True)
  15626. predict error 0
  15627. dir: dir isL
  15628. --- END Output Phase ---
  15629. /|--- Input Phase ---
  15630. =>WM: (14170: I2 ^dir L)
  15631. =>WM: (14169: I2 ^reward 1)
  15632. =>WM: (14168: I2 ^see 1)
  15633. =>WM: (14167: N1009 ^status complete)
  15634. <=WM: (14156: I2 ^dir L)
  15635. <=WM: (14155: I2 ^reward 1)
  15636. <=WM: (14154: I2 ^see 1)
  15637. =>WM: (14171: I2 ^level-1 L1-root)
  15638. <=WM: (14157: I2 ^level-1 R1-root)
  15639. --- END Input Phase ---
  15640. --- Proposal Phase ---
  15641. --- Inner Elaboration Phase, active level 1 (S1) ---
  15642. Firing rl*prefer*rvt*predict-yes*H0*3*H1*11
  15643. -->
  15644. (S1 ^operator O2017 = -0.2062723012911647)
  15645. Firing rl*prefer*rvt*predict-no*H0*4*H1*10
  15646. -->
  15647. (S1 ^operator O2018 = 0.685530273786795)
  15648. Firing prefer*rvt*predict-no*H0*4*H1
  15649. -->
  15650. Firing prefer*rvt*predict-yes*H0*3*H1
  15651. -->
  15652. Firing elaborate*copy-see-to-output-link
  15653. -->
  15654. (I3 ^see 1 +)
  15655. Firing elaborate*reward*based*on*reward
  15656. -->
  15657. (R1013 ^value 1 +)
  15658. (R1 ^reward R1013 +)
  15659. Firing propose*predict-yes
  15660. -->
  15661. (O2019 ^name predict-yes +)
  15662. (S1 ^operator O2019 +)
  15663. Firing propose*predict-no
  15664. -->
  15665. (O2020 ^name predict-no +)
  15666. (S1 ^operator O2020 +)
  15667. Firing rl*prefer*rvt*predict-no*H0*4
  15668. -->
  15669. (S1 ^operator O2018 = 0.3145079413521559)
  15670. Firing rl*prefer*rvt*predict-yes*H0*3
  15671. -->
  15672. (S1 ^operator O2017 = 0.3907869885089824)
  15673. Firing prefer*rvt*predict-yes*H0
  15674. -->
  15675. Firing prefer*rvt*predict-no*H0
  15676. -->
  15677. Firing elaborate*copy-dir-to-output-link
  15678. -->
  15679. (I3 ^dir L +)
  15680. inner elaboration loop at bottom goal.
  15681. Retracting elaborate*copy-see-to-output-link
  15682. -->
  15683. (I3 ^see 1 +)
  15684. Retracting propose*predict-no
  15685. -->
  15686. (O2018 ^name predict-no +)
  15687. (S1 ^operator O2018 +)
  15688. Retracting propose*predict-yes
  15689. -->
  15690. (O2017 ^name predict-yes +)
  15691. (S1 ^operator O2017 +)
  15692. Retracting elaborate*reward*based*on*reward
  15693. -->
  15694. (R1012 ^value 1 +)
  15695. (R1 ^reward R1012 +)
  15696. Retracting elaborate*copy-dir-to-output-link
  15697. -->
  15698. (I3 ^dir L +)
  15699. Retracting rl*prefer*rvt*predict-no*H0*4*H1*16
  15700. -->
  15701. (S1 ^operator O2018 = -0.168718511744511)
  15702. Retracting rl*prefer*rvt*predict-no*H0*4
  15703. -->
  15704. (S1 ^operator O2018 = 0.3145079413521559)
  15705. Retracting rl*prefer*rvt*predict-yes*H0*3*H1*17
  15706. -->
  15707. (S1 ^operator O2017 = 0.6093091841289463)
  15708. Retracting rl*prefer*rvt*predict-yes*H0*3
  15709. -->
  15710. (S1 ^operator O2017 = 0.3907869885089824)
  15711. =>WM: (14177: S1 ^operator O2020 +)
  15712. =>WM: (14176: S1 ^operator O2019 +)
  15713. =>WM: (14175: O2020 ^name predict-no)
  15714. =>WM: (14174: O2019 ^name predict-yes)
  15715. =>WM: (14173: R1013 ^value 1)
  15716. =>WM: (14172: R1 ^reward R1013)
  15717. <=WM: (14163: S1 ^operator O2017 +)
  15718. <=WM: (14165: S1 ^operator O2017)
  15719. <=WM: (14164: S1 ^operator O2018 +)
  15720. <=WM: (14158: R1 ^reward R1012)
  15721. <=WM: (14161: O2018 ^name predict-no)
  15722. <=WM: (14160: O2017 ^name predict-yes)
  15723. <=WM: (14159: R1012 ^value 1)
  15724. --- Inner Elaboration Phase, active level 1 (S1) ---
  15725. Firi